linux_dsm_epyc7002/fs/read_write.c

1025 lines
22 KiB
C
Raw Normal View History

/*
* linux/fs/read_write.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
#include <linux/slab.h>
#include <linux/stat.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 "read_write.h"
#include "internal.h"
#include <asm/uaccess.h>
#include <asm/unistd.h>
const struct file_operations generic_ro_fops = {
.llseek = generic_file_llseek,
.read = do_sync_read,
.aio_read = generic_file_aio_read,
.mmap = generic_file_readonly_mmap,
.splice_read = generic_file_splice_read,
};
EXPORT_SYMBOL(generic_ro_fops);
static inline int unsigned_offsets(struct file *file)
{
return file->f_mode & FMODE_UNSIGNED_OFFSET;
}
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>
2011-09-16 06:06:48 +07:00
static loff_t lseek_execute(struct file *file, struct inode *inode,
loff_t offset, loff_t maxsize)
{
if (offset < 0 && !unsigned_offsets(file))
return -EINVAL;
if (offset > maxsize)
return -EINVAL;
if (offset != file->f_pos) {
file->f_pos = offset;
file->f_version = 0;
}
return offset;
}
/**
* generic_file_llseek_size - generic llseek implementation for regular files
* @file: file structure to seek on
* @offset: file offset to seek to
* @whence: type of seek
* @size: max size of this file in file system
* @eof: offset used for SEEK_END position
*
* This is a variant of generic_file_llseek that allows passing in a custom
* maximum file size and a custom EOF position, for e.g. hashed directories
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>
2011-09-16 06:06:48 +07:00
*
* 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>
2011-09-16 06:06:48 +07:00
* 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)
{
struct inode *inode = file->f_mapping->host;
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>
2011-09-16 06:06:48 +07:00
/*
* 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 = lseek_execute(file, inode, 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>
2011-09-16 06:06:48 +07:00
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 (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 (offset >= eof)
return -ENXIO;
offset = eof;
break;
}
return lseek_execute(file, inode, 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 under i_mutex.
*/
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);
/**
* noop_llseek - No Operation Performed llseek implementation
* @file: file structure to seek on
* @offset: file offset to seek to
* @whence: type of seek
*
* This is an implementation of ->llseek useable for the rare special case when
* userspace expects the seek to succeed but the (device) file is actually not
* able to perform the seek. In this case you use noop_llseek() instead of
* falling back to the default implementation of ->llseek.
*/
loff_t noop_llseek(struct file *file, loff_t offset, int whence)
{
return file->f_pos;
}
EXPORT_SYMBOL(noop_llseek);
loff_t no_llseek(struct file *file, loff_t offset, int whence)
{
return -ESPIPE;
}
EXPORT_SYMBOL(no_llseek);
loff_t default_llseek(struct file *file, loff_t offset, int whence)
{
struct inode *inode = file_inode(file);
loff_t retval;
mutex_lock(&inode->i_mutex);
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:
mutex_unlock(&inode->i_mutex);
return retval;
}
EXPORT_SYMBOL(default_llseek);
loff_t vfs_llseek(struct file *file, loff_t offset, int whence)
{
loff_t (*fn)(struct file *, loff_t, int);
fn = no_llseek;
if (file->f_mode & FMODE_LSEEK) {
if (file->f_op && file->f_op->llseek)
fn = file->f_op->llseek;
}
return fn(file, offset, whence);
}
EXPORT_SYMBOL(vfs_llseek);
SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence)
{
off_t retval;
struct fd f = fdget(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(f);
return retval;
}
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE3(lseek, unsigned int, fd, compat_off_t, offset, unsigned int, whence)
{
return sys_lseek(fd, offset, whence);
}
#endif
#ifdef __ARCH_WANT_SYS_LLSEEK
SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high,
unsigned long, offset_low, loff_t __user *, result,
unsigned int, whence)
{
int retval;
struct fd f = fdget(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(f);
return retval;
}
#endif
/*
* rw_verify_area doesn't like huge counts. We limit
* them to something that fits in "int" so that others
* won't have to do range checks all the time.
*/
int rw_verify_area(int read_write, struct file *file, loff_t *ppos, size_t count)
{
struct inode *inode;
loff_t pos;
int retval = -EINVAL;
inode = file_inode(file);
if (unlikely((ssize_t) count < 0))
return retval;
pos = *ppos;
if (unlikely(pos < 0)) {
if (!unsigned_offsets(file))
return retval;
if (count >= -pos) /* both values are in 0..LLONG_MAX */
return -EOVERFLOW;
} else if (unlikely((loff_t) (pos + count) < 0)) {
if (!unsigned_offsets(file))
return retval;
}
if (unlikely(inode->i_flock && mandatory_lock(inode))) {
retval = locks_mandatory_area(
read_write == READ ? FLOCK_VERIFY_READ : FLOCK_VERIFY_WRITE,
inode, file, pos, count);
if (retval < 0)
return retval;
}
retval = security_file_permission(file,
read_write == READ ? MAY_READ : MAY_WRITE);
if (retval)
return retval;
return count > MAX_RW_COUNT ? MAX_RW_COUNT : count;
}
static void wait_on_retry_sync_kiocb(struct kiocb *iocb)
{
set_current_state(TASK_UNINTERRUPTIBLE);
if (!kiocbIsKicked(iocb))
schedule();
else
kiocbClearKicked(iocb);
__set_current_state(TASK_RUNNING);
}
ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos)
{
struct iovec iov = { .iov_base = buf, .iov_len = len };
struct kiocb kiocb;
ssize_t ret;
init_sync_kiocb(&kiocb, filp);
kiocb.ki_pos = *ppos;
kiocb.ki_left = len;
kiocb.ki_nbytes = len;
for (;;) {
ret = filp->f_op->aio_read(&kiocb, &iov, 1, kiocb.ki_pos);
if (ret != -EIOCBRETRY)
break;
wait_on_retry_sync_kiocb(&kiocb);
}
if (-EIOCBQUEUED == ret)
ret = wait_on_sync_kiocb(&kiocb);
*ppos = kiocb.ki_pos;
return ret;
}
EXPORT_SYMBOL(do_sync_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_op || (!file->f_op->read && !file->f_op->aio_read))
return -EINVAL;
if (unlikely(!access_ok(VERIFY_WRITE, buf, count)))
return -EFAULT;
ret = rw_verify_area(READ, file, pos, count);
if (ret >= 0) {
count = ret;
if (file->f_op->read)
ret = file->f_op->read(file, buf, count, pos);
else
ret = do_sync_read(file, buf, count, pos);
if (ret > 0) {
fsnotify_access(file);
add_rchar(current, ret);
}
inc_syscr(current);
}
return ret;
}
EXPORT_SYMBOL(vfs_read);
ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos)
{
struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = len };
struct kiocb kiocb;
ssize_t ret;
init_sync_kiocb(&kiocb, filp);
kiocb.ki_pos = *ppos;
kiocb.ki_left = len;
kiocb.ki_nbytes = len;
for (;;) {
ret = filp->f_op->aio_write(&kiocb, &iov, 1, kiocb.ki_pos);
if (ret != -EIOCBRETRY)
break;
wait_on_retry_sync_kiocb(&kiocb);
}
if (-EIOCBQUEUED == ret)
ret = wait_on_sync_kiocb(&kiocb);
*ppos = kiocb.ki_pos;
return ret;
}
EXPORT_SYMBOL(do_sync_write);
ssize_t __kernel_write(struct file *file, const char *buf, size_t count, loff_t *pos)
{
mm_segment_t old_fs;
const char __user *p;
ssize_t ret;
if (!file->f_op || (!file->f_op->write && !file->f_op->aio_write))
return -EINVAL;
old_fs = get_fs();
set_fs(get_ds());
p = (__force const char __user *)buf;
if (count > MAX_RW_COUNT)
count = MAX_RW_COUNT;
if (file->f_op->write)
ret = file->f_op->write(file, p, count, pos);
else
ret = do_sync_write(file, p, count, pos);
set_fs(old_fs);
if (ret > 0) {
fsnotify_modify(file);
add_wchar(current, ret);
}
inc_syscw(current);
return ret;
}
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_op || (!file->f_op->write && !file->f_op->aio_write))
return -EINVAL;
if (unlikely(!access_ok(VERIFY_READ, buf, count)))
return -EFAULT;
ret = rw_verify_area(WRITE, file, pos, count);
if (ret >= 0) {
count = ret;
if (file->f_op->write)
ret = file->f_op->write(file, buf, count, pos);
else
ret = do_sync_write(file, buf, count, pos);
if (ret > 0) {
fsnotify_modify(file);
add_wchar(current, ret);
}
inc_syscw(current);
}
return ret;
}
EXPORT_SYMBOL(vfs_write);
static inline loff_t file_pos_read(struct file *file)
{
return file->f_pos;
}
static inline void file_pos_write(struct file *file, loff_t pos)
{
file->f_pos = pos;
}
SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count)
{
struct fd f = fdget(fd);
ssize_t ret = -EBADF;
if (f.file) {
loff_t pos = file_pos_read(f.file);
ret = vfs_read(f.file, buf, count, &pos);
file_pos_write(f.file, pos);
fdput(f);
}
return ret;
}
SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf,
size_t, count)
{
struct fd f = fdget(fd);
ssize_t ret = -EBADF;
if (f.file) {
loff_t pos = file_pos_read(f.file);
ret = vfs_write(f.file, buf, count, &pos);
file_pos_write(f.file, pos);
fdput(f);
}
return ret;
}
SYSCALL_DEFINE(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;
}
#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
asmlinkage long SyS_pread64(long fd, long buf, long count, loff_t pos)
{
return SYSC_pread64((unsigned int) fd, (char __user *) buf,
(size_t) count, pos);
}
SYSCALL_ALIAS(sys_pread64, SyS_pread64);
#endif
SYSCALL_DEFINE(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;
}
#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
asmlinkage long SyS_pwrite64(long fd, long buf, long count, loff_t pos)
{
return SYSC_pwrite64((unsigned int) fd, (const char __user *) buf,
(size_t) count, pos);
}
SYSCALL_ALIAS(sys_pwrite64, SyS_pwrite64);
#endif
/*
* Reduce an iovec's length in-place. Return the resulting number of segments
*/
unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to)
{
unsigned long seg = 0;
size_t len = 0;
while (seg < nr_segs) {
seg++;
if (len + iov->iov_len >= to) {
iov->iov_len = to - len;
break;
}
len += iov->iov_len;
iov++;
}
return seg;
}
EXPORT_SYMBOL(iov_shorten);
ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov,
unsigned long nr_segs, size_t len, loff_t *ppos, iov_fn_t fn)
{
struct kiocb kiocb;
ssize_t ret;
init_sync_kiocb(&kiocb, filp);
kiocb.ki_pos = *ppos;
kiocb.ki_left = len;
kiocb.ki_nbytes = len;
for (;;) {
ret = fn(&kiocb, iov, nr_segs, kiocb.ki_pos);
if (ret != -EIOCBRETRY)
break;
wait_on_retry_sync_kiocb(&kiocb);
}
if (ret == -EIOCBQUEUED)
ret = wait_on_sync_kiocb(&kiocb);
*ppos = kiocb.ki_pos;
return ret;
}
/* Do it by hand, with file-ops */
ssize_t do_loop_readv_writev(struct file *filp, struct iovec *iov,
unsigned long nr_segs, loff_t *ppos, io_fn_t fn)
{
struct iovec *vector = iov;
ssize_t ret = 0;
while (nr_segs > 0) {
void __user *base;
size_t len;
ssize_t nr;
base = vector->iov_base;
len = vector->iov_len;
vector++;
nr_segs--;
nr = fn(filp, base, len, ppos);
if (nr < 0) {
if (!ret)
ret = nr;
break;
}
ret += nr;
if (nr != len)
break;
}
return ret;
}
/* A write operation does a read from user space and vice versa */
#define vrfy_dir(type) ((type) == READ ? VERIFY_WRITE : VERIFY_READ)
ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
unsigned long nr_segs, unsigned long fast_segs,
struct iovec *fast_pointer,
struct iovec **ret_pointer)
{
unsigned long seg;
ssize_t ret;
struct iovec *iov = fast_pointer;
/*
* SuS says "The readv() function *may* fail if the iovcnt argument
* was less than or equal to 0, or greater than {IOV_MAX}. Linux has
* traditionally returned zero for zero segments, so...
*/
if (nr_segs == 0) {
ret = 0;
goto out;
}
/*
* First get the "struct iovec" from user memory and
* verify all the pointers
*/
if (nr_segs > UIO_MAXIOV) {
ret = -EINVAL;
goto out;
}
if (nr_segs > fast_segs) {
iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL);
if (iov == NULL) {
ret = -ENOMEM;
goto out;
}
}
if (copy_from_user(iov, uvector, nr_segs*sizeof(*uvector))) {
ret = -EFAULT;
goto out;
}
/*
* According to the Single Unix Specification we should return EINVAL
* if an element length is < 0 when cast to ssize_t or if the
* total length would overflow the ssize_t return value of the
* system call.
*
* Linux caps all read/write calls to MAX_RW_COUNT, and avoids the
* overflow case.
*/
ret = 0;
for (seg = 0; seg < nr_segs; seg++) {
void __user *buf = iov[seg].iov_base;
ssize_t len = (ssize_t)iov[seg].iov_len;
/* see if we we're about to use an invalid len or if
* it's about to overflow ssize_t */
if (len < 0) {
ret = -EINVAL;
goto out;
}
if (type >= 0
Cross Memory Attach The basic idea behind cross memory attach is to allow MPI programs doing intra-node communication to do a single copy of the message rather than a double copy of the message via shared memory. The following patch attempts to achieve this by allowing a destination process, given an address and size from a source process, to copy memory directly from the source process into its own address space via a system call. There is also a symmetrical ability to copy from the current process's address space into a destination process's address space. - Use of /proc/pid/mem has been considered, but there are issues with using it: - Does not allow for specifying iovecs for both src and dest, assuming preadv or pwritev was implemented either the area read from or written to would need to be contiguous. - Currently mem_read allows only processes who are currently ptrace'ing the target and are still able to ptrace the target to read from the target. This check could possibly be moved to the open call, but its not clear exactly what race this restriction is stopping (reason appears to have been lost) - Having to send the fd of /proc/self/mem via SCM_RIGHTS on unix domain socket is a bit ugly from a userspace point of view, especially when you may have hundreds if not (eventually) thousands of processes that all need to do this with each other - Doesn't allow for some future use of the interface we would like to consider adding in the future (see below) - Interestingly reading from /proc/pid/mem currently actually involves two copies! (But this could be fixed pretty easily) As mentioned previously use of vmsplice instead was considered, but has problems. Since you need the reader and writer working co-operatively if the pipe is not drained then you block. Which requires some wrapping to do non blocking on the send side or polling on the receive. In all to all communication it requires ordering otherwise you can deadlock. And in the example of many MPI tasks writing to one MPI task vmsplice serialises the copying. There are some cases of MPI collectives where even a single copy interface does not get us the performance gain we could. For example in an MPI_Reduce rather than copy the data from the source we would like to instead use it directly in a mathops (say the reduce is doing a sum) as this would save us doing a copy. We don't need to keep a copy of the data from the source. I haven't implemented this, but I think this interface could in the future do all this through the use of the flags - eg could specify the math operation and type and the kernel rather than just copying the data would apply the specified operation between the source and destination and store it in the destination. Although we don't have a "second user" of the interface (though I've had some nibbles from people who may be interested in using it for intra process messaging which is not MPI). This interface is something which hardware vendors are already doing for their custom drivers to implement fast local communication. And so in addition to this being useful for OpenMPI it would mean the driver maintainers don't have to fix things up when the mm changes. There was some discussion about how much faster a true zero copy would go. Here's a link back to the email with some testing I did on that: http://marc.info/?l=linux-mm&m=130105930902915&w=2 There is a basic man page for the proposed interface here: http://ozlabs.org/~cyeoh/cma/process_vm_readv.txt This has been implemented for x86 and powerpc, other architecture should mainly (I think) just need to add syscall numbers for the process_vm_readv and process_vm_writev. There are 32 bit compatibility versions for 64-bit kernels. For arch maintainers there are some simple tests to be able to quickly verify that the syscalls are working correctly here: http://ozlabs.org/~cyeoh/cma/cma-test-20110718.tgz Signed-off-by: Chris Yeoh <yeohc@au1.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Howells <dhowells@redhat.com> Cc: James Morris <jmorris@namei.org> Cc: <linux-man@vger.kernel.org> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-11-01 07:06:39 +07:00
&& unlikely(!access_ok(vrfy_dir(type), buf, len))) {
ret = -EFAULT;
goto out;
}
if (len > MAX_RW_COUNT - ret) {
len = MAX_RW_COUNT - ret;
iov[seg].iov_len = len;
}
ret += len;
}
out:
*ret_pointer = iov;
return ret;
}
static ssize_t do_readv_writev(int type, struct file *file,
const struct iovec __user * uvector,
unsigned long nr_segs, loff_t *pos)
{
size_t tot_len;
struct iovec iovstack[UIO_FASTIOV];
struct iovec *iov = iovstack;
ssize_t ret;
io_fn_t fn;
iov_fn_t fnv;
if (!file->f_op) {
ret = -EINVAL;
goto out;
}
ret = rw_copy_check_uvector(type, uvector, nr_segs,
ARRAY_SIZE(iovstack), iovstack, &iov);
if (ret <= 0)
goto out;
tot_len = ret;
ret = rw_verify_area(type, file, pos, tot_len);
if (ret < 0)
goto out;
fnv = NULL;
if (type == READ) {
fn = file->f_op->read;
fnv = file->f_op->aio_read;
} else {
fn = (io_fn_t)file->f_op->write;
fnv = file->f_op->aio_write;
}
if (fnv)
ret = do_sync_readv_writev(file, iov, nr_segs, tot_len,
pos, fnv);
else
ret = do_loop_readv_writev(file, iov, nr_segs, pos, fn);
out:
if (iov != iovstack)
kfree(iov);
if ((ret + (type == READ)) > 0) {
if (type == READ)
fsnotify_access(file);
else
fsnotify_modify(file);
}
return ret;
}
ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
unsigned long vlen, loff_t *pos)
{
if (!(file->f_mode & FMODE_READ))
return -EBADF;
if (!file->f_op || (!file->f_op->aio_read && !file->f_op->read))
return -EINVAL;
return do_readv_writev(READ, file, vec, vlen, pos);
}
EXPORT_SYMBOL(vfs_readv);
ssize_t vfs_writev(struct file *file, const struct iovec __user *vec,
unsigned long vlen, loff_t *pos)
{
if (!(file->f_mode & FMODE_WRITE))
return -EBADF;
if (!file->f_op || (!file->f_op->aio_write && !file->f_op->write))
return -EINVAL;
return do_readv_writev(WRITE, file, vec, vlen, pos);
}
EXPORT_SYMBOL(vfs_writev);
SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
unsigned long, vlen)
{
struct fd f = fdget(fd);
ssize_t ret = -EBADF;
if (f.file) {
loff_t pos = file_pos_read(f.file);
ret = vfs_readv(f.file, vec, vlen, &pos);
file_pos_write(f.file, pos);
fdput(f);
}
if (ret > 0)
add_rchar(current, ret);
inc_syscr(current);
return ret;
}
SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
unsigned long, vlen)
{
struct fd f = fdget(fd);
ssize_t ret = -EBADF;
if (f.file) {
loff_t pos = file_pos_read(f.file);
ret = vfs_writev(f.file, vec, vlen, &pos);
file_pos_write(f.file, pos);
fdput(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 22:03:22 +07:00
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;
}
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>
2009-04-03 06:59:23 +07:00
SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
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 22:03:22 +07:00
unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
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>
2009-04-03 06:59:23 +07:00
{
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 22:03:22 +07:00
loff_t pos = pos_from_hilo(pos_h, pos_l);
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>
2009-04-03 06:59:23 +07:00
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>
2009-04-03 06:59:23 +07:00
ret = -ESPIPE;
if (f.file->f_mode & FMODE_PREAD)
ret = vfs_readv(f.file, vec, vlen, &pos);
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>
2009-04-03 06:59:23 +07:00
}
if (ret > 0)
add_rchar(current, ret);
inc_syscr(current);
return ret;
}
SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
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 22:03:22 +07:00
unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
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>
2009-04-03 06:59:23 +07:00
{
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 22:03:22 +07:00
loff_t pos = pos_from_hilo(pos_h, pos_l);
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>
2009-04-03 06:59:23 +07:00
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>
2009-04-03 06:59:23 +07:00
ret = -ESPIPE;
if (f.file->f_mode & FMODE_PWRITE)
ret = vfs_writev(f.file, vec, vlen, &pos);
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>
2009-04-03 06:59:23 +07:00
}
if (ret > 0)
add_wchar(current, ret);
inc_syscw(current);
return ret;
}
ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, size_t count,
loff_t max)
{
struct fd in, out;
struct inode *in_inode, *out_inode;
loff_t pos;
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)
ppos = &in.file->f_pos;
else
if (!(in.file->f_mode & FMODE_PREAD))
goto fput_in;
retval = rw_verify_area(READ, in.file, ppos, count);
if (retval < 0)
goto fput_in;
count = retval;
/*
* Get output file, and verify that it is ok..
*/
retval = -EBADF;
out = fdget(out_fd);
if (!out.file)
goto fput_in;
if (!(out.file->f_mode & FMODE_WRITE))
goto fput_out;
retval = -EINVAL;
in_inode = file_inode(in.file);
out_inode = file_inode(out.file);
retval = rw_verify_area(WRITE, out.file, &out.file->f_pos, count);
if (retval < 0)
goto fput_out;
count = retval;
if (!max)
max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes);
pos = *ppos;
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
retval = do_splice_direct(in.file, ppos, out.file, count, fl);
if (retval > 0) {
add_rchar(current, retval);
add_wchar(current, retval);
fsnotify_access(in.file);
fsnotify_modify(out.file);
}
inc_syscr(current);
inc_syscw(current);
if (*ppos > 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);
}