linux_dsm_epyc7002/fs/read_write.c
Linus Torvalds e28cc71572 Relax the rw_verify_area() error checking.
In particular, allow over-large read- or write-requests to be downgraded
to a more reasonable range, rather than considering them outright errors.

We want to protect lower layers from (the sadly all too common) overflow
conditions, but prefer to do so by chopping the requests up, rather than
just refusing them outright.

Cc: Peter Anvin <hpa@zytor.com>
Cc: Ulrich Drepper <drepper@redhat.com>
Cc: Andi Kleen <ak@suse.de>
Cc: Al Viro <viro@ftp.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-04 16:20:40 -08:00

769 lines
16 KiB
C

/*
* 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/smp_lock.h>
#include <linux/fsnotify.h>
#include <linux/security.h>
#include <linux/module.h>
#include <linux/syscalls.h>
#include <linux/pagemap.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
struct file_operations generic_ro_fops = {
.llseek = generic_file_llseek,
.read = generic_file_read,
.mmap = generic_file_readonly_mmap,
.sendfile = generic_file_sendfile,
};
EXPORT_SYMBOL(generic_ro_fops);
loff_t generic_file_llseek(struct file *file, loff_t offset, int origin)
{
long long retval;
struct inode *inode = file->f_mapping->host;
down(&inode->i_sem);
switch (origin) {
case 2:
offset += inode->i_size;
break;
case 1:
offset += file->f_pos;
}
retval = -EINVAL;
if (offset>=0 && offset<=inode->i_sb->s_maxbytes) {
if (offset != file->f_pos) {
file->f_pos = offset;
file->f_version = 0;
}
retval = offset;
}
up(&inode->i_sem);
return retval;
}
EXPORT_SYMBOL(generic_file_llseek);
loff_t remote_llseek(struct file *file, loff_t offset, int origin)
{
long long retval;
lock_kernel();
switch (origin) {
case 2:
offset += i_size_read(file->f_dentry->d_inode);
break;
case 1:
offset += file->f_pos;
}
retval = -EINVAL;
if (offset>=0 && offset<=file->f_dentry->d_inode->i_sb->s_maxbytes) {
if (offset != file->f_pos) {
file->f_pos = offset;
file->f_version = 0;
}
retval = offset;
}
unlock_kernel();
return retval;
}
EXPORT_SYMBOL(remote_llseek);
loff_t no_llseek(struct file *file, loff_t offset, int origin)
{
return -ESPIPE;
}
EXPORT_SYMBOL(no_llseek);
loff_t default_llseek(struct file *file, loff_t offset, int origin)
{
long long retval;
lock_kernel();
switch (origin) {
case 2:
offset += i_size_read(file->f_dentry->d_inode);
break;
case 1:
offset += file->f_pos;
}
retval = -EINVAL;
if (offset >= 0) {
if (offset != file->f_pos) {
file->f_pos = offset;
file->f_version = 0;
}
retval = offset;
}
unlock_kernel();
return retval;
}
EXPORT_SYMBOL(default_llseek);
loff_t vfs_llseek(struct file *file, loff_t offset, int origin)
{
loff_t (*fn)(struct file *, loff_t, int);
fn = no_llseek;
if (file->f_mode & FMODE_LSEEK) {
fn = default_llseek;
if (file->f_op && file->f_op->llseek)
fn = file->f_op->llseek;
}
return fn(file, offset, origin);
}
EXPORT_SYMBOL(vfs_llseek);
asmlinkage off_t sys_lseek(unsigned int fd, off_t offset, unsigned int origin)
{
off_t retval;
struct file * file;
int fput_needed;
retval = -EBADF;
file = fget_light(fd, &fput_needed);
if (!file)
goto bad;
retval = -EINVAL;
if (origin <= 2) {
loff_t res = vfs_llseek(file, offset, origin);
retval = res;
if (res != (loff_t)retval)
retval = -EOVERFLOW; /* LFS: should only happen on 32 bit platforms */
}
fput_light(file, fput_needed);
bad:
return retval;
}
#ifdef __ARCH_WANT_SYS_LLSEEK
asmlinkage long sys_llseek(unsigned int fd, unsigned long offset_high,
unsigned long offset_low, loff_t __user * result,
unsigned int origin)
{
int retval;
struct file * file;
loff_t offset;
int fput_needed;
retval = -EBADF;
file = fget_light(fd, &fput_needed);
if (!file)
goto bad;
retval = -EINVAL;
if (origin > 2)
goto out_putf;
offset = vfs_llseek(file, ((loff_t) offset_high << 32) | offset_low,
origin);
retval = (int)offset;
if (offset >= 0) {
retval = -EFAULT;
if (!copy_to_user(result, &offset, sizeof(offset)))
retval = 0;
}
out_putf:
fput_light(file, fput_needed);
bad:
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.
*/
#define MAX_RW_COUNT (INT_MAX & PAGE_CACHE_MASK)
int rw_verify_area(int read_write, struct file *file, loff_t *ppos, size_t count)
{
struct inode *inode;
loff_t pos;
if (unlikely((ssize_t) count < 0))
goto Einval;
pos = *ppos;
if (unlikely((pos < 0) || (loff_t) (pos + count) < 0))
goto Einval;
inode = file->f_dentry->d_inode;
if (inode->i_flock && MANDATORY_LOCK(inode)) {
int retval = locks_mandatory_area(
read_write == READ ? FLOCK_VERIFY_READ : FLOCK_VERIFY_WRITE,
inode, file, pos, count);
if (retval < 0)
return retval;
}
return count > MAX_RW_COUNT ? MAX_RW_COUNT : count;
Einval:
return -EINVAL;
}
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 kiocb kiocb;
ssize_t ret;
init_sync_kiocb(&kiocb, filp);
kiocb.ki_pos = *ppos;
while (-EIOCBRETRY ==
(ret = filp->f_op->aio_read(&kiocb, buf, len, kiocb.ki_pos)))
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;
ret = security_file_permission (file, MAY_READ);
if (!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->f_dentry);
current->rchar += ret;
}
current->syscr++;
}
}
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 kiocb kiocb;
ssize_t ret;
init_sync_kiocb(&kiocb, filp);
kiocb.ki_pos = *ppos;
while (-EIOCBRETRY ==
(ret = filp->f_op->aio_write(&kiocb, buf, len, kiocb.ki_pos)))
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 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;
ret = security_file_permission (file, MAY_WRITE);
if (!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->f_dentry);
current->wchar += ret;
}
current->syscw++;
}
}
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;
}
asmlinkage ssize_t sys_read(unsigned int fd, char __user * buf, size_t count)
{
struct file *file;
ssize_t ret = -EBADF;
int fput_needed;
file = fget_light(fd, &fput_needed);
if (file) {
loff_t pos = file_pos_read(file);
ret = vfs_read(file, buf, count, &pos);
file_pos_write(file, pos);
fput_light(file, fput_needed);
}
return ret;
}
EXPORT_SYMBOL_GPL(sys_read);
asmlinkage ssize_t sys_write(unsigned int fd, const char __user * buf, size_t count)
{
struct file *file;
ssize_t ret = -EBADF;
int fput_needed;
file = fget_light(fd, &fput_needed);
if (file) {
loff_t pos = file_pos_read(file);
ret = vfs_write(file, buf, count, &pos);
file_pos_write(file, pos);
fput_light(file, fput_needed);
}
return ret;
}
asmlinkage ssize_t sys_pread64(unsigned int fd, char __user *buf,
size_t count, loff_t pos)
{
struct file *file;
ssize_t ret = -EBADF;
int fput_needed;
if (pos < 0)
return -EINVAL;
file = fget_light(fd, &fput_needed);
if (file) {
ret = -ESPIPE;
if (file->f_mode & FMODE_PREAD)
ret = vfs_read(file, buf, count, &pos);
fput_light(file, fput_needed);
}
return ret;
}
asmlinkage ssize_t sys_pwrite64(unsigned int fd, const char __user *buf,
size_t count, loff_t pos)
{
struct file *file;
ssize_t ret = -EBADF;
int fput_needed;
if (pos < 0)
return -EINVAL;
file = fget_light(fd, &fput_needed);
if (file) {
ret = -ESPIPE;
if (file->f_mode & FMODE_PWRITE)
ret = vfs_write(file, buf, count, &pos);
fput_light(file, fput_needed);
}
return ret;
}
/*
* Reduce an iovec's length in-place. Return the resulting number of segments
*/
unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to)
{
unsigned long seg = 0;
size_t len = 0;
while (seg < nr_segs) {
seg++;
if (len + iov->iov_len >= to) {
iov->iov_len = to - len;
break;
}
len += iov->iov_len;
iov++;
}
return seg;
}
EXPORT_SYMBOL(iov_shorten);
/* A write operation does a read from user space and vice versa */
#define vrfy_dir(type) ((type) == READ ? VERIFY_WRITE : VERIFY_READ)
static ssize_t do_readv_writev(int type, struct file *file,
const struct iovec __user * uvector,
unsigned long nr_segs, loff_t *pos)
{
typedef ssize_t (*io_fn_t)(struct file *, char __user *, size_t, loff_t *);
typedef ssize_t (*iov_fn_t)(struct file *, const struct iovec *, unsigned long, loff_t *);
size_t tot_len;
struct iovec iovstack[UIO_FASTIOV];
struct iovec *iov=iovstack, *vector;
ssize_t ret;
int seg;
io_fn_t fn;
iov_fn_t fnv;
/*
* 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...
*/
ret = 0;
if (nr_segs == 0)
goto out;
/*
* First get the "struct iovec" from user memory and
* verify all the pointers
*/
ret = -EINVAL;
if ((nr_segs > UIO_MAXIOV) || (nr_segs <= 0))
goto out;
if (!file->f_op)
goto out;
if (nr_segs > UIO_FASTIOV) {
ret = -ENOMEM;
iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL);
if (!iov)
goto out;
}
ret = -EFAULT;
if (copy_from_user(iov, uvector, nr_segs*sizeof(*uvector)))
goto out;
/*
* Single unix specification:
* We should -EINVAL if an element length is not >= 0 and fitting an
* ssize_t. The total length is fitting an ssize_t
*
* Be careful here because iov_len is a size_t not an ssize_t
*/
tot_len = 0;
ret = -EINVAL;
for (seg = 0; seg < nr_segs; seg++) {
void __user *buf = iov[seg].iov_base;
ssize_t len = (ssize_t)iov[seg].iov_len;
if (len < 0) /* size_t not fitting an ssize_t .. */
goto out;
if (unlikely(!access_ok(vrfy_dir(type), buf, len)))
goto Efault;
tot_len += len;
if ((ssize_t)tot_len < 0) /* maths overflow on the ssize_t */
goto out;
}
if (tot_len == 0) {
ret = 0;
goto out;
}
ret = rw_verify_area(type, file, pos, tot_len);
if (ret < 0)
goto out;
ret = security_file_permission(file, type == READ ? MAY_READ : MAY_WRITE);
if (ret)
goto out;
fnv = NULL;
if (type == READ) {
fn = file->f_op->read;
fnv = file->f_op->readv;
} else {
fn = (io_fn_t)file->f_op->write;
fnv = file->f_op->writev;
}
if (fnv) {
ret = fnv(file, iov, nr_segs, pos);
goto out;
}
/* Do it by hand, with file-ops */
ret = 0;
vector = iov;
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(file, base, len, pos);
if (nr < 0) {
if (!ret) ret = nr;
break;
}
ret += nr;
if (nr != len)
break;
}
out:
if (iov != iovstack)
kfree(iov);
if ((ret + (type == READ)) > 0) {
if (type == READ)
fsnotify_access(file->f_dentry);
else
fsnotify_modify(file->f_dentry);
}
return ret;
Efault:
ret = -EFAULT;
goto out;
}
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->readv && !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->writev && !file->f_op->write))
return -EINVAL;
return do_readv_writev(WRITE, file, vec, vlen, pos);
}
EXPORT_SYMBOL(vfs_writev);
asmlinkage ssize_t
sys_readv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen)
{
struct file *file;
ssize_t ret = -EBADF;
int fput_needed;
file = fget_light(fd, &fput_needed);
if (file) {
loff_t pos = file_pos_read(file);
ret = vfs_readv(file, vec, vlen, &pos);
file_pos_write(file, pos);
fput_light(file, fput_needed);
}
if (ret > 0)
current->rchar += ret;
current->syscr++;
return ret;
}
asmlinkage ssize_t
sys_writev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen)
{
struct file *file;
ssize_t ret = -EBADF;
int fput_needed;
file = fget_light(fd, &fput_needed);
if (file) {
loff_t pos = file_pos_read(file);
ret = vfs_writev(file, vec, vlen, &pos);
file_pos_write(file, pos);
fput_light(file, fput_needed);
}
if (ret > 0)
current->wchar += ret;
current->syscw++;
return ret;
}
static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
size_t count, loff_t max)
{
struct file * in_file, * out_file;
struct inode * in_inode, * out_inode;
loff_t pos;
ssize_t retval;
int fput_needed_in, fput_needed_out;
/*
* Get input file, and verify that it is ok..
*/
retval = -EBADF;
in_file = fget_light(in_fd, &fput_needed_in);
if (!in_file)
goto out;
if (!(in_file->f_mode & FMODE_READ))
goto fput_in;
retval = -EINVAL;
in_inode = in_file->f_dentry->d_inode;
if (!in_inode)
goto fput_in;
if (!in_file->f_op || !in_file->f_op->sendfile)
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;
retval = security_file_permission (in_file, MAY_READ);
if (retval)
goto fput_in;
/*
* Get output file, and verify that it is ok..
*/
retval = -EBADF;
out_file = fget_light(out_fd, &fput_needed_out);
if (!out_file)
goto fput_in;
if (!(out_file->f_mode & FMODE_WRITE))
goto fput_out;
retval = -EINVAL;
if (!out_file->f_op || !out_file->f_op->sendpage)
goto fput_out;
out_inode = out_file->f_dentry->d_inode;
retval = rw_verify_area(WRITE, out_file, &out_file->f_pos, count);
if (retval < 0)
goto fput_out;
count = retval;
retval = security_file_permission (out_file, MAY_WRITE);
if (retval)
goto fput_out;
if (!max)
max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes);
pos = *ppos;
retval = -EINVAL;
if (unlikely(pos < 0))
goto fput_out;
if (unlikely(pos + count > max)) {
retval = -EOVERFLOW;
if (pos >= max)
goto fput_out;
count = max - pos;
}
retval = in_file->f_op->sendfile(in_file, ppos, count, file_send_actor, out_file);
if (retval > 0) {
current->rchar += retval;
current->wchar += retval;
}
current->syscr++;
current->syscw++;
if (*ppos > max)
retval = -EOVERFLOW;
fput_out:
fput_light(out_file, fput_needed_out);
fput_in:
fput_light(in_file, fput_needed_in);
out:
return retval;
}
asmlinkage ssize_t sys_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);
}
asmlinkage ssize_t sys_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);
}