diff options
Diffstat (limited to 'drivers/base/arch_topology.c')
| -rw-r--r-- | drivers/base/arch_topology.c | 220 |
1 files changed, 188 insertions, 32 deletions
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index ff16a36a908b..e7d6e6657ffa 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -7,6 +7,7 @@ */ #include <linux/acpi.h> +#include <linux/cacheinfo.h> #include <linux/cpu.h> #include <linux/cpufreq.h> #include <linux/device.h> @@ -19,9 +20,13 @@ #include <linux/rcupdate.h> #include <linux/sched.h> +#define CREATE_TRACE_POINTS +#include <trace/events/thermal_pressure.h> + static DEFINE_PER_CPU(struct scale_freq_data __rcu *, sft_data); static struct cpumask scale_freq_counters_mask; static bool scale_freq_invariant; +static DEFINE_PER_CPU(u32, freq_factor) = 1; static bool supports_scale_freq_counters(const struct cpumask *cpus) { @@ -155,15 +160,51 @@ void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity) DEFINE_PER_CPU(unsigned long, thermal_pressure); -void topology_set_thermal_pressure(const struct cpumask *cpus, - unsigned long th_pressure) +/** + * topology_update_thermal_pressure() - Update thermal pressure for CPUs + * @cpus : The related CPUs for which capacity has been reduced + * @capped_freq : The maximum allowed frequency that CPUs can run at + * + * Update the value of thermal pressure for all @cpus in the mask. The + * cpumask should include all (online+offline) affected CPUs, to avoid + * operating on stale data when hot-plug is used for some CPUs. The + * @capped_freq reflects the currently allowed max CPUs frequency due to + * thermal capping. It might be also a boost frequency value, which is bigger + * than the internal 'freq_factor' max frequency. In such case the pressure + * value should simply be removed, since this is an indication that there is + * no thermal throttling. The @capped_freq must be provided in kHz. + */ +void topology_update_thermal_pressure(const struct cpumask *cpus, + unsigned long capped_freq) { + unsigned long max_capacity, capacity, th_pressure; + u32 max_freq; int cpu; + cpu = cpumask_first(cpus); + max_capacity = arch_scale_cpu_capacity(cpu); + max_freq = per_cpu(freq_factor, cpu); + + /* Convert to MHz scale which is used in 'freq_factor' */ + capped_freq /= 1000; + + /* + * Handle properly the boost frequencies, which should simply clean + * the thermal pressure value. + */ + if (max_freq <= capped_freq) + capacity = max_capacity; + else + capacity = mult_frac(max_capacity, capped_freq, max_freq); + + th_pressure = max_capacity - capacity; + + trace_thermal_pressure_update(cpu, th_pressure); + for_each_cpu(cpu, cpus) WRITE_ONCE(per_cpu(thermal_pressure, cpu), th_pressure); } -EXPORT_SYMBOL_GPL(topology_set_thermal_pressure); +EXPORT_SYMBOL_GPL(topology_update_thermal_pressure); static ssize_t cpu_capacity_show(struct device *dev, struct device_attribute *attr, @@ -217,7 +258,6 @@ static void update_topology_flags_workfn(struct work_struct *work) update_topology = 0; } -static DEFINE_PER_CPU(u32, freq_factor) = 1; static u32 *raw_capacity; static int free_raw_capacity(void) @@ -305,6 +345,46 @@ bool __init topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu) return !ret; } +#ifdef CONFIG_ACPI_CPPC_LIB +#include <acpi/cppc_acpi.h> + +void topology_init_cpu_capacity_cppc(void) +{ + struct cppc_perf_caps perf_caps; + int cpu; + + if (likely(!acpi_cpc_valid())) + return; + + raw_capacity = kcalloc(num_possible_cpus(), sizeof(*raw_capacity), + GFP_KERNEL); + if (!raw_capacity) + return; + + for_each_possible_cpu(cpu) { + if (!cppc_get_perf_caps(cpu, &perf_caps) && + (perf_caps.highest_perf >= perf_caps.nominal_perf) && + (perf_caps.highest_perf >= perf_caps.lowest_perf)) { + raw_capacity[cpu] = perf_caps.highest_perf; + pr_debug("cpu_capacity: CPU%d cpu_capacity=%u (raw).\n", + cpu, raw_capacity[cpu]); + continue; + } + + pr_err("cpu_capacity: CPU%d missing/invalid highest performance.\n", cpu); + pr_err("cpu_capacity: partial information: fallback to 1024 for all CPUs\n"); + goto exit; + } + + topology_normalize_cpu_scale(); + schedule_work(&update_topology_flags_work); + pr_debug("cpu_capacity: cpu_capacity initialization done\n"); + +exit: + free_raw_capacity(); +} +#endif + #ifdef CONFIG_CPU_FREQ static cpumask_var_t cpus_to_visit; static void parsing_done_workfn(struct work_struct *work); @@ -353,9 +433,8 @@ static int __init register_cpufreq_notifier(void) int ret; /* - * on ACPI-based systems we need to use the default cpu capacity - * until we have the necessary code to parse the cpu capacity, so - * skip registering cpufreq notifier. + * On ACPI-based systems skip registering cpufreq notifier as cpufreq + * information is not needed for cpu capacity initialization. */ if (!acpi_disabled || !raw_capacity) return -EINVAL; @@ -418,7 +497,7 @@ static int __init get_cpu_for_node(struct device_node *node) } static int __init parse_core(struct device_node *core, int package_id, - int core_id) + int cluster_id, int core_id) { char name[20]; bool leaf = true; @@ -434,6 +513,7 @@ static int __init parse_core(struct device_node *core, int package_id, cpu = get_cpu_for_node(t); if (cpu >= 0) { cpu_topology[cpu].package_id = package_id; + cpu_topology[cpu].cluster_id = cluster_id; cpu_topology[cpu].core_id = core_id; cpu_topology[cpu].thread_id = i; } else if (cpu != -ENODEV) { @@ -455,6 +535,7 @@ static int __init parse_core(struct device_node *core, int package_id, } cpu_topology[cpu].package_id = package_id; + cpu_topology[cpu].cluster_id = cluster_id; cpu_topology[cpu].core_id = core_id; } else if (leaf && cpu != -ENODEV) { pr_err("%pOF: Can't get CPU for leaf core\n", core); @@ -464,13 +545,13 @@ static int __init parse_core(struct device_node *core, int package_id, return 0; } -static int __init parse_cluster(struct device_node *cluster, int depth) +static int __init parse_cluster(struct device_node *cluster, int package_id, + int cluster_id, int depth) { char name[20]; bool leaf = true; bool has_cores = false; struct device_node *c; - static int package_id __initdata; int core_id = 0; int i, ret; @@ -485,7 +566,9 @@ static int __init parse_cluster(struct device_node *cluster, int depth) c = of_get_child_by_name(cluster, name); if (c) { leaf = false; - ret = parse_cluster(c, depth + 1); + ret = parse_cluster(c, package_id, i, depth + 1); + if (depth > 0) + pr_warn("Topology for clusters of clusters not yet supported\n"); of_node_put(c); if (ret != 0) return ret; @@ -509,7 +592,8 @@ static int __init parse_cluster(struct device_node *cluster, int depth) } if (leaf) { - ret = parse_core(c, package_id, core_id++); + ret = parse_core(c, package_id, cluster_id, + core_id++); } else { pr_err("%pOF: Non-leaf cluster with core %s\n", cluster, name); @@ -526,10 +610,33 @@ static int __init parse_cluster(struct device_node *cluster, int depth) if (leaf && !has_cores) pr_warn("%pOF: empty cluster\n", cluster); - if (leaf) + return 0; +} + +static int __init parse_socket(struct device_node *socket) +{ + char name[20]; + struct device_node *c; + bool has_socket = false; + int package_id = 0, ret; + + do { + snprintf(name, sizeof(name), "socket%d", package_id); + c = of_get_child_by_name(socket, name); + if (c) { + has_socket = true; + ret = parse_cluster(c, package_id, -1, 0); + of_node_put(c); + if (ret != 0) + return ret; + } package_id++; + } while (c); - return 0; + if (!has_socket) + ret = parse_cluster(socket, 0, -1, 0); + + return ret; } static int __init parse_dt_topology(void) @@ -552,7 +659,7 @@ static int __init parse_dt_topology(void) if (!map) goto out; - ret = parse_cluster(map, 0); + ret = parse_socket(map); if (ret != 0) goto out_map; @@ -563,8 +670,10 @@ static int __init parse_dt_topology(void) * only mark cores described in the DT as possible. */ for_each_possible_cpu(cpu) - if (cpu_topology[cpu].package_id == -1) + if (cpu_topology[cpu].package_id < 0) { ret = -EINVAL; + break; + } out_map: of_node_put(map); @@ -589,29 +698,51 @@ const struct cpumask *cpu_coregroup_mask(int cpu) /* not numa in package, lets use the package siblings */ core_mask = &cpu_topology[cpu].core_sibling; } - if (cpu_topology[cpu].llc_id != -1) { + + if (last_level_cache_is_valid(cpu)) { if (cpumask_subset(&cpu_topology[cpu].llc_sibling, core_mask)) core_mask = &cpu_topology[cpu].llc_sibling; } + /* + * For systems with no shared cpu-side LLC but with clusters defined, + * extend core_mask to cluster_siblings. The sched domain builder will + * then remove MC as redundant with CLS if SCHED_CLUSTER is enabled. + */ + if (IS_ENABLED(CONFIG_SCHED_CLUSTER) && + cpumask_subset(core_mask, &cpu_topology[cpu].cluster_sibling)) + core_mask = &cpu_topology[cpu].cluster_sibling; + return core_mask; } const struct cpumask *cpu_clustergroup_mask(int cpu) { + /* + * Forbid cpu_clustergroup_mask() to span more or the same CPUs as + * cpu_coregroup_mask(). + */ + if (cpumask_subset(cpu_coregroup_mask(cpu), + &cpu_topology[cpu].cluster_sibling)) + return topology_sibling_cpumask(cpu); + return &cpu_topology[cpu].cluster_sibling; } void update_siblings_masks(unsigned int cpuid) { struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid]; - int cpu; + int cpu, ret; + + ret = detect_cache_attributes(cpuid); + if (ret && ret != -ENOENT) + pr_info("Early cacheinfo failed, ret = %d\n", ret); /* update core and thread sibling masks */ for_each_online_cpu(cpu) { cpu_topo = &cpu_topology[cpu]; - if (cpuid_topo->llc_id == cpu_topo->llc_id) { + if (last_level_cache_is_shared(cpu, cpuid)) { cpumask_set_cpu(cpu, &cpuid_topo->llc_sibling); cpumask_set_cpu(cpuid, &cpu_topo->llc_sibling); } @@ -619,15 +750,17 @@ void update_siblings_masks(unsigned int cpuid) if (cpuid_topo->package_id != cpu_topo->package_id) continue; - if (cpuid_topo->cluster_id == cpu_topo->cluster_id && - cpuid_topo->cluster_id != -1) { + cpumask_set_cpu(cpuid, &cpu_topo->core_sibling); + cpumask_set_cpu(cpu, &cpuid_topo->core_sibling); + + if (cpuid_topo->cluster_id != cpu_topo->cluster_id) + continue; + + if (cpuid_topo->cluster_id >= 0) { cpumask_set_cpu(cpu, &cpuid_topo->cluster_sibling); cpumask_set_cpu(cpuid, &cpu_topo->cluster_sibling); } - cpumask_set_cpu(cpuid, &cpu_topo->core_sibling); - cpumask_set_cpu(cpu, &cpuid_topo->core_sibling); - if (cpuid_topo->core_id != cpu_topo->core_id) continue; @@ -663,7 +796,6 @@ void __init reset_cpu_topology(void) cpu_topo->core_id = -1; cpu_topo->cluster_id = -1; cpu_topo->package_id = -1; - cpu_topo->llc_id = -1; clear_cpu_topology(cpu); } @@ -693,15 +825,39 @@ __weak int __init parse_acpi_topology(void) #if defined(CONFIG_ARM64) || defined(CONFIG_RISCV) void __init init_cpu_topology(void) { + int ret; + reset_cpu_topology(); + ret = parse_acpi_topology(); + if (!ret) + ret = of_have_populated_dt() && parse_dt_topology(); - /* - * Discard anything that was parsed if we hit an error so we - * don't use partial information. - */ - if (parse_acpi_topology()) - reset_cpu_topology(); - else if (of_have_populated_dt() && parse_dt_topology()) + if (ret) { + /* + * Discard anything that was parsed if we hit an error so we + * don't use partial information. + */ reset_cpu_topology(); + return; + } +} + +void store_cpu_topology(unsigned int cpuid) +{ + struct cpu_topology *cpuid_topo = &cpu_topology[cpuid]; + + if (cpuid_topo->package_id != -1) + goto topology_populated; + + cpuid_topo->thread_id = -1; + cpuid_topo->core_id = cpuid; + cpuid_topo->package_id = cpu_to_node(cpuid); + + pr_debug("CPU%u: package %d core %d thread %d\n", + cpuid, cpuid_topo->package_id, cpuid_topo->core_id, + cpuid_topo->thread_id); + +topology_populated: + update_siblings_masks(cpuid); } #endif |