Merge tag 'sched-core-2022-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Cleanups for SCHED_DEADLINE

 - Tracing updates/fixes

 - CPU Accounting fixes

 - First wave of changes to optimize the overhead of the scheduler
   build, from the fast-headers tree - including placeholder *_api.h
   headers for later header split-ups.

 - Preempt-dynamic using static_branch() for ARM64

 - Isolation housekeeping mask rework; preperatory for further changes

 - NUMA-balancing: deal with CPU-less nodes

 - NUMA-balancing: tune systems that have multiple LLC cache domains per
   node (eg. AMD)

 - Updates to RSEQ UAPI in preparation for glibc usage

 - Lots of RSEQ/selftests, for same

 - Add Suren as PSI co-maintainer

* tag 'sched-core-2022-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (81 commits)
  sched/headers: ARM needs asm/paravirt_api_clock.h too
  sched/numa: Fix boot crash on arm64 systems
  headers/prep: Fix header to build standalone: <linux/psi.h>
  sched/headers: Only include <linux/entry-common.h> when CONFIG_GENERIC_ENTRY=y
  cgroup: Fix suspicious rcu_dereference_check() usage warning
  sched/preempt: Tell about PREEMPT_DYNAMIC on kernel headers
  sched/topology: Remove redundant variable and fix incorrect type in build_sched_domains
  sched/deadline,rt: Remove unused parameter from pick_next_[rt|dl]_entity()
  sched/deadline,rt: Remove unused functions for !CONFIG_SMP
  sched/deadline: Use __node_2_[pdl|dle]() and rb_first_cached() consistently
  sched/deadline: Merge dl_task_can_attach() and dl_cpu_busy()
  sched/deadline: Move bandwidth mgmt and reclaim functions into sched class source file
  sched/deadline: Remove unused def_dl_bandwidth
  sched/tracing: Report TASK_RTLOCK_WAIT tasks as TASK_UNINTERRUPTIBLE
  sched/tracing: Don't re-read p->state when emitting sched_switch event
  sched/rt: Plug rt_mutex_setprio() vs push_rt_task() race
  sched/cpuacct: Remove redundant RCU read lock
  sched/cpuacct: Optimize away RCU read lock
  sched/cpuacct: Fix charge percpu cpuusage
  sched/headers: Reorganize, clean up and optimize kernel/sched/sched.h dependencies
  ...

1 files changed, 9 insertions, 9 deletions

diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index cffcd08f4ec8..3dbf351d12d5 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -6,13 +6,6 @@
  * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
  */
 
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include "sched.h"
-
-#include <linux/sched/cpufreq.h>
-#include <trace/events/power.h>
-
 #define IOWAIT_BOOST_MIN	(SCHED_CAPACITY_SCALE / 8)
 
 struct sugov_tunables {
@@ -289,6 +282,7 @@ static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time)
 	 * into the same scale so we can compare.
 	 */
 	boost = (sg_cpu->iowait_boost * sg_cpu->max) >> SCHED_CAPACITY_SHIFT;
+	boost = uclamp_rq_util_with(cpu_rq(sg_cpu->cpu), boost, NULL);
 	if (sg_cpu->util < boost)
 		sg_cpu->util = boost;
 }
@@ -348,8 +342,11 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
 	/*
 	 * Do not reduce the frequency if the CPU has not been idle
 	 * recently, as the reduction is likely to be premature then.
+	 *
+	 * Except when the rq is capped by uclamp_max.
 	 */
-	if (sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) {
+	if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) &&
+	    sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) {
 		next_f = sg_policy->next_freq;
 
 		/* Restore cached freq as next_freq has changed */
@@ -395,8 +392,11 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time,
 	/*
 	 * Do not reduce the target performance level if the CPU has not been
 	 * idle recently, as the reduction is likely to be premature then.
+	 *
+	 * Except when the rq is capped by uclamp_max.
 	 */
-	if (sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util)
+	if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) &&
+	    sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util)
 		sg_cpu->util = prev_util;
 
 	cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl),