Merge branch 'next' into for-linus

Prepare input updates for 5.17 merge window.

1 files changed, 82 insertions, 25 deletions

diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 3bb96a8b49c9..643d412ac623 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -291,6 +291,8 @@ static void thread_group_start_cputime(struct task_struct *tsk, u64 *samples)
 	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
 	struct posix_cputimers *pct = &tsk->signal->posix_cputimers;
 
+	lockdep_assert_task_sighand_held(tsk);
+
 	/* Check if cputimer isn't running. This is accessed without locking. */
 	if (!READ_ONCE(pct->timers_active)) {
 		struct task_cputime sum;
@@ -405,6 +407,55 @@ static int posix_cpu_timer_create(struct k_itimer *new_timer)
 	return 0;
 }
 
+static struct posix_cputimer_base *timer_base(struct k_itimer *timer,
+					      struct task_struct *tsk)
+{
+	int clkidx = CPUCLOCK_WHICH(timer->it_clock);
+
+	if (CPUCLOCK_PERTHREAD(timer->it_clock))
+		return tsk->posix_cputimers.bases + clkidx;
+	else
+		return tsk->signal->posix_cputimers.bases + clkidx;
+}
+
+/*
+ * Force recalculating the base earliest expiration on the next tick.
+ * This will also re-evaluate the need to keep around the process wide
+ * cputime counter and tick dependency and eventually shut these down
+ * if necessary.
+ */
+static void trigger_base_recalc_expires(struct k_itimer *timer,
+					struct task_struct *tsk)
+{
+	struct posix_cputimer_base *base = timer_base(timer, tsk);
+
+	base->nextevt = 0;
+}
+
+/*
+ * Dequeue the timer and reset the base if it was its earliest expiration.
+ * It makes sure the next tick recalculates the base next expiration so we
+ * don't keep the costly process wide cputime counter around for a random
+ * amount of time, along with the tick dependency.
+ *
+ * If another timer gets queued between this and the next tick, its
+ * expiration will update the base next event if necessary on the next
+ * tick.
+ */
+static void disarm_timer(struct k_itimer *timer, struct task_struct *p)
+{
+	struct cpu_timer *ctmr = &timer->it.cpu;
+	struct posix_cputimer_base *base;
+
+	if (!cpu_timer_dequeue(ctmr))
+		return;
+
+	base = timer_base(timer, p);
+	if (cpu_timer_getexpires(ctmr) == base->nextevt)
+		trigger_base_recalc_expires(timer, p);
+}
+
+
 /*
  * Clean up a CPU-clock timer that is about to be destroyed.
  * This is called from timer deletion with the timer already locked.
@@ -439,7 +490,7 @@ static int posix_cpu_timer_del(struct k_itimer *timer)
 		if (timer->it.cpu.firing)
 			ret = TIMER_RETRY;
 		else
-			cpu_timer_dequeue(ctmr);
+			disarm_timer(timer, p);
 
 		unlock_task_sighand(p, &flags);
 	}
@@ -498,15 +549,9 @@ void posix_cpu_timers_exit_group(struct task_struct *tsk)
  */
 static void arm_timer(struct k_itimer *timer, struct task_struct *p)
 {
-	int clkidx = CPUCLOCK_WHICH(timer->it_clock);
+	struct posix_cputimer_base *base = timer_base(timer, p);
 	struct cpu_timer *ctmr = &timer->it.cpu;
 	u64 newexp = cpu_timer_getexpires(ctmr);
-	struct posix_cputimer_base *base;
-
-	if (CPUCLOCK_PERTHREAD(timer->it_clock))
-		base = p->posix_cputimers.bases + clkidx;
-	else
-		base = p->signal->posix_cputimers.bases + clkidx;
 
 	if (!cpu_timer_enqueue(&base->tqhead, ctmr))
 		return;
@@ -523,7 +568,7 @@ static void arm_timer(struct k_itimer *timer, struct task_struct *p)
 	if (CPUCLOCK_PERTHREAD(timer->it_clock))
 		tick_dep_set_task(p, TICK_DEP_BIT_POSIX_TIMER);
 	else
-		tick_dep_set_signal(p->signal, TICK_DEP_BIT_POSIX_TIMER);
+		tick_dep_set_signal(p, TICK_DEP_BIT_POSIX_TIMER);
 }
 
 /*
@@ -703,16 +748,29 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 	timer->it_overrun_last = 0;
 	timer->it_overrun = -1;
 
-	if (new_expires != 0 && !(val < new_expires)) {
+	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);
+		}
+
 		/*
-		 * The designated time already passed, so we notify
-		 * immediately, even if the thread never runs to
-		 * accumulate more time on this clock.
+		 * Make sure we don't keep around the process wide cputime
+		 * counter or the tick dependency if they are not necessary.
 		 */
-		cpu_timer_fire(timer);
-	}
+		sighand = lock_task_sighand(p, &flags);
+		if (!sighand)
+			goto out;
+
+		if (!cpu_timer_queued(ctmr))
+			trigger_base_recalc_expires(timer, p);
 
-	ret = 0;
+		unlock_task_sighand(p, &flags);
+	}
  out:
 	rcu_read_unlock();
 	if (old)
@@ -991,6 +1049,11 @@ static void posix_cpu_timer_rearm(struct k_itimer *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;
+
 	/*
 	 * Fetch the current sample and update the timer's expiry time.
 	 */
@@ -1001,11 +1064,6 @@ static void posix_cpu_timer_rearm(struct k_itimer *timer)
 
 	bump_cpu_timer(timer, now);
 
-	/* Protect timer list r/w in arm_timer() */
-	sighand = lock_task_sighand(p, &flags);
-	if (unlikely(sighand == NULL))
-		goto out;
-
 	/*
 	 * Now re-arm for the new expiry time.
 	 */
@@ -1346,9 +1404,8 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clkid,
 			}
 		}
 
-		if (!*newval)
-			return;
-		*newval += now;
+		if (*newval)
+			*newval += now;
 	}
 
 	/*
@@ -1358,7 +1415,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clkid,
 	if (*newval < *nextevt)
 		*nextevt = *newval;
 
-	tick_dep_set_signal(tsk->signal, TICK_DEP_BIT_POSIX_TIMER);
+	tick_dep_set_signal(tsk, TICK_DEP_BIT_POSIX_TIMER);
 }
 
 static int do_cpu_nanosleep(const clockid_t which_clock, int flags,