1 files changed, 173 insertions, 138 deletions

diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 4dd14a6620c1..5d24dc53799b 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -15,114 +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>
 
-void store_cpu_topology(unsigned int cpuid)
-{
-	struct cpu_topology *cpuid_topo = &cpu_topology[cpuid];
-	u64 mpidr;
-
-	if (cpuid_topo->package_id != -1)
-		goto topology_populated;
-
-	mpidr = read_cpuid_mpidr();
-
-	/* Uniprocessor systems can rely on default topology values */
-	if (mpidr & MPIDR_UP_BITMASK)
-		return;
-
-	/*
-	 * This would be the place to create cpu topology based on MPIDR.
-	 *
-	 * However, it cannot be trusted to depict the actual topology; some
-	 * pieces of the architecture enforce an artificial cap on Aff0 values
-	 * (e.g. GICv3's ICC_SGI1R_EL1 limits it to 15), leading to an
-	 * artificial cycling of Aff1, Aff2 and Aff3 values. IOW, these end up
-	 * having absolutely no relationship to the actual underlying system
-	 * topology, and cannot be reasonably used as core / package ID.
-	 *
-	 * If the MT bit is set, Aff0 *could* be used to define a thread ID, but
-	 * we still wouldn't be able to obtain a sane core ID. This means we
-	 * need to entirely ignore MPIDR for any topology deduction.
-	 */
-	cpuid_topo->thread_id  = -1;
-	cpuid_topo->core_id    = cpuid;
-	cpuid_topo->package_id = cpu_to_node(cpuid);
-
-	pr_debug("CPU%u: cluster %d core %d thread %d mpidr %#016llx\n",
-		 cpuid, cpuid_topo->package_id, cpuid_topo->core_id,
-		 cpuid_topo->thread_id, mpidr);
-
-topology_populated:
-	update_siblings_masks(cpuid);
-}
-
-#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) {
-		int i, cache_id;
-
-		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_package(cpu);
-		cpu_topology[cpu].package_id = topology_id;
-
-		i = acpi_find_last_cache_level(cpu);
-
-		if (i > 0) {
-			/*
-			 * this is the only part of cpu_topology that has
-			 * a direct relationship with the cache topology
-			 */
-			cache_id = find_acpi_cpu_cache_topology(cpu, i);
-			if (cache_id > 0)
-				cpu_topology[cpu].llc_id = cache_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)
@@ -134,19 +36,34 @@ int __init parse_acpi_topology(void)
 #undef pr_fmt
 #define pr_fmt(fmt) "AMU: " fmt
 
-static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, arch_max_freq_scale);
-static DEFINE_PER_CPU(u64, arch_const_cycles_prev);
-static DEFINE_PER_CPU(u64, arch_core_cycles_prev);
+/*
+ * Ensure that amu_scale_freq_tick() will return SCHED_CAPACITY_SCALE until
+ * the CPU capacity and its associated frequency have been correctly
+ * initialized.
+ */
+static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, arch_max_freq_scale) =  1UL << (2 * SCHED_CAPACITY_SHIFT);
 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;
 
@@ -155,8 +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;
 	}
@@ -164,14 +81,14 @@ static inline bool freq_counters_valid(int cpu)
 	return true;
 }
 
-static int freq_inv_set_max_ratio(int cpu, u64 max_rate, u64 ref_rate)
+void freq_inv_set_max_ratio(int cpu, u64 max_rate)
 {
-	u64 ratio;
+	u64 ratio, ref_rate = arch_timer_get_rate();
 
 	if (unlikely(!max_rate || !ref_rate)) {
-		pr_debug("CPU%d: invalid maximum or reference frequency.\n",
+		WARN_ONCE(1, "CPU%d: invalid maximum or reference frequency.\n",
 			 cpu);
-		return -EINVAL;
+		return;
 	}
 
 	/*
@@ -191,27 +108,30 @@ static int freq_inv_set_max_ratio(int cpu, u64 max_rate, u64 ref_rate)
 	ratio = div64_u64(ratio, max_rate);
 	if (!ratio) {
 		WARN_ONCE(1, "Reference frequency too low.\n");
-		return -EINVAL;
+		return;
 	}
 
-	per_cpu(arch_max_freq_scale, cpu) = (unsigned long)ratio;
-
-	return 0;
+	WRITE_ONCE(per_cpu(arch_max_freq_scale, cpu), (unsigned long)ratio);
 }
 
 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;
@@ -231,6 +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 = {
@@ -238,20 +160,114 @@ 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) {
-		if (!freq_counters_valid(cpu) ||
-		    freq_inv_set_max_ratio(cpu,
-					   cpufreq_get_hw_max_freq(cpu) * 1000,
-					   arch_timer_get_rate()))
+	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);
@@ -289,17 +305,8 @@ static struct notifier_block init_amu_fie_notifier = {
 
 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,
+	return cpufreq_register_notifier(&init_amu_fie_notifier,
 					CPUFREQ_POLICY_NOTIFIER);
-	if (ret)
-		free_cpumask_var(amu_fie_cpus);
-
-	return ret;
 }
 core_initcall(init_amu_fie);
 
@@ -308,12 +315,25 @@ core_initcall(init_amu_fie);
 
 static void cpu_read_corecnt(void *val)
 {
+	/*
+	 * A value of 0 can be returned if the current CPU does not support AMUs
+	 * or if the counter is disabled for this CPU. A return value of 0 at
+	 * counter read is properly handled as an error case by the users of the
+	 * counter.
+	 */
 	*(u64 *)val = read_corecnt();
 }
 
 static void cpu_read_constcnt(void *val)
 {
-	*(u64 *)val = read_constcnt();
+	/*
+	 * Return 0 if the current CPU is affected by erratum 2457168. A value
+	 * of 0 is also returned if the current CPU does not support AMUs or if
+	 * the counter is disabled. A return value of 0 at counter read is
+	 * properly handled as an error case by the users of the counter.
+	 */
+	*(u64 *)val = this_cpu_has_cap(ARM64_WORKAROUND_2457168) ?
+		      0UL : read_constcnt();
 }
 
 static inline
@@ -340,7 +360,22 @@ int counters_read_on_cpu(int cpu, smp_call_func_t func, u64 *val)
  */
 bool cpc_ffh_supported(void)
 {
-	return freq_counters_valid(get_cpu_with_amu_feat());
+	int cpu = get_cpu_with_amu_feat();
+
+	/*
+	 * FFH is considered supported if there is at least one present CPU that
+	 * supports AMUs. Using FFH to read core and reference counters for CPUs
+	 * that do not support AMUs, have counters disabled or that are affected
+	 * by errata, will result in a return value of 0.
+	 *
+	 * This is done to allow any enabled and valid counters to be read
+	 * through FFH, knowing that potentially returning 0 as counter value is
+	 * properly handled by the users of these counters.
+	 */
+	if ((cpu >= nr_cpu_ids) || !cpumask_test_cpu(cpu, cpu_present_mask))
+		return false;
+
+	return true;
 }
 
 int cpc_read_ffh(int cpu, struct cpc_reg *reg, u64 *val)