mirror of
https://github.com/edk2-porting/linux-next.git
synced 2024-12-23 20:53:53 +08:00
ed8cae8ba0
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>
287 lines
6.9 KiB
C
287 lines
6.9 KiB
C
/*
|
|
* This file contains various system calls that have different calling
|
|
* conventions on different platforms.
|
|
*
|
|
* Copyright (C) 1999-2000, 2002-2003, 2005 Hewlett-Packard Co
|
|
* David Mosberger-Tang <davidm@hpl.hp.com>
|
|
*/
|
|
#include <linux/errno.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/mman.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/shm.h>
|
|
#include <linux/file.h> /* doh, must come after sched.h... */
|
|
#include <linux/smp.h>
|
|
#include <linux/syscalls.h>
|
|
#include <linux/highuid.h>
|
|
#include <linux/hugetlb.h>
|
|
|
|
#include <asm/shmparam.h>
|
|
#include <asm/uaccess.h>
|
|
|
|
unsigned long
|
|
arch_get_unmapped_area (struct file *filp, unsigned long addr, unsigned long len,
|
|
unsigned long pgoff, unsigned long flags)
|
|
{
|
|
long map_shared = (flags & MAP_SHARED);
|
|
unsigned long start_addr, align_mask = PAGE_SIZE - 1;
|
|
struct mm_struct *mm = current->mm;
|
|
struct vm_area_struct *vma;
|
|
|
|
if (len > RGN_MAP_LIMIT)
|
|
return -ENOMEM;
|
|
|
|
/* handle fixed mapping: prevent overlap with huge pages */
|
|
if (flags & MAP_FIXED) {
|
|
if (is_hugepage_only_range(mm, addr, len))
|
|
return -EINVAL;
|
|
return addr;
|
|
}
|
|
|
|
#ifdef CONFIG_HUGETLB_PAGE
|
|
if (REGION_NUMBER(addr) == RGN_HPAGE)
|
|
addr = 0;
|
|
#endif
|
|
if (!addr)
|
|
addr = mm->free_area_cache;
|
|
|
|
if (map_shared && (TASK_SIZE > 0xfffffffful))
|
|
/*
|
|
* For 64-bit tasks, align shared segments to 1MB to avoid potential
|
|
* performance penalty due to virtual aliasing (see ASDM). For 32-bit
|
|
* tasks, we prefer to avoid exhausting the address space too quickly by
|
|
* limiting alignment to a single page.
|
|
*/
|
|
align_mask = SHMLBA - 1;
|
|
|
|
full_search:
|
|
start_addr = addr = (addr + align_mask) & ~align_mask;
|
|
|
|
for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
|
|
/* At this point: (!vma || addr < vma->vm_end). */
|
|
if (TASK_SIZE - len < addr || RGN_MAP_LIMIT - len < REGION_OFFSET(addr)) {
|
|
if (start_addr != TASK_UNMAPPED_BASE) {
|
|
/* Start a new search --- just in case we missed some holes. */
|
|
addr = TASK_UNMAPPED_BASE;
|
|
goto full_search;
|
|
}
|
|
return -ENOMEM;
|
|
}
|
|
if (!vma || addr + len <= vma->vm_start) {
|
|
/* Remember the address where we stopped this search: */
|
|
mm->free_area_cache = addr + len;
|
|
return addr;
|
|
}
|
|
addr = (vma->vm_end + align_mask) & ~align_mask;
|
|
}
|
|
}
|
|
|
|
asmlinkage long
|
|
ia64_getpriority (int which, int who)
|
|
{
|
|
long prio;
|
|
|
|
prio = sys_getpriority(which, who);
|
|
if (prio >= 0) {
|
|
force_successful_syscall_return();
|
|
prio = 20 - prio;
|
|
}
|
|
return prio;
|
|
}
|
|
|
|
/* XXX obsolete, but leave it here until the old libc is gone... */
|
|
asmlinkage unsigned long
|
|
sys_getpagesize (void)
|
|
{
|
|
return PAGE_SIZE;
|
|
}
|
|
|
|
asmlinkage unsigned long
|
|
ia64_brk (unsigned long brk)
|
|
{
|
|
unsigned long rlim, retval, newbrk, oldbrk;
|
|
struct mm_struct *mm = current->mm;
|
|
|
|
/*
|
|
* Most of this replicates the code in sys_brk() except for an additional safety
|
|
* check and the clearing of r8. However, we can't call sys_brk() because we need
|
|
* to acquire the mmap_sem before we can do the test...
|
|
*/
|
|
down_write(&mm->mmap_sem);
|
|
|
|
if (brk < mm->end_code)
|
|
goto out;
|
|
newbrk = PAGE_ALIGN(brk);
|
|
oldbrk = PAGE_ALIGN(mm->brk);
|
|
if (oldbrk == newbrk)
|
|
goto set_brk;
|
|
|
|
/* Always allow shrinking brk. */
|
|
if (brk <= mm->brk) {
|
|
if (!do_munmap(mm, newbrk, oldbrk-newbrk))
|
|
goto set_brk;
|
|
goto out;
|
|
}
|
|
|
|
/* Check against unimplemented/unmapped addresses: */
|
|
if ((newbrk - oldbrk) > RGN_MAP_LIMIT || REGION_OFFSET(newbrk) > RGN_MAP_LIMIT)
|
|
goto out;
|
|
|
|
/* Check against rlimit.. */
|
|
rlim = current->signal->rlim[RLIMIT_DATA].rlim_cur;
|
|
if (rlim < RLIM_INFINITY && brk - mm->start_data > rlim)
|
|
goto out;
|
|
|
|
/* Check against existing mmap mappings. */
|
|
if (find_vma_intersection(mm, oldbrk, newbrk+PAGE_SIZE))
|
|
goto out;
|
|
|
|
/* Ok, looks good - let it rip. */
|
|
if (do_brk(oldbrk, newbrk-oldbrk) != oldbrk)
|
|
goto out;
|
|
set_brk:
|
|
mm->brk = brk;
|
|
out:
|
|
retval = mm->brk;
|
|
up_write(&mm->mmap_sem);
|
|
force_successful_syscall_return();
|
|
return retval;
|
|
}
|
|
|
|
/*
|
|
* On IA-64, we return the two file descriptors in ret0 and ret1 (r8
|
|
* and r9) as this is faster than doing a copy_to_user().
|
|
*/
|
|
asmlinkage long
|
|
sys_pipe (void)
|
|
{
|
|
struct pt_regs *regs = task_pt_regs(current);
|
|
int fd[2];
|
|
int retval;
|
|
|
|
retval = do_pipe_flags(fd, 0);
|
|
if (retval)
|
|
goto out;
|
|
retval = fd[0];
|
|
regs->r9 = fd[1];
|
|
out:
|
|
return retval;
|
|
}
|
|
|
|
int ia64_mmap_check(unsigned long addr, unsigned long len,
|
|
unsigned long flags)
|
|
{
|
|
unsigned long roff;
|
|
|
|
/*
|
|
* Don't permit mappings into unmapped space, the virtual page table
|
|
* of a region, or across a region boundary. Note: RGN_MAP_LIMIT is
|
|
* equal to 2^n-PAGE_SIZE (for some integer n <= 61) and len > 0.
|
|
*/
|
|
roff = REGION_OFFSET(addr);
|
|
if ((len > RGN_MAP_LIMIT) || (roff > (RGN_MAP_LIMIT - len)))
|
|
return -EINVAL;
|
|
return 0;
|
|
}
|
|
|
|
static inline unsigned long
|
|
do_mmap2 (unsigned long addr, unsigned long len, int prot, int flags, int fd, unsigned long pgoff)
|
|
{
|
|
struct file *file = NULL;
|
|
|
|
flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
|
|
if (!(flags & MAP_ANONYMOUS)) {
|
|
file = fget(fd);
|
|
if (!file)
|
|
return -EBADF;
|
|
|
|
if (!file->f_op || !file->f_op->mmap) {
|
|
addr = -ENODEV;
|
|
goto out;
|
|
}
|
|
}
|
|
|
|
/* Careful about overflows.. */
|
|
len = PAGE_ALIGN(len);
|
|
if (!len || len > TASK_SIZE) {
|
|
addr = -EINVAL;
|
|
goto out;
|
|
}
|
|
|
|
down_write(¤t->mm->mmap_sem);
|
|
addr = do_mmap_pgoff(file, addr, len, prot, flags, pgoff);
|
|
up_write(¤t->mm->mmap_sem);
|
|
|
|
out: if (file)
|
|
fput(file);
|
|
return addr;
|
|
}
|
|
|
|
/*
|
|
* mmap2() is like mmap() except that the offset is expressed in units
|
|
* of PAGE_SIZE (instead of bytes). This allows to mmap2() (pieces
|
|
* of) files that are larger than the address space of the CPU.
|
|
*/
|
|
asmlinkage unsigned long
|
|
sys_mmap2 (unsigned long addr, unsigned long len, int prot, int flags, int fd, long pgoff)
|
|
{
|
|
addr = do_mmap2(addr, len, prot, flags, fd, pgoff);
|
|
if (!IS_ERR((void *) addr))
|
|
force_successful_syscall_return();
|
|
return addr;
|
|
}
|
|
|
|
asmlinkage unsigned long
|
|
sys_mmap (unsigned long addr, unsigned long len, int prot, int flags, int fd, long off)
|
|
{
|
|
if (offset_in_page(off) != 0)
|
|
return -EINVAL;
|
|
|
|
addr = do_mmap2(addr, len, prot, flags, fd, off >> PAGE_SHIFT);
|
|
if (!IS_ERR((void *) addr))
|
|
force_successful_syscall_return();
|
|
return addr;
|
|
}
|
|
|
|
asmlinkage unsigned long
|
|
ia64_mremap (unsigned long addr, unsigned long old_len, unsigned long new_len, unsigned long flags,
|
|
unsigned long new_addr)
|
|
{
|
|
extern unsigned long do_mremap (unsigned long addr,
|
|
unsigned long old_len,
|
|
unsigned long new_len,
|
|
unsigned long flags,
|
|
unsigned long new_addr);
|
|
|
|
down_write(¤t->mm->mmap_sem);
|
|
{
|
|
addr = do_mremap(addr, old_len, new_len, flags, new_addr);
|
|
}
|
|
up_write(¤t->mm->mmap_sem);
|
|
|
|
if (IS_ERR((void *) addr))
|
|
return addr;
|
|
|
|
force_successful_syscall_return();
|
|
return addr;
|
|
}
|
|
|
|
#ifndef CONFIG_PCI
|
|
|
|
asmlinkage long
|
|
sys_pciconfig_read (unsigned long bus, unsigned long dfn, unsigned long off, unsigned long len,
|
|
void *buf)
|
|
{
|
|
return -ENOSYS;
|
|
}
|
|
|
|
asmlinkage long
|
|
sys_pciconfig_write (unsigned long bus, unsigned long dfn, unsigned long off, unsigned long len,
|
|
void *buf)
|
|
{
|
|
return -ENOSYS;
|
|
}
|
|
|
|
#endif /* CONFIG_PCI */
|