[PATCH RFC] pidns: introduce syscall getvpid

[Eric W. Biederman]

Konstantin Khlebnikov <khlebnikov at yandex-team.ru> writes:

> pid_t getvpid(pid_t pid, pid_t source, pid_t target);
>
> This syscall converts pid from one pid-ns into pid in another pid-ns:
> it takes @pid in namespace of @source task (zero for current) and
> returns related pid in namespace of @target task (zero for current too).
> If pid is unreachable from target pid-ns then it returns zero.

This interface as presented is inherently racy.  It would be better
if source and target were file descriptors referring to the namespaces
you wish to translate between.

> Such conversion is required for interaction between processes from
> different pid-namespaces. For example when system service talks with
> client from isolated container via socket about task in container:

Sockets are already supported.  At least the metadata of sockets is.

Maybe we need this but I am not convinced of it's utility. 

What are you trying to do that motivates this?

Eric


> getvpid(pid, client_pid, 0)  -> pid in our pid namespace
> getvpid(pid, 0, client_pid)  -> pid in client pid namespace
>
> Also service can get pid of init task and match it with container:
>
> getvpid(1, client_pid, 0)    -> pid of init task for client_pid
>
> Seems like gdb and strace could use this too for converting pids of
> newly forked tasks (IIRR they get pid from %rax) into pid from
> correct namespace for further interaction.
>
> As a bonus syscall getvpid can compare pid namespaces and
> test isolation without mounted procfs:
>
> getvpid(1, 0, pid) == 0      -> pid in our sub-pid-namespace
> getvpid(1, 0, pid) == 1      -> pid in our pid-namespace
> getvpid(1, pid1, pid2) == 0  -> pid1 isolated from pid2
> getvpid(1, pid1, pid2) == 1  -> tasks are in one pid-namespace
> getvpid(1, pid1, pid2) > 1   -> pid1 is in sub-pidns of pid2
>
> Signed-off-by: Konstantin Khlebnikov <khlebnikov at yandex-team.ru>
> ---
>  arch/x86/entry/syscalls/syscall_32.tbl |    1 +
>  arch/x86/entry/syscalls/syscall_64.tbl |    1 +
>  include/linux/syscalls.h               |    1 +
>  kernel/pid.c                           |   36 ++++++++++++++++++++++++++++++++
>  4 files changed, 39 insertions(+)
>
> diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
> index 7663c455b9f6..dadb55d42fc9 100644
> --- a/arch/x86/entry/syscalls/syscall_32.tbl
> +++ b/arch/x86/entry/syscalls/syscall_32.tbl
> @@ -382,3 +382,4 @@
>  373	i386	shutdown		sys_shutdown
>  374	i386	userfaultfd		sys_userfaultfd
>  375	i386	membarrier		sys_membarrier
> +376	i386	getvpid			sys_getvpid
> diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
> index 278842fdf1f6..0338f2eb3b7c 100644
> --- a/arch/x86/entry/syscalls/syscall_64.tbl
> +++ b/arch/x86/entry/syscalls/syscall_64.tbl
> @@ -331,6 +331,7 @@
>  322	64	execveat		stub_execveat
>  323	common	userfaultfd		sys_userfaultfd
>  324	common	membarrier		sys_membarrier
> +325	common	getvpid			sys_getvpid
>  
>  #
>  # x32-specific system call numbers start at 512 to avoid cache impact
> diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
> index a460e2ef2843..3405c30999e3 100644
> --- a/include/linux/syscalls.h
> +++ b/include/linux/syscalls.h
> @@ -222,6 +222,7 @@ asmlinkage long sys_nanosleep(struct timespec __user *rqtp, struct timespec __us
>  asmlinkage long sys_alarm(unsigned int seconds);
>  asmlinkage long sys_getpid(void);
>  asmlinkage long sys_getppid(void);
> +asmlinkage long sys_getvpid(pid_t pid, pid_t source, pid_t target);
>  asmlinkage long sys_getuid(void);
>  asmlinkage long sys_geteuid(void);
>  asmlinkage long sys_getgid(void);
> diff --git a/kernel/pid.c b/kernel/pid.c
> index ca368793808e..caa676ff7364 100644
> --- a/kernel/pid.c
> +++ b/kernel/pid.c
> @@ -567,6 +567,42 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
>  	return pid;
>  }
>  
> +/**
> + * sys_getvpid - convert pid from one pid-namespace into pid from another
> + *
> + * @pid    - pid of requested task
> + * @source - pid of task in source pid-namespace, zero for current
> + * @target - pid of task in target pid-namespace, zero for current
> + *
> + * Returns pid from target pid-ns or zero if pid is unreachable.
> + * Returns -ESRCH if some of pids are not found.
> + */
> +SYSCALL_DEFINE3(getvpid, pid_t, pid, pid_t, source, pid_t, target)
> +{
> +#ifdef CONFIG_PID_NS
> +	struct pid_namespace *current_ns = task_active_pid_ns(current);
> +	struct pid_namespace *source_ns = current_ns, *target_ns = current_ns;
> +	struct pid *task_pid;
> +	pid_t result = -ESRCH;
> +
> +	rcu_read_lock();
> +	if (source)
> +		source_ns = ns_of_pid(find_pid_ns(source, current_ns));
> +	if (target)
> +		target_ns = ns_of_pid(find_pid_ns(target, current_ns));
> +	if (source_ns && target_ns) {
> +		task_pid = find_pid_ns(pid, source_ns);
> +		if (task_pid)
> +			result = pid_nr_ns(task_pid, target_ns);
> +	}
> +	rcu_read_unlock();
> +
> +	return result;
> +#else
> +	return pid;
> +#endif /* CONFIG_PID_NS */
> +}
> +
>  /*
>   * The pid hash table is scaled according to the amount of memory in the
>   * machine.  From a minimum of 16 slots up to 4096 slots at one gigabyte or