Merge tag 'sched-urgent-2024-05-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fixes from Ingo Molnar:

 - Fix a sched_balance_newidle setting bug

 - Fix bug in the setting of /sys/fs/cgroup/test/cpu.max.burst

 - Fix variable-shadowing build warning

 - Extend sched-domains debug output

 - Fix documentation

 - Fix comments

* tag 'sched-urgent-2024-05-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/core: Fix incorrect initialization of the 'burst' parameter in cpu_max_write()
  sched/fair: Remove stale FREQUENCY_UTIL comment
  sched/fair: Fix initial util_avg calculation
  docs: cgroup-v1: Clarify that domain levels are system-specific
  sched/debug: Dump domains' level
  sched/fair: Allow disabling sched_balance_newidle with sched_relax_domain_level
  arch/topology: Fix variable naming to avoid shadowing

Author: torvalds

Documentation/admin-guide/cgroup-v1/cpusets.rst

@@ -568,7 +568,7 @@ on the next tick.  For some applications in special situation, waiting
 
 The 'cpuset.sched_relax_domain_level' file allows you to request changing
 this searching range as you like.  This file takes int value which
-indicates size of searching range in levels ideally as follows,
+indicates size of searching range in levels approximately as follows,
 otherwise initial value -1 that indicates the cpuset has no request.
 
 ====== ===========================================================
@@ -581,6 +581,11 @@ otherwise initial value -1 that indicates the cpuset has no request.
    5   search system wide [on NUMA system]
 ====== ===========================================================
 
+Not all levels can be present and values can change depending on the
+system architecture and kernel configuration. Check
+/sys/kernel/debug/sched/domains/cpu*/domain*/ for system-specific
+details.
+
 The system default is architecture dependent.  The system default
 can be changed using the relax_domain_level= boot parameter.
 

drivers/base/arch_topology.c

@@ -179,7 +179,7 @@ DEFINE_PER_CPU(unsigned long, hw_pressure);
 void topology_update_hw_pressure(const struct cpumask *cpus,
 				      unsigned long capped_freq)
 {
-	unsigned long max_capacity, capacity, hw_pressure;
+	unsigned long max_capacity, capacity, pressure;
 	u32 max_freq;
 	int cpu;
 
@@ -196,12 +196,12 @@ void topology_update_hw_pressure(const struct cpumask *cpus,
 	else
 		capacity = mult_frac(max_capacity, capped_freq, max_freq);
 
-	hw_pressure = max_capacity - capacity;
+	pressure = max_capacity - capacity;
 
-	trace_hw_pressure_update(cpu, hw_pressure);
+	trace_hw_pressure_update(cpu, pressure);
 
 	for_each_cpu(cpu, cpus)
-		WRITE_ONCE(per_cpu(hw_pressure, cpu), hw_pressure);
+		WRITE_ONCE(per_cpu(hw_pressure, cpu), pressure);
 }
 EXPORT_SYMBOL_GPL(topology_update_hw_pressure);
 

kernel/cgroup/cpuset.c

@@ -2941,7 +2941,7 @@ bool current_cpuset_is_being_rebound(void)
 static int update_relax_domain_level(struct cpuset *cs, s64 val)
 {
 #ifdef CONFIG_SMP
-	if (val < -1 || val >= sched_domain_level_max)
+	if (val < -1 || val > sched_domain_level_max + 1)
 		return -EINVAL;
 #endif
 

kernel/sched/core.c

@@ -11401,7 +11401,7 @@ static ssize_t cpu_max_write(struct kernfs_open_file *of,
 {
 	struct task_group *tg = css_tg(of_css(of));
 	u64 period = tg_get_cfs_period(tg);
-	u64 burst = tg_get_cfs_burst(tg);
+	u64 burst = tg->cfs_bandwidth.burst;
 	u64 quota;
 	int ret;
 

kernel/sched/debug.c

@@ -425,6 +425,7 @@ static void register_sd(struct sched_domain *sd, struct dentry *parent)
 
 	debugfs_create_file("flags", 0444, parent, &sd->flags, &sd_flags_fops);
 	debugfs_create_file("groups_flags", 0444, parent, &sd->groups->flags, &sd_flags_fops);
+	debugfs_create_u32("level", 0444, parent, (u32 *)&sd->level);
 }
 
 void update_sched_domain_debugfs(void)

kernel/sched/fair.c

@@ -1030,7 +1030,8 @@ void init_entity_runnable_average(struct sched_entity *se)
  * With new tasks being created, their initial util_avgs are extrapolated
  * based on the cfs_rq's current util_avg:
  *
- *   util_avg = cfs_rq->util_avg / (cfs_rq->load_avg + 1) * se.load.weight
+ *   util_avg = cfs_rq->avg.util_avg / (cfs_rq->avg.load_avg + 1)
+ *		* se_weight(se)
  *
  * However, in many cases, the above util_avg does not give a desired
  * value. Moreover, the sum of the util_avgs may be divergent, such
@@ -1077,7 +1078,7 @@ void post_init_entity_util_avg(struct task_struct *p)
 
 	if (cap > 0) {
 		if (cfs_rq->avg.util_avg != 0) {
-			sa->util_avg  = cfs_rq->avg.util_avg * se->load.weight;
+			sa->util_avg  = cfs_rq->avg.util_avg * se_weight(se);
 			sa->util_avg /= (cfs_rq->avg.load_avg + 1);
 
 			if (sa->util_avg > cap)
@@ -7898,8 +7899,8 @@ eenv_pd_max_util(struct energy_env *eenv, struct cpumask *pd_cpus,
 		 * Performance domain frequency: utilization clamping
 		 * must be considered since it affects the selection
 		 * of the performance domain frequency.
-		 * NOTE: in case RT tasks are running, by default the
-		 * FREQUENCY_UTIL's utilization can be max OPP.
+		 * NOTE: in case RT tasks are running, by default the min
+		 * utilization can be max OPP.
 		 */
 		eff_util = effective_cpu_util(cpu, util, &min, &max);
 

kernel/sched/topology.c

@@ -1474,7 +1474,7 @@ 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);
 	}