posix-cpu-timers: Force next_expiration recalc after timer deletion

A timer deletion only dequeues the timer but it doesn't shutdown
the related costly process wide cputimer counter and the tick dependency.

The following code snippet keeps this overhead around for one week after
the timer deletion:

	void trigger_process_counter(void)
	{
		timer_t id;
		struct itimerspec val = { };

		val.it_value.tv_sec = 604800;
		timer_create(CLOCK_PROCESS_CPUTIME_ID, NULL, &id);
		timer_settime(id, 0, &val, NULL);
		timer_delete(id);
	}

Make sure the next target's tick recalculates the nearest expiration and
clears the process wide counter and tick dependency if necessary.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210726125513.271824-3-frederic@kernel.org

2 files changed, 35 insertions, 2 deletions

diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index 896c16d2c5fb..4cf1fbe8d1bc 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -82,12 +82,14 @@ static inline bool cpu_timer_enqueue(struct timerqueue_head *head,
 	return timerqueue_add(head, &ctmr->node);
 }
 
-static inline void cpu_timer_dequeue(struct cpu_timer *ctmr)
+static inline bool cpu_timer_dequeue(struct cpu_timer *ctmr)
 {
 	if (ctmr->head) {
 		timerqueue_del(ctmr->head, &ctmr->node);
 		ctmr->head = NULL;
+		return true;
 	}
+	return false;
 }
 
 static inline u64 cpu_timer_getexpires(struct cpu_timer *ctmr)
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 4693d3c71e7e..61c78b62fe6a 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -408,6 +408,37 @@ static int posix_cpu_timer_create(struct k_itimer *new_timer)
 }
 
 /*
+ * 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;
+	int clkidx;
+
+	if (!cpu_timer_dequeue(ctmr))
+		return;
+
+	clkidx = CPUCLOCK_WHICH(timer->it_clock);
+
+	if (CPUCLOCK_PERTHREAD(timer->it_clock))
+		base = p->posix_cputimers.bases + clkidx;
+	else
+		base = p->signal->posix_cputimers.bases + clkidx;
+
+	if (cpu_timer_getexpires(ctmr) == base->nextevt)
+		base->nextevt = 0;
+}
+
+
+/*
  * Clean up a CPU-clock timer that is about to be destroyed.
  * This is called from timer deletion with the timer already locked.
  * If we return TIMER_RETRY, it's necessary to release the timer's lock
@@ -441,7 +472,7 @@ 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);
 	}