diff options
52 files changed, 972 insertions, 413 deletions
diff --git a/Documentation/devicetree/bindings/cpufreq/airoha,en7581-cpufreq.yaml b/Documentation/devicetree/bindings/cpufreq/airoha,en7581-cpufreq.yaml new file mode 100644 index 000000000000..7d4510b3219c --- /dev/null +++ b/Documentation/devicetree/bindings/cpufreq/airoha,en7581-cpufreq.yaml @@ -0,0 +1,55 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/cpufreq/airoha,en7581-cpufreq.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Airoha EN7581 CPUFreq + +maintainers: + - Christian Marangi <ansuelsmth@gmail.com> + +description: | + On newer Airoha SoC, CPU Frequency is scaled indirectly with SMC commands + to ATF. + + A virtual clock is exposed. This virtual clock is a get-only clock and + is used to expose the current global CPU clock. The frequency info comes + by the output of the SMC command that reports the clock in MHz. + + The SMC sets the CPU clock by providing an index, this is modelled as + performance states in a power domain. + + CPUs can't be individually scaled as the CPU frequency is shared across + all CPUs and is global. + +properties: + compatible: + const: airoha,en7581-cpufreq + + '#clock-cells': + const: 0 + + '#power-domain-cells': + const: 0 + + operating-points-v2: true + +required: + - compatible + - '#clock-cells' + - '#power-domain-cells' + - operating-points-v2 + +additionalProperties: false + +examples: + - | + performance-domain { + compatible = "airoha,en7581-cpufreq"; + + operating-points-v2 = <&cpu_smcc_opp_table>; + + #power-domain-cells = <0>; + #clock-cells = <0>; + }; diff --git a/Documentation/devicetree/bindings/cpufreq/apple,cluster-cpufreq.yaml b/Documentation/devicetree/bindings/cpufreq/apple,cluster-cpufreq.yaml index 76cb9726660e..896276b8c6bb 100644 --- a/Documentation/devicetree/bindings/cpufreq/apple,cluster-cpufreq.yaml +++ b/Documentation/devicetree/bindings/cpufreq/apple,cluster-cpufreq.yaml @@ -24,9 +24,17 @@ properties: - apple,t8112-cluster-cpufreq - const: apple,cluster-cpufreq - items: - - const: apple,t6000-cluster-cpufreq + - enum: + - apple,s8000-cluster-cpufreq + - apple,t8010-cluster-cpufreq + - apple,t8015-cluster-cpufreq + - apple,t6000-cluster-cpufreq - const: apple,t8103-cluster-cpufreq - const: apple,cluster-cpufreq + - items: + - const: apple,t7000-cluster-cpufreq + - const: apple,s5l8960x-cluster-cpufreq + - const: apple,s5l8960x-cluster-cpufreq reg: maxItems: 1 diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 4a67e83300e1..cbc9a7a75def 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -496,6 +496,7 @@ struct dpm_watchdog { struct device *dev; struct task_struct *tsk; struct timer_list timer; + bool fatal; }; #define DECLARE_DPM_WATCHDOG_ON_STACK(wd) \ @@ -512,11 +513,23 @@ struct dpm_watchdog { static void dpm_watchdog_handler(struct timer_list *t) { struct dpm_watchdog *wd = from_timer(wd, t, timer); + struct timer_list *timer = &wd->timer; + unsigned int time_left; + + if (wd->fatal) { + dev_emerg(wd->dev, "**** DPM device timeout ****\n"); + show_stack(wd->tsk, NULL, KERN_EMERG); + panic("%s %s: unrecoverable failure\n", + dev_driver_string(wd->dev), dev_name(wd->dev)); + } + + time_left = CONFIG_DPM_WATCHDOG_TIMEOUT - CONFIG_DPM_WATCHDOG_WARNING_TIMEOUT; + dev_warn(wd->dev, "**** DPM device timeout after %u seconds; %u seconds until panic ****\n", + CONFIG_DPM_WATCHDOG_WARNING_TIMEOUT, time_left); + show_stack(wd->tsk, NULL, KERN_WARNING); - dev_emerg(wd->dev, "**** DPM device timeout ****\n"); - show_stack(wd->tsk, NULL, KERN_EMERG); - panic("%s %s: unrecoverable failure\n", - dev_driver_string(wd->dev), dev_name(wd->dev)); + wd->fatal = true; + mod_timer(timer, jiffies + HZ * time_left); } /** @@ -530,10 +543,11 @@ static void dpm_watchdog_set(struct dpm_watchdog *wd, struct device *dev) wd->dev = dev; wd->tsk = current; + wd->fatal = CONFIG_DPM_WATCHDOG_TIMEOUT == CONFIG_DPM_WATCHDOG_WARNING_TIMEOUT; timer_setup_on_stack(timer, dpm_watchdog_handler, 0); /* use same timeout value for both suspend and resume */ - timer->expires = jiffies + HZ * CONFIG_DPM_WATCHDOG_TIMEOUT; + timer->expires = jiffies + HZ * CONFIG_DPM_WATCHDOG_WARNING_TIMEOUT; add_timer(timer); } @@ -914,7 +928,7 @@ static void device_resume(struct device *dev, pm_message_t state, bool async) goto Complete; if (dev->power.direct_complete) { - /* Match the pm_runtime_disable() in __device_suspend(). */ + /* Match the pm_runtime_disable() in device_suspend(). */ pm_runtime_enable(dev); goto Complete; } diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c index f8163b559bf9..f84018125b46 100644 --- a/drivers/base/power/sysfs.c +++ b/drivers/base/power/sysfs.c @@ -6,7 +6,6 @@ #include <linux/export.h> #include <linux/pm_qos.h> #include <linux/pm_runtime.h> -#include <linux/pm_wakeup.h> #include <linux/atomic.h> #include <linux/jiffies.h> #include "power.h" diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c index 5a5a9e978e85..8aa28c08b289 100644 --- a/drivers/base/power/wakeirq.c +++ b/drivers/base/power/wakeirq.c @@ -103,6 +103,32 @@ void dev_pm_clear_wake_irq(struct device *dev) } EXPORT_SYMBOL_GPL(dev_pm_clear_wake_irq); +static void devm_pm_clear_wake_irq(void *dev) +{ + dev_pm_clear_wake_irq(dev); +} + +/** + * devm_pm_set_wake_irq - device-managed variant of dev_pm_set_wake_irq + * @dev: Device entry + * @irq: Device IO interrupt + * + * + * Attach a device IO interrupt as a wake IRQ, same with dev_pm_set_wake_irq, + * but the device will be auto clear wake capability on driver detach. + */ +int devm_pm_set_wake_irq(struct device *dev, int irq) +{ + int ret; + + ret = dev_pm_set_wake_irq(dev, irq); + if (ret) + return ret; + + return devm_add_action_or_reset(dev, devm_pm_clear_wake_irq, dev); +} +EXPORT_SYMBOL_GPL(devm_pm_set_wake_irq); + /** * handle_threaded_wake_irq - Handler for dedicated wake-up interrupts * @irq: Device specific dedicated wake-up interrupt diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig index 26e98fea991a..d64b07ec48e5 100644 --- a/drivers/cpufreq/Kconfig +++ b/drivers/cpufreq/Kconfig @@ -232,7 +232,7 @@ config CPUFREQ_VIRT If in doubt, say N. config CPUFREQ_DT_PLATDEV - tristate "Generic DT based cpufreq platdev driver" + bool "Generic DT based cpufreq platdev driver" depends on OF help This adds a generic DT based cpufreq platdev driver for frequency diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index 5f7e13e60c80..704e84d00639 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -15,6 +15,14 @@ config ARM_ALLWINNER_SUN50I_CPUFREQ_NVMEM To compile this driver as a module, choose M here: the module will be called sun50i-cpufreq-nvmem. +config ARM_AIROHA_SOC_CPUFREQ + tristate "Airoha EN7581 SoC CPUFreq support" + depends on ARCH_AIROHA || COMPILE_TEST + select PM_OPP + default ARCH_AIROHA + help + This adds the CPUFreq driver for Airoha EN7581 SoCs. + config ARM_APPLE_SOC_CPUFREQ tristate "Apple Silicon SoC CPUFreq support" depends on ARCH_APPLE || (COMPILE_TEST && 64BIT) diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile index d35a28dd9463..890fff99f37d 100644 --- a/drivers/cpufreq/Makefile +++ b/drivers/cpufreq/Makefile @@ -53,6 +53,7 @@ obj-$(CONFIG_X86_AMD_FREQ_SENSITIVITY) += amd_freq_sensitivity.o ################################################################################## # ARM SoC drivers +obj-$(CONFIG_ARM_AIROHA_SOC_CPUFREQ) += airoha-cpufreq.o obj-$(CONFIG_ARM_APPLE_SOC_CPUFREQ) += apple-soc-cpufreq.o obj-$(CONFIG_ARM_ARMADA_37XX_CPUFREQ) += armada-37xx-cpufreq.o obj-$(CONFIG_ARM_ARMADA_8K_CPUFREQ) += armada-8k-cpufreq.o diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index c9ebacf5c88e..302df42d6887 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -623,7 +623,14 @@ static int acpi_cpufreq_blacklist(struct cpuinfo_x86 *c) #endif #ifdef CONFIG_ACPI_CPPC_LIB -static u64 get_max_boost_ratio(unsigned int cpu) +/* + * get_max_boost_ratio: Computes the max_boost_ratio as the ratio + * between the highest_perf and the nominal_perf. + * + * Returns the max_boost_ratio for @cpu. Returns the CPPC nominal + * frequency via @nominal_freq if it is non-NULL pointer. + */ +static u64 get_max_boost_ratio(unsigned int cpu, u64 *nominal_freq) { struct cppc_perf_caps perf_caps; u64 highest_perf, nominal_perf; @@ -652,6 +659,9 @@ static u64 get_max_boost_ratio(unsigned int cpu) nominal_perf = perf_caps.nominal_perf; + if (nominal_freq) + *nominal_freq = perf_caps.nominal_freq; + if (!highest_perf || !nominal_perf) { pr_debug("CPU%d: highest or nominal performance missing\n", cpu); return 0; @@ -664,8 +674,12 @@ static u64 get_max_boost_ratio(unsigned int cpu) return div_u64(highest_perf << SCHED_CAPACITY_SHIFT, nominal_perf); } + #else -static inline u64 get_max_boost_ratio(unsigned int cpu) { return 0; } +static inline u64 get_max_boost_ratio(unsigned int cpu, u64 *nominal_freq) +{ + return 0; +} #endif static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) @@ -675,9 +689,9 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) struct acpi_cpufreq_data *data; unsigned int cpu = policy->cpu; struct cpuinfo_x86 *c = &cpu_data(cpu); + u64 max_boost_ratio, nominal_freq = 0; unsigned int valid_states = 0; unsigned int result = 0; - u64 max_boost_ratio; unsigned int i; #ifdef CONFIG_SMP static int blacklisted; @@ -827,16 +841,20 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) } freq_table[valid_states].frequency = CPUFREQ_TABLE_END; - max_boost_ratio = get_max_boost_ratio(cpu); + max_boost_ratio = get_max_boost_ratio(cpu, &nominal_freq); if (max_boost_ratio) { - unsigned int freq = freq_table[0].frequency; + unsigned int freq = nominal_freq; /* - * Because the loop above sorts the freq_table entries in the - * descending order, freq is the maximum frequency in the table. - * Assume that it corresponds to the CPPC nominal frequency and - * use it to set cpuinfo.max_freq. + * The loop above sorts the freq_table entries in the + * descending order. If ACPI CPPC has not advertised + * the nominal frequency (this is possible in CPPC + * revisions prior to 3), then use the first entry in + * the pstate table as a proxy for nominal frequency. */ + if (!freq) + freq = freq_table[0].frequency; + policy->cpuinfo.max_freq = freq * max_boost_ratio >> SCHED_CAPACITY_SHIFT; } else { /* diff --git a/drivers/cpufreq/airoha-cpufreq.c b/drivers/cpufreq/airoha-cpufreq.c new file mode 100644 index 000000000000..4fe39eadd163 --- /dev/null +++ b/drivers/cpufreq/airoha-cpufreq.c @@ -0,0 +1,152 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bitfield.h> +#include <linux/cpufreq.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/pm_domain.h> +#include <linux/pm_runtime.h> +#include <linux/slab.h> + +#include "cpufreq-dt.h" + +struct airoha_cpufreq_priv { + int opp_token; + struct dev_pm_domain_list *pd_list; + struct platform_device *cpufreq_dt; +}; + +static struct platform_device *cpufreq_pdev; + +/* NOP function to disable OPP from setting clock */ +static int airoha_cpufreq_config_clks_nop(struct device *dev, + struct opp_table *opp_table, + struct dev_pm_opp *opp, + void *data, bool scaling_down) +{ + return 0; +} + +static const char * const airoha_cpufreq_clk_names[] = { "cpu", NULL }; +static const char * const airoha_cpufreq_pd_names[] = { "perf" }; + +static int airoha_cpufreq_probe(struct platform_device *pdev) +{ + const struct dev_pm_domain_attach_data attach_data = { + .pd_names = airoha_cpufreq_pd_names, + .num_pd_names = ARRAY_SIZE(airoha_cpufreq_pd_names), + .pd_flags = PD_FLAG_DEV_LINK_ON | PD_FLAG_REQUIRED_OPP, + }; + struct dev_pm_opp_config config = { + .clk_names = airoha_cpufreq_clk_names, + .config_clks = airoha_cpufreq_config_clks_nop, + }; + struct platform_device *cpufreq_dt; + struct airoha_cpufreq_priv *priv; + struct device *dev = &pdev->dev; + struct device *cpu_dev; + int ret; + + /* CPUs refer to the same OPP table */ + cpu_dev = get_cpu_device(0); + if (!cpu_dev) + return -ENODEV; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + /* Set OPP table conf with NOP config_clks */ + priv->opp_token = dev_pm_opp_set_config(cpu_dev, &config); + if (priv->opp_token < 0) + return dev_err_probe(dev, priv->opp_token, "Failed to set OPP config\n"); + + /* Attach PM for OPP */ + ret = dev_pm_domain_attach_list(cpu_dev, &attach_data, + &priv->pd_list); + if (ret) + goto clear_opp_config; + + cpufreq_dt = platform_device_register_simple("cpufreq-dt", -1, NULL, 0); + ret = PTR_ERR_OR_ZERO(cpufreq_dt); + if (ret) { + dev_err(dev, "failed to create cpufreq-dt device: %d\n", ret); + goto detach_pm; + } + + priv->cpufreq_dt = cpufreq_dt; + platform_set_drvdata(pdev, priv); + + return 0; + +detach_pm: + dev_pm_domain_detach_list(priv->pd_list); +clear_opp_config: + dev_pm_opp_clear_config(priv->opp_token); + + return ret; +} + +static void airoha_cpufreq_remove(struct platform_device *pdev) +{ + struct airoha_cpufreq_priv *priv = platform_get_drvdata(pdev); + + platform_device_unregister(priv->cpufreq_dt); + + dev_pm_domain_detach_list(priv->pd_list); + + dev_pm_opp_clear_config(priv->opp_token); +} + +static struct platform_driver airoha_cpufreq_driver = { + .probe = airoha_cpufreq_probe, + .remove = airoha_cpufreq_remove, + .driver = { + .name = "airoha-cpufreq", + }, +}; + +static const struct of_device_id airoha_cpufreq_match_list[] __initconst = { + { .compatible = "airoha,en7581" }, + {}, +}; +MODULE_DEVICE_TABLE(of, airoha_cpufreq_match_list); + +static int __init airoha_cpufreq_init(void) +{ + struct device_node *np = of_find_node_by_path("/"); + const struct of_device_id *match; + int ret; + + if (!np) + return -ENODEV; + + match = of_match_node(airoha_cpufreq_match_list, np); + of_node_put(np); + if (!match) + return -ENODEV; + + ret = platform_driver_register(&airoha_cpufreq_driver); + if (unlikely(ret < 0)) + return ret; + + cpufreq_pdev = platform_device_register_data(NULL, "airoha-cpufreq", + -1, match, sizeof(*match)); + ret = PTR_ERR_OR_ZERO(cpufreq_pdev); + if (ret) + platform_driver_unregister(&airoha_cpufreq_driver); + + return ret; +} +module_init(airoha_cpufreq_init); + +static void __exit airoha_cpufreq_exit(void) +{ + platform_device_unregister(cpufreq_pdev); + platform_driver_unregister(&airoha_cpufreq_driver); +} +module_exit(airoha_cpufreq_exit); + +MODULE_AUTHOR("Christian Marangi <ansuelsmth@gmail.com>"); +MODULE_DESCRIPTION("CPUfreq driver for Airoha SoCs"); +MODULE_LICENSE("GPL"); diff --git a/drivers/cpufreq/amd-pstate-trace.h b/drivers/cpufreq/amd-pstate-trace.h index 35f38ae67fb1..8d692415d905 100644 --- a/drivers/cpufreq/amd-pstate-trace.h +++ b/drivers/cpufreq/amd-pstate-trace.h @@ -32,7 +32,6 @@ TRACE_EVENT(amd_pstate_perf, u64 aperf, u64 tsc, unsigned int cpu_id, - bool changed, bool fast_switch ), @@ -44,7 +43,6 @@ TRACE_EVENT(amd_pstate_perf, aperf, tsc, cpu_id, - changed, fast_switch ), @@ -57,7 +55,6 @@ TRACE_EVENT(amd_pstate_perf, __field(unsigned long long, aperf) __field(unsigned long long, tsc) __field(unsigned int, cpu_id) - __field(bool, changed) __field(bool, fast_switch) ), @@ -70,11 +67,10 @@ TRACE_EVENT(amd_pstate_perf, __entry->aperf = aperf; __entry->tsc = tsc; __entry->cpu_id = cpu_id; - __entry->changed = changed; __entry->fast_switch = fast_switch; ), - TP_printk("amd_min_perf=%lu amd_des_perf=%lu amd_max_perf=%lu freq=%llu mperf=%llu aperf=%llu tsc=%llu cpu_id=%u changed=%s fast_switch=%s", + TP_printk("amd_min_perf=%lu amd_des_perf=%lu amd_max_perf=%lu freq=%llu mperf=%llu aperf=%llu tsc=%llu cpu_id=%u fast_switch=%s", (unsigned long)__entry->min_perf, (unsigned long)__entry->target_perf, (unsigned long)__entry->capacity, @@ -83,11 +79,55 @@ TRACE_EVENT(amd_pstate_perf, (unsigned long long)__entry->aperf, (unsigned long long)__entry->tsc, (unsigned int)__entry->cpu_id, - (__entry->changed) ? "true" : "false", (__entry->fast_switch) ? "true" : "false" ) ); +TRACE_EVENT(amd_pstate_epp_perf, + + TP_PROTO(unsigned int cpu_id, + unsigned int highest_perf, + unsigned int epp, + unsigned int min_perf, + unsigned int max_perf, + bool boost + ), + + TP_ARGS(cpu_id, + highest_perf, + epp, + min_perf, + max_perf, + boost), + + TP_STRUCT__entry( + __field(unsigned int, cpu_id) + __field(unsigned int, highest_perf) + __field(unsigned int, epp) + __field(unsigned int, min_perf) + __field(unsigned int, max_perf) + __field(bool, boost) + ), + + TP_fast_assign( + __entry->cpu_id = cpu_id; + __entry->highest_perf = highest_perf; + __entry->epp = epp; + __entry->min_perf = min_perf; + __entry->max_perf = max_perf; + __entry->boost = boost; + ), + + TP_printk("cpu%u: [%u<->%u]/%u, epp=%u, boost=%u", + (unsigned int)__entry->cpu_id, + (unsigned int)__entry->min_perf, + (unsigned int)__entry->max_perf, + (unsigned int)__entry->highest_perf, + (unsigned int)__entry->epp, + (bool)__entry->boost + ) +); + #endif /* _AMD_PSTATE_TRACE_H */ /* This part must be outside protection */ diff --git a/drivers/cpufreq/amd-pstate-ut.c b/drivers/cpufreq/amd-pstate-ut.c index a261d7300951..3a0a380c3590 100644 --- a/drivers/cpufreq/amd-pstate-ut.c +++ b/drivers/cpufreq/amd-pstate-ut.c @@ -207,7 +207,6 @@ static void amd_pstate_ut_check_freq(u32 index) int cpu = 0; struct cpufreq_policy *policy = NULL; struct amd_cpudata *cpudata = NULL; - u32 nominal_freq_khz; for_each_possible_cpu(cpu) { policy = cpufreq_cpu_get(cpu); @@ -215,14 +214,13 @@ static void amd_pstate_ut_check_freq(u32 index) break; cpudata = policy->driver_data; - nominal_freq_khz = cpudata->nominal_freq*1000; - if (!((cpudata->max_freq >= nominal_freq_khz) && - (nominal_freq_khz > cpudata->lowest_nonlinear_freq) && + if (!((cpudata->max_freq >= cpudata->nominal_freq) && + (cpudata->nominal_freq > cpudata->lowest_nonlinear_freq) && (cpudata->lowest_nonlinear_freq > cpudata->min_freq) && (cpudata->min_freq > 0))) { amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_FAIL; pr_err("%s cpu%d max=%d >= nominal=%d > lowest_nonlinear=%d > min=%d > 0, the formula is incorrect!\n", - __func__, cpu, cpudata->max_freq, nominal_freq_khz, + __func__, cpu, cpudata->max_freq, cpudata->nominal_freq, cpudata->lowest_nonlinear_freq, cpudata->min_freq); goto skip_test; } @@ -236,13 +234,13 @@ static void amd_pstate_ut_check_freq(u32 index) if (cpudata->boost_supported) { if ((policy->max == cpudata->max_freq) || - (policy->max == nominal_freq_khz)) + (policy->max == cpudata->nominal_freq)) amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_PASS; else { amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_FAIL; pr_err("%s cpu%d policy_max=%d should be equal cpu_max=%d or cpu_nominal=%d !\n", __func__, cpu, policy->max, cpudata->max_freq, - nominal_freq_khz); + cpudata->nominal_freq); goto skip_test; } } else { diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 66e5dfc711c0..dd9b8d6993d6 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -22,6 +22,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/bitfield.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> @@ -88,6 +89,11 @@ static bool cppc_enabled; static bool amd_pstate_prefcore = true; static struct quirk_entry *quirks; +#define AMD_CPPC_MAX_PERF_MASK GENMASK(7, 0) +#define AMD_CPPC_MIN_PERF_MASK GENMASK(15, 8) +#define AMD_CPPC_DES_PERF_MASK GENMASK(23, 16) +#define AMD_CPPC_EPP_PERF_MASK GENMASK(31, 24) + /* * AMD Energy Preference Performance (EPP) * The EPP is used in the CCLK DPM controller to drive @@ -180,120 +186,145 @@ static inline int get_mode_idx_from_str(const char *str, size_t size) static DEFINE_MUTEX(amd_pstate_limits_lock); static DEFINE_MUTEX(amd_pstate_driver_lock); -static s16 amd_pstate_get_epp(struct amd_cpudata *cpudata, u64 cppc_req_cached) +static s16 msr_get_epp(struct amd_cpudata *cpudata) { - u64 epp; + u64 value; int ret; - if (cpu_feature_enabled(X86_FEATURE_CPPC)) { - if (!cppc_req_cached) { - epp = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, - &cppc_req_cached); - if (epp) - return epp; - } - epp = (cppc_req_cached >> 24) & 0xFF; - } else { - ret = cppc_get_epp_perf(cpudata->cpu, &epp); - if (ret < 0) { - pr_debug("Could not retrieve energy perf value (%d)\n", ret); - return -EIO; - } + ret = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, &value); + if (ret < 0) { + pr_debug("Could not retrieve energy perf value (%d)\n", ret); + return ret; } - return (s16)(epp & 0xff); + return FIELD_GET(AMD_CPPC_EPP_PERF_MASK, value); } -static int amd_pstate_get_energy_pref_index(struct amd_cpudata *cpudata) +DEFINE_STATIC_CALL(amd_pstate_get_epp, msr_get_epp); + +static inline s16 amd_pstate_get_epp(struct amd_cpudata *cpudata) { - s16 epp; - int index = -EINVAL; + return static_call(amd_pstate_get_epp)(cpudata); +} - epp = amd_pstate_get_epp(cpudata, 0); - if (epp < 0) - return epp; +static s16 shmem_get_epp(struct amd_cpudata *cpudata) +{ + u64 epp; + int ret; - switch (epp) { - case AMD_CPPC_EPP_PERFORMANCE: - index = EPP_INDEX_PERFORMANCE; - break; - case AMD_CPPC_EPP_BALANCE_PERFORMANCE: - index = EPP_INDEX_BALANCE_PERFORMANCE; - break; - case AMD_CPPC_EPP_BALANCE_POWERSAVE: - index = EPP_INDEX_BALANCE_POWERSAVE; - break; - case AMD_CPPC_EPP_POWERSAVE: - index = EPP_INDEX_POWERSAVE; - break; - default: - break; + ret = cppc_get_epp_perf(cpudata->cpu, &epp); + if (ret < 0) { + pr_debug("Could not retrieve energy perf value (%d)\n", ret); + return ret; } - return index; + return (s16)(epp & 0xff); } -static void msr_update_perf(struct amd_cpudata *cpudata, u32 min_perf, - u32 des_perf, u32 max_perf, bool fast_switch) +static int msr_update_perf(struct amd_cpudata *cpudata, u32 min_perf, + u32 des_perf, u32 max_perf, u32 epp, bool fast_switch) { - if (fast_switch) - wrmsrl(MSR_AMD_CPPC_REQ, READ_ONCE(cpudata->cppc_req_cached)); - else - wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, - READ_ONCE(cpudata->cppc_req_cached)); + u64 value, prev; + + value = prev = READ_ONCE(cpudata->cppc_req_cached); + + value &= ~(AMD_CPPC_MAX_PERF_MASK | AMD_CPPC_MIN_PERF_MASK | + AMD_CPPC_DES_PERF_MASK | AMD_CPPC_EPP_PERF_MASK); + value |= FIELD_PREP(AMD_CPPC_MAX_PERF_MASK, max_perf); + value |= FIELD_PREP(AMD_CPPC_DES_PERF_MASK, des_perf); + value |= FIELD_PREP(AMD_CPPC_MIN_PERF_MASK, min_perf); + value |= FIELD_PREP(AMD_CPPC_EPP_PERF_MASK, epp); + + if (value == prev) + return 0; + + if (fast_switch) { + wrmsrl(MSR_AMD_CPPC_REQ, value); + return 0; + } else { + int ret = wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value); + + if (ret) + return ret; + } + + WRITE_ONCE(cpudata->cppc_req_cached, value); + WRITE_ONCE(cpudata->epp_cached, epp); + + return 0; } DEFINE_STATIC_CALL(amd_pstate_update_perf, msr_update_perf); -static inline void amd_pstate_update_perf(struct amd_cpudata *cpudata, +static inline int amd_pstate_update_perf(struct amd_cpudata *cpudata, u32 min_perf, u32 des_perf, - u32 max_perf, bool fast_switch) + u32 max_perf, u32 epp, + bool fast_switch) { - static_call(amd_pstate_update_perf)(cpudata, min_perf, des_perf, - max_perf, fast_switch); + return static_call(amd_pstate_update_perf)(cpudata, min_perf, des_perf, + max_perf, epp, fast_switch); } -static int amd_pstate_set_epp(struct amd_cpudata *cpudata, u32 epp) +static int msr_set_epp(struct amd_cpudata *cpudata, u32 epp) { + u64 value, prev; int ret; - struct cppc_perf_ctrls perf_ctrls; - if (cpu_feature_enabled(X86_FEATURE_CPPC)) { - u64 value = READ_ONCE(cpudata->cppc_req_cached); - - value &= ~GENMASK_ULL(31, 24); - value |= (u64)epp << 24; - WRITE_ONCE(cpudata->cppc_req_cached, value); + value = prev = READ_ONCE(cpudata->cppc_req_cached); + value &= ~AMD_CPPC_EPP_PERF_MASK; + value |= FIELD_PREP(AMD_CPPC_EPP_PERF_MASK, epp); - ret = wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value); - if (!ret) - cpudata->epp_cached = epp; - } else { - amd_pstate_update_perf(cpudata, cpudata->min_limit_perf, 0U, - cpudata->max_limit_perf, false); + if (value == prev) + return 0; - perf_ctrls.energy_perf = epp; - ret = cppc_set_epp_perf(cpudata->cpu, &perf_ctrls, 1); - if (ret) { - pr_debug("failed to set energy perf value (%d)\n", ret); - return ret; - } - cpudata->epp_cached = epp; + ret = wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value); + if (ret) { + pr_err("failed to set energy perf value (%d)\n", ret); + return ret; } + /* update both so that msr_update_perf() can effectively check */ + WRITE_ONCE(cpudata->epp_cached, epp); + WRITE_ONCE(cpudata->cppc_req_cached, value); + return ret; } -static int amd_pstate_set_energy_pref_index(struct amd_cpudata *cpudata, - int pref_index) +DEFINE_STATIC_CALL(amd_pstate_set_epp, msr_set_epp); + +static inline int amd_pstate_set_epp(struct amd_cpudata *cpudata, u32 epp) +{ + return static_call(amd_pstate_set_epp)(cpudata, epp); +} + +static int shmem_set_epp(struct amd_cpudata *cpudata, u32 epp) { - int epp = -EINVAL; int ret; + struct cppc_perf_ctrls perf_ctrls; + + if (epp == cpudata->epp_cached) + return 0; + + perf_ctrls.energy_perf = epp; + ret = cppc_set_epp_perf(cpudata->cpu, &perf_ctrls, 1); + if (ret) { + pr_debug("failed to set energy perf value (%d)\n", ret); + return ret; + } + WRITE_ONCE(cpudata->epp_cached, epp); + + return ret; +} + +static int amd_pstate_set_energy_pref_index(struct cpufreq_policy *policy, + int pref_index) +{ + struct amd_cpudata *cpudata = policy->driver_data; + int epp; if (!pref_index) epp = cpudata->epp_default; - - if (epp == -EINVAL) + else epp = epp_values[pref_index]; if (epp > 0 && cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) { @@ -301,9 +332,15 @@ static int amd_pstate_set_energy_pref_index(struct amd_cpudata *cpudata, return -EBUSY; } - ret = amd_pstate_set_epp(cpudata, epp); + if (trace_amd_pstate_epp_perf_enabled()) { + trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf, + epp, + FIELD_GET(AMD_CPPC_MIN_PERF_MASK, cpudata->cppc_req_cached), + FIELD_GET(AMD_CPPC_MAX_PERF_MASK, cpudata->cppc_req_cached), + policy->boost_enabled); + } - return ret; + return amd_pstate_set_epp(cpudata, epp); } static inline int msr_cppc_enable(bool enable) @@ -442,17 +479,23 @@ static inline int amd_pstate_init_perf(struct amd_cpudata *cpudata) return static_call(amd_pstate_init_perf)(cpudata); } -static void shmem_update_perf(struct amd_cpudata *cpudata, - u32 min_perf, u32 des_perf, - u32 max_perf, bool fast_switch) +static int shmem_update_perf(struct amd_cpudata *cpudata, u32 min_perf, + u32 des_perf, u32 max_perf, u32 epp, bool fast_switch) { struct cppc_perf_ctrls perf_ctrls; + if (cppc_state == AMD_PSTATE_ACTIVE) { + int ret = shmem_set_epp(cpudata, epp); + + if (ret) + return ret; + } + perf_ctrls.max_perf = max_perf; perf_ctrls.min_perf = min_perf; perf_ctrls.desired_perf = des_perf; - cppc_set_perf(cpudata->cpu, &perf_ctrls); + return cppc_set_perf(cpudata->cpu, &perf_ctrls); } static inline bool amd_pstate_sample(struct amd_cpudata *cpudata) @@ -493,14 +536,8 @@ static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf, { unsigned long max_freq; struct cpufreq_policy *policy = cpufreq_cpu_get(cpudata->cpu); - u64 prev = READ_ONCE(cpudata->cppc_req_cached); u32 nominal_perf = READ_ONCE(cpudata->nominal_perf); - u64 value = prev; - min_perf = clamp_t(unsigned long, min_perf, cpudata->min_limit_perf, - cpudata->max_limit_perf); - max_perf = clamp_t(unsigned long, max_perf, cpudata->min_limit_perf, - cpudata->max_limit_perf); des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf); max_freq = READ_ONCE(cpudata->max_limit_freq); @@ -511,34 +548,18 @@ static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf, des_perf = 0; } - value &= ~AMD_CPPC_MIN_PERF(~0L); - value |= AMD_CPPC_MIN_PERF(min_perf); - - value &= ~AMD_CPPC_DES_PERF(~0L); - value |= AMD_CPPC_DES_PERF(des_perf); - /* limit the max perf when core performance boost feature is disabled */ if (!cpudata->boost_supported) max_perf = min_t(unsigned long, nominal_perf, max_perf); - value &= ~AMD_CPPC_MAX_PERF(~0L); - value |= AMD_CPPC_MAX_PERF(max_perf); - if (trace_amd_pstate_perf_enabled() && amd_pstate_sample(cpudata)) { trace_amd_pstate_perf(min_perf, des_perf, max_perf, cpudata->freq, cpudata->cur.mperf, cpudata->cur.aperf, cpudata->cur.tsc, - cpudata->cpu, (value != prev), fast_switch); + cpudata->cpu, fast_switch); } - if (value == prev) - goto cpufreq_policy_put; + amd_pstate_update_perf(cpudata, min_perf, des_perf, max_perf, 0, fast_switch); - WRITE_ONCE(cpudata->cppc_req_cached, value); - - amd_pstate_update_perf(cpudata, min_perf, des_perf, - max_perf, fast_switch); - -cpufreq_policy_put: cpufreq_cpu_put(policy); } @@ -570,7 +591,7 @@ static int amd_pstate_verify(struct cpufreq_policy_data *policy_data) static int amd_pstate_update_min_max_limit(struct cpufreq_policy *policy) { - u32 max_limit_perf, min_limit_perf, lowest_perf, max_perf, max_freq; + u32 max_limit_perf, min_limit_perf, max_perf, max_freq; struct amd_cpudata *cpudata = policy->driver_data; max_perf = READ_ONCE(cpudata->highest_perf); @@ -578,12 +599,8 @@ static int amd_pstate_update_min_max_limit(struct cpufreq_policy *policy) max_limit_perf = div_u64(policy->max * max_perf, max_freq); min_limit_perf = div_u64(policy->min * max_perf, max_freq); - lowest_perf = READ_ONCE(cpudata->lowest_perf); - if (min_limit_perf < lowest_perf) - min_limit_perf = lowest_perf; - - if (max_limit_perf < min_limit_perf) - max_limit_perf = min_limit_perf; + if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) + min_limit_perf = min(cpudata->nominal_perf, max_limit_perf); WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf); WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf); @@ -704,8 +721,8 @@ static int amd_pstate_cpu_boost_update(struct cpufreq_policy *policy, bool on) if (on) policy->cpuinfo.max_freq = max_freq; - else if (policy->cpuinfo.max_freq > nominal_freq * 1000) - policy->cpuinfo.max_freq = nominal_freq * 1000; + else if (policy->cpuinfo.max_freq > nominal_freq) + policy->cpuinfo.max_freq = nominal_freq; policy->max = policy->cpuinfo.max_freq; @@ -727,12 +744,11 @@ static int amd_pstate_set_boost(struct cpufreq_policy *policy, int state) pr_err("Boost mode is not supported by this processor or SBIOS\n"); return -EOPNOTSUPP; } - mutex_lock(&amd_pstate_driver_lock); + guard(mutex)(&amd_pstate_driver_lock); + ret = amd_pstate_cpu_boost_update(policy, state); - WRITE_ONCE(cpudata->boost_state, !ret ? state : false); policy->boost_enabled = !ret ? state : false; refresh_frequency_limits(policy); - mutex_unlock(&amd_pstate_driver_lock); return ret; } @@ -752,9 +768,6 @@ static int amd_pstate_init_boost_support(struct amd_cpudata *cpudata) goto exit_err; } - /* at least one CPU supports CPB, even if others fail later on to set up */ - current_pstate_driver->boost_enabled = true; - ret = rdmsrl_on_cpu(cpudata->cpu, MSR_K7_HWCR, &boost_val); if (ret) { pr_err_once("failed to read initial CPU boost state!\n"); @@ -802,7 +815,7 @@ static void amd_pstate_init_prefcore(struct amd_cpudata *cpudata) * sched_set_itmt_support(true) has been called and it is valid to * update them at any time after it has been called. */ - sched_set_itmt_core_prio((int)READ_ONCE(cpudata->highest_perf), cpudata->cpu); + sched_set_itmt_core_prio((int)READ_ONCE(cpudata->prefcore_ranking), cpudata->cpu); schedule_work(&sched_prefcore_work); } @@ -823,7 +836,8 @@ static void amd_pstate_update_limits(unsigned int cpu) if (!amd_pstate_prefcore) return; - mutex_lock(&amd_pstate_driver_lock); + guard(mutex)(&amd_pstate_driver_lock); + ret = amd_get_highest_perf(cpu, &cur_high); if (ret) goto free_cpufreq_put; @@ -843,7 +857,6 @@ free_cpufreq_put: if (!highest_perf_changed) cpufreq_update_policy(cpu); - mutex_unlock(&amd_pstate_driver_lock); } /* @@ -895,9 +908,8 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata) { int ret; u32 min_freq, max_freq; - u32 nominal_perf, nominal_freq; + u32 highest_perf, nominal_perf, nominal_freq; u32 lowest_nonlinear_perf, lowest_nonlinear_freq; - u32 boost_ratio, lowest_nonlinear_ratio; struct cppc_perf_caps cppc_perf; ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); @@ -905,29 +917,25 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata) return ret; if (quirks && quirks->lowest_freq) - min_freq = quirks->lowest_freq * 1000; + min_freq = quirks->lowest_freq; else - min_freq = cppc_perf.lowest_freq * 1000; + min_freq = cppc_perf.lowest_freq; if (quirks && quirks->nominal_freq) - nominal_freq = quirks->nominal_freq ; + nominal_freq = quirks->nominal_freq; else nominal_freq = cppc_perf.nominal_freq; + highest_perf = READ_ONCE(cpudata->highest_perf); nominal_perf = READ_ONCE(cpudata->nominal_perf); - - boost_ratio = div_u64(cpudata->highest_perf << SCHED_CAPACITY_SHIFT, nominal_perf); - max_freq = (nominal_freq * boost_ratio >> SCHED_CAPACITY_SHIFT) * 1000; + max_freq = div_u64((u64)highest_perf * nominal_freq, nominal_perf); lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf); - lowest_nonlinear_ratio = div_u64(lowest_nonlinear_perf << SCHED_CAPACITY_SHIFT, - nominal_perf); - lowest_nonlinear_freq = (nominal_freq * lowest_nonlinear_ratio >> SCHED_CAPACITY_SHIFT) * 1000; - - WRITE_ONCE(cpudata->min_freq, min_freq); - WRITE_ONCE(cpudata->lowest_nonlinear_freq, lowest_nonlinear_freq); - WRITE_ONCE(cpudata->nominal_freq, nominal_freq); - WRITE_ONCE(cpudata->max_freq, max_freq); + lowest_nonlinear_freq = div_u64((u64)nominal_freq * lowest_nonlinear_perf, nominal_perf); + WRITE_ONCE(cpudata->min_freq, min_freq * 1000); + WRITE_ONCE(cpudata->lowest_nonlinear_freq, lowest_nonlinear_freq * 1000); + WRITE_ONCE(cpudata->nominal_freq, nominal_freq * 1000); + WRITE_ONCE(cpudata->max_freq, max_freq * 1000); /** * Below values need to be initialized correctly, otherwise driver will fail to load @@ -937,13 +945,13 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata) */ if (min_freq <= 0 || max_freq <= 0 || nominal_freq <= 0 || min_freq > max_freq) { pr_err("min_freq(%d) or max_freq(%d) or nominal_freq(%d) value is incorrect\n", - min_freq, max_freq, nominal_freq * 1000); + min_freq, max_freq, nominal_freq); return -EINVAL; } - if (lowest_nonlinear_freq <= min_freq || lowest_nonlinear_freq > nominal_freq * 1000) { + if (lowest_nonlinear_freq <= min_freq || lowest_nonlinear_freq > nominal_freq) { pr_err("lowest_nonlinear_freq(%d) value is out of range [min_freq(%d), nominal_freq(%d)]\n", - lowest_nonlinear_freq, min_freq, nominal_freq * 1000); + lowest_nonlinear_freq, min_freq, nominal_freq); return -EINVAL; } @@ -1160,7 +1168,6 @@ static ssize_t show_energy_performance_available_preferences( static ssize_t store_energy_performance_preference( struct cpufreq_policy *policy, const char *buf, size_t count) { - struct amd_cpudata *cpudata = policy->driver_data; char str_preference[21]; ssize_t ret; @@ -1172,11 +1179,11 @@ static ssize_t store_energy_performance_preference( if (ret < 0) return -EINVAL; - mutex_lock(&amd_pstate_limits_lock); - ret = amd_pstate_set_energy_pref_index(cpudata, ret); - mutex_unlock(&amd_pstate_limits_lock); + guard(mutex)(&amd_pstate_limits_lock); + + ret = amd_pstate_set_energy_pref_index(policy, ret); - return ret ?: count; + return ret ? ret : count; } static ssize_t show_energy_performance_preference( @@ -1185,9 +1192,22 @@ static ssize_t show_energy_performance_preference( struct amd_cpudata *cpudata = policy->driver_data; int preference; - preference = amd_pstate_get_energy_pref_index(cpudata); - if (preference < 0) - return preference; + switch (cpudata->epp_cached) { + case AMD_CPPC_EPP_PERFORMANCE: + preference = EPP_INDEX_PERFORMANCE; + break; + case AMD_CPPC_EPP_BALANCE_PERFORMANCE: + preference = EPP_INDEX_BALANCE_PERFORMANCE; + break; + case AMD_CPPC_EPP_BALANCE_POWERSAVE: + preference = EPP_INDEX_BALANCE_POWERSAVE; + break; + case AMD_CPPC_EPP_POWERSAVE: + preference = EPP_INDEX_POWERSAVE; + break; + default: + return -EINVAL; + } return sysfs_emit(buf, "%s\n", energy_perf_strings[preference]); } @@ -1236,6 +1256,9 @@ static int amd_pstate_register_driver(int mode) return ret; } + /* at least one CPU supports CPB */ + current_pstate_driver->boost_enabled = cpu_feature_enabled(X86_FEATURE_CPB); + ret = cpufreq_register_driver(current_pstate_driver); if (ret) { amd_pstate_driver_cleanup(); @@ -1340,13 +1363,10 @@ EXPORT_SYMBOL_GPL(amd_pstate_update_status); static ssize_t status_show(struct device *dev, struct device_attribute *attr, char *buf) { - ssize_t ret; - mutex_lock(&amd_pstate_driver_lock); - ret = amd_pstate_show_status(buf); - mutex_unlock(&amd_pstate_driver_lock); + guard(mutex)(&amd_pstate_driver_lock); - return ret; + return amd_pstate_show_status(buf); } static ssize_t status_store(struct device *a, struct device_attribute *b, @@ -1355,9 +1375,8 @@ static ssize_t status_store(struct device *a, struct device_attribute *b, char *p = memchr(buf, '\n', count); int ret; - mutex_lock(&amd_pstate_driver_lock); + guard(mutex)(&amd_pstate_driver_lock); ret = amd_pstate_update_status(buf, p ? p - buf : count); - mutex_unlock(&amd_pstate_driver_lock); return ret < 0 ? ret : count; } @@ -1451,7 +1470,6 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) return -ENOMEM; cpudata->cpu = policy->cpu; - cpudata->epp_policy = 0; ret = amd_pstate_init_perf(cpudata); if (ret) @@ -1477,8 +1495,6 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) policy->driver_data = cpudata; - cpudata->epp_cached = cpudata->epp_default = amd_pstate_get_epp(cpudata, 0); - policy->min = policy->cpuinfo.min_freq; policy->max = policy->cpuinfo.max_freq; @@ -1489,10 +1505,13 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) * the default cpufreq governor is neither powersave nor performance. */ if (amd_pstate_acpi_pm_profile_server() || - amd_pstate_acpi_pm_profile_undefined()) + amd_pstate_acpi_pm_profile_undefined()) { policy->policy = CPUFREQ_POLICY_PERFORMANCE; - else + cpudata->epp_default = amd_pstate_get_epp(cpudata); + } else { policy->policy = CPUFREQ_POLICY_POWERSAVE; + cpudata->epp_default = AMD_CPPC_EPP_BALANCE_PERFORMANCE; + } if (cpu_feature_enabled(X86_FEATURE_CPPC)) { ret = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, &value); @@ -1505,6 +1524,9 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) return ret; WRITE_ONCE(cpudata->cppc_cap1_cached, value); } + ret = amd_pstate_set_epp(cpudata, cpudata->epp_default); + if (ret) + return ret; current_pstate_driver->adjust_perf = NULL; @@ -1530,51 +1552,24 @@ static void amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy) static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy) { struct amd_cpudata *cpudata = policy->driver_data; - u32 max_perf, min_perf; - u64 value; - s16 epp; + u32 epp; - max_perf = READ_ONCE(cpudata->highest_perf); - min_perf = READ_ONCE(cpudata->lowest_perf); amd_pstate_update_min_max_limit(policy); - max_perf = clamp_t(unsigned long, max_perf, cpudata->min_limit_perf, - cpudata->max_limit_perf); - min_perf = clamp_t(unsigned long, min_perf, cpudata->min_limit_perf, - cpudata->max_limit_perf); - value = READ_ONCE(cpudata->cppc_req_cached); - if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) - min_perf = min(cpudata->nominal_perf, max_perf); - - /* Initial min/max values for CPPC Performance Controls Register */ - value &= ~AMD_CPPC_MIN_PERF(~0L); - value |= AMD_CPPC_MIN_PERF(min_perf); - - value &= ~AMD_CPPC_MAX_PERF(~0L); - value |= AMD_CPPC_MAX_PERF(max_perf); - - /* CPPC EPP feature require to set zero to the desire perf bit */ - value &= ~AMD_CPPC_DES_PERF(~0L); - value |= AMD_CPPC_DES_PERF(0); - - cpudata->epp_policy = cpudata->policy; + epp = 0; + else + epp = READ_ONCE(cpudata->epp_cached); - /* Get BIOS pre-defined epp value */ - epp = amd_pstate_get_epp(cpudata, value); - if (epp < 0) { - /** - * This return value can only be negative for shared_memory - * systems where EPP register read/write not supported. - */ - return epp; + if (trace_amd_pstate_epp_perf_enabled()) { + trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf, epp, + cpudata->min_limit_perf, + cpudata->max_limit_perf, + policy->boost_enabled); } - if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) - epp = 0; - - WRITE_ONCE(cpudata->cppc_req_cached, value); - return amd_pstate_set_epp(cpudata, epp); + return amd_pstate_update_perf(cpudata, cpudata->min_limit_perf, 0U, + cpudata->max_limit_perf, epp, false); } static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy) @@ -1603,87 +1598,63 @@ static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy) return 0; } -static void amd_pstate_epp_reenable(struct amd_cpudata *cpudata) +static int amd_pstate_epp_reenable(struct cpufreq_policy *policy) { - struct cppc_perf_ctrls perf_ctrls; - u64 value, max_perf; + struct amd_cpudata *cpudata = policy->driver_data; + u64 max_perf; int ret; ret = amd_pstate_cppc_enable(true); if (ret) pr_err("failed to enable amd pstate during resume, return %d\n", ret); - value = READ_ONCE(cpudata->cppc_req_cached); max_perf = READ_ONCE(cpudata->highest_perf); - if (cpu_feature_enabled(X86_FEATURE_CPPC)) { - wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value); - } else { - perf_ctrls.max_perf = max_perf; - cppc_set_perf(cpudata->cpu, &perf_ctrls); - perf_ctrls.energy_perf = AMD_CPPC_ENERGY_PERF_PREF(cpudata->epp_cached); - cppc_set_epp_perf(cpudata->cpu, &perf_ctrls, 1); + if (trace_amd_pstate_epp_perf_enabled()) { + trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf, + cpudata->epp_cached, + FIELD_GET(AMD_CPPC_MIN_PERF_MASK, cpudata->cppc_req_cached), + max_perf, policy->boost_enabled); } + + return amd_pstate_update_perf(cpudata, 0, 0, max_perf, cpudata->epp_cached, false); } static int amd_pstate_epp_cpu_online(struct cpufreq_policy *policy) { struct amd_cpudata *cpudata = policy->driver_data; + int ret; pr_debug("AMD CPU Core %d going online\n", cpudata->cpu); - if (cppc_state == AMD_PSTATE_ACTIVE) { - amd_pstate_epp_reenable(cpudata); - cpudata->suspended = false; - } + ret = amd_pstate_epp_reenable(policy); + if (ret) + return ret; + cpudata->suspended = false; return 0; } -static void amd_pstate_epp_offline(struct cpufreq_policy *policy) -{ - struct amd_cpudata *cpudata = policy->driver_data; - struct cppc_perf_ctrls perf_ctrls; - int min_perf; - u64 value; - - min_perf = READ_ONCE(cpudata->lowest_perf); - value = READ_ONCE(cpudata->cppc_req_cached); - - mutex_lock(&amd_pstate_limits_lock); - if (cpu_feature_enabled(X86_FEATURE_CPPC)) { - cpudata->epp_policy = CPUFREQ_POLICY_UNKNOWN; - - /* Set max perf same as min perf */ - value &= ~AMD_CPPC_MAX_PERF(~0L); - value |= AMD_CPPC_MAX_PERF(min_perf); - value &= ~AMD_CPPC_MIN_PERF(~0L); - value |= AMD_CPPC_MIN_PERF(min_perf); - wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value); - } else { - perf_ctrls.desired_perf = 0; - perf_ctrls.min_perf = min_perf; - perf_ctrls.max_perf = min_perf; - cppc_set_perf(cpudata->cpu, &perf_ctrls); - perf_ctrls.energy_perf = AMD_CPPC_ENERGY_PERF_PREF(HWP_EPP_BALANCE_POWERSAVE); - cppc_set_epp_perf(cpudata->cpu, &perf_ctrls, 1); - } - mutex_unlock(&amd_pstate_limits_lock); -} - static int amd_pstate_epp_cpu_offline(struct cpufreq_policy *policy) { struct amd_cpudata *cpudata = policy->driver_data; - - pr_debug("AMD CPU Core %d going offline\n", cpudata->cpu); + int min_perf; if (cpudata->suspended) return 0; - if (cppc_state == AMD_PSTATE_ACTIVE) - amd_pstate_epp_offline(policy); + min_perf = READ_ONCE(cpudata->lowest_perf); - return 0; + guard(mutex)(&amd_pstate_limits_lock); + + if (trace_amd_pstate_epp_perf_enabled()) { + trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf, + AMD_CPPC_EPP_BALANCE_POWERSAVE, + min_perf, min_perf, policy->boost_enabled); + } + + return amd_pstate_update_perf(cpudata, min_perf, 0, min_perf, + AMD_CPPC_EPP_BALANCE_POWERSAVE, false); } static int amd_pstate_epp_suspend(struct cpufreq_policy *policy) @@ -1711,12 +1682,10 @@ static int amd_pstate_epp_resume(struct cpufreq_policy *policy) struct amd_cpudata *cpudata = policy->driver_data; if (cpudata->suspended) { - mutex_lock(&amd_pstate_limits_lock); + guard(mutex)(&amd_pstate_limits_lock); /* enable amd pstate from suspend state*/ - amd_pstate_epp_reenable(cpudata); - - mutex_unlock(&amd_pstate_limits_lock); + amd_pstate_epp_reenable(policy); cpudata->suspended = false; } @@ -1869,6 +1838,8 @@ static int __init amd_pstate_init(void) static_call_update(amd_pstate_cppc_enable, shmem_cppc_enable); static_call_update(amd_pstate_init_perf, shmem_init_perf); static_call_update(amd_pstate_update_perf, shmem_update_perf); + static_call_update(amd_pstate_get_epp, shmem_get_epp); + static_call_update(amd_pstate_set_epp, shmem_set_epp); } if (amd_pstate_prefcore) { diff --git a/drivers/cpufreq/amd-pstate.h b/drivers/cpufreq/amd-pstate.h index cd573bc6b6db..9747e3be6cee 100644 --- a/drivers/cpufreq/amd-pstate.h +++ b/drivers/cpufreq/amd-pstate.h @@ -57,7 +57,6 @@ struct amd_aperf_mperf { * @hw_prefcore: check whether HW supports preferred core featue. * Only when hw_prefcore and early prefcore param are true, * AMD P-State driver supports preferred core featue. - * @epp_policy: Last saved policy used to set energy-performance preference * @epp_cached: Cached CPPC energy-performance preference value * @policy: Cpufreq policy value * @cppc_cap1_cached Cached MSR_AMD_CPPC_CAP1 register value @@ -94,13 +93,11 @@ struct amd_cpudata { bool hw_prefcore; /* EPP feature related attributes*/ - s16 epp_policy; s16 epp_cached; u32 policy; u64 cppc_cap1_cached; bool suspended; s16 epp_default; - bool boost_state; }; /* diff --git a/drivers/cpufreq/apple-soc-cpufreq.c b/drivers/cpufreq/apple-soc-cpufreq.c index 4dcacab9b4bf..269b18c62d04 100644 --- a/drivers/cpufreq/apple-soc-cpufreq.c +++ b/drivers/cpufreq/apple-soc-cpufreq.c @@ -22,11 +22,14 @@ #include <linux/pm_opp.h> #include <linux/slab.h> -#define APPLE_DVFS_CMD 0x20 -#define APPLE_DVFS_CMD_BUSY BIT(31) -#define APPLE_DVFS_CMD_SET BIT(25) -#define APPLE_DVFS_CMD_PS2 GENMASK(16, 12) -#define APPLE_DVFS_CMD_PS1 GENMASK(4, 0) +#define APPLE_DVFS_CMD 0x20 +#define APPLE_DVFS_CMD_BUSY BIT(31) +#define APPLE_DVFS_CMD_SET BIT(25) +#define APPLE_DVFS_CMD_PS1_S5L8960X GENMASK(24, 22) +#define APPLE_DVFS_CMD_PS1_S5L8960X_SHIFT 22 +#define APPLE_DVFS_CMD_PS2 GENMASK(15, 12) +#define APPLE_DVFS_CMD_PS1 GENMASK(4, 0) +#define APPLE_DVFS_CMD_PS1_SHIFT 0 /* Same timebase as CPU counter (24MHz) */ #define APPLE_DVFS_LAST_CHG_TIME 0x38 @@ -35,6 +38,9 @@ * Apple ran out of bits and had to shift this in T8112... */ #define APPLE_DVFS_STATUS 0x50 +#define APPLE_DVFS_STATUS_CUR_PS_S5L8960X GENMASK(5, 3) +#define APPLE_DVFS_STATUS_CUR_PS_SHIFT_S5L8960X 3 +#define APPLE_DVFS_STATUS_TGT_PS_S5L8960X GENMASK(2, 0) #define APPLE_DVFS_STATUS_CUR_PS_T8103 GENMASK(7, 4) #define APPLE_DVFS_STATUS_CUR_PS_SHIFT_T8103 4 #define APPLE_DVFS_STATUS_TGT_PS_T8103 GENMASK(3, 0) @@ -52,12 +58,15 @@ #define APPLE_DVFS_PLL_FACTOR_MULT GENMASK(31, 16) #define APPLE_DVFS_PLL_FACTOR_DIV GENMASK(15, 0) -#define APPLE_DVFS_TRANSITION_TIMEOUT 100 +#define APPLE_DVFS_TRANSITION_TIMEOUT 400 struct apple_soc_cpufreq_info { + bool has_ps2; u64 max_pstate; u64 cur_pstate_mask; u64 cur_pstate_shift; + u64 ps1_mask; + u64 ps1_shift; }; struct apple_cpu_priv { @@ -68,25 +77,47 @@ struct apple_cpu_priv { static struct cpufreq_driver apple_soc_cpufreq_driver; +static const struct apple_soc_cpufreq_info soc_s5l8960x_info = { + .has_ps2 = false, + .max_pstate = 7, + .cur_pstate_mask = APPLE_DVFS_STATUS_CUR_PS_S5L8960X, + .cur_pstate_shift = APPLE_DVFS_STATUS_CUR_PS_SHIFT_S5L8960X, + .ps1_mask = APPLE_DVFS_CMD_PS1_S5L8960X, + .ps1_shift = APPLE_DVFS_CMD_PS1_S5L8960X_SHIFT, +}; + static const struct apple_soc_cpufreq_info soc_t8103_info = { + .has_ps2 = true, .max_pstate = 15, .cur_pstate_mask = APPLE_DVFS_STATUS_CUR_PS_T8103, .cur_pstate_shift = APPLE_DVFS_STATUS_CUR_PS_SHIFT_T8103, + .ps1_mask = APPLE_DVFS_CMD_PS1, + .ps1_shift = APPLE_DVFS_CMD_PS1_SHIFT, }; static const struct apple_soc_cpufreq_info soc_t8112_info = { + .has_ps2 = false, .max_pstate = 31, .cur_pstate_mask = APPLE_DVFS_STATUS_CUR_PS_T8112, .cur_pstate_shift = APPLE_DVFS_STATUS_CUR_PS_SHIFT_T8112, + .ps1_mask = APPLE_DVFS_CMD_PS1, + .ps1_shift = APPLE_DVFS_CMD_PS1_SHIFT, }; static const struct apple_soc_cpufreq_info soc_default_info = { + .has_ps2 = false, .max_pstate = 15, .cur_pstate_mask = 0, /* fallback */ + .ps1_mask = APPLE_DVFS_CMD_PS1, + .ps1_shift = APPLE_DVFS_CMD_PS1_SHIFT, }; static const struct of_device_id apple_soc_cpufreq_of_match[] __maybe_unused = { { + .compatible = "apple,s5l8960x-cluster-cpufreq", + .data = &soc_s5l8960x_info, + }, + { .compatible = "apple,t8103-cluster-cpufreq", .data = &soc_t8103_info, }, @@ -109,7 +140,7 @@ static unsigned int apple_soc_cpufreq_get_rate(unsigned int cpu) unsigned int pstate; if (priv->info->cur_pstate_mask) { - u64 reg = readq_relaxed(priv->reg_base + APPLE_DVFS_STATUS); + u32 reg = readl_relaxed(priv->reg_base + APPLE_DVFS_STATUS); pstate = (reg & priv->info->cur_pstate_mask) >> priv->info->cur_pstate_shift; } else { @@ -148,9 +179,12 @@ static int apple_soc_cpufreq_set_target(struct cpufreq_policy *policy, return -EIO; } - reg &= ~(APPLE_DVFS_CMD_PS1 | APPLE_DVFS_CMD_PS2); - reg |= FIELD_PREP(APPLE_DVFS_CMD_PS1, pstate); - reg |= FIELD_PREP(APPLE_DVFS_CMD_PS2, pstate); + reg &= ~priv->info->ps1_mask; + reg |= pstate << priv->info->ps1_shift; + if (priv->info->has_ps2) { + reg &= ~APPLE_DVFS_CMD_PS2; + reg |= FIELD_PREP(APPLE_DVFS_CMD_PS2, pstate); + } reg |= APPLE_DVFS_CMD_SET; writeq_relaxed(reg, priv->reg_base + APPLE_DVFS_CMD); @@ -275,7 +309,7 @@ static int apple_soc_cpufreq_init(struct cpufreq_policy *policy) transition_latency = dev_pm_opp_get_max_transition_latency(cpu_dev); if (!transition_latency) - transition_latency = CPUFREQ_ETERNAL; + transition_latency = APPLE_DVFS_TRANSITION_TIMEOUT * NSEC_PER_USEC; policy->cpuinfo.transition_latency = transition_latency; policy->dvfs_possible_from_any_cpu = true; diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c index 2a3e8bd317c9..2aa00769cf09 100644 --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -103,6 +103,8 @@ static const struct of_device_id allowlist[] __initconst = { * platforms using "operating-points-v2" property. */ static const struct of_device_id blocklist[] __initconst = { + { .compatible = "airoha,en7581", }, + { .compatible = "allwinner,sun50i-a100" }, { .compatible = "allwinner,sun50i-h6", }, { .compatible = "allwinner,sun50i-h616", }, @@ -235,5 +237,3 @@ create_pdev: sizeof(struct cpufreq_dt_platform_data))); } core_initcall(cpufreq_dt_platdev_init); -MODULE_DESCRIPTION("Generic DT based cpufreq platdev driver"); -MODULE_LICENSE("GPL"); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 1a4cae54a01b..1076e37a18ad 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -25,6 +25,7 @@ #include <linux/mutex.h> #include <linux/pm_qos.h> #include <linux/slab.h> +#include <linux/string_choices.h> #include <linux/suspend.h> #include <linux/syscore_ops.h> #include <linux/tick.h> @@ -602,12 +603,12 @@ static ssize_t store_boost(struct kobject *kobj, struct kobj_attribute *attr, if (cpufreq_boost_trigger_state(enable)) { pr_err("%s: Cannot %s BOOST!\n", - __func__, enable ? "enable" : "disable"); + __func__, str_enable_disable(enable)); return -EINVAL; } pr_debug("%s: cpufreq BOOST %s\n", - __func__, enable ? "enabled" : "disabled"); + __func__, str_enabled_disabled(enable)); return count; } @@ -1538,7 +1539,7 @@ static int cpufreq_online(unsigned int cpu) /* * Register with the energy model before - * sugov_eas_rebuild_sd() is called, which will result + * em_rebuild_sched_domains() is called, which will result * in rebuilding of the sched domains, which should only be done * once the energy model is properly initialized for the policy * first. @@ -2812,7 +2813,7 @@ err_reset_state: write_unlock_irqrestore(&cpufreq_driver_lock, flags); pr_err("%s: Cannot %s BOOST\n", - __func__, state ? "enable" : "disable"); + __func__, str_enable_disable(state)); return ret; } diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index b8e2396a708a..9c4cc01fd51a 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -28,6 +28,7 @@ #include <linux/pm_qos.h> #include <linux/bitfield.h> #include <trace/events/power.h> +#include <linux/units.h> #include <asm/cpu.h> #include <asm/div64.h> @@ -302,11 +303,11 @@ static bool hwp_is_hybrid; static struct cpufreq_driver *intel_pstate_driver __read_mostly; -#define HYBRID_SCALING_FACTOR 78741 +#define HYBRID_SCALING_FACTOR_ADL 78741 #define HYBRID_SCALING_FACTOR_MTL 80000 #define HYBRID_SCALING_FACTOR_LNL 86957 -static int hybrid_scaling_factor = HYBRID_SCALING_FACTOR; +static int hybrid_scaling_factor; static inline int core_get_scaling(void) { @@ -414,18 +415,15 @@ static int intel_pstate_get_cppc_guaranteed(int cpu) static int intel_pstate_cppc_get_scaling(int cpu) { struct cppc_perf_caps cppc_perf; - int ret; - - ret = cppc_get_perf_caps(cpu, &cppc_perf); /* - * If the nominal frequency and the nominal performance are not - * zero and the ratio between them is not 100, return the hybrid - * scaling factor. + * Compute the perf-to-frequency scaling factor for the given CPU if + * possible, unless it would be 0. */ - if (!ret && cppc_perf.nominal_perf && cppc_perf.nominal_freq && - cppc_perf.nominal_perf * 100 != cppc_perf.nominal_freq) - return hybrid_scaling_factor; + if (!cppc_get_perf_caps(cpu, &cppc_perf) && + cppc_perf.nominal_perf && cppc_perf.nominal_freq) + return div_u64(cppc_perf.nominal_freq * KHZ_PER_MHZ, + cppc_perf.nominal_perf); return core_get_scaling(); } @@ -2211,24 +2209,30 @@ static void hybrid_get_type(void *data) static int hwp_get_cpu_scaling(int cpu) { - u8 cpu_type = 0; + if (hybrid_scaling_factor) { + u8 cpu_type = 0; - smp_call_function_single(cpu, hybrid_get_type, &cpu_type, 1); - /* P-cores have a smaller perf level-to-freqency scaling factor. */ - if (cpu_type == 0x40) - return hybrid_scaling_factor; + smp_call_function_single(cpu, hybrid_get_type, &cpu_type, 1); - /* Use default core scaling for E-cores */ - if (cpu_type == 0x20) + /* + * Return the hybrid scaling factor for P-cores and use the + * default core scaling for E-cores. + */ + if (cpu_type == 0x40) + return hybrid_scaling_factor; + + if (cpu_type == 0x20) + return core_get_scaling(); + } + + /* Use core scaling on non-hybrid systems. */ + if (!cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) return core_get_scaling(); /* - * If reached here, this system is either non-hybrid (like Tiger - * Lake) or hybrid-capable (like Alder Lake or Raptor Lake) with - * no E cores (in which case CPUID for hybrid support is 0). - * - * The CPPC nominal_frequency field is 0 for non-hybrid systems, - * so the default core scaling will be used for them. + * The system is hybrid, but the hybrid scaling factor is not known or + * the CPU type is not one of the above, so use CPPC to compute the + * scaling factor for this CPU. */ return intel_pstate_cppc_get_scaling(cpu); } @@ -2709,7 +2713,7 @@ static int intel_pstate_init_cpu(unsigned int cpunum) } cpu->epp_powersave = -EINVAL; - cpu->epp_policy = 0; + cpu->epp_policy = CPUFREQ_POLICY_UNKNOWN; intel_pstate_get_cpu_pstates(cpu); @@ -3665,8 +3669,12 @@ static const struct x86_cpu_id intel_epp_default[] = { }; static const struct x86_cpu_id intel_hybrid_scaling_factor[] = { + X86_MATCH_VFM(INTEL_ALDERLAKE, HYBRID_SCALING_FACTOR_ADL), + X86_MATCH_VFM(INTEL_ALDERLAKE_L, HYBRID_SCALING_FACTOR_ADL), + X86_MATCH_VFM(INTEL_RAPTORLAKE, HYBRID_SCALING_FACTOR_ADL), + X86_MATCH_VFM(INTEL_RAPTORLAKE_P, HYBRID_SCALING_FACTOR_ADL), + X86_MATCH_VFM(INTEL_RAPTORLAKE_S, HYBRID_SCALING_FACTOR_ADL), X86_MATCH_VFM(INTEL_METEORLAKE_L, HYBRID_SCALING_FACTOR_MTL), - X86_MATCH_VFM(INTEL_ARROWLAKE, HYBRID_SCALING_FACTOR_MTL), X86_MATCH_VFM(INTEL_LUNARLAKE_M, HYBRID_SCALING_FACTOR_LNL), {} }; diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c index 8de759247771..ae79d909943b 100644 --- a/drivers/cpufreq/powernv-cpufreq.c +++ b/drivers/cpufreq/powernv-cpufreq.c @@ -18,6 +18,7 @@ #include <linux/of.h> #include <linux/reboot.h> #include <linux/slab.h> +#include <linux/string_choices.h> #include <linux/cpu.h> #include <linux/hashtable.h> #include <trace/events/power.h> @@ -281,7 +282,7 @@ next: pr_info("cpufreq pstate min 0x%x nominal 0x%x max 0x%x\n", pstate_min, pstate_nominal, pstate_max); pr_info("Workload Optimized Frequency is %s in the platform\n", - (powernv_pstate_info.wof_enabled) ? "enabled" : "disabled"); + str_enabled_disabled(powernv_pstate_info.wof_enabled)); pstate_ids = of_get_property(power_mgt, "ibm,pstate-ids", &len_ids); if (!pstate_ids) { diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c index 98129565acb8..b2e7e89feaac 100644 --- a/drivers/cpufreq/qcom-cpufreq-hw.c +++ b/drivers/cpufreq/qcom-cpufreq-hw.c @@ -143,14 +143,12 @@ static unsigned long qcom_lmh_get_throttle_freq(struct qcom_cpufreq_data *data) } /* Get the frequency requested by the cpufreq core for the CPU */ -static unsigned int qcom_cpufreq_get_freq(unsigned int cpu) +static unsigned int qcom_cpufreq_get_freq(struct cpufreq_policy *policy) { struct qcom_cpufreq_data *data; const struct qcom_cpufreq_soc_data *soc_data; - struct cpufreq_policy *policy; unsigned int index; - policy = cpufreq_cpu_get_raw(cpu); if (!policy) return 0; @@ -163,12 +161,10 @@ static unsigned int qcom_cpufreq_get_freq(unsigned int cpu) return policy->freq_table[index].frequency; } -static unsigned int qcom_cpufreq_hw_get(unsigned int cpu) +static unsigned int __qcom_cpufreq_hw_get(struct cpufreq_policy *policy) { struct qcom_cpufreq_data *data; - struct cpufreq_policy *policy; - policy = cpufreq_cpu_get_raw(cpu); if (!policy) return 0; @@ -177,7 +173,12 @@ static unsigned int qcom_cpufreq_hw_get(unsigned int cpu) if (data->throttle_irq >= 0) return qcom_lmh_get_throttle_freq(data) / HZ_PER_KHZ; - return qcom_cpufreq_get_freq(cpu); + return qcom_cpufreq_get_freq(policy); +} + +static unsigned int qcom_cpufreq_hw_get(unsigned int cpu) +{ + return __qcom_cpufreq_hw_get(cpufreq_cpu_get_raw(cpu)); } static unsigned int qcom_cpufreq_hw_fast_switch(struct cpufreq_policy *policy, @@ -363,7 +364,7 @@ static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data) * If h/w throttled frequency is higher than what cpufreq has requested * for, then stop polling and switch back to interrupt mechanism. */ - if (throttled_freq >= qcom_cpufreq_get_freq(cpu)) + if (throttled_freq >= qcom_cpufreq_get_freq(cpufreq_cpu_get_raw(cpu))) enable_irq(data->throttle_irq); else mod_delayed_work(system_highpri_wq, &data->throttle_work, @@ -441,7 +442,6 @@ static int qcom_cpufreq_hw_lmh_init(struct cpufreq_policy *policy, int index) return data->throttle_irq; data->cancel_throttle = false; - data->policy = policy; mutex_init(&data->throttle_lock); INIT_DEFERRABLE_WORK(&data->throttle_work, qcom_lmh_dcvs_poll); @@ -552,6 +552,7 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy) policy->driver_data = data; policy->dvfs_possible_from_any_cpu = true; + data->policy = policy; ret = qcom_cpufreq_hw_read_lut(cpu_dev, policy); if (ret) { @@ -622,11 +623,24 @@ static unsigned long qcom_cpufreq_hw_recalc_rate(struct clk_hw *hw, unsigned lon { struct qcom_cpufreq_data *data = container_of(hw, struct qcom_cpufreq_data, cpu_clk); - return qcom_lmh_get_throttle_freq(data); + return __qcom_cpufreq_hw_get(data->policy) * HZ_PER_KHZ; +} + +/* + * Since we cannot determine the closest rate of the target rate, let's just + * return the actual rate at which the clock is running at. This is needed to + * make clk_set_rate() API work properly. + */ +static int qcom_cpufreq_hw_determine_rate(struct clk_hw *hw, struct clk_rate_request *req) +{ + req->rate = qcom_cpufreq_hw_recalc_rate(hw, 0); + + return 0; } static const struct clk_ops qcom_cpufreq_hw_clk_ops = { .recalc_rate = qcom_cpufreq_hw_recalc_rate, + .determine_rate = qcom_cpufreq_hw_determine_rate, }; static int qcom_cpufreq_hw_driver_probe(struct platform_device *pdev) diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c index 07d6f9a9b7c8..b8fe758aeb01 100644 --- a/drivers/cpufreq/scmi-cpufreq.c +++ b/drivers/cpufreq/scmi-cpufreq.c @@ -16,6 +16,7 @@ #include <linux/export.h> #include <linux/module.h> #include <linux/pm_opp.h> +#include <linux/pm_qos.h> #include <linux/slab.h> #include <linux/scmi_protocol.h> #include <linux/types.h> @@ -26,6 +27,8 @@ struct scmi_data { int nr_opp; struct device *cpu_dev; cpumask_var_t opp_shared_cpus; + struct notifier_block limit_notify_nb; + struct freq_qos_request limits_freq_req; }; static struct scmi_protocol_handle *ph; @@ -174,6 +177,22 @@ static struct freq_attr *scmi_cpufreq_hw_attr[] = { NULL, }; +static int scmi_limit_notify_cb(struct notifier_block *nb, unsigned long event, void *data) +{ + struct scmi_data *priv = container_of(nb, struct scmi_data, limit_notify_nb); + struct scmi_perf_limits_report *limit_notify = data; + unsigned int limit_freq_khz; + int ret; + + limit_freq_khz = limit_notify->range_max_freq / HZ_PER_KHZ; + + ret = freq_qos_update_request(&priv->limits_freq_req, limit_freq_khz); + if (ret < 0) + pr_warn("failed to update freq constraint: %d\n", ret); + + return NOTIFY_OK; +} + static int scmi_cpufreq_init(struct cpufreq_policy *policy) { int ret, nr_opp, domain; @@ -181,6 +200,7 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy) struct device *cpu_dev; struct scmi_data *priv; struct cpufreq_frequency_table *freq_table; + struct scmi_device *sdev = cpufreq_get_driver_data(); cpu_dev = get_cpu_device(policy->cpu); if (!cpu_dev) { @@ -294,6 +314,23 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy) } } + ret = freq_qos_add_request(&policy->constraints, &priv->limits_freq_req, FREQ_QOS_MAX, + FREQ_QOS_MAX_DEFAULT_VALUE); + if (ret < 0) { + dev_err(cpu_dev, "failed to add qos limits request: %d\n", ret); + goto out_free_table; + } + + priv->limit_notify_nb.notifier_call = scmi_limit_notify_cb; + ret = sdev->handle->notify_ops->event_notifier_register(sdev->handle, SCMI_PROTOCOL_PERF, + SCMI_EVENT_PERFORMANCE_LIMITS_CHANGED, + &priv->domain_id, + &priv->limit_notify_nb); + if (ret) + dev_warn(&sdev->dev, + "failed to register for limits change notifier for domain %d\n", + priv->domain_id); + return 0; out_free_table: @@ -313,7 +350,13 @@ out_free_priv: static void scmi_cpufreq_exit(struct cpufreq_policy *policy) { struct scmi_data *priv = policy->driver_data; + struct scmi_device *sdev = cpufreq_get_driver_data(); + sdev->handle->notify_ops->event_notifier_unregister(sdev->handle, SCMI_PROTOCOL_PERF, + SCMI_EVENT_PERFORMANCE_LIMITS_CHANGED, + &priv->domain_id, + &priv->limit_notify_nb); + freq_qos_remove_request(&priv->limits_freq_req); dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table); dev_pm_opp_remove_all_dynamic(priv->cpu_dev); free_cpumask_var(priv->opp_shared_cpus); @@ -372,6 +415,8 @@ static int scmi_cpufreq_probe(struct scmi_device *sdev) if (!handle) return -ENODEV; + scmi_cpufreq_driver.driver_data = sdev; + perf_ops = handle->devm_protocol_get(sdev, SCMI_PROTOCOL_PERF, &ph); if (IS_ERR(perf_ops)) return PTR_ERR(perf_ops); diff --git a/drivers/cpufreq/sparc-us2e-cpufreq.c b/drivers/cpufreq/sparc-us2e-cpufreq.c index 8a0cd5312a59..15899dd77c08 100644 --- a/drivers/cpufreq/sparc-us2e-cpufreq.c +++ b/drivers/cpufreq/sparc-us2e-cpufreq.c @@ -323,7 +323,7 @@ static int __init us2e_freq_init(void) impl = ((ver >> 32) & 0xffff); if (manuf == 0x17 && impl == 0x13) { - us2e_freq_table = kzalloc(NR_CPUS * sizeof(*us2e_freq_table), + us2e_freq_table = kcalloc(NR_CPUS, sizeof(*us2e_freq_table), GFP_KERNEL); if (!us2e_freq_table) return -ENOMEM; diff --git a/drivers/cpufreq/sparc-us3-cpufreq.c b/drivers/cpufreq/sparc-us3-cpufreq.c index b50f9d13e6d2..de50a2f3b124 100644 --- a/drivers/cpufreq/sparc-us3-cpufreq.c +++ b/drivers/cpufreq/sparc-us3-cpufreq.c @@ -171,7 +171,7 @@ static int __init us3_freq_init(void) impl == CHEETAH_PLUS_IMPL || impl == JAGUAR_IMPL || impl == PANTHER_IMPL)) { - us3_freq_table = kzalloc(NR_CPUS * sizeof(*us3_freq_table), + us3_freq_table = kcalloc(NR_CPUS, sizeof(*us3_freq_table), GFP_KERNEL); if (!us3_freq_table) return -ENOMEM; diff --git a/drivers/devfreq/devfreq-event.c b/drivers/devfreq/devfreq-event.c index 3ebac2496679..70219099c604 100644 --- a/drivers/devfreq/devfreq-event.c +++ b/drivers/devfreq/devfreq-event.c @@ -244,13 +244,9 @@ struct devfreq_event_dev *devfreq_event_get_edev_by_phandle(struct device *dev, edev = NULL; out: mutex_unlock(&devfreq_event_list_lock); - - if (!edev) { - of_node_put(node); - return ERR_PTR(-ENODEV); - } - of_node_put(node); + if (!edev) + return ERR_PTR(-ENODEV); return edev; } diff --git a/drivers/devfreq/exynos-bus.c b/drivers/devfreq/exynos-bus.c index 7d06c476d8e9..b9ea7ad2e51b 100644 --- a/drivers/devfreq/exynos-bus.c +++ b/drivers/devfreq/exynos-bus.c @@ -236,8 +236,7 @@ err_regulator: return ret; } -static int exynos_bus_parse_of(struct device_node *np, - struct exynos_bus *bus) +static int exynos_bus_parse_of(struct exynos_bus *bus) { struct device *dev = bus->dev; struct dev_pm_opp *opp; @@ -408,7 +407,7 @@ static int exynos_bus_probe(struct platform_device *pdev) } /* Parse the device-tree to get the resource information */ - ret = exynos_bus_parse_of(np, bus); + ret = exynos_bus_parse_of(bus); if (ret < 0) goto err_reg; diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 239ce0d046f3..118fe1d37c22 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -1652,6 +1652,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = { X86_MATCH_VFM(INTEL_ATOM_TREMONT_D, &idle_cpu_snr), X86_MATCH_VFM(INTEL_ATOM_CRESTMONT, &idle_cpu_grr), X86_MATCH_VFM(INTEL_ATOM_CRESTMONT_X, &idle_cpu_srf), + X86_MATCH_VFM(INTEL_ATOM_DARKMONT_X, &idle_cpu_srf), {} }; diff --git a/drivers/opp/core.c b/drivers/opp/core.c index be3291b53719..73e9a3b2f29b 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -1528,11 +1528,6 @@ err: return ERR_PTR(ret); } -void _get_opp_table_kref(struct opp_table *opp_table) -{ - kref_get(&opp_table->kref); -} - static struct opp_table *_update_opp_table_clk(struct device *dev, struct opp_table *opp_table, bool getclk) @@ -1693,6 +1688,17 @@ static void _opp_table_kref_release(struct kref *kref) kfree(opp_table); } +void _get_opp_table_kref(struct opp_table *opp_table) +{ + kref_get(&opp_table->kref); +} + +void dev_pm_opp_get_opp_table_ref(struct opp_table *opp_table) +{ + _get_opp_table_kref(opp_table); +} +EXPORT_SYMBOL_GPL(dev_pm_opp_get_opp_table_ref); + void dev_pm_opp_put_opp_table(struct opp_table *opp_table) { kref_put_mutex(&opp_table->kref, _opp_table_kref_release, @@ -1727,6 +1733,7 @@ void dev_pm_opp_get(struct dev_pm_opp *opp) { kref_get(&opp->kref); } +EXPORT_SYMBOL_GPL(dev_pm_opp_get); void dev_pm_opp_put(struct dev_pm_opp *opp) { diff --git a/drivers/opp/of.c b/drivers/opp/of.c index fd5ed2858258..a24f76f5fd01 100644 --- a/drivers/opp/of.c +++ b/drivers/opp/of.c @@ -926,7 +926,7 @@ static struct dev_pm_opp *_opp_add_static_v2(struct opp_table *opp_table, ret = _of_opp_alloc_required_opps(opp_table, new_opp); if (ret) - goto free_opp; + goto put_node; if (!of_property_read_u32(np, "clock-latency-ns", &val)) new_opp->clock_latency_ns = val; @@ -976,6 +976,8 @@ static struct dev_pm_opp *_opp_add_static_v2(struct opp_table *opp_table, free_required_opps: _of_opp_free_required_opps(opp_table, new_opp); +put_node: + of_node_put(np); free_opp: _opp_free(new_opp); diff --git a/drivers/opp/opp.h b/drivers/opp/opp.h index 430651e7424a..5c7c81190e41 100644 --- a/drivers/opp/opp.h +++ b/drivers/opp/opp.h @@ -250,7 +250,6 @@ struct opp_table { }; /* Routines internal to opp core */ -void dev_pm_opp_get(struct dev_pm_opp *opp); bool _opp_remove_all_static(struct opp_table *opp_table); void _get_opp_table_kref(struct opp_table *opp_table); int _get_opp_count(struct opp_table *opp_table); diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 752e0b297582..78318d49276d 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -179,6 +179,7 @@ int em_dev_compute_costs(struct device *dev, struct em_perf_state *table, int em_dev_update_chip_binning(struct device *dev); int em_update_performance_limits(struct em_perf_domain *pd, unsigned long freq_min_khz, unsigned long freq_max_khz); +void em_rebuild_sched_domains(void); /** * em_pd_get_efficient_state() - Get an efficient performance state from the EM @@ -404,6 +405,7 @@ int em_update_performance_limits(struct em_perf_domain *pd, { return -EINVAL; } +static inline void em_rebuild_sched_domains(void) {} #endif #endif diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 414146abfe81..c247317aae38 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -100,6 +100,7 @@ struct dev_pm_opp_data { #if defined(CONFIG_PM_OPP) struct opp_table *dev_pm_opp_get_opp_table(struct device *dev); +void dev_pm_opp_get_opp_table_ref(struct opp_table *opp_table); void dev_pm_opp_put_opp_table(struct opp_table *opp_table); unsigned long dev_pm_opp_get_bw(struct dev_pm_opp *opp, bool peak, int index); @@ -160,6 +161,7 @@ struct dev_pm_opp *dev_pm_opp_find_bw_ceil(struct device *dev, struct dev_pm_opp *dev_pm_opp_find_bw_floor(struct device *dev, unsigned int *bw, int index); +void dev_pm_opp_get(struct dev_pm_opp *opp); void dev_pm_opp_put(struct dev_pm_opp *opp); int dev_pm_opp_add_dynamic(struct device *dev, struct dev_pm_opp_data *opp); @@ -205,6 +207,8 @@ static inline struct opp_table *dev_pm_opp_get_opp_table_indexed(struct device * return ERR_PTR(-EOPNOTSUPP); } +static inline void dev_pm_opp_get_opp_table_ref(struct opp_table *opp_table) {} + static inline void dev_pm_opp_put_opp_table(struct opp_table *opp_table) {} static inline unsigned long dev_pm_opp_get_bw(struct dev_pm_opp *opp, bool peak, int index) @@ -341,6 +345,8 @@ static inline struct dev_pm_opp *dev_pm_opp_find_bw_floor(struct device *dev, return ERR_PTR(-EOPNOTSUPP); } +static inline void dev_pm_opp_get(struct dev_pm_opp *opp) {} + static inline void dev_pm_opp_put(struct dev_pm_opp *opp) {} static inline int diff --git a/include/linux/pm_wakeirq.h b/include/linux/pm_wakeirq.h index d9642c6cf852..25b63ed51b76 100644 --- a/include/linux/pm_wakeirq.h +++ b/include/linux/pm_wakeirq.h @@ -10,6 +10,7 @@ extern int dev_pm_set_wake_irq(struct device *dev, int irq); extern int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq); extern int dev_pm_set_dedicated_wake_irq_reverse(struct device *dev, int irq); extern void dev_pm_clear_wake_irq(struct device *dev); +extern int devm_pm_set_wake_irq(struct device *dev, int irq); #else /* !CONFIG_PM */ @@ -32,5 +33,10 @@ static inline void dev_pm_clear_wake_irq(struct device *dev) { } +static inline int devm_pm_set_wake_irq(struct device *dev, int irq) +{ + return 0; +} + #endif /* CONFIG_PM */ #endif /* _LINUX_PM_WAKEIRQ_H */ diff --git a/include/linux/pm_wakeup.h b/include/linux/pm_wakeup.h index 222f7530806c..d501c09c60cd 100644 --- a/include/linux/pm_wakeup.h +++ b/include/linux/pm_wakeup.h @@ -240,4 +240,21 @@ static inline int device_init_wakeup(struct device *dev, bool enable) return 0; } +static void device_disable_wakeup(void *dev) +{ + device_init_wakeup(dev, false); +} + +/** + * devm_device_init_wakeup - Resource managed device wakeup initialization. + * @dev: Device to handle. + * + * This function is the devm managed version of device_init_wakeup(dev, true). + */ +static inline int devm_device_init_wakeup(struct device *dev) +{ + device_init_wakeup(dev, true); + return devm_add_action_or_reset(dev, device_disable_wakeup, dev); +} + #endif /* _LINUX_PM_WAKEUP_H */ diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index afce8130d8b9..ca947ed32e3d 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -257,11 +257,30 @@ config DPM_WATCHDOG boot session. config DPM_WATCHDOG_TIMEOUT - int "Watchdog timeout in seconds" + int "Watchdog timeout to panic in seconds" range 1 120 default 120 depends on DPM_WATCHDOG +config DPM_WATCHDOG_WARNING_TIMEOUT + int "Watchdog timeout to warn in seconds" + range 1 DPM_WATCHDOG_TIMEOUT + default DPM_WATCHDOG_TIMEOUT + depends on DPM_WATCHDOG + help + If the DPM watchdog warning timeout and main timeout are + different then a non-fatal warning (with a stack trace of + the stuck suspend routine) will be printed when the warning + timeout expires. If the suspend routine gets un-stuck + before the main timeout expires then no other action is + taken. If the routine continues to be stuck and the main + timeout expires then an emergency-level message and stack + trace will be printed and the system will panic. + + If the warning timeout is equal to the main timeout (the + default) then the warning will never happen and the system + will jump straight to panic when the main timeout expires. + config PM_TRACE bool help diff --git a/kernel/power/autosleep.c b/kernel/power/autosleep.c index b29c8aca7486..865df641b97c 100644 --- a/kernel/power/autosleep.c +++ b/kernel/power/autosleep.c @@ -9,7 +9,6 @@ #include <linux/device.h> #include <linux/mutex.h> -#include <linux/pm_wakeup.h> #include "power.h" diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index d07faf42eace..3874f0e97651 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -908,3 +908,20 @@ int em_update_performance_limits(struct em_perf_domain *pd, return 0; } EXPORT_SYMBOL_GPL(em_update_performance_limits); + +static void rebuild_sd_workfn(struct work_struct *work) +{ + rebuild_sched_domains_energy(); +} + +void em_rebuild_sched_domains(void) +{ + static DECLARE_WORK(rebuild_sd_work, rebuild_sd_workfn); + + /* + * When called from the cpufreq_register_driver() path, the + * cpu_hotplug_lock is already held, so use a work item to + * avoid nested locking in rebuild_sched_domains(). + */ + schedule_work(&rebuild_sd_work); +} diff --git a/kernel/power/power.h b/kernel/power/power.h index de0e6b1077f2..c352dea2f67b 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -110,7 +110,7 @@ extern int hibernate_preallocate_memory(void); extern void clear_or_poison_free_pages(void); -/** +/* * Auxiliary structure used for reading the snapshot image data and * metadata from and writing them to the list of page backup entries * (PBEs) which is the main data structure of swsusp. diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 28c77904ea74..a2a29e3fffca 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -83,7 +83,7 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time) if (unlikely(sg_policy->limits_changed)) { sg_policy->limits_changed = false; - sg_policy->need_freq_update = true; + sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS); return true; } @@ -96,7 +96,7 @@ static bool sugov_update_next_freq(struct sugov_policy *sg_policy, u64 time, unsigned int next_freq) { if (sg_policy->need_freq_update) - sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS); + sg_policy->need_freq_update = false; else if (sg_policy->next_freq == next_freq) return false; @@ -604,31 +604,6 @@ static const struct kobj_type sugov_tunables_ktype = { /********************** cpufreq governor interface *********************/ -#ifdef CONFIG_ENERGY_MODEL -static void rebuild_sd_workfn(struct work_struct *work) -{ - rebuild_sched_domains_energy(); -} - -static DECLARE_WORK(rebuild_sd_work, rebuild_sd_workfn); - -/* - * EAS shouldn't be attempted without sugov, so rebuild the sched_domains - * on governor changes to make sure the scheduler knows about it. - */ -static void sugov_eas_rebuild_sd(void) -{ - /* - * When called from the cpufreq_register_driver() path, the - * cpu_hotplug_lock is already held, so use a work item to - * avoid nested locking in rebuild_sched_domains(). - */ - schedule_work(&rebuild_sd_work); -} -#else -static inline void sugov_eas_rebuild_sd(void) { }; -#endif - struct cpufreq_governor schedutil_gov; static struct sugov_policy *sugov_policy_alloc(struct cpufreq_policy *policy) @@ -784,7 +759,11 @@ static int sugov_init(struct cpufreq_policy *policy) goto fail; out: - sugov_eas_rebuild_sd(); + /* + * Schedutil is the preferred governor for EAS, so rebuild sched domains + * on governor changes to make sure the scheduler knows about them. + */ + em_rebuild_sched_domains(); mutex_unlock(&global_tunables_lock); return 0; @@ -826,7 +805,7 @@ static void sugov_exit(struct cpufreq_policy *policy) sugov_policy_free(sg_policy); cpufreq_disable_fast_switch(policy); - sugov_eas_rebuild_sd(); + em_rebuild_sched_domains(); } static int sugov_start(struct cpufreq_policy *policy) diff --git a/tools/power/cpupower/Makefile b/tools/power/cpupower/Makefile index 175004ce44b2..51a95239fe06 100644 --- a/tools/power/cpupower/Makefile +++ b/tools/power/cpupower/Makefile @@ -87,11 +87,19 @@ INSTALL_SCRIPT = ${INSTALL} -m 644 # to something more interesting, like "arm-linux-". If you want # to compile vs uClibc, that can be done here as well. CROSS ?= #/usr/i386-linux-uclibc/usr/bin/i386-uclibc- +ifneq ($(CROSS), ) +CC = $(CROSS)gcc +LD = $(CROSS)gcc +AR = $(CROSS)ar +STRIP = $(CROSS)strip +RANLIB = $(CROSS)ranlib +else CC ?= $(CROSS)gcc LD ?= $(CROSS)gcc AR ?= $(CROSS)ar STRIP ?= $(CROSS)strip RANLIB ?= $(CROSS)ranlib +endif HOSTCC = gcc MKDIR = mkdir diff --git a/tools/power/cpupower/bindings/python/Makefile b/tools/power/cpupower/bindings/python/Makefile index e1ebb1d60cd4..741f21477432 100644 --- a/tools/power/cpupower/bindings/python/Makefile +++ b/tools/power/cpupower/bindings/python/Makefile @@ -11,6 +11,7 @@ HAVE_PYCONFIG := $(shell if which python-config >/dev/null 2>&1; then echo 1; el LIB_DIR := ../../lib PY_INCLUDE = $(firstword $(shell python-config --includes)) OBJECTS_LIB = $(wildcard $(LIB_DIR)/*.o) +INSTALL_DIR = $(shell python3 -c "import site; print(site.getsitepackages()[0])") all: _raw_pylibcpupower.so @@ -28,6 +29,15 @@ else ifeq ($(HAVE_PYCONFIG),0) endif swig -python raw_pylibcpupower.swg +# Only installs the Python bindings +install: _raw_pylibcpupower.so + install -D _raw_pylibcpupower.so $(INSTALL_DIR)/_raw_pylibcpupower.so + install -D raw_pylibcpupower.py $(INSTALL_DIR)/raw_pylibcpupower.py + +uninstall: + rm -f $(INSTALL_DIR)/_raw_pylibcpupower.so + rm -f $(INSTALL_DIR)/raw_pylibcpupower.py + # Will only clean the bindings folder; will not clean the actual cpupower folder clean: rm -f raw_pylibcpupower.py raw_pylibcpupower_wrap.c raw_pylibcpupower_wrap.o _raw_pylibcpupower.so diff --git a/tools/power/cpupower/bindings/python/README b/tools/power/cpupower/bindings/python/README index 0a4bb2581e8a..952e2e02fd32 100644 --- a/tools/power/cpupower/bindings/python/README +++ b/tools/power/cpupower/bindings/python/README @@ -48,6 +48,31 @@ To run the test script: $ python test_raw_pylibcpupower.py +developing/using the bindings directly +-------------------------------------- + +You need to add the Python bindings directory to your $PYTHONPATH. + +You would set the path in the Bash terminal or in the Bash profile: + +PYTHONPATH=~/linux/tools/power/cpupower/bindings/python:$PYTHONPATH + +This allows you to set a specific repo of the bindings to use. + + +installing/uninstalling +----------------------- + +Python uses a system specific site-packages folder to look up modules to import +by default. You do not need to install cpupower to use the SWIG bindings. + +You can install and uninstall the bindings to the site-packages with: + +sudo make install + +sudo make uninstall + + credits ------- diff --git a/tools/power/cpupower/bindings/python/raw_pylibcpupower.swg b/tools/power/cpupower/bindings/python/raw_pylibcpupower.swg index 96556d87a745..d82af6fa93c3 100644 --- a/tools/power/cpupower/bindings/python/raw_pylibcpupower.swg +++ b/tools/power/cpupower/bindings/python/raw_pylibcpupower.swg @@ -134,6 +134,9 @@ void cpufreq_put_stats(struct cpufreq_stats *stats); unsigned long cpufreq_get_transitions(unsigned int cpu); +char *cpufreq_get_energy_performance_preference(unsigned int cpu); +void cpufreq_put_energy_performance_preference(char *ptr); + int cpufreq_set_policy(unsigned int cpu, struct cpufreq_policy *policy); int cpufreq_modify_policy_min(unsigned int cpu, unsigned long min_freq); @@ -160,6 +163,8 @@ int cpuidle_state_disable(unsigned int cpu, unsigned int idlestate, unsigned int disable); unsigned long cpuidle_state_latency(unsigned int cpu, unsigned int idlestate); +unsigned long cpuidle_state_residency(unsigned int cpu, + unsigned int idlestate); unsigned long cpuidle_state_usage(unsigned int cpu, unsigned int idlestate); unsigned long long cpuidle_state_time(unsigned int cpu, diff --git a/tools/power/cpupower/lib/cpufreq.c b/tools/power/cpupower/lib/cpufreq.c index 1516d23c17c9..8dda3db2dff0 100644 --- a/tools/power/cpupower/lib/cpufreq.c +++ b/tools/power/cpupower/lib/cpufreq.c @@ -102,6 +102,10 @@ unsigned long cpufreq_get_sysfs_value_from_table(unsigned int cpu, if (len == 0) return 0; + if (!strcmp(linebuf, "enabled\n")) + return 1; + if (!strcmp(linebuf, "disabled\n")) + return 0; value = strtoul(linebuf, &endp, 0); if (endp == linebuf || errno == ERANGE) @@ -123,12 +127,14 @@ static unsigned long sysfs_cpufreq_get_one_value(unsigned int cpu, enum cpufreq_string { SCALING_DRIVER, SCALING_GOVERNOR, + ENERGY_PERFORMANCE_PREFERENCE, MAX_CPUFREQ_STRING_FILES }; static const char *cpufreq_string_files[MAX_CPUFREQ_STRING_FILES] = { [SCALING_DRIVER] = "scaling_driver", [SCALING_GOVERNOR] = "scaling_governor", + [ENERGY_PERFORMANCE_PREFERENCE] = "energy_performance_preference", }; @@ -203,6 +209,18 @@ unsigned long cpufreq_get_transition_latency(unsigned int cpu) return sysfs_cpufreq_get_one_value(cpu, CPUINFO_LATENCY); } +char *cpufreq_get_energy_performance_preference(unsigned int cpu) +{ + return sysfs_cpufreq_get_one_string(cpu, ENERGY_PERFORMANCE_PREFERENCE); +} + +void cpufreq_put_energy_performance_preference(char *ptr) +{ + if (!ptr) + return; + free(ptr); +} + int cpufreq_get_hardware_limits(unsigned int cpu, unsigned long *min, unsigned long *max) diff --git a/tools/power/cpupower/lib/cpufreq.h b/tools/power/cpupower/lib/cpufreq.h index 2f3c84035806..bfc617311ebd 100644 --- a/tools/power/cpupower/lib/cpufreq.h +++ b/tools/power/cpupower/lib/cpufreq.h @@ -68,6 +68,14 @@ unsigned long cpufreq_get_freq_hardware(unsigned int cpu); unsigned long cpufreq_get_transition_latency(unsigned int cpu); +/* determine energy performance preference + * + * returns NULL on failure, else the string that represents the energy performance + * preference requested. + */ +char *cpufreq_get_energy_performance_preference(unsigned int cpu); +void cpufreq_put_energy_performance_preference(char *ptr); + /* determine hardware CPU frequency limits * * These may be limited further by thermal, energy or other diff --git a/tools/power/cpupower/utils/cpufreq-info.c b/tools/power/cpupower/utils/cpufreq-info.c index c96b77365c63..fc750e127404 100644 --- a/tools/power/cpupower/utils/cpufreq-info.c +++ b/tools/power/cpupower/utils/cpufreq-info.c @@ -120,7 +120,6 @@ static void print_duration(unsigned long duration) } else printf("%lu ns", duration); } - return; } static int get_boost_mode_x86(unsigned int cpu) @@ -255,7 +254,12 @@ static int get_freq_kernel(unsigned int cpu, unsigned int human) static int get_freq_hardware(unsigned int cpu, unsigned int human) { - unsigned long freq = cpufreq_get_freq_hardware(cpu); + unsigned long freq; + + if (cpupower_cpu_info.caps & CPUPOWER_CAP_APERF) + return -EINVAL; + + freq = cpufreq_get_freq_hardware(cpu); printf(_(" current CPU frequency: ")); if (!freq) { printf("Unable to call hardware\n"); @@ -418,12 +422,32 @@ static int get_freq_stats(unsigned int cpu, unsigned int human) return 0; } +/* --epp / -z */ + +static int get_epp(unsigned int cpu, bool interactive) +{ + char *epp; + + epp = cpufreq_get_energy_performance_preference(cpu); + if (!epp) + return -EINVAL; + if (interactive) + printf(_(" energy performance preference: %s\n"), epp); + + cpufreq_put_energy_performance_preference(epp); + + return 0; +} + /* --latency / -y */ static int get_latency(unsigned int cpu, unsigned int human) { unsigned long latency = cpufreq_get_transition_latency(cpu); + if (!get_epp(cpu, false)) + return -EINVAL; + printf(_(" maximum transition latency: ")); if (!latency || latency == UINT_MAX) { printf(_(" Cannot determine or is not supported.\n")); @@ -457,6 +481,7 @@ static void debug_output_one(unsigned int cpu) get_related_cpus(cpu); get_affected_cpus(cpu); get_latency(cpu, 1); + get_epp(cpu, true); get_hardware_limits(cpu, 1); freqs = cpufreq_get_available_frequencies(cpu); @@ -497,6 +522,7 @@ static struct option info_opts[] = { {"human", no_argument, NULL, 'm'}, {"no-rounding", no_argument, NULL, 'n'}, {"performance", no_argument, NULL, 'c'}, + {"epp", no_argument, NULL, 'z'}, { }, }; @@ -510,7 +536,7 @@ int cmd_freq_info(int argc, char **argv) int output_param = 0; do { - ret = getopt_long(argc, argv, "oefwldpgrasmybnc", info_opts, + ret = getopt_long(argc, argv, "oefwldpgrasmybncz", info_opts, NULL); switch (ret) { case '?': @@ -534,6 +560,7 @@ int cmd_freq_info(int argc, char **argv) case 's': case 'y': case 'c': + case 'z': if (output_param) { output_param = -1; cont = 0; @@ -643,6 +670,9 @@ int cmd_freq_info(int argc, char **argv) case 'c': ret = get_perf_cap(cpu); break; + case 'z': + ret = get_epp(cpu, true); + break; } if (ret) return ret; diff --git a/tools/power/cpupower/utils/helpers/amd.c b/tools/power/cpupower/utils/helpers/amd.c index 0a56e22240fc..795562e879de 100644 --- a/tools/power/cpupower/utils/helpers/amd.c +++ b/tools/power/cpupower/utils/helpers/amd.c @@ -177,6 +177,8 @@ enum amd_pstate_value { AMD_PSTATE_HIGHEST_PERF, AMD_PSTATE_MAX_FREQ, AMD_PSTATE_LOWEST_NONLINEAR_FREQ, + AMD_PSTATE_HW_PREFCORE, + AMD_PSTATE_PREFCORE_RANKING, MAX_AMD_PSTATE_VALUE_READ_FILES, }; @@ -184,6 +186,8 @@ static const char *amd_pstate_value_files[MAX_AMD_PSTATE_VALUE_READ_FILES] = { [AMD_PSTATE_HIGHEST_PERF] = "amd_pstate_highest_perf", [AMD_PSTATE_MAX_FREQ] = "amd_pstate_max_freq", [AMD_PSTATE_LOWEST_NONLINEAR_FREQ] = "amd_pstate_lowest_nonlinear_freq", + [AMD_PSTATE_HW_PREFCORE] = "amd_pstate_hw_prefcore", + [AMD_PSTATE_PREFCORE_RANKING] = "amd_pstate_prefcore_ranking", }; static unsigned long amd_pstate_get_data(unsigned int cpu, @@ -215,7 +219,9 @@ void amd_pstate_boost_init(unsigned int cpu, int *support, int *active) void amd_pstate_show_perf_and_freq(unsigned int cpu, int no_rounding) { - printf(_(" AMD PSTATE Highest Performance: %lu. Maximum Frequency: "), + + printf(_(" amd-pstate limits:\n")); + printf(_(" Highest Performance: %lu. Maximum Frequency: "), amd_pstate_get_data(cpu, AMD_PSTATE_HIGHEST_PERF)); /* * If boost isn't active, the cpuinfo_max doesn't indicate real max @@ -224,22 +230,26 @@ void amd_pstate_show_perf_and_freq(unsigned int cpu, int no_rounding) print_speed(amd_pstate_get_data(cpu, AMD_PSTATE_MAX_FREQ), no_rounding); printf(".\n"); - printf(_(" AMD PSTATE Nominal Performance: %lu. Nominal Frequency: "), + printf(_(" Nominal Performance: %lu. Nominal Frequency: "), acpi_cppc_get_data(cpu, NOMINAL_PERF)); print_speed(acpi_cppc_get_data(cpu, NOMINAL_FREQ) * 1000, no_rounding); printf(".\n"); - printf(_(" AMD PSTATE Lowest Non-linear Performance: %lu. Lowest Non-linear Frequency: "), + printf(_(" Lowest Non-linear Performance: %lu. Lowest Non-linear Frequency: "), acpi_cppc_get_data(cpu, LOWEST_NONLINEAR_PERF)); print_speed(amd_pstate_get_data(cpu, AMD_PSTATE_LOWEST_NONLINEAR_FREQ), no_rounding); printf(".\n"); - printf(_(" AMD PSTATE Lowest Performance: %lu. Lowest Frequency: "), + printf(_(" Lowest Performance: %lu. Lowest Frequency: "), acpi_cppc_get_data(cpu, LOWEST_PERF)); print_speed(acpi_cppc_get_data(cpu, LOWEST_FREQ) * 1000, no_rounding); printf(".\n"); + + printf(_(" Preferred Core Support: %lu. Preferred Core Ranking: %lu.\n"), + amd_pstate_get_data(cpu, AMD_PSTATE_HW_PREFCORE), + amd_pstate_get_data(cpu, AMD_PSTATE_PREFCORE_RANKING)); } /* AMD P-State Helper Functions ************************************/ diff --git a/tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c b/tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c index 55e55b6b42f9..f5a2a326b1b7 100644 --- a/tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c +++ b/tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c @@ -117,7 +117,7 @@ static int hsw_ext_start(void) for (num = 0; num < HSW_EXT_CSTATE_COUNT; num++) { for (cpu = 0; cpu < cpu_count; cpu++) { - hsw_ext_get_count(num, &val, cpu); + is_valid[cpu] = !hsw_ext_get_count(num, &val, cpu); previous_count[num][cpu] = val; } } @@ -134,7 +134,7 @@ static int hsw_ext_stop(void) for (num = 0; num < HSW_EXT_CSTATE_COUNT; num++) { for (cpu = 0; cpu < cpu_count; cpu++) { - is_valid[cpu] = !hsw_ext_get_count(num, &val, cpu); + is_valid[cpu] |= !hsw_ext_get_count(num, &val, cpu); current_count[num][cpu] = val; } } diff --git a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c index ae6af354a81d..73b6b10cbdd2 100644 --- a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c +++ b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c @@ -33,7 +33,7 @@ static int mperf_get_count_percent(unsigned int self_id, double *percent, unsigned int cpu); static int mperf_get_count_freq(unsigned int id, unsigned long long *count, unsigned int cpu); -static struct timespec time_start, time_end; +static struct timespec *time_start, *time_end; static cstate_t mperf_cstates[MPERF_CSTATE_COUNT] = { { @@ -148,7 +148,7 @@ static int mperf_measure_stats(unsigned int cpu) ret = get_aperf_mperf(cpu, &aval, &mval); aperf_current_count[cpu] = aval; mperf_current_count[cpu] = mval; - is_valid[cpu] = !ret; + is_valid[cpu] |= !ret; return 0; } @@ -174,7 +174,7 @@ static int mperf_get_count_percent(unsigned int id, double *percent, dprint("%s: TSC Ref - mperf_diff: %llu, tsc_diff: %llu\n", mperf_cstates[id].name, mperf_diff, tsc_diff); } else if (max_freq_mode == MAX_FREQ_SYSFS) { - timediff = max_frequency * timespec_diff_us(time_start, time_end); + timediff = max_frequency * timespec_diff_us(time_start[cpu], time_end[cpu]); *percent = 100.0 * mperf_diff / timediff; dprint("%s: MAXFREQ - mperf_diff: %llu, time_diff: %llu\n", mperf_cstates[id].name, mperf_diff, timediff); @@ -207,7 +207,7 @@ static int mperf_get_count_freq(unsigned int id, unsigned long long *count, if (max_freq_mode == MAX_FREQ_TSC_REF) { /* Calculate max_freq from TSC count */ tsc_diff = tsc_at_measure_end[cpu] - tsc_at_measure_start[cpu]; - time_diff = timespec_diff_us(time_start, time_end); + time_diff = timespec_diff_us(time_start[cpu], time_end[cpu]); max_frequency = tsc_diff / time_diff; } @@ -226,9 +226,8 @@ static int mperf_start(void) { int cpu; - clock_gettime(CLOCK_REALTIME, &time_start); - for (cpu = 0; cpu < cpu_count; cpu++) { + clock_gettime(CLOCK_REALTIME, &time_start[cpu]); mperf_get_tsc(&tsc_at_measure_start[cpu]); mperf_init_stats(cpu); } @@ -243,9 +242,9 @@ static int mperf_stop(void) for (cpu = 0; cpu < cpu_count; cpu++) { mperf_measure_stats(cpu); mperf_get_tsc(&tsc_at_measure_end[cpu]); + clock_gettime(CLOCK_REALTIME, &time_end[cpu]); } - clock_gettime(CLOCK_REALTIME, &time_end); return 0; } @@ -349,6 +348,8 @@ struct cpuidle_monitor *mperf_register(void) aperf_current_count = calloc(cpu_count, sizeof(unsigned long long)); tsc_at_measure_start = calloc(cpu_count, sizeof(unsigned long long)); tsc_at_measure_end = calloc(cpu_count, sizeof(unsigned long long)); + time_start = calloc(cpu_count, sizeof(struct timespec)); + time_end = calloc(cpu_count, sizeof(struct timespec)); mperf_monitor.name_len = strlen(mperf_monitor.name); return &mperf_monitor; } @@ -361,6 +362,8 @@ void mperf_unregister(void) free(aperf_current_count); free(tsc_at_measure_start); free(tsc_at_measure_end); + free(time_start); + free(time_end); free(is_valid); } diff --git a/tools/power/cpupower/utils/idle_monitor/nhm_idle.c b/tools/power/cpupower/utils/idle_monitor/nhm_idle.c index 16eaf006f61f..6b1733782ffa 100644 --- a/tools/power/cpupower/utils/idle_monitor/nhm_idle.c +++ b/tools/power/cpupower/utils/idle_monitor/nhm_idle.c @@ -151,7 +151,7 @@ static int nhm_stop(void) for (num = 0; num < NHM_CSTATE_COUNT; num++) { for (cpu = 0; cpu < cpu_count; cpu++) { - is_valid[cpu] = !nhm_get_count(num, &val, cpu); + is_valid[cpu] |= !nhm_get_count(num, &val, cpu); current_count[num][cpu] = val; } } diff --git a/tools/power/cpupower/utils/idle_monitor/snb_idle.c b/tools/power/cpupower/utils/idle_monitor/snb_idle.c index 811d63ab17a7..5969b88a85b4 100644 --- a/tools/power/cpupower/utils/idle_monitor/snb_idle.c +++ b/tools/power/cpupower/utils/idle_monitor/snb_idle.c @@ -115,7 +115,7 @@ static int snb_start(void) for (num = 0; num < SNB_CSTATE_COUNT; num++) { for (cpu = 0; cpu < cpu_count; cpu++) { - snb_get_count(num, &val, cpu); + is_valid[cpu] = !snb_get_count(num, &val, cpu); previous_count[num][cpu] = val; } } @@ -132,7 +132,7 @@ static int snb_stop(void) for (num = 0; num < SNB_CSTATE_COUNT; num++) { for (cpu = 0; cpu < cpu_count; cpu++) { - is_valid[cpu] = !snb_get_count(num, &val, cpu); + is_valid[cpu] |= !snb_get_count(num, &val, cpu); current_count[num][cpu] = val; } } diff --git a/tools/testing/selftests/cpufreq/.gitignore b/tools/testing/selftests/cpufreq/.gitignore new file mode 100644 index 000000000000..67604e91e068 --- /dev/null +++ b/tools/testing/selftests/cpufreq/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +cpufreq_selftest.* diff --git a/tools/testing/selftests/cpufreq/Makefile b/tools/testing/selftests/cpufreq/Makefile index c86ca8342222..9b2ccb10b0cf 100644 --- a/tools/testing/selftests/cpufreq/Makefile +++ b/tools/testing/selftests/cpufreq/Makefile @@ -3,6 +3,7 @@ all: TEST_PROGS := main.sh TEST_FILES := cpu.sh cpufreq.sh governor.sh module.sh special-tests.sh +EXTRA_CLEAN := cpufreq_selftest.dmesg_cpufreq.txt cpufreq_selftest.dmesg_full.txt cpufreq_selftest.txt include ../lib.mk |