Merge tag 'sched-core-2024-05-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Add cpufreq pressure feedback for the scheduler

 - Rework misfit load-balancing wrt affinity restrictions

 - Clean up and simplify the code around ::overutilized and
   ::overload access.

 - Simplify sched_balance_newidle()

 - Bump SCHEDSTAT_VERSION to 16 due to a cleanup of CPU_MAX_IDLE_TYPES
   handling that changed the output.

 - Rework & clean up <asm/vtime.h> interactions wrt arch_vtime_task_switch()

 - Reorganize, clean up and unify most of the higher level
   scheduler balancing function names around the sched_balance_*()
   prefix

 - Simplify the balancing flag code (sched_balance_running)

 - Miscellaneous cleanups & fixes

* tag 'sched-core-2024-05-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (50 commits)
  sched/pelt: Remove shift of thermal clock
  sched/cpufreq: Rename arch_update_thermal_pressure() => arch_update_hw_pressure()
  thermal/cpufreq: Remove arch_update_thermal_pressure()
  sched/cpufreq: Take cpufreq feedback into account
  cpufreq: Add a cpufreq pressure feedback for the scheduler
  sched/fair: Fix update of rd->sg_overutilized
  sched/vtime: Do not include <asm/vtime.h> header
  s390/irq,nmi: Include <asm/vtime.h> header directly
  s390/vtime: Remove unused __ARCH_HAS_VTIME_TASK_SWITCH leftover
  sched/vtime: Get rid of generic vtime_task_switch() implementation
  sched/vtime: Remove confusing arch_vtime_task_switch() declaration
  sched/balancing: Simplify the sg_status bitmask and use separate ->overloaded and ->overutilized flags
  sched/fair: Rename set_rd_overutilized_status() to set_rd_overutilized()
  sched/fair: Rename SG_OVERLOAD to SG_OVERLOADED
  sched/fair: Rename {set|get}_rd_overload() to {set|get}_rd_overloaded()
  sched/fair: Rename root_domain::overload to ::overloaded
  sched/fair: Use helper functions to access root_domain::overload
  sched/fair: Check root_domain::overload value before update
  sched/fair: Combine EAS check with root_domain::overutilized access
  sched/fair: Simplify the continue_balancing logic in sched_balance_newidle()
  ...

1 files changed, 27 insertions, 29 deletions

diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 99ea5986038c..63aecd2a7a9f 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1330,23 +1330,12 @@ next:
 }
 
 /*
- * Asymmetric CPU capacity bits
- */
-struct asym_cap_data {
-	struct list_head link;
-	unsigned long capacity;
-	unsigned long cpus[];
-};
-
-/*
  * Set of available CPUs grouped by their corresponding capacities
  * Each list entry contains a CPU mask reflecting CPUs that share the same
  * 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 +1375,39 @@ 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 descendingly.
+	 */
 	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 +1430,8 @@ 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 +1441,8 @@ 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);
 	}
 }
 
@@ -2507,16 +2514,9 @@ 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 +2530,8 @@ 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: