diff options
Diffstat (limited to 'drivers')
| -rw-r--r-- | drivers/base/arch_topology.c | 27 | ||||
| -rw-r--r-- | drivers/cpufreq/Kconfig.arm | 10 | ||||
| -rw-r--r-- | drivers/cpufreq/cppc_cpufreq.c | 290 | ||||
| -rw-r--r-- | drivers/cpufreq/cpufreq-dt-platdev.c | 10 | ||||
| -rw-r--r-- | drivers/cpufreq/mediatek-cpufreq.c | 1 | ||||
| -rw-r--r-- | drivers/cpufreq/scmi-cpufreq.c | 2 |
6 files changed, 303 insertions, 37 deletions
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index c1179edc0f3b..921312a8d957 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -18,10 +18,11 @@ #include <linux/cpumask.h> #include <linux/init.h> #include <linux/percpu.h> +#include <linux/rcupdate.h> #include <linux/sched.h> #include <linux/smp.h> -static DEFINE_PER_CPU(struct scale_freq_data *, sft_data); +static DEFINE_PER_CPU(struct scale_freq_data __rcu *, sft_data); static struct cpumask scale_freq_counters_mask; static bool scale_freq_invariant; @@ -66,16 +67,20 @@ void topology_set_scale_freq_source(struct scale_freq_data *data, if (cpumask_empty(&scale_freq_counters_mask)) scale_freq_invariant = topology_scale_freq_invariant(); + rcu_read_lock(); + for_each_cpu(cpu, cpus) { - sfd = per_cpu(sft_data, cpu); + sfd = rcu_dereference(*per_cpu_ptr(&sft_data, cpu)); /* Use ARCH provided counters whenever possible */ if (!sfd || sfd->source != SCALE_FREQ_SOURCE_ARCH) { - per_cpu(sft_data, cpu) = data; + rcu_assign_pointer(per_cpu(sft_data, cpu), data); cpumask_set_cpu(cpu, &scale_freq_counters_mask); } } + rcu_read_unlock(); + update_scale_freq_invariant(true); } EXPORT_SYMBOL_GPL(topology_set_scale_freq_source); @@ -86,22 +91,32 @@ void topology_clear_scale_freq_source(enum scale_freq_source source, struct scale_freq_data *sfd; int cpu; + rcu_read_lock(); + for_each_cpu(cpu, cpus) { - sfd = per_cpu(sft_data, cpu); + sfd = rcu_dereference(*per_cpu_ptr(&sft_data, cpu)); if (sfd && sfd->source == source) { - per_cpu(sft_data, cpu) = NULL; + rcu_assign_pointer(per_cpu(sft_data, cpu), NULL); cpumask_clear_cpu(cpu, &scale_freq_counters_mask); } } + rcu_read_unlock(); + + /* + * Make sure all references to previous sft_data are dropped to avoid + * use-after-free races. + */ + synchronize_rcu(); + update_scale_freq_invariant(false); } EXPORT_SYMBOL_GPL(topology_clear_scale_freq_source); void topology_scale_freq_tick(void) { - struct scale_freq_data *sfd = *this_cpu_ptr(&sft_data); + struct scale_freq_data *sfd = rcu_dereference_sched(*this_cpu_ptr(&sft_data)); if (sfd) sfd->set_freq_scale(); diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index e65e0a43be64..a5c5f70acfc9 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -19,6 +19,16 @@ config ACPI_CPPC_CPUFREQ If in doubt, say N. +config ACPI_CPPC_CPUFREQ_FIE + bool "Frequency Invariance support for CPPC cpufreq driver" + depends on ACPI_CPPC_CPUFREQ && GENERIC_ARCH_TOPOLOGY + default y + help + This extends frequency invariance support in the CPPC cpufreq driver, + by using CPPC delivered and reference performance counters. + + If in doubt, say N. + config ARM_ALLWINNER_SUN50I_CPUFREQ_NVMEM tristate "Allwinner nvmem based SUN50I CPUFreq driver" depends on ARCH_SUNXI diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index be4f62e2c5f1..d4c27022b9c9 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -10,14 +10,18 @@ #define pr_fmt(fmt) "CPPC Cpufreq:" fmt +#include <linux/arch_topology.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/delay.h> #include <linux/cpu.h> #include <linux/cpufreq.h> #include <linux/dmi.h> +#include <linux/irq_work.h> +#include <linux/kthread.h> #include <linux/time.h> #include <linux/vmalloc.h> +#include <uapi/linux/sched/types.h> #include <asm/unaligned.h> @@ -57,6 +61,216 @@ static struct cppc_workaround_oem_info wa_info[] = { } }; +#ifdef CONFIG_ACPI_CPPC_CPUFREQ_FIE + +/* Frequency invariance support */ +struct cppc_freq_invariance { + int cpu; + struct irq_work irq_work; + struct kthread_work work; + struct cppc_perf_fb_ctrs prev_perf_fb_ctrs; + struct cppc_cpudata *cpu_data; +}; + +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, + struct cppc_perf_fb_ctrs *fb_ctrs_t1); + +/** + * cppc_scale_freq_workfn - CPPC arch_freq_scale updater for frequency invariance + * @work: The work item. + * + * The CPPC driver register itself with the topology core to provide its own + * implementation (cppc_scale_freq_tick()) of topology_scale_freq_tick() which + * gets called by the scheduler on every tick. + * + * Note that the arch specific counters have higher priority than CPPC counters, + * if available, though the CPPC driver doesn't need to have any special + * handling for that. + * + * On an invocation of cppc_scale_freq_tick(), we schedule an irq work (since we + * reach here from hard-irq context), which then schedules a normal work item + * and cppc_scale_freq_workfn() updates the per_cpu arch_freq_scale variable + * based on the counter updates since the last tick. + */ +static void cppc_scale_freq_workfn(struct kthread_work *work) +{ + struct cppc_freq_invariance *cppc_fi; + struct cppc_perf_fb_ctrs fb_ctrs = {0}; + struct cppc_cpudata *cpu_data; + unsigned long local_freq_scale; + u64 perf; + + cppc_fi = container_of(work, struct cppc_freq_invariance, work); + cpu_data = cppc_fi->cpu_data; + + if (cppc_get_perf_ctrs(cppc_fi->cpu, &fb_ctrs)) { + pr_warn("%s: failed to read perf counters\n", __func__); + return; + } + + perf = cppc_perf_from_fbctrs(cpu_data, &cppc_fi->prev_perf_fb_ctrs, + &fb_ctrs); + cppc_fi->prev_perf_fb_ctrs = fb_ctrs; + + perf <<= SCHED_CAPACITY_SHIFT; + local_freq_scale = div64_u64(perf, cpu_data->perf_caps.highest_perf); + + /* This can happen due to counter's overflow */ + if (unlikely(local_freq_scale > 1024)) + local_freq_scale = 1024; + + per_cpu(arch_freq_scale, cppc_fi->cpu) = local_freq_scale; +} + +static void cppc_irq_work(struct irq_work *irq_work) +{ + struct cppc_freq_invariance *cppc_fi; + + cppc_fi = container_of(irq_work, struct cppc_freq_invariance, irq_work); + kthread_queue_work(kworker_fie, &cppc_fi->work); +} + +static void cppc_scale_freq_tick(void) +{ + struct cppc_freq_invariance *cppc_fi = &per_cpu(cppc_freq_inv, smp_processor_id()); + + /* + * cppc_get_perf_ctrs() can potentially sleep, call that from the right + * context. + */ + irq_work_queue(&cppc_fi->irq_work); +} + +static struct scale_freq_data cppc_sftd = { + .source = SCALE_FREQ_SOURCE_CPPC, + .set_freq_scale = cppc_scale_freq_tick, +}; + +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) + return; + + for_each_cpu(cpu, policy->cpus) { + cppc_fi = &per_cpu(cppc_freq_inv, cpu); + cppc_fi->cpu = cpu; + cppc_fi->cpu_data = policy->driver_data; + kthread_init_work(&cppc_fi->work, cppc_scale_freq_workfn); + init_irq_work(&cppc_fi->irq_work, cppc_irq_work); + + ret = cppc_get_perf_ctrs(cpu, &cppc_fi->prev_perf_fb_ctrs); + if (ret) { + pr_warn("%s: failed to read perf counters for cpu:%d: %d\n", + __func__, cpu, ret); + + /* + * Don't abort if the CPU was offline while the driver + * was getting registered. + */ + if (cpu_online(cpu)) + return; + } + } + + /* Register for freq-invariance */ + topology_set_scale_freq_source(&cppc_sftd, policy->cpus); +} + +/* + * We free all the resources on policy's removal and not on CPU removal as the + * irq-work are per-cpu and the hotplug core takes care of flushing the pending + * irq-works (hint: smpcfd_dying_cpu()) on CPU hotplug. Even if the kthread-work + * fires on another CPU after the concerned CPU is removed, it won't harm. + * + * We just need to make sure to remove them all on policy->exit(). + */ +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) + return; + + /* policy->cpus will be empty here, use related_cpus instead */ + topology_clear_scale_freq_source(SCALE_FREQ_SOURCE_CPPC, policy->related_cpus); + + for_each_cpu(cpu, policy->related_cpus) { + cppc_fi = &per_cpu(cppc_freq_inv, cpu); + irq_work_sync(&cppc_fi->irq_work); + kthread_cancel_work_sync(&cppc_fi->work); + } +} + +static void __init cppc_freq_invariance_init(void) +{ + struct sched_attr attr = { + .size = sizeof(struct sched_attr), + .sched_policy = SCHED_DEADLINE, + .sched_nice = 0, + .sched_priority = 0, + /* + * Fake (unused) bandwidth; workaround to "fix" + * priority inheritance. + */ + .sched_runtime = 1000000, + .sched_deadline = 10000000, + .sched_period = 10000000, + }; + int ret; + + if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate) + return; + + kworker_fie = kthread_create_worker(0, "cppc_fie"); + if (IS_ERR(kworker_fie)) + return; + + ret = sched_setattr_nocheck(kworker_fie->task, &attr); + if (ret) { + pr_warn("%s: failed to set SCHED_DEADLINE: %d\n", __func__, + ret); + kthread_destroy_worker(kworker_fie); + return; + } +} + +static void cppc_freq_invariance_exit(void) +{ + if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate) + return; + + kthread_destroy_worker(kworker_fie); + kworker_fie = NULL; +} + +#else +static inline void cppc_cpufreq_cpu_fie_init(struct cpufreq_policy *policy) +{ +} + +static inline void cppc_cpufreq_cpu_fie_exit(struct cpufreq_policy *policy) +{ +} + +static inline void cppc_freq_invariance_init(void) +{ +} + +static inline void cppc_freq_invariance_exit(void) +{ +} +#endif /* CONFIG_ACPI_CPPC_CPUFREQ_FIE */ + /* Callback function used to retrieve the max frequency from DMI */ static void cppc_find_dmi_mhz(const struct dmi_header *dm, void *private) { @@ -256,6 +470,16 @@ out: return NULL; } +static void cppc_cpufreq_put_cpu_data(struct cpufreq_policy *policy) +{ + struct cppc_cpudata *cpu_data = policy->driver_data; + + list_del(&cpu_data->node); + free_cpumask_var(cpu_data->shared_cpu_map); + kfree(cpu_data); + policy->driver_data = NULL; +} + static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy) { unsigned int cpu = policy->cpu; @@ -309,7 +533,8 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy) default: pr_debug("Unsupported CPU co-ord type: %d\n", policy->shared_type); - return -EFAULT; + ret = -EFAULT; + goto out; } /* @@ -324,10 +549,17 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy) cpu_data->perf_ctrls.desired_perf = caps->highest_perf; ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls); - if (ret) + if (ret) { pr_debug("Err setting perf value:%d on CPU:%d. ret:%d\n", caps->highest_perf, cpu, ret); + goto out; + } + cppc_cpufreq_cpu_fie_init(policy); + return 0; + +out: + cppc_cpufreq_put_cpu_data(policy); return ret; } @@ -338,6 +570,8 @@ static int cppc_cpufreq_cpu_exit(struct cpufreq_policy *policy) unsigned int cpu = policy->cpu; int ret; + cppc_cpufreq_cpu_fie_exit(policy); + cpu_data->perf_ctrls.desired_perf = caps->lowest_perf; ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls); @@ -345,12 +579,7 @@ static int cppc_cpufreq_cpu_exit(struct cpufreq_policy *policy) pr_debug("Err setting perf value:%d on CPU:%d. ret:%d\n", caps->lowest_perf, cpu, ret); - /* Remove CPU node from list and free driver data for policy */ - free_cpumask_var(cpu_data->shared_cpu_map); - list_del(&cpu_data->node); - kfree(policy->driver_data); - policy->driver_data = NULL; - + cppc_cpufreq_put_cpu_data(policy); return 0; } @@ -362,28 +591,25 @@ static inline u64 get_delta(u64 t1, u64 t0) return (u32)t1 - (u32)t0; } -static int cppc_get_rate_from_fbctrs(struct cppc_cpudata *cpu_data, - struct cppc_perf_fb_ctrs fb_ctrs_t0, - struct cppc_perf_fb_ctrs fb_ctrs_t1) +static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data, + struct cppc_perf_fb_ctrs *fb_ctrs_t0, + struct cppc_perf_fb_ctrs *fb_ctrs_t1) { u64 delta_reference, delta_delivered; - u64 reference_perf, delivered_perf; + u64 reference_perf; - reference_perf = fb_ctrs_t0.reference_perf; + reference_perf = fb_ctrs_t0->reference_perf; - delta_reference = get_delta(fb_ctrs_t1.reference, - fb_ctrs_t0.reference); - delta_delivered = get_delta(fb_ctrs_t1.delivered, - fb_ctrs_t0.delivered); + delta_reference = get_delta(fb_ctrs_t1->reference, + fb_ctrs_t0->reference); + delta_delivered = get_delta(fb_ctrs_t1->delivered, + fb_ctrs_t0->delivered); - /* Check to avoid divide-by zero */ - if (delta_reference || delta_delivered) - delivered_perf = (reference_perf * delta_delivered) / - delta_reference; - else - delivered_perf = cpu_data->perf_ctrls.desired_perf; + /* Check to avoid divide-by zero and invalid delivered_perf */ + if (!delta_reference || !delta_delivered) + return cpu_data->perf_ctrls.desired_perf; - return cppc_cpufreq_perf_to_khz(cpu_data, delivered_perf); + return (reference_perf * delta_delivered) / delta_reference; } static unsigned int cppc_cpufreq_get_rate(unsigned int cpu) @@ -391,6 +617,7 @@ static unsigned int cppc_cpufreq_get_rate(unsigned int cpu) struct cppc_perf_fb_ctrs fb_ctrs_t0 = {0}, fb_ctrs_t1 = {0}; struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); struct cppc_cpudata *cpu_data = policy->driver_data; + u64 delivered_perf; int ret; cpufreq_cpu_put(policy); @@ -405,7 +632,10 @@ static unsigned int cppc_cpufreq_get_rate(unsigned int cpu) if (ret) return ret; - return cppc_get_rate_from_fbctrs(cpu_data, fb_ctrs_t0, fb_ctrs_t1); + delivered_perf = cppc_perf_from_fbctrs(cpu_data, &fb_ctrs_t0, + &fb_ctrs_t1); + + return cppc_cpufreq_perf_to_khz(cpu_data, delivered_perf); } static int cppc_cpufreq_set_boost(struct cpufreq_policy *policy, int state) @@ -506,14 +736,21 @@ static void cppc_check_hisi_workaround(void) static int __init cppc_cpufreq_init(void) { + int ret; + if ((acpi_disabled) || !acpi_cpc_valid()) return -ENODEV; INIT_LIST_HEAD(&cpu_data_list); cppc_check_hisi_workaround(); + cppc_freq_invariance_init(); - return cpufreq_register_driver(&cppc_cpufreq_driver); + ret = cpufreq_register_driver(&cppc_cpufreq_driver); + if (ret) + cppc_freq_invariance_exit(); + + return ret; } static inline void free_cpu_data(void) @@ -531,6 +768,7 @@ static inline void free_cpu_data(void) static void __exit cppc_cpufreq_exit(void) { cpufreq_unregister_driver(&cppc_cpufreq_driver); + cppc_freq_invariance_exit(); free_cpu_data(); } diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c index 5e07065ec22f..bef7528aecd3 100644 --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -15,7 +15,7 @@ * Machines for which the cpufreq device is *always* created, mostly used for * platforms using "operating-points" (V1) property. */ -static const struct of_device_id whitelist[] __initconst = { +static const struct of_device_id allowlist[] __initconst = { { .compatible = "allwinner,sun4i-a10", }, { .compatible = "allwinner,sun5i-a10s", }, { .compatible = "allwinner,sun5i-a13", }, @@ -100,7 +100,7 @@ static const struct of_device_id whitelist[] __initconst = { * Machines for which the cpufreq device is *not* created, mostly used for * platforms using "operating-points-v2" property. */ -static const struct of_device_id blacklist[] __initconst = { +static const struct of_device_id blocklist[] __initconst = { { .compatible = "allwinner,sun50i-h6", }, { .compatible = "arm,vexpress", }, @@ -126,6 +126,7 @@ static const struct of_device_id blacklist[] __initconst = { { .compatible = "mediatek,mt8173", }, { .compatible = "mediatek,mt8176", }, { .compatible = "mediatek,mt8183", }, + { .compatible = "mediatek,mt8365", }, { .compatible = "mediatek,mt8516", }, { .compatible = "nvidia,tegra20", }, @@ -137,6 +138,7 @@ static const struct of_device_id blacklist[] __initconst = { { .compatible = "qcom,msm8996", }, { .compatible = "qcom,qcs404", }, { .compatible = "qcom,sc7180", }, + { .compatible = "qcom,sc7280", }, { .compatible = "qcom,sdm845", }, { .compatible = "st,stih407", }, @@ -177,13 +179,13 @@ static int __init cpufreq_dt_platdev_init(void) if (!np) return -ENODEV; - match = of_match_node(whitelist, np); + match = of_match_node(allowlist, np); if (match) { data = match->data; goto create_pdev; } - if (cpu0_node_has_opp_v2_prop() && !of_match_node(blacklist, np)) + if (cpu0_node_has_opp_v2_prop() && !of_match_node(blocklist, np)) goto create_pdev; of_node_put(np); diff --git a/drivers/cpufreq/mediatek-cpufreq.c b/drivers/cpufreq/mediatek-cpufreq.c index f2e491b25b07..87019d5a9547 100644 --- a/drivers/cpufreq/mediatek-cpufreq.c +++ b/drivers/cpufreq/mediatek-cpufreq.c @@ -537,6 +537,7 @@ static const struct of_device_id mtk_cpufreq_machines[] __initconst = { { .compatible = "mediatek,mt8173", }, { .compatible = "mediatek,mt8176", }, { .compatible = "mediatek,mt8183", }, + { .compatible = "mediatek,mt8365", }, { .compatible = "mediatek,mt8516", }, { } diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c index c8a4364ad3c2..ec9a87ca2dbb 100644 --- a/drivers/cpufreq/scmi-cpufreq.c +++ b/drivers/cpufreq/scmi-cpufreq.c @@ -174,7 +174,7 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy) nr_opp = dev_pm_opp_get_opp_count(cpu_dev); if (nr_opp <= 0) { dev_err(cpu_dev, "%s: No OPPs for this device: %d\n", - __func__, ret); + __func__, nr_opp); ret = -ENODEV; goto out_free_opp; |