Merge tag 'sched-urgent-2020-04-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fixes/updates from Thomas Gleixner:

 - Deduplicate the average computations in the scheduler core and the
   fair class code.

 - Fix a raise between runtime distribution and assignement which can
   cause exceeding the quota by up to 70%.

 - Prevent negative results in the imbalanace calculation

 - Remove a stale warning in the workqueue code which can be triggered
   since the call site was moved out of preempt disabled code. It's a
   false positive.

 - Deduplicate the print macros for procfs

 - Add the ucmap values to the SCHED_DEBUG procfs output for completness

* tag 'sched-urgent-2020-04-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/debug: Add task uclamp values to SCHED_DEBUG procfs
  sched/debug: Factor out printing formats into common macros
  sched/debug: Remove redundant macro define
  sched/core: Remove unused rq::last_load_update_tick
  workqueue: Remove the warning in wq_worker_sleeping()
  sched/fair: Fix negative imbalance in imbalance calculation
  sched/fair: Fix race between runtime distribution and assignment
  sched/fair: Align rq->avg_idle and rq->avg_scan_cost

kernel/sched/core.c

@@ -2119,12 +2119,6 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
 	return cpu;
 }
 
-static void update_avg(u64 *avg, u64 sample)
-{
-	s64 diff = sample - *avg;
-	*avg += diff >> 3;
-}
-
 void sched_set_stop_task(int cpu, struct task_struct *stop)
 {
 	struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
@@ -4126,7 +4120,8 @@ static inline void sched_submit_work(struct task_struct *tsk)
 	 * it wants to wake up a task to maintain concurrency.
 	 * As this function is called inside the schedule() context,
 	 * we disable preemption to avoid it calling schedule() again
-	 * in the possible wakeup of a kworker.
+	 * in the possible wakeup of a kworker and because wq_worker_sleeping()
+	 * requires it.
 	 */
 	if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER)) {
 		preempt_disable();
@@ -6699,7 +6694,6 @@ void __init sched_init(void)
 
 		rq_attach_root(rq, &def_root_domain);
 #ifdef CONFIG_NO_HZ_COMMON
-		rq->last_load_update_tick = jiffies;
 		rq->last_blocked_load_update_tick = jiffies;
 		atomic_set(&rq->nohz_flags, 0);
 #endif

kernel/sched/debug.c

@@ -816,10 +816,12 @@ static int __init init_sched_debug_procfs(void)
 
 __initcall(init_sched_debug_procfs);
 
-#define __P(F)	SEQ_printf(m, "%-45s:%21Ld\n",	     #F, (long long)F)
-#define   P(F)	SEQ_printf(m, "%-45s:%21Ld\n",	     #F, (long long)p->F)
-#define __PN(F)	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F))
-#define   PN(F)	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F))
+#define __PS(S, F) SEQ_printf(m, "%-45s:%21Ld\n", S, (long long)(F))
+#define __P(F) __PS(#F, F)
+#define   P(F) __PS(#F, p->F)
+#define __PSN(S, F) SEQ_printf(m, "%-45s:%14Ld.%06ld\n", S, SPLIT_NS((long long)(F)))
+#define __PN(F) __PSN(#F, F)
+#define   PN(F) __PSN(#F, p->F)
 
 
 #ifdef CONFIG_NUMA_BALANCING
@@ -868,18 +870,9 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 	SEQ_printf(m,
 		"---------------------------------------------------------"
 		"----------\n");
-#define __P(F) \
-	SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)F)
-#define P(F) \
-	SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)p->F)
-#define P_SCHEDSTAT(F) \
-	SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)schedstat_val(p->F))
-#define __PN(F) \
-	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F))
-#define PN(F) \
-	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F))
-#define PN_SCHEDSTAT(F) \
-	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)schedstat_val(p->F)))
+
+#define P_SCHEDSTAT(F)  __PS(#F, schedstat_val(p->F))
+#define PN_SCHEDSTAT(F) __PSN(#F, schedstat_val(p->F))
 
 	PN(se.exec_start);
 	PN(se.vruntime);
@@ -939,10 +932,8 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 	}
 
 	__P(nr_switches);
-	SEQ_printf(m, "%-45s:%21Ld\n",
-		   "nr_voluntary_switches", (long long)p->nvcsw);
-	SEQ_printf(m, "%-45s:%21Ld\n",
-		   "nr_involuntary_switches", (long long)p->nivcsw);
+	__PS("nr_voluntary_switches", p->nvcsw);
+	__PS("nr_involuntary_switches", p->nivcsw);
 
 	P(se.load.weight);
 #ifdef CONFIG_SMP
@@ -955,6 +946,12 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 	P(se.avg.last_update_time);
 	P(se.avg.util_est.ewma);
 	P(se.avg.util_est.enqueued);
+#endif
+#ifdef CONFIG_UCLAMP_TASK
+	__PS("uclamp.min", p->uclamp[UCLAMP_MIN].value);
+	__PS("uclamp.max", p->uclamp[UCLAMP_MAX].value);
+	__PS("effective uclamp.min", uclamp_eff_value(p, UCLAMP_MIN));
+	__PS("effective uclamp.max", uclamp_eff_value(p, UCLAMP_MAX));
 #endif
 	P(policy);
 	P(prio);
@@ -963,11 +960,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 		P(dl.deadline);
 	}
 #undef PN_SCHEDSTAT
-#undef PN
-#undef __PN
 #undef P_SCHEDSTAT
-#undef P
-#undef __P
 
 	{
 		unsigned int this_cpu = raw_smp_processor_id();
@@ -975,8 +968,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 
 		t0 = cpu_clock(this_cpu);
 		t1 = cpu_clock(this_cpu);
-		SEQ_printf(m, "%-45s:%21Ld\n",
-			   "clock-delta", (long long)(t1-t0));
+		__PS("clock-delta", t1-t0);
 	}
 
 	sched_show_numa(p, m);

kernel/sched/fair.c

@@ -4836,11 +4836,10 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 		resched_curr(rq);
 }
 
-static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, u64 remaining)
+static void distribute_cfs_runtime(struct cfs_bandwidth *cfs_b)
 {
 	struct cfs_rq *cfs_rq;
-	u64 runtime;
-	u64 starting_runtime = remaining;
+	u64 runtime, remaining = 1;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(cfs_rq, &cfs_b->throttled_cfs_rq,
@@ -4855,10 +4854,13 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, u64 remaining)
 		/* By the above check, this should never be true */
 		SCHED_WARN_ON(cfs_rq->runtime_remaining > 0);
 
+		raw_spin_lock(&cfs_b->lock);
 		runtime = -cfs_rq->runtime_remaining + 1;
-		if (runtime > remaining)
-			runtime = remaining;
-		remaining -= runtime;
+		if (runtime > cfs_b->runtime)
+			runtime = cfs_b->runtime;
+		cfs_b->runtime -= runtime;
+		remaining = cfs_b->runtime;
+		raw_spin_unlock(&cfs_b->lock);
 
 		cfs_rq->runtime_remaining += runtime;
 
@@ -4873,8 +4875,6 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, u64 remaining)
 			break;
 	}
 	rcu_read_unlock();
-
-	return starting_runtime - remaining;
 }
 
 /*
@@ -4885,7 +4885,6 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, u64 remaining)
  */
 static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, unsigned long flags)
 {
-	u64 runtime;
 	int throttled;
 
 	/* no need to continue the timer with no bandwidth constraint */
@@ -4914,24 +4913,17 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, u
 	cfs_b->nr_throttled += overrun;
 
 	/*
-	 * This check is repeated as we are holding onto the new bandwidth while
-	 * we unthrottle. This can potentially race with an unthrottled group
-	 * trying to acquire new bandwidth from the global pool. This can result
-	 * in us over-using our runtime if it is all used during this loop, but
-	 * only by limited amounts in that extreme case.
+	 * This check is repeated as we release cfs_b->lock while we unthrottle.
 	 */
 	while (throttled && cfs_b->runtime > 0 && !cfs_b->distribute_running) {
-		runtime = cfs_b->runtime;
 		cfs_b->distribute_running = 1;
 		raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
 		/* we can't nest cfs_b->lock while distributing bandwidth */
-		runtime = distribute_cfs_runtime(cfs_b, runtime);
+		distribute_cfs_runtime(cfs_b);
 		raw_spin_lock_irqsave(&cfs_b->lock, flags);
 
 		cfs_b->distribute_running = 0;
 		throttled = !list_empty(&cfs_b->throttled_cfs_rq);
-
-		lsub_positive(&cfs_b->runtime, runtime);
 	}
 
 	/*
@@ -5065,10 +5057,9 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
 	if (!runtime)
 		return;
 
-	runtime = distribute_cfs_runtime(cfs_b, runtime);
+	distribute_cfs_runtime(cfs_b);
 
 	raw_spin_lock_irqsave(&cfs_b->lock, flags);
-	lsub_positive(&cfs_b->runtime, runtime);
 	cfs_b->distribute_running = 0;
 	raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
 }
@@ -6080,8 +6071,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 	struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
 	struct sched_domain *this_sd;
 	u64 avg_cost, avg_idle;
-	u64 time, cost;
-	s64 delta;
+	u64 time;
 	int this = smp_processor_id();
 	int cpu, nr = INT_MAX;
 
@@ -6119,9 +6109,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 	}
 
 	time = cpu_clock(this) - time;
-	cost = this_sd->avg_scan_cost;
-	delta = (s64)(time - cost) / 8;
-	this_sd->avg_scan_cost += delta;
+	update_avg(&this_sd->avg_scan_cost, time);
 
 	return cpu;
 }
@@ -9048,6 +9036,14 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 
 		sds->avg_load = (sds->total_load * SCHED_CAPACITY_SCALE) /
 				sds->total_capacity;
+		/*
+		 * If the local group is more loaded than the selected
+		 * busiest group don't try to pull any tasks.
+		 */
+		if (local->avg_load >= busiest->avg_load) {
+			env->imbalance = 0;
+			return;
+		}
 	}
 
 	/*

kernel/sched/sched.h

@@ -195,6 +195,12 @@ static inline int task_has_dl_policy(struct task_struct *p)
 
 #define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
 
+static inline void update_avg(u64 *avg, u64 sample)
+{
+	s64 diff = sample - *avg;
+	*avg += diff / 8;
+}
+
 /*
  * !! For sched_setattr_nocheck() (kernel) only !!
  *
@@ -882,7 +888,6 @@ struct rq {
 #endif
 #ifdef CONFIG_NO_HZ_COMMON
 #ifdef CONFIG_SMP
-	unsigned long		last_load_update_tick;
 	unsigned long		last_blocked_load_update_tick;
 	unsigned int		has_blocked_load;
 #endif /* CONFIG_SMP */

kernel/workqueue.c

@@ -858,7 +858,8 @@ void wq_worker_running(struct task_struct *task)
  * @task: task going to sleep
  *
  * This function is called from schedule() when a busy worker is
- * going to sleep.
+ * going to sleep. Preemption needs to be disabled to protect ->sleeping
+ * assignment.
  */
 void wq_worker_sleeping(struct task_struct *task)
 {
@@ -875,7 +876,8 @@ void wq_worker_sleeping(struct task_struct *task)
 
 	pool = worker->pool;
 
-	if (WARN_ON_ONCE(worker->sleeping))
+	/* Return if preempted before wq_worker_running() was reached */
+	if (worker->sleeping)
 		return;
 
 	worker->sleeping = 1;