mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-10-07 17:19:02 +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
87 lines
3.2 KiB
C
87 lines
3.2 KiB
C
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
|
|
#ifndef _UAPI_LINUX_SCHED_H
|
|
#define _UAPI_LINUX_SCHED_H
|
|
|
|
#include <linux/types.h>
|
|
|
|
/*
|
|
* cloning flags:
|
|
*/
|
|
#define CSIGNAL 0x000000ff /* signal mask to be sent at exit */
|
|
#define CLONE_VM 0x00000100 /* set if VM shared between processes */
|
|
#define CLONE_FS 0x00000200 /* set if fs info shared between processes */
|
|
#define CLONE_FILES 0x00000400 /* set if open files shared between processes */
|
|
#define CLONE_SIGHAND 0x00000800 /* set if signal handlers and blocked signals shared */
|
|
#define CLONE_PIDFD 0x00001000 /* set if a pidfd should be placed in parent */
|
|
#define CLONE_PTRACE 0x00002000 /* set if we want to let tracing continue on the child too */
|
|
#define CLONE_VFORK 0x00004000 /* set if the parent wants the child to wake it up on mm_release */
|
|
#define CLONE_PARENT 0x00008000 /* set if we want to have the same parent as the cloner */
|
|
#define CLONE_THREAD 0x00010000 /* Same thread group? */
|
|
#define CLONE_NEWNS 0x00020000 /* New mount namespace group */
|
|
#define CLONE_SYSVSEM 0x00040000 /* share system V SEM_UNDO semantics */
|
|
#define CLONE_SETTLS 0x00080000 /* create a new TLS for the child */
|
|
#define CLONE_PARENT_SETTID 0x00100000 /* set the TID in the parent */
|
|
#define CLONE_CHILD_CLEARTID 0x00200000 /* clear the TID in the child */
|
|
#define CLONE_DETACHED 0x00400000 /* Unused, ignored */
|
|
#define CLONE_UNTRACED 0x00800000 /* set if the tracing process can't force CLONE_PTRACE on this clone */
|
|
#define CLONE_CHILD_SETTID 0x01000000 /* set the TID in the child */
|
|
#define CLONE_NEWCGROUP 0x02000000 /* New cgroup namespace */
|
|
#define CLONE_NEWUTS 0x04000000 /* New utsname namespace */
|
|
#define CLONE_NEWIPC 0x08000000 /* New ipc namespace */
|
|
#define CLONE_NEWUSER 0x10000000 /* New user namespace */
|
|
#define CLONE_NEWPID 0x20000000 /* New pid namespace */
|
|
#define CLONE_NEWNET 0x40000000 /* New network namespace */
|
|
#define CLONE_IO 0x80000000 /* Clone io context */
|
|
|
|
/*
|
|
* Arguments for the clone3 syscall
|
|
*/
|
|
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;
|
|
};
|
|
|
|
/*
|
|
* Scheduling policies
|
|
*/
|
|
#define SCHED_NORMAL 0
|
|
#define SCHED_FIFO 1
|
|
#define SCHED_RR 2
|
|
#define SCHED_BATCH 3
|
|
/* SCHED_ISO: reserved but not implemented yet */
|
|
#define SCHED_IDLE 5
|
|
#define SCHED_DEADLINE 6
|
|
|
|
/* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */
|
|
#define SCHED_RESET_ON_FORK 0x40000000
|
|
|
|
/*
|
|
* For the sched_{set,get}attr() calls
|
|
*/
|
|
#define SCHED_FLAG_RESET_ON_FORK 0x01
|
|
#define SCHED_FLAG_RECLAIM 0x02
|
|
#define SCHED_FLAG_DL_OVERRUN 0x04
|
|
#define SCHED_FLAG_KEEP_POLICY 0x08
|
|
#define SCHED_FLAG_KEEP_PARAMS 0x10
|
|
#define SCHED_FLAG_UTIL_CLAMP_MIN 0x20
|
|
#define SCHED_FLAG_UTIL_CLAMP_MAX 0x40
|
|
|
|
#define SCHED_FLAG_KEEP_ALL (SCHED_FLAG_KEEP_POLICY | \
|
|
SCHED_FLAG_KEEP_PARAMS)
|
|
|
|
#define SCHED_FLAG_UTIL_CLAMP (SCHED_FLAG_UTIL_CLAMP_MIN | \
|
|
SCHED_FLAG_UTIL_CLAMP_MAX)
|
|
|
|
#define SCHED_FLAG_ALL (SCHED_FLAG_RESET_ON_FORK | \
|
|
SCHED_FLAG_RECLAIM | \
|
|
SCHED_FLAG_DL_OVERRUN | \
|
|
SCHED_FLAG_KEEP_ALL | \
|
|
SCHED_FLAG_UTIL_CLAMP)
|
|
|
|
#endif /* _UAPI_LINUX_SCHED_H */
|