linux_dsm_epyc7002/include/linux/pid.h
Christian Brauner b3e5838252
clone: add CLONE_PIDFD
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>
2019-05-07 14:31:03 +02:00

196 lines
5.7 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_PID_H
#define _LINUX_PID_H
#include <linux/rculist.h>
enum pid_type
{
PIDTYPE_PID,
PIDTYPE_TGID,
PIDTYPE_PGID,
PIDTYPE_SID,
PIDTYPE_MAX,
};
/*
* What is struct pid?
*
* A struct pid is the kernel's internal notion of a process identifier.
* It refers to individual tasks, process groups, and sessions. While
* there are processes attached to it the struct pid lives in a hash
* table, so it and then the processes that it refers to can be found
* quickly from the numeric pid value. The attached processes may be
* quickly accessed by following pointers from struct pid.
*
* Storing pid_t values in the kernel and referring to them later has a
* problem. The process originally with that pid may have exited and the
* pid allocator wrapped, and another process could have come along
* and been assigned that pid.
*
* Referring to user space processes by holding a reference to struct
* task_struct has a problem. When the user space process exits
* the now useless task_struct is still kept. A task_struct plus a
* stack consumes around 10K of low kernel memory. More precisely
* this is THREAD_SIZE + sizeof(struct task_struct). By comparison
* a struct pid is about 64 bytes.
*
* Holding a reference to struct pid solves both of these problems.
* It is small so holding a reference does not consume a lot of
* resources, and since a new struct pid is allocated when the numeric pid
* value is reused (when pids wrap around) we don't mistakenly refer to new
* processes.
*/
/*
* struct upid is used to get the id of the struct pid, as it is
* seen in particular namespace. Later the struct pid is found with
* find_pid_ns() using the int nr and struct pid_namespace *ns.
*/
struct upid {
int nr;
struct pid_namespace *ns;
};
struct pid
{
atomic_t count;
unsigned int level;
/* lists of tasks that use this pid */
struct hlist_head tasks[PIDTYPE_MAX];
struct rcu_head rcu;
struct upid numbers[1];
};
extern struct pid init_struct_pid;
extern const struct file_operations pidfd_fops;
static inline struct pid *get_pid(struct pid *pid)
{
if (pid)
atomic_inc(&pid->count);
return pid;
}
extern void put_pid(struct pid *pid);
extern struct task_struct *pid_task(struct pid *pid, enum pid_type);
extern struct task_struct *get_pid_task(struct pid *pid, enum pid_type);
extern struct pid *get_task_pid(struct task_struct *task, enum pid_type type);
/*
* these helpers must be called with the tasklist_lock write-held.
*/
extern void attach_pid(struct task_struct *task, enum pid_type);
extern void detach_pid(struct task_struct *task, enum pid_type);
extern void change_pid(struct task_struct *task, enum pid_type,
struct pid *pid);
extern void transfer_pid(struct task_struct *old, struct task_struct *new,
enum pid_type);
struct pid_namespace;
extern struct pid_namespace init_pid_ns;
/*
* look up a PID in the hash table. Must be called with the tasklist_lock
* or rcu_read_lock() held.
*
* find_pid_ns() finds the pid in the namespace specified
* find_vpid() finds the pid by its virtual id, i.e. in the current namespace
*
* see also find_task_by_vpid() set in include/linux/sched.h
*/
extern struct pid *find_pid_ns(int nr, struct pid_namespace *ns);
extern struct pid *find_vpid(int nr);
/*
* Lookup a PID in the hash table, and return with it's count elevated.
*/
extern struct pid *find_get_pid(int nr);
extern struct pid *find_ge_pid(int nr, struct pid_namespace *);
extern struct pid *alloc_pid(struct pid_namespace *ns);
extern void free_pid(struct pid *pid);
extern void disable_pid_allocation(struct pid_namespace *ns);
/*
* ns_of_pid() returns the pid namespace in which the specified pid was
* allocated.
*
* NOTE:
* ns_of_pid() is expected to be called for a process (task) that has
* an attached 'struct pid' (see attach_pid(), detach_pid()) i.e @pid
* is expected to be non-NULL. If @pid is NULL, caller should handle
* the resulting NULL pid-ns.
*/
static inline struct pid_namespace *ns_of_pid(struct pid *pid)
{
struct pid_namespace *ns = NULL;
if (pid)
ns = pid->numbers[pid->level].ns;
return ns;
}
/*
* is_child_reaper returns true if the pid is the init process
* of the current namespace. As this one could be checked before
* pid_ns->child_reaper is assigned in copy_process, we check
* with the pid number.
*/
static inline bool is_child_reaper(struct pid *pid)
{
return pid->numbers[pid->level].nr == 1;
}
/*
* the helpers to get the pid's id seen from different namespaces
*
* pid_nr() : global id, i.e. the id seen from the init namespace;
* pid_vnr() : virtual id, i.e. the id seen from the pid namespace of
* current.
* pid_nr_ns() : id seen from the ns specified.
*
* see also task_xid_nr() etc in include/linux/sched.h
*/
static inline pid_t pid_nr(struct pid *pid)
{
pid_t nr = 0;
if (pid)
nr = pid->numbers[0].nr;
return nr;
}
pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns);
pid_t pid_vnr(struct pid *pid);
#define do_each_pid_task(pid, type, task) \
do { \
if ((pid) != NULL) \
hlist_for_each_entry_rcu((task), \
&(pid)->tasks[type], pid_links[type]) {
/*
* Both old and new leaders may be attached to
* the same pid in the middle of de_thread().
*/
#define while_each_pid_task(pid, type, task) \
if (type == PIDTYPE_PID) \
break; \
} \
} while (0)
#define do_each_pid_thread(pid, type, task) \
do_each_pid_task(pid, type, task) { \
struct task_struct *tg___ = task; \
for_each_thread(tg___, task) {
#define while_each_pid_thread(pid, type, task) \
} \
task = tg___; \
} while_each_pid_task(pid, type, task)
#endif /* _LINUX_PID_H */