diff options
Diffstat (limited to 'drivers/cpufreq/cppc_cpufreq.c')
| -rw-r--r-- | drivers/cpufreq/cppc_cpufreq.c | 287 |
1 files changed, 257 insertions, 30 deletions
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index db17196266e4..432dfb4e8027 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -61,7 +61,17 @@ static struct cppc_workaround_oem_info wa_info[] = { } }; +static struct cpufreq_driver cppc_cpufreq_driver; + +static enum { + FIE_UNSET = -1, + FIE_ENABLED, + FIE_DISABLED +} fie_disabled = FIE_UNSET; + #ifdef CONFIG_ACPI_CPPC_CPUFREQ_FIE +module_param(fie_disabled, int, 0444); +MODULE_PARM_DESC(fie_disabled, "Disable Frequency Invariance Engine (FIE)"); /* Frequency invariance support */ struct cppc_freq_invariance { @@ -75,7 +85,6 @@ struct cppc_freq_invariance { static DEFINE_PER_CPU(struct cppc_freq_invariance, cppc_freq_inv); static struct kthread_worker *kworker_fie; -static struct cpufreq_driver cppc_cpufreq_driver; static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpu); static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data, struct cppc_perf_fb_ctrs *fb_ctrs_t0, @@ -157,7 +166,7 @@ static void cppc_cpufreq_cpu_fie_init(struct cpufreq_policy *policy) struct cppc_freq_invariance *cppc_fi; int cpu, ret; - if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate) + if (fie_disabled) return; for_each_cpu(cpu, policy->cpus) { @@ -198,7 +207,7 @@ static void cppc_cpufreq_cpu_fie_exit(struct cpufreq_policy *policy) struct cppc_freq_invariance *cppc_fi; int cpu; - if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate) + if (fie_disabled) return; /* policy->cpus will be empty here, use related_cpus instead */ @@ -228,7 +237,15 @@ static void __init cppc_freq_invariance_init(void) }; int ret; - if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate) + if (fie_disabled != FIE_ENABLED && fie_disabled != FIE_DISABLED) { + fie_disabled = FIE_ENABLED; + if (cppc_perf_ctrs_in_pcc()) { + pr_info("FIE not enabled on systems with registers in PCC\n"); + fie_disabled = FIE_DISABLED; + } + } + + if (fie_disabled) return; kworker_fie = kthread_create_worker(0, "cppc_fie"); @@ -246,7 +263,7 @@ static void __init cppc_freq_invariance_init(void) static void cppc_freq_invariance_exit(void) { - if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate) + if (fie_disabled) return; kthread_destroy_worker(kworker_fie); @@ -303,52 +320,48 @@ static u64 cppc_get_dmi_max_khz(void) /* * If CPPC lowest_freq and nominal_freq registers are exposed then we can - * use them to convert perf to freq and vice versa - * - * If the perf/freq point lies between Nominal and Lowest, we can treat - * (Low perf, Low freq) and (Nom Perf, Nom freq) as 2D co-ordinates of a line - * and extrapolate the rest - * For perf/freq > Nominal, we use the ratio perf:freq at Nominal for conversion + * use them to convert perf to freq and vice versa. The conversion is + * extrapolated as an affine function passing by the 2 points: + * - (Low perf, Low freq) + * - (Nominal perf, Nominal perf) */ static unsigned int cppc_cpufreq_perf_to_khz(struct cppc_cpudata *cpu_data, unsigned int perf) { struct cppc_perf_caps *caps = &cpu_data->perf_caps; + s64 retval, offset = 0; static u64 max_khz; u64 mul, div; if (caps->lowest_freq && caps->nominal_freq) { - if (perf >= caps->nominal_perf) { - mul = caps->nominal_freq; - div = caps->nominal_perf; - } else { - mul = caps->nominal_freq - caps->lowest_freq; - div = caps->nominal_perf - caps->lowest_perf; - } + mul = caps->nominal_freq - caps->lowest_freq; + div = caps->nominal_perf - caps->lowest_perf; + offset = caps->nominal_freq - div64_u64(caps->nominal_perf * mul, div); } else { if (!max_khz) max_khz = cppc_get_dmi_max_khz(); mul = max_khz; div = caps->highest_perf; } - return (u64)perf * mul / div; + + retval = offset + div64_u64(perf * mul, div); + if (retval >= 0) + return retval; + return 0; } static unsigned int cppc_cpufreq_khz_to_perf(struct cppc_cpudata *cpu_data, unsigned int freq) { struct cppc_perf_caps *caps = &cpu_data->perf_caps; + s64 retval, offset = 0; static u64 max_khz; u64 mul, div; if (caps->lowest_freq && caps->nominal_freq) { - if (freq >= caps->nominal_freq) { - mul = caps->nominal_perf; - div = caps->nominal_freq; - } else { - mul = caps->lowest_perf; - div = caps->lowest_freq; - } + mul = caps->nominal_perf - caps->lowest_perf; + div = caps->nominal_freq - caps->lowest_freq; + offset = caps->nominal_perf - div64_u64(caps->nominal_freq * mul, div); } else { if (!max_khz) max_khz = cppc_get_dmi_max_khz(); @@ -356,7 +369,10 @@ static unsigned int cppc_cpufreq_khz_to_perf(struct cppc_cpudata *cpu_data, div = max_khz; } - return (u64)freq * mul / div; + retval = offset + div64_u64(freq * mul, div); + if (retval >= 0) + return retval; + return 0; } static int cppc_cpufreq_set_target(struct cpufreq_policy *policy, @@ -390,6 +406,27 @@ static int cppc_cpufreq_set_target(struct cpufreq_policy *policy, return ret; } +static unsigned int cppc_cpufreq_fast_switch(struct cpufreq_policy *policy, + unsigned int target_freq) +{ + struct cppc_cpudata *cpu_data = policy->driver_data; + unsigned int cpu = policy->cpu; + u32 desired_perf; + int ret; + + desired_perf = cppc_cpufreq_khz_to_perf(cpu_data, target_freq); + cpu_data->perf_ctrls.desired_perf = desired_perf; + ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls); + + if (ret) { + pr_debug("Failed to set target on CPU:%d. ret:%d\n", + cpu, ret); + return 0; + } + + return target_freq; +} + static int cppc_verify_policy(struct cpufreq_policy_data *policy) { cpufreq_verify_within_cpu_limits(policy); @@ -420,15 +457,199 @@ static unsigned int cppc_cpufreq_get_transition_delay_us(unsigned int cpu) } return cppc_get_transition_latency(cpu) / NSEC_PER_USEC; } - #else - static unsigned int cppc_cpufreq_get_transition_delay_us(unsigned int cpu) { return cppc_get_transition_latency(cpu) / NSEC_PER_USEC; } #endif +#if defined(CONFIG_ARM64) && defined(CONFIG_ENERGY_MODEL) + +static DEFINE_PER_CPU(unsigned int, efficiency_class); +static void cppc_cpufreq_register_em(struct cpufreq_policy *policy); + +/* Create an artificial performance state every CPPC_EM_CAP_STEP capacity unit. */ +#define CPPC_EM_CAP_STEP (20) +/* Increase the cost value by CPPC_EM_COST_STEP every performance state. */ +#define CPPC_EM_COST_STEP (1) +/* Add a cost gap correspnding to the energy of 4 CPUs. */ +#define CPPC_EM_COST_GAP (4 * SCHED_CAPACITY_SCALE * CPPC_EM_COST_STEP \ + / CPPC_EM_CAP_STEP) + +static unsigned int get_perf_level_count(struct cpufreq_policy *policy) +{ + struct cppc_perf_caps *perf_caps; + unsigned int min_cap, max_cap; + struct cppc_cpudata *cpu_data; + int cpu = policy->cpu; + + cpu_data = policy->driver_data; + perf_caps = &cpu_data->perf_caps; + max_cap = arch_scale_cpu_capacity(cpu); + min_cap = div_u64(max_cap * perf_caps->lowest_perf, perf_caps->highest_perf); + if ((min_cap == 0) || (max_cap < min_cap)) + return 0; + return 1 + max_cap / CPPC_EM_CAP_STEP - min_cap / CPPC_EM_CAP_STEP; +} + +/* + * The cost is defined as: + * cost = power * max_frequency / frequency + */ +static inline unsigned long compute_cost(int cpu, int step) +{ + return CPPC_EM_COST_GAP * per_cpu(efficiency_class, cpu) + + step * CPPC_EM_COST_STEP; +} + +static int cppc_get_cpu_power(struct device *cpu_dev, + unsigned long *power, unsigned long *KHz) +{ + unsigned long perf_step, perf_prev, perf, perf_check; + unsigned int min_step, max_step, step, step_check; + unsigned long prev_freq = *KHz; + unsigned int min_cap, max_cap; + struct cpufreq_policy *policy; + + struct cppc_perf_caps *perf_caps; + struct cppc_cpudata *cpu_data; + + policy = cpufreq_cpu_get_raw(cpu_dev->id); + cpu_data = policy->driver_data; + perf_caps = &cpu_data->perf_caps; + max_cap = arch_scale_cpu_capacity(cpu_dev->id); + min_cap = div_u64(max_cap * perf_caps->lowest_perf, + perf_caps->highest_perf); + + perf_step = CPPC_EM_CAP_STEP * perf_caps->highest_perf / max_cap; + min_step = min_cap / CPPC_EM_CAP_STEP; + max_step = max_cap / CPPC_EM_CAP_STEP; + + perf_prev = cppc_cpufreq_khz_to_perf(cpu_data, *KHz); + step = perf_prev / perf_step; + + if (step > max_step) + return -EINVAL; + + if (min_step == max_step) { + step = max_step; + perf = perf_caps->highest_perf; + } else if (step < min_step) { + step = min_step; + perf = perf_caps->lowest_perf; + } else { + step++; + if (step == max_step) + perf = perf_caps->highest_perf; + else + perf = step * perf_step; + } + + *KHz = cppc_cpufreq_perf_to_khz(cpu_data, perf); + perf_check = cppc_cpufreq_khz_to_perf(cpu_data, *KHz); + step_check = perf_check / perf_step; + + /* + * To avoid bad integer approximation, check that new frequency value + * increased and that the new frequency will be converted to the + * desired step value. + */ + while ((*KHz == prev_freq) || (step_check != step)) { + perf++; + *KHz = cppc_cpufreq_perf_to_khz(cpu_data, perf); + perf_check = cppc_cpufreq_khz_to_perf(cpu_data, *KHz); + step_check = perf_check / perf_step; + } + + /* + * With an artificial EM, only the cost value is used. Still the power + * is populated such as 0 < power < EM_MAX_POWER. This allows to add + * more sense to the artificial performance states. + */ + *power = compute_cost(cpu_dev->id, step); + + return 0; +} + +static int cppc_get_cpu_cost(struct device *cpu_dev, unsigned long KHz, + unsigned long *cost) +{ + unsigned long perf_step, perf_prev; + struct cppc_perf_caps *perf_caps; + struct cpufreq_policy *policy; + struct cppc_cpudata *cpu_data; + unsigned int max_cap; + int step; + + policy = cpufreq_cpu_get_raw(cpu_dev->id); + cpu_data = policy->driver_data; + perf_caps = &cpu_data->perf_caps; + max_cap = arch_scale_cpu_capacity(cpu_dev->id); + + perf_prev = cppc_cpufreq_khz_to_perf(cpu_data, KHz); + perf_step = CPPC_EM_CAP_STEP * perf_caps->highest_perf / max_cap; + step = perf_prev / perf_step; + + *cost = compute_cost(cpu_dev->id, step); + + return 0; +} + +static int populate_efficiency_class(void) +{ + struct acpi_madt_generic_interrupt *gicc; + DECLARE_BITMAP(used_classes, 256) = {}; + int class, cpu, index; + + for_each_possible_cpu(cpu) { + gicc = acpi_cpu_get_madt_gicc(cpu); + class = gicc->efficiency_class; + bitmap_set(used_classes, class, 1); + } + + if (bitmap_weight(used_classes, 256) <= 1) { + pr_debug("Efficiency classes are all equal (=%d). " + "No EM registered", class); + return -EINVAL; + } + + /* + * Squeeze efficiency class values on [0:#efficiency_class-1]. + * Values are per spec in [0:255]. + */ + index = 0; + for_each_set_bit(class, used_classes, 256) { + for_each_possible_cpu(cpu) { + gicc = acpi_cpu_get_madt_gicc(cpu); + if (gicc->efficiency_class == class) + per_cpu(efficiency_class, cpu) = index; + } + index++; + } + cppc_cpufreq_driver.register_em = cppc_cpufreq_register_em; + + return 0; +} + +static void cppc_cpufreq_register_em(struct cpufreq_policy *policy) +{ + struct cppc_cpudata *cpu_data; + struct em_data_callback em_cb = + EM_ADV_DATA_CB(cppc_get_cpu_power, cppc_get_cpu_cost); + + cpu_data = policy->driver_data; + em_dev_register_perf_domain(get_cpu_device(policy->cpu), + get_perf_level_count(policy), &em_cb, + cpu_data->shared_cpu_map, 0); +} + +#else +static int populate_efficiency_class(void) +{ + return 0; +} +#endif static struct cppc_cpudata *cppc_cpufreq_get_cpu_data(unsigned int cpu) { @@ -537,6 +758,9 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy) goto out; } + policy->fast_switch_possible = cppc_allow_fast_switch(); + policy->dvfs_possible_from_any_cpu = true; + /* * If 'highest_perf' is greater than 'nominal_perf', we assume CPU Boost * is supported. @@ -682,6 +906,7 @@ static struct cpufreq_driver cppc_cpufreq_driver = { .verify = cppc_verify_policy, .target = cppc_cpufreq_set_target, .get = cppc_cpufreq_get_rate, + .fast_switch = cppc_cpufreq_fast_switch, .init = cppc_cpufreq_cpu_init, .exit = cppc_cpufreq_cpu_exit, .set_boost = cppc_cpufreq_set_boost, @@ -727,6 +952,7 @@ static void cppc_check_hisi_workaround(void) wa_info[i].oem_revision == tbl->oem_revision) { /* Overwrite the get() callback */ cppc_cpufreq_driver.get = hisi_cppc_cpufreq_get_rate; + fie_disabled = FIE_DISABLED; break; } } @@ -738,11 +964,12 @@ static int __init cppc_cpufreq_init(void) { int ret; - if ((acpi_disabled) || !acpi_cpc_valid()) + if (!acpi_cpc_valid()) return -ENODEV; cppc_check_hisi_workaround(); cppc_freq_invariance_init(); + populate_efficiency_class(); ret = cpufreq_register_driver(&cppc_cpufreq_driver); if (ret) |