linux/arch/sparc/kernel/sys_sparc.c

467 lines
11 KiB
C
Raw Normal View History

/* linux/arch/sparc/kernel/sys_sparc.c
*
* This file contains various random system calls that
* have a non-standard calling sequence on the Linux/sparc
* platform.
*/
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/sem.h>
#include <linux/msg.h>
#include <linux/shm.h>
#include <linux/stat.h>
#include <linux/syscalls.h>
#include <linux/mman.h>
#include <linux/utsname.h>
#include <linux/smp.h>
#include <linux/smp_lock.h>
#include <linux/ipc.h>
#include <asm/uaccess.h>
[PATCH] provide kernel_execve on all architectures This adds the new kernel_execve function on all architectures that were using _syscall3() to implement execve. The implementation uses code from the _syscall3 macros provided in the unistd.h header file. I don't have cross-compilers for any of these architectures, so the patch is untested with the exception of i386. Most architectures can probably implement this in a nicer way in assembly or by combining it with the sys_execve implementation itself, but this should do it for now. [bunk@stusta.de: m68knommu build fix] [markh@osdl.org: build fix] [bero@arklinux.org: build fix] [ralf@linux-mips.org: mips fix] [schwidefsky@de.ibm.com: s390 fix] Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Andi Kleen <ak@muc.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Ian Molton <spyro@f2s.com> Cc: Mikael Starvik <starvik@axis.com> Cc: David Howells <dhowells@redhat.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: Hirokazu Takata <takata.hirokazu@renesas.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp> Cc: Richard Curnow <rc@rc0.org.uk> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Cc: Miles Bader <uclinux-v850@lsi.nec.co.jp> Cc: Chris Zankel <chris@zankel.net> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Roman Zippel <zippel@linux-m68k.org> Signed-off-by: Ralf Baechle <ralf@linux-mips.org> Signed-off-by: Bernhard Rosenkraenzer <bero@arklinux.org> Signed-off-by: Mark Haverkamp <markh@osdl.org> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-02 17:18:34 +08:00
#include <asm/unistd.h>
/* #define DEBUG_UNIMP_SYSCALL */
/* XXX Make this per-binary type, this way we can detect the type of
* XXX a binary. Every Sparc executable calls this very early on.
*/
asmlinkage unsigned long sys_getpagesize(void)
{
return PAGE_SIZE; /* Possibly older binaries want 8192 on sun4's? */
}
#define COLOUR_ALIGN(addr) (((addr)+SHMLBA-1)&~(SHMLBA-1))
unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags)
{
struct vm_area_struct * vmm;
if (flags & MAP_FIXED) {
/* We do not accept a shared mapping if it would violate
* cache aliasing constraints.
*/
if ((flags & MAP_SHARED) && (addr & (SHMLBA - 1)))
return -EINVAL;
return addr;
}
/* See asm-sparc/uaccess.h */
if (len > TASK_SIZE - PAGE_SIZE)
return -ENOMEM;
if (ARCH_SUN4C && len > 0x20000000)
return -ENOMEM;
if (!addr)
addr = TASK_UNMAPPED_BASE;
if (flags & MAP_SHARED)
addr = COLOUR_ALIGN(addr);
else
addr = PAGE_ALIGN(addr);
for (vmm = find_vma(current->mm, addr); ; vmm = vmm->vm_next) {
/* At this point: (!vmm || addr < vmm->vm_end). */
if (ARCH_SUN4C && addr < 0xe0000000 && 0x20000000 - len < addr) {
addr = PAGE_OFFSET;
vmm = find_vma(current->mm, PAGE_OFFSET);
}
if (TASK_SIZE - PAGE_SIZE - len < addr)
return -ENOMEM;
if (!vmm || addr + len <= vmm->vm_start)
return addr;
addr = vmm->vm_end;
if (flags & MAP_SHARED)
addr = COLOUR_ALIGN(addr);
}
}
asmlinkage unsigned long sparc_brk(unsigned long brk)
{
if(ARCH_SUN4C) {
if ((brk & 0xe0000000) != (current->mm->brk & 0xe0000000))
return current->mm->brk;
}
return sys_brk(brk);
}
/*
* sys_pipe() is the normal C calling standard for creating
* a pipe. It's not the way unix traditionally does this, though.
*/
asmlinkage int sparc_pipe(struct pt_regs *regs)
{
int fd[2];
int error;
flag parameters: pipe This patch introduces the new syscall pipe2 which is like pipe but it also takes an additional parameter which takes a flag value. This patch implements the handling of O_CLOEXEC for the flag. I did not add support for the new syscall for the architectures which have a special sys_pipe implementation. I think the maintainers of those archs have the chance to go with the unified implementation but that's up to them. The implementation introduces do_pipe_flags. I did that instead of changing all callers of do_pipe because some of the callers are written in assembler. I would probably screw up changing the assembly code. To avoid breaking code do_pipe is now a small wrapper around do_pipe_flags. Once all callers are changed over to do_pipe_flags the old do_pipe function can be removed. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include <fcntl.h> #include <stdio.h> #include <unistd.h> #include <sys/syscall.h> #ifndef __NR_pipe2 # ifdef __x86_64__ # define __NR_pipe2 293 # elif defined __i386__ # define __NR_pipe2 331 # else # error "need __NR_pipe2" # endif #endif int main (void) { int fd[2]; if (syscall (__NR_pipe2, fd, 0) != 0) { puts ("pipe2(0) failed"); return 1; } for (int i = 0; i < 2; ++i) { int coe = fcntl (fd[i], F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { printf ("pipe2(0) set close-on-exit for fd[%d]\n", i); return 1; } } close (fd[0]); close (fd[1]); if (syscall (__NR_pipe2, fd, O_CLOEXEC) != 0) { puts ("pipe2(O_CLOEXEC) failed"); return 1; } for (int i = 0; i < 2; ++i) { int coe = fcntl (fd[i], F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { printf ("pipe2(O_CLOEXEC) does not set close-on-exit for fd[%d]\n", i); return 1; } } close (fd[0]); close (fd[1]); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper <drepper@redhat.com> Acked-by: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk.manpages@googlemail.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:29:30 +08:00
error = do_pipe_flags(fd, 0);
if (error)
goto out;
regs->u_regs[UREG_I1] = fd[1];
error = fd[0];
out:
return error;
}
/*
* sys_ipc() is the de-multiplexer for the SysV IPC calls..
*
* This is really horribly ugly.
*/
asmlinkage int sys_ipc (uint call, int first, int second, int third, void __user *ptr, long fifth)
{
int version, err;
version = call >> 16; /* hack for backward compatibility */
call &= 0xffff;
if (call <= SEMCTL)
switch (call) {
case SEMOP:
err = sys_semtimedop (first, (struct sembuf __user *)ptr, second, NULL);
goto out;
case SEMTIMEDOP:
err = sys_semtimedop (first, (struct sembuf __user *)ptr, second, (const struct timespec __user *) fifth);
goto out;
case SEMGET:
err = sys_semget (first, second, third);
goto out;
case SEMCTL: {
union semun fourth;
err = -EINVAL;
if (!ptr)
goto out;
err = -EFAULT;
if (get_user(fourth.__pad,
(void __user * __user *)ptr))
goto out;
err = sys_semctl (first, second, third, fourth);
goto out;
}
default:
err = -ENOSYS;
goto out;
}
if (call <= MSGCTL)
switch (call) {
case MSGSND:
err = sys_msgsnd (first, (struct msgbuf __user *) ptr,
second, third);
goto out;
case MSGRCV:
switch (version) {
case 0: {
struct ipc_kludge tmp;
err = -EINVAL;
if (!ptr)
goto out;
err = -EFAULT;
if (copy_from_user(&tmp, (struct ipc_kludge __user *) ptr, sizeof (tmp)))
goto out;
err = sys_msgrcv (first, tmp.msgp, second, tmp.msgtyp, third);
goto out;
}
case 1: default:
err = sys_msgrcv (first,
(struct msgbuf __user *) ptr,
second, fifth, third);
goto out;
}
case MSGGET:
err = sys_msgget ((key_t) first, second);
goto out;
case MSGCTL:
err = sys_msgctl (first, second, (struct msqid_ds __user *) ptr);
goto out;
default:
err = -ENOSYS;
goto out;
}
if (call <= SHMCTL)
switch (call) {
case SHMAT:
switch (version) {
case 0: default: {
ulong raddr;
err = do_shmat (first, (char __user *) ptr, second, &raddr);
if (err)
goto out;
err = -EFAULT;
if (put_user (raddr, (ulong __user *) third))
goto out;
err = 0;
goto out;
}
case 1: /* iBCS2 emulator entry point */
err = -EINVAL;
goto out;
}
case SHMDT:
err = sys_shmdt ((char __user *)ptr);
goto out;
case SHMGET:
err = sys_shmget (first, second, third);
goto out;
case SHMCTL:
err = sys_shmctl (first, second, (struct shmid_ds __user *) ptr);
goto out;
default:
err = -ENOSYS;
goto out;
}
else
err = -ENOSYS;
out:
return err;
}
int sparc_mmap_check(unsigned long addr, unsigned long len)
{
if (ARCH_SUN4C &&
(len > 0x20000000 ||
(addr < 0xe0000000 && addr + len > 0x20000000)))
return -EINVAL;
/* See asm-sparc/uaccess.h */
if (len > TASK_SIZE - PAGE_SIZE || addr + len > TASK_SIZE - PAGE_SIZE)
return -EINVAL;
return 0;
}
/* Linux version of mmap */
static unsigned long do_mmap2(unsigned long addr, unsigned long len,
unsigned long prot, unsigned long flags, unsigned long fd,
unsigned long pgoff)
{
struct file * file = NULL;
unsigned long retval = -EBADF;
if (!(flags & MAP_ANONYMOUS)) {
file = fget(fd);
if (!file)
goto out;
}
len = PAGE_ALIGN(len);
flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
down_write(&current->mm->mmap_sem);
retval = do_mmap_pgoff(file, addr, len, prot, flags, pgoff);
up_write(&current->mm->mmap_sem);
if (file)
fput(file);
out:
return retval;
}
asmlinkage unsigned long sys_mmap2(unsigned long addr, unsigned long len,
unsigned long prot, unsigned long flags, unsigned long fd,
unsigned long pgoff)
{
/* Make sure the shift for mmap2 is constant (12), no matter what PAGE_SIZE
we have. */
return do_mmap2(addr, len, prot, flags, fd, pgoff >> (PAGE_SHIFT - 12));
}
asmlinkage unsigned long sys_mmap(unsigned long addr, unsigned long len,
unsigned long prot, unsigned long flags, unsigned long fd,
unsigned long off)
{
return do_mmap2(addr, len, prot, flags, fd, off >> PAGE_SHIFT);
}
long sparc_remap_file_pages(unsigned long start, unsigned long size,
unsigned long prot, unsigned long pgoff,
unsigned long flags)
{
/* This works on an existing mmap so we don't need to validate
* the range as that was done at the original mmap call.
*/
return sys_remap_file_pages(start, size, prot,
(pgoff >> (PAGE_SHIFT - 12)), flags);
}
extern unsigned long do_mremap(unsigned long addr,
unsigned long old_len, unsigned long new_len,
unsigned long flags, unsigned long new_addr);
asmlinkage unsigned long sparc_mremap(unsigned long addr,
unsigned long old_len, unsigned long new_len,
unsigned long flags, unsigned long new_addr)
{
unsigned long ret = -EINVAL;
if (unlikely(sparc_mmap_check(addr, old_len)))
goto out;
if (unlikely(sparc_mmap_check(new_addr, new_len)))
goto out;
down_write(&current->mm->mmap_sem);
ret = do_mremap(addr, old_len, new_len, flags, new_addr);
up_write(&current->mm->mmap_sem);
out:
return ret;
}
/* we come to here via sys_nis_syscall so it can setup the regs argument */
asmlinkage unsigned long
c_sys_nis_syscall (struct pt_regs *regs)
{
static int count = 0;
if (count++ > 5)
return -ENOSYS;
printk ("%s[%d]: Unimplemented SPARC system call %d\n",
current->comm, task_pid_nr(current), (int)regs->u_regs[1]);
#ifdef DEBUG_UNIMP_SYSCALL
show_regs (regs);
#endif
return -ENOSYS;
}
/* #define DEBUG_SPARC_BREAKPOINT */
asmlinkage void
sparc_breakpoint (struct pt_regs *regs)
{
siginfo_t info;
lock_kernel();
#ifdef DEBUG_SPARC_BREAKPOINT
printk ("TRAP: Entering kernel PC=%x, nPC=%x\n", regs->pc, regs->npc);
#endif
info.si_signo = SIGTRAP;
info.si_errno = 0;
info.si_code = TRAP_BRKPT;
info.si_addr = (void __user *)regs->pc;
info.si_trapno = 0;
force_sig_info(SIGTRAP, &info, current);
#ifdef DEBUG_SPARC_BREAKPOINT
printk ("TRAP: Returning to space: PC=%x nPC=%x\n", regs->pc, regs->npc);
#endif
unlock_kernel();
}
asmlinkage int
sparc_sigaction (int sig, const struct old_sigaction __user *act,
struct old_sigaction __user *oact)
{
struct k_sigaction new_ka, old_ka;
int ret;
WARN_ON_ONCE(sig >= 0);
sig = -sig;
if (act) {
unsigned long mask;
if (!access_ok(VERIFY_READ, act, sizeof(*act)) ||
__get_user(new_ka.sa.sa_handler, &act->sa_handler) ||
__get_user(new_ka.sa.sa_restorer, &act->sa_restorer))
return -EFAULT;
__get_user(new_ka.sa.sa_flags, &act->sa_flags);
__get_user(mask, &act->sa_mask);
siginitset(&new_ka.sa.sa_mask, mask);
new_ka.ka_restorer = NULL;
}
ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL);
if (!ret && oact) {
/* In the clone() case we could copy half consistent
* state to the user, however this could sleep and
* deadlock us if we held the signal lock on SMP. So for
* now I take the easy way out and do no locking.
*/
if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) ||
__put_user(old_ka.sa.sa_handler, &oact->sa_handler) ||
__put_user(old_ka.sa.sa_restorer, &oact->sa_restorer))
return -EFAULT;
__put_user(old_ka.sa.sa_flags, &oact->sa_flags);
__put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask);
}
return ret;
}
asmlinkage long
sys_rt_sigaction(int sig,
const struct sigaction __user *act,
struct sigaction __user *oact,
void __user *restorer,
size_t sigsetsize)
{
struct k_sigaction new_ka, old_ka;
int ret;
/* XXX: Don't preclude handling different sized sigset_t's. */
if (sigsetsize != sizeof(sigset_t))
return -EINVAL;
if (act) {
new_ka.ka_restorer = restorer;
if (copy_from_user(&new_ka.sa, act, sizeof(*act)))
return -EFAULT;
}
ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL);
if (!ret && oact) {
if (copy_to_user(oact, &old_ka.sa, sizeof(*oact)))
return -EFAULT;
}
return ret;
}
asmlinkage int sys_getdomainname(char __user *name, int len)
{
int nlen, err;
if (len < 0)
return -EINVAL;
down_read(&uts_sem);
nlen = strlen(utsname()->domainname) + 1;
err = -EINVAL;
if (nlen > len)
goto out;
err = -EFAULT;
if (!copy_to_user(name, utsname()->domainname, nlen))
err = 0;
out:
up_read(&uts_sem);
return err;
}
[PATCH] provide kernel_execve on all architectures This adds the new kernel_execve function on all architectures that were using _syscall3() to implement execve. The implementation uses code from the _syscall3 macros provided in the unistd.h header file. I don't have cross-compilers for any of these architectures, so the patch is untested with the exception of i386. Most architectures can probably implement this in a nicer way in assembly or by combining it with the sys_execve implementation itself, but this should do it for now. [bunk@stusta.de: m68knommu build fix] [markh@osdl.org: build fix] [bero@arklinux.org: build fix] [ralf@linux-mips.org: mips fix] [schwidefsky@de.ibm.com: s390 fix] Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Andi Kleen <ak@muc.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Ian Molton <spyro@f2s.com> Cc: Mikael Starvik <starvik@axis.com> Cc: David Howells <dhowells@redhat.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: Hirokazu Takata <takata.hirokazu@renesas.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp> Cc: Richard Curnow <rc@rc0.org.uk> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Cc: Miles Bader <uclinux-v850@lsi.nec.co.jp> Cc: Chris Zankel <chris@zankel.net> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Roman Zippel <zippel@linux-m68k.org> Signed-off-by: Ralf Baechle <ralf@linux-mips.org> Signed-off-by: Bernhard Rosenkraenzer <bero@arklinux.org> Signed-off-by: Mark Haverkamp <markh@osdl.org> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-02 17:18:34 +08:00
/*
* Do a system call from kernel instead of calling sys_execve so we
* end up with proper pt_regs.
*/
int kernel_execve(const char *filename, char *const argv[], char *const envp[])
{
long __res;
register long __g1 __asm__ ("g1") = __NR_execve;
register long __o0 __asm__ ("o0") = (long)(filename);
register long __o1 __asm__ ("o1") = (long)(argv);
register long __o2 __asm__ ("o2") = (long)(envp);
asm volatile ("t 0x10\n\t"
"bcc 1f\n\t"
"mov %%o0, %0\n\t"
"sub %%g0, %%o0, %0\n\t"
"1:\n\t"
: "=r" (__res), "=&r" (__o0)
: "1" (__o0), "r" (__o1), "r" (__o2), "r" (__g1)
: "cc");
return __res;
}