linux/fs/read_write.c

1738 lines
41 KiB
C
Raw Normal View History

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>
2017-11-01 14:07:57 +00:00
// 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 = filemap_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)
vfs: do (nearly) lockless generic_file_llseek The i_mutex lock use of generic _file_llseek hurts. Independent processes accessing the same file synchronize over a single lock, even though they have no need for synchronization at all. Under high utilization this can cause llseek to scale very poorly on larger systems. This patch does some rethinking of the llseek locking model: First the 64bit f_pos is not necessarily atomic without locks on 32bit systems. This can already cause races with read() today. This was discussed on linux-kernel in the past and deemed acceptable. The patch does not change that. Let's look at the different seek variants: SEEK_SET: Doesn't really need any locking. If there's a race one writer wins, the other loses. For 32bit the non atomic update races against read() stay the same. Without a lock they can also happen against write() now. The read() race was deemed acceptable in past discussions, and I think if it's ok for read it's ok for write too. => Don't need a lock. SEEK_END: This behaves like SEEK_SET plus it reads the maximum size too. Reading the maximum size would have the 32bit atomic problem. But luckily we already have a way to read the maximum size without locking (i_size_read), so we can just use that instead. Without i_mutex there is no synchronization with write() anymore, however since the write() update is atomic on 64bit it just behaves like another racy SEEK_SET. On non atomic 32bit it's the same as SEEK_SET. => Don't need a lock, but need to use i_size_read() SEEK_CUR: This has a read-modify-write race window on the same file. One could argue that any application doing unsynchronized seeks on the same file is already broken. But for the sake of not adding a regression here I'm using the file->f_lock to synchronize this. Using this lock is much better than the inode mutex because it doesn't synchronize between processes. => So still need a lock, but can use a f_lock. This patch implements this new scheme in generic_file_llseek. I dropped generic_file_llseek_unlocked and changed all callers. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
2011-09-15 23:06:48 +00:00
{
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);
vfs: do (nearly) lockless generic_file_llseek The i_mutex lock use of generic _file_llseek hurts. Independent processes accessing the same file synchronize over a single lock, even though they have no need for synchronization at all. Under high utilization this can cause llseek to scale very poorly on larger systems. This patch does some rethinking of the llseek locking model: First the 64bit f_pos is not necessarily atomic without locks on 32bit systems. This can already cause races with read() today. This was discussed on linux-kernel in the past and deemed acceptable. The patch does not change that. Let's look at the different seek variants: SEEK_SET: Doesn't really need any locking. If there's a race one writer wins, the other loses. For 32bit the non atomic update races against read() stay the same. Without a lock they can also happen against write() now. The read() race was deemed acceptable in past discussions, and I think if it's ok for read it's ok for write too. => Don't need a lock. SEEK_END: This behaves like SEEK_SET plus it reads the maximum size too. Reading the maximum size would have the 32bit atomic problem. But luckily we already have a way to read the maximum size without locking (i_size_read), so we can just use that instead. Without i_mutex there is no synchronization with write() anymore, however since the write() update is atomic on 64bit it just behaves like another racy SEEK_SET. On non atomic 32bit it's the same as SEEK_SET. => Don't need a lock, but need to use i_size_read() SEEK_CUR: This has a read-modify-write race window on the same file. One could argue that any application doing unsynchronized seeks on the same file is already broken. But for the sake of not adding a regression here I'm using the file->f_lock to synchronize this. Using this lock is much better than the inode mutex because it doesn't synchronize between processes. => So still need a lock, but can use a f_lock. This patch implements this new scheme in generic_file_llseek. I dropped generic_file_llseek_unlocked and changed all callers. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
2011-09-15 23:06:48 +00:00
/**
* 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
* @maxsize: 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
vfs: do (nearly) lockless generic_file_llseek The i_mutex lock use of generic _file_llseek hurts. Independent processes accessing the same file synchronize over a single lock, even though they have no need for synchronization at all. Under high utilization this can cause llseek to scale very poorly on larger systems. This patch does some rethinking of the llseek locking model: First the 64bit f_pos is not necessarily atomic without locks on 32bit systems. This can already cause races with read() today. This was discussed on linux-kernel in the past and deemed acceptable. The patch does not change that. Let's look at the different seek variants: SEEK_SET: Doesn't really need any locking. If there's a race one writer wins, the other loses. For 32bit the non atomic update races against read() stay the same. Without a lock they can also happen against write() now. The read() race was deemed acceptable in past discussions, and I think if it's ok for read it's ok for write too. => Don't need a lock. SEEK_END: This behaves like SEEK_SET plus it reads the maximum size too. Reading the maximum size would have the 32bit atomic problem. But luckily we already have a way to read the maximum size without locking (i_size_read), so we can just use that instead. Without i_mutex there is no synchronization with write() anymore, however since the write() update is atomic on 64bit it just behaves like another racy SEEK_SET. On non atomic 32bit it's the same as SEEK_SET. => Don't need a lock, but need to use i_size_read() SEEK_CUR: This has a read-modify-write race window on the same file. One could argue that any application doing unsynchronized seeks on the same file is already broken. But for the sake of not adding a regression here I'm using the file->f_lock to synchronize this. Using this lock is much better than the inode mutex because it doesn't synchronize between processes. => So still need a lock, but can use a f_lock. This patch implements this new scheme in generic_file_llseek. I dropped generic_file_llseek_unlocked and changed all callers. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
2011-09-15 23:06:48 +00:00
*
* Synchronization:
* SEEK_SET and SEEK_END are unsynchronized (but atomic on 64bit platforms)
vfs: do (nearly) lockless generic_file_llseek The i_mutex lock use of generic _file_llseek hurts. Independent processes accessing the same file synchronize over a single lock, even though they have no need for synchronization at all. Under high utilization this can cause llseek to scale very poorly on larger systems. This patch does some rethinking of the llseek locking model: First the 64bit f_pos is not necessarily atomic without locks on 32bit systems. This can already cause races with read() today. This was discussed on linux-kernel in the past and deemed acceptable. The patch does not change that. Let's look at the different seek variants: SEEK_SET: Doesn't really need any locking. If there's a race one writer wins, the other loses. For 32bit the non atomic update races against read() stay the same. Without a lock they can also happen against write() now. The read() race was deemed acceptable in past discussions, and I think if it's ok for read it's ok for write too. => Don't need a lock. SEEK_END: This behaves like SEEK_SET plus it reads the maximum size too. Reading the maximum size would have the 32bit atomic problem. But luckily we already have a way to read the maximum size without locking (i_size_read), so we can just use that instead. Without i_mutex there is no synchronization with write() anymore, however since the write() update is atomic on 64bit it just behaves like another racy SEEK_SET. On non atomic 32bit it's the same as SEEK_SET. => Don't need a lock, but need to use i_size_read() SEEK_CUR: This has a read-modify-write race window on the same file. One could argue that any application doing unsynchronized seeks on the same file is already broken. But for the sake of not adding a regression here I'm using the file->f_lock to synchronize this. Using this lock is much better than the inode mutex because it doesn't synchronize between processes. => So still need a lock, but can use a f_lock. This patch implements this new scheme in generic_file_llseek. I dropped generic_file_llseek_unlocked and changed all callers. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
2011-09-15 23:06:48 +00:00
* 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;
vfs: do (nearly) lockless generic_file_llseek The i_mutex lock use of generic _file_llseek hurts. Independent processes accessing the same file synchronize over a single lock, even though they have no need for synchronization at all. Under high utilization this can cause llseek to scale very poorly on larger systems. This patch does some rethinking of the llseek locking model: First the 64bit f_pos is not necessarily atomic without locks on 32bit systems. This can already cause races with read() today. This was discussed on linux-kernel in the past and deemed acceptable. The patch does not change that. Let's look at the different seek variants: SEEK_SET: Doesn't really need any locking. If there's a race one writer wins, the other loses. For 32bit the non atomic update races against read() stay the same. Without a lock they can also happen against write() now. The read() race was deemed acceptable in past discussions, and I think if it's ok for read it's ok for write too. => Don't need a lock. SEEK_END: This behaves like SEEK_SET plus it reads the maximum size too. Reading the maximum size would have the 32bit atomic problem. But luckily we already have a way to read the maximum size without locking (i_size_read), so we can just use that instead. Without i_mutex there is no synchronization with write() anymore, however since the write() update is atomic on 64bit it just behaves like another racy SEEK_SET. On non atomic 32bit it's the same as SEEK_SET. => Don't need a lock, but need to use i_size_read() SEEK_CUR: This has a read-modify-write race window on the same file. One could argue that any application doing unsynchronized seeks on the same file is already broken. But for the sake of not adding a regression here I'm using the file->f_lock to synchronize this. Using this lock is much better than the inode mutex because it doesn't synchronize between processes. => So still need a lock, but can use a f_lock. This patch implements this new scheme in generic_file_llseek. I dropped generic_file_llseek_unlocked and changed all callers. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
2011-09-15 23:06:48 +00:00
/*
* 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);
vfs: do (nearly) lockless generic_file_llseek The i_mutex lock use of generic _file_llseek hurts. Independent processes accessing the same file synchronize over a single lock, even though they have no need for synchronization at all. Under high utilization this can cause llseek to scale very poorly on larger systems. This patch does some rethinking of the llseek locking model: First the 64bit f_pos is not necessarily atomic without locks on 32bit systems. This can already cause races with read() today. This was discussed on linux-kernel in the past and deemed acceptable. The patch does not change that. Let's look at the different seek variants: SEEK_SET: Doesn't really need any locking. If there's a race one writer wins, the other loses. For 32bit the non atomic update races against read() stay the same. Without a lock they can also happen against write() now. The read() race was deemed acceptable in past discussions, and I think if it's ok for read it's ok for write too. => Don't need a lock. SEEK_END: This behaves like SEEK_SET plus it reads the maximum size too. Reading the maximum size would have the 32bit atomic problem. But luckily we already have a way to read the maximum size without locking (i_size_read), so we can just use that instead. Without i_mutex there is no synchronization with write() anymore, however since the write() update is atomic on 64bit it just behaves like another racy SEEK_SET. On non atomic 32bit it's the same as SEEK_SET. => Don't need a lock, but need to use i_size_read() SEEK_CUR: This has a read-modify-write race window on the same file. One could argue that any application doing unsynchronized seeks on the same file is already broken. But for the sake of not adding a regression here I'm using the file->f_lock to synchronize this. Using this lock is much better than the inode mutex because it doesn't synchronize between processes. => So still need a lock, but can use a f_lock. This patch implements this new scheme in generic_file_llseek. I dropped generic_file_llseek_unlocked and changed all callers. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
2011-09-15 23:06:48 +00:00
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 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)
{
if (!(file->f_mode & FMODE_LSEEK))
return -ESPIPE;
return file->f_op->llseek(file, offset, whence);
}
EXPORT_SYMBOL(vfs_llseek);
static off_t ksys_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;
}
SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence)
{
return ksys_lseek(fd, offset, whence);
}
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE3(lseek, unsigned int, fd, compat_off_t, offset, unsigned int, whence)
{
return ksys_lseek(fd, offset, whence);
}
#endif
#if !defined(CONFIG_64BIT) || defined(CONFIG_COMPAT) || \
defined(__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)
{
int mask = read_write == READ ? MAY_READ : MAY_WRITE;
int ret;
if (unlikely((ssize_t) count < 0))
return -EINVAL;
vfs: pass ppos=NULL to .read()/.write() of FMODE_STREAM files This amends commit 10dce8af3422 ("fs: stream_open - opener for stream-like files so that read and write can run simultaneously without deadlock") in how position is passed into .read()/.write() handler for stream-like files: Rasmus noticed that we currently pass 0 as position and ignore any position change if that is done by a file implementation. This papers over bugs if ppos is used in files that declare themselves as being stream-like as such bugs will go unnoticed. Even if a file implementation is correctly converted into using stream_open, its read/write later could be changed to use ppos and even though that won't be working correctly, that bug might go unnoticed without someone doing wrong behaviour analysis. It is thus better to pass ppos=NULL into read/write for stream-like files as that don't give any chance for ppos usage bugs because it will oops if ppos is ever used inside .read() or .write(). Note 1: rw_verify_area, new_sync_{read,write} needs to be updated because they are called by vfs_read/vfs_write & friends before file_operations .read/.write . Note 2: if file backend uses new-style .read_iter/.write_iter, position is still passed into there as non-pointer kiocb.ki_pos . Currently stream_open.cocci (semantic patch added by 10dce8af3422) ignores files whose file_operations has *_iter methods. Suggested-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by: Kirill Smelkov <kirr@nexedi.com>
2019-04-12 09:31:57 +00:00
if (ppos) {
loff_t pos = *ppos;
if (unlikely(pos < 0)) {
if (!unsigned_offsets(file))
return -EINVAL;
vfs: pass ppos=NULL to .read()/.write() of FMODE_STREAM files This amends commit 10dce8af3422 ("fs: stream_open - opener for stream-like files so that read and write can run simultaneously without deadlock") in how position is passed into .read()/.write() handler for stream-like files: Rasmus noticed that we currently pass 0 as position and ignore any position change if that is done by a file implementation. This papers over bugs if ppos is used in files that declare themselves as being stream-like as such bugs will go unnoticed. Even if a file implementation is correctly converted into using stream_open, its read/write later could be changed to use ppos and even though that won't be working correctly, that bug might go unnoticed without someone doing wrong behaviour analysis. It is thus better to pass ppos=NULL into read/write for stream-like files as that don't give any chance for ppos usage bugs because it will oops if ppos is ever used inside .read() or .write(). Note 1: rw_verify_area, new_sync_{read,write} needs to be updated because they are called by vfs_read/vfs_write & friends before file_operations .read/.write . Note 2: if file backend uses new-style .read_iter/.write_iter, position is still passed into there as non-pointer kiocb.ki_pos . Currently stream_open.cocci (semantic patch added by 10dce8af3422) ignores files whose file_operations has *_iter methods. Suggested-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by: Kirill Smelkov <kirr@nexedi.com>
2019-04-12 09:31:57 +00:00
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 -EINVAL;
vfs: pass ppos=NULL to .read()/.write() of FMODE_STREAM files This amends commit 10dce8af3422 ("fs: stream_open - opener for stream-like files so that read and write can run simultaneously without deadlock") in how position is passed into .read()/.write() handler for stream-like files: Rasmus noticed that we currently pass 0 as position and ignore any position change if that is done by a file implementation. This papers over bugs if ppos is used in files that declare themselves as being stream-like as such bugs will go unnoticed. Even if a file implementation is correctly converted into using stream_open, its read/write later could be changed to use ppos and even though that won't be working correctly, that bug might go unnoticed without someone doing wrong behaviour analysis. It is thus better to pass ppos=NULL into read/write for stream-like files as that don't give any chance for ppos usage bugs because it will oops if ppos is ever used inside .read() or .write(). Note 1: rw_verify_area, new_sync_{read,write} needs to be updated because they are called by vfs_read/vfs_write & friends before file_operations .read/.write . Note 2: if file backend uses new-style .read_iter/.write_iter, position is still passed into there as non-pointer kiocb.ki_pos . Currently stream_open.cocci (semantic patch added by 10dce8af3422) ignores files whose file_operations has *_iter methods. Suggested-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by: Kirill Smelkov <kirr@nexedi.com>
2019-04-12 09:31:57 +00:00
}
}
vfs: pass ppos=NULL to .read()/.write() of FMODE_STREAM files This amends commit 10dce8af3422 ("fs: stream_open - opener for stream-like files so that read and write can run simultaneously without deadlock") in how position is passed into .read()/.write() handler for stream-like files: Rasmus noticed that we currently pass 0 as position and ignore any position change if that is done by a file implementation. This papers over bugs if ppos is used in files that declare themselves as being stream-like as such bugs will go unnoticed. Even if a file implementation is correctly converted into using stream_open, its read/write later could be changed to use ppos and even though that won't be working correctly, that bug might go unnoticed without someone doing wrong behaviour analysis. It is thus better to pass ppos=NULL into read/write for stream-like files as that don't give any chance for ppos usage bugs because it will oops if ppos is ever used inside .read() or .write(). Note 1: rw_verify_area, new_sync_{read,write} needs to be updated because they are called by vfs_read/vfs_write & friends before file_operations .read/.write . Note 2: if file backend uses new-style .read_iter/.write_iter, position is still passed into there as non-pointer kiocb.ki_pos . Currently stream_open.cocci (semantic patch added by 10dce8af3422) ignores files whose file_operations has *_iter methods. Suggested-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by: Kirill Smelkov <kirr@nexedi.com>
2019-04-12 09:31:57 +00:00
ret = security_file_permission(file, mask);
if (ret)
return ret;
return fsnotify_file_area_perm(file, mask, ppos, count);
}
EXPORT_SYMBOL(rw_verify_area);
static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos)
{
struct kiocb kiocb;
struct iov_iter iter;
ssize_t ret;
init_sync_kiocb(&kiocb, filp);
vfs: pass ppos=NULL to .read()/.write() of FMODE_STREAM files This amends commit 10dce8af3422 ("fs: stream_open - opener for stream-like files so that read and write can run simultaneously without deadlock") in how position is passed into .read()/.write() handler for stream-like files: Rasmus noticed that we currently pass 0 as position and ignore any position change if that is done by a file implementation. This papers over bugs if ppos is used in files that declare themselves as being stream-like as such bugs will go unnoticed. Even if a file implementation is correctly converted into using stream_open, its read/write later could be changed to use ppos and even though that won't be working correctly, that bug might go unnoticed without someone doing wrong behaviour analysis. It is thus better to pass ppos=NULL into read/write for stream-like files as that don't give any chance for ppos usage bugs because it will oops if ppos is ever used inside .read() or .write(). Note 1: rw_verify_area, new_sync_{read,write} needs to be updated because they are called by vfs_read/vfs_write & friends before file_operations .read/.write . Note 2: if file backend uses new-style .read_iter/.write_iter, position is still passed into there as non-pointer kiocb.ki_pos . Currently stream_open.cocci (semantic patch added by 10dce8af3422) ignores files whose file_operations has *_iter methods. Suggested-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by: Kirill Smelkov <kirr@nexedi.com>
2019-04-12 09:31:57 +00:00
kiocb.ki_pos = (ppos ? *ppos : 0);
iov_iter_ubuf(&iter, ITER_DEST, buf, len);
ret = call_read_iter(filp, &kiocb, &iter);
BUG_ON(ret == -EIOCBQUEUED);
vfs: pass ppos=NULL to .read()/.write() of FMODE_STREAM files This amends commit 10dce8af3422 ("fs: stream_open - opener for stream-like files so that read and write can run simultaneously without deadlock") in how position is passed into .read()/.write() handler for stream-like files: Rasmus noticed that we currently pass 0 as position and ignore any position change if that is done by a file implementation. This papers over bugs if ppos is used in files that declare themselves as being stream-like as such bugs will go unnoticed. Even if a file implementation is correctly converted into using stream_open, its read/write later could be changed to use ppos and even though that won't be working correctly, that bug might go unnoticed without someone doing wrong behaviour analysis. It is thus better to pass ppos=NULL into read/write for stream-like files as that don't give any chance for ppos usage bugs because it will oops if ppos is ever used inside .read() or .write(). Note 1: rw_verify_area, new_sync_{read,write} needs to be updated because they are called by vfs_read/vfs_write & friends before file_operations .read/.write . Note 2: if file backend uses new-style .read_iter/.write_iter, position is still passed into there as non-pointer kiocb.ki_pos . Currently stream_open.cocci (semantic patch added by 10dce8af3422) ignores files whose file_operations has *_iter methods. Suggested-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by: Kirill Smelkov <kirr@nexedi.com>
2019-04-12 09:31:57 +00:00
if (ppos)
*ppos = kiocb.ki_pos;
return ret;
}
static int warn_unsupported(struct file *file, const char *op)
{
pr_warn_ratelimited(
"kernel %s not supported for file %pD4 (pid: %d comm: %.20s)\n",
op, file, current->pid, current->comm);
return -EINVAL;
}
ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos)
{
struct kvec iov = {
.iov_base = buf,
.iov_len = min_t(size_t, count, MAX_RW_COUNT),
};
struct kiocb kiocb;
struct iov_iter iter;
ssize_t ret;
if (WARN_ON_ONCE(!(file->f_mode & FMODE_READ)))
return -EINVAL;
if (!(file->f_mode & FMODE_CAN_READ))
return -EINVAL;
/*
* Also fail if ->read_iter and ->read are both wired up as that
* implies very convoluted semantics.
*/
if (unlikely(!file->f_op->read_iter || file->f_op->read))
return warn_unsupported(file, "read");
init_sync_kiocb(&kiocb, file);
kiocb.ki_pos = pos ? *pos : 0;
iov_iter_kvec(&iter, ITER_DEST, &iov, 1, iov.iov_len);
ret = file->f_op->read_iter(&kiocb, &iter);
if (ret > 0) {
if (pos)
*pos = kiocb.ki_pos;
fsnotify_access(file);
add_rchar(current, ret);
}
inc_syscr(current);
return ret;
}
ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos)
{
ssize_t ret;
ret = rw_verify_area(READ, file, pos, count);
if (ret)
return ret;
return __kernel_read(file, buf, count, pos);
}
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;
Remove 'type' argument from access_ok() function Nobody has actually used the type (VERIFY_READ vs VERIFY_WRITE) argument of the user address range verification function since we got rid of the old racy i386-only code to walk page tables by hand. It existed because the original 80386 would not honor the write protect bit when in kernel mode, so you had to do COW by hand before doing any user access. But we haven't supported that in a long time, and these days the 'type' argument is a purely historical artifact. A discussion about extending 'user_access_begin()' to do the range checking resulted this patch, because there is no way we're going to move the old VERIFY_xyz interface to that model. And it's best done at the end of the merge window when I've done most of my merges, so let's just get this done once and for all. This patch was mostly done with a sed-script, with manual fix-ups for the cases that weren't of the trivial 'access_ok(VERIFY_xyz' form. There were a couple of notable cases: - csky still had the old "verify_area()" name as an alias. - the iter_iov code had magical hardcoded knowledge of the actual values of VERIFY_{READ,WRITE} (not that they mattered, since nothing really used it) - microblaze used the type argument for a debug printout but other than those oddities this should be a total no-op patch. I tried to fix up all architectures, did fairly extensive grepping for access_ok() uses, and the changes are trivial, but I may have missed something. Any missed conversion should be trivially fixable, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 02:57:57 +00:00
if (unlikely(!access_ok(buf, count)))
return -EFAULT;
ret = rw_verify_area(READ, file, pos, count);
if (ret)
return ret;
if (count > MAX_RW_COUNT)
count = MAX_RW_COUNT;
if (file->f_op->read)
ret = file->f_op->read(file, buf, count, pos);
else if (file->f_op->read_iter)
ret = new_sync_read(file, buf, count, pos);
else
ret = -EINVAL;
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 kiocb kiocb;
struct iov_iter iter;
ssize_t ret;
init_sync_kiocb(&kiocb, filp);
vfs: pass ppos=NULL to .read()/.write() of FMODE_STREAM files This amends commit 10dce8af3422 ("fs: stream_open - opener for stream-like files so that read and write can run simultaneously without deadlock") in how position is passed into .read()/.write() handler for stream-like files: Rasmus noticed that we currently pass 0 as position and ignore any position change if that is done by a file implementation. This papers over bugs if ppos is used in files that declare themselves as being stream-like as such bugs will go unnoticed. Even if a file implementation is correctly converted into using stream_open, its read/write later could be changed to use ppos and even though that won't be working correctly, that bug might go unnoticed without someone doing wrong behaviour analysis. It is thus better to pass ppos=NULL into read/write for stream-like files as that don't give any chance for ppos usage bugs because it will oops if ppos is ever used inside .read() or .write(). Note 1: rw_verify_area, new_sync_{read,write} needs to be updated because they are called by vfs_read/vfs_write & friends before file_operations .read/.write . Note 2: if file backend uses new-style .read_iter/.write_iter, position is still passed into there as non-pointer kiocb.ki_pos . Currently stream_open.cocci (semantic patch added by 10dce8af3422) ignores files whose file_operations has *_iter methods. Suggested-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by: Kirill Smelkov <kirr@nexedi.com>
2019-04-12 09:31:57 +00:00
kiocb.ki_pos = (ppos ? *ppos : 0);
iov_iter_ubuf(&iter, ITER_SOURCE, (void __user *)buf, len);
ret = call_write_iter(filp, &kiocb, &iter);
BUG_ON(ret == -EIOCBQUEUED);
vfs: pass ppos=NULL to .read()/.write() of FMODE_STREAM files This amends commit 10dce8af3422 ("fs: stream_open - opener for stream-like files so that read and write can run simultaneously without deadlock") in how position is passed into .read()/.write() handler for stream-like files: Rasmus noticed that we currently pass 0 as position and ignore any position change if that is done by a file implementation. This papers over bugs if ppos is used in files that declare themselves as being stream-like as such bugs will go unnoticed. Even if a file implementation is correctly converted into using stream_open, its read/write later could be changed to use ppos and even though that won't be working correctly, that bug might go unnoticed without someone doing wrong behaviour analysis. It is thus better to pass ppos=NULL into read/write for stream-like files as that don't give any chance for ppos usage bugs because it will oops if ppos is ever used inside .read() or .write(). Note 1: rw_verify_area, new_sync_{read,write} needs to be updated because they are called by vfs_read/vfs_write & friends before file_operations .read/.write . Note 2: if file backend uses new-style .read_iter/.write_iter, position is still passed into there as non-pointer kiocb.ki_pos . Currently stream_open.cocci (semantic patch added by 10dce8af3422) ignores files whose file_operations has *_iter methods. Suggested-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by: Kirill Smelkov <kirr@nexedi.com>
2019-04-12 09:31:57 +00:00
if (ret > 0 && ppos)
*ppos = kiocb.ki_pos;
return ret;
}
/* caller is responsible for file_start_write/file_end_write */
ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *pos)
{
struct kiocb kiocb;
ssize_t ret;
if (WARN_ON_ONCE(!(file->f_mode & FMODE_WRITE)))
return -EBADF;
if (!(file->f_mode & FMODE_CAN_WRITE))
return -EINVAL;
/*
* Also fail if ->write_iter and ->write are both wired up as that
* implies very convoluted semantics.
*/
if (unlikely(!file->f_op->write_iter || file->f_op->write))
return warn_unsupported(file, "write");
init_sync_kiocb(&kiocb, file);
kiocb.ki_pos = pos ? *pos : 0;
ret = file->f_op->write_iter(&kiocb, from);
if (ret > 0) {
if (pos)
*pos = kiocb.ki_pos;
fsnotify_modify(file);
add_wchar(current, ret);
}
inc_syscw(current);
return ret;
}
/* caller is responsible for file_start_write/file_end_write */
ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos)
{
struct kvec iov = {
.iov_base = (void *)buf,
.iov_len = min_t(size_t, count, MAX_RW_COUNT),
};
struct iov_iter iter;
iov_iter_kvec(&iter, ITER_SOURCE, &iov, 1, iov.iov_len);
return __kernel_write_iter(file, &iter, pos);
}
autofs: use __kernel_write() for the autofs pipe writing autofs got broken in some configurations by commit 13c164b1a186 ("autofs: switch to kernel_write") because there is now an extra LSM permission check done by security_file_permission() in rw_verify_area(). autofs is one if the few places that really does want the much more limited __kernel_write(), because the write is an internal kernel one that shouldn't do any user permission checks (it also doesn't need the file_start_write/file_end_write logic, since it's just a pipe). There are a couple of other cases like that - accounting, core dumping, and splice - but autofs stands out because it can be built as a module. As a result, we need to export this internal __kernel_write() function again. We really don't want any other module to use this, but we don't have a "EXPORT_SYMBOL_FOR_AUTOFS_ONLY()". But we can mark it GPL-only to at least approximate that "internal use only" for licensing. While in this area, make autofs pass in NULL for the file position pointer, since it's always a pipe, and we now use a NULL file pointer for streaming file descriptors (see file_ppos() and commit 438ab720c675: "vfs: pass ppos=NULL to .read()/.write() of FMODE_STREAM files") This effectively reverts commits 9db977522449 ("fs: unexport __kernel_write") and 13c164b1a186 ("autofs: switch to kernel_write"). Fixes: 13c164b1a186 ("autofs: switch to kernel_write") Reported-by: Ondrej Mosnacek <omosnace@redhat.com> Acked-by: Christoph Hellwig <hch@lst.de> Acked-by: Acked-by: Ian Kent <raven@themaw.net> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-30 00:18:34 +00:00
/*
* This "EXPORT_SYMBOL_GPL()" is more of a "EXPORT_SYMBOL_DONTUSE()",
* but autofs is one of the few internal kernel users that actually
* wants this _and_ can be built as a module. So we need to export
* this symbol for autofs, even though it really isn't appropriate
* for any other kernel modules.
*/
EXPORT_SYMBOL_GPL(__kernel_write);
ssize_t kernel_write(struct file *file, const void *buf, size_t count,
loff_t *pos)
{
ssize_t ret;
ret = rw_verify_area(WRITE, file, pos, count);
if (ret)
return ret;
file_start_write(file);
ret = __kernel_write(file, buf, count, pos);
file_end_write(file);
return ret;
}
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;
Remove 'type' argument from access_ok() function Nobody has actually used the type (VERIFY_READ vs VERIFY_WRITE) argument of the user address range verification function since we got rid of the old racy i386-only code to walk page tables by hand. It existed because the original 80386 would not honor the write protect bit when in kernel mode, so you had to do COW by hand before doing any user access. But we haven't supported that in a long time, and these days the 'type' argument is a purely historical artifact. A discussion about extending 'user_access_begin()' to do the range checking resulted this patch, because there is no way we're going to move the old VERIFY_xyz interface to that model. And it's best done at the end of the merge window when I've done most of my merges, so let's just get this done once and for all. This patch was mostly done with a sed-script, with manual fix-ups for the cases that weren't of the trivial 'access_ok(VERIFY_xyz' form. There were a couple of notable cases: - csky still had the old "verify_area()" name as an alias. - the iter_iov code had magical hardcoded knowledge of the actual values of VERIFY_{READ,WRITE} (not that they mattered, since nothing really used it) - microblaze used the type argument for a debug printout but other than those oddities this should be a total no-op patch. I tried to fix up all architectures, did fairly extensive grepping for access_ok() uses, and the changes are trivial, but I may have missed something. Any missed conversion should be trivially fixable, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 02:57:57 +00:00
if (unlikely(!access_ok(buf, count)))
return -EFAULT;
ret = rw_verify_area(WRITE, file, pos, count);
if (ret)
return ret;
if (count > MAX_RW_COUNT)
count = MAX_RW_COUNT;
file_start_write(file);
if (file->f_op->write)
ret = file->f_op->write(file, buf, count, pos);
else if (file->f_op->write_iter)
ret = new_sync_write(file, buf, count, pos);
else
ret = -EINVAL;
if (ret > 0) {
fsnotify_modify(file);
add_wchar(current, ret);
}
inc_syscw(current);
file_end_write(file);
return ret;
}
vfs: pass ppos=NULL to .read()/.write() of FMODE_STREAM files This amends commit 10dce8af3422 ("fs: stream_open - opener for stream-like files so that read and write can run simultaneously without deadlock") in how position is passed into .read()/.write() handler for stream-like files: Rasmus noticed that we currently pass 0 as position and ignore any position change if that is done by a file implementation. This papers over bugs if ppos is used in files that declare themselves as being stream-like as such bugs will go unnoticed. Even if a file implementation is correctly converted into using stream_open, its read/write later could be changed to use ppos and even though that won't be working correctly, that bug might go unnoticed without someone doing wrong behaviour analysis. It is thus better to pass ppos=NULL into read/write for stream-like files as that don't give any chance for ppos usage bugs because it will oops if ppos is ever used inside .read() or .write(). Note 1: rw_verify_area, new_sync_{read,write} needs to be updated because they are called by vfs_read/vfs_write & friends before file_operations .read/.write . Note 2: if file backend uses new-style .read_iter/.write_iter, position is still passed into there as non-pointer kiocb.ki_pos . Currently stream_open.cocci (semantic patch added by 10dce8af3422) ignores files whose file_operations has *_iter methods. Suggested-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by: Kirill Smelkov <kirr@nexedi.com>
2019-04-12 09:31:57 +00:00
/* file_ppos returns &file->f_pos or NULL if file is stream */
static inline loff_t *file_ppos(struct file *file)
{
vfs: pass ppos=NULL to .read()/.write() of FMODE_STREAM files This amends commit 10dce8af3422 ("fs: stream_open - opener for stream-like files so that read and write can run simultaneously without deadlock") in how position is passed into .read()/.write() handler for stream-like files: Rasmus noticed that we currently pass 0 as position and ignore any position change if that is done by a file implementation. This papers over bugs if ppos is used in files that declare themselves as being stream-like as such bugs will go unnoticed. Even if a file implementation is correctly converted into using stream_open, its read/write later could be changed to use ppos and even though that won't be working correctly, that bug might go unnoticed without someone doing wrong behaviour analysis. It is thus better to pass ppos=NULL into read/write for stream-like files as that don't give any chance for ppos usage bugs because it will oops if ppos is ever used inside .read() or .write(). Note 1: rw_verify_area, new_sync_{read,write} needs to be updated because they are called by vfs_read/vfs_write & friends before file_operations .read/.write . Note 2: if file backend uses new-style .read_iter/.write_iter, position is still passed into there as non-pointer kiocb.ki_pos . Currently stream_open.cocci (semantic patch added by 10dce8af3422) ignores files whose file_operations has *_iter methods. Suggested-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by: Kirill Smelkov <kirr@nexedi.com>
2019-04-12 09:31:57 +00:00
return file->f_mode & FMODE_STREAM ? NULL : &file->f_pos;
}
ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count)
{
struct fd f = fdget_pos(fd);
ssize_t ret = -EBADF;
if (f.file) {
vfs: pass ppos=NULL to .read()/.write() of FMODE_STREAM files This amends commit 10dce8af3422 ("fs: stream_open - opener for stream-like files so that read and write can run simultaneously without deadlock") in how position is passed into .read()/.write() handler for stream-like files: Rasmus noticed that we currently pass 0 as position and ignore any position change if that is done by a file implementation. This papers over bugs if ppos is used in files that declare themselves as being stream-like as such bugs will go unnoticed. Even if a file implementation is correctly converted into using stream_open, its read/write later could be changed to use ppos and even though that won't be working correctly, that bug might go unnoticed without someone doing wrong behaviour analysis. It is thus better to pass ppos=NULL into read/write for stream-like files as that don't give any chance for ppos usage bugs because it will oops if ppos is ever used inside .read() or .write(). Note 1: rw_verify_area, new_sync_{read,write} needs to be updated because they are called by vfs_read/vfs_write & friends before file_operations .read/.write . Note 2: if file backend uses new-style .read_iter/.write_iter, position is still passed into there as non-pointer kiocb.ki_pos . Currently stream_open.cocci (semantic patch added by 10dce8af3422) ignores files whose file_operations has *_iter methods. Suggested-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by: Kirill Smelkov <kirr@nexedi.com>
2019-04-12 09:31:57 +00:00
loff_t pos, *ppos = file_ppos(f.file);
if (ppos) {
pos = *ppos;
ppos = &pos;
}
ret = vfs_read(f.file, buf, count, ppos);
if (ret >= 0 && ppos)
f.file->f_pos = pos;
fdput_pos(f);
}
return ret;
}
SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count)
{
return ksys_read(fd, buf, count);
}
ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count)
{
struct fd f = fdget_pos(fd);
ssize_t ret = -EBADF;
if (f.file) {
vfs: pass ppos=NULL to .read()/.write() of FMODE_STREAM files This amends commit 10dce8af3422 ("fs: stream_open - opener for stream-like files so that read and write can run simultaneously without deadlock") in how position is passed into .read()/.write() handler for stream-like files: Rasmus noticed that we currently pass 0 as position and ignore any position change if that is done by a file implementation. This papers over bugs if ppos is used in files that declare themselves as being stream-like as such bugs will go unnoticed. Even if a file implementation is correctly converted into using stream_open, its read/write later could be changed to use ppos and even though that won't be working correctly, that bug might go unnoticed without someone doing wrong behaviour analysis. It is thus better to pass ppos=NULL into read/write for stream-like files as that don't give any chance for ppos usage bugs because it will oops if ppos is ever used inside .read() or .write(). Note 1: rw_verify_area, new_sync_{read,write} needs to be updated because they are called by vfs_read/vfs_write & friends before file_operations .read/.write . Note 2: if file backend uses new-style .read_iter/.write_iter, position is still passed into there as non-pointer kiocb.ki_pos . Currently stream_open.cocci (semantic patch added by 10dce8af3422) ignores files whose file_operations has *_iter methods. Suggested-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by: Kirill Smelkov <kirr@nexedi.com>
2019-04-12 09:31:57 +00:00
loff_t pos, *ppos = file_ppos(f.file);
if (ppos) {
pos = *ppos;
ppos = &pos;
}
ret = vfs_write(f.file, buf, count, ppos);
if (ret >= 0 && ppos)
f.file->f_pos = pos;
fdput_pos(f);
}
return ret;
}
SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf,
size_t, count)
{
return ksys_write(fd, buf, count);
}
ssize_t ksys_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(pread64, unsigned int, fd, char __user *, buf,
size_t, count, loff_t, pos)
{
return ksys_pread64(fd, buf, count, pos);
}
#if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_PREAD64)
COMPAT_SYSCALL_DEFINE5(pread64, unsigned int, fd, char __user *, buf,
size_t, count, compat_arg_u64_dual(pos))
{
return ksys_pread64(fd, buf, count, compat_arg_u64_glue(pos));
}
#endif
ssize_t ksys_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;
}
SYSCALL_DEFINE4(pwrite64, unsigned int, fd, const char __user *, buf,
size_t, count, loff_t, pos)
{
return ksys_pwrite64(fd, buf, count, pos);
}
#if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_PWRITE64)
COMPAT_SYSCALL_DEFINE5(pwrite64, unsigned int, fd, const char __user *, buf,
size_t, count, compat_arg_u64_dual(pos))
{
return ksys_pwrite64(fd, buf, count, compat_arg_u64_glue(pos));
}
#endif
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;
vfs: pass ppos=NULL to .read()/.write() of FMODE_STREAM files This amends commit 10dce8af3422 ("fs: stream_open - opener for stream-like files so that read and write can run simultaneously without deadlock") in how position is passed into .read()/.write() handler for stream-like files: Rasmus noticed that we currently pass 0 as position and ignore any position change if that is done by a file implementation. This papers over bugs if ppos is used in files that declare themselves as being stream-like as such bugs will go unnoticed. Even if a file implementation is correctly converted into using stream_open, its read/write later could be changed to use ppos and even though that won't be working correctly, that bug might go unnoticed without someone doing wrong behaviour analysis. It is thus better to pass ppos=NULL into read/write for stream-like files as that don't give any chance for ppos usage bugs because it will oops if ppos is ever used inside .read() or .write(). Note 1: rw_verify_area, new_sync_{read,write} needs to be updated because they are called by vfs_read/vfs_write & friends before file_operations .read/.write . Note 2: if file backend uses new-style .read_iter/.write_iter, position is still passed into there as non-pointer kiocb.ki_pos . Currently stream_open.cocci (semantic patch added by 10dce8af3422) ignores files whose file_operations has *_iter methods. Suggested-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by: Kirill Smelkov <kirr@nexedi.com>
2019-04-12 09:31:57 +00:00
kiocb.ki_pos = (ppos ? *ppos : 0);
if (type == READ)
ret = call_read_iter(filp, &kiocb, iter);
else
ret = call_write_iter(filp, &kiocb, iter);
BUG_ON(ret == -EIOCBQUEUED);
vfs: pass ppos=NULL to .read()/.write() of FMODE_STREAM files This amends commit 10dce8af3422 ("fs: stream_open - opener for stream-like files so that read and write can run simultaneously without deadlock") in how position is passed into .read()/.write() handler for stream-like files: Rasmus noticed that we currently pass 0 as position and ignore any position change if that is done by a file implementation. This papers over bugs if ppos is used in files that declare themselves as being stream-like as such bugs will go unnoticed. Even if a file implementation is correctly converted into using stream_open, its read/write later could be changed to use ppos and even though that won't be working correctly, that bug might go unnoticed without someone doing wrong behaviour analysis. It is thus better to pass ppos=NULL into read/write for stream-like files as that don't give any chance for ppos usage bugs because it will oops if ppos is ever used inside .read() or .write(). Note 1: rw_verify_area, new_sync_{read,write} needs to be updated because they are called by vfs_read/vfs_write & friends before file_operations .read/.write . Note 2: if file backend uses new-style .read_iter/.write_iter, position is still passed into there as non-pointer kiocb.ki_pos . Currently stream_open.cocci (semantic patch added by 10dce8af3422) ignores files whose file_operations has *_iter methods. Suggested-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by: Kirill Smelkov <kirr@nexedi.com>
2019-04-12 09:31:57 +00:00
if (ppos)
*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)) {
ssize_t nr;
if (type == READ) {
nr = filp->f_op->read(filp, iter_iov_addr(iter),
iter_iov_len(iter), ppos);
} else {
nr = filp->f_op->write(filp, iter_iov_addr(iter),
iter_iov_len(iter), ppos);
}
if (nr < 0) {
if (!ret)
ret = nr;
break;
}
ret += nr;
if (nr != iter_iov_len(iter))
break;
iov_iter_advance(iter, nr);
}
return ret;
}
ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb,
struct iov_iter *iter)
{
size_t tot_len;
ssize_t ret = 0;
if (!file->f_op->read_iter)
return -EINVAL;
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, &iocb->ki_pos, tot_len);
if (ret < 0)
return ret;
ret = call_read_iter(file, iocb, iter);
out:
if (ret >= 0)
fsnotify_access(file);
return ret;
}
EXPORT_SYMBOL(vfs_iocb_iter_read);
ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos,
rwf_t flags)
{
size_t tot_len;
ssize_t ret = 0;
if (!file->f_op->read_iter)
return -EINVAL;
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, ppos, tot_len);
if (ret < 0)
return ret;
ret = do_iter_readv_writev(file, iter, ppos, READ, flags);
out:
if (ret >= 0)
fsnotify_access(file);
return ret;
}
EXPORT_SYMBOL(vfs_iter_read);
/*
* Caller is responsible for calling kiocb_end_write() on completion
* if async iocb was queued.
*/
ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb,
struct iov_iter *iter)
{
size_t tot_len;
ssize_t ret = 0;
if (!file->f_op->write_iter)
return -EINVAL;
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, &iocb->ki_pos, tot_len);
if (ret < 0)
return ret;
kiocb_start_write(iocb);
ret = call_write_iter(file, iocb, iter);
if (ret != -EIOCBQUEUED)
kiocb_end_write(iocb);
if (ret > 0)
fsnotify_modify(file);
return ret;
}
EXPORT_SYMBOL(vfs_iocb_iter_write);
ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos,
rwf_t flags)
{
size_t tot_len;
ssize_t ret;
if (!(file->f_mode & FMODE_WRITE))
return -EBADF;
if (!(file->f_mode & FMODE_CAN_WRITE))
return -EINVAL;
if (!file->f_op->write_iter)
return -EINVAL;
tot_len = iov_iter_count(iter);
if (!tot_len)
return 0;
ret = rw_verify_area(WRITE, file, ppos, tot_len);
if (ret < 0)
return ret;
file_start_write(file);
ret = do_iter_readv_writev(file, iter, ppos, WRITE, flags);
if (ret > 0)
fsnotify_modify(file);
file_end_write(file);
return ret;
}
EXPORT_SYMBOL(vfs_iter_write);
static 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;
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;
ret = import_iovec(ITER_DEST, vec, vlen, ARRAY_SIZE(iovstack), &iov,
&iter);
if (ret < 0)
return ret;
tot_len = iov_iter_count(&iter);
if (!tot_len)
goto out;
ret = rw_verify_area(READ, file, pos, tot_len);
if (ret < 0)
goto out;
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);
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;
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;
ret = import_iovec(ITER_SOURCE, vec, vlen, ARRAY_SIZE(iovstack), &iov,
&iter);
if (ret < 0)
return ret;
tot_len = iov_iter_count(&iter);
if (!tot_len)
goto out;
ret = rw_verify_area(WRITE, file, pos, tot_len);
if (ret < 0)
goto out;
file_start_write(file);
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);
file_end_write(file);
out:
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) {
vfs: pass ppos=NULL to .read()/.write() of FMODE_STREAM files This amends commit 10dce8af3422 ("fs: stream_open - opener for stream-like files so that read and write can run simultaneously without deadlock") in how position is passed into .read()/.write() handler for stream-like files: Rasmus noticed that we currently pass 0 as position and ignore any position change if that is done by a file implementation. This papers over bugs if ppos is used in files that declare themselves as being stream-like as such bugs will go unnoticed. Even if a file implementation is correctly converted into using stream_open, its read/write later could be changed to use ppos and even though that won't be working correctly, that bug might go unnoticed without someone doing wrong behaviour analysis. It is thus better to pass ppos=NULL into read/write for stream-like files as that don't give any chance for ppos usage bugs because it will oops if ppos is ever used inside .read() or .write(). Note 1: rw_verify_area, new_sync_{read,write} needs to be updated because they are called by vfs_read/vfs_write & friends before file_operations .read/.write . Note 2: if file backend uses new-style .read_iter/.write_iter, position is still passed into there as non-pointer kiocb.ki_pos . Currently stream_open.cocci (semantic patch added by 10dce8af3422) ignores files whose file_operations has *_iter methods. Suggested-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by: Kirill Smelkov <kirr@nexedi.com>
2019-04-12 09:31:57 +00:00
loff_t pos, *ppos = file_ppos(f.file);
if (ppos) {
pos = *ppos;
ppos = &pos;
}
ret = vfs_readv(f.file, vec, vlen, ppos, flags);
if (ret >= 0 && ppos)
f.file->f_pos = 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) {
vfs: pass ppos=NULL to .read()/.write() of FMODE_STREAM files This amends commit 10dce8af3422 ("fs: stream_open - opener for stream-like files so that read and write can run simultaneously without deadlock") in how position is passed into .read()/.write() handler for stream-like files: Rasmus noticed that we currently pass 0 as position and ignore any position change if that is done by a file implementation. This papers over bugs if ppos is used in files that declare themselves as being stream-like as such bugs will go unnoticed. Even if a file implementation is correctly converted into using stream_open, its read/write later could be changed to use ppos and even though that won't be working correctly, that bug might go unnoticed without someone doing wrong behaviour analysis. It is thus better to pass ppos=NULL into read/write for stream-like files as that don't give any chance for ppos usage bugs because it will oops if ppos is ever used inside .read() or .write(). Note 1: rw_verify_area, new_sync_{read,write} needs to be updated because they are called by vfs_read/vfs_write & friends before file_operations .read/.write . Note 2: if file backend uses new-style .read_iter/.write_iter, position is still passed into there as non-pointer kiocb.ki_pos . Currently stream_open.cocci (semantic patch added by 10dce8af3422) ignores files whose file_operations has *_iter methods. Suggested-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by: Kirill Smelkov <kirr@nexedi.com>
2019-04-12 09:31:57 +00:00
loff_t pos, *ppos = file_ppos(f.file);
if (ppos) {
pos = *ppos;
ppos = &pos;
}
ret = vfs_writev(f.file, vec, vlen, ppos, flags);
if (ret >= 0 && ppos)
f.file->f_pos = pos;
fdput_pos(f);
}
if (ret > 0)
add_wchar(current, ret);
inc_syscw(current);
return ret;
}
Make non-compat preadv/pwritev use native register size Instead of always splitting the file offset into 32-bit 'high' and 'low' parts, just split them into the largest natural word-size - which in C terms is 'unsigned long'. This allows 64-bit architectures to avoid the unnecessary 32-bit shifting and masking for native format (while the compat interfaces will obviously always have to do it). This also changes the order of 'high' and 'low' to be "low first". Why? Because when we have it like this, the 64-bit system calls now don't use the "pos_high" argument at all, and it makes more sense for the native system call to simply match the user-mode prototype. This results in a much more natural calling convention, and allows the compiler to generate much more straightforward code. On x86-64, we now generate testq %rcx, %rcx # pos_l js .L122 #, movq %rcx, -48(%rbp) # pos_l, pos from the C source loff_t pos = pos_from_hilo(pos_h, pos_l); ... if (pos < 0) return -EINVAL; and the 'pos_h' register isn't even touched. It used to generate code like mov %r8d, %r8d # pos_low, pos_low salq $32, %rcx #, tmp71 movq %r8, %rax # pos_low, pos.386 orq %rcx, %rax # tmp71, pos.386 js .L122 #, movq %rax, -48(%rbp) # pos.386, pos which isn't _that_ horrible, but it does show how the natural word size is just a more sensible interface (same arguments will hold in the user level glibc wrapper function, of course, so the kernel side is just half of the equation!) Note: in all cases the user code wrapper can again be the same. You can just do #define HALF_BITS (sizeof(unsigned long)*4) __syscall(PWRITEV, fd, iov, count, offset, (offset >> HALF_BITS) >> HALF_BITS); or something like that. That way the user mode wrapper will also be nicely passing in a zero (it won't actually have to do the shifts, the compiler will understand what is going on) for the last argument. And that is a good idea, even if nobody will necessarily ever care: if we ever do move to a 128-bit lloff_t, this particular system call might be left alone. Of course, that will be the least of our worries if we really ever need to care, so this may not be worth really caring about. [ Fixed for lost 'loff_t' cast noticed by Andrew Morton ] Acked-by: Gerd Hoffmann <kraxel@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: linux-api@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: Ingo Molnar <mingo@elte.hu> Cc: Ralf Baechle <ralf@linux-mips.org>> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-03 15:03:22 +00:00
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)
preadv/pwritev: Add preadv and pwritev system calls. This patch adds preadv and pwritev system calls. These syscalls are a pretty straightforward combination of pread and readv (same for write). They are quite useful for doing vectored I/O in threaded applications. Using lseek+readv instead opens race windows you'll have to plug with locking. Other systems have such system calls too, for example NetBSD, check here: http://www.daemon-systems.org/man/preadv.2.html The application-visible interface provided by glibc should look like this to be compatible to the existing implementations in the *BSD family: ssize_t preadv(int d, const struct iovec *iov, int iovcnt, off_t offset); ssize_t pwritev(int d, const struct iovec *iov, int iovcnt, off_t offset); This prototype has one problem though: On 32bit archs is the (64bit) offset argument unaligned, which the syscall ABI of several archs doesn't allow to do. At least s390 needs a wrapper in glibc to handle this. As we'll need a wrappers in glibc anyway I've decided to push problem to glibc entriely and use a syscall prototype which works without arch-specific wrappers inside the kernel: The offset argument is explicitly splitted into two 32bit values. The patch sports the actual system call implementation and the windup in the x86 system call tables. Other archs follow as separate patches. Signed-off-by: Gerd Hoffmann <kraxel@redhat.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: <linux-api@vger.kernel.org> Cc: <linux-arch@vger.kernel.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-02 23:59:23 +00:00
{
struct fd f;
preadv/pwritev: Add preadv and pwritev system calls. This patch adds preadv and pwritev system calls. These syscalls are a pretty straightforward combination of pread and readv (same for write). They are quite useful for doing vectored I/O in threaded applications. Using lseek+readv instead opens race windows you'll have to plug with locking. Other systems have such system calls too, for example NetBSD, check here: http://www.daemon-systems.org/man/preadv.2.html The application-visible interface provided by glibc should look like this to be compatible to the existing implementations in the *BSD family: ssize_t preadv(int d, const struct iovec *iov, int iovcnt, off_t offset); ssize_t pwritev(int d, const struct iovec *iov, int iovcnt, off_t offset); This prototype has one problem though: On 32bit archs is the (64bit) offset argument unaligned, which the syscall ABI of several archs doesn't allow to do. At least s390 needs a wrapper in glibc to handle this. As we'll need a wrappers in glibc anyway I've decided to push problem to glibc entriely and use a syscall prototype which works without arch-specific wrappers inside the kernel: The offset argument is explicitly splitted into two 32bit values. The patch sports the actual system call implementation and the windup in the x86 system call tables. Other archs follow as separate patches. Signed-off-by: Gerd Hoffmann <kraxel@redhat.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: <linux-api@vger.kernel.org> Cc: <linux-arch@vger.kernel.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-02 23:59:23 +00:00
ssize_t ret = -EBADF;
if (pos < 0)
return -EINVAL;
f = fdget(fd);
if (f.file) {
preadv/pwritev: Add preadv and pwritev system calls. This patch adds preadv and pwritev system calls. These syscalls are a pretty straightforward combination of pread and readv (same for write). They are quite useful for doing vectored I/O in threaded applications. Using lseek+readv instead opens race windows you'll have to plug with locking. Other systems have such system calls too, for example NetBSD, check here: http://www.daemon-systems.org/man/preadv.2.html The application-visible interface provided by glibc should look like this to be compatible to the existing implementations in the *BSD family: ssize_t preadv(int d, const struct iovec *iov, int iovcnt, off_t offset); ssize_t pwritev(int d, const struct iovec *iov, int iovcnt, off_t offset); This prototype has one problem though: On 32bit archs is the (64bit) offset argument unaligned, which the syscall ABI of several archs doesn't allow to do. At least s390 needs a wrapper in glibc to handle this. As we'll need a wrappers in glibc anyway I've decided to push problem to glibc entriely and use a syscall prototype which works without arch-specific wrappers inside the kernel: The offset argument is explicitly splitted into two 32bit values. The patch sports the actual system call implementation and the windup in the x86 system call tables. Other archs follow as separate patches. Signed-off-by: Gerd Hoffmann <kraxel@redhat.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: <linux-api@vger.kernel.org> Cc: <linux-arch@vger.kernel.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-02 23:59:23 +00:00
ret = -ESPIPE;
if (f.file->f_mode & FMODE_PREAD)
ret = vfs_readv(f.file, vec, vlen, &pos, flags);
fdput(f);
preadv/pwritev: Add preadv and pwritev system calls. This patch adds preadv and pwritev system calls. These syscalls are a pretty straightforward combination of pread and readv (same for write). They are quite useful for doing vectored I/O in threaded applications. Using lseek+readv instead opens race windows you'll have to plug with locking. Other systems have such system calls too, for example NetBSD, check here: http://www.daemon-systems.org/man/preadv.2.html The application-visible interface provided by glibc should look like this to be compatible to the existing implementations in the *BSD family: ssize_t preadv(int d, const struct iovec *iov, int iovcnt, off_t offset); ssize_t pwritev(int d, const struct iovec *iov, int iovcnt, off_t offset); This prototype has one problem though: On 32bit archs is the (64bit) offset argument unaligned, which the syscall ABI of several archs doesn't allow to do. At least s390 needs a wrapper in glibc to handle this. As we'll need a wrappers in glibc anyway I've decided to push problem to glibc entriely and use a syscall prototype which works without arch-specific wrappers inside the kernel: The offset argument is explicitly splitted into two 32bit values. The patch sports the actual system call implementation and the windup in the x86 system call tables. Other archs follow as separate patches. Signed-off-by: Gerd Hoffmann <kraxel@redhat.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: <linux-api@vger.kernel.org> Cc: <linux-arch@vger.kernel.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-02 23:59:23 +00:00
}
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)
preadv/pwritev: Add preadv and pwritev system calls. This patch adds preadv and pwritev system calls. These syscalls are a pretty straightforward combination of pread and readv (same for write). They are quite useful for doing vectored I/O in threaded applications. Using lseek+readv instead opens race windows you'll have to plug with locking. Other systems have such system calls too, for example NetBSD, check here: http://www.daemon-systems.org/man/preadv.2.html The application-visible interface provided by glibc should look like this to be compatible to the existing implementations in the *BSD family: ssize_t preadv(int d, const struct iovec *iov, int iovcnt, off_t offset); ssize_t pwritev(int d, const struct iovec *iov, int iovcnt, off_t offset); This prototype has one problem though: On 32bit archs is the (64bit) offset argument unaligned, which the syscall ABI of several archs doesn't allow to do. At least s390 needs a wrapper in glibc to handle this. As we'll need a wrappers in glibc anyway I've decided to push problem to glibc entriely and use a syscall prototype which works without arch-specific wrappers inside the kernel: The offset argument is explicitly splitted into two 32bit values. The patch sports the actual system call implementation and the windup in the x86 system call tables. Other archs follow as separate patches. Signed-off-by: Gerd Hoffmann <kraxel@redhat.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: <linux-api@vger.kernel.org> Cc: <linux-arch@vger.kernel.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-02 23:59:23 +00:00
{
struct fd f;
preadv/pwritev: Add preadv and pwritev system calls. This patch adds preadv and pwritev system calls. These syscalls are a pretty straightforward combination of pread and readv (same for write). They are quite useful for doing vectored I/O in threaded applications. Using lseek+readv instead opens race windows you'll have to plug with locking. Other systems have such system calls too, for example NetBSD, check here: http://www.daemon-systems.org/man/preadv.2.html The application-visible interface provided by glibc should look like this to be compatible to the existing implementations in the *BSD family: ssize_t preadv(int d, const struct iovec *iov, int iovcnt, off_t offset); ssize_t pwritev(int d, const struct iovec *iov, int iovcnt, off_t offset); This prototype has one problem though: On 32bit archs is the (64bit) offset argument unaligned, which the syscall ABI of several archs doesn't allow to do. At least s390 needs a wrapper in glibc to handle this. As we'll need a wrappers in glibc anyway I've decided to push problem to glibc entriely and use a syscall prototype which works without arch-specific wrappers inside the kernel: The offset argument is explicitly splitted into two 32bit values. The patch sports the actual system call implementation and the windup in the x86 system call tables. Other archs follow as separate patches. Signed-off-by: Gerd Hoffmann <kraxel@redhat.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: <linux-api@vger.kernel.org> Cc: <linux-arch@vger.kernel.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-02 23:59:23 +00:00
ssize_t ret = -EBADF;
if (pos < 0)
return -EINVAL;
f = fdget(fd);
if (f.file) {
preadv/pwritev: Add preadv and pwritev system calls. This patch adds preadv and pwritev system calls. These syscalls are a pretty straightforward combination of pread and readv (same for write). They are quite useful for doing vectored I/O in threaded applications. Using lseek+readv instead opens race windows you'll have to plug with locking. Other systems have such system calls too, for example NetBSD, check here: http://www.daemon-systems.org/man/preadv.2.html The application-visible interface provided by glibc should look like this to be compatible to the existing implementations in the *BSD family: ssize_t preadv(int d, const struct iovec *iov, int iovcnt, off_t offset); ssize_t pwritev(int d, const struct iovec *iov, int iovcnt, off_t offset); This prototype has one problem though: On 32bit archs is the (64bit) offset argument unaligned, which the syscall ABI of several archs doesn't allow to do. At least s390 needs a wrapper in glibc to handle this. As we'll need a wrappers in glibc anyway I've decided to push problem to glibc entriely and use a syscall prototype which works without arch-specific wrappers inside the kernel: The offset argument is explicitly splitted into two 32bit values. The patch sports the actual system call implementation and the windup in the x86 system call tables. Other archs follow as separate patches. Signed-off-by: Gerd Hoffmann <kraxel@redhat.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: <linux-api@vger.kernel.org> Cc: <linux-arch@vger.kernel.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-02 23:59:23 +00:00
ret = -ESPIPE;
if (f.file->f_mode & FMODE_PWRITE)
ret = vfs_writev(f.file, vec, vlen, &pos, flags);
fdput(f);
preadv/pwritev: Add preadv and pwritev system calls. This patch adds preadv and pwritev system calls. These syscalls are a pretty straightforward combination of pread and readv (same for write). They are quite useful for doing vectored I/O in threaded applications. Using lseek+readv instead opens race windows you'll have to plug with locking. Other systems have such system calls too, for example NetBSD, check here: http://www.daemon-systems.org/man/preadv.2.html The application-visible interface provided by glibc should look like this to be compatible to the existing implementations in the *BSD family: ssize_t preadv(int d, const struct iovec *iov, int iovcnt, off_t offset); ssize_t pwritev(int d, const struct iovec *iov, int iovcnt, off_t offset); This prototype has one problem though: On 32bit archs is the (64bit) offset argument unaligned, which the syscall ABI of several archs doesn't allow to do. At least s390 needs a wrapper in glibc to handle this. As we'll need a wrappers in glibc anyway I've decided to push problem to glibc entriely and use a syscall prototype which works without arch-specific wrappers inside the kernel: The offset argument is explicitly splitted into two 32bit values. The patch sports the actual system call implementation and the windup in the x86 system call tables. Other archs follow as separate patches. Signed-off-by: Gerd Hoffmann <kraxel@redhat.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: <linux-api@vger.kernel.org> Cc: <linux-arch@vger.kernel.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-02 23:59:23 +00:00
}
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);
}
/*
* Various compat syscalls. Note that they all pretend to take a native
* iovec - import_iovec will properly treat those as compat_iovecs based on
* in_compat_syscall().
*/
#ifdef CONFIG_COMPAT
#ifdef __ARCH_WANT_COMPAT_SYS_PREADV64
COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd,
const struct iovec __user *, vec,
unsigned long, vlen, loff_t, pos)
{
return do_preadv(fd, vec, vlen, pos, 0);
}
#endif
COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd,
const struct 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_preadv(fd, vec, vlen, pos, 0);
}
#ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2
COMPAT_SYSCALL_DEFINE5(preadv64v2, unsigned long, fd,
const struct iovec __user *, vec,
unsigned long, vlen, loff_t, pos, rwf_t, flags)
{
if (pos == -1)
return do_readv(fd, vec, vlen, flags);
return do_preadv(fd, vec, vlen, pos, flags);
}
#endif
COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd,
const struct 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_readv(fd, vec, vlen, flags);
return do_preadv(fd, vec, vlen, pos, flags);
}
#ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64
COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd,
const struct iovec __user *, vec,
unsigned long, vlen, loff_t, pos)
{
return do_pwritev(fd, vec, vlen, pos, 0);
}
#endif
COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd,
const struct 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_pwritev(fd, vec, vlen, pos, 0);
}
#ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2
COMPAT_SYSCALL_DEFINE5(pwritev64v2, unsigned long, fd,
const struct iovec __user *, vec,
unsigned long, vlen, loff_t, pos, rwf_t, flags)
{
if (pos == -1)
return do_writev(fd, vec, vlen, flags);
return do_pwritev(fd, vec, vlen, pos, flags);
}
#endif
COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd,
const struct 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_writev(fd, vec, vlen, flags);
return do_pwritev(fd, vec, vlen, pos, flags);
}
#endif /* CONFIG_COMPAT */
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;
struct pipe_inode_info *opipe;
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;
in_inode = file_inode(in.file);
out_inode = file_inode(out.file);
out_pos = out.file->f_pos;
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
opipe = get_pipe_info(out.file, true);
if (!opipe) {
retval = rw_verify_area(WRITE, out.file, &out_pos, count);
if (retval < 0)
goto fput_out;
retval = do_splice_direct(in.file, &pos, out.file, &out_pos,
count, fl);
} else {
fs: sendfile handles O_NONBLOCK of out_fd sendfile has to return EAGAIN if out_fd is nonblocking and the write into it would block. Here is a small reproducer for the problem: #define _GNU_SOURCE /* See feature_test_macros(7) */ #include <fcntl.h> #include <stdio.h> #include <unistd.h> #include <errno.h> #include <sys/stat.h> #include <sys/types.h> #include <sys/sendfile.h> #define FILE_SIZE (1UL << 30) int main(int argc, char **argv) { int p[2], fd; if (pipe2(p, O_NONBLOCK)) return 1; fd = open(argv[1], O_RDWR | O_TMPFILE, 0666); if (fd < 0) return 1; ftruncate(fd, FILE_SIZE); if (sendfile(p[1], fd, 0, FILE_SIZE) == -1) { fprintf(stderr, "FAIL\n"); } if (sendfile(p[1], fd, 0, FILE_SIZE) != -1 || errno != EAGAIN) { fprintf(stderr, "FAIL\n"); } return 0; } It worked before b964bf53e540, it is stuck after b964bf53e540, and it works again with this fix. This regression occurred because do_splice_direct() calls pipe_write that handles O_NONBLOCK. Here is a trace log from the reproducer: 1) | __x64_sys_sendfile64() { 1) | do_sendfile() { 1) | __fdget() 1) | rw_verify_area() 1) | __fdget() 1) | rw_verify_area() 1) | do_splice_direct() { 1) | rw_verify_area() 1) | splice_direct_to_actor() { 1) | do_splice_to() { 1) | rw_verify_area() 1) | generic_file_splice_read() 1) + 74.153 us | } 1) | direct_splice_actor() { 1) | iter_file_splice_write() { 1) | __kmalloc() 1) 0.148 us | pipe_lock(); 1) 0.153 us | splice_from_pipe_next.part.0(); 1) 0.162 us | page_cache_pipe_buf_confirm(); ... 16 times 1) 0.159 us | page_cache_pipe_buf_confirm(); 1) | vfs_iter_write() { 1) | do_iter_write() { 1) | rw_verify_area() 1) | do_iter_readv_writev() { 1) | pipe_write() { 1) | mutex_lock() 1) 0.153 us | mutex_unlock(); 1) 1.368 us | } 1) 1.686 us | } 1) 5.798 us | } 1) 6.084 us | } 1) 0.174 us | kfree(); 1) 0.152 us | pipe_unlock(); 1) + 14.461 us | } 1) + 14.783 us | } 1) 0.164 us | page_cache_pipe_buf_release(); ... 16 times 1) 0.161 us | page_cache_pipe_buf_release(); 1) | touch_atime() 1) + 95.854 us | } 1) + 99.784 us | } 1) ! 107.393 us | } 1) ! 107.699 us | } Link: https://lkml.kernel.org/r/20220415005015.525191-1-avagin@gmail.com Fixes: b964bf53e540 ("teach sendfile(2) to handle send-to-pipe directly") Signed-off-by: Andrei Vagin <avagin@gmail.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-17 04:37:10 +00:00
if (out.file->f_flags & O_NONBLOCK)
fl |= SPLICE_F_NONBLOCK;
retval = splice_file_to_pipe(in.file, opipe, &pos, count, fl);
}
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
/*
* Performs necessary checks before doing a file copy
*
* Can adjust amount of bytes to copy via @req_count argument.
* Returns appropriate error code that caller should return or
* zero in case the copy should be allowed.
*/
static int generic_copy_file_checks(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
size_t *req_count, unsigned int flags)
{
struct inode *inode_in = file_inode(file_in);
struct inode *inode_out = file_inode(file_out);
uint64_t count = *req_count;
loff_t size_in;
int ret;
ret = generic_file_rw_checks(file_in, file_out);
if (ret)
return ret;
vfs: fix copy_file_range() regression in cross-fs copies A regression has been reported by Nicolas Boichat, found while using the copy_file_range syscall to copy a tracefs file. Before commit 5dae222a5ff0 ("vfs: allow copy_file_range to copy across devices") the kernel would return -EXDEV to userspace when trying to copy a file across different filesystems. After this commit, the syscall doesn't fail anymore and instead returns zero (zero bytes copied), as this file's content is generated on-the-fly and thus reports a size of zero. Another regression has been reported by He Zhe - the assertion of WARN_ON_ONCE(ret == -EOPNOTSUPP) can be triggered from userspace when copying from a sysfs file whose read operation may return -EOPNOTSUPP. Since we do not have test coverage for copy_file_range() between any two types of filesystems, the best way to avoid these sort of issues in the future is for the kernel to be more picky about filesystems that are allowed to do copy_file_range(). This patch restores some cross-filesystem copy restrictions that existed prior to commit 5dae222a5ff0 ("vfs: allow copy_file_range to copy across devices"), namely, cross-sb copy is not allowed for filesystems that do not implement ->copy_file_range(). Filesystems that do implement ->copy_file_range() have full control of the result - if this method returns an error, the error is returned to the user. Before this change this was only true for fs that did not implement the ->remap_file_range() operation (i.e. nfsv3). Filesystems that do not implement ->copy_file_range() still fall-back to the generic_copy_file_range() implementation when the copy is within the same sb. This helps the kernel can maintain a more consistent story about which filesystems support copy_file_range(). nfsd and ksmbd servers are modified to fall-back to the generic_copy_file_range() implementation in case vfs_copy_file_range() fails with -EOPNOTSUPP or -EXDEV, which preserves behavior of server-side-copy. fall-back to generic_copy_file_range() is not implemented for the smb operation FSCTL_DUPLICATE_EXTENTS_TO_FILE, which is arguably a correct change of behavior. Fixes: 5dae222a5ff0 ("vfs: allow copy_file_range to copy across devices") Link: https://lore.kernel.org/linux-fsdevel/20210212044405.4120619-1-drinkcat@chromium.org/ Link: https://lore.kernel.org/linux-fsdevel/CANMq1KDZuxir2LM5jOTm0xx+BnvW=ZmpsG47CyHFJwnw7zSX6Q@mail.gmail.com/ Link: https://lore.kernel.org/linux-fsdevel/20210126135012.1.If45b7cdc3ff707bc1efa17f5366057d60603c45f@changeid/ Link: https://lore.kernel.org/linux-fsdevel/20210630161320.29006-1-lhenriques@suse.de/ Reported-by: Nicolas Boichat <drinkcat@chromium.org> Reported-by: kernel test robot <oliver.sang@intel.com> Signed-off-by: Luis Henriques <lhenriques@suse.de> Fixes: 64bf5ff58dff ("vfs: no fallback for ->copy_file_range") Link: https://lore.kernel.org/linux-fsdevel/20f17f64-88cb-4e80-07c1-85cb96c83619@windriver.com/ Reported-by: He Zhe <zhe.he@windriver.com> Tested-by: Namjae Jeon <linkinjeon@kernel.org> Tested-by: Luis Henriques <lhenriques@suse.de> Signed-off-by: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-06-30 19:58:49 +00:00
/*
* We allow some filesystems to handle cross sb copy, but passing
* a file of the wrong filesystem type to filesystem driver can result
* in an attempt to dereference the wrong type of ->private_data, so
* avoid doing that until we really have a good reason.
*
* nfs and cifs define several different file_system_type structures
* and several different sets of file_operations, but they all end up
* using the same ->copy_file_range() function pointer.
*/
if (flags & COPY_FILE_SPLICE) {
/* cross sb splice is allowed */
} else if (file_out->f_op->copy_file_range) {
vfs: fix copy_file_range() regression in cross-fs copies A regression has been reported by Nicolas Boichat, found while using the copy_file_range syscall to copy a tracefs file. Before commit 5dae222a5ff0 ("vfs: allow copy_file_range to copy across devices") the kernel would return -EXDEV to userspace when trying to copy a file across different filesystems. After this commit, the syscall doesn't fail anymore and instead returns zero (zero bytes copied), as this file's content is generated on-the-fly and thus reports a size of zero. Another regression has been reported by He Zhe - the assertion of WARN_ON_ONCE(ret == -EOPNOTSUPP) can be triggered from userspace when copying from a sysfs file whose read operation may return -EOPNOTSUPP. Since we do not have test coverage for copy_file_range() between any two types of filesystems, the best way to avoid these sort of issues in the future is for the kernel to be more picky about filesystems that are allowed to do copy_file_range(). This patch restores some cross-filesystem copy restrictions that existed prior to commit 5dae222a5ff0 ("vfs: allow copy_file_range to copy across devices"), namely, cross-sb copy is not allowed for filesystems that do not implement ->copy_file_range(). Filesystems that do implement ->copy_file_range() have full control of the result - if this method returns an error, the error is returned to the user. Before this change this was only true for fs that did not implement the ->remap_file_range() operation (i.e. nfsv3). Filesystems that do not implement ->copy_file_range() still fall-back to the generic_copy_file_range() implementation when the copy is within the same sb. This helps the kernel can maintain a more consistent story about which filesystems support copy_file_range(). nfsd and ksmbd servers are modified to fall-back to the generic_copy_file_range() implementation in case vfs_copy_file_range() fails with -EOPNOTSUPP or -EXDEV, which preserves behavior of server-side-copy. fall-back to generic_copy_file_range() is not implemented for the smb operation FSCTL_DUPLICATE_EXTENTS_TO_FILE, which is arguably a correct change of behavior. Fixes: 5dae222a5ff0 ("vfs: allow copy_file_range to copy across devices") Link: https://lore.kernel.org/linux-fsdevel/20210212044405.4120619-1-drinkcat@chromium.org/ Link: https://lore.kernel.org/linux-fsdevel/CANMq1KDZuxir2LM5jOTm0xx+BnvW=ZmpsG47CyHFJwnw7zSX6Q@mail.gmail.com/ Link: https://lore.kernel.org/linux-fsdevel/20210126135012.1.If45b7cdc3ff707bc1efa17f5366057d60603c45f@changeid/ Link: https://lore.kernel.org/linux-fsdevel/20210630161320.29006-1-lhenriques@suse.de/ Reported-by: Nicolas Boichat <drinkcat@chromium.org> Reported-by: kernel test robot <oliver.sang@intel.com> Signed-off-by: Luis Henriques <lhenriques@suse.de> Fixes: 64bf5ff58dff ("vfs: no fallback for ->copy_file_range") Link: https://lore.kernel.org/linux-fsdevel/20f17f64-88cb-4e80-07c1-85cb96c83619@windriver.com/ Reported-by: He Zhe <zhe.he@windriver.com> Tested-by: Namjae Jeon <linkinjeon@kernel.org> Tested-by: Luis Henriques <lhenriques@suse.de> Signed-off-by: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-06-30 19:58:49 +00:00
if (file_in->f_op->copy_file_range !=
file_out->f_op->copy_file_range)
return -EXDEV;
} else if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb) {
return -EXDEV;
}
/* 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;
/* Ensure offsets don't wrap. */
if (pos_in + count < pos_in || pos_out + count < pos_out)
return -EOVERFLOW;
/* Shorten the copy to EOF */
size_in = i_size_read(inode_in);
if (pos_in >= size_in)
count = 0;
else
count = min(count, size_in - (uint64_t)pos_in);
ret = generic_write_check_limits(file_out, pos_out, &count);
if (ret)
return ret;
/* Don't allow overlapped copying within the same file. */
if (inode_in == inode_out &&
pos_out + count > pos_in &&
pos_out < pos_in + count)
return -EINVAL;
*req_count = count;
return 0;
}
/*
* 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)
{
ssize_t ret;
bool splice = flags & COPY_FILE_SPLICE;
bool samesb = file_inode(file_in)->i_sb == file_inode(file_out)->i_sb;
if (flags & ~COPY_FILE_SPLICE)
return -EINVAL;
ret = generic_copy_file_checks(file_in, pos_in, file_out, pos_out, &len,
flags);
if (unlikely(ret))
return ret;
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 (len == 0)
return 0;
file_start_write(file_out);
/*
vfs: fix copy_file_range() regression in cross-fs copies A regression has been reported by Nicolas Boichat, found while using the copy_file_range syscall to copy a tracefs file. Before commit 5dae222a5ff0 ("vfs: allow copy_file_range to copy across devices") the kernel would return -EXDEV to userspace when trying to copy a file across different filesystems. After this commit, the syscall doesn't fail anymore and instead returns zero (zero bytes copied), as this file's content is generated on-the-fly and thus reports a size of zero. Another regression has been reported by He Zhe - the assertion of WARN_ON_ONCE(ret == -EOPNOTSUPP) can be triggered from userspace when copying from a sysfs file whose read operation may return -EOPNOTSUPP. Since we do not have test coverage for copy_file_range() between any two types of filesystems, the best way to avoid these sort of issues in the future is for the kernel to be more picky about filesystems that are allowed to do copy_file_range(). This patch restores some cross-filesystem copy restrictions that existed prior to commit 5dae222a5ff0 ("vfs: allow copy_file_range to copy across devices"), namely, cross-sb copy is not allowed for filesystems that do not implement ->copy_file_range(). Filesystems that do implement ->copy_file_range() have full control of the result - if this method returns an error, the error is returned to the user. Before this change this was only true for fs that did not implement the ->remap_file_range() operation (i.e. nfsv3). Filesystems that do not implement ->copy_file_range() still fall-back to the generic_copy_file_range() implementation when the copy is within the same sb. This helps the kernel can maintain a more consistent story about which filesystems support copy_file_range(). nfsd and ksmbd servers are modified to fall-back to the generic_copy_file_range() implementation in case vfs_copy_file_range() fails with -EOPNOTSUPP or -EXDEV, which preserves behavior of server-side-copy. fall-back to generic_copy_file_range() is not implemented for the smb operation FSCTL_DUPLICATE_EXTENTS_TO_FILE, which is arguably a correct change of behavior. Fixes: 5dae222a5ff0 ("vfs: allow copy_file_range to copy across devices") Link: https://lore.kernel.org/linux-fsdevel/20210212044405.4120619-1-drinkcat@chromium.org/ Link: https://lore.kernel.org/linux-fsdevel/CANMq1KDZuxir2LM5jOTm0xx+BnvW=ZmpsG47CyHFJwnw7zSX6Q@mail.gmail.com/ Link: https://lore.kernel.org/linux-fsdevel/20210126135012.1.If45b7cdc3ff707bc1efa17f5366057d60603c45f@changeid/ Link: https://lore.kernel.org/linux-fsdevel/20210630161320.29006-1-lhenriques@suse.de/ Reported-by: Nicolas Boichat <drinkcat@chromium.org> Reported-by: kernel test robot <oliver.sang@intel.com> Signed-off-by: Luis Henriques <lhenriques@suse.de> Fixes: 64bf5ff58dff ("vfs: no fallback for ->copy_file_range") Link: https://lore.kernel.org/linux-fsdevel/20f17f64-88cb-4e80-07c1-85cb96c83619@windriver.com/ Reported-by: He Zhe <zhe.he@windriver.com> Tested-by: Namjae Jeon <linkinjeon@kernel.org> Tested-by: Luis Henriques <lhenriques@suse.de> Signed-off-by: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-06-30 19:58:49 +00:00
* Cloning is supported by more file systems, so we implement copy on
* same sb using clone, but for filesystems where both clone and copy
* are supported (e.g. nfs,cifs), we only call the copy method.
*/
if (!splice && file_out->f_op->copy_file_range) {
vfs: fix copy_file_range() regression in cross-fs copies A regression has been reported by Nicolas Boichat, found while using the copy_file_range syscall to copy a tracefs file. Before commit 5dae222a5ff0 ("vfs: allow copy_file_range to copy across devices") the kernel would return -EXDEV to userspace when trying to copy a file across different filesystems. After this commit, the syscall doesn't fail anymore and instead returns zero (zero bytes copied), as this file's content is generated on-the-fly and thus reports a size of zero. Another regression has been reported by He Zhe - the assertion of WARN_ON_ONCE(ret == -EOPNOTSUPP) can be triggered from userspace when copying from a sysfs file whose read operation may return -EOPNOTSUPP. Since we do not have test coverage for copy_file_range() between any two types of filesystems, the best way to avoid these sort of issues in the future is for the kernel to be more picky about filesystems that are allowed to do copy_file_range(). This patch restores some cross-filesystem copy restrictions that existed prior to commit 5dae222a5ff0 ("vfs: allow copy_file_range to copy across devices"), namely, cross-sb copy is not allowed for filesystems that do not implement ->copy_file_range(). Filesystems that do implement ->copy_file_range() have full control of the result - if this method returns an error, the error is returned to the user. Before this change this was only true for fs that did not implement the ->remap_file_range() operation (i.e. nfsv3). Filesystems that do not implement ->copy_file_range() still fall-back to the generic_copy_file_range() implementation when the copy is within the same sb. This helps the kernel can maintain a more consistent story about which filesystems support copy_file_range(). nfsd and ksmbd servers are modified to fall-back to the generic_copy_file_range() implementation in case vfs_copy_file_range() fails with -EOPNOTSUPP or -EXDEV, which preserves behavior of server-side-copy. fall-back to generic_copy_file_range() is not implemented for the smb operation FSCTL_DUPLICATE_EXTENTS_TO_FILE, which is arguably a correct change of behavior. Fixes: 5dae222a5ff0 ("vfs: allow copy_file_range to copy across devices") Link: https://lore.kernel.org/linux-fsdevel/20210212044405.4120619-1-drinkcat@chromium.org/ Link: https://lore.kernel.org/linux-fsdevel/CANMq1KDZuxir2LM5jOTm0xx+BnvW=ZmpsG47CyHFJwnw7zSX6Q@mail.gmail.com/ Link: https://lore.kernel.org/linux-fsdevel/20210126135012.1.If45b7cdc3ff707bc1efa17f5366057d60603c45f@changeid/ Link: https://lore.kernel.org/linux-fsdevel/20210630161320.29006-1-lhenriques@suse.de/ Reported-by: Nicolas Boichat <drinkcat@chromium.org> Reported-by: kernel test robot <oliver.sang@intel.com> Signed-off-by: Luis Henriques <lhenriques@suse.de> Fixes: 64bf5ff58dff ("vfs: no fallback for ->copy_file_range") Link: https://lore.kernel.org/linux-fsdevel/20f17f64-88cb-4e80-07c1-85cb96c83619@windriver.com/ Reported-by: He Zhe <zhe.he@windriver.com> Tested-by: Namjae Jeon <linkinjeon@kernel.org> Tested-by: Luis Henriques <lhenriques@suse.de> Signed-off-by: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-06-30 19:58:49 +00:00
ret = file_out->f_op->copy_file_range(file_in, pos_in,
file_out, pos_out,
len, flags);
} else if (!splice && file_in->f_op->remap_file_range && samesb) {
vfs: fix copy_file_range() regression in cross-fs copies A regression has been reported by Nicolas Boichat, found while using the copy_file_range syscall to copy a tracefs file. Before commit 5dae222a5ff0 ("vfs: allow copy_file_range to copy across devices") the kernel would return -EXDEV to userspace when trying to copy a file across different filesystems. After this commit, the syscall doesn't fail anymore and instead returns zero (zero bytes copied), as this file's content is generated on-the-fly and thus reports a size of zero. Another regression has been reported by He Zhe - the assertion of WARN_ON_ONCE(ret == -EOPNOTSUPP) can be triggered from userspace when copying from a sysfs file whose read operation may return -EOPNOTSUPP. Since we do not have test coverage for copy_file_range() between any two types of filesystems, the best way to avoid these sort of issues in the future is for the kernel to be more picky about filesystems that are allowed to do copy_file_range(). This patch restores some cross-filesystem copy restrictions that existed prior to commit 5dae222a5ff0 ("vfs: allow copy_file_range to copy across devices"), namely, cross-sb copy is not allowed for filesystems that do not implement ->copy_file_range(). Filesystems that do implement ->copy_file_range() have full control of the result - if this method returns an error, the error is returned to the user. Before this change this was only true for fs that did not implement the ->remap_file_range() operation (i.e. nfsv3). Filesystems that do not implement ->copy_file_range() still fall-back to the generic_copy_file_range() implementation when the copy is within the same sb. This helps the kernel can maintain a more consistent story about which filesystems support copy_file_range(). nfsd and ksmbd servers are modified to fall-back to the generic_copy_file_range() implementation in case vfs_copy_file_range() fails with -EOPNOTSUPP or -EXDEV, which preserves behavior of server-side-copy. fall-back to generic_copy_file_range() is not implemented for the smb operation FSCTL_DUPLICATE_EXTENTS_TO_FILE, which is arguably a correct change of behavior. Fixes: 5dae222a5ff0 ("vfs: allow copy_file_range to copy across devices") Link: https://lore.kernel.org/linux-fsdevel/20210212044405.4120619-1-drinkcat@chromium.org/ Link: https://lore.kernel.org/linux-fsdevel/CANMq1KDZuxir2LM5jOTm0xx+BnvW=ZmpsG47CyHFJwnw7zSX6Q@mail.gmail.com/ Link: https://lore.kernel.org/linux-fsdevel/20210126135012.1.If45b7cdc3ff707bc1efa17f5366057d60603c45f@changeid/ Link: https://lore.kernel.org/linux-fsdevel/20210630161320.29006-1-lhenriques@suse.de/ Reported-by: Nicolas Boichat <drinkcat@chromium.org> Reported-by: kernel test robot <oliver.sang@intel.com> Signed-off-by: Luis Henriques <lhenriques@suse.de> Fixes: 64bf5ff58dff ("vfs: no fallback for ->copy_file_range") Link: https://lore.kernel.org/linux-fsdevel/20f17f64-88cb-4e80-07c1-85cb96c83619@windriver.com/ Reported-by: He Zhe <zhe.he@windriver.com> Tested-by: Namjae Jeon <linkinjeon@kernel.org> Tested-by: Luis Henriques <lhenriques@suse.de> Signed-off-by: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-06-30 19:58:49 +00:00
ret = file_in->f_op->remap_file_range(file_in, pos_in,
file_out, pos_out,
min_t(loff_t, MAX_RW_COUNT, len),
REMAP_FILE_CAN_SHORTEN);
/* fallback to splice */
if (ret <= 0)
splice = true;
} else if (samesb) {
/* Fallback to splice for same sb copy for backward compat */
splice = true;
}
file_end_write(file_out);
if (!splice)
goto done;
vfs: fix copy_file_range() regression in cross-fs copies A regression has been reported by Nicolas Boichat, found while using the copy_file_range syscall to copy a tracefs file. Before commit 5dae222a5ff0 ("vfs: allow copy_file_range to copy across devices") the kernel would return -EXDEV to userspace when trying to copy a file across different filesystems. After this commit, the syscall doesn't fail anymore and instead returns zero (zero bytes copied), as this file's content is generated on-the-fly and thus reports a size of zero. Another regression has been reported by He Zhe - the assertion of WARN_ON_ONCE(ret == -EOPNOTSUPP) can be triggered from userspace when copying from a sysfs file whose read operation may return -EOPNOTSUPP. Since we do not have test coverage for copy_file_range() between any two types of filesystems, the best way to avoid these sort of issues in the future is for the kernel to be more picky about filesystems that are allowed to do copy_file_range(). This patch restores some cross-filesystem copy restrictions that existed prior to commit 5dae222a5ff0 ("vfs: allow copy_file_range to copy across devices"), namely, cross-sb copy is not allowed for filesystems that do not implement ->copy_file_range(). Filesystems that do implement ->copy_file_range() have full control of the result - if this method returns an error, the error is returned to the user. Before this change this was only true for fs that did not implement the ->remap_file_range() operation (i.e. nfsv3). Filesystems that do not implement ->copy_file_range() still fall-back to the generic_copy_file_range() implementation when the copy is within the same sb. This helps the kernel can maintain a more consistent story about which filesystems support copy_file_range(). nfsd and ksmbd servers are modified to fall-back to the generic_copy_file_range() implementation in case vfs_copy_file_range() fails with -EOPNOTSUPP or -EXDEV, which preserves behavior of server-side-copy. fall-back to generic_copy_file_range() is not implemented for the smb operation FSCTL_DUPLICATE_EXTENTS_TO_FILE, which is arguably a correct change of behavior. Fixes: 5dae222a5ff0 ("vfs: allow copy_file_range to copy across devices") Link: https://lore.kernel.org/linux-fsdevel/20210212044405.4120619-1-drinkcat@chromium.org/ Link: https://lore.kernel.org/linux-fsdevel/CANMq1KDZuxir2LM5jOTm0xx+BnvW=ZmpsG47CyHFJwnw7zSX6Q@mail.gmail.com/ Link: https://lore.kernel.org/linux-fsdevel/20210126135012.1.If45b7cdc3ff707bc1efa17f5366057d60603c45f@changeid/ Link: https://lore.kernel.org/linux-fsdevel/20210630161320.29006-1-lhenriques@suse.de/ Reported-by: Nicolas Boichat <drinkcat@chromium.org> Reported-by: kernel test robot <oliver.sang@intel.com> Signed-off-by: Luis Henriques <lhenriques@suse.de> Fixes: 64bf5ff58dff ("vfs: no fallback for ->copy_file_range") Link: https://lore.kernel.org/linux-fsdevel/20f17f64-88cb-4e80-07c1-85cb96c83619@windriver.com/ Reported-by: He Zhe <zhe.he@windriver.com> Tested-by: Namjae Jeon <linkinjeon@kernel.org> Tested-by: Luis Henriques <lhenriques@suse.de> Signed-off-by: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-06-30 19:58:49 +00:00
/*
* We can get here for same sb copy of filesystems that do not implement
* ->copy_file_range() in case filesystem does not support clone or in
* case filesystem supports clone but rejected the clone request (e.g.
* because it was not block aligned).
*
* In both cases, fall back to kernel copy so we are able to maintain a
* consistent story about which filesystems support copy_file_range()
* and which filesystems do not, that will allow userspace tools to
* make consistent desicions w.r.t using copy_file_range().
*
* We also get here if caller (e.g. nfsd) requested COPY_FILE_SPLICE
* for server-side-copy between any two sb.
*
* In any case, we call do_splice_direct() and not splice_file_range(),
* without file_start_write() held, to avoid possible deadlocks related
* to splicing from input file, while file_start_write() is held on
* the output file on a different sb.
vfs: fix copy_file_range() regression in cross-fs copies A regression has been reported by Nicolas Boichat, found while using the copy_file_range syscall to copy a tracefs file. Before commit 5dae222a5ff0 ("vfs: allow copy_file_range to copy across devices") the kernel would return -EXDEV to userspace when trying to copy a file across different filesystems. After this commit, the syscall doesn't fail anymore and instead returns zero (zero bytes copied), as this file's content is generated on-the-fly and thus reports a size of zero. Another regression has been reported by He Zhe - the assertion of WARN_ON_ONCE(ret == -EOPNOTSUPP) can be triggered from userspace when copying from a sysfs file whose read operation may return -EOPNOTSUPP. Since we do not have test coverage for copy_file_range() between any two types of filesystems, the best way to avoid these sort of issues in the future is for the kernel to be more picky about filesystems that are allowed to do copy_file_range(). This patch restores some cross-filesystem copy restrictions that existed prior to commit 5dae222a5ff0 ("vfs: allow copy_file_range to copy across devices"), namely, cross-sb copy is not allowed for filesystems that do not implement ->copy_file_range(). Filesystems that do implement ->copy_file_range() have full control of the result - if this method returns an error, the error is returned to the user. Before this change this was only true for fs that did not implement the ->remap_file_range() operation (i.e. nfsv3). Filesystems that do not implement ->copy_file_range() still fall-back to the generic_copy_file_range() implementation when the copy is within the same sb. This helps the kernel can maintain a more consistent story about which filesystems support copy_file_range(). nfsd and ksmbd servers are modified to fall-back to the generic_copy_file_range() implementation in case vfs_copy_file_range() fails with -EOPNOTSUPP or -EXDEV, which preserves behavior of server-side-copy. fall-back to generic_copy_file_range() is not implemented for the smb operation FSCTL_DUPLICATE_EXTENTS_TO_FILE, which is arguably a correct change of behavior. Fixes: 5dae222a5ff0 ("vfs: allow copy_file_range to copy across devices") Link: https://lore.kernel.org/linux-fsdevel/20210212044405.4120619-1-drinkcat@chromium.org/ Link: https://lore.kernel.org/linux-fsdevel/CANMq1KDZuxir2LM5jOTm0xx+BnvW=ZmpsG47CyHFJwnw7zSX6Q@mail.gmail.com/ Link: https://lore.kernel.org/linux-fsdevel/20210126135012.1.If45b7cdc3ff707bc1efa17f5366057d60603c45f@changeid/ Link: https://lore.kernel.org/linux-fsdevel/20210630161320.29006-1-lhenriques@suse.de/ Reported-by: Nicolas Boichat <drinkcat@chromium.org> Reported-by: kernel test robot <oliver.sang@intel.com> Signed-off-by: Luis Henriques <lhenriques@suse.de> Fixes: 64bf5ff58dff ("vfs: no fallback for ->copy_file_range") Link: https://lore.kernel.org/linux-fsdevel/20f17f64-88cb-4e80-07c1-85cb96c83619@windriver.com/ Reported-by: He Zhe <zhe.he@windriver.com> Tested-by: Namjae Jeon <linkinjeon@kernel.org> Tested-by: Luis Henriques <lhenriques@suse.de> Signed-off-by: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-06-30 19:58:49 +00:00
*/
ret = do_splice_direct(file_in, &pos_in, file_out, &pos_out,
min_t(size_t, len, MAX_RW_COUNT), 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);
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 = -EINVAL;
if (flags != 0)
goto out;
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;
}
/*
* Don't operate on ranges the page cache doesn't support, and don't exceed the
* LFS limits. If pos is under the limit it becomes a short access. If it
* exceeds the limit we return -EFBIG.
*/
int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count)
{
struct inode *inode = file->f_mapping->host;
loff_t max_size = inode->i_sb->s_maxbytes;
loff_t limit = rlimit(RLIMIT_FSIZE);
if (limit != RLIM_INFINITY) {
if (pos >= limit) {
send_sig(SIGXFSZ, current, 0);
return -EFBIG;
}
*count = min(*count, limit - pos);
}
if (!(file->f_flags & O_LARGEFILE))
max_size = MAX_NON_LFS;
if (unlikely(pos >= max_size))
return -EFBIG;
*count = min(*count, max_size - pos);
return 0;
}
/* Like generic_write_checks(), but takes size of write instead of iter. */
int generic_write_checks_count(struct kiocb *iocb, loff_t *count)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
if (IS_SWAPFILE(inode))
return -ETXTBSY;
if (!*count)
return 0;
if (iocb->ki_flags & IOCB_APPEND)
iocb->ki_pos = i_size_read(inode);
if ((iocb->ki_flags & IOCB_NOWAIT) &&
!((iocb->ki_flags & IOCB_DIRECT) ||
(file->f_mode & FMODE_BUF_WASYNC)))
return -EINVAL;
return generic_write_check_limits(iocb->ki_filp, iocb->ki_pos, count);
}
EXPORT_SYMBOL(generic_write_checks_count);
/*
* Performs necessary checks before doing a write
*
* Can adjust writing position or amount of bytes to write.
* Returns appropriate error code that caller should return or
* zero in case that write should be allowed.
*/
ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
{
loff_t count = iov_iter_count(from);
int ret;
ret = generic_write_checks_count(iocb, &count);
if (ret)
return ret;
iov_iter_truncate(from, count);
return iov_iter_count(from);
}
EXPORT_SYMBOL(generic_write_checks);
/*
* Performs common checks before doing a file copy/clone
* from @file_in to @file_out.
*/
int generic_file_rw_checks(struct file *file_in, struct file *file_out)
{
struct inode *inode_in = file_inode(file_in);
struct inode *inode_out = file_inode(file_out);
/* Don't copy 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;
if (!(file_in->f_mode & FMODE_READ) ||
!(file_out->f_mode & FMODE_WRITE) ||
(file_out->f_flags & O_APPEND))
return -EBADF;
return 0;
}