linux_dsm_epyc7002/arch/x86/ia32/sys_ia32.c
Tejun Heo 5a0e3ad6af include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files.  percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.

percpu.h -> slab.h dependency is about to be removed.  Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability.  As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.

  http://userweb.kernel.org/~tj/misc/slabh-sweep.py

The script does the followings.

* Scan files for gfp and slab usages and update includes such that
  only the necessary includes are there.  ie. if only gfp is used,
  gfp.h, if slab is used, slab.h.

* When the script inserts a new include, it looks at the include
  blocks and try to put the new include such that its order conforms
  to its surrounding.  It's put in the include block which contains
  core kernel includes, in the same order that the rest are ordered -
  alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
  doesn't seem to be any matching order.

* If the script can't find a place to put a new include (mostly
  because the file doesn't have fitting include block), it prints out
  an error message indicating which .h file needs to be added to the
  file.

The conversion was done in the following steps.

1. The initial automatic conversion of all .c files updated slightly
   over 4000 files, deleting around 700 includes and adding ~480 gfp.h
   and ~3000 slab.h inclusions.  The script emitted errors for ~400
   files.

2. Each error was manually checked.  Some didn't need the inclusion,
   some needed manual addition while adding it to implementation .h or
   embedding .c file was more appropriate for others.  This step added
   inclusions to around 150 files.

3. The script was run again and the output was compared to the edits
   from #2 to make sure no file was left behind.

4. Several build tests were done and a couple of problems were fixed.
   e.g. lib/decompress_*.c used malloc/free() wrappers around slab
   APIs requiring slab.h to be added manually.

5. The script was run on all .h files but without automatically
   editing them as sprinkling gfp.h and slab.h inclusions around .h
   files could easily lead to inclusion dependency hell.  Most gfp.h
   inclusion directives were ignored as stuff from gfp.h was usually
   wildly available and often used in preprocessor macros.  Each
   slab.h inclusion directive was examined and added manually as
   necessary.

6. percpu.h was updated not to include slab.h.

7. Build test were done on the following configurations and failures
   were fixed.  CONFIG_GCOV_KERNEL was turned off for all tests (as my
   distributed build env didn't work with gcov compiles) and a few
   more options had to be turned off depending on archs to make things
   build (like ipr on powerpc/64 which failed due to missing writeq).

   * x86 and x86_64 UP and SMP allmodconfig and a custom test config.
   * powerpc and powerpc64 SMP allmodconfig
   * sparc and sparc64 SMP allmodconfig
   * ia64 SMP allmodconfig
   * s390 SMP allmodconfig
   * alpha SMP allmodconfig
   * um on x86_64 SMP allmodconfig

8. percpu.h modifications were reverted so that it could be applied as
   a separate patch and serve as bisection point.

Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.

Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-30 22:02:32 +09:00

549 lines
15 KiB
C

/*
* sys_ia32.c: Conversion between 32bit and 64bit native syscalls. Based on
* sys_sparc32
*
* Copyright (C) 2000 VA Linux Co
* Copyright (C) 2000 Don Dugger <n0ano@valinux.com>
* Copyright (C) 1999 Arun Sharma <arun.sharma@intel.com>
* Copyright (C) 1997,1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
* Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu)
* Copyright (C) 2000 Hewlett-Packard Co.
* Copyright (C) 2000 David Mosberger-Tang <davidm@hpl.hp.com>
* Copyright (C) 2000,2001,2002 Andi Kleen, SuSE Labs (x86-64 port)
*
* These routines maintain argument size conversion between 32bit and 64bit
* environment. In 2.5 most of this should be moved to a generic directory.
*
* This file assumes that there is a hole at the end of user address space.
*
* Some of the functions are LE specific currently. These are
* hopefully all marked. This should be fixed.
*/
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/signal.h>
#include <linux/syscalls.h>
#include <linux/times.h>
#include <linux/utsname.h>
#include <linux/smp_lock.h>
#include <linux/mm.h>
#include <linux/uio.h>
#include <linux/poll.h>
#include <linux/personality.h>
#include <linux/stat.h>
#include <linux/rwsem.h>
#include <linux/compat.h>
#include <linux/vfs.h>
#include <linux/ptrace.h>
#include <linux/highuid.h>
#include <linux/sysctl.h>
#include <linux/slab.h>
#include <asm/mman.h>
#include <asm/types.h>
#include <asm/uaccess.h>
#include <asm/atomic.h>
#include <asm/vgtod.h>
#include <asm/sys_ia32.h>
#define AA(__x) ((unsigned long)(__x))
asmlinkage long sys32_truncate64(char __user *filename,
unsigned long offset_low,
unsigned long offset_high)
{
return sys_truncate(filename, ((loff_t) offset_high << 32) | offset_low);
}
asmlinkage long sys32_ftruncate64(unsigned int fd, unsigned long offset_low,
unsigned long offset_high)
{
return sys_ftruncate(fd, ((loff_t) offset_high << 32) | offset_low);
}
/*
* Another set for IA32/LFS -- x86_64 struct stat is different due to
* support for 64bit inode numbers.
*/
static int cp_stat64(struct stat64 __user *ubuf, struct kstat *stat)
{
typeof(ubuf->st_uid) uid = 0;
typeof(ubuf->st_gid) gid = 0;
SET_UID(uid, stat->uid);
SET_GID(gid, stat->gid);
if (!access_ok(VERIFY_WRITE, ubuf, sizeof(struct stat64)) ||
__put_user(huge_encode_dev(stat->dev), &ubuf->st_dev) ||
__put_user(stat->ino, &ubuf->__st_ino) ||
__put_user(stat->ino, &ubuf->st_ino) ||
__put_user(stat->mode, &ubuf->st_mode) ||
__put_user(stat->nlink, &ubuf->st_nlink) ||
__put_user(uid, &ubuf->st_uid) ||
__put_user(gid, &ubuf->st_gid) ||
__put_user(huge_encode_dev(stat->rdev), &ubuf->st_rdev) ||
__put_user(stat->size, &ubuf->st_size) ||
__put_user(stat->atime.tv_sec, &ubuf->st_atime) ||
__put_user(stat->atime.tv_nsec, &ubuf->st_atime_nsec) ||
__put_user(stat->mtime.tv_sec, &ubuf->st_mtime) ||
__put_user(stat->mtime.tv_nsec, &ubuf->st_mtime_nsec) ||
__put_user(stat->ctime.tv_sec, &ubuf->st_ctime) ||
__put_user(stat->ctime.tv_nsec, &ubuf->st_ctime_nsec) ||
__put_user(stat->blksize, &ubuf->st_blksize) ||
__put_user(stat->blocks, &ubuf->st_blocks))
return -EFAULT;
return 0;
}
asmlinkage long sys32_stat64(char __user *filename,
struct stat64 __user *statbuf)
{
struct kstat stat;
int ret = vfs_stat(filename, &stat);
if (!ret)
ret = cp_stat64(statbuf, &stat);
return ret;
}
asmlinkage long sys32_lstat64(char __user *filename,
struct stat64 __user *statbuf)
{
struct kstat stat;
int ret = vfs_lstat(filename, &stat);
if (!ret)
ret = cp_stat64(statbuf, &stat);
return ret;
}
asmlinkage long sys32_fstat64(unsigned int fd, struct stat64 __user *statbuf)
{
struct kstat stat;
int ret = vfs_fstat(fd, &stat);
if (!ret)
ret = cp_stat64(statbuf, &stat);
return ret;
}
asmlinkage long sys32_fstatat(unsigned int dfd, char __user *filename,
struct stat64 __user *statbuf, int flag)
{
struct kstat stat;
int error;
error = vfs_fstatat(dfd, filename, &stat, flag);
if (error)
return error;
return cp_stat64(statbuf, &stat);
}
/*
* Linux/i386 didn't use to be able to handle more than
* 4 system call parameters, so these system calls used a memory
* block for parameter passing..
*/
struct mmap_arg_struct32 {
unsigned int addr;
unsigned int len;
unsigned int prot;
unsigned int flags;
unsigned int fd;
unsigned int offset;
};
asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *arg)
{
struct mmap_arg_struct32 a;
if (copy_from_user(&a, arg, sizeof(a)))
return -EFAULT;
if (a.offset & ~PAGE_MASK)
return -EINVAL;
return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd,
a.offset>>PAGE_SHIFT);
}
asmlinkage long sys32_mprotect(unsigned long start, size_t len,
unsigned long prot)
{
return sys_mprotect(start, len, prot);
}
asmlinkage long sys32_rt_sigaction(int sig, struct sigaction32 __user *act,
struct sigaction32 __user *oact,
unsigned int sigsetsize)
{
struct k_sigaction new_ka, old_ka;
int ret;
compat_sigset_t set32;
/* XXX: Don't preclude handling different sized sigset_t's. */
if (sigsetsize != sizeof(compat_sigset_t))
return -EINVAL;
if (act) {
compat_uptr_t handler, restorer;
if (!access_ok(VERIFY_READ, act, sizeof(*act)) ||
__get_user(handler, &act->sa_handler) ||
__get_user(new_ka.sa.sa_flags, &act->sa_flags) ||
__get_user(restorer, &act->sa_restorer) ||
__copy_from_user(&set32, &act->sa_mask,
sizeof(compat_sigset_t)))
return -EFAULT;
new_ka.sa.sa_handler = compat_ptr(handler);
new_ka.sa.sa_restorer = compat_ptr(restorer);
/*
* FIXME: here we rely on _COMPAT_NSIG_WORS to be >=
* than _NSIG_WORDS << 1
*/
switch (_NSIG_WORDS) {
case 4: new_ka.sa.sa_mask.sig[3] = set32.sig[6]
| (((long)set32.sig[7]) << 32);
case 3: new_ka.sa.sa_mask.sig[2] = set32.sig[4]
| (((long)set32.sig[5]) << 32);
case 2: new_ka.sa.sa_mask.sig[1] = set32.sig[2]
| (((long)set32.sig[3]) << 32);
case 1: new_ka.sa.sa_mask.sig[0] = set32.sig[0]
| (((long)set32.sig[1]) << 32);
}
}
ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL);
if (!ret && oact) {
/*
* FIXME: here we rely on _COMPAT_NSIG_WORS to be >=
* than _NSIG_WORDS << 1
*/
switch (_NSIG_WORDS) {
case 4:
set32.sig[7] = (old_ka.sa.sa_mask.sig[3] >> 32);
set32.sig[6] = old_ka.sa.sa_mask.sig[3];
case 3:
set32.sig[5] = (old_ka.sa.sa_mask.sig[2] >> 32);
set32.sig[4] = old_ka.sa.sa_mask.sig[2];
case 2:
set32.sig[3] = (old_ka.sa.sa_mask.sig[1] >> 32);
set32.sig[2] = old_ka.sa.sa_mask.sig[1];
case 1:
set32.sig[1] = (old_ka.sa.sa_mask.sig[0] >> 32);
set32.sig[0] = old_ka.sa.sa_mask.sig[0];
}
if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) ||
__put_user(ptr_to_compat(old_ka.sa.sa_handler),
&oact->sa_handler) ||
__put_user(ptr_to_compat(old_ka.sa.sa_restorer),
&oact->sa_restorer) ||
__put_user(old_ka.sa.sa_flags, &oact->sa_flags) ||
__copy_to_user(&oact->sa_mask, &set32,
sizeof(compat_sigset_t)))
return -EFAULT;
}
return ret;
}
asmlinkage long sys32_sigaction(int sig, struct old_sigaction32 __user *act,
struct old_sigaction32 __user *oact)
{
struct k_sigaction new_ka, old_ka;
int ret;
if (act) {
compat_old_sigset_t mask;
compat_uptr_t handler, restorer;
if (!access_ok(VERIFY_READ, act, sizeof(*act)) ||
__get_user(handler, &act->sa_handler) ||
__get_user(new_ka.sa.sa_flags, &act->sa_flags) ||
__get_user(restorer, &act->sa_restorer) ||
__get_user(mask, &act->sa_mask))
return -EFAULT;
new_ka.sa.sa_handler = compat_ptr(handler);
new_ka.sa.sa_restorer = compat_ptr(restorer);
siginitset(&new_ka.sa.sa_mask, mask);
}
ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL);
if (!ret && oact) {
if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) ||
__put_user(ptr_to_compat(old_ka.sa.sa_handler),
&oact->sa_handler) ||
__put_user(ptr_to_compat(old_ka.sa.sa_restorer),
&oact->sa_restorer) ||
__put_user(old_ka.sa.sa_flags, &oact->sa_flags) ||
__put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask))
return -EFAULT;
}
return ret;
}
asmlinkage long sys32_rt_sigprocmask(int how, compat_sigset_t __user *set,
compat_sigset_t __user *oset,
unsigned int sigsetsize)
{
sigset_t s;
compat_sigset_t s32;
int ret;
mm_segment_t old_fs = get_fs();
if (set) {
if (copy_from_user(&s32, set, sizeof(compat_sigset_t)))
return -EFAULT;
switch (_NSIG_WORDS) {
case 4: s.sig[3] = s32.sig[6] | (((long)s32.sig[7]) << 32);
case 3: s.sig[2] = s32.sig[4] | (((long)s32.sig[5]) << 32);
case 2: s.sig[1] = s32.sig[2] | (((long)s32.sig[3]) << 32);
case 1: s.sig[0] = s32.sig[0] | (((long)s32.sig[1]) << 32);
}
}
set_fs(KERNEL_DS);
ret = sys_rt_sigprocmask(how,
set ? (sigset_t __user *)&s : NULL,
oset ? (sigset_t __user *)&s : NULL,
sigsetsize);
set_fs(old_fs);
if (ret)
return ret;
if (oset) {
switch (_NSIG_WORDS) {
case 4: s32.sig[7] = (s.sig[3] >> 32); s32.sig[6] = s.sig[3];
case 3: s32.sig[5] = (s.sig[2] >> 32); s32.sig[4] = s.sig[2];
case 2: s32.sig[3] = (s.sig[1] >> 32); s32.sig[2] = s.sig[1];
case 1: s32.sig[1] = (s.sig[0] >> 32); s32.sig[0] = s.sig[0];
}
if (copy_to_user(oset, &s32, sizeof(compat_sigset_t)))
return -EFAULT;
}
return 0;
}
asmlinkage long sys32_alarm(unsigned int seconds)
{
return alarm_setitimer(seconds);
}
asmlinkage long sys32_waitpid(compat_pid_t pid, unsigned int *stat_addr,
int options)
{
return compat_sys_wait4(pid, stat_addr, options, NULL);
}
/* 32-bit timeval and related flotsam. */
asmlinkage long sys32_sysfs(int option, u32 arg1, u32 arg2)
{
return sys_sysfs(option, arg1, arg2);
}
asmlinkage long sys32_sched_rr_get_interval(compat_pid_t pid,
struct compat_timespec __user *interval)
{
struct timespec t;
int ret;
mm_segment_t old_fs = get_fs();
set_fs(KERNEL_DS);
ret = sys_sched_rr_get_interval(pid, (struct timespec __user *)&t);
set_fs(old_fs);
if (put_compat_timespec(&t, interval))
return -EFAULT;
return ret;
}
asmlinkage long sys32_rt_sigpending(compat_sigset_t __user *set,
compat_size_t sigsetsize)
{
sigset_t s;
compat_sigset_t s32;
int ret;
mm_segment_t old_fs = get_fs();
set_fs(KERNEL_DS);
ret = sys_rt_sigpending((sigset_t __user *)&s, sigsetsize);
set_fs(old_fs);
if (!ret) {
switch (_NSIG_WORDS) {
case 4: s32.sig[7] = (s.sig[3] >> 32); s32.sig[6] = s.sig[3];
case 3: s32.sig[5] = (s.sig[2] >> 32); s32.sig[4] = s.sig[2];
case 2: s32.sig[3] = (s.sig[1] >> 32); s32.sig[2] = s.sig[1];
case 1: s32.sig[1] = (s.sig[0] >> 32); s32.sig[0] = s.sig[0];
}
if (copy_to_user(set, &s32, sizeof(compat_sigset_t)))
return -EFAULT;
}
return ret;
}
asmlinkage long sys32_rt_sigqueueinfo(int pid, int sig,
compat_siginfo_t __user *uinfo)
{
siginfo_t info;
int ret;
mm_segment_t old_fs = get_fs();
if (copy_siginfo_from_user32(&info, uinfo))
return -EFAULT;
set_fs(KERNEL_DS);
ret = sys_rt_sigqueueinfo(pid, sig, (siginfo_t __user *)&info);
set_fs(old_fs);
return ret;
}
/* warning: next two assume little endian */
asmlinkage long sys32_pread(unsigned int fd, char __user *ubuf, u32 count,
u32 poslo, u32 poshi)
{
return sys_pread64(fd, ubuf, count,
((loff_t)AA(poshi) << 32) | AA(poslo));
}
asmlinkage long sys32_pwrite(unsigned int fd, char __user *ubuf, u32 count,
u32 poslo, u32 poshi)
{
return sys_pwrite64(fd, ubuf, count,
((loff_t)AA(poshi) << 32) | AA(poslo));
}
asmlinkage long sys32_personality(unsigned long personality)
{
int ret;
if (personality(current->personality) == PER_LINUX32 &&
personality == PER_LINUX)
personality = PER_LINUX32;
ret = sys_personality(personality);
if (ret == PER_LINUX32)
ret = PER_LINUX;
return ret;
}
asmlinkage long sys32_sendfile(int out_fd, int in_fd,
compat_off_t __user *offset, s32 count)
{
mm_segment_t old_fs = get_fs();
int ret;
off_t of;
if (offset && get_user(of, offset))
return -EFAULT;
set_fs(KERNEL_DS);
ret = sys_sendfile(out_fd, in_fd, offset ? (off_t __user *)&of : NULL,
count);
set_fs(old_fs);
if (offset && put_user(of, offset))
return -EFAULT;
return ret;
}
asmlinkage long sys32_execve(char __user *name, compat_uptr_t __user *argv,
compat_uptr_t __user *envp, struct pt_regs *regs)
{
long error;
char *filename;
filename = getname(name);
error = PTR_ERR(filename);
if (IS_ERR(filename))
return error;
error = compat_do_execve(filename, argv, envp, regs);
putname(filename);
return error;
}
asmlinkage long sys32_clone(unsigned int clone_flags, unsigned int newsp,
struct pt_regs *regs)
{
void __user *parent_tid = (void __user *)regs->dx;
void __user *child_tid = (void __user *)regs->di;
if (!newsp)
newsp = regs->sp;
return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid);
}
/*
* Some system calls that need sign extended arguments. This could be
* done by a generic wrapper.
*/
long sys32_lseek(unsigned int fd, int offset, unsigned int whence)
{
return sys_lseek(fd, offset, whence);
}
long sys32_kill(int pid, int sig)
{
return sys_kill(pid, sig);
}
long sys32_fadvise64_64(int fd, __u32 offset_low, __u32 offset_high,
__u32 len_low, __u32 len_high, int advice)
{
return sys_fadvise64_64(fd,
(((u64)offset_high)<<32) | offset_low,
(((u64)len_high)<<32) | len_low,
advice);
}
long sys32_vm86_warning(void)
{
struct task_struct *me = current;
static char lastcomm[sizeof(me->comm)];
if (strncmp(lastcomm, me->comm, sizeof(lastcomm))) {
compat_printk(KERN_INFO
"%s: vm86 mode not supported on 64 bit kernel\n",
me->comm);
strncpy(lastcomm, me->comm, sizeof(lastcomm));
}
return -ENOSYS;
}
long sys32_lookup_dcookie(u32 addr_low, u32 addr_high,
char __user *buf, size_t len)
{
return sys_lookup_dcookie(((u64)addr_high << 32) | addr_low, buf, len);
}
asmlinkage ssize_t sys32_readahead(int fd, unsigned off_lo, unsigned off_hi,
size_t count)
{
return sys_readahead(fd, ((u64)off_hi << 32) | off_lo, count);
}
asmlinkage long sys32_sync_file_range(int fd, unsigned off_low, unsigned off_hi,
unsigned n_low, unsigned n_hi, int flags)
{
return sys_sync_file_range(fd,
((u64)off_hi << 32) | off_low,
((u64)n_hi << 32) | n_low, flags);
}
asmlinkage long sys32_fadvise64(int fd, unsigned offset_lo, unsigned offset_hi,
size_t len, int advice)
{
return sys_fadvise64_64(fd, ((u64)offset_hi << 32) | offset_lo,
len, advice);
}
asmlinkage long sys32_fallocate(int fd, int mode, unsigned offset_lo,
unsigned offset_hi, unsigned len_lo,
unsigned len_hi)
{
return sys_fallocate(fd, mode, ((u64)offset_hi << 32) | offset_lo,
((u64)len_hi << 32) | len_lo);
}