On 08/11, Adrian Reber wrote:
>
> include/linux/pid.h | 2 +-
> include/linux/sched/task.h | 1 +
> include/uapi/linux/sched.h | 1 +
> kernel/fork.c | 22 ++++++++++++++++++++--
> kernel/pid.c | 36 +++++++++++++++++++++++++++++-------
> 5 files changed, 52 insertions(+), 10 deletions(-)
Looks good to me...
A couple of nits below, but I won't insist, feel free to ignore.
> +/*
> + * Different sizes of struct clone_args
> + */
> +#define CLONE3_ARGS_SIZE_V0 64
I don't really understand why do we want the "size < CLONE3_ARGS_SIZE_V0"
check in copy_clone_args_from_user(), but I won't argue.
> +/* V1 includes set_tid */
> +#define CLONE3_ARGS_SIZE_V1 72
unused?
> @@ -2031,7 +2038,13 @@ static __latent_entropy struct task_struct
> *copy_process(
> stackleak_task_init(p);
>
> if (pid != &init_struct_pid) {
> - pid = alloc_pid(p->nsproxy->pid_ns_for_children);
> + if (args->set_tid && !ns_capable(
> + p->nsproxy->pid_ns_for_children->user_ns,
> + CAP_SYS_ADMIN)) {
> + retval = -EPERM;
> + goto bad_fork_cleanup_thread;
> + }
> + pid = alloc_pid(p->nsproxy->pid_ns_for_children, args->set_tid);
copy_process() is already huge and complex, why not move this check into
alloc_pid() ? Again, note that is accepts the same ->pid_ns_for_children.
> @@ -166,6 +166,9 @@ struct pid *alloc_pid(struct pid_namespace *ns)
> struct upid *upid;
> int retval = -ENOMEM;
>
> + if (set_tid < 0 || set_tid >= pid_max)
> + return ERR_PTR(-EINVAL);
> +
> pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL);
> if (!pid)
> return ERR_PTR(retval);
> @@ -186,12 +189,31 @@ struct pid *alloc_pid(struct pid_namespace *ns)
> if (idr_get_cursor(&tmp->idr) > RESERVED_PIDS)
> pid_min = RESERVED_PIDS;
>
> - /*
> - * Store a null pointer so find_pid_ns does not find
> - * a partially initialized PID (see below).
> - */
> - nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min,
> - pid_max, GFP_ATOMIC);
> + if (set_tid) {
> + /*
> + * Also fail if a PID != 1 is requested
> + * and no PID 1 exists.
> + */
> + nr = -EINVAL;
> + if (set_tid == 1 || !idr_is_empty(&tmp->idr))
On the second thought, I think we should check ns->child_reaper != NULL
rather than !idr_is_empty(), this looks more robust and clean.
And this way alloc_pid() can do everything lockless at the start,
if (set_tid) {
if (set_tid < 0 || set_tid >= pid_max)
return ERR_PTR(-EINVAL);
if (set_tid != 1 && !ns->child_reaper)
return ERR_PTR(-EINVAL);
if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN))
return ERR_PTR(-EPERM);
}
and just for record... this is off-topic and I need to recheck, but
today "ns->pid_allocated = 0" in free_pid() doesn't look right to me...
This logic predates unshare(CLONE_PIDNS).
Oleg.
