Merge tag 'sched-core-2020-12-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Thomas Gleixner:

 - migrate_disable/enable() support which originates from the RT tree
   and is now a prerequisite for the new preemptible kmap_local() API
   which aims to replace kmap_atomic().

 - A fair amount of topology and NUMA related improvements

 - Improvements for the frequency invariant calculations

 - Enhanced robustness for the global CPU priority tracking and decision
   making

 - The usual small fixes and enhancements all over the place

* tag 'sched-core-2020-12-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (61 commits)
  sched/fair: Trivial correction of the newidle_balance() comment
  sched/fair: Clear SMT siblings after determining the core is not idle
  sched: Fix kernel-doc markup
  x86: Print ratio freq_max/freq_base used in frequency invariance calculations
  x86, sched: Use midpoint of max_boost and max_P for frequency invariance on AMD EPYC
  x86, sched: Calculate frequency invariance for AMD systems
  irq_work: Optimize irq_work_single()
  smp: Cleanup smp_call_function*()
  irq_work: Cleanup
  sched: Limit the amount of NUMA imbalance that can exist at fork time
  sched/numa: Allow a floating imbalance between NUMA nodes
  sched: Avoid unnecessary calculation of load imbalance at clone time
  sched/numa: Rename nr_running and break out the magic number
  sched: Make migrate_disable/enable() independent of RT
  sched/topology: Condition EAS enablement on FIE support
  arm64: Rebuild sched domains on invariance status changes
  sched/topology,schedutil: Wrap sched domains rebuild
  sched/uclamp: Allow to reset a task uclamp constraint value
  sched/core: Fix typos in comments
  Documentation: scheduler: fix information on arch SD flags, sched_domain and sched_debug
  ...

8 files changed, 105 insertions, 37 deletions

diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index b8026ec684ba..c8308befdb1e 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -223,6 +223,7 @@ static DEFINE_STATIC_KEY_FALSE(amu_fie_key);
 
 static int __init init_amu_fie(void)
 {
+	bool invariance_status = topology_scale_freq_invariant();
 	cpumask_var_t valid_cpus;
 	bool have_policy = false;
 	int ret = 0;
@@ -269,6 +270,15 @@ static int __init init_amu_fie(void)
 	if (!topology_scale_freq_invariant())
 		static_branch_disable(&amu_fie_key);
 
+	/*
+	 * Task scheduler behavior depends on frequency invariance support,
+	 * either cpufreq or counter driven. If the support status changes as
+	 * a result of counter initialisation and use, retrigger the build of
+	 * scheduling domains to ensure the information is propagated properly.
+	 */
+	if (invariance_status != topology_scale_freq_invariant())
+		rebuild_sched_domains_energy();
+
 free_valid_mask:
 	free_cpumask_var(valid_cpus);
 
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 75ebd8d7bd5d..d7e288f3a1e7 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -702,7 +702,6 @@ unsigned long arch_align_stack(unsigned long sp)
 	return sp & ALMASK;
 }
 
-static DEFINE_PER_CPU(call_single_data_t, backtrace_csd);
 static struct cpumask backtrace_csd_busy;
 
 static void handle_backtrace(void *info)
@@ -711,6 +710,9 @@ static void handle_backtrace(void *info)
 	cpumask_clear_cpu(smp_processor_id(), &backtrace_csd_busy);
 }
 
+static DEFINE_PER_CPU(call_single_data_t, backtrace_csd) =
+	CSD_INIT(handle_backtrace, NULL);
+
 static void raise_backtrace(cpumask_t *mask)
 {
 	call_single_data_t *csd;
@@ -730,7 +732,6 @@ static void raise_backtrace(cpumask_t *mask)
 		}
 
 		csd = &per_cpu(backtrace_csd, cpu);
-		csd->func = handle_backtrace;
 		smp_call_function_single_async(cpu, csd);
 	}
 }
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 48d84d5fcc36..74b9102fd06e 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -687,36 +687,23 @@ EXPORT_SYMBOL(flush_tlb_one);
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 
-static DEFINE_PER_CPU(call_single_data_t, tick_broadcast_csd);
-
-void tick_broadcast(const struct cpumask *mask)
-{
-	call_single_data_t *csd;
-	int cpu;
-
-	for_each_cpu(cpu, mask) {
-		csd = &per_cpu(tick_broadcast_csd, cpu);
-		smp_call_function_single_async(cpu, csd);
-	}
-}
-
 static void tick_broadcast_callee(void *info)
 {
 	tick_receive_broadcast();
 }
 
-static int __init tick_broadcast_init(void)
+static DEFINE_PER_CPU(call_single_data_t, tick_broadcast_csd) =
+	CSD_INIT(tick_broadcast_callee, NULL);
+
+void tick_broadcast(const struct cpumask *mask)
 {
 	call_single_data_t *csd;
 	int cpu;
 
-	for (cpu = 0; cpu < NR_CPUS; cpu++) {
+	for_each_cpu(cpu, mask) {
 		csd = &per_cpu(tick_broadcast_csd, cpu);
-		csd->func = tick_broadcast_callee;
+		smp_call_function_single_async(cpu, csd);
 	}
-
-	return 0;
 }
-early_initcall(tick_broadcast_init);
 
 #endif /* CONFIG_GENERIC_CLOCKEVENTS_BROADCAST */
diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c
index 75217fb63d7b..9dd5ad1b553d 100644
--- a/arch/s390/pci/pci_irq.c
+++ b/arch/s390/pci/pci_irq.c
@@ -179,9 +179,7 @@ static void zpci_handle_fallback_irq(void)
 		if (atomic_inc_return(&cpu_data->scheduled) > 1)
 			continue;
 
-		cpu_data->csd.func = zpci_handle_remote_irq;
-		cpu_data->csd.info = &cpu_data->scheduled;
-		cpu_data->csd.flags = 0;
+		INIT_CSD(&cpu_data->csd, zpci_handle_remote_irq, &cpu_data->scheduled);
 		smp_call_function_single_async(cpu, &cpu_data->csd);
 	}
 }
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index f4234575f3fd..488a8e848754 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -218,4 +218,9 @@ static inline void arch_set_max_freq_ratio(bool turbo_disabled)
 }
 #endif
 
+#ifdef CONFIG_ACPI_CPPC_LIB
+void init_freq_invariance_cppc(void);
+#define init_freq_invariance_cppc init_freq_invariance_cppc
+#endif
+
 #endif /* _ASM_X86_TOPOLOGY_H */
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index 3492aa36bf09..6f7b8cc1bc9f 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -74,10 +74,9 @@ static ssize_t cpuid_read(struct file *file, char __user *buf,
 
 	init_completion(&cmd.done);
 	for (; count; count -= 16) {
-		call_single_data_t csd = {
-			.func = cpuid_smp_cpuid,
-			.info = &cmd,
-		};
+		call_single_data_t csd;
+
+		INIT_CSD(&csd, cpuid_smp_cpuid, &cmd);
 
 		cmd.regs.eax = pos;
 		cmd.regs.ecx = pos >> 32;
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 99bdcebaedfc..9278ed7b564e 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -82,6 +82,10 @@
 #include <asm/hw_irq.h>
 #include <asm/stackprotector.h>
 
+#ifdef CONFIG_ACPI_CPPC_LIB
+#include <acpi/cppc_acpi.h>
+#endif
+
 /* representing HT siblings of each logical CPU */
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
 EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
@@ -148,7 +152,7 @@ static inline void smpboot_restore_warm_reset_vector(void)
 	*((volatile u32 *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0;
 }
 
-static void init_freq_invariance(bool secondary);
+static void init_freq_invariance(bool secondary, bool cppc_ready);
 
 /*
  * Report back to the Boot Processor during boot time or to the caller processor
@@ -186,7 +190,7 @@ static void smp_callin(void)
 	 */
 	set_cpu_sibling_map(raw_smp_processor_id());
 
-	init_freq_invariance(true);
+	init_freq_invariance(true, false);
 
 	/*
 	 * Get our bogomips.
@@ -1341,7 +1345,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	set_sched_topology(x86_topology);
 
 	set_cpu_sibling_map(0);
-	init_freq_invariance(false);
+	init_freq_invariance(false, false);
 	smp_sanity_check();
 
 	switch (apic_intr_mode) {
@@ -2028,6 +2032,48 @@ out:
 	return true;
 }
 
+#ifdef CONFIG_ACPI_CPPC_LIB
+static bool amd_set_max_freq_ratio(void)
+{
+	struct cppc_perf_caps perf_caps;
+	u64 highest_perf, nominal_perf;
+	u64 perf_ratio;
+	int rc;
+
+	rc = cppc_get_perf_caps(0, &perf_caps);
+	if (rc) {
+		pr_debug("Could not retrieve perf counters (%d)\n", rc);
+		return false;
+	}
+
+	highest_perf = perf_caps.highest_perf;
+	nominal_perf = perf_caps.nominal_perf;
+
+	if (!highest_perf || !nominal_perf) {
+		pr_debug("Could not retrieve highest or nominal performance\n");
+		return false;
+	}
+
+	perf_ratio = div_u64(highest_perf * SCHED_CAPACITY_SCALE, nominal_perf);
+	/* midpoint between max_boost and max_P */
+	perf_ratio = (perf_ratio + SCHED_CAPACITY_SCALE) >> 1;
+	if (!perf_ratio) {
+		pr_debug("Non-zero highest/nominal perf values led to a 0 ratio\n");
+		return false;
+	}
+
+	arch_turbo_freq_ratio = perf_ratio;
+	arch_set_max_freq_ratio(false);
+
+	return true;
+}
+#else
+static bool amd_set_max_freq_ratio(void)
+{
+	return false;
+}
+#endif
+
 static void init_counter_refs(void)
 {
 	u64 aperf, mperf;
@@ -2039,7 +2085,7 @@ static void init_counter_refs(void)
 	this_cpu_write(arch_prev_mperf, mperf);
 }
 
-static void init_freq_invariance(bool secondary)
+static void init_freq_invariance(bool secondary, bool cppc_ready)
 {
 	bool ret = false;
 
@@ -2055,15 +2101,38 @@ static void init_freq_invariance(bool secondary)
 
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
 		ret = intel_set_max_freq_ratio();
+	else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
+		if (!cppc_ready) {
+			return;
+		}
+		ret = amd_set_max_freq_ratio();
+	}
 
 	if (ret) {
 		init_counter_refs();
 		static_branch_enable(&arch_scale_freq_key);
+		pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio);
 	} else {
 		pr_debug("Couldn't determine max cpu frequency, necessary for scale-invariant accounting.\n");
 	}
 }
 
+#ifdef CONFIG_ACPI_CPPC_LIB
+static DEFINE_MUTEX(freq_invariance_lock);
+
+void init_freq_invariance_cppc(void)
+{
+	static bool secondary;
+
+	mutex_lock(&freq_invariance_lock);
+
+	init_freq_invariance(secondary, true);
+	secondary = true;
+
+	mutex_unlock(&freq_invariance_lock);
+}
+#endif
+
 static void disable_freq_invariance_workfn(struct work_struct *work)
 {
 	static_branch_disable(&arch_scale_freq_key);
@@ -2113,7 +2182,7 @@ error:
 	schedule_work(&disable_freq_invariance_work);
 }
 #else
-static inline void init_freq_invariance(bool secondary)
+static inline void init_freq_invariance(bool secondary, bool cppc_ready)
 {
 }
 #endif /* CONFIG_X86_64 */
diff --git a/arch/x86/lib/msr-smp.c b/arch/x86/lib/msr-smp.c
index fee8b9c0520c..75a0915b0d01 100644
--- a/arch/x86/lib/msr-smp.c
+++ b/arch/x86/lib/msr-smp.c
@@ -169,12 +169,11 @@ static void __wrmsr_safe_on_cpu(void *info)
 int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
 {
 	struct msr_info_completion rv;
-	call_single_data_t csd = {
-		.func	= __rdmsr_safe_on_cpu,
-		.info	= &rv,
-	};
+	call_single_data_t csd;
 	int err;
 
+	INIT_CSD(&csd, __rdmsr_safe_on_cpu, &rv);
+
 	memset(&rv, 0, sizeof(rv));
 	init_completion(&rv.done);
 	rv.msr.msr_no = msr_no;