Merge tag 'sched-core-2023-06-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "Scheduler SMP load-balancer improvements:

   - Avoid unnecessary migrations within SMT domains on hybrid systems.

     Problem:

        On hybrid CPU systems, (processors with a mixture of
        higher-frequency SMT cores and lower-frequency non-SMT cores),
        under the old code lower-priority CPUs pulled tasks from the
        higher-priority cores if more than one SMT sibling was busy -
        resulting in many unnecessary task migrations.

     Solution:

        The new code improves the load balancer to recognize SMT cores
        with more than one busy sibling and allows lower-priority CPUs
        to pull tasks, which avoids superfluous migrations and lets
        lower-priority cores inspect all SMT siblings for the busiest
        queue.

   - Implement the 'runnable boosting' feature in the EAS balancer:
     consider CPU contention in frequency, EAS max util & load-balance
     busiest CPU selection.

     This improves CPU utilization for certain workloads, while leaves
     other key workloads unchanged.

  Scheduler infrastructure improvements:

   - Rewrite the scheduler topology setup code by consolidating it into
     the build_sched_topology() helper function and building it
     dynamically on the fly.

   - Resolve the local_clock() vs. noinstr complications by rewriting
     the code: provide separate sched_clock_noinstr() and
     local_clock_noinstr() functions to be used in instrumentation code,
     and make sure it is all instrumentation-safe.

  Fixes:

   - Fix a kthread_park() race with wait_woken()

   - Fix misc wait_task_inactive() bugs unearthed by the -rt merge:
       - Fix UP PREEMPT bug by unifying the SMP and UP implementations
       - Fix task_struct::saved_state handling

   - Fix various rq clock update bugs, unearthed by turning on the rq
     clock debugging code.

   - Fix the PSI WINDOW_MIN_US trigger limit, which was easy to trigger
     by creating enough cgroups, by removing the warnign and restricting
     window size triggers to PSI file write-permission or
     CAP_SYS_RESOURCE.

   - Propagate SMT flags in the topology when removing degenerate domain

   - Fix grub_reclaim() calculation bug in the deadline scheduler code

   - Avoid resetting the min update period when it is unnecessary, in
     psi_trigger_destroy().

   - Don't balance a task to its current running CPU in load_balance(),
     which was possible on certain NUMA topologies with overlapping
     groups.

   - Fix the sched-debug printing of rq->nr_uninterruptible

  Cleanups:

   - Address various -Wmissing-prototype warnings, as a preparation to
     (maybe) enable this warning in the future.

   - Remove unused code

   - Mark more functions __init

   - Fix shadow-variable warnings"

* tag 'sched-core-2023-06-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (50 commits)
  sched/core: Avoid multiple calling update_rq_clock() in __cfsb_csd_unthrottle()
  sched/core: Avoid double calling update_rq_clock() in __balance_push_cpu_stop()
  sched/core: Fixed missing rq clock update before calling set_rq_offline()
  sched/deadline: Update GRUB description in the documentation
  sched/deadline: Fix bandwidth reclaim equation in GRUB
  sched/wait: Fix a kthread_park race with wait_woken()
  sched/topology: Mark set_sched_topology() __init
  sched/fair: Rename variable cpu_util eff_util
  arm64/arch_timer: Fix MMIO byteswap
  sched/fair, cpufreq: Introduce 'runnable boosting'
  sched/fair: Refactor CPU utilization functions
  cpuidle: Use local_clock_noinstr()
  sched/clock: Provide local_clock_noinstr()
  x86/tsc: Provide sched_clock_noinstr()
  clocksource: hyper-v: Provide noinstr sched_clock()
  clocksource: hyper-v: Adjust hv_read_tsc_page_tsc() to avoid special casing U64_MAX
  x86/vdso: Fix gettimeofday masking
  math64: Always inline u128 version of mul_u64_u64_shr()
  s390/time: Provide sched_clock_noinstr()
  loongarch: Provide noinstr sched_clock_read()
  ...

1 files changed, 158 insertions, 120 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a68d1276bab0..7eb6e2927390 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2213,6 +2213,154 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 		rq_clock_skip_update(rq);
 }
 
+static __always_inline
+int __task_state_match(struct task_struct *p, unsigned int state)
+{
+	if (READ_ONCE(p->__state) & state)
+		return 1;
+
+#ifdef CONFIG_PREEMPT_RT
+	if (READ_ONCE(p->saved_state) & state)
+		return -1;
+#endif
+	return 0;
+}
+
+static __always_inline
+int task_state_match(struct task_struct *p, unsigned int state)
+{
+#ifdef CONFIG_PREEMPT_RT
+	int match;
+
+	/*
+	 * Serialize against current_save_and_set_rtlock_wait_state() and
+	 * current_restore_rtlock_saved_state().
+	 */
+	raw_spin_lock_irq(&p->pi_lock);
+	match = __task_state_match(p, state);
+	raw_spin_unlock_irq(&p->pi_lock);
+
+	return match;
+#else
+	return __task_state_match(p, state);
+#endif
+}
+
+/*
+ * wait_task_inactive - wait for a thread to unschedule.
+ *
+ * Wait for the thread to block in any of the states set in @match_state.
+ * If it changes, i.e. @p might have woken up, then return zero.  When we
+ * succeed in waiting for @p to be off its CPU, we return a positive number
+ * (its total switch count).  If a second call a short while later returns the
+ * same number, the caller can be sure that @p has remained unscheduled the
+ * whole time.
+ *
+ * The caller must ensure that the task *will* unschedule sometime soon,
+ * else this function might spin for a *long* time. This function can't
+ * be called with interrupts off, or it may introduce deadlock with
+ * smp_call_function() if an IPI is sent by the same process we are
+ * waiting to become inactive.
+ */
+unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state)
+{
+	int running, queued, match;
+	struct rq_flags rf;
+	unsigned long ncsw;
+	struct rq *rq;
+
+	for (;;) {
+		/*
+		 * We do the initial early heuristics without holding
+		 * any task-queue locks at all. We'll only try to get
+		 * the runqueue lock when things look like they will
+		 * work out!
+		 */
+		rq = task_rq(p);
+
+		/*
+		 * If the task is actively running on another CPU
+		 * still, just relax and busy-wait without holding
+		 * any locks.
+		 *
+		 * NOTE! Since we don't hold any locks, it's not
+		 * even sure that "rq" stays as the right runqueue!
+		 * But we don't care, since "task_on_cpu()" will
+		 * return false if the runqueue has changed and p
+		 * is actually now running somewhere else!
+		 */
+		while (task_on_cpu(rq, p)) {
+			if (!task_state_match(p, match_state))
+				return 0;
+			cpu_relax();
+		}
+
+		/*
+		 * Ok, time to look more closely! We need the rq
+		 * lock now, to be *sure*. If we're wrong, we'll
+		 * just go back and repeat.
+		 */
+		rq = task_rq_lock(p, &rf);
+		trace_sched_wait_task(p);
+		running = task_on_cpu(rq, p);
+		queued = task_on_rq_queued(p);
+		ncsw = 0;
+		if ((match = __task_state_match(p, match_state))) {
+			/*
+			 * When matching on p->saved_state, consider this task
+			 * still queued so it will wait.
+			 */
+			if (match < 0)
+				queued = 1;
+			ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
+		}
+		task_rq_unlock(rq, p, &rf);
+
+		/*
+		 * If it changed from the expected state, bail out now.
+		 */
+		if (unlikely(!ncsw))
+			break;
+
+		/*
+		 * Was it really running after all now that we
+		 * checked with the proper locks actually held?
+		 *
+		 * Oops. Go back and try again..
+		 */
+		if (unlikely(running)) {
+			cpu_relax();
+			continue;
+		}
+
+		/*
+		 * It's not enough that it's not actively running,
+		 * it must be off the runqueue _entirely_, and not
+		 * preempted!
+		 *
+		 * So if it was still runnable (but just not actively
+		 * running right now), it's preempted, and we should
+		 * yield - it could be a while.
+		 */
+		if (unlikely(queued)) {
+			ktime_t to = NSEC_PER_SEC / HZ;
+
+			set_current_state(TASK_UNINTERRUPTIBLE);
+			schedule_hrtimeout(&to, HRTIMER_MODE_REL_HARD);
+			continue;
+		}
+
+		/*
+		 * Ahh, all good. It wasn't running, and it wasn't
+		 * runnable, which means that it will never become
+		 * running in the future either. We're all done!
+		 */
+		break;
+	}
+
+	return ncsw;
+}
+
 #ifdef CONFIG_SMP
 
 static void
@@ -2398,7 +2546,6 @@ static struct rq *__migrate_task(struct rq *rq, struct rq_flags *rf,
 	if (!is_cpu_allowed(p, dest_cpu))
 		return rq;
 
-	update_rq_clock(rq);
 	rq = move_queued_task(rq, rf, p, dest_cpu);
 
 	return rq;
@@ -2456,10 +2603,12 @@ static int migration_cpu_stop(void *data)
 				goto out;
 		}
 
-		if (task_on_rq_queued(p))
+		if (task_on_rq_queued(p)) {
+			update_rq_clock(rq);
 			rq = __migrate_task(rq, &rf, p, arg->dest_cpu);
-		else
+		} else {
 			p->wake_cpu = arg->dest_cpu;
+		}
 
 		/*
 		 * XXX __migrate_task() can fail, at which point we might end
@@ -3341,114 +3490,6 @@ out:
 }
 #endif /* CONFIG_NUMA_BALANCING */
 
-/*
- * wait_task_inactive - wait for a thread to unschedule.
- *
- * Wait for the thread to block in any of the states set in @match_state.
- * If it changes, i.e. @p might have woken up, then return zero.  When we
- * succeed in waiting for @p to be off its CPU, we return a positive number
- * (its total switch count).  If a second call a short while later returns the
- * same number, the caller can be sure that @p has remained unscheduled the
- * whole time.
- *
- * The caller must ensure that the task *will* unschedule sometime soon,
- * else this function might spin for a *long* time. This function can't
- * be called with interrupts off, or it may introduce deadlock with
- * smp_call_function() if an IPI is sent by the same process we are
- * waiting to become inactive.
- */
-unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state)
-{
-	int running, queued;
-	struct rq_flags rf;
-	unsigned long ncsw;
-	struct rq *rq;
-
-	for (;;) {
-		/*
-		 * We do the initial early heuristics without holding
-		 * any task-queue locks at all. We'll only try to get
-		 * the runqueue lock when things look like they will
-		 * work out!
-		 */
-		rq = task_rq(p);
-
-		/*
-		 * If the task is actively running on another CPU
-		 * still, just relax and busy-wait without holding
-		 * any locks.
-		 *
-		 * NOTE! Since we don't hold any locks, it's not
-		 * even sure that "rq" stays as the right runqueue!
-		 * But we don't care, since "task_on_cpu()" will
-		 * return false if the runqueue has changed and p
-		 * is actually now running somewhere else!
-		 */
-		while (task_on_cpu(rq, p)) {
-			if (!(READ_ONCE(p->__state) & match_state))
-				return 0;
-			cpu_relax();
-		}
-
-		/*
-		 * Ok, time to look more closely! We need the rq
-		 * lock now, to be *sure*. If we're wrong, we'll
-		 * just go back and repeat.
-		 */
-		rq = task_rq_lock(p, &rf);
-		trace_sched_wait_task(p);
-		running = task_on_cpu(rq, p);
-		queued = task_on_rq_queued(p);
-		ncsw = 0;
-		if (READ_ONCE(p->__state) & match_state)
-			ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
-		task_rq_unlock(rq, p, &rf);
-
-		/*
-		 * If it changed from the expected state, bail out now.
-		 */
-		if (unlikely(!ncsw))
-			break;
-
-		/*
-		 * Was it really running after all now that we
-		 * checked with the proper locks actually held?
-		 *
-		 * Oops. Go back and try again..
-		 */
-		if (unlikely(running)) {
-			cpu_relax();
-			continue;
-		}
-
-		/*
-		 * It's not enough that it's not actively running,
-		 * it must be off the runqueue _entirely_, and not
-		 * preempted!
-		 *
-		 * So if it was still runnable (but just not actively
-		 * running right now), it's preempted, and we should
-		 * yield - it could be a while.
-		 */
-		if (unlikely(queued)) {
-			ktime_t to = NSEC_PER_SEC / HZ;
-
-			set_current_state(TASK_UNINTERRUPTIBLE);
-			schedule_hrtimeout(&to, HRTIMER_MODE_REL_HARD);
-			continue;
-		}
-
-		/*
-		 * Ahh, all good. It wasn't running, and it wasn't
-		 * runnable, which means that it will never become
-		 * running in the future either. We're all done!
-		 */
-		break;
-	}
-
-	return ncsw;
-}
-
 /***
  * kick_process - kick a running thread to enter/exit the kernel
  * @p: the to-be-kicked thread
@@ -4003,15 +4044,14 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
 static __always_inline
 bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success)
 {
+	int match;
+
 	if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) {
 		WARN_ON_ONCE((state & TASK_RTLOCK_WAIT) &&
 			     state != TASK_RTLOCK_WAIT);
 	}
 
-	if (READ_ONCE(p->__state) & state) {
-		*success = 1;
-		return true;
-	}
+	*success = !!(match = __task_state_match(p, state));
 
 #ifdef CONFIG_PREEMPT_RT
 	/*
@@ -4027,12 +4067,10 @@ bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success)
 	 * p::saved_state to TASK_RUNNING so any further tests will
 	 * not result in false positives vs. @success
 	 */
-	if (p->saved_state & state) {
+	if (match < 0)
 		p->saved_state = TASK_RUNNING;
-		*success = 1;
-	}
 #endif
-	return false;
+	return match > 0;
 }
 
 /*
@@ -9548,6 +9586,7 @@ void set_rq_offline(struct rq *rq)
 	if (rq->online) {
 		const struct sched_class *class;
 
+		update_rq_clock(rq);
 		for_each_class(class) {
 			if (class->rq_offline)
 				class->rq_offline(rq);
@@ -9689,7 +9728,6 @@ int sched_cpu_deactivate(unsigned int cpu)
 
 	rq_lock_irqsave(rq, &rf);
 	if (rq->rd) {
-		update_rq_clock(rq);
 		BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
 		set_rq_offline(rq);
 	}