Merge tag 'sched-core-2023-06-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "Scheduler SMP load-balancer improvements:

   - Avoid unnecessary migrations within SMT domains on hybrid systems.

     Problem:

        On hybrid CPU systems, (processors with a mixture of
        higher-frequency SMT cores and lower-frequency non-SMT cores),
        under the old code lower-priority CPUs pulled tasks from the
        higher-priority cores if more than one SMT sibling was busy -
        resulting in many unnecessary task migrations.

     Solution:

        The new code improves the load balancer to recognize SMT cores
        with more than one busy sibling and allows lower-priority CPUs
        to pull tasks, which avoids superfluous migrations and lets
        lower-priority cores inspect all SMT siblings for the busiest
        queue.

   - Implement the 'runnable boosting' feature in the EAS balancer:
     consider CPU contention in frequency, EAS max util & load-balance
     busiest CPU selection.

     This improves CPU utilization for certain workloads, while leaves
     other key workloads unchanged.

  Scheduler infrastructure improvements:

   - Rewrite the scheduler topology setup code by consolidating it into
     the build_sched_topology() helper function and building it
     dynamically on the fly.

   - Resolve the local_clock() vs. noinstr complications by rewriting
     the code: provide separate sched_clock_noinstr() and
     local_clock_noinstr() functions to be used in instrumentation code,
     and make sure it is all instrumentation-safe.

  Fixes:

   - Fix a kthread_park() race with wait_woken()

   - Fix misc wait_task_inactive() bugs unearthed by the -rt merge:
       - Fix UP PREEMPT bug by unifying the SMP and UP implementations
       - Fix task_struct::saved_state handling

   - Fix various rq clock update bugs, unearthed by turning on the rq
     clock debugging code.

   - Fix the PSI WINDOW_MIN_US trigger limit, which was easy to trigger
     by creating enough cgroups, by removing the warnign and restricting
     window size triggers to PSI file write-permission or
     CAP_SYS_RESOURCE.

   - Propagate SMT flags in the topology when removing degenerate domain

   - Fix grub_reclaim() calculation bug in the deadline scheduler code

   - Avoid resetting the min update period when it is unnecessary, in
     psi_trigger_destroy().

   - Don't balance a task to its current running CPU in load_balance(),
     which was possible on certain NUMA topologies with overlapping
     groups.

   - Fix the sched-debug printing of rq->nr_uninterruptible

  Cleanups:

   - Address various -Wmissing-prototype warnings, as a preparation to
     (maybe) enable this warning in the future.

   - Remove unused code

   - Mark more functions __init

   - Fix shadow-variable warnings"

* tag 'sched-core-2023-06-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (50 commits)
  sched/core: Avoid multiple calling update_rq_clock() in __cfsb_csd_unthrottle()
  sched/core: Avoid double calling update_rq_clock() in __balance_push_cpu_stop()
  sched/core: Fixed missing rq clock update before calling set_rq_offline()
  sched/deadline: Update GRUB description in the documentation
  sched/deadline: Fix bandwidth reclaim equation in GRUB
  sched/wait: Fix a kthread_park race with wait_woken()
  sched/topology: Mark set_sched_topology() __init
  sched/fair: Rename variable cpu_util eff_util
  arm64/arch_timer: Fix MMIO byteswap
  sched/fair, cpufreq: Introduce 'runnable boosting'
  sched/fair: Refactor CPU utilization functions
  cpuidle: Use local_clock_noinstr()
  sched/clock: Provide local_clock_noinstr()
  x86/tsc: Provide sched_clock_noinstr()
  clocksource: hyper-v: Provide noinstr sched_clock()
  clocksource: hyper-v: Adjust hv_read_tsc_page_tsc() to avoid special casing U64_MAX
  x86/vdso: Fix gettimeofday masking
  math64: Always inline u128 version of mul_u64_u64_shr()
  s390/time: Provide sched_clock_noinstr()
  loongarch: Provide noinstr sched_clock_read()
  ...

1 files changed, 44 insertions, 52 deletions

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 8779a7ed3e87..ed2d51960a7d 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -602,7 +602,7 @@ static int x86_core_flags(void)
 #ifdef CONFIG_SCHED_SMT
 static int x86_smt_flags(void)
 {
-	return cpu_smt_flags() | x86_sched_itmt_flags();
+	return cpu_smt_flags();
 }
 #endif
 #ifdef CONFIG_SCHED_CLUSTER
@@ -613,50 +613,57 @@ static int x86_cluster_flags(void)
 #endif
 #endif
 
-static struct sched_domain_topology_level x86_numa_in_package_topology[] = {
-#ifdef CONFIG_SCHED_SMT
-	{ cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) },
-#endif
-#ifdef CONFIG_SCHED_CLUSTER
-	{ cpu_clustergroup_mask, x86_cluster_flags, SD_INIT_NAME(CLS) },
-#endif
-#ifdef CONFIG_SCHED_MC
-	{ cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC) },
-#endif
-	{ NULL, },
-};
+/*
+ * Set if a package/die has multiple NUMA nodes inside.
+ * AMD Magny-Cours, Intel Cluster-on-Die, and Intel
+ * Sub-NUMA Clustering have this.
+ */
+static bool x86_has_numa_in_package;
 
-static struct sched_domain_topology_level x86_hybrid_topology[] = {
-#ifdef CONFIG_SCHED_SMT
-	{ cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) },
-#endif
-#ifdef CONFIG_SCHED_MC
-	{ cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC) },
-#endif
-	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
-	{ NULL, },
-};
+static struct sched_domain_topology_level x86_topology[6];
+
+static void __init build_sched_topology(void)
+{
+	int i = 0;
 
-static struct sched_domain_topology_level x86_topology[] = {
 #ifdef CONFIG_SCHED_SMT
-	{ cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) },
+	x86_topology[i++] = (struct sched_domain_topology_level){
+		cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT)
+	};
 #endif
 #ifdef CONFIG_SCHED_CLUSTER
-	{ cpu_clustergroup_mask, x86_cluster_flags, SD_INIT_NAME(CLS) },
+	/*
+	 * For now, skip the cluster domain on Hybrid.
+	 */
+	if (!cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) {
+		x86_topology[i++] = (struct sched_domain_topology_level){
+			cpu_clustergroup_mask, x86_cluster_flags, SD_INIT_NAME(CLS)
+		};
+	}
 #endif
 #ifdef CONFIG_SCHED_MC
-	{ cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC) },
+	x86_topology[i++] = (struct sched_domain_topology_level){
+		cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC)
+	};
 #endif
-	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
-	{ NULL, },
-};
+	/*
+	 * When there is NUMA topology inside the package skip the DIE domain
+	 * since the NUMA domains will auto-magically create the right spanning
+	 * domains based on the SLIT.
+	 */
+	if (!x86_has_numa_in_package) {
+		x86_topology[i++] = (struct sched_domain_topology_level){
+			cpu_cpu_mask, SD_INIT_NAME(DIE)
+		};
+	}
 
-/*
- * Set if a package/die has multiple NUMA nodes inside.
- * AMD Magny-Cours, Intel Cluster-on-Die, and Intel
- * Sub-NUMA Clustering have this.
- */
-static bool x86_has_numa_in_package;
+	/*
+	 * There must be one trailing NULL entry left.
+	 */
+	BUG_ON(i >= ARRAY_SIZE(x86_topology)-1);
+
+	set_sched_topology(x86_topology);
+}
 
 void set_cpu_sibling_map(int cpu)
 {
@@ -1264,15 +1271,6 @@ void __init smp_prepare_cpus_common(void)
 		zalloc_cpumask_var(&per_cpu(cpu_l2c_shared_map, i), GFP_KERNEL);
 	}
 
-	/*
-	 * Set 'default' x86 topology, this matches default_topology() in that
-	 * it has NUMA nodes as a topology level. See also
-	 * native_smp_cpus_done().
-	 *
-	 * Must be done before set_cpus_sibling_map() is ran.
-	 */
-	set_sched_topology(x86_topology);
-
 	set_cpu_sibling_map(0);
 }
 
@@ -1393,13 +1391,7 @@ void __init native_smp_cpus_done(unsigned int max_cpus)
 	pr_debug("Boot done\n");
 
 	calculate_max_logical_packages();
-
-	/* XXX for now assume numa-in-package and hybrid don't overlap */
-	if (x86_has_numa_in_package)
-		set_sched_topology(x86_numa_in_package_topology);
-	if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU))
-		set_sched_topology(x86_hybrid_topology);
-
+	build_sched_topology();
 	nmi_selftest();
 	impress_friends();
 	cache_aps_init();