1 files changed, 129 insertions, 138 deletions

diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 4576aaed13b2..881a9ce96af7 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -233,11 +233,12 @@ __initcall(init_posix_timers);
  * The siginfo si_overrun field and the return value of timer_getoverrun(2)
  * are of type int. Clamp the overrun value to INT_MAX
  */
-static inline int timer_overrun_to_int(struct k_itimer *timr, int baseval)
+static inline int timer_overrun_to_int(struct k_itimer *timr)
 {
-	s64 sum = timr->it_overrun_last + (s64)baseval;
+	if (timr->it_overrun_last > (s64)INT_MAX)
+		return INT_MAX;
 
-	return sum > (s64)INT_MAX ? INT_MAX : (int)sum;
+	return (int)timr->it_overrun_last;
 }
 
 static void common_hrtimer_rearm(struct k_itimer *timr)
@@ -249,62 +250,62 @@ static void common_hrtimer_rearm(struct k_itimer *timr)
 	hrtimer_restart(timer);
 }
 
+static bool __posixtimer_deliver_signal(struct kernel_siginfo *info, struct k_itimer *timr)
+{
+	guard(spinlock)(&timr->it_lock);
+
+	/*
+	 * Check if the timer is still alive or whether it got modified
+	 * since the signal was queued. In either case, don't rearm and
+	 * drop the signal.
+	 */
+	if (timr->it_signal_seq != timr->it_sigqueue_seq || WARN_ON_ONCE(!timr->it_signal))
+		return false;
+
+	if (!timr->it_interval || WARN_ON_ONCE(timr->it_status != POSIX_TIMER_REQUEUE_PENDING))
+		return true;
+
+	timr->kclock->timer_rearm(timr);
+	timr->it_status = POSIX_TIMER_ARMED;
+	timr->it_overrun_last = timr->it_overrun;
+	timr->it_overrun = -1LL;
+	++timr->it_signal_seq;
+	info->si_overrun = timer_overrun_to_int(timr);
+	return true;
+}
+
 /*
- * This function is called from the signal delivery code if
- * info->si_sys_private is not zero, which indicates that the timer has to
- * be rearmed. Restart the timer and update info::si_overrun.
+ * This function is called from the signal delivery code. It decides
+ * whether the signal should be dropped and rearms interval timers.  The
+ * timer can be unconditionally accessed as there is a reference held on
+ * it.
  */
-void posixtimer_rearm(struct kernel_siginfo *info)
+bool posixtimer_deliver_signal(struct kernel_siginfo *info, struct sigqueue *timer_sigq)
 {
-	struct k_itimer *timr;
-	unsigned long flags;
-
-	timr = lock_timer(info->si_tid, &flags);
-	if (!timr)
-		return;
+	struct k_itimer *timr = container_of(timer_sigq, struct k_itimer, sigq);
+	bool ret;
 
-	if (timr->it_interval && timr->it_requeue_pending == info->si_sys_private) {
-		timr->kclock->timer_rearm(timr);
+	/*
+	 * Release siglock to ensure proper locking order versus
+	 * timr::it_lock. Keep interrupts disabled.
+	 */
+	spin_unlock(&current->sighand->siglock);
 
-		timr->it_active = 1;
-		timr->it_overrun_last = timr->it_overrun;
-		timr->it_overrun = -1LL;
-		++timr->it_requeue_pending;
+	ret = __posixtimer_deliver_signal(info, timr);
 
-		info->si_overrun = timer_overrun_to_int(timr, info->si_overrun);
-	}
+	/* Drop the reference which was acquired when the signal was queued */
+	posixtimer_putref(timr);
 
-	unlock_timer(timr, flags);
+	spin_lock(&current->sighand->siglock);
+	return ret;
 }
 
-int posix_timer_queue_signal(struct k_itimer *timr)
+void posix_timer_queue_signal(struct k_itimer *timr)
 {
-	int ret, si_private = 0;
-	enum pid_type type;
-
 	lockdep_assert_held(&timr->it_lock);
 
-	timr->it_active = 0;
-	if (timr->it_interval)
-		si_private = ++timr->it_requeue_pending;
-
-	/*
-	 * FIXME: if ->sigq is queued we can race with
-	 * dequeue_signal()->posixtimer_rearm().
-	 *
-	 * If dequeue_signal() sees the "right" value of
-	 * si_sys_private it calls posixtimer_rearm().
-	 * We re-queue ->sigq and drop ->it_lock().
-	 * posixtimer_rearm() locks the timer
-	 * and re-schedules it while ->sigq is pending.
-	 * Not really bad, but not that we want.
-	 */
-	timr->sigq->info.si_sys_private = si_private;
-
-	type = !(timr->it_sigev_notify & SIGEV_THREAD_ID) ? PIDTYPE_TGID : PIDTYPE_PID;
-	ret = send_sigqueue(timr->sigq, timr->it_pid, type);
-	/* If we failed to send the signal the timer stops. */
-	return ret > 0;
+	timr->it_status = timr->it_interval ? POSIX_TIMER_REQUEUE_PENDING : POSIX_TIMER_DISARMED;
+	posixtimer_send_sigqueue(timr);
 }
 
 /*
@@ -317,62 +318,10 @@ int posix_timer_queue_signal(struct k_itimer *timr)
 static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer)
 {
 	struct k_itimer *timr = container_of(timer, struct k_itimer, it.real.timer);
-	enum hrtimer_restart ret = HRTIMER_NORESTART;
-	unsigned long flags;
-
-	spin_lock_irqsave(&timr->it_lock, flags);
-
-	if (posix_timer_queue_signal(timr)) {
-		/*
-		 * The signal was not queued due to SIG_IGN. As a
-		 * consequence the timer is not going to be rearmed from
-		 * the signal delivery path. But as a real signal handler
-		 * can be installed later the timer must be rearmed here.
-		 */
-		if (timr->it_interval != 0) {
-			ktime_t now = hrtimer_cb_get_time(timer);
-
-			/*
-			 * FIXME: What we really want, is to stop this
-			 * timer completely and restart it in case the
-			 * SIG_IGN is removed. This is a non trivial
-			 * change to the signal handling code.
-			 *
-			 * For now let timers with an interval less than a
-			 * jiffy expire every jiffy and recheck for a
-			 * valid signal handler.
-			 *
-			 * This avoids interrupt starvation in case of a
-			 * very small interval, which would expire the
-			 * timer immediately again.
-			 *
-			 * Moving now ahead of time by one jiffy tricks
-			 * hrtimer_forward() to expire the timer later,
-			 * while it still maintains the overrun accuracy
-			 * for the price of a slight inconsistency in the
-			 * timer_gettime() case. This is at least better
-			 * than a timer storm.
-			 *
-			 * Only required when high resolution timers are
-			 * enabled as the periodic tick based timers are
-			 * automatically aligned to the next tick.
-			 */
-			if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS)) {
-				ktime_t kj = TICK_NSEC;
-
-				if (timr->it_interval < kj)
-					now = ktime_add(now, kj);
-			}
-
-			timr->it_overrun += hrtimer_forward(timer, now, timr->it_interval);
-			ret = HRTIMER_RESTART;
-			++timr->it_requeue_pending;
-			timr->it_active = 1;
-		}
-	}
 
-	unlock_timer(timr, flags);
-	return ret;
+	guard(spinlock_irqsave)(&timr->it_lock);
+	posix_timer_queue_signal(timr);
+	return HRTIMER_NORESTART;
 }
 
 static struct pid *good_sigevent(sigevent_t * event)
@@ -399,32 +348,27 @@ static struct pid *good_sigevent(sigevent_t * event)
 	}
 }
 
-static struct k_itimer * alloc_posix_timer(void)
+static struct k_itimer *alloc_posix_timer(void)
 {
 	struct k_itimer *tmr = kmem_cache_zalloc(posix_timers_cache, GFP_KERNEL);
 
 	if (!tmr)
 		return tmr;
-	if (unlikely(!(tmr->sigq = sigqueue_alloc()))) {
+
+	if (unlikely(!posixtimer_init_sigqueue(&tmr->sigq))) {
 		kmem_cache_free(posix_timers_cache, tmr);
 		return NULL;
 	}
-	clear_siginfo(&tmr->sigq->info);
+	rcuref_init(&tmr->rcuref, 1);
 	return tmr;
 }
 
-static void k_itimer_rcu_free(struct rcu_head *head)
-{
-	struct k_itimer *tmr = container_of(head, struct k_itimer, rcu);
-
-	kmem_cache_free(posix_timers_cache, tmr);
-}
-
-static void posix_timer_free(struct k_itimer *tmr)
+void posixtimer_free_timer(struct k_itimer *tmr)
 {
 	put_pid(tmr->it_pid);
-	sigqueue_free(tmr->sigq);
-	call_rcu(&tmr->rcu, k_itimer_rcu_free);
+	if (tmr->sigq.ucounts)
+		dec_rlimit_put_ucounts(tmr->sigq.ucounts, UCOUNT_RLIMIT_SIGPENDING);
+	kfree_rcu(tmr, rcu);
 }
 
 static void posix_timer_unhash_and_free(struct k_itimer *tmr)
@@ -432,7 +376,7 @@ static void posix_timer_unhash_and_free(struct k_itimer *tmr)
 	spin_lock(&hash_lock);
 	hlist_del_rcu(&tmr->t_hash);
 	spin_unlock(&hash_lock);
-	posix_timer_free(tmr);
+	posixtimer_putref(tmr);
 }
 
 static int common_timer_create(struct k_itimer *new_timer)
@@ -467,7 +411,7 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event,
 	 */
 	new_timer_id = posix_timer_add(new_timer);
 	if (new_timer_id < 0) {
-		posix_timer_free(new_timer);
+		posixtimer_free_timer(new_timer);
 		return new_timer_id;
 	}
 
@@ -485,18 +429,23 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event,
 			goto out;
 		}
 		new_timer->it_sigev_notify     = event->sigev_notify;
-		new_timer->sigq->info.si_signo = event->sigev_signo;
-		new_timer->sigq->info.si_value = event->sigev_value;
+		new_timer->sigq.info.si_signo = event->sigev_signo;
+		new_timer->sigq.info.si_value = event->sigev_value;
 	} else {
 		new_timer->it_sigev_notify     = SIGEV_SIGNAL;
-		new_timer->sigq->info.si_signo = SIGALRM;
-		memset(&new_timer->sigq->info.si_value, 0, sizeof(sigval_t));
-		new_timer->sigq->info.si_value.sival_int = new_timer->it_id;
+		new_timer->sigq.info.si_signo = SIGALRM;
+		memset(&new_timer->sigq.info.si_value, 0, sizeof(sigval_t));
+		new_timer->sigq.info.si_value.sival_int = new_timer->it_id;
 		new_timer->it_pid = get_pid(task_tgid(current));
 	}
 
-	new_timer->sigq->info.si_tid   = new_timer->it_id;
-	new_timer->sigq->info.si_code  = SI_TIMER;
+	if (new_timer->it_sigev_notify & SIGEV_THREAD_ID)
+		new_timer->it_pid_type = PIDTYPE_PID;
+	else
+		new_timer->it_pid_type = PIDTYPE_TGID;
+
+	new_timer->sigq.info.si_tid = new_timer->it_id;
+	new_timer->sigq.info.si_code = SI_TIMER;
 
 	if (copy_to_user(created_timer_id, &new_timer_id, sizeof (new_timer_id))) {
 		error = -EFAULT;
@@ -580,7 +529,14 @@ static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags)
 	 *  1) Set timr::it_signal to NULL with timr::it_lock held
 	 *  2) Release timr::it_lock
 	 *  3) Remove from the hash under hash_lock
-	 *  4) Call RCU for removal after the grace period
+	 *  4) Put the reference count.
+	 *
+	 * The reference count might not drop to zero if timr::sigq is
+	 * queued. In that case the signal delivery or flush will put the
+	 * last reference count.
+	 *
+	 * When the reference count reaches zero, the timer is scheduled
+	 * for RCU removal after the grace period.
 	 *
 	 * Holding rcu_read_lock() accross the lookup ensures that
 	 * the timer cannot be freed.
@@ -647,10 +603,10 @@ void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting)
 	/* interval timer ? */
 	if (iv) {
 		cur_setting->it_interval = ktime_to_timespec64(iv);
-	} else if (!timr->it_active) {
+	} else if (timr->it_status == POSIX_TIMER_DISARMED) {
 		/*
 		 * SIGEV_NONE oneshot timers are never queued and therefore
-		 * timr->it_active is always false. The check below
+		 * timr->it_status is always DISARMED. The check below
 		 * vs. remaining time will handle this case.
 		 *
 		 * For all other timers there is nothing to update here, so
@@ -667,7 +623,7 @@ void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting)
 	 * is a SIGEV_NONE timer move the expiry time forward by intervals,
 	 * so expiry is > now.
 	 */
-	if (iv && (timr->it_requeue_pending & REQUEUE_PENDING || sig_none))
+	if (iv && timr->it_status != POSIX_TIMER_ARMED)
 		timr->it_overrun += kc->timer_forward(timr, now);
 
 	remaining = kc->timer_remaining(timr, now);
@@ -775,7 +731,7 @@ SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id)
 	if (!timr)
 		return -EINVAL;
 
-	overrun = timer_overrun_to_int(timr, 0);
+	overrun = timer_overrun_to_int(timr);
 	unlock_timer(timr, flags);
 
 	return overrun;
@@ -867,8 +823,6 @@ void posix_timer_set_common(struct k_itimer *timer, struct itimerspec64 *new_set
 	else
 		timer->it_interval = 0;
 
-	/* Prevent reloading in case there is a signal pending */
-	timer->it_requeue_pending = (timer->it_requeue_pending + 2) & ~REQUEUE_PENDING;
 	/* Reset overrun accounting */
 	timer->it_overrun_last = 0;
 	timer->it_overrun = -1LL;
@@ -886,8 +840,6 @@ int common_timer_set(struct k_itimer *timr, int flags,
 	if (old_setting)
 		common_timer_get(timr, old_setting);
 
-	/* Prevent rearming by clearing the interval */
-	timr->it_interval = 0;
 	/*
 	 * Careful here. On SMP systems the timer expiry function could be
 	 * active and spinning on timr->it_lock.
@@ -895,7 +847,7 @@ int common_timer_set(struct k_itimer *timr, int flags,
 	if (kc->timer_try_to_cancel(timr) < 0)
 		return TIMER_RETRY;
 
-	timr->it_active = 0;
+	timr->it_status = POSIX_TIMER_DISARMED;
 	posix_timer_set_common(timr, new_setting);
 
 	/* Keep timer disarmed when it_value is zero */
@@ -908,7 +860,8 @@ int common_timer_set(struct k_itimer *timr, int flags,
 	sigev_none = timr->it_sigev_notify == SIGEV_NONE;
 
 	kc->timer_arm(timr, expires, flags & TIMER_ABSTIME, sigev_none);
-	timr->it_active = !sigev_none;
+	if (!sigev_none)
+		timr->it_status = POSIX_TIMER_ARMED;
 	return 0;
 }
 
@@ -936,6 +889,9 @@ retry:
 	if (old_spec64)
 		old_spec64->it_interval = ktime_to_timespec64(timr->it_interval);
 
+	/* Prevent signal delivery and rearming. */
+	timr->it_signal_seq++;
+
 	kc = timr->kclock;
 	if (WARN_ON_ONCE(!kc || !kc->timer_set))
 		error = -EINVAL;
@@ -1004,17 +960,31 @@ int common_timer_del(struct k_itimer *timer)
 {
 	const struct k_clock *kc = timer->kclock;
 
-	timer->it_interval = 0;
 	if (kc->timer_try_to_cancel(timer) < 0)
 		return TIMER_RETRY;
-	timer->it_active = 0;
+	timer->it_status = POSIX_TIMER_DISARMED;
 	return 0;
 }
 
+/*
+ * If the deleted timer is on the ignored list, remove it and
+ * drop the associated reference.
+ */
+static inline void posix_timer_cleanup_ignored(struct k_itimer *tmr)
+{
+	if (!hlist_unhashed(&tmr->ignored_list)) {
+		hlist_del_init(&tmr->ignored_list);
+		posixtimer_putref(tmr);
+	}
+}
+
 static inline int timer_delete_hook(struct k_itimer *timer)
 {
 	const struct k_clock *kc = timer->kclock;
 
+	/* Prevent signal delivery and rearming. */
+	timer->it_signal_seq++;
+
 	if (WARN_ON_ONCE(!kc || !kc->timer_del))
 		return -EINVAL;
 	return kc->timer_del(timer);
@@ -1040,12 +1010,18 @@ retry_delete:
 
 	spin_lock(&current->sighand->siglock);
 	hlist_del(&timer->list);
-	spin_unlock(&current->sighand->siglock);
+	posix_timer_cleanup_ignored(timer);
 	/*
 	 * A concurrent lookup could check timer::it_signal lockless. It
 	 * will reevaluate with timer::it_lock held and observe the NULL.
+	 *
+	 * It must be written with siglock held so that the signal code
+	 * observes timer->it_signal == NULL in do_sigaction(SIG_IGN),
+	 * which prevents it from moving a pending signal of a deleted
+	 * timer to the ignore list.
 	 */
 	WRITE_ONCE(timer->it_signal, NULL);
+	spin_unlock(&current->sighand->siglock);
 
 	unlock_timer(timer, flags);
 	posix_timer_unhash_and_free(timer);
@@ -1091,6 +1067,8 @@ retry_delete:
 	}
 	hlist_del(&timer->list);
 
+	posix_timer_cleanup_ignored(timer);
+
 	/*
 	 * Setting timer::it_signal to NULL is technically not required
 	 * here as nothing can access the timer anymore legitimately via
@@ -1123,6 +1101,19 @@ void exit_itimers(struct task_struct *tsk)
 	/* The timers are not longer accessible via tsk::signal */
 	while (!hlist_empty(&timers))
 		itimer_delete(hlist_entry(timers.first, struct k_itimer, list));
+
+	/*
+	 * There should be no timers on the ignored list. itimer_delete() has
+	 * mopped them up.
+	 */
+	if (!WARN_ON_ONCE(!hlist_empty(&tsk->signal->ignored_posix_timers)))
+		return;
+
+	hlist_move_list(&tsk->signal->ignored_posix_timers, &timers);
+	while (!hlist_empty(&timers)) {
+		posix_timer_cleanup_ignored(hlist_entry(timers.first, struct k_itimer,
+							ignored_list));
+	}
 }
 
 SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,