summaryrefslogtreecommitdiff
path: root/arch/arm64/kernel/topology.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm64/kernel/topology.c')
-rw-r--r--arch/arm64/kernel/topology.c550
1 files changed, 322 insertions, 228 deletions
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 8d48b233e6ce..5d24dc53799b 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -11,303 +11,397 @@
* for more details.
*/
+#include <linux/acpi.h>
#include <linux/arch_topology.h>
-#include <linux/cpu.h>
-#include <linux/cpumask.h>
+#include <linux/cacheinfo.h>
+#include <linux/cpufreq.h>
+#include <linux/cpu_smt.h>
#include <linux/init.h>
#include <linux/percpu.h>
-#include <linux/node.h>
-#include <linux/nodemask.h>
-#include <linux/of.h>
-#include <linux/sched.h>
-#include <linux/sched/topology.h>
-#include <linux/slab.h>
-#include <linux/string.h>
+#include <linux/sched/isolation.h>
+#include <linux/xarray.h>
#include <asm/cpu.h>
#include <asm/cputype.h>
#include <asm/topology.h>
-static int __init get_cpu_for_node(struct device_node *node)
+#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)
+#else
+#define read_corecnt() (0UL)
+#define read_constcnt() (0UL)
+#endif
+
+#undef pr_fmt
+#define pr_fmt(fmt) "AMU: " fmt
+
+/*
+ * 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)
{
- struct device_node *cpu_node;
- int cpu;
+ struct amu_cntr_sample *amu_sample = this_cpu_ptr(&cpu_amu_samples);
- cpu_node = of_parse_phandle(node, "cpu", 0);
- if (!cpu_node)
- return -1;
+ amu_sample->arch_core_cycles_prev = read_corecnt();
+ amu_sample->arch_const_cycles_prev = read_constcnt();
+}
- for_each_possible_cpu(cpu) {
- if (of_get_cpu_node(cpu, NULL) == cpu_node) {
- topology_parse_cpu_capacity(cpu_node, cpu);
- of_node_put(cpu_node);
- return cpu;
- }
+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;
+
+ if (!cpu_has_amu_feat(cpu)) {
+ pr_debug("CPU%d: counters are not supported.\n", cpu);
+ return false;
}
- pr_crit("Unable to find CPU node for %pOF\n", cpu_node);
+ 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;
+ }
- of_node_put(cpu_node);
- return -1;
+ return true;
}
-static int __init parse_core(struct device_node *core, int cluster_id,
- int core_id)
+void freq_inv_set_max_ratio(int cpu, u64 max_rate)
{
- char name[10];
- bool leaf = true;
- int i = 0;
- int cpu;
- struct device_node *t;
-
- do {
- snprintf(name, sizeof(name), "thread%d", i);
- t = of_get_child_by_name(core, name);
- if (t) {
- leaf = false;
- cpu = get_cpu_for_node(t);
- if (cpu >= 0) {
- cpu_topology[cpu].cluster_id = cluster_id;
- cpu_topology[cpu].core_id = core_id;
- cpu_topology[cpu].thread_id = i;
- } else {
- pr_err("%pOF: Can't get CPU for thread\n",
- t);
- of_node_put(t);
- return -EINVAL;
- }
- of_node_put(t);
- }
- i++;
- } while (t);
-
- cpu = get_cpu_for_node(core);
- if (cpu >= 0) {
- if (!leaf) {
- pr_err("%pOF: Core has both threads and CPU\n",
- core);
- return -EINVAL;
- }
+ u64 ratio, ref_rate = arch_timer_get_rate();
- cpu_topology[cpu].cluster_id = cluster_id;
- cpu_topology[cpu].core_id = core_id;
- } else if (leaf) {
- pr_err("%pOF: Can't get CPU for leaf core\n", core);
- return -EINVAL;
+ if (unlikely(!max_rate || !ref_rate)) {
+ WARN_ONCE(1, "CPU%d: invalid maximum or reference frequency.\n",
+ cpu);
+ return;
}
- return 0;
+ /*
+ * Pre-compute the fixed ratio between the frequency of the constant
+ * reference counter and the maximum frequency of the CPU.
+ *
+ * ref_rate
+ * arch_max_freq_scale = ---------- * SCHED_CAPACITY_SCALE²
+ * max_rate
+ *
+ * We use a factor of 2 * SCHED_CAPACITY_SHIFT -> SCHED_CAPACITY_SCALE²
+ * in order to ensure a good resolution for arch_max_freq_scale for
+ * very low reference frequencies (down to the KHz range which should
+ * be unlikely).
+ */
+ ratio = ref_rate << (2 * SCHED_CAPACITY_SHIFT);
+ ratio = div64_u64(ratio, max_rate);
+ if (!ratio) {
+ WARN_ONCE(1, "Reference frequency too low.\n");
+ return;
+ }
+
+ WRITE_ONCE(per_cpu(arch_max_freq_scale, cpu), (unsigned long)ratio);
}
-static int __init parse_cluster(struct device_node *cluster, int depth)
+static void amu_scale_freq_tick(void)
{
- char name[10];
- bool leaf = true;
- bool has_cores = false;
- struct device_node *c;
- static int cluster_id __initdata;
- int core_id = 0;
- int i, ret;
+ 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 = amu_sample->arch_const_cycles_prev;
+ prev_core_cnt = amu_sample->arch_core_cycles_prev;
+
+ update_freq_counters_refs();
+
+ const_cnt = amu_sample->arch_const_cycles_prev;
+ core_cnt = amu_sample->arch_core_cycles_prev;
/*
- * First check for child clusters; we currently ignore any
- * information about the nesting of clusters and present the
- * scheduler with a flat list of them.
+ * This should not happen unless the AMUs have been reset and the
+ * counter values have not been restored - unlikely
*/
- i = 0;
- do {
- snprintf(name, sizeof(name), "cluster%d", i);
- c = of_get_child_by_name(cluster, name);
- if (c) {
- leaf = false;
- ret = parse_cluster(c, depth + 1);
- of_node_put(c);
- if (ret != 0)
- return ret;
- }
- i++;
- } while (c);
-
- /* Now check for cores */
- i = 0;
- do {
- snprintf(name, sizeof(name), "core%d", i);
- c = of_get_child_by_name(cluster, name);
- if (c) {
- has_cores = true;
-
- if (depth == 0) {
- pr_err("%pOF: cpu-map children should be clusters\n",
- c);
- of_node_put(c);
- return -EINVAL;
- }
+ if (unlikely(core_cnt <= prev_core_cnt ||
+ const_cnt <= prev_const_cnt))
+ return;
- if (leaf) {
- ret = parse_core(c, cluster_id, core_id++);
- } else {
- pr_err("%pOF: Non-leaf cluster with core %s\n",
- cluster, name);
- ret = -EINVAL;
- }
+ /*
+ * /\core arch_max_freq_scale
+ * scale = ------- * --------------------
+ * /\const SCHED_CAPACITY_SCALE
+ *
+ * See validate_cpu_freq_invariance_counters() for details on
+ * arch_max_freq_scale and the use of SCHED_CAPACITY_SHIFT.
+ */
+ scale = core_cnt - prev_core_cnt;
+ scale *= this_cpu_read(arch_max_freq_scale);
+ scale = div64_u64(scale >> SCHED_CAPACITY_SHIFT,
+ const_cnt - prev_const_cnt);
- of_node_put(c);
- if (ret != 0)
- return ret;
- }
- i++;
- } while (c);
+ scale = min_t(unsigned long, scale, SCHED_CAPACITY_SCALE);
+ this_cpu_write(arch_freq_scale, (unsigned long)scale);
- if (leaf && !has_cores)
- pr_warn("%pOF: empty cluster\n", cluster);
+ amu_sample->last_scale_update = jiffies;
+}
- if (leaf)
- cluster_id++;
+static struct scale_freq_data amu_sfd = {
+ .source = SCALE_FREQ_SOURCE_ARCH,
+ .set_freq_scale = amu_scale_freq_tick,
+};
- return 0;
+static __always_inline bool amu_fie_cpu_supported(unsigned int cpu)
+{
+ return cpumask_available(amu_fie_cpus) &&
+ cpumask_test_cpu(cpu, amu_fie_cpus);
}
-static int __init parse_dt_topology(void)
+void arch_cpu_idle_enter(void)
{
- struct device_node *cn, *map;
- int ret = 0;
- int cpu;
+ unsigned int cpu = smp_processor_id();
- cn = of_find_node_by_path("/cpus");
- if (!cn) {
- pr_err("No CPU information found in DT\n");
- return 0;
- }
+ if (!amu_fie_cpu_supported(cpu))
+ return;
- /*
- * When topology is provided cpu-map is essentially a root
- * cluster with restricted subnodes.
- */
- map = of_get_child_by_name(cn, "cpu-map");
- if (!map)
- goto out;
+ /* 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();
+}
- ret = parse_cluster(map, 0);
- if (ret != 0)
- goto out_map;
+#define AMU_SAMPLE_EXP_MS 20
- topology_normalize_cpu_scale();
+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;
- /*
- * Check that all cores are in the topology; the SMP code will
- * only mark cores described in the DT as possible.
- */
- for_each_possible_cpu(cpu)
- if (cpu_topology[cpu].cluster_id == -1)
- ret = -EINVAL;
-
-out_map:
- of_node_put(map);
-out:
- of_node_put(cn);
- return ret;
-}
+ if (!amu_fie_cpu_supported(cpu) || !arch_scale_freq_ref(cpu))
+ return -EOPNOTSUPP;
-/*
- * cpu topology table
- */
-struct cpu_topology cpu_topology[NR_CPUS];
-EXPORT_SYMBOL_GPL(cpu_topology);
+ while (1) {
-const struct cpumask *cpu_coregroup_mask(int cpu)
-{
- return &cpu_topology[cpu].core_sibling;
+ 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 update_siblings_masks(unsigned int cpuid)
+static void amu_fie_setup(const struct cpumask *cpus)
{
- struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
int cpu;
- /* update core and thread sibling masks */
- for_each_possible_cpu(cpu) {
- cpu_topo = &cpu_topology[cpu];
+ /* We are already set since the last insmod of cpufreq driver */
+ if (cpumask_available(amu_fie_cpus) &&
+ unlikely(cpumask_subset(cpus, amu_fie_cpus)))
+ return;
- if (cpuid_topo->cluster_id != cpu_topo->cluster_id)
- continue;
+ for_each_cpu(cpu, cpus)
+ if (!freq_counters_valid(cpu))
+ return;
- cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
- if (cpu != cpuid)
- cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);
+ 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;
+ }
- if (cpuid_topo->core_id != cpu_topo->core_id)
- continue;
+ cpumask_or(amu_fie_cpus, amu_fie_cpus, cpus);
- cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling);
- if (cpu != cpuid)
- cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling);
- }
+ topology_set_scale_freq_source(&amu_sfd, amu_fie_cpus);
+
+ pr_debug("CPUs[%*pbl]: counters will be used for FIE.",
+ cpumask_pr_args(cpus));
}
-void store_cpu_topology(unsigned int cpuid)
+static int init_amu_fie_callback(struct notifier_block *nb, unsigned long val,
+ void *data)
{
- struct cpu_topology *cpuid_topo = &cpu_topology[cpuid];
- u64 mpidr;
+ struct cpufreq_policy *policy = data;
- if (cpuid_topo->cluster_id != -1)
- goto topology_populated;
+ if (val == CPUFREQ_CREATE_POLICY)
+ amu_fie_setup(policy->related_cpus);
- mpidr = read_cpuid_mpidr();
+ /*
+ * We don't need to handle CPUFREQ_REMOVE_POLICY event as the AMU
+ * counters don't have any dependency on cpufreq driver once we have
+ * initialized AMU support and enabled invariance. The AMU counters will
+ * keep on working just fine in the absence of the cpufreq driver, and
+ * for the CPUs for which there are no counters available, the last set
+ * value of arch_freq_scale will remain valid as that is the frequency
+ * those CPUs are running at.
+ */
- /* Uniprocessor systems can rely on default topology values */
- if (mpidr & MPIDR_UP_BITMASK)
- return;
+ return 0;
+}
- /* Create cpu topology mapping based on MPIDR. */
- if (mpidr & MPIDR_MT_BITMASK) {
- /* Multiprocessor system : Multi-threads per core */
- cpuid_topo->thread_id = MPIDR_AFFINITY_LEVEL(mpidr, 0);
- cpuid_topo->core_id = MPIDR_AFFINITY_LEVEL(mpidr, 1);
- cpuid_topo->cluster_id = MPIDR_AFFINITY_LEVEL(mpidr, 2) |
- MPIDR_AFFINITY_LEVEL(mpidr, 3) << 8;
- } else {
- /* Multiprocessor system : Single-thread per core */
- cpuid_topo->thread_id = -1;
- cpuid_topo->core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0);
- cpuid_topo->cluster_id = MPIDR_AFFINITY_LEVEL(mpidr, 1) |
- MPIDR_AFFINITY_LEVEL(mpidr, 2) << 8 |
- MPIDR_AFFINITY_LEVEL(mpidr, 3) << 16;
- }
+static struct notifier_block init_amu_fie_notifier = {
+ .notifier_call = init_amu_fie_callback,
+};
+
+static int __init init_amu_fie(void)
+{
+ return cpufreq_register_notifier(&init_amu_fie_notifier,
+ CPUFREQ_POLICY_NOTIFIER);
+}
+core_initcall(init_amu_fie);
- pr_debug("CPU%u: cluster %d core %d thread %d mpidr %#016llx\n",
- cpuid, cpuid_topo->cluster_id, cpuid_topo->core_id,
- cpuid_topo->thread_id, mpidr);
+#ifdef CONFIG_ACPI_CPPC_LIB
+#include <acpi/cppc_acpi.h>
-topology_populated:
- update_siblings_masks(cpuid);
+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)
+{
+ /*
+ * 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 void __init reset_cpu_topology(void)
+static inline
+int counters_read_on_cpu(int cpu, smp_call_func_t func, u64 *val)
{
- unsigned int cpu;
+ /*
+ * Abort call on counterless CPU or when interrupts are
+ * disabled - can lead to deadlock in smp sync call.
+ */
+ if (!cpu_has_amu_feat(cpu))
+ return -EOPNOTSUPP;
- for_each_possible_cpu(cpu) {
- struct cpu_topology *cpu_topo = &cpu_topology[cpu];
+ if (WARN_ON_ONCE(irqs_disabled()))
+ return -EPERM;
- cpu_topo->thread_id = -1;
- cpu_topo->core_id = 0;
- cpu_topo->cluster_id = -1;
+ smp_call_function_single(cpu, func, val, 1);
- cpumask_clear(&cpu_topo->core_sibling);
- cpumask_set_cpu(cpu, &cpu_topo->core_sibling);
- cpumask_clear(&cpu_topo->thread_sibling);
- cpumask_set_cpu(cpu, &cpu_topo->thread_sibling);
- }
+ return 0;
}
-void __init init_cpu_topology(void)
+/*
+ * Refer to drivers/acpi/cppc_acpi.c for the description of the functions
+ * below.
+ */
+bool cpc_ffh_supported(void)
{
- reset_cpu_topology();
+ int cpu = get_cpu_with_amu_feat();
/*
- * Discard anything that was parsed if we hit an error so we
- * don't use partial information.
+ * 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 (of_have_populated_dt() && parse_dt_topology())
- reset_cpu_topology();
+ 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)
+{
+ int ret = -EOPNOTSUPP;
+
+ switch ((u64)reg->address) {
+ case 0x0:
+ ret = counters_read_on_cpu(cpu, cpu_read_corecnt, val);
+ break;
+ case 0x1:
+ ret = counters_read_on_cpu(cpu, cpu_read_constcnt, val);
+ break;
+ }
+
+ if (!ret) {
+ *val &= GENMASK_ULL(reg->bit_offset + reg->bit_width - 1,
+ reg->bit_offset);
+ *val >>= reg->bit_offset;
+ }
+
+ return ret;
+}
+
+int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val)
+{
+ return -EOPNOTSUPP;
}
+#endif /* CONFIG_ACPI_CPPC_LIB */
generated by cgit (git 2.34.1) at 2025-12-25 11:02:19 +0000