mirror of
https://github.com/torvalds/linux.git
synced 2024-12-04 01:51:34 +00:00
8f6ccf6159
-----BEGIN PGP SIGNATURE-----
iHUEABYKAB0WIQRAhzRXHqcMeLMyaSiRxhvAZXjcogUCXSMhhgAKCRCRxhvAZXjc
or7kAP9VzDcQaK/WoDd2ezh2C7Wh5hNy9z/qJVCa6Tb+N+g1UgEAxbhFUg55uGOA
JNf7fGar5JF5hBMIXR+NqOi1/sb4swg=
=ELWo
-----END PGP SIGNATURE-----
Merge tag 'clone3-v5.3' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux
Pull clone3 system call from Christian Brauner:
"This adds the clone3 syscall which is an extensible successor to clone
after we snagged the last flag with CLONE_PIDFD during the 5.2 merge
window for clone(). It cleanly supports all of the flags from clone()
and thus all legacy workloads.
There are few user visible differences between clone3 and clone.
First, CLONE_DETACHED will cause EINVAL with clone3 so we can reuse
this flag. Second, the CSIGNAL flag is deprecated and will cause
EINVAL to be reported. It is superseeded by a dedicated "exit_signal"
argument in struct clone_args thus freeing up even more flags. And
third, clone3 gives CLONE_PIDFD a dedicated return argument in struct
clone_args instead of abusing CLONE_PARENT_SETTID's parent_tidptr
argument.
The clone3 uapi is designed to be easy to handle on 32- and 64 bit:
/* uapi */
struct clone_args {
__aligned_u64 flags;
__aligned_u64 pidfd;
__aligned_u64 child_tid;
__aligned_u64 parent_tid;
__aligned_u64 exit_signal;
__aligned_u64 stack;
__aligned_u64 stack_size;
__aligned_u64 tls;
};
and a separate kernel struct is used that uses proper kernel typing:
/* kernel internal */
struct kernel_clone_args {
u64 flags;
int __user *pidfd;
int __user *child_tid;
int __user *parent_tid;
int exit_signal;
unsigned long stack;
unsigned long stack_size;
unsigned long tls;
};
The system call comes with a size argument which enables the kernel to
detect what version of clone_args userspace is passing in. clone3
validates that any additional bytes a given kernel does not know about
are set to zero and that the size never exceeds a page.
A nice feature is that this patchset allowed us to cleanup and
simplify various core kernel codepaths in kernel/fork.c by making the
internal _do_fork() function take struct kernel_clone_args even for
legacy clone().
This patch also unblocks the time namespace patchset which wants to
introduce a new CLONE_TIMENS flag.
Note, that clone3 has only been wired up for x86{_32,64}, arm{64}, and
xtensa. These were the architectures that did not require special
massaging.
Other architectures treat fork-like system calls individually and
after some back and forth neither Arnd nor I felt confident that we
dared to add clone3 unconditionally to all architectures. We agreed to
leave this up to individual architecture maintainers. This is why
there's an additional patch that introduces __ARCH_WANT_SYS_CLONE3
which any architecture can set once it has implemented support for
clone3. The patch also adds a cond_syscall(clone3) for architectures
such as nios2 or h8300 that generate their syscall table by simply
including asm-generic/unistd.h. The hope is to get rid of
__ARCH_WANT_SYS_CLONE3 and cond_syscall() rather soon"
* tag 'clone3-v5.3' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux:
arch: handle arches who do not yet define clone3
arch: wire-up clone3() syscall
fork: add clone3
67 lines
1.5 KiB
C
67 lines
1.5 KiB
C
/* SPDX-License-Identifier: GPL-2.0-only */
|
|
/*
|
|
* arch/arm/include/asm/unistd.h
|
|
*
|
|
* Copyright (C) 2001-2005 Russell King
|
|
*
|
|
* Please forward _all_ changes to this file to rmk@arm.linux.org.uk,
|
|
* no matter what the change is. Thanks!
|
|
*/
|
|
#ifndef __ASM_ARM_UNISTD_H
|
|
#define __ASM_ARM_UNISTD_H
|
|
|
|
#include <uapi/asm/unistd.h>
|
|
#include <asm/unistd-nr.h>
|
|
|
|
#define __ARCH_WANT_NEW_STAT
|
|
#define __ARCH_WANT_STAT64
|
|
#define __ARCH_WANT_SYS_GETHOSTNAME
|
|
#define __ARCH_WANT_SYS_PAUSE
|
|
#define __ARCH_WANT_SYS_GETPGRP
|
|
#define __ARCH_WANT_SYS_NICE
|
|
#define __ARCH_WANT_SYS_SIGPENDING
|
|
#define __ARCH_WANT_SYS_SIGPROCMASK
|
|
#define __ARCH_WANT_SYS_OLD_MMAP
|
|
#define __ARCH_WANT_SYS_OLD_SELECT
|
|
#define __ARCH_WANT_SYS_UTIME32
|
|
|
|
#if !defined(CONFIG_AEABI) || defined(CONFIG_OABI_COMPAT)
|
|
#define __ARCH_WANT_SYS_TIME32
|
|
#define __ARCH_WANT_SYS_IPC
|
|
#define __ARCH_WANT_SYS_OLDUMOUNT
|
|
#define __ARCH_WANT_SYS_ALARM
|
|
#define __ARCH_WANT_SYS_OLD_GETRLIMIT
|
|
#define __ARCH_WANT_OLD_READDIR
|
|
#define __ARCH_WANT_SYS_SOCKETCALL
|
|
#endif
|
|
#define __ARCH_WANT_SYS_FORK
|
|
#define __ARCH_WANT_SYS_VFORK
|
|
#define __ARCH_WANT_SYS_CLONE
|
|
#define __ARCH_WANT_SYS_CLONE3
|
|
|
|
/*
|
|
* Unimplemented (or alternatively implemented) syscalls
|
|
*/
|
|
#define __IGNORE_fadvise64_64
|
|
|
|
#ifdef __ARM_EABI__
|
|
/*
|
|
* The following syscalls are obsolete and no longer available for EABI:
|
|
* __NR_time
|
|
* __NR_umount
|
|
* __NR_stime
|
|
* __NR_alarm
|
|
* __NR_utime
|
|
* __NR_getrlimit
|
|
* __NR_select
|
|
* __NR_readdir
|
|
* __NR_mmap
|
|
* __NR_socketcall
|
|
* __NR_syscall
|
|
* __NR_ipc
|
|
*/
|
|
#define __IGNORE_getrlimit
|
|
#endif
|
|
|
|
#endif /* __ASM_ARM_UNISTD_H */
|