mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
b3e5838252
This patchset makes it possible to retrieve pid file descriptors at process creation time by introducing the new flag CLONE_PIDFD to the clone() system call. Linus originally suggested to implement this as a new flag to clone() instead of making it a separate system call. As spotted by Linus, there is exactly one bit for clone() left. CLONE_PIDFD creates file descriptors based on the anonymous inode implementation in the kernel that will also be used to implement the new mount api. They serve as a simple opaque handle on pids. Logically, this makes it possible to interpret a pidfd differently, narrowing or widening the scope of various operations (e.g. signal sending). Thus, a pidfd cannot just refer to a tgid, but also a tid, or in theory - given appropriate flag arguments in relevant syscalls - a process group or session. A pidfd does not represent a privilege. This does not imply it cannot ever be that way but for now this is not the case. A pidfd comes with additional information in fdinfo if the kernel supports procfs. The fdinfo file contains the pid of the process in the callers pid namespace in the same format as the procfs status file, i.e. "Pid:\t%d". As suggested by Oleg, with CLONE_PIDFD the pidfd is returned in the parent_tidptr argument of clone. This has the advantage that we can give back the associated pid and the pidfd at the same time. To remove worries about missing metadata access this patchset comes with a sample program that illustrates how a combination of CLONE_PIDFD, and pidfd_send_signal() can be used to gain race-free access to process metadata through /proc/<pid>. The sample program can easily be translated into a helper that would be suitable for inclusion in libc so that users don't have to worry about writing it themselves. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Christian Brauner <christian@brauner.io> Co-developed-by: Jann Horn <jannh@google.com> Signed-off-by: Jann Horn <jannh@google.com> Reviewed-by: Oleg Nesterov <oleg@redhat.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Kees Cook <keescook@chromium.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: David Howells <dhowells@redhat.com> Cc: "Michael Kerrisk (man-pages)" <mtk.manpages@gmail.com> Cc: Andy Lutomirsky <luto@kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Aleksa Sarai <cyphar@cyphar.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Al Viro <viro@zeniv.linux.org.uk>
60 lines
2.5 KiB
C
60 lines
2.5 KiB
C
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
|
|
#ifndef _UAPI_LINUX_SCHED_H
|
|
#define _UAPI_LINUX_SCHED_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 */
|
|
|
|
/*
|
|
* 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_ALL (SCHED_FLAG_RESET_ON_FORK | \
|
|
SCHED_FLAG_RECLAIM | \
|
|
SCHED_FLAG_DL_OVERRUN)
|
|
|
|
#endif /* _UAPI_LINUX_SCHED_H */
|