Merge tag 'sched-core-2020-12-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Thomas Gleixner:

 - migrate_disable/enable() support which originates from the RT tree
   and is now a prerequisite for the new preemptible kmap_local() API
   which aims to replace kmap_atomic().

 - A fair amount of topology and NUMA related improvements

 - Improvements for the frequency invariant calculations

 - Enhanced robustness for the global CPU priority tracking and decision
   making

 - The usual small fixes and enhancements all over the place

* tag 'sched-core-2020-12-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (61 commits)
  sched/fair: Trivial correction of the newidle_balance() comment
  sched/fair: Clear SMT siblings after determining the core is not idle
  sched: Fix kernel-doc markup
  x86: Print ratio freq_max/freq_base used in frequency invariance calculations
  x86, sched: Use midpoint of max_boost and max_P for frequency invariance on AMD EPYC
  x86, sched: Calculate frequency invariance for AMD systems
  irq_work: Optimize irq_work_single()
  smp: Cleanup smp_call_function*()
  irq_work: Cleanup
  sched: Limit the amount of NUMA imbalance that can exist at fork time
  sched/numa: Allow a floating imbalance between NUMA nodes
  sched: Avoid unnecessary calculation of load imbalance at clone time
  sched/numa: Rename nr_running and break out the magic number
  sched: Make migrate_disable/enable() independent of RT
  sched/topology: Condition EAS enablement on FIE support
  arm64: Rebuild sched domains on invariance status changes
  sched/topology,schedutil: Wrap sched domains rebuild
  sched/uclamp: Allow to reset a task uclamp constraint value
  sched/core: Fix typos in comments
  Documentation: scheduler: fix information on arch SD flags, sched_domain and sched_debug
  ...

1 files changed, 54 insertions, 7 deletions

diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index dd7770226086..5d3675c7a76b 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -211,6 +211,15 @@ unsigned int sysctl_sched_energy_aware = 1;
 DEFINE_MUTEX(sched_energy_mutex);
 bool sched_energy_update;
 
+void rebuild_sched_domains_energy(void)
+{
+	mutex_lock(&sched_energy_mutex);
+	sched_energy_update = true;
+	rebuild_sched_domains();
+	sched_energy_update = false;
+	mutex_unlock(&sched_energy_mutex);
+}
+
 #ifdef CONFIG_PROC_SYSCTL
 int sched_energy_aware_handler(struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
@@ -223,13 +232,8 @@ int sched_energy_aware_handler(struct ctl_table *table, int write,
 	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	if (!ret && write) {
 		state = static_branch_unlikely(&sched_energy_present);
-		if (state != sysctl_sched_energy_aware) {
-			mutex_lock(&sched_energy_mutex);
-			sched_energy_update = 1;
-			rebuild_sched_domains();
-			sched_energy_update = 0;
-			mutex_unlock(&sched_energy_mutex);
-		}
+		if (state != sysctl_sched_energy_aware)
+			rebuild_sched_domains_energy();
 	}
 
 	return ret;
@@ -324,6 +328,7 @@ static void sched_energy_set(bool has_eas)
  *    3. no SMT is detected.
  *    4. the EM complexity is low enough to keep scheduling overheads low;
  *    5. schedutil is driving the frequency of all CPUs of the rd;
+ *    6. frequency invariance support is present;
  *
  * The complexity of the Energy Model is defined as:
  *
@@ -372,6 +377,14 @@ static bool build_perf_domains(const struct cpumask *cpu_map)
 		goto free;
 	}
 
+	if (!arch_scale_freq_invariant()) {
+		if (sched_debug()) {
+			pr_warn("rd %*pbl: Disabling EAS: frequency-invariant load tracking not yet supported",
+				cpumask_pr_args(cpu_map));
+		}
+		goto free;
+	}
+
 	for_each_cpu(i, cpu_map) {
 		/* Skip already covered CPUs. */
 		if (find_pd(pd, i))
@@ -516,6 +529,7 @@ static int init_rootdomain(struct root_domain *rd)
 	init_irq_work(&rd->rto_push_work, rto_push_irq_work_func);
 #endif
 
+	rd->visit_gen = 0;
 	init_dl_bw(&rd->dl_bw);
 	if (cpudl_init(&rd->cpudl) != 0)
 		goto free_rto_mask;
@@ -674,6 +688,7 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
 	struct sched_domain *tmp;
+	int numa_distance = 0;
 
 	/* Remove the sched domains which do not contribute to scheduling. */
 	for (tmp = sd; tmp; ) {
@@ -705,6 +720,38 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 			sd->child = NULL;
 	}
 
+	for (tmp = sd; tmp; tmp = tmp->parent)
+		numa_distance += !!(tmp->flags & SD_NUMA);
+
+	/*
+	 * FIXME: Diameter >=3 is misrepresented.
+	 *
+	 * Smallest diameter=3 topology is:
+	 *
+	 *   node   0   1   2   3
+	 *     0:  10  20  30  40
+	 *     1:  20  10  20  30
+	 *     2:  30  20  10  20
+	 *     3:  40  30  20  10
+	 *
+	 *   0 --- 1 --- 2 --- 3
+	 *
+	 * NUMA-3	0-3		N/A		N/A		0-3
+	 *  groups:	{0-2},{1-3}					{1-3},{0-2}
+	 *
+	 * NUMA-2	0-2		0-3		0-3		1-3
+	 *  groups:	{0-1},{1-3}	{0-2},{2-3}	{1-3},{0-1}	{2-3},{0-2}
+	 *
+	 * NUMA-1	0-1		0-2		1-3		2-3
+	 *  groups:	{0},{1}		{1},{2},{0}	{2},{3},{1}	{3},{2}
+	 *
+	 * NUMA-0	0		1		2		3
+	 *
+	 * The NUMA-2 groups for nodes 0 and 3 are obviously buggered, as the
+	 * group span isn't a subset of the domain span.
+	 */
+	WARN_ONCE(numa_distance > 2, "Shortest NUMA path spans too many nodes\n");
+
 	sched_domain_debug(sd, cpu);
 
 	rq_attach_root(rq, rd);