Merge branch 'sched/urgent' into sched/core, to pick up fixes and refresh the branch

Signed-off-by: Ingo Molnar <mingo@kernel.org>

5 files changed, 43 insertions, 7 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 27aff98645e8..65e10ac34660 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -9185,7 +9185,7 @@ void __init init_idle(struct task_struct *idle, int cpu)
 	 * PF_KTHREAD should already be set at this point; regardless, make it
 	 * look like a proper per-CPU kthread.
 	 */
-	idle->flags |= PF_IDLE | PF_KTHREAD | PF_NO_SETAFFINITY;
+	idle->flags |= PF_KTHREAD | PF_NO_SETAFFINITY;
 	kthread_set_per_cpu(idle, cpu);
 
 #ifdef CONFIG_SMP
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 4492608b7d7f..458d359f5991 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -350,7 +350,8 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
 	 * Except when the rq is capped by uclamp_max.
 	 */
 	if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) &&
-	    sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) {
+	    sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq &&
+	    !sg_policy->need_freq_update) {
 		next_f = sg_policy->next_freq;
 
 		/* Restore cached freq as next_freq has changed */
diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index a286e726eb4b..42c40cfdf836 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -101,6 +101,7 @@ static inline int __cpupri_find(struct cpupri *cp, struct task_struct *p,
 
 	if (lowest_mask) {
 		cpumask_and(lowest_mask, &p->cpus_mask, vec->mask);
+		cpumask_and(lowest_mask, lowest_mask, cpu_active_mask);
 
 		/*
 		 * We have to ensure that we have at least one bit
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e2a69af8be36..52c498fd6c46 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -651,6 +651,10 @@ void avg_vruntime_update(struct cfs_rq *cfs_rq, s64 delta)
 	cfs_rq->avg_vruntime -= cfs_rq->avg_load * delta;
 }
 
+/*
+ * Specifically: avg_runtime() + 0 must result in entity_eligible() := true
+ * For this to be so, the result of this function must have a left bias.
+ */
 u64 avg_vruntime(struct cfs_rq *cfs_rq)
 {
 	struct sched_entity *curr = cfs_rq->curr;
@@ -664,8 +668,12 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq)
 		load += weight;
 	}
 
-	if (load)
+	if (load) {
+		/* sign flips effective floor / ceil */
+		if (avg < 0)
+			avg -= (load - 1);
 		avg = div_s64(avg, load);
+	}
 
 	return cfs_rq->min_vruntime + avg;
 }
@@ -4889,10 +4897,12 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq) {}
 static void
 place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
-	u64 vslice = calc_delta_fair(se->slice, se);
-	u64 vruntime = avg_vruntime(cfs_rq);
+	u64 vslice, vruntime = avg_vruntime(cfs_rq);
 	s64 lag = 0;
 
+	se->slice = sysctl_sched_base_slice;
+	vslice = calc_delta_fair(se->slice, se);
+
 	/*
 	 * Due to how V is constructed as the weighted average of entities,
 	 * adding tasks with positive lag, or removing tasks with negative lag
@@ -6599,6 +6609,7 @@ dequeue_throttle:
 /* Working cpumask for: load_balance, load_balance_newidle. */
 static DEFINE_PER_CPU(cpumask_var_t, load_balance_mask);
 static DEFINE_PER_CPU(cpumask_var_t, select_rq_mask);
+static DEFINE_PER_CPU(cpumask_var_t, should_we_balance_tmpmask);
 
 #ifdef CONFIG_NO_HZ_COMMON
 
@@ -9563,7 +9574,7 @@ static inline long sibling_imbalance(struct lb_env *env,
 	imbalance /= ncores_local + ncores_busiest;
 
 	/* Take advantage of resource in an empty sched group */
-	if (imbalance == 0 && local->sum_nr_running == 0 &&
+	if (imbalance <= 1 && local->sum_nr_running == 0 &&
 	    busiest->sum_nr_running > 1)
 		imbalance = 2;
 
@@ -9751,6 +9762,15 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 		break;
 
 	case group_smt_balance:
+		/*
+		 * Check if we have spare CPUs on either SMT group to
+		 * choose has spare or fully busy handling.
+		 */
+		if (sgs->idle_cpus != 0 || busiest->idle_cpus != 0)
+			goto has_spare;
+
+		fallthrough;
+
 	case group_fully_busy:
 		/*
 		 * Select the fully busy group with highest avg_load. In
@@ -9790,6 +9810,7 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 			else
 				return true;
 		}
+has_spare:
 
 		/*
 		 * Select not overloaded group with lowest number of idle cpus
@@ -10901,6 +10922,7 @@ static int active_load_balance_cpu_stop(void *data);
 
 static int should_we_balance(struct lb_env *env)
 {
+	struct cpumask *swb_cpus = this_cpu_cpumask_var_ptr(should_we_balance_tmpmask);
 	struct sched_group *sg = env->sd->groups;
 	int cpu, idle_smt = -1;
 
@@ -10924,8 +10946,9 @@ static int should_we_balance(struct lb_env *env)
 		return 1;
 	}
 
+	cpumask_copy(swb_cpus, group_balance_mask(sg));
 	/* Try to find first idle CPU */
-	for_each_cpu_and(cpu, group_balance_mask(sg), env->cpus) {
+	for_each_cpu_and(cpu, swb_cpus, env->cpus) {
 		if (!idle_cpu(cpu))
 			continue;
 
@@ -10937,6 +10960,14 @@ static int should_we_balance(struct lb_env *env)
 		if (!(env->sd->flags & SD_SHARE_CPUCAPACITY) && !is_core_idle(cpu)) {
 			if (idle_smt == -1)
 				idle_smt = cpu;
+			/*
+			 * If the core is not idle, and first SMT sibling which is
+			 * idle has been found, then its not needed to check other
+			 * SMT siblings for idleness:
+			 */
+#ifdef CONFIG_SCHED_SMT
+			cpumask_andnot(swb_cpus, swb_cpus, cpu_smt_mask(cpu));
+#endif
 			continue;
 		}
 
@@ -12902,6 +12933,8 @@ __init void init_sched_fair_class(void)
 	for_each_possible_cpu(i) {
 		zalloc_cpumask_var_node(&per_cpu(load_balance_mask, i), GFP_KERNEL, cpu_to_node(i));
 		zalloc_cpumask_var_node(&per_cpu(select_rq_mask,    i), GFP_KERNEL, cpu_to_node(i));
+		zalloc_cpumask_var_node(&per_cpu(should_we_balance_tmpmask, i),
+					GFP_KERNEL, cpu_to_node(i));
 
 #ifdef CONFIG_CFS_BANDWIDTH
 		INIT_CSD(&cpu_rq(i)->cfsb_csd, __cfsb_csd_unthrottle, cpu_rq(i));
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 26f714003c1f..565f8374ddbb 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -373,6 +373,7 @@ EXPORT_SYMBOL_GPL(play_idle_precise);
 
 void cpu_startup_entry(enum cpuhp_state state)
 {
+	current->flags |= PF_IDLE;
 	arch_cpu_idle_prepare();
 	cpuhp_online_idle(state);
 	while (1)