mirror of
https://sourceware.org/git/glibc.git
synced 2024-11-23 01:33:36 +08:00
0d6f9f6265
Returning a pidfd allows a process to keep a race-free handle for a
child process, otherwise, the caller will need to either use pidfd_open
(which still might be subject to TOCTOU) or keep the old racy interface
base on pid_t.
To correct use pifd_spawn, the kernel must support not only returning
the pidfd with clone/clone3 but also waitid (P_PIDFD) (added on Linux
5.4). If kernel does not support the waitid, pidfd return ENOSYS.
It avoids the need to racy workarounds, such as reading the procfs
fdinfo to get the pid to use along with other wait interfaces.
These interfaces are similar to the posix_spawn and posix_spawnp, with
the only difference being it returns a process file descriptor (int)
instead of a process ID (pid_t). Their prototypes are:
int pidfd_spawn (int *restrict pidfd,
const char *restrict file,
const posix_spawn_file_actions_t *restrict facts,
const posix_spawnattr_t *restrict attrp,
char *const argv[restrict],
char *const envp[restrict])
int pidfd_spawnp (int *restrict pidfd,
const char *restrict path,
const posix_spawn_file_actions_t *restrict facts,
const posix_spawnattr_t *restrict attrp,
char *const argv[restrict_arr],
char *const envp[restrict_arr]);
A new symbol is used instead of a posix_spawn extension to avoid
possible issues with language bindings that might track the return
argument lifetime. Although on Linux pid_t and int are interchangeable,
POSIX only states that pid_t should be a signed integer.
Both symbols reuse the posix_spawn posix_spawn_file_actions_t and
posix_spawnattr_t, to void rehash posix_spawn API or add a new one. It
also means that both interfaces support the same attribute and file
actions, and a new flag or file action on posix_spawn is also added
automatically for pidfd_spawn.
Also, using posix_spawn plumbing allows the reusing of most of the
current testing with some changes:
- waitid is used instead of waitpid since it is a more generic
interface.
- tst-posix_spawn-setsid.c is adapted to take into consideration that
the caller can check for session id directly. The test now spawns
itself and writes the session id as a file instead.
- tst-spawn3.c need to know where pidfd_spawn is used so it keeps an
extra file description unused.
Checked on x86_64-linux-gnu on Linux 4.15 (no CLONE_PIDFD or waitid
support), Linux 5.4 (full support), and Linux 6.2.
Reviewed-by: Florian Weimer <fweimer@redhat.com>
48 lines
1.8 KiB
C
48 lines
1.8 KiB
C
#ifndef _CLONE_INTERNAL_H
|
|
#define _CLONE_INTERNAL_H
|
|
|
|
#include <clone3.h>
|
|
|
|
/* The clone3 syscall provides a superset of the functionality of the clone
|
|
interface. The kernel might extend __CL_ARGS struct in the future, with
|
|
each version with a different __SIZE. If the child is created, it will
|
|
start __FUNC function with __ARG arguments.
|
|
|
|
Different than kernel, the implementation also returns EINVAL for an
|
|
invalid NULL __CL_ARGS or __FUNC (similar to __clone).
|
|
|
|
All callers are responsible for correctly aligning the stack. The stack is
|
|
not aligned prior to the syscall (this differs from the exported __clone).
|
|
|
|
This function is only implemented if the ABI defines HAVE_CLONE3_WRAPPER.
|
|
*/
|
|
extern int __clone3 (struct clone_args *__cl_args, size_t __size,
|
|
int (*__func) (void *__arg), void *__arg);
|
|
|
|
/* The internal wrapper of clone/clone2 and clone3. Different than __clone3,
|
|
it will align the stack if required. If __clone3 returns -1 with ENOSYS,
|
|
fall back to clone or clone2. */
|
|
extern int __clone_internal (struct clone_args *__cl_args,
|
|
int (*__func) (void *__arg), void *__arg);
|
|
/* clone3 wrapper with a sticky check to avoid re-issuing the syscall if
|
|
it fails with ENOSYS. */
|
|
extern int __clone3_internal (struct clone_args *cl_args,
|
|
int (*func) (void *args), void *arg)
|
|
attribute_hidden;
|
|
/* The fallback code which calls clone/clone2 based on clone3 arguments. */
|
|
extern int __clone_internal_fallback (struct clone_args *__cl_args,
|
|
int (*__func) (void *__arg),
|
|
void *__arg)
|
|
attribute_hidden;
|
|
|
|
/* Return whether the kernel supports pid file descriptor, including clone
|
|
with CLONE_PIDFD and waitid with P_PIDFD. */
|
|
extern bool __clone_pidfd_supported (void) attribute_hidden;
|
|
|
|
#ifndef _ISOMAC
|
|
libc_hidden_proto (__clone3)
|
|
libc_hidden_proto (__clone_internal)
|
|
#endif
|
|
|
|
#endif
|