Re: Linux 5.15.213

[Greg Kroah-Hartman <gregkh@linuxfoundation.org>]

diff --git a/Makefile b/Makefile
index 35b1f66d7218..783acda54d74 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 15
-SUBLEVEL = 212
+SUBLEVEL = 213
 EXTRAVERSION =
 NAME = Trick or Treat
 
diff --git a/kernel/exit.c b/kernel/exit.c
index 3c6ddf7320fa..776994c28887 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -200,7 +200,13 @@ static void __exit_signal(struct task_struct *tsk)
 	 * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals.
 	 */
 	flush_sigqueue(&tsk->pending);
-	tsk->sighand = NULL;
+
+	/*
+	 * Ensure that all preceeding state is visible. Pairs with
+	 * the smp_acquire__after_ctrl_dep() in the sighand == NULL
+	 * path of lock_task_sighand().
+	 */
+	smp_store_release(&tsk->sighand, NULL);
 	spin_unlock(&sighand->siglock);
 
 	__cleanup_sighand(sighand);
diff --git a/kernel/signal.c b/kernel/signal.c
index 10a315e461d3..662377d23c95 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1388,8 +1388,16 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
 	rcu_read_lock();
 	for (;;) {
 		sighand = rcu_dereference(tsk->sighand);
-		if (unlikely(sighand == NULL))
+		if (unlikely(sighand == NULL)) {
+			/*
+			 * Pairs with the smp_store_release() in
+			 * __exit_signal().  It ensures that all state
+			 * modifications to the task preceeding the store are
+			 * visible to the callers of lock_task_sighand().
+			 */
+			smp_acquire__after_ctrl_dep();
 			break;
+		}
 
 		/*
 		 * This sighand can be already freed and even reused, but
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index c99e11da83e8..52deada50891 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -455,6 +455,109 @@ static void disarm_timer(struct k_itimer *timer, struct task_struct *p)
 		trigger_base_recalc_expires(timer, p);
 }
 
+/*
+ * Lookup the task via timer->it.cpu.pid and attempt to lock the task's sighand.
+ *
+ * This can race with the reaping of the task:
+ *
+ * CPU0					CPU1
+ *
+ * // Finds task
+ * p = pid_task(pid, pid_type);		__exit_signal(p)
+ *					  lock(p, sighand);
+ *					  posix_cpu_timers*_exit();
+ * sighand = lock_task_sighand(p);	  unhash_task(p);
+ *					  p->sighand = NULL;
+ *					  unlock(sighand);
+ *
+ * In this case sighand is NULL, which means the task and the associated timer
+ * queue cannot be longer accessed safely.
+ *
+ * __exit_signal() invokes posix_cpu_timers_exit() and if the thread group is
+ * dead it also invokes posix_cpu_timers_group_exit(). These functions delete
+ * all pending timers from the related timer queues. The POSIX timers (k_itimer)
+ * themself are still accessible, but not longer connected to the task.
+ *
+ * exec() works slightly differently. The task which exec()'s terminates all
+ * other threads in the thread group and runs __exit_signal() on them. As the
+ * thread group is not dead they only clean up the per task timers via
+ * posix_cpu_timers_exit().
+ *
+ * As the TGID on exec() stays the same per process timers stay queued, if they
+ * are armed. This works without a problem when exec() is done by the thread
+ * group leader. If a non-leader thread exec()'s this can end up in the
+ * following scenario:
+ *
+ * CPU0					CPU1
+ * // Returns old leader
+ * p = pid_task(pid, pid_type);		de_thread()
+ *					switch_leader()
+ *					release_task(old leader)
+ *					  __exit_signal()
+ *					  old_leader->sighand = NULL;
+ * // Returns NULL
+ * sighand = lock_task_sighand(p)
+ *
+ * That's problematic for several functions:
+ *
+ *  - posix_cpu_timer_del(): If the timer is still enqueued on the task the
+ *    underlying k_itimer will be freed which results in a UAF in
+ *    run_posix_cpu_timers() or on timerqueue related add/delete operations.
+ *    If the timer is not enqueued, the failure is harmless
+ *
+ *  - posix_cpu_timer_set(): Independent of the enqueued state that results in a
+ *    transient failure which is user space visible (-ESRCH) for regular posix
+ *    timers. But for the use case in do_cpu_nanosleep() it's the same UAF
+ *    problem just that the timer is allocated on the stack.
+ *
+ *  - posix_cpu_timer_rearm(): Timer is not enqueued at that point, but this
+ *    silently ignores the rearm request, which is a functional problem as the
+ *    timer wont expire anymore.
+ */
+static struct task_struct *timer_lock_sighand(struct k_itimer *timer, unsigned long *flags)
+{
+	enum pid_type type = clock_pid_type(timer->it_clock);
+	struct cpu_timer *ctmr = &timer->it.cpu;
+
+	guard(rcu)();
+
+	for (;;) {
+		struct task_struct *t = pid_task(timer->it.cpu.pid, type);
+
+		/* Fail if the task cannot be found. */
+		if (!t)
+			break;
+
+		/* Try to lock the task's sighand */
+		if (lock_task_sighand(t, flags))
+			return t;
+
+		/*
+		 * The next PID lookup might either fail or return the new
+		 * leader. This is correct for both exit() and exec().
+		 */
+	}
+
+	/*
+	 * If the timer is still enqueued, warn. There is nothing safe to do
+	 * here as there might be two timers in there which are removed in
+	 * parallel and that will cause more damage than good. This should never
+	 * happen!
+	 *
+	 * Ensure that the stores to the timer and timerqueue are visible:
+	 *
+	 * __exit_signal()
+	 *   posix_cpu_timers*_exit()
+	 *   write_seqlock(seqlock)
+	 *	smp_wmb(); <-------
+	 *   __unhash_process()	  |	!pid_task()
+	 *			  ---->	smp_rmb();
+	 *				WARN_ON_ONCE(...)
+	 */
+	smp_rmb();
+	WARN_ON_ONCE(ctmr->head || timerqueue_node_queued(&ctmr->node));
+	return NULL;
+}
 
 /*
  * Clean up a CPU-clock timer that is about to be destroyed.
@@ -464,29 +567,13 @@ static void disarm_timer(struct k_itimer *timer, struct task_struct *p)
  */
 static int posix_cpu_timer_del(struct k_itimer *timer)
 {
-	struct cpu_timer *ctmr = &timer->it.cpu;
-	struct sighand_struct *sighand;
 	struct task_struct *p;
 	unsigned long flags;
 	int ret = 0;
 
-	rcu_read_lock();
-	p = cpu_timer_task_rcu(timer);
-	if (!p)
-		goto out;
+	p = timer_lock_sighand(timer, &flags);
 
-	/*
-	 * Protect against sighand release/switch in exit/exec and process/
-	 * thread timer list entry concurrent read/writes.
-	 */
-	sighand = lock_task_sighand(p, &flags);
-	if (unlikely(sighand == NULL)) {
-		/*
-		 * This raced with the reaping of the task. The exit cleanup
-		 * should have removed this timer from the timer queue.
-		 */
-		WARN_ON_ONCE(ctmr->head || timerqueue_node_queued(&ctmr->node));
-	} else {
+	if (likely(p)) {
 		if (timer->it.cpu.firing)
 			ret = TIMER_RETRY;
 		else
@@ -495,10 +582,8 @@ static int posix_cpu_timer_del(struct k_itimer *timer)
 		unlock_task_sighand(p, &flags);
 	}
 
-out:
-	rcu_read_unlock();
 	if (!ret)
-		put_pid(ctmr->pid);
+		put_pid(timer->it.cpu.pid);
 
 	return ret;
 }
@@ -620,21 +705,17 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 	clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock);
 	u64 old_expires, new_expires, old_incr, val;
 	struct cpu_timer *ctmr = &timer->it.cpu;
-	struct sighand_struct *sighand;
 	struct task_struct *p;
 	unsigned long flags;
 	int ret = 0;
 
-	rcu_read_lock();
-	p = cpu_timer_task_rcu(timer);
-	if (!p) {
-		/*
-		 * If p has just been reaped, we can no
-		 * longer get any information about it at all.
-		 */
-		rcu_read_unlock();
+	p = timer_lock_sighand(timer, &flags);
+	/*
+	 * If p has just been reaped, we can no longer get any information about
+	 * it at all.
+	 */
+	if (!p)
 		return -ESRCH;
-	}
 
 	/*
 	 * Use the to_ktime conversion because that clamps the maximum
@@ -642,20 +723,6 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 	 */
 	new_expires = ktime_to_ns(timespec64_to_ktime(new->it_value));
 
-	/*
-	 * Protect against sighand release/switch in exit/exec and p->cpu_timers
-	 * and p->signal->cpu_timers read/write in arm_timer()
-	 */
-	sighand = lock_task_sighand(p, &flags);
-	/*
-	 * If p has just been reaped, we can no
-	 * longer get any information about it at all.
-	 */
-	if (unlikely(sighand == NULL)) {
-		rcu_read_unlock();
-		return -ESRCH;
-	}
-
 	/*
 	 * Disarm any old timer after extracting its expiry time.
 	 */
@@ -704,6 +771,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 				old->it_value.tv_sec = 0;
 			}
 		}
+		old->it_interval = ns_to_timespec64(old_incr);
 	}
 
 	if (unlikely(ret)) {
@@ -714,7 +782,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 		 * it as an overrun (thanks to bump_cpu_timer above).
 		 */
 		unlock_task_sighand(p, &flags);
-		goto out;
+		return ret;
 	}
 
 	if (new_expires != 0 && !(timer_flags & TIMER_ABSTIME)) {
@@ -727,11 +795,11 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 	 * arm the timer (we'll just fake it for timer_gettime).
 	 */
 	cpu_timer_setexpires(ctmr, new_expires);
-	if (new_expires != 0 && val < new_expires) {
+	if (new_expires != 0 && val < new_expires)
 		arm_timer(timer, p);
-	}
+	else
+		trigger_base_recalc_expires(timer, p);
 
-	unlock_task_sighand(p, &flags);
 	/*
 	 * Install the new reload setting, and
 	 * set up the signal and overrun bookkeeping.
@@ -748,35 +816,18 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 	timer->it_overrun_last = 0;
 	timer->it_overrun = -1;
 
-	if (val >= new_expires) {
-		if (new_expires != 0) {
-			/*
-			 * The designated time already passed, so we notify
-			 * immediately, even if the thread never runs to
-			 * accumulate more time on this clock.
-			 */
-			cpu_timer_fire(timer);
-		}
+	unlock_task_sighand(p, &flags);
 
+	if (new_expires && val >= new_expires) {
 		/*
-		 * Make sure we don't keep around the process wide cputime
-		 * counter or the tick dependency if they are not necessary.
+		 * The designated time already passed, so we notify immediately,
+		 * even if the thread never runs to accumulate more time on this
+		 * clock.
 		 */
-		sighand = lock_task_sighand(p, &flags);
-		if (!sighand)
-			goto out;
-
-		if (!cpu_timer_queued(ctmr))
-			trigger_base_recalc_expires(timer, p);
-
-		unlock_task_sighand(p, &flags);
+		cpu_timer_fire(timer);
 	}
- out:
-	rcu_read_unlock();
-	if (old)
-		old->it_interval = ns_to_timespec64(old_incr);
 
-	return ret;
+	return 0;
 }
 
 static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp)
@@ -1042,19 +1093,12 @@ static void posix_cpu_timer_rearm(struct k_itimer *timer)
 {
 	clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock);
 	struct task_struct *p;
-	struct sighand_struct *sighand;
 	unsigned long flags;
 	u64 now;
 
-	rcu_read_lock();
-	p = cpu_timer_task_rcu(timer);
-	if (!p)
-		goto out;
-
-	/* Protect timer list r/w in arm_timer() */
-	sighand = lock_task_sighand(p, &flags);
-	if (unlikely(sighand == NULL))
-		goto out;
+	p = timer_lock_sighand(timer, &flags);
+	if (unlikely(!p))
+		return;
 
 	/*
 	 * Fetch the current sample and update the timer's expiry time.
@@ -1071,8 +1115,6 @@ static void posix_cpu_timer_rearm(struct k_itimer *timer)
 	 */
 	arm_timer(timer, p);
 	unlock_task_sighand(p, &flags);
-out:
-	rcu_read_unlock();
 }
 
 /**