1 files changed, 163 insertions, 117 deletions

diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 99ea5986038c..b958fe48e020 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -6,13 +6,19 @@
 #include <linux/bsearch.h>
 
 DEFINE_MUTEX(sched_domains_mutex);
+void sched_domains_mutex_lock(void)
+{
+	mutex_lock(&sched_domains_mutex);
+}
+void sched_domains_mutex_unlock(void)
+{
+	mutex_unlock(&sched_domains_mutex);
+}
 
 /* Protected by sched_domains_mutex: */
 static cpumask_var_t sched_domains_tmpmask;
 static cpumask_var_t sched_domains_tmpmask2;
 
-#ifdef CONFIG_SCHED_DEBUG
-
 static int __init sched_debug_setup(char *str)
 {
 	sched_debug_verbose = true;
@@ -151,15 +157,6 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu)
 			break;
 	}
 }
-#else /* !CONFIG_SCHED_DEBUG */
-
-# define sched_debug_verbose 0
-# define sched_domain_debug(sd, cpu) do { } while (0)
-static inline bool sched_debug(void)
-{
-	return false;
-}
-#endif /* CONFIG_SCHED_DEBUG */
 
 /* Generate a mask of SD flags with the SDF_NEEDS_GROUPS metaflag */
 #define SD_FLAG(name, mflags) (name * !!((mflags) & SDF_NEEDS_GROUPS)) |
@@ -215,8 +212,6 @@ static bool sched_energy_update;
 static bool sched_is_eas_possible(const struct cpumask *cpu_mask)
 {
 	bool any_asym_capacity = false;
-	struct cpufreq_policy *policy;
-	struct cpufreq_governor *gov;
 	int i;
 
 	/* EAS is enabled for asymmetric CPU capacity topologies. */
@@ -251,25 +246,12 @@ static bool sched_is_eas_possible(const struct cpumask *cpu_mask)
 		return false;
 	}
 
-	/* Do not attempt EAS if schedutil is not being used. */
-	for_each_cpu(i, cpu_mask) {
-		policy = cpufreq_cpu_get(i);
-		if (!policy) {
-			if (sched_debug()) {
-				pr_info("rd %*pbl: Checking EAS, cpufreq policy not set for CPU: %d",
-					cpumask_pr_args(cpu_mask), i);
-			}
-			return false;
-		}
-		gov = policy->governor;
-		cpufreq_cpu_put(policy);
-		if (gov != &schedutil_gov) {
-			if (sched_debug()) {
-				pr_info("rd %*pbl: Checking EAS, schedutil is mandatory\n",
-					cpumask_pr_args(cpu_mask));
-			}
-			return false;
+	if (!cpufreq_ready_for_eas(cpu_mask)) {
+		if (sched_debug()) {
+			pr_info("rd %*pbl: Checking EAS: cpufreq is not ready\n",
+				cpumask_pr_args(cpu_mask));
 		}
+		return false;
 	}
 
 	return true;
@@ -285,7 +267,7 @@ void rebuild_sched_domains_energy(void)
 }
 
 #ifdef CONFIG_PROC_SYSCTL
-static int sched_energy_aware_handler(struct ctl_table *table, int write,
+static int sched_energy_aware_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret, state;
@@ -312,7 +294,7 @@ static int sched_energy_aware_handler(struct ctl_table *table, int write,
 	return ret;
 }
 
-static struct ctl_table sched_energy_aware_sysctls[] = {
+static const struct ctl_table sched_energy_aware_sysctls[] = {
 	{
 		.procname       = "sched_energy_aware",
 		.data           = &sysctl_sched_energy_aware,
@@ -322,7 +304,6 @@ static struct ctl_table sched_energy_aware_sysctls[] = {
 		.extra1         = SYSCTL_ZERO,
 		.extra2         = SYSCTL_ONE,
 	},
-	{}
 };
 
 static int __init sched_energy_aware_sysctl_init(void)
@@ -502,7 +483,7 @@ void rq_attach_root(struct rq *rq, struct root_domain *rd)
 		cpumask_clear_cpu(rq->cpu, old_rd->span);
 
 		/*
-		 * If we dont want to free the old_rd yet then
+		 * If we don't want to free the old_rd yet then
 		 * set old_rd to NULL to skip the freeing later
 		 * in this function:
 		 */
@@ -517,6 +498,14 @@ void rq_attach_root(struct rq *rq, struct root_domain *rd)
 	if (cpumask_test_cpu(rq->cpu, cpu_active_mask))
 		set_rq_online(rq);
 
+	/*
+	 * Because the rq is not a task, dl_add_task_root_domain() did not
+	 * move the fair server bw to the rd if it already started.
+	 * Add it now.
+	 */
+	if (rq->fair_server.dl_server)
+		__dl_server_attach_root(&rq->fair_server, rq);
+
 	rq_unlock_irqrestore(rq, &rf);
 
 	if (old_rd)
@@ -553,7 +542,7 @@ static int init_rootdomain(struct root_domain *rd)
 	rd->rto_push_work = IRQ_WORK_INIT_HARD(rto_push_irq_work_func);
 #endif
 
-	rd->visit_gen = 0;
+	rd->visit_cookie = 0;
 	init_dl_bw(&rd->dl_bw);
 	if (cpudl_init(&rd->cpudl) != 0)
 		goto free_rto_mask;
@@ -1177,7 +1166,7 @@ fail:
  * uniquely identify each group (for a given domain):
  *
  *  - The first is the balance_cpu (see should_we_balance() and the
- *    load-balance blub in fair.c); for each group we only want 1 CPU to
+ *    load-balance blurb in fair.c); for each group we only want 1 CPU to
  *    continue balancing at a higher domain.
  *
  *  - The second is the sched_group_capacity; we want all identical groups
@@ -1329,14 +1318,63 @@ next:
 	update_group_capacity(sd, cpu);
 }
 
-/*
- * Asymmetric CPU capacity bits
- */
-struct asym_cap_data {
-	struct list_head link;
-	unsigned long capacity;
-	unsigned long cpus[];
-};
+#ifdef CONFIG_SMP
+
+/* Update the "asym_prefer_cpu" when arch_asym_cpu_priority() changes. */
+void sched_update_asym_prefer_cpu(int cpu, int old_prio, int new_prio)
+{
+	int asym_prefer_cpu = cpu;
+	struct sched_domain *sd;
+
+	guard(rcu)();
+
+	for_each_domain(cpu, sd) {
+		struct sched_group *sg;
+		int group_cpu;
+
+		if (!(sd->flags & SD_ASYM_PACKING))
+			continue;
+
+		/*
+		 * Groups of overlapping domain are replicated per NUMA
+		 * node and will require updating "asym_prefer_cpu" on
+		 * each local copy.
+		 *
+		 * If you are hitting this warning, consider moving
+		 * "sg->asym_prefer_cpu" to "sg->sgc->asym_prefer_cpu"
+		 * which is shared by all the overlapping groups.
+		 */
+		WARN_ON_ONCE(sd->flags & SD_OVERLAP);
+
+		sg = sd->groups;
+		if (cpu != sg->asym_prefer_cpu) {
+			/*
+			 * Since the parent is a superset of the current group,
+			 * if the cpu is not the "asym_prefer_cpu" at the
+			 * current level, it cannot be the preferred CPU at a
+			 * higher levels either.
+			 */
+			if (!sched_asym_prefer(cpu, sg->asym_prefer_cpu))
+				return;
+
+			WRITE_ONCE(sg->asym_prefer_cpu, cpu);
+			continue;
+		}
+
+		/* Ranking has improved; CPU is still the preferred one. */
+		if (new_prio >= old_prio)
+			continue;
+
+		for_each_cpu(group_cpu, sched_group_span(sg)) {
+			if (sched_asym_prefer(group_cpu, asym_prefer_cpu))
+				asym_prefer_cpu = group_cpu;
+		}
+
+		WRITE_ONCE(sg->asym_prefer_cpu, asym_prefer_cpu);
+	}
+}
+
+#endif /* CONFIG_SMP */
 
 /*
  * Set of available CPUs grouped by their corresponding capacities
@@ -1344,9 +1382,7 @@ struct asym_cap_data {
  * capacity.
  * The lifespan of data is unlimited.
  */
-static LIST_HEAD(asym_cap_list);
-
-#define cpu_capacity_span(asym_data) to_cpumask((asym_data)->cpus)
+LIST_HEAD(asym_cap_list);
 
 /*
  * Verify whether there is any CPU capacity asymmetry in a given sched domain.
@@ -1386,21 +1422,39 @@ asym_cpu_capacity_classify(const struct cpumask *sd_span,
 
 }
 
+static void free_asym_cap_entry(struct rcu_head *head)
+{
+	struct asym_cap_data *entry = container_of(head, struct asym_cap_data, rcu);
+	kfree(entry);
+}
+
 static inline void asym_cpu_capacity_update_data(int cpu)
 {
 	unsigned long capacity = arch_scale_cpu_capacity(cpu);
-	struct asym_cap_data *entry = NULL;
+	struct asym_cap_data *insert_entry = NULL;
+	struct asym_cap_data *entry;
 
+	/*
+	 * Search if capacity already exits. If not, track which the entry
+	 * where we should insert to keep the list ordered descending.
+	 */
 	list_for_each_entry(entry, &asym_cap_list, link) {
 		if (capacity == entry->capacity)
 			goto done;
+		else if (!insert_entry && capacity > entry->capacity)
+			insert_entry = list_prev_entry(entry, link);
 	}
 
 	entry = kzalloc(sizeof(*entry) + cpumask_size(), GFP_KERNEL);
 	if (WARN_ONCE(!entry, "Failed to allocate memory for asymmetry data\n"))
 		return;
 	entry->capacity = capacity;
-	list_add(&entry->link, &asym_cap_list);
+
+	/* If NULL then the new capacity is the smallest, add last. */
+	if (!insert_entry)
+		list_add_tail_rcu(&entry->link, &asym_cap_list);
+	else
+		list_add_rcu(&entry->link, &insert_entry->link);
 done:
 	__cpumask_set_cpu(cpu, cpu_capacity_span(entry));
 }
@@ -1423,8 +1477,8 @@ static void asym_cpu_capacity_scan(void)
 
 	list_for_each_entry_safe(entry, next, &asym_cap_list, link) {
 		if (cpumask_empty(cpu_capacity_span(entry))) {
-			list_del(&entry->link);
-			kfree(entry);
+			list_del_rcu(&entry->link);
+			call_rcu(&entry->rcu, free_asym_cap_entry);
 		}
 	}
 
@@ -1434,8 +1488,8 @@ static void asym_cpu_capacity_scan(void)
 	 */
 	if (list_is_singular(&asym_cap_list)) {
 		entry = list_first_entry(&asym_cap_list, typeof(*entry), link);
-		list_del(&entry->link);
-		kfree(entry);
+		list_del_rcu(&entry->link);
+		call_rcu(&entry->rcu, free_asym_cap_entry);
 	}
 }
 
@@ -1468,7 +1522,7 @@ static void set_domain_attribute(struct sched_domain *sd,
 	} else
 		request = attr->relax_domain_level;
 
-	if (sd->level > request) {
+	if (sd->level >= request) {
 		/* Turn off idle balance on this domain: */
 		sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
 	}
@@ -1621,9 +1675,7 @@ sd_init(struct sched_domain_topology_level *tl,
 		.max_newidle_lb_cost	= 0,
 		.last_decay_max_lb_cost	= jiffies,
 		.child			= child,
-#ifdef CONFIG_SCHED_DEBUG
 		.name			= tl->name,
-#endif
 	};
 
 	sd_span = sched_domain_span(sd);
@@ -1847,7 +1899,7 @@ void sched_init_numa(int offline_node)
 	struct cpumask ***masks;
 
 	/*
-	 * O(nr_nodes^2) deduplicating selection sort -- in order to find the
+	 * O(nr_nodes^2) de-duplicating selection sort -- in order to find the
 	 * unique distances in the node_distance() table.
 	 */
 	distance_map = bitmap_alloc(NR_DISTANCE_VALUES, GFP_KERNEL);
@@ -2089,7 +2141,7 @@ int sched_numa_find_closest(const struct cpumask *cpus, int cpu)
 	for (i = 0; i < sched_domains_numa_levels; i++) {
 		if (!masks[i][j])
 			break;
-		cpu = cpumask_any_and(cpus, masks[i][j]);
+		cpu = cpumask_any_and_distribute(cpus, masks[i][j]);
 		if (cpu < nr_cpu_ids) {
 			found = cpu;
 			break;
@@ -2263,9 +2315,7 @@ static int __sdt_alloc(const struct cpumask *cpu_map)
 			if (!sgc)
 				return -ENOMEM;
 
-#ifdef CONFIG_SCHED_DEBUG
 			sgc->id = j;
-#endif
 
 			*per_cpu_ptr(sdd->sgc, j) = sgc;
 		}
@@ -2324,10 +2374,8 @@ static struct sched_domain *build_sched_domain(struct sched_domain_topology_leve
 		if (!cpumask_subset(sched_domain_span(child),
 				    sched_domain_span(sd))) {
 			pr_err("BUG: arch topology borken\n");
-#ifdef CONFIG_SCHED_DEBUG
 			pr_err("     the %s domain not a subset of the %s domain\n",
 					child->name, sd->name);
-#endif
 			/* Fixup, ensure @sd has at least @child CPUs. */
 			cpumask_or(sched_domain_span(sd),
 				   sched_domain_span(sd),
@@ -2342,37 +2390,54 @@ static struct sched_domain *build_sched_domain(struct sched_domain_topology_leve
 
 /*
  * Ensure topology masks are sane, i.e. there are no conflicts (overlaps) for
- * any two given CPUs at this (non-NUMA) topology level.
+ * any two given CPUs on non-NUMA topology levels.
  */
-static bool topology_span_sane(struct sched_domain_topology_level *tl,
-			      const struct cpumask *cpu_map, int cpu)
+static bool topology_span_sane(const struct cpumask *cpu_map)
 {
-	int i;
+	struct sched_domain_topology_level *tl;
+	struct cpumask *covered, *id_seen;
+	int cpu;
 
-	/* NUMA levels are allowed to overlap */
-	if (tl->flags & SDTL_OVERLAP)
-		return true;
+	lockdep_assert_held(&sched_domains_mutex);
+	covered = sched_domains_tmpmask;
+	id_seen = sched_domains_tmpmask2;
 
-	/*
-	 * Non-NUMA levels cannot partially overlap - they must be either
-	 * completely equal or completely disjoint. Otherwise we can end up
-	 * breaking the sched_group lists - i.e. a later get_group() pass
-	 * breaks the linking done for an earlier span.
-	 */
-	for_each_cpu(i, cpu_map) {
-		if (i == cpu)
+	for_each_sd_topology(tl) {
+
+		/* NUMA levels are allowed to overlap */
+		if (tl->flags & SDTL_OVERLAP)
 			continue;
+
+		cpumask_clear(covered);
+		cpumask_clear(id_seen);
+
 		/*
-		 * We should 'and' all those masks with 'cpu_map' to exactly
-		 * match the topology we're about to build, but that can only
-		 * remove CPUs, which only lessens our ability to detect
-		 * overlaps
+		 * Non-NUMA levels cannot partially overlap - they must be either
+		 * completely equal or completely disjoint. Otherwise we can end up
+		 * breaking the sched_group lists - i.e. a later get_group() pass
+		 * breaks the linking done for an earlier span.
 		 */
-		if (!cpumask_equal(tl->mask(cpu), tl->mask(i)) &&
-		    cpumask_intersects(tl->mask(cpu), tl->mask(i)))
-			return false;
-	}
+		for_each_cpu(cpu, cpu_map) {
+			const struct cpumask *tl_cpu_mask = tl->mask(cpu);
+			int id;
 
+			/* lowest bit set in this mask is used as a unique id */
+			id = cpumask_first(tl_cpu_mask);
+
+			if (cpumask_test_cpu(id, id_seen)) {
+				/* First CPU has already been seen, ensure identical spans */
+				if (!cpumask_equal(tl->mask(id), tl_cpu_mask))
+					return false;
+			} else {
+				/* First CPU hasn't been seen before, ensure it's a completely new span */
+				if (cpumask_intersects(tl_cpu_mask, covered))
+					return false;
+
+				cpumask_or(covered, covered, tl_cpu_mask);
+				cpumask_set_cpu(id, id_seen);
+			}
+		}
+	}
 	return true;
 }
 
@@ -2405,9 +2470,6 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 		sd = NULL;
 		for_each_sd_topology(tl) {
 
-			if (WARN_ON(!topology_span_sane(tl, cpu_map, i)))
-				goto error;
-
 			sd = build_sched_domain(tl, cpu_map, attr, sd, i);
 
 			has_asym |= sd->flags & SD_ASYM_CPUCAPACITY;
@@ -2421,6 +2483,9 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 		}
 	}
 
+	if (WARN_ON(!topology_span_sane(cpu_map)))
+		goto error;
+
 	/* Build the groups for the domains */
 	for_each_cpu(i, cpu_map) {
 		for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
@@ -2507,16 +2572,9 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 	/* Attach the domains */
 	rcu_read_lock();
 	for_each_cpu(i, cpu_map) {
-		unsigned long capacity;
-
 		rq = cpu_rq(i);
 		sd = *per_cpu_ptr(d.sd, i);
 
-		capacity = arch_scale_cpu_capacity(i);
-		/* Use READ_ONCE()/WRITE_ONCE() to avoid load/store tearing: */
-		if (capacity > READ_ONCE(d.rd->max_cpu_capacity))
-			WRITE_ONCE(d.rd->max_cpu_capacity, capacity);
-
 		cpu_attach_domain(sd, d.rd, i);
 
 		if (lowest_flag_domain(i, SD_CLUSTER))
@@ -2530,10 +2588,8 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 	if (has_cluster)
 		static_branch_inc_cpuslocked(&sched_cluster_active);
 
-	if (rq && sched_debug_verbose) {
-		pr_info("root domain span: %*pbl (max cpu_capacity = %lu)\n",
-			cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity);
-	}
+	if (rq && sched_debug_verbose)
+		pr_info("root domain span: %*pbl\n", cpumask_pr_args(cpu_map));
 
 	ret = 0;
 error:
@@ -2681,7 +2737,7 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
  *
  * Call with hotplug lock and sched_domains_mutex held
  */
-void partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[],
+static void partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[],
 				    struct sched_domain_attr *dattr_new)
 {
 	bool __maybe_unused has_eas = false;
@@ -2713,19 +2769,8 @@ void partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[],
 	for (i = 0; i < ndoms_cur; i++) {
 		for (j = 0; j < n && !new_topology; j++) {
 			if (cpumask_equal(doms_cur[i], doms_new[j]) &&
-			    dattrs_equal(dattr_cur, i, dattr_new, j)) {
-				struct root_domain *rd;
-
-				/*
-				 * This domain won't be destroyed and as such
-				 * its dl_bw->total_bw needs to be cleared.  It
-				 * will be recomputed in function
-				 * update_tasks_root_domain().
-				 */
-				rd = cpu_rq(cpumask_any(doms_cur[i]))->rd;
-				dl_clear_root_domain(rd);
+			    dattrs_equal(dattr_cur, i, dattr_new, j))
 				goto match1;
-			}
 		}
 		/* No match - a current sched domain not in new doms_new[] */
 		detach_destroy_domains(doms_cur[i]);
@@ -2755,7 +2800,7 @@ match2:
 	}
 
 #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
-	/* Build perf. domains: */
+	/* Build perf domains: */
 	for (i = 0; i < ndoms_new; i++) {
 		for (j = 0; j < n && !sched_energy_update; j++) {
 			if (cpumask_equal(doms_new[i], doms_cur[j]) &&
@@ -2764,7 +2809,7 @@ match2:
 				goto match3;
 			}
 		}
-		/* No match - add perf. domains for a new rd */
+		/* No match - add perf domains for a new rd */
 		has_eas |= build_perf_domains(doms_new[i]);
 match3:
 		;
@@ -2782,6 +2827,7 @@ match3:
 	ndoms_cur = ndoms_new;
 
 	update_sched_domain_debugfs();
+	dl_rebuild_rd_accounting();
 }
 
 /*
@@ -2790,7 +2836,7 @@ match3:
 void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 			     struct sched_domain_attr *dattr_new)
 {
-	mutex_lock(&sched_domains_mutex);
+	sched_domains_mutex_lock();
 	partition_sched_domains_locked(ndoms_new, doms_new, dattr_new);
-	mutex_unlock(&sched_domains_mutex);
+	sched_domains_mutex_unlock();
 }