Merge branch 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm…

…/linux/kernel/git/tip/tip

Pull scheduler fixes from Ingo Molnar:
 "Misc fixes: various scheduler metrics corner case fixes, a
  sched_features deadlock fix, and a topology fix for certain NUMA
  systems"

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/fair: Fix kernel-doc notation warning
  sched/fair: Fix load_balance redo for !imbalance
  sched/fair: Fix scale_rt_capacity() for SMT
  sched/fair: Fix vruntime_normalized() for remote non-migration wakeup
  sched/pelt: Fix update_blocked_averages() for RT and DL classes
  sched/topology: Set correct NUMA topology type
  sched/debug: Fix potential deadlock when writing to sched_features

kernel/sched/debug.c

@@ -89,12 +89,12 @@ struct static_key sched_feat_keys[__SCHED_FEAT_NR] = {
 
 static void sched_feat_disable(int i)
 {
-	static_key_disable(&sched_feat_keys[i]);
+	static_key_disable_cpuslocked(&sched_feat_keys[i]);
 }
 
 static void sched_feat_enable(int i)
 {
-	static_key_enable(&sched_feat_keys[i]);
+	static_key_enable_cpuslocked(&sched_feat_keys[i]);
 }
 #else
 static void sched_feat_disable(int i) { };
@@ -146,9 +146,11 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
 
 	/* Ensure the static_key remains in a consistent state */
 	inode = file_inode(filp);
+	cpus_read_lock();
 	inode_lock(inode);
 	ret = sched_feat_set(cmp);
 	inode_unlock(inode);
+	cpus_read_unlock();
 	if (ret < 0)
 		return ret;
 

kernel/sched/fair.c

@@ -3362,6 +3362,7 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
  * attach_entity_load_avg - attach this entity to its cfs_rq load avg
  * @cfs_rq: cfs_rq to attach to
  * @se: sched_entity to attach
+ * @flags: migration hints
  *
  * Must call update_cfs_rq_load_avg() before this, since we rely on
  * cfs_rq->avg.last_update_time being current.
@@ -7263,6 +7264,7 @@ static void update_blocked_averages(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
 	struct cfs_rq *cfs_rq, *pos;
+	const struct sched_class *curr_class;
 	struct rq_flags rf;
 	bool done = true;
 
@@ -7299,8 +7301,10 @@ static void update_blocked_averages(int cpu)
 		if (cfs_rq_has_blocked(cfs_rq))
 			done = false;
 	}
-	update_rt_rq_load_avg(rq_clock_task(rq), rq, 0);
-	update_dl_rq_load_avg(rq_clock_task(rq), rq, 0);
+
+	curr_class = rq->curr->sched_class;
+	update_rt_rq_load_avg(rq_clock_task(rq), rq, curr_class == &rt_sched_class);
+	update_dl_rq_load_avg(rq_clock_task(rq), rq, curr_class == &dl_sched_class);
 	update_irq_load_avg(rq, 0);
 	/* Don't need periodic decay once load/util_avg are null */
 	if (others_have_blocked(rq))
@@ -7365,13 +7369,16 @@ static inline void update_blocked_averages(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
 	struct cfs_rq *cfs_rq = &rq->cfs;
+	const struct sched_class *curr_class;
 	struct rq_flags rf;
 
 	rq_lock_irqsave(rq, &rf);
 	update_rq_clock(rq);
 	update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq);
-	update_rt_rq_load_avg(rq_clock_task(rq), rq, 0);
-	update_dl_rq_load_avg(rq_clock_task(rq), rq, 0);
+
+	curr_class = rq->curr->sched_class;
+	update_rt_rq_load_avg(rq_clock_task(rq), rq, curr_class == &rt_sched_class);
+	update_dl_rq_load_avg(rq_clock_task(rq), rq, curr_class == &dl_sched_class);
 	update_irq_load_avg(rq, 0);
 #ifdef CONFIG_NO_HZ_COMMON
 	rq->last_blocked_load_update_tick = jiffies;
@@ -7482,10 +7489,10 @@ static inline int get_sd_load_idx(struct sched_domain *sd,
 	return load_idx;
 }
 
-static unsigned long scale_rt_capacity(int cpu)
+static unsigned long scale_rt_capacity(struct sched_domain *sd, int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	unsigned long max = arch_scale_cpu_capacity(NULL, cpu);
+	unsigned long max = arch_scale_cpu_capacity(sd, cpu);
 	unsigned long used, free;
 	unsigned long irq;
 
@@ -7507,7 +7514,7 @@ static unsigned long scale_rt_capacity(int cpu)
 
 static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 {
-	unsigned long capacity = scale_rt_capacity(cpu);
+	unsigned long capacity = scale_rt_capacity(sd, cpu);
 	struct sched_group *sdg = sd->groups;
 
 	cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(sd, cpu);
@@ -8269,7 +8276,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
 force_balance:
 	/* Looks like there is an imbalance. Compute it */
 	calculate_imbalance(env, &sds);
-	return sds.busiest;
+	return env->imbalance ? sds.busiest : NULL;
 
 out_balanced:
 	env->imbalance = 0;
@@ -9638,7 +9645,8 @@ static inline bool vruntime_normalized(struct task_struct *p)
 	 * - A task which has been woken up by try_to_wake_up() and
 	 *   waiting for actually being woken up by sched_ttwu_pending().
 	 */
-	if (!se->sum_exec_runtime || p->state == TASK_WAKING)
+	if (!se->sum_exec_runtime ||
+	    (p->state == TASK_WAKING && p->sched_remote_wakeup))
 		return true;
 
 	return false;

kernel/sched/topology.c

@@ -1295,7 +1295,7 @@ static void init_numa_topology_type(void)
 
 	n = sched_max_numa_distance;
 
-	if (sched_domains_numa_levels <= 1) {
+	if (sched_domains_numa_levels <= 2) {
 		sched_numa_topology_type = NUMA_DIRECT;
 		return;
 	}
@@ -1380,9 +1380,6 @@ void sched_init_numa(void)
 			break;
 	}
 
-	if (!level)
-		return;
-
 	/*
 	 * 'level' contains the number of unique distances
 	 *