1 files changed, 202 insertions, 74 deletions

diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 1a2c72f3e7f8..b32f13358fbb 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -15,62 +15,16 @@
 #include <linux/arch_topology.h>
 #include <linux/cacheinfo.h>
 #include <linux/cpufreq.h>
+#include <linux/cpu_smt.h>
 #include <linux/init.h>
 #include <linux/percpu.h>
+#include <linux/sched/isolation.h>
+#include <linux/xarray.h>
 
 #include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/topology.h>
 
-#ifdef CONFIG_ACPI
-static bool __init acpi_cpu_is_threaded(int cpu)
-{
-	int is_threaded = acpi_pptt_cpu_is_thread(cpu);
-
-	/*
-	 * if the PPTT doesn't have thread information, assume a homogeneous
-	 * machine and return the current CPU's thread state.
-	 */
-	if (is_threaded < 0)
-		is_threaded = read_cpuid_mpidr() & MPIDR_MT_BITMASK;
-
-	return !!is_threaded;
-}
-
-/*
- * Propagate the topology information of the processor_topology_node tree to the
- * cpu_topology array.
- */
-int __init parse_acpi_topology(void)
-{
-	int cpu, topology_id;
-
-	if (acpi_disabled)
-		return 0;
-
-	for_each_possible_cpu(cpu) {
-		topology_id = find_acpi_cpu_topology(cpu, 0);
-		if (topology_id < 0)
-			return topology_id;
-
-		if (acpi_cpu_is_threaded(cpu)) {
-			cpu_topology[cpu].thread_id = topology_id;
-			topology_id = find_acpi_cpu_topology(cpu, 1);
-			cpu_topology[cpu].core_id   = topology_id;
-		} else {
-			cpu_topology[cpu].thread_id  = -1;
-			cpu_topology[cpu].core_id    = topology_id;
-		}
-		topology_id = find_acpi_cpu_topology_cluster(cpu);
-		cpu_topology[cpu].cluster_id = topology_id;
-		topology_id = find_acpi_cpu_topology_package(cpu);
-		cpu_topology[cpu].package_id = topology_id;
-	}
-
-	return 0;
-}
-#endif
-
 #ifdef CONFIG_ARM64_AMU_EXTN
 #define read_corecnt()	read_sysreg_s(SYS_AMEVCNTR0_CORE_EL0)
 #define read_constcnt()	read_sysreg_s(SYS_AMEVCNTR0_CONST_EL0)
@@ -88,18 +42,28 @@ int __init parse_acpi_topology(void)
  * initialized.
  */
 static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, arch_max_freq_scale) =  1UL << (2 * SCHED_CAPACITY_SHIFT);
-static DEFINE_PER_CPU(u64, arch_const_cycles_prev);
-static DEFINE_PER_CPU(u64, arch_core_cycles_prev);
 static cpumask_var_t amu_fie_cpus;
 
+struct amu_cntr_sample {
+	u64		arch_const_cycles_prev;
+	u64		arch_core_cycles_prev;
+	unsigned long	last_scale_update;
+};
+
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct amu_cntr_sample, cpu_amu_samples);
+
 void update_freq_counters_refs(void)
 {
-	this_cpu_write(arch_core_cycles_prev, read_corecnt());
-	this_cpu_write(arch_const_cycles_prev, read_constcnt());
+	struct amu_cntr_sample *amu_sample = this_cpu_ptr(&cpu_amu_samples);
+
+	amu_sample->arch_core_cycles_prev = read_corecnt();
+	amu_sample->arch_const_cycles_prev = read_constcnt();
 }
 
 static inline bool freq_counters_valid(int cpu)
 {
+	struct amu_cntr_sample *amu_sample = per_cpu_ptr(&cpu_amu_samples, cpu);
+
 	if ((cpu >= nr_cpu_ids) || !cpumask_test_cpu(cpu, cpu_present_mask))
 		return false;
 
@@ -108,8 +72,8 @@ static inline bool freq_counters_valid(int cpu)
 		return false;
 	}
 
-	if (unlikely(!per_cpu(arch_const_cycles_prev, cpu) ||
-		     !per_cpu(arch_core_cycles_prev, cpu))) {
+	if (unlikely(!amu_sample->arch_const_cycles_prev ||
+		     !amu_sample->arch_core_cycles_prev)) {
 		pr_debug("CPU%d: cycle counters are not enabled.\n", cpu);
 		return false;
 	}
@@ -152,17 +116,22 @@ void freq_inv_set_max_ratio(int cpu, u64 max_rate)
 
 static void amu_scale_freq_tick(void)
 {
+	struct amu_cntr_sample *amu_sample = this_cpu_ptr(&cpu_amu_samples);
 	u64 prev_core_cnt, prev_const_cnt;
 	u64 core_cnt, const_cnt, scale;
 
-	prev_const_cnt = this_cpu_read(arch_const_cycles_prev);
-	prev_core_cnt = this_cpu_read(arch_core_cycles_prev);
+	prev_const_cnt = amu_sample->arch_const_cycles_prev;
+	prev_core_cnt = amu_sample->arch_core_cycles_prev;
 
 	update_freq_counters_refs();
 
-	const_cnt = this_cpu_read(arch_const_cycles_prev);
-	core_cnt = this_cpu_read(arch_core_cycles_prev);
+	const_cnt = amu_sample->arch_const_cycles_prev;
+	core_cnt = amu_sample->arch_core_cycles_prev;
 
+	/*
+	 * This should not happen unless the AMUs have been reset and the
+	 * counter values have not been restored - unlikely
+	 */
 	if (unlikely(core_cnt <= prev_core_cnt ||
 		     const_cnt <= prev_const_cnt))
 		return;
@@ -182,6 +151,8 @@ static void amu_scale_freq_tick(void)
 
 	scale = min_t(unsigned long, scale, SCHED_CAPACITY_SCALE);
 	this_cpu_write(arch_freq_scale, (unsigned long)scale);
+
+	amu_sample->last_scale_update = jiffies;
 }
 
 static struct scale_freq_data amu_sfd = {
@@ -189,22 +160,119 @@ static struct scale_freq_data amu_sfd = {
 	.set_freq_scale = amu_scale_freq_tick,
 };
 
+static __always_inline bool amu_fie_cpu_supported(unsigned int cpu)
+{
+	return cpumask_available(amu_fie_cpus) &&
+		cpumask_test_cpu(cpu, amu_fie_cpus);
+}
+
+void arch_cpu_idle_enter(void)
+{
+	unsigned int cpu = smp_processor_id();
+
+	if (!amu_fie_cpu_supported(cpu))
+		return;
+
+	/* Kick in AMU update but only if one has not happened already */
+	if (housekeeping_cpu(cpu, HK_TYPE_TICK) &&
+	    time_is_before_jiffies(per_cpu(cpu_amu_samples.last_scale_update, cpu)))
+		amu_scale_freq_tick();
+}
+
+#define AMU_SAMPLE_EXP_MS	20
+
+int arch_freq_get_on_cpu(int cpu)
+{
+	struct amu_cntr_sample *amu_sample;
+	unsigned int start_cpu = cpu;
+	unsigned long last_update;
+	unsigned int freq = 0;
+	u64 scale;
+
+	if (!amu_fie_cpu_supported(cpu) || !arch_scale_freq_ref(cpu))
+		return -EOPNOTSUPP;
+
+	while (1) {
+
+		amu_sample = per_cpu_ptr(&cpu_amu_samples, cpu);
+
+		last_update = amu_sample->last_scale_update;
+
+		/*
+		 * For those CPUs that are in full dynticks mode, or those that have
+		 * not seen tick for a while, try an alternative source for the counters
+		 * (and thus freq scale), if available, for given policy: this boils
+		 * down to identifying an active cpu within the same freq domain, if any.
+		 */
+		if (!housekeeping_cpu(cpu, HK_TYPE_TICK) ||
+		    time_is_before_jiffies(last_update + msecs_to_jiffies(AMU_SAMPLE_EXP_MS))) {
+			struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+			int ref_cpu;
+
+			if (!policy)
+				return -EINVAL;
+
+			if (!cpumask_intersects(policy->related_cpus,
+						housekeeping_cpumask(HK_TYPE_TICK))) {
+				cpufreq_cpu_put(policy);
+				return -EOPNOTSUPP;
+			}
+
+			for_each_cpu_wrap(ref_cpu, policy->cpus, cpu + 1) {
+				if (ref_cpu == start_cpu) {
+					/* Prevent verifying same CPU twice */
+					ref_cpu = nr_cpu_ids;
+					break;
+				}
+				if (!idle_cpu(ref_cpu))
+					break;
+			}
+
+			cpufreq_cpu_put(policy);
+
+			if (ref_cpu >= nr_cpu_ids)
+				/* No alternative to pull info from */
+				return -EAGAIN;
+
+			cpu = ref_cpu;
+		} else {
+			break;
+		}
+	}
+	/*
+	 * Reversed computation to the one used to determine
+	 * the arch_freq_scale value
+	 * (see amu_scale_freq_tick for details)
+	 */
+	scale = arch_scale_freq_capacity(cpu);
+	freq = scale * arch_scale_freq_ref(cpu);
+	freq >>= SCHED_CAPACITY_SHIFT;
+	return freq;
+}
+
 static void amu_fie_setup(const struct cpumask *cpus)
 {
 	int cpu;
 
 	/* We are already set since the last insmod of cpufreq driver */
-	if (unlikely(cpumask_subset(cpus, amu_fie_cpus)))
+	if (cpumask_available(amu_fie_cpus) &&
+	    unlikely(cpumask_subset(cpus, amu_fie_cpus)))
 		return;
 
-	for_each_cpu(cpu, cpus) {
+	for_each_cpu(cpu, cpus)
 		if (!freq_counters_valid(cpu))
 			return;
+
+	if (!cpumask_available(amu_fie_cpus) &&
+	    !zalloc_cpumask_var(&amu_fie_cpus, GFP_KERNEL)) {
+		WARN_ONCE(1, "Failed to allocate FIE cpumask for CPUs[%*pbl]\n",
+			  cpumask_pr_args(cpus));
+		return;
 	}
 
 	cpumask_or(amu_fie_cpus, amu_fie_cpus, cpus);
 
-	topology_set_scale_freq_source(&amu_sfd, amu_fie_cpus);
+	topology_set_scale_freq_source(&amu_sfd, cpus);
 
 	pr_debug("CPUs[%*pbl]: counters will be used for FIE.",
 		 cpumask_pr_args(cpus));
@@ -216,7 +284,7 @@ static int init_amu_fie_callback(struct notifier_block *nb, unsigned long val,
 	struct cpufreq_policy *policy = data;
 
 	if (val == CPUFREQ_CREATE_POLICY)
-		amu_fie_setup(policy->related_cpus);
+		amu_fie_setup(policy->cpus);
 
 	/*
 	 * We don't need to handle CPUFREQ_REMOVE_POLICY event as the AMU
@@ -235,19 +303,70 @@ static struct notifier_block init_amu_fie_notifier = {
 	.notifier_call = init_amu_fie_callback,
 };
 
+static int cpuhp_topology_online(unsigned int cpu)
+{
+	struct cpufreq_policy *policy = cpufreq_cpu_policy(cpu);
+
+	/* Those are cheap checks */
+
+	/*
+	 * Skip this CPU if:
+	 *  - it has no cpufreq policy assigned yet,
+	 *  - no policy exists that spans CPUs with AMU counters, or
+	 *  - it was already handled.
+	 */
+	if (unlikely(!policy) || !cpumask_available(amu_fie_cpus) ||
+	    cpumask_test_cpu(cpu, amu_fie_cpus))
+		return 0;
+
+	/*
+	 * Only proceed if all already-online CPUs in this policy
+	 * support AMU counters.
+	 */
+	if (unlikely(!cpumask_subset(policy->cpus, amu_fie_cpus)))
+		return 0;
+
+	/*
+	 * If the new online CPU cannot pass this check, all the CPUs related to
+	 * the same policy should be clear from amu_fie_cpus mask, otherwise they
+	 * may use different source of the freq scale.
+	 */
+	if (!freq_counters_valid(cpu)) {
+		topology_clear_scale_freq_source(SCALE_FREQ_SOURCE_ARCH,
+						 policy->related_cpus);
+		cpumask_andnot(amu_fie_cpus, amu_fie_cpus, policy->related_cpus);
+		return 0;
+	}
+
+	cpumask_set_cpu(cpu, amu_fie_cpus);
+
+	topology_set_scale_freq_source(&amu_sfd, cpumask_of(cpu));
+
+	pr_debug("CPU[%u]: counter will be used for FIE.", cpu);
+
+	return 0;
+}
+
 static int __init init_amu_fie(void)
 {
 	int ret;
 
-	if (!zalloc_cpumask_var(&amu_fie_cpus, GFP_KERNEL))
-		return -ENOMEM;
-
 	ret = cpufreq_register_notifier(&init_amu_fie_notifier,
 					CPUFREQ_POLICY_NOTIFIER);
 	if (ret)
-		free_cpumask_var(amu_fie_cpus);
+		return ret;
+
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"arm64/topology:online",
+					cpuhp_topology_online,
+					NULL);
+	if (ret < 0) {
+		cpufreq_unregister_notifier(&init_amu_fie_notifier,
+					    CPUFREQ_POLICY_NOTIFIER);
+		return ret;
+	}
 
-	return ret;
+	return 0;
 }
 core_initcall(init_amu_fie);
 
@@ -281,16 +400,25 @@ static inline
 int counters_read_on_cpu(int cpu, smp_call_func_t func, u64 *val)
 {
 	/*
-	 * Abort call on counterless CPU or when interrupts are
-	 * disabled - can lead to deadlock in smp sync call.
+	 * Abort call on counterless CPU.
 	 */
 	if (!cpu_has_amu_feat(cpu))
 		return -EOPNOTSUPP;
 
-	if (WARN_ON_ONCE(irqs_disabled()))
-		return -EPERM;
-
-	smp_call_function_single(cpu, func, val, 1);
+	if (irqs_disabled()) {
+		/*
+		 * When IRQs are disabled (tick path: sched_tick ->
+		 * topology_scale_freq_tick or cppc_scale_freq_tick), only local
+		 * CPU counter reads are allowed. Remote CPU counter read would
+		 * require smp_call_function_single() which is unsafe with IRQs
+		 * disabled.
+		 */
+		if (WARN_ON_ONCE(cpu != smp_processor_id()))
+			return -EPERM;
+		func(val);
+	} else {
+		smp_call_function_single(cpu, func, val, 1);
+	}
 
 	return 0;
 }