OpenCloudOS-Kernel/samples/pidfd/pidfd-metadata.c

121 lines
2.3 KiB
C
Raw Normal View History

samples: show race-free pidfd metadata access This is a sample program showing userspace how to get race-free access to process metadata from a pidfd. It is rather easy to do and userspace can actually simply reuse code that currently parses a process's status file in procfs. The program can easily be extended into a generic helper suitable for inclusion in a libc to make it even easier for userspace to gain metadata access. Since this came up in a discussion because this API is going to be used in various service managers: A lot of programs will have a whitelist seccomp filter that returns <some-errno> for all new syscalls. This means that programs might get confused if CLONE_PIDFD works but the later pidfd_send_signal() syscall doesn't. Hence, here's a ahead of time check that pidfd_send_signal() is supported: bool pidfd_send_signal_supported() { int procfd = open("/proc/self", O_DIRECTORY | O_RDONLY | O_CLOEXEC); if (procfd < 0) return false; /* * A process is always allowed to signal itself so * pidfd_send_signal() should never fail this test. If it does * it must mean it is not available, blocked by an LSM, seccomp, * or other. */ return pidfd_send_signal(procfd, 0, NULL, 0) == 0; } 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>
2019-04-08 03:18:11 +08:00
// SPDX-License-Identifier: GPL-2.0
#define _GNU_SOURCE
#include <err.h>
#include <errno.h>
#include <fcntl.h>
#include <inttypes.h>
#include <limits.h>
#include <sched.h>
#include <signal.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/stat.h>
#include <sys/syscall.h>
#include <sys/types.h>
#include <sys/wait.h>
#include <unistd.h>
#ifndef CLONE_PIDFD
#define CLONE_PIDFD 0x00001000
#endif
#ifndef __NR_pidfd_send_signal
#define __NR_pidfd_send_signal -1
#endif
samples: show race-free pidfd metadata access This is a sample program showing userspace how to get race-free access to process metadata from a pidfd. It is rather easy to do and userspace can actually simply reuse code that currently parses a process's status file in procfs. The program can easily be extended into a generic helper suitable for inclusion in a libc to make it even easier for userspace to gain metadata access. Since this came up in a discussion because this API is going to be used in various service managers: A lot of programs will have a whitelist seccomp filter that returns <some-errno> for all new syscalls. This means that programs might get confused if CLONE_PIDFD works but the later pidfd_send_signal() syscall doesn't. Hence, here's a ahead of time check that pidfd_send_signal() is supported: bool pidfd_send_signal_supported() { int procfd = open("/proc/self", O_DIRECTORY | O_RDONLY | O_CLOEXEC); if (procfd < 0) return false; /* * A process is always allowed to signal itself so * pidfd_send_signal() should never fail this test. If it does * it must mean it is not available, blocked by an LSM, seccomp, * or other. */ return pidfd_send_signal(procfd, 0, NULL, 0) == 0; } 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>
2019-04-08 03:18:11 +08:00
static int do_child(void *args)
{
printf("%d\n", getpid());
_exit(EXIT_SUCCESS);
}
static pid_t pidfd_clone(int flags, int *pidfd)
{
size_t stack_size = 1024;
char *stack[1024] = { 0 };
#ifdef __ia64__
return __clone2(do_child, stack, stack_size, flags | SIGCHLD, NULL, pidfd);
#else
return clone(do_child, stack + stack_size, flags | SIGCHLD, NULL, pidfd);
#endif
}
static inline int sys_pidfd_send_signal(int pidfd, int sig, siginfo_t *info,
unsigned int flags)
{
return syscall(__NR_pidfd_send_signal, pidfd, sig, info, flags);
}
static int pidfd_metadata_fd(pid_t pid, int pidfd)
{
int procfd, ret;
char path[100];
snprintf(path, sizeof(path), "/proc/%d", pid);
procfd = open(path, O_DIRECTORY | O_RDONLY | O_CLOEXEC);
if (procfd < 0) {
warn("Failed to open %s\n", path);
return -1;
}
/*
* Verify that the pid has not been recycled and our /proc/<pid> handle
* is still valid.
*/
ret = sys_pidfd_send_signal(pidfd, 0, NULL, 0);
if (ret < 0) {
switch (errno) {
case EPERM:
/* Process exists, just not allowed to signal it. */
break;
default:
warn("Failed to signal process\n");
close(procfd);
procfd = -1;
}
}
return procfd;
}
int main(int argc, char *argv[])
{
int pidfd = -1, ret = EXIT_FAILURE;
samples: show race-free pidfd metadata access This is a sample program showing userspace how to get race-free access to process metadata from a pidfd. It is rather easy to do and userspace can actually simply reuse code that currently parses a process's status file in procfs. The program can easily be extended into a generic helper suitable for inclusion in a libc to make it even easier for userspace to gain metadata access. Since this came up in a discussion because this API is going to be used in various service managers: A lot of programs will have a whitelist seccomp filter that returns <some-errno> for all new syscalls. This means that programs might get confused if CLONE_PIDFD works but the later pidfd_send_signal() syscall doesn't. Hence, here's a ahead of time check that pidfd_send_signal() is supported: bool pidfd_send_signal_supported() { int procfd = open("/proc/self", O_DIRECTORY | O_RDONLY | O_CLOEXEC); if (procfd < 0) return false; /* * A process is always allowed to signal itself so * pidfd_send_signal() should never fail this test. If it does * it must mean it is not available, blocked by an LSM, seccomp, * or other. */ return pidfd_send_signal(procfd, 0, NULL, 0) == 0; } 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>
2019-04-08 03:18:11 +08:00
char buf[4096] = { 0 };
pid_t pid;
int procfd, statusfd;
ssize_t bytes;
pid = pidfd_clone(CLONE_PIDFD, &pidfd);
if (pid < 0)
err(ret, "CLONE_PIDFD");
if (pidfd == -1) {
warnx("CLONE_PIDFD is not supported by the kernel");
goto out;
}
samples: show race-free pidfd metadata access This is a sample program showing userspace how to get race-free access to process metadata from a pidfd. It is rather easy to do and userspace can actually simply reuse code that currently parses a process's status file in procfs. The program can easily be extended into a generic helper suitable for inclusion in a libc to make it even easier for userspace to gain metadata access. Since this came up in a discussion because this API is going to be used in various service managers: A lot of programs will have a whitelist seccomp filter that returns <some-errno> for all new syscalls. This means that programs might get confused if CLONE_PIDFD works but the later pidfd_send_signal() syscall doesn't. Hence, here's a ahead of time check that pidfd_send_signal() is supported: bool pidfd_send_signal_supported() { int procfd = open("/proc/self", O_DIRECTORY | O_RDONLY | O_CLOEXEC); if (procfd < 0) return false; /* * A process is always allowed to signal itself so * pidfd_send_signal() should never fail this test. If it does * it must mean it is not available, blocked by an LSM, seccomp, * or other. */ return pidfd_send_signal(procfd, 0, NULL, 0) == 0; } 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>
2019-04-08 03:18:11 +08:00
procfd = pidfd_metadata_fd(pid, pidfd);
close(pidfd);
if (procfd < 0)
goto out;
statusfd = openat(procfd, "status", O_RDONLY | O_CLOEXEC);
close(procfd);
if (statusfd < 0)
goto out;
bytes = read(statusfd, buf, sizeof(buf));
if (bytes > 0)
bytes = write(STDOUT_FILENO, buf, bytes);
close(statusfd);
ret = EXIT_SUCCESS;
out:
(void)wait(NULL);
exit(ret);
}