The rlimit counter is tied to uid in the user_namespace. This allows
rlimit values to be specified in userns even if they are already
globally exceeded by the user. However, the value of the previous
user_namespaces cannot be exceeded.
Changelog
v11:
* Revert most of changes to fix performance issues.
v10:
* Fix memory leak on get_ucounts failure.
Signed-off-by: Alexey Gladkov <legion@kernel.org>
Link: https://lkml.kernel.org/r/df9d7764dddd50f28616b7840de74ec0f81711a8.1619094428.git.legion@kernel.org
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
collect_sigign_sigcatch(p, &ignored, &caught);
num_threads = get_nr_threads(p);
rcu_read_lock(); /* FIXME: is this correct? */
- qsize = atomic_read(&__task_cred(p)->user->sigpending);
+ qsize = get_ucounts_value(task_ucounts(p), UCOUNT_RLIMIT_SIGPENDING);
rcu_read_unlock();
qlim = task_rlimit(p, RLIMIT_SIGPENDING);
unlock_task_sighand(p, &flags);
*/
struct user_struct {
refcount_t __count; /* reference count */
- atomic_t sigpending; /* How many pending signals does this user have? */
#ifdef CONFIG_FANOTIFY
atomic_t fanotify_listeners;
#endif
__SIGINFO;
} kernel_siginfo_t;
+struct ucounts;
+
/*
* Real Time signals may be queued.
*/
struct list_head list;
int flags;
kernel_siginfo_t info;
- struct user_struct *user;
+ struct ucounts *ucounts;
};
/* flags values. */
#endif
UCOUNT_RLIMIT_NPROC,
UCOUNT_RLIMIT_MSGQUEUE,
+ UCOUNT_RLIMIT_SIGPENDING,
UCOUNT_COUNTS,
};
init_user_ns.ucount_max[UCOUNT_RLIMIT_NPROC] = task_rlimit(&init_task, RLIMIT_NPROC);
init_user_ns.ucount_max[UCOUNT_RLIMIT_MSGQUEUE] = task_rlimit(&init_task, RLIMIT_MSGQUEUE);
+ init_user_ns.ucount_max[UCOUNT_RLIMIT_SIGPENDING] = task_rlimit(&init_task, RLIMIT_SIGPENDING);
#ifdef CONFIG_VMAP_STACK
cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache",
__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimit)
{
struct sigqueue *q = NULL;
- struct user_struct *user;
- int sigpending;
+ struct ucounts *ucounts = NULL;
+ long sigpending;
/*
* Protect access to @t credentials. This can go away when all
* changes from/to zero.
*/
rcu_read_lock();
- user = __task_cred(t)->user;
- sigpending = atomic_inc_return(&user->sigpending);
+ ucounts = task_ucounts(t);
+ sigpending = inc_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING, 1);
if (sigpending == 1)
- get_uid(user);
+ ucounts = get_ucounts(ucounts);
rcu_read_unlock();
- if (override_rlimit || likely(sigpending <= task_rlimit(t, RLIMIT_SIGPENDING))) {
+ if (override_rlimit || (sigpending < LONG_MAX && sigpending <= task_rlimit(t, RLIMIT_SIGPENDING))) {
q = kmem_cache_alloc(sigqueue_cachep, flags);
} else {
print_dropped_signal(sig);
}
if (unlikely(q == NULL)) {
- if (atomic_dec_and_test(&user->sigpending))
- free_uid(user);
+ if (ucounts && dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING, 1))
+ put_ucounts(ucounts);
} else {
INIT_LIST_HEAD(&q->list);
q->flags = 0;
- q->user = user;
+ q->ucounts = ucounts;
}
-
return q;
}
{
if (q->flags & SIGQUEUE_PREALLOC)
return;
- if (atomic_dec_and_test(&q->user->sigpending))
- free_uid(q->user);
+ if (q->ucounts && dec_rlimit_ucounts(q->ucounts, UCOUNT_RLIMIT_SIGPENDING, 1)) {
+ put_ucounts(q->ucounts);
+ q->ucounts = NULL;
+ }
kmem_cache_free(sigqueue_cachep, q);
}
#endif
{ },
{ },
+ { },
{ }
};
#endif /* CONFIG_SYSCTL */
/* root_user.__count is 1, for init task cred */
struct user_struct root_user = {
.__count = REFCOUNT_INIT(1),
- .sigpending = ATOMIC_INIT(0),
.locked_shm = 0,
.uid = GLOBAL_ROOT_UID,
.ratelimit = RATELIMIT_STATE_INIT(root_user.ratelimit, 0, 0),
}
ns->ucount_max[UCOUNT_RLIMIT_NPROC] = rlimit(RLIMIT_NPROC);
ns->ucount_max[UCOUNT_RLIMIT_MSGQUEUE] = rlimit(RLIMIT_MSGQUEUE);
+ ns->ucount_max[UCOUNT_RLIMIT_SIGPENDING] = rlimit(RLIMIT_SIGPENDING);
ns->ucounts = ucounts;
/* Inherit USERNS_SETGROUPS_ALLOWED from our parent */