This adds the pidfd_open() syscall. It allows a caller to retrieve pollable pidfds for a process which did not get created via CLONE_PIDFD, i.e. for a process that is created via traditional fork()/clone() calls that is only referenced by a PID:
int pidfd = pidfd_open(1234, 0); ret = pidfd_send_signal(pidfd, SIGSTOP, NULL, 0);
With the introduction of pidfds through CLONE_PIDFD it is possible to created pidfds at process creation time. However, a lot of processes get created with traditional PID-based calls such as fork() or clone() (without CLONE_PIDFD). For these processes a caller can currently not create a pollable pidfd. This is a problem for Android's low memory killer (LMK) and service managers such as systemd. Both are examples of tools that want to make use of pidfds to get reliable notification of process exit for non-parents (pidfd polling) and race-free signal sending (pidfd_send_signal()). They intend to switch to this API for process supervision/management as soon as possible. Having no way to get pollable pidfds from PID-only processes is one of the biggest blockers for them in adopting this api. With pidfd_open() making it possible to retrieve pidfds for PID-based processes we enable them to adopt this api.
In line with Arnd's recent changes to consolidate syscall numbers across architectures, I have added the pidfd_open() syscall to all architectures at the same time.
Signed-off-by: Christian Brauner christian@brauner.io Reviewed-by: Oleg Nesterov oleg@redhat.com Acked-by: Arnd Bergmann arnd@arndb.de Cc: "Eric W. Biederman" ebiederm@xmission.com Cc: Kees Cook keescook@chromium.org Cc: Joel Fernandes (Google) joel@joelfernandes.org Cc: Thomas Gleixner tglx@linutronix.de Cc: Jann Horn jannh@google.com Cc: David Howells dhowells@redhat.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 Cc: linux-api@vger.kernel.org --- v1: - kbuild test robot lkp@intel.com: - add missing entry for pidfd_open to arch/arm/tools/syscall.tbl - Oleg Nesterov oleg@redhat.com: - use simpler thread-group leader check v2: - Oleg Nesterov oleg@redhat.com: - avoid using additional variable - remove unneeded comment - Arnd Bergmann arnd@arndb.de: - switch from 428 to 434 since the new mount api has taken it - bump syscall numbers in arch/arm64/include/asm/unistd.h - Joel Fernandes (Google) joel@joelfernandes.org: - switch from ESRCH to EINVAL when the passed-in pid does not refer to a thread-group leader - Christian Brauner christian@brauner.io: - rebase on v5.2-rc1 - adapt syscall number to account for new mount api syscalls v3: - Arnd Bergmann arnd@arndb.de: - add missing syscall entries for mips-o32 and mips-n64 --- arch/alpha/kernel/syscalls/syscall.tbl | 1 + arch/arm/tools/syscall.tbl | 1 + arch/arm64/include/asm/unistd.h | 2 +- arch/arm64/include/asm/unistd32.h | 2 + arch/ia64/kernel/syscalls/syscall.tbl | 1 + arch/m68k/kernel/syscalls/syscall.tbl | 1 + arch/microblaze/kernel/syscalls/syscall.tbl | 1 + arch/mips/kernel/syscalls/syscall_n32.tbl | 1 + arch/mips/kernel/syscalls/syscall_n64.tbl | 1 + arch/mips/kernel/syscalls/syscall_o32.tbl | 1 + arch/parisc/kernel/syscalls/syscall.tbl | 1 + arch/powerpc/kernel/syscalls/syscall.tbl | 1 + arch/s390/kernel/syscalls/syscall.tbl | 1 + arch/sh/kernel/syscalls/syscall.tbl | 1 + arch/sparc/kernel/syscalls/syscall.tbl | 1 + arch/x86/entry/syscalls/syscall_32.tbl | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 1 + arch/xtensa/kernel/syscalls/syscall.tbl | 1 + include/linux/pid.h | 1 + include/linux/syscalls.h | 1 + include/uapi/asm-generic/unistd.h | 4 +- kernel/fork.c | 2 +- kernel/pid.c | 43 +++++++++++++++++++++ 23 files changed, 68 insertions(+), 3 deletions(-)
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index 9e7704e44f6d..1db9bbcfb84e 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -473,3 +473,4 @@ 541 common fsconfig sys_fsconfig 542 common fsmount sys_fsmount 543 common fspick sys_fspick +544 common pidfd_open sys_pidfd_open diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index aaf479a9e92d..81e6e1817c45 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -447,3 +447,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 70e6882853c0..e8f7d95a1481 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -44,7 +44,7 @@ #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5) #define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800)
-#define __NR_compat_syscalls 434 +#define __NR_compat_syscalls 435 #endif
#define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index c39e90600bb3..7a3158ccd68e 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -886,6 +886,8 @@ __SYSCALL(__NR_fsconfig, sys_fsconfig) __SYSCALL(__NR_fsmount, sys_fsmount) #define __NR_fspick 433 __SYSCALL(__NR_fspick, sys_fspick) +#define __NR_pidfd_open 434 +__SYSCALL(__NR_pidfd_open, sys_pidfd_open)
/* * Please add new compat syscalls above this comment and update diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl index e01df3f2f80d..ecc44926737b 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -354,3 +354,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 7e3d0734b2f3..9a3eb2558568 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -433,3 +433,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index 26339e417695..ad706f83c755 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -439,3 +439,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 0e2dd68ade57..97035e19ad03 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -372,3 +372,4 @@ 431 n32 fsconfig sys_fsconfig 432 n32 fsmount sys_fsmount 433 n32 fspick sys_fspick +434 n32 pidfd_open sys_pidfd_open diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index 5eebfa0d155c..d7292722d3b0 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -348,3 +348,4 @@ 431 n64 fsconfig sys_fsconfig 432 n64 fsmount sys_fsmount 433 n64 fspick sys_fspick +434 n64 pidfd_open sys_pidfd_open diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 3cc1374e02d0..dba084c92f14 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -421,3 +421,4 @@ 431 o32 fsconfig sys_fsconfig 432 o32 fsmount sys_fsmount 433 o32 fspick sys_fspick +434 o32 pidfd_open sys_pidfd_open diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index c9e377d59232..5022b9e179c2 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -430,3 +430,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 103655d84b4b..f2c3bda2d39f 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -515,3 +515,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index e822b2964a83..6ebacfeaf853 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -436,3 +436,4 @@ 431 common fsconfig sys_fsconfig sys_fsconfig 432 common fsmount sys_fsmount sys_fsmount 433 common fspick sys_fspick sys_fspick +434 common pidfd_open sys_pidfd_open sys_pidfd_open diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index 016a727d4357..834c9c7d79fa 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -436,3 +436,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index e047480b1605..c58e71f21129 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -479,3 +479,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index ad968b7bac72..43e4429a5272 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -438,3 +438,4 @@ 431 i386 fsconfig sys_fsconfig __ia32_sys_fsconfig 432 i386 fsmount sys_fsmount __ia32_sys_fsmount 433 i386 fspick sys_fspick __ia32_sys_fspick +434 i386 pidfd_open sys_pidfd_open __ia32_sys_pidfd_open diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index b4e6f9e6204a..1bee0a77fdd3 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -355,6 +355,7 @@ 431 common fsconfig __x64_sys_fsconfig 432 common fsmount __x64_sys_fsmount 433 common fspick __x64_sys_fspick +434 common pidfd_open __x64_sys_pidfd_open
# # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index 5fa0ee1c8e00..782b81945ccc 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -404,3 +404,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open diff --git a/include/linux/pid.h b/include/linux/pid.h index 3c8ef5a199ca..c938a92eab99 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -67,6 +67,7 @@ struct pid extern struct pid init_struct_pid;
extern const struct file_operations pidfd_fops; +extern int pidfd_create(struct pid *pid);
static inline struct pid *get_pid(struct pid *pid) { diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index e2870fe1be5b..989055e0b501 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -929,6 +929,7 @@ asmlinkage long sys_clock_adjtime32(clockid_t which_clock, struct old_timex32 __user *tx); asmlinkage long sys_syncfs(int fd); asmlinkage long sys_setns(int fd, int nstype); +asmlinkage long sys_pidfd_open(pid_t pid, unsigned int flags); asmlinkage long sys_sendmmsg(int fd, struct mmsghdr __user *msg, unsigned int vlen, unsigned flags); asmlinkage long sys_process_vm_readv(pid_t pid, diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index a87904daf103..e5684a4512c0 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -844,9 +844,11 @@ __SYSCALL(__NR_fsconfig, sys_fsconfig) __SYSCALL(__NR_fsmount, sys_fsmount) #define __NR_fspick 433 __SYSCALL(__NR_fspick, sys_fspick) +#define __NR_pidfd_open 434 +__SYSCALL(__NR_pidfd_open, sys_pidfd_open)
#undef __NR_syscalls -#define __NR_syscalls 434 +#define __NR_syscalls 435
/* * 32 bit systems traditionally used different diff --git a/kernel/fork.c b/kernel/fork.c index b4cba953040a..c3df226f47a1 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1724,7 +1724,7 @@ const struct file_operations pidfd_fops = { * Return: On success, a cloexec pidfd is returned. * On error, a negative errno number will be returned. */ -static int pidfd_create(struct pid *pid) +int pidfd_create(struct pid *pid) { int fd;
diff --git a/kernel/pid.c b/kernel/pid.c index 89548d35eefb..8fc9d94f6ac1 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -37,6 +37,7 @@ #include <linux/syscalls.h> #include <linux/proc_ns.h> #include <linux/proc_fs.h> +#include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/idr.h>
@@ -450,6 +451,48 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns) return idr_get_next(&ns->idr, &nr); }
+/** + * pidfd_open() - Open new pid file descriptor. + * + * @pid: pid for which to retrieve a pidfd + * @flags: flags to pass + * + * This creates a new pid file descriptor with the O_CLOEXEC flag set for + * the process identified by @pid. Currently, the process identified by + * @pid must be a thread-group leader. This restriction currently exists + * for all aspects of pidfds including pidfd creation (CLONE_PIDFD cannot + * be used with CLONE_THREAD) and pidfd polling (only supports thread group + * leaders). + * + * Return: On success, a cloexec pidfd is returned. + * On error, a negative errno number will be returned. + */ +SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags) +{ + int fd, ret; + struct pid *p; + + if (flags) + return -EINVAL; + + if (pid <= 0) + return -EINVAL; + + p = find_get_pid(pid); + if (!p) + return -ESRCH; + + ret = 0; + rcu_read_lock(); + if (!pid_task(p, PIDTYPE_TGID)) + ret = -EINVAL; + rcu_read_unlock(); + + fd = ret ?: pidfd_create(p); + put_pid(p); + return fd; +} + void __init pid_idr_init(void) { /* Verify no one has done anything silly: */
This adds testing for the new pidfd_open() syscalls. Specifically, we test: - that no invalid flags can be passed to pidfd_open() - that no invalid pid can be passed to pidfd_open() - that a pidfd can be retrieved with pidfd_open() - that the retrieved pidfd references the correct pid
Signed-off-by: Christian Brauner christian@brauner.io Cc: Arnd Bergmann arnd@arndb.de Cc: "Eric W. Biederman" ebiederm@xmission.com Cc: Kees Cook keescook@chromium.org Cc: Joel Fernandes (Google) joel@joelfernandes.org Cc: Thomas Gleixner tglx@linutronix.de Cc: Jann Horn jannh@google.com 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: Oleg Nesterov oleg@redhat.com Cc: Aleksa Sarai cyphar@cyphar.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Al Viro viro@zeniv.linux.org.uk Cc: linux-api@vger.kernel.org --- v1: unchanged v2: - Christian Brauner christian@brauner.io: - set number of planned tests via ksft_set_plan() v3: unchanged --- tools/testing/selftests/pidfd/.gitignore | 1 + tools/testing/selftests/pidfd/Makefile | 2 +- tools/testing/selftests/pidfd/pidfd.h | 57 ++++++ .../testing/selftests/pidfd/pidfd_open_test.c | 169 ++++++++++++++++++ tools/testing/selftests/pidfd/pidfd_test.c | 41 +---- 5 files changed, 229 insertions(+), 41 deletions(-) create mode 100644 tools/testing/selftests/pidfd/pidfd.h create mode 100644 tools/testing/selftests/pidfd/pidfd_open_test.c
diff --git a/tools/testing/selftests/pidfd/.gitignore b/tools/testing/selftests/pidfd/.gitignore index 822a1e63d045..16d84d117bc0 100644 --- a/tools/testing/selftests/pidfd/.gitignore +++ b/tools/testing/selftests/pidfd/.gitignore @@ -1 +1,2 @@ +pidfd_open_test pidfd_test diff --git a/tools/testing/selftests/pidfd/Makefile b/tools/testing/selftests/pidfd/Makefile index deaf8073bc06..b36c0be70848 100644 --- a/tools/testing/selftests/pidfd/Makefile +++ b/tools/testing/selftests/pidfd/Makefile @@ -1,6 +1,6 @@ CFLAGS += -g -I../../../../usr/include/
-TEST_GEN_PROGS := pidfd_test +TEST_GEN_PROGS := pidfd_test pidfd_open_test
include ../lib.mk
diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h new file mode 100644 index 000000000000..8452e910463f --- /dev/null +++ b/tools/testing/selftests/pidfd/pidfd.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __PIDFD_H +#define __PIDFD_H + +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <sched.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <syscall.h> +#include <sys/mount.h> + +#include "../kselftest.h" + +/* + * The kernel reserves 300 pids via RESERVED_PIDS in kernel/pid.c + * That means, when it wraps around any pid < 300 will be skipped. + * So we need to use a pid > 300 in order to test recycling. + */ +#define PID_RECYCLE 1000 + +/* + * Define a few custom error codes for the child process to clearly indicate + * what is happening. This way we can tell the difference between a system + * error, a test error, etc. + */ +#define PIDFD_PASS 0 +#define PIDFD_FAIL 1 +#define PIDFD_ERROR 2 +#define PIDFD_SKIP 3 +#define PIDFD_XFAIL 4 + +int wait_for_pid(pid_t pid) +{ + int status, ret; + +again: + ret = waitpid(pid, &status, 0); + if (ret == -1) { + if (errno == EINTR) + goto again; + + return -1; + } + + if (!WIFEXITED(status)) + return -1; + + return WEXITSTATUS(status); +} + + +#endif /* __PIDFD_H */ diff --git a/tools/testing/selftests/pidfd/pidfd_open_test.c b/tools/testing/selftests/pidfd/pidfd_open_test.c new file mode 100644 index 000000000000..0377133dd6dc --- /dev/null +++ b/tools/testing/selftests/pidfd/pidfd_open_test.c @@ -0,0 +1,169 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <inttypes.h> +#include <limits.h> +#include <linux/types.h> +#include <linux/wait.h> +#include <sched.h> +#include <signal.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <syscall.h> +#include <sys/mount.h> +#include <sys/prctl.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "pidfd.h" +#include "../kselftest.h" + +static inline int sys_pidfd_open(pid_t pid, unsigned int flags) +{ + return syscall(__NR_pidfd_open, pid, flags); +} + +static int safe_int(const char *numstr, int *converted) +{ + char *err = NULL; + long sli; + + errno = 0; + sli = strtol(numstr, &err, 0); + if (errno == ERANGE && (sli == LONG_MAX || sli == LONG_MIN)) + return -ERANGE; + + if (errno != 0 && sli == 0) + return -EINVAL; + + if (err == numstr || *err != '\0') + return -EINVAL; + + if (sli > INT_MAX || sli < INT_MIN) + return -ERANGE; + + *converted = (int)sli; + return 0; +} + +static int char_left_gc(const char *buffer, size_t len) +{ + size_t i; + + for (i = 0; i < len; i++) { + if (buffer[i] == ' ' || + buffer[i] == '\t') + continue; + + return i; + } + + return 0; +} + +static int char_right_gc(const char *buffer, size_t len) +{ + int i; + + for (i = len - 1; i >= 0; i--) { + if (buffer[i] == ' ' || + buffer[i] == '\t' || + buffer[i] == '\n' || + buffer[i] == '\0') + continue; + + return i + 1; + } + + return 0; +} + +static char *trim_whitespace_in_place(char *buffer) +{ + buffer += char_left_gc(buffer, strlen(buffer)); + buffer[char_right_gc(buffer, strlen(buffer))] = '\0'; + return buffer; +} + +static pid_t get_pid_from_fdinfo_file(int pidfd, const char *key, size_t keylen) +{ + int ret; + char path[512]; + FILE *f; + size_t n = 0; + pid_t result = -1; + char *line = NULL; + + snprintf(path, sizeof(path), "/proc/self/fdinfo/%d", pidfd); + + f = fopen(path, "re"); + if (!f) + return -1; + + while (getline(&line, &n, f) != -1) { + char *numstr; + + if (strncmp(line, key, keylen)) + continue; + + numstr = trim_whitespace_in_place(line + 4); + ret = safe_int(numstr, &result); + if (ret < 0) + goto out; + + break; + } + +out: + free(line); + fclose(f); + return result; +} + +int main(int argc, char **argv) +{ + int pidfd = -1, ret = 1; + pid_t pid; + + ksft_set_plan(3); + + pidfd = sys_pidfd_open(-1, 0); + if (pidfd >= 0) { + ksft_print_msg( + "%s - succeeded to open pidfd for invalid pid -1\n", + strerror(errno)); + goto on_error; + } + ksft_test_result_pass("do not allow invalid pid test: passed\n"); + + pidfd = sys_pidfd_open(getpid(), 1); + if (pidfd >= 0) { + ksft_print_msg( + "%s - succeeded to open pidfd with invalid flag value specified\n", + strerror(errno)); + goto on_error; + } + ksft_test_result_pass("do not allow invalid flag test: passed\n"); + + pidfd = sys_pidfd_open(getpid(), 0); + if (pidfd < 0) { + ksft_print_msg("%s - failed to open pidfd\n", strerror(errno)); + goto on_error; + } + ksft_test_result_pass("open a new pidfd test: passed\n"); + + pid = get_pid_from_fdinfo_file(pidfd, "Pid:", sizeof("Pid:") - 1); + ksft_print_msg("pidfd %d refers to process with pid %d\n", pidfd, pid); + + ret = 0; + +on_error: + if (pidfd >= 0) + close(pidfd); + + return !ret ? ksft_exit_pass() : ksft_exit_fail(); +} diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c index 5bae1792e3d6..a03387052aa7 100644 --- a/tools/testing/selftests/pidfd/pidfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_test.c @@ -14,6 +14,7 @@ #include <sys/wait.h> #include <unistd.h>
+#include "pidfd.h" #include "../kselftest.h"
static inline int sys_pidfd_send_signal(int pidfd, int sig, siginfo_t *info, @@ -62,28 +63,6 @@ static int test_pidfd_send_signal_simple_success(void) return 0; }
-static int wait_for_pid(pid_t pid) -{ - int status, ret; - -again: - ret = waitpid(pid, &status, 0); - if (ret == -1) { - if (errno == EINTR) - goto again; - - return -1; - } - - if (ret != pid) - goto again; - - if (!WIFEXITED(status)) - return -1; - - return WEXITSTATUS(status); -} - static int test_pidfd_send_signal_exited_fail(void) { int pidfd, ret, saved_errno; @@ -128,13 +107,6 @@ static int test_pidfd_send_signal_exited_fail(void) return 0; }
-/* - * The kernel reserves 300 pids via RESERVED_PIDS in kernel/pid.c - * That means, when it wraps around any pid < 300 will be skipped. - * So we need to use a pid > 300 in order to test recycling. - */ -#define PID_RECYCLE 1000 - /* * Maximum number of cycles we allow. This is equivalent to PID_MAX_DEFAULT. * If users set a higher limit or we have cycled PIDFD_MAX_DEFAULT number of @@ -143,17 +115,6 @@ static int test_pidfd_send_signal_exited_fail(void) */ #define PIDFD_MAX_DEFAULT 0x8000
-/* - * Define a few custom error codes for the child process to clearly indicate - * what is happening. This way we can tell the difference between a system - * error, a test error, etc. - */ -#define PIDFD_PASS 0 -#define PIDFD_FAIL 1 -#define PIDFD_ERROR 2 -#define PIDFD_SKIP 3 -#define PIDFD_XFAIL 4 - static int test_pidfd_send_signal_recycled_pid_fail(void) { int i, ret;
On Mon, May 20, 2019 at 05:56:29PM +0200, Christian Brauner wrote:
This adds the pidfd_open() syscall. It allows a caller to retrieve pollable pidfds for a process which did not get created via CLONE_PIDFD, i.e. for a process that is created via traditional fork()/clone() calls that is only referenced by a PID:
int pidfd = pidfd_open(1234, 0); ret = pidfd_send_signal(pidfd, SIGSTOP, NULL, 0);
With the introduction of pidfds through CLONE_PIDFD it is possible to created pidfds at process creation time. However, a lot of processes get created with traditional PID-based calls such as fork() or clone() (without CLONE_PIDFD). For these processes a caller can currently not create a pollable pidfd. This is a problem for Android's low memory killer (LMK) and service managers such as systemd. Both are examples of tools that want to make use of pidfds to get reliable notification of process exit for non-parents (pidfd polling) and race-free signal sending (pidfd_send_signal()). They intend to switch to this API for process supervision/management as soon as possible. Having no way to get pollable pidfds from PID-only processes is one of the biggest blockers for them in adopting this api. With pidfd_open() making it possible to retrieve pidfds for PID-based processes we enable them to adopt this api.
In line with Arnd's recent changes to consolidate syscall numbers across architectures, I have added the pidfd_open() syscall to all architectures at the same time.
Signed-off-by: Christian Brauner christian@brauner.io Reviewed-by: Oleg Nesterov oleg@redhat.com
This now also carries a Reviewed-by from David.
Acked-by: Arnd Bergmann arnd@arndb.de Cc: "Eric W. Biederman" ebiederm@xmission.com Cc: Kees Cook keescook@chromium.org Cc: Joel Fernandes (Google) joel@joelfernandes.org Cc: Thomas Gleixner tglx@linutronix.de Cc: Jann Horn jannh@google.com Cc: David Howells dhowells@redhat.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 Cc: linux-api@vger.kernel.org
I've moved pidfd_open() into my for-next branch together with Joel's pidfd polling changes. Everything is based on v5.2-rc1.
The chosen syscall number for now is 434. David is going to send out another pile of mount api related syscalls. I'll coordinate with him accordingly prior to the 5.3 merge window.
Thanks! Christian
On Tue, May 21, 2019 at 04:32:20PM +0200, Christian Brauner wrote:
On Mon, May 20, 2019 at 05:56:29PM +0200, Christian Brauner wrote:
This adds the pidfd_open() syscall. It allows a caller to retrieve pollable pidfds for a process which did not get created via CLONE_PIDFD, i.e. for a process that is created via traditional fork()/clone() calls that is only referenced by a PID:
int pidfd = pidfd_open(1234, 0); ret = pidfd_send_signal(pidfd, SIGSTOP, NULL, 0);
With the introduction of pidfds through CLONE_PIDFD it is possible to created pidfds at process creation time. However, a lot of processes get created with traditional PID-based calls such as fork() or clone() (without CLONE_PIDFD). For these processes a caller can currently not create a pollable pidfd. This is a problem for Android's low memory killer (LMK) and service managers such as systemd. Both are examples of tools that want to make use of pidfds to get reliable notification of process exit for non-parents (pidfd polling) and race-free signal sending (pidfd_send_signal()). They intend to switch to this API for process supervision/management as soon as possible. Having no way to get pollable pidfds from PID-only processes is one of the biggest blockers for them in adopting this api. With pidfd_open() making it possible to retrieve pidfds for PID-based processes we enable them to adopt this api.
In line with Arnd's recent changes to consolidate syscall numbers across architectures, I have added the pidfd_open() syscall to all architectures at the same time.
Signed-off-by: Christian Brauner christian@brauner.io Reviewed-by: Oleg Nesterov oleg@redhat.com
This now also carries a Reviewed-by from David.
Acked-by: Arnd Bergmann arnd@arndb.de Cc: "Eric W. Biederman" ebiederm@xmission.com Cc: Kees Cook keescook@chromium.org Cc: Joel Fernandes (Google) joel@joelfernandes.org Cc: Thomas Gleixner tglx@linutronix.de Cc: Jann Horn jannh@google.com Cc: David Howells dhowells@redhat.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 Cc: linux-api@vger.kernel.org
I've moved pidfd_open() into my for-next branch together with Joel's pidfd polling changes. Everything is based on v5.2-rc1.
The chosen syscall number for now is 434. David is going to send out another pile of mount api related syscalls. I'll coordinate with him accordingly prior to the 5.3 merge window.
After talking to Arnd, I split the syscall addition and the per-arch wiring-up of pidfd_open() into two patches. There are no functional changes and everything is still sitting in for-next.
Thanks! Christian
On 20.05.2019 18:56, Christian Brauner wrote:
This adds the pidfd_open() syscall. It allows a caller to retrieve pollable pidfds for a process which did not get created via CLONE_PIDFD, i.e. for a process that is created via traditional fork()/clone() calls that is only referenced by a PID:
int pidfd = pidfd_open(1234, 0); ret = pidfd_send_signal(pidfd, SIGSTOP, NULL, 0);
With the introduction of pidfds through CLONE_PIDFD it is possible to created pidfds at process creation time. However, a lot of processes get created with traditional PID-based calls such as fork() or clone() (without CLONE_PIDFD). For these processes a caller can currently not create a pollable pidfd. This is a problem for Android's low memory killer (LMK) and service managers such as systemd. Both are examples of tools that want to make use of pidfds to get reliable notification of process exit for non-parents (pidfd polling) and race-free signal sending (pidfd_send_signal()). They intend to switch to this API for process supervision/management as soon as possible. Having no way to get pollable pidfds from PID-only processes is one of the biggest blockers for them in adopting this api. With pidfd_open() making it possible to retrieve pidfds for PID-based processes we enable them to adopt this api.
In line with Arnd's recent changes to consolidate syscall numbers across architectures, I have added the pidfd_open() syscall to all architectures at the same time.
As I see pidfd_open() works only within current pid-namespace.
Have you considered separate argument for pidns-fd or flag for opening pid in pid-ns referred by nsproxy->pid_ns_for_children set by setns.
This could be used for use cases I've tried to cover by syscall "translate_pid" https://lkml.org/lkml/2018/6/1/788
Signed-off-by: Christian Brauner christian@brauner.io Reviewed-by: Oleg Nesterov oleg@redhat.com Acked-by: Arnd Bergmann arnd@arndb.de Cc: "Eric W. Biederman" ebiederm@xmission.com Cc: Kees Cook keescook@chromium.org Cc: Joel Fernandes (Google) joel@joelfernandes.org Cc: Thomas Gleixner tglx@linutronix.de Cc: Jann Horn jannh@google.com Cc: David Howells dhowells@redhat.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 Cc: linux-api@vger.kernel.org
v1:
- kbuild test robot lkp@intel.com:
- add missing entry for pidfd_open to arch/arm/tools/syscall.tbl
- Oleg Nesterov oleg@redhat.com:
- use simpler thread-group leader check
v2:
- Oleg Nesterov oleg@redhat.com:
- avoid using additional variable
- remove unneeded comment
- Arnd Bergmann arnd@arndb.de:
- switch from 428 to 434 since the new mount api has taken it
- bump syscall numbers in arch/arm64/include/asm/unistd.h
- Joel Fernandes (Google) joel@joelfernandes.org:
- switch from ESRCH to EINVAL when the passed-in pid does not refer to a thread-group leader
- Christian Brauner christian@brauner.io:
- rebase on v5.2-rc1
- adapt syscall number to account for new mount api syscalls
v3:
- Arnd Bergmann arnd@arndb.de:
- add missing syscall entries for mips-o32 and mips-n64
arch/alpha/kernel/syscalls/syscall.tbl | 1 + arch/arm/tools/syscall.tbl | 1 + arch/arm64/include/asm/unistd.h | 2 +- arch/arm64/include/asm/unistd32.h | 2 + arch/ia64/kernel/syscalls/syscall.tbl | 1 + arch/m68k/kernel/syscalls/syscall.tbl | 1 + arch/microblaze/kernel/syscalls/syscall.tbl | 1 + arch/mips/kernel/syscalls/syscall_n32.tbl | 1 + arch/mips/kernel/syscalls/syscall_n64.tbl | 1 + arch/mips/kernel/syscalls/syscall_o32.tbl | 1 + arch/parisc/kernel/syscalls/syscall.tbl | 1 + arch/powerpc/kernel/syscalls/syscall.tbl | 1 + arch/s390/kernel/syscalls/syscall.tbl | 1 + arch/sh/kernel/syscalls/syscall.tbl | 1 + arch/sparc/kernel/syscalls/syscall.tbl | 1 + arch/x86/entry/syscalls/syscall_32.tbl | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 1 + arch/xtensa/kernel/syscalls/syscall.tbl | 1 + include/linux/pid.h | 1 + include/linux/syscalls.h | 1 + include/uapi/asm-generic/unistd.h | 4 +- kernel/fork.c | 2 +- kernel/pid.c | 43 +++++++++++++++++++++ 23 files changed, 68 insertions(+), 3 deletions(-)
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index 9e7704e44f6d..1db9bbcfb84e 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -473,3 +473,4 @@ 541 common fsconfig sys_fsconfig 542 common fsmount sys_fsmount 543 common fspick sys_fspick +544 common pidfd_open sys_pidfd_open diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index aaf479a9e92d..81e6e1817c45 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -447,3 +447,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 70e6882853c0..e8f7d95a1481 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -44,7 +44,7 @@ #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5) #define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800) -#define __NR_compat_syscalls 434 +#define __NR_compat_syscalls 435 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index c39e90600bb3..7a3158ccd68e 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -886,6 +886,8 @@ __SYSCALL(__NR_fsconfig, sys_fsconfig) __SYSCALL(__NR_fsmount, sys_fsmount) #define __NR_fspick 433 __SYSCALL(__NR_fspick, sys_fspick) +#define __NR_pidfd_open 434 +__SYSCALL(__NR_pidfd_open, sys_pidfd_open) /*
- Please add new compat syscalls above this comment and update
diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl index e01df3f2f80d..ecc44926737b 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -354,3 +354,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 7e3d0734b2f3..9a3eb2558568 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -433,3 +433,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index 26339e417695..ad706f83c755 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -439,3 +439,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 0e2dd68ade57..97035e19ad03 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -372,3 +372,4 @@ 431 n32 fsconfig sys_fsconfig 432 n32 fsmount sys_fsmount 433 n32 fspick sys_fspick +434 n32 pidfd_open sys_pidfd_open diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index 5eebfa0d155c..d7292722d3b0 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -348,3 +348,4 @@ 431 n64 fsconfig sys_fsconfig 432 n64 fsmount sys_fsmount 433 n64 fspick sys_fspick +434 n64 pidfd_open sys_pidfd_open diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 3cc1374e02d0..dba084c92f14 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -421,3 +421,4 @@ 431 o32 fsconfig sys_fsconfig 432 o32 fsmount sys_fsmount 433 o32 fspick sys_fspick +434 o32 pidfd_open sys_pidfd_open diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index c9e377d59232..5022b9e179c2 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -430,3 +430,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 103655d84b4b..f2c3bda2d39f 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -515,3 +515,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index e822b2964a83..6ebacfeaf853 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -436,3 +436,4 @@ 431 common fsconfig sys_fsconfig sys_fsconfig 432 common fsmount sys_fsmount sys_fsmount 433 common fspick sys_fspick sys_fspick +434 common pidfd_open sys_pidfd_open sys_pidfd_open diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index 016a727d4357..834c9c7d79fa 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -436,3 +436,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index e047480b1605..c58e71f21129 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -479,3 +479,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index ad968b7bac72..43e4429a5272 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -438,3 +438,4 @@ 431 i386 fsconfig sys_fsconfig __ia32_sys_fsconfig 432 i386 fsmount sys_fsmount __ia32_sys_fsmount 433 i386 fspick sys_fspick __ia32_sys_fspick +434 i386 pidfd_open sys_pidfd_open __ia32_sys_pidfd_open diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index b4e6f9e6204a..1bee0a77fdd3 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -355,6 +355,7 @@ 431 common fsconfig __x64_sys_fsconfig 432 common fsmount __x64_sys_fsmount 433 common fspick __x64_sys_fspick +434 common pidfd_open __x64_sys_pidfd_open # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index 5fa0ee1c8e00..782b81945ccc 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -404,3 +404,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open diff --git a/include/linux/pid.h b/include/linux/pid.h index 3c8ef5a199ca..c938a92eab99 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -67,6 +67,7 @@ struct pid extern struct pid init_struct_pid; extern const struct file_operations pidfd_fops; +extern int pidfd_create(struct pid *pid); static inline struct pid *get_pid(struct pid *pid) { diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index e2870fe1be5b..989055e0b501 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -929,6 +929,7 @@ asmlinkage long sys_clock_adjtime32(clockid_t which_clock, struct old_timex32 __user *tx); asmlinkage long sys_syncfs(int fd); asmlinkage long sys_setns(int fd, int nstype); +asmlinkage long sys_pidfd_open(pid_t pid, unsigned int flags); asmlinkage long sys_sendmmsg(int fd, struct mmsghdr __user *msg, unsigned int vlen, unsigned flags); asmlinkage long sys_process_vm_readv(pid_t pid, diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index a87904daf103..e5684a4512c0 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -844,9 +844,11 @@ __SYSCALL(__NR_fsconfig, sys_fsconfig) __SYSCALL(__NR_fsmount, sys_fsmount) #define __NR_fspick 433 __SYSCALL(__NR_fspick, sys_fspick) +#define __NR_pidfd_open 434 +__SYSCALL(__NR_pidfd_open, sys_pidfd_open) #undef __NR_syscalls -#define __NR_syscalls 434 +#define __NR_syscalls 435 /*
- 32 bit systems traditionally used different
diff --git a/kernel/fork.c b/kernel/fork.c index b4cba953040a..c3df226f47a1 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1724,7 +1724,7 @@ const struct file_operations pidfd_fops = {
- Return: On success, a cloexec pidfd is returned.
On error, a negative errno number will be returned.
*/ -static int pidfd_create(struct pid *pid) +int pidfd_create(struct pid *pid) { int fd; diff --git a/kernel/pid.c b/kernel/pid.c index 89548d35eefb..8fc9d94f6ac1 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -37,6 +37,7 @@ #include <linux/syscalls.h> #include <linux/proc_ns.h> #include <linux/proc_fs.h> +#include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/idr.h> @@ -450,6 +451,48 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns) return idr_get_next(&ns->idr, &nr); } +/**
- pidfd_open() - Open new pid file descriptor.
- @pid: pid for which to retrieve a pidfd
- @flags: flags to pass
- This creates a new pid file descriptor with the O_CLOEXEC flag set for
- the process identified by @pid. Currently, the process identified by
- @pid must be a thread-group leader. This restriction currently exists
- for all aspects of pidfds including pidfd creation (CLONE_PIDFD cannot
- be used with CLONE_THREAD) and pidfd polling (only supports thread group
- leaders).
- Return: On success, a cloexec pidfd is returned.
On error, a negative errno number will be returned.
- */
+SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags) +{
- int fd, ret;
- struct pid *p;
- if (flags)
return -EINVAL;
- if (pid <= 0)
return -EINVAL;
- p = find_get_pid(pid);
- if (!p)
return -ESRCH;
- ret = 0;
- rcu_read_lock();
- if (!pid_task(p, PIDTYPE_TGID))
ret = -EINVAL;
- rcu_read_unlock();
- fd = ret ?: pidfd_create(p);
- put_pid(p);
- return fd;
+}
- void __init pid_idr_init(void) { /* Verify no one has done anything silly: */
linux-kselftest-mirror@lists.linaro.org