diff options
Diffstat (limited to 'drivers/cpufreq')
-rw-r--r-- | drivers/cpufreq/Kconfig | 29 | ||||
-rw-r--r-- | drivers/cpufreq/Kconfig.arm | 27 | ||||
-rw-r--r-- | drivers/cpufreq/amd-pstate.c | 475 | ||||
-rw-r--r-- | drivers/cpufreq/brcmstb-avs-cpufreq.c | 7 | ||||
-rw-r--r-- | drivers/cpufreq/cppc_cpufreq.c | 14 | ||||
-rw-r--r-- | drivers/cpufreq/cpufreq-dt-platdev.c | 11 | ||||
-rw-r--r-- | drivers/cpufreq/cpufreq-dt.c | 23 | ||||
-rw-r--r-- | drivers/cpufreq/cpufreq.c | 97 | ||||
-rw-r--r-- | drivers/cpufreq/cpufreq_ondemand.c | 1 | ||||
-rw-r--r-- | drivers/cpufreq/freq_table.c | 14 | ||||
-rw-r--r-- | drivers/cpufreq/imx6q-cpufreq.c | 45 | ||||
-rw-r--r-- | drivers/cpufreq/intel_pstate.c | 219 | ||||
-rw-r--r-- | drivers/cpufreq/mediatek-cpufreq-hw.c | 19 | ||||
-rw-r--r-- | drivers/cpufreq/mediatek-cpufreq.c | 10 | ||||
-rw-r--r-- | drivers/cpufreq/pmac32-cpufreq.c | 8 | ||||
-rw-r--r-- | drivers/cpufreq/qcom-cpufreq-hw.c | 4 | ||||
-rw-r--r-- | drivers/cpufreq/scmi-cpufreq.c | 46 | ||||
-rw-r--r-- | drivers/cpufreq/sun50i-cpufreq-nvmem.c | 209 | ||||
-rw-r--r-- | drivers/cpufreq/tegra124-cpufreq.c | 19 | ||||
-rw-r--r-- | drivers/cpufreq/ti-cpufreq.c | 4 |
20 files changed, 887 insertions, 394 deletions
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig index 35efb53d5492..94e55c40970a 100644 --- a/drivers/cpufreq/Kconfig +++ b/drivers/cpufreq/Kconfig @@ -302,4 +302,33 @@ config QORIQ_CPUFREQ which are capable of changing the CPU's frequency dynamically. endif + +config ACPI_CPPC_CPUFREQ + tristate "CPUFreq driver based on the ACPI CPPC spec" + depends on ACPI_PROCESSOR + depends on ARM || ARM64 || RISCV + select ACPI_CPPC_LIB + help + This adds a CPUFreq driver which uses CPPC methods + as described in the ACPIv5.1 spec. CPPC stands for + Collaborative Processor Performance Controls. It + is based on an abstract continuous scale of CPU + performance values which allows the remote power + processor to flexibly optimize for power and + performance. CPPC relies on power management firmware + support for its operation. + + If in doubt, say N. + +config ACPI_CPPC_CPUFREQ_FIE + bool "Frequency Invariance support for CPPC cpufreq driver" + depends on ACPI_CPPC_CPUFREQ && GENERIC_ARCH_TOPOLOGY + depends on ARM || ARM64 || RISCV + default y + help + This extends frequency invariance support in the CPPC cpufreq driver, + by using CPPC delivered and reference performance counters. + + If in doubt, say N. + endmenu diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index f911606897b8..96b404ce829f 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -3,32 +3,6 @@ # ARM CPU Frequency scaling drivers # -config ACPI_CPPC_CPUFREQ - tristate "CPUFreq driver based on the ACPI CPPC spec" - depends on ACPI_PROCESSOR - select ACPI_CPPC_LIB - help - This adds a CPUFreq driver which uses CPPC methods - as described in the ACPIv5.1 spec. CPPC stands for - Collaborative Processor Performance Controls. It - is based on an abstract continuous scale of CPU - performance values which allows the remote power - processor to flexibly optimize for power and - performance. CPPC relies on power management firmware - support for its operation. - - If in doubt, say N. - -config ACPI_CPPC_CPUFREQ_FIE - bool "Frequency Invariance support for CPPC cpufreq driver" - depends on ACPI_CPPC_CPUFREQ && GENERIC_ARCH_TOPOLOGY - default y - help - This extends frequency invariance support in the CPPC cpufreq driver, - by using CPPC delivered and reference performance counters. - - If in doubt, say N. - config ARM_ALLWINNER_SUN50I_CPUFREQ_NVMEM tristate "Allwinner nvmem based SUN50I CPUFreq driver" depends on ARCH_SUNXI @@ -173,6 +147,7 @@ config ARM_QCOM_CPUFREQ_NVMEM config ARM_QCOM_CPUFREQ_HW tristate "QCOM CPUFreq HW driver" depends on ARCH_QCOM || COMPILE_TEST + depends on COMMON_CLK help Support for the CPUFreq HW driver. Some QCOM chipsets have a HW engine to offload the steps diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 1791d37fbc53..1b7e82a0ad2e 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -37,6 +37,7 @@ #include <linux/uaccess.h> #include <linux/static_call.h> #include <linux/amd-pstate.h> +#include <linux/topology.h> #include <acpi/processor.h> #include <acpi/cppc_acpi.h> @@ -49,6 +50,8 @@ #define AMD_PSTATE_TRANSITION_LATENCY 20000 #define AMD_PSTATE_TRANSITION_DELAY 1000 +#define CPPC_HIGHEST_PERF_PERFORMANCE 196 +#define CPPC_HIGHEST_PERF_DEFAULT 166 /* * TODO: We need more time to fine tune processors with shared memory solution @@ -64,6 +67,8 @@ static struct cpufreq_driver amd_pstate_driver; static struct cpufreq_driver amd_pstate_epp_driver; static int cppc_state = AMD_PSTATE_UNDEFINED; static bool cppc_enabled; +static bool amd_pstate_prefcore = true; +static struct quirk_entry *quirks; /* * AMD Energy Preference Performance (EPP) @@ -108,6 +113,41 @@ static unsigned int epp_values[] = { typedef int (*cppc_mode_transition_fn)(int); +static struct quirk_entry quirk_amd_7k62 = { + .nominal_freq = 2600, + .lowest_freq = 550, +}; + +static int __init dmi_matched_7k62_bios_bug(const struct dmi_system_id *dmi) +{ + /** + * match the broken bios for family 17h processor support CPPC V2 + * broken BIOS lack of nominal_freq and lowest_freq capabilities + * definition in ACPI tables + */ + if (boot_cpu_has(X86_FEATURE_ZEN2)) { + quirks = dmi->driver_data; + pr_info("Overriding nominal and lowest frequencies for %s\n", dmi->ident); + return 1; + } + + return 0; +} + +static const struct dmi_system_id amd_pstate_quirks_table[] __initconst = { + { + .callback = dmi_matched_7k62_bios_bug, + .ident = "AMD EPYC 7K62", + .matches = { + DMI_MATCH(DMI_BIOS_VERSION, "5.14"), + DMI_MATCH(DMI_BIOS_RELEASE, "12/12/2019"), + }, + .driver_data = &quirk_amd_7k62, + }, + {} +}; +MODULE_DEVICE_TABLE(dmi, amd_pstate_quirks_table); + static inline int get_mode_idx_from_str(const char *str, size_t size) { int i; @@ -287,6 +327,21 @@ static inline int amd_pstate_enable(bool enable) return static_call(amd_pstate_enable)(enable); } +static u32 amd_pstate_highest_perf_set(struct amd_cpudata *cpudata) +{ + struct cpuinfo_x86 *c = &cpu_data(0); + + /* + * For AMD CPUs with Family ID 19H and Model ID range 0x70 to 0x7f, + * the highest performance level is set to 196. + * https://bugzilla.kernel.org/show_bug.cgi?id=218759 + */ + if (c->x86 == 0x19 && (c->x86_model >= 0x70 && c->x86_model <= 0x7f)) + return CPPC_HIGHEST_PERF_PERFORMANCE; + + return CPPC_HIGHEST_PERF_DEFAULT; +} + static int pstate_init_perf(struct amd_cpudata *cpudata) { u64 cap1; @@ -297,13 +352,14 @@ static int pstate_init_perf(struct amd_cpudata *cpudata) if (ret) return ret; - /* - * TODO: Introduce AMD specific power feature. - * - * CPPC entry doesn't indicate the highest performance in some ASICs. + /* For platforms that do not support the preferred core feature, the + * highest_pef may be configured with 166 or 255, to avoid max frequency + * calculated wrongly. we take the AMD_CPPC_HIGHEST_PERF(cap1) value as + * the default max perf. */ - highest_perf = amd_get_highest_perf(); - if (highest_perf > AMD_CPPC_HIGHEST_PERF(cap1)) + if (cpudata->hw_prefcore) + highest_perf = amd_pstate_highest_perf_set(cpudata); + else highest_perf = AMD_CPPC_HIGHEST_PERF(cap1); WRITE_ONCE(cpudata->highest_perf, highest_perf); @@ -311,6 +367,7 @@ static int pstate_init_perf(struct amd_cpudata *cpudata) WRITE_ONCE(cpudata->nominal_perf, AMD_CPPC_NOMINAL_PERF(cap1)); WRITE_ONCE(cpudata->lowest_nonlinear_perf, AMD_CPPC_LOWNONLIN_PERF(cap1)); WRITE_ONCE(cpudata->lowest_perf, AMD_CPPC_LOWEST_PERF(cap1)); + WRITE_ONCE(cpudata->prefcore_ranking, AMD_CPPC_HIGHEST_PERF(cap1)); WRITE_ONCE(cpudata->min_limit_perf, AMD_CPPC_LOWEST_PERF(cap1)); return 0; } @@ -324,8 +381,9 @@ static int cppc_init_perf(struct amd_cpudata *cpudata) if (ret) return ret; - highest_perf = amd_get_highest_perf(); - if (highest_perf > cppc_perf.highest_perf) + if (cpudata->hw_prefcore) + highest_perf = amd_pstate_highest_perf_set(cpudata); + else highest_perf = cppc_perf.highest_perf; WRITE_ONCE(cpudata->highest_perf, highest_perf); @@ -334,6 +392,7 @@ static int cppc_init_perf(struct amd_cpudata *cpudata) WRITE_ONCE(cpudata->lowest_nonlinear_perf, cppc_perf.lowest_nonlinear_perf); WRITE_ONCE(cpudata->lowest_perf, cppc_perf.lowest_perf); + WRITE_ONCE(cpudata->prefcore_ranking, cppc_perf.highest_perf); WRITE_ONCE(cpudata->min_limit_perf, cppc_perf.lowest_perf); if (cppc_state == AMD_PSTATE_ACTIVE) @@ -477,12 +536,19 @@ static int amd_pstate_verify(struct cpufreq_policy_data *policy) static int amd_pstate_update_min_max_limit(struct cpufreq_policy *policy) { - u32 max_limit_perf, min_limit_perf; + u32 max_limit_perf, min_limit_perf, lowest_perf; struct amd_cpudata *cpudata = policy->driver_data; max_limit_perf = div_u64(policy->max * cpudata->highest_perf, cpudata->max_freq); min_limit_perf = div_u64(policy->min * cpudata->highest_perf, cpudata->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; + WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf); WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf); WRITE_ONCE(cpudata->max_limit_freq, policy->max); @@ -570,7 +636,7 @@ static void amd_pstate_adjust_perf(unsigned int cpu, if (target_perf < capacity) des_perf = DIV_ROUND_UP(cap_perf * target_perf, capacity); - min_perf = READ_ONCE(cpudata->highest_perf); + min_perf = READ_ONCE(cpudata->lowest_perf); if (_min_perf < capacity) min_perf = DIV_ROUND_UP(cap_perf * _min_perf, capacity); @@ -590,125 +656,245 @@ static void amd_pstate_adjust_perf(unsigned int cpu, cpufreq_cpu_put(policy); } -static int amd_get_min_freq(struct amd_cpudata *cpudata) +static int amd_pstate_set_boost(struct cpufreq_policy *policy, int state) { - struct cppc_perf_caps cppc_perf; + struct amd_cpudata *cpudata = policy->driver_data; + int ret; - int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); - if (ret) + if (!cpudata->boost_supported) { + pr_err("Boost mode is not supported by this processor or SBIOS\n"); + return -EINVAL; + } + + if (state) + policy->cpuinfo.max_freq = cpudata->max_freq; + else + policy->cpuinfo.max_freq = cpudata->nominal_freq; + + policy->max = policy->cpuinfo.max_freq; + + ret = freq_qos_update_request(&cpudata->req[1], + policy->cpuinfo.max_freq); + if (ret < 0) return ret; - /* Switch to khz */ - return cppc_perf.lowest_freq * 1000; + return 0; } -static int amd_get_max_freq(struct amd_cpudata *cpudata) +static void amd_pstate_boost_init(struct amd_cpudata *cpudata) { - struct cppc_perf_caps cppc_perf; - u32 max_perf, max_freq, nominal_freq, nominal_perf; - u64 boost_ratio; - - int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); - if (ret) - return ret; + u32 highest_perf, nominal_perf; - nominal_freq = cppc_perf.nominal_freq; + highest_perf = READ_ONCE(cpudata->highest_perf); nominal_perf = READ_ONCE(cpudata->nominal_perf); - max_perf = READ_ONCE(cpudata->highest_perf); - boost_ratio = div_u64(max_perf << SCHED_CAPACITY_SHIFT, - nominal_perf); + if (highest_perf <= nominal_perf) + return; - max_freq = nominal_freq * boost_ratio >> SCHED_CAPACITY_SHIFT; + cpudata->boost_supported = true; + current_pstate_driver->boost_enabled = true; +} + +static void amd_perf_ctl_reset(unsigned int cpu) +{ + wrmsrl_on_cpu(cpu, MSR_AMD_PERF_CTL, 0); +} - /* Switch to khz */ - return max_freq * 1000; +/* + * Set amd-pstate preferred core enable can't be done directly from cpufreq callbacks + * due to locking, so queue the work for later. + */ +static void amd_pstste_sched_prefcore_workfn(struct work_struct *work) +{ + sched_set_itmt_support(); } +static DECLARE_WORK(sched_prefcore_work, amd_pstste_sched_prefcore_workfn); -static int amd_get_nominal_freq(struct amd_cpudata *cpudata) +/* + * Get the highest performance register value. + * @cpu: CPU from which to get highest performance. + * @highest_perf: Return address. + * + * Return: 0 for success, -EIO otherwise. + */ +static int amd_pstate_get_highest_perf(int cpu, u32 *highest_perf) { - struct cppc_perf_caps cppc_perf; + int ret; - int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); - if (ret) - return ret; + if (boot_cpu_has(X86_FEATURE_CPPC)) { + u64 cap1; + + ret = rdmsrl_safe_on_cpu(cpu, MSR_AMD_CPPC_CAP1, &cap1); + if (ret) + return ret; + WRITE_ONCE(*highest_perf, AMD_CPPC_HIGHEST_PERF(cap1)); + } else { + u64 cppc_highest_perf; + + ret = cppc_get_highest_perf(cpu, &cppc_highest_perf); + if (ret) + return ret; + WRITE_ONCE(*highest_perf, cppc_highest_perf); + } - /* Switch to khz */ - return cppc_perf.nominal_freq * 1000; + return (ret); } -static int amd_get_lowest_nonlinear_freq(struct amd_cpudata *cpudata) +#define CPPC_MAX_PERF U8_MAX + +static void amd_pstate_init_prefcore(struct amd_cpudata *cpudata) { - struct cppc_perf_caps cppc_perf; - u32 lowest_nonlinear_freq, lowest_nonlinear_perf, - nominal_freq, nominal_perf; - u64 lowest_nonlinear_ratio; + int ret, prio; + u32 highest_perf; - int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); + ret = amd_pstate_get_highest_perf(cpudata->cpu, &highest_perf); if (ret) - return ret; - - nominal_freq = cppc_perf.nominal_freq; - nominal_perf = READ_ONCE(cpudata->nominal_perf); + return; - lowest_nonlinear_perf = cppc_perf.lowest_nonlinear_perf; + cpudata->hw_prefcore = true; + /* check if CPPC preferred core feature is enabled*/ + if (highest_perf < CPPC_MAX_PERF) + prio = (int)highest_perf; + else { + pr_debug("AMD CPPC preferred core is unsupported!\n"); + cpudata->hw_prefcore = false; + return; + } - lowest_nonlinear_ratio = div_u64(lowest_nonlinear_perf << SCHED_CAPACITY_SHIFT, - nominal_perf); + if (!amd_pstate_prefcore) + return; - lowest_nonlinear_freq = nominal_freq * lowest_nonlinear_ratio >> SCHED_CAPACITY_SHIFT; + /* + * The priorities can be set regardless of whether or not + * 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(prio, cpudata->cpu); - /* Switch to khz */ - return lowest_nonlinear_freq * 1000; + schedule_work(&sched_prefcore_work); } -static int amd_pstate_set_boost(struct cpufreq_policy *policy, int state) +static void amd_pstate_update_limits(unsigned int cpu) { + struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); struct amd_cpudata *cpudata = policy->driver_data; + u32 prev_high = 0, cur_high = 0; int ret; + bool highest_perf_changed = false; - if (!cpudata->boost_supported) { - pr_err("Boost mode is not supported by this processor or SBIOS\n"); - return -EINVAL; - } + mutex_lock(&amd_pstate_driver_lock); + if ((!amd_pstate_prefcore) || (!cpudata->hw_prefcore)) + goto free_cpufreq_put; - if (state) - policy->cpuinfo.max_freq = cpudata->max_freq; - else - policy->cpuinfo.max_freq = cpudata->nominal_freq; + ret = amd_pstate_get_highest_perf(cpu, &cur_high); + if (ret) + goto free_cpufreq_put; - policy->max = policy->cpuinfo.max_freq; + prev_high = READ_ONCE(cpudata->prefcore_ranking); + if (prev_high != cur_high) { + highest_perf_changed = true; + WRITE_ONCE(cpudata->prefcore_ranking, cur_high); - ret = freq_qos_update_request(&cpudata->req[1], - policy->cpuinfo.max_freq); - if (ret < 0) - return ret; + if (cur_high < CPPC_MAX_PERF) + sched_set_itmt_core_prio((int)cur_high, cpu); + } - return 0; +free_cpufreq_put: + cpufreq_cpu_put(policy); + + if (!highest_perf_changed) + cpufreq_update_policy(cpu); + + mutex_unlock(&amd_pstate_driver_lock); } -static void amd_pstate_boost_init(struct amd_cpudata *cpudata) +/* + * Get pstate transition delay time from ACPI tables that firmware set + * instead of using hardcode value directly. + */ +static u32 amd_pstate_get_transition_delay_us(unsigned int cpu) { - u32 highest_perf, nominal_perf; + u32 transition_delay_ns; - highest_perf = READ_ONCE(cpudata->highest_perf); - nominal_perf = READ_ONCE(cpudata->nominal_perf); + transition_delay_ns = cppc_get_transition_latency(cpu); + if (transition_delay_ns == CPUFREQ_ETERNAL) + return AMD_PSTATE_TRANSITION_DELAY; - if (highest_perf <= nominal_perf) - return; + return transition_delay_ns / NSEC_PER_USEC; +} - cpudata->boost_supported = true; - current_pstate_driver->boost_enabled = true; +/* + * Get pstate transition latency value from ACPI tables that firmware + * set instead of using hardcode value directly. + */ +static u32 amd_pstate_get_transition_latency(unsigned int cpu) +{ + u32 transition_latency; + + transition_latency = cppc_get_transition_latency(cpu); + if (transition_latency == CPUFREQ_ETERNAL) + return AMD_PSTATE_TRANSITION_LATENCY; + + return transition_latency; } -static void amd_perf_ctl_reset(unsigned int cpu) +/* + * amd_pstate_init_freq: Initialize the max_freq, min_freq, + * nominal_freq and lowest_nonlinear_freq for + * the @cpudata object. + * + * Requires: highest_perf, lowest_perf, nominal_perf and + * lowest_nonlinear_perf members of @cpudata to be + * initialized. + * + * Returns 0 on success, non-zero value on failure. + */ +static int amd_pstate_init_freq(struct amd_cpudata *cpudata) { - wrmsrl_on_cpu(cpu, MSR_AMD_PERF_CTL, 0); + int ret; + u32 min_freq; + u32 highest_perf, max_freq; + u32 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); + if (ret) + return ret; + + if (quirks && quirks->lowest_freq) + min_freq = quirks->lowest_freq * 1000; + else + min_freq = cppc_perf.lowest_freq * 1000; + + if (quirks && quirks->nominal_freq) + nominal_freq = quirks->nominal_freq ; + else + nominal_freq = cppc_perf.nominal_freq; + + nominal_perf = READ_ONCE(cpudata->nominal_perf); + + highest_perf = READ_ONCE(cpudata->highest_perf); + boost_ratio = div_u64(highest_perf << SCHED_CAPACITY_SHIFT, nominal_perf); + max_freq = (nominal_freq * boost_ratio >> SCHED_CAPACITY_SHIFT) * 1000; + + 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); + + return 0; } static int amd_pstate_cpu_init(struct cpufreq_policy *policy) { - int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret; + int min_freq, max_freq, nominal_freq, ret; struct device *dev; struct amd_cpudata *cpudata; @@ -727,24 +913,31 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy) cpudata->cpu = policy->cpu; + amd_pstate_init_prefcore(cpudata); + ret = amd_pstate_init_perf(cpudata); if (ret) goto free_cpudata1; - min_freq = amd_get_min_freq(cpudata); - max_freq = amd_get_max_freq(cpudata); - nominal_freq = amd_get_nominal_freq(cpudata); - lowest_nonlinear_freq = amd_get_lowest_nonlinear_freq(cpudata); + ret = amd_pstate_init_freq(cpudata); + if (ret) + goto free_cpudata1; + + min_freq = READ_ONCE(cpudata->min_freq); + max_freq = READ_ONCE(cpudata->max_freq); + nominal_freq = READ_ONCE(cpudata->nominal_freq); - if (min_freq < 0 || max_freq < 0 || min_freq > max_freq) { - dev_err(dev, "min_freq(%d) or max_freq(%d) value is incorrect\n", - min_freq, max_freq); + if (min_freq <= 0 || max_freq <= 0 || + nominal_freq <= 0 || min_freq > max_freq) { + dev_err(dev, + "min_freq(%d) or max_freq(%d) or nominal_freq (%d) value is incorrect, check _CPC in ACPI tables\n", + min_freq, max_freq, nominal_freq); ret = -EINVAL; goto free_cpudata1; } - policy->cpuinfo.transition_latency = AMD_PSTATE_TRANSITION_LATENCY; - policy->transition_delay_us = AMD_PSTATE_TRANSITION_DELAY; + policy->cpuinfo.transition_latency = amd_pstate_get_transition_latency(policy->cpu); + policy->transition_delay_us = amd_pstate_get_transition_delay_us(policy->cpu); policy->min = min_freq; policy->max = max_freq; @@ -772,13 +965,8 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy) goto free_cpudata2; } - /* Initial processor data capability frequencies */ - cpudata->max_freq = max_freq; - cpudata->min_freq = min_freq; cpudata->max_limit_freq = max_freq; cpudata->min_limit_freq = min_freq; - cpudata->nominal_freq = nominal_freq; - cpudata->lowest_nonlinear_freq = lowest_nonlinear_freq; policy->driver_data = cpudata; @@ -842,7 +1030,7 @@ static ssize_t show_amd_pstate_max_freq(struct cpufreq_policy *policy, int max_freq; struct amd_cpudata *cpudata = policy->driver_data; - max_freq = amd_get_max_freq(cpudata); + max_freq = READ_ONCE(cpudata->max_freq); if (max_freq < 0) return max_freq; @@ -855,7 +1043,7 @@ static ssize_t show_amd_pstate_lowest_nonlinear_freq(struct cpufreq_policy *poli int freq; struct amd_cpudata *cpudata = policy->driver_data; - freq = amd_get_lowest_nonlinear_freq(cpudata); + freq = READ_ONCE(cpudata->lowest_nonlinear_freq); if (freq < 0) return freq; @@ -877,6 +1065,28 @@ static ssize_t show_amd_pstate_highest_perf(struct cpufreq_policy *policy, return sysfs_emit(buf, "%u\n", perf); } +static ssize_t show_amd_pstate_prefcore_ranking(struct cpufreq_policy *policy, + char *buf) +{ + u32 perf; + struct amd_cpudata *cpudata = policy->driver_data; + + perf = READ_ONCE(cpudata->prefcore_ranking); + + return sysfs_emit(buf, "%u\n", perf); +} + +static ssize_t show_amd_pstate_hw_prefcore(struct cpufreq_policy *policy, + char *buf) +{ + bool hw_prefcore; + struct amd_cpudata *cpudata = policy->driver_data; + + hw_prefcore = READ_ONCE(cpudata->hw_prefcore); + + return sysfs_emit(buf, "%s\n", str_enabled_disabled(hw_prefcore)); +} + static ssize_t show_energy_performance_available_preferences( struct cpufreq_policy *policy, char *buf) { @@ -1074,18 +1284,29 @@ static ssize_t status_store(struct device *a, struct device_attribute *b, return ret < 0 ? ret : count; } +static ssize_t prefcore_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%s\n", str_enabled_disabled(amd_pstate_prefcore)); +} + cpufreq_freq_attr_ro(amd_pstate_max_freq); cpufreq_freq_attr_ro(amd_pstate_lowest_nonlinear_freq); cpufreq_freq_attr_ro(amd_pstate_highest_perf); +cpufreq_freq_attr_ro(amd_pstate_prefcore_ranking); +cpufreq_freq_attr_ro(amd_pstate_hw_prefcore); cpufreq_freq_attr_rw(energy_performance_preference); cpufreq_freq_attr_ro(energy_performance_available_preferences); static DEVICE_ATTR_RW(status); +static DEVICE_ATTR_RO(prefcore); static struct freq_attr *amd_pstate_attr[] = { &amd_pstate_max_freq, &amd_pstate_lowest_nonlinear_freq, &amd_pstate_highest_perf, + &amd_pstate_prefcore_ranking, + &amd_pstate_hw_prefcore, NULL, }; @@ -1093,6 +1314,8 @@ static struct freq_attr *amd_pstate_epp_attr[] = { &amd_pstate_max_freq, &amd_pstate_lowest_nonlinear_freq, &amd_pstate_highest_perf, + &amd_pstate_prefcore_ranking, + &amd_pstate_hw_prefcore, &energy_performance_preference, &energy_performance_available_preferences, NULL, @@ -1100,6 +1323,7 @@ static struct freq_attr *amd_pstate_epp_attr[] = { static struct attribute *pstate_global_attributes[] = { &dev_attr_status.attr, + &dev_attr_prefcore.attr, NULL }; @@ -1130,7 +1354,7 @@ static bool amd_pstate_acpi_pm_profile_undefined(void) static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) { - int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret; + int min_freq, max_freq, nominal_freq, ret; struct amd_cpudata *cpudata; struct device *dev; u64 value; @@ -1151,17 +1375,24 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) cpudata->cpu = policy->cpu; cpudata->epp_policy = 0; + amd_pstate_init_prefcore(cpudata); + ret = amd_pstate_init_perf(cpudata); if (ret) goto free_cpudata1; - min_freq = amd_get_min_freq(cpudata); - max_freq = amd_get_max_freq(cpudata); - nominal_freq = amd_get_nominal_freq(cpudata); - lowest_nonlinear_freq = amd_get_lowest_nonlinear_freq(cpudata); - if (min_freq < 0 || max_freq < 0 || min_freq > max_freq) { - dev_err(dev, "min_freq(%d) or max_freq(%d) value is incorrect\n", - min_freq, max_freq); + ret = amd_pstate_init_freq(cpudata); + if (ret) + goto free_cpudata1; + + min_freq = READ_ONCE(cpudata->min_freq); + max_freq = READ_ONCE(cpudata->max_freq); + nominal_freq = READ_ONCE(cpudata->nominal_freq); + if (min_freq <= 0 || max_freq <= 0 || + nominal_freq <= 0 || min_freq > max_freq) { + dev_err(dev, + "min_freq(%d) or max_freq(%d) or nominal_freq(%d) value is incorrect, check _CPC in ACPI tables\n", + min_freq, max_freq, nominal_freq); ret = -EINVAL; goto free_cpudata1; } @@ -1171,12 +1402,6 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) /* It will be updated by governor */ policy->cur = policy->cpuinfo.min_freq; - /* Initial processor data capability frequencies */ - cpudata->max_freq = max_freq; - cpudata->min_freq = min_freq; - cpudata->nominal_freq = nominal_freq; - cpudata->lowest_nonlinear_freq = lowest_nonlinear_freq; - policy->driver_data = cpudata; cpudata->epp_cached = amd_pstate_get_epp(cpudata, 0); @@ -1216,6 +1441,13 @@ free_cpudata1: static int amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy) { + struct amd_cpudata *cpudata = policy->driver_data; + + if (cpudata) { + kfree(cpudata); + policy->driver_data = NULL; + } + pr_debug("CPU %d exiting\n", policy->cpu); return 0; } @@ -1232,6 +1464,12 @@ static void amd_pstate_epp_update_limit(struct cpufreq_policy *policy) max_limit_perf = div_u64(policy->max * cpudata->highest_perf, cpudata->max_freq); min_limit_perf = div_u64(policy->min * cpudata->highest_perf, cpudata->max_freq); + if (min_limit_perf < min_perf) + min_limit_perf = min_perf; + + if (max_limit_perf < min_limit_perf) + max_limit_perf = min_limit_perf; + WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf); WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf); @@ -1432,6 +1670,7 @@ static struct cpufreq_driver amd_pstate_driver = { .suspend = amd_pstate_cpu_suspend, .resume = amd_pstate_cpu_resume, .set_boost = amd_pstate_set_boost, + .update_limits = amd_pstate_update_limits, .name = "amd-pstate", .attr = amd_pstate_attr, }; @@ -1446,6 +1685,7 @@ static struct cpufreq_driver amd_pstate_epp_driver = { .online = amd_pstate_epp_cpu_online, .suspend = amd_pstate_epp_suspend, .resume = amd_pstate_epp_resume, + .update_limits = amd_pstate_update_limits, .name = "amd-pstate-epp", .attr = amd_pstate_epp_attr, }; @@ -1486,6 +1726,11 @@ static int __init amd_pstate_init(void) if (cpufreq_get_current_driver()) return -EEXIST; + quirks = NULL; + + /* check if this machine need CPPC quirks */ + dmi_check_system(amd_pstate_quirks_table); + switch (cppc_state) { case AMD_PSTATE_UNDEFINED: /* Disable on the following configs by default: @@ -1567,7 +1812,17 @@ static int __init amd_pstate_param(char *str) return amd_pstate_set_driver(mode_idx); } + +static int __init amd_prefcore_param(char *str) +{ + if (!strcmp(str, "disable")) + amd_pstate_prefcore = false; + + return 0; +} + early_param("amd_pstate", amd_pstate_param); +early_param("amd_prefcore", amd_prefcore_param); MODULE_AUTHOR("Huang Rui <ray.huang@amd.com>"); MODULE_DESCRIPTION("AMD Processor P-state Frequency Driver"); diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c index 35fb3a559ea9..ea8438550b49 100644 --- a/drivers/cpufreq/brcmstb-avs-cpufreq.c +++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c @@ -481,7 +481,12 @@ static bool brcm_avs_is_firmware_loaded(struct private_data *priv) static unsigned int brcm_avs_cpufreq_get(unsigned int cpu) { struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); - struct private_data *priv = policy->driver_data; + struct private_data *priv; + + if (!policy) + return 0; + + priv = policy->driver_data; cpufreq_cpu_put(policy); diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index 64420d9cfd1e..15f1d41920a3 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -741,10 +741,15 @@ static unsigned int cppc_cpufreq_get_rate(unsigned int cpu) { struct cppc_perf_fb_ctrs fb_ctrs_t0 = {0}, fb_ctrs_t1 = {0}; struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); - struct cppc_cpudata *cpu_data = policy->driver_data; + struct cppc_cpudata *cpu_data; u64 delivered_perf; int ret; + if (!policy) + return -ENODEV; + + cpu_data = policy->driver_data; + cpufreq_cpu_put(policy); ret = cppc_get_perf_ctrs(cpu, &fb_ctrs_t0); @@ -822,10 +827,15 @@ static struct cpufreq_driver cppc_cpufreq_driver = { static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpu) { struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); - struct cppc_cpudata *cpu_data = policy->driver_data; + struct cppc_cpudata *cpu_data; u64 desired_perf; int ret; + if (!policy) + return -ENODEV; + + cpu_data = policy->driver_data; + cpufreq_cpu_put(policy); ret = cppc_get_desired_perf(cpu, &desired_perf); diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c index bd1e1357cef8..c74dd1e01e0d 100644 --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -104,6 +104,9 @@ static const struct of_device_id allowlist[] __initconst = { */ static const struct of_device_id blocklist[] __initconst = { { .compatible = "allwinner,sun50i-h6", }, + { .compatible = "allwinner,sun50i-h616", }, + { .compatible = "allwinner,sun50i-h618", }, + { .compatible = "allwinner,sun50i-h700", }, { .compatible = "apple,arm-platform", }, @@ -156,6 +159,7 @@ static const struct of_device_id blocklist[] __initconst = { { .compatible = "qcom,sc7280", }, { .compatible = "qcom,sc8180x", }, { .compatible = "qcom,sc8280xp", }, + { .compatible = "qcom,sdm670", }, { .compatible = "qcom,sdm845", }, { .compatible = "qcom,sdx75", }, { .compatible = "qcom,sm6115", }, @@ -194,19 +198,18 @@ static const struct of_device_id blocklist[] __initconst = { static bool __init cpu0_node_has_opp_v2_prop(void) { - struct device_node *np = of_cpu_device_node_get(0); + struct device_node *np __free(device_node) = of_cpu_device_node_get(0); bool ret = false; if (of_property_present(np, "operating-points-v2")) ret = true; - of_node_put(np); return ret; } static int __init cpufreq_dt_platdev_init(void) { - struct device_node *np = of_find_node_by_path("/"); + struct device_node *np __free(device_node) = of_find_node_by_path("/"); const struct of_device_id *match; const void *data = NULL; @@ -222,11 +225,9 @@ static int __init cpufreq_dt_platdev_init(void) if (cpu0_node_has_opp_v2_prop() && !of_match_node(blocklist, np)) goto create_pdev; - of_node_put(np); return -ENODEV; create_pdev: - of_node_put(np); return PTR_ERR_OR_ZERO(platform_device_register_data(NULL, "cpufreq-dt", -1, data, sizeof(struct cpufreq_dt_platform_data))); diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c index 8bd6e5e8f121..907e22632fda 100644 --- a/drivers/cpufreq/cpufreq-dt.c +++ b/drivers/cpufreq/cpufreq-dt.c @@ -68,12 +68,9 @@ static int set_target(struct cpufreq_policy *policy, unsigned int index) */ static const char *find_supply_name(struct device *dev) { - struct device_node *np; + struct device_node *np __free(device_node) = of_node_get(dev->of_node); struct property *pp; int cpu = dev->id; - const char *name = NULL; - - np = of_node_get(dev->of_node); /* This must be valid for sure */ if (WARN_ON(!np)) @@ -82,22 +79,16 @@ static const char *find_supply_name(struct device *dev) /* Try "cpu0" for older DTs */ if (!cpu) { pp = of_find_property(np, "cpu0-supply", NULL); - if (pp) { - name = "cpu0"; - goto node_put; - } + if (pp) + return "cpu0"; } pp = of_find_property(np, "cpu-supply", NULL); - if (pp) { - name = "cpu"; - goto node_put; - } + if (pp) + return "cpu"; dev_dbg(dev, "no regulator for cpu%d\n", cpu); -node_put: - of_node_put(np); - return name; + return NULL; } static int cpufreq_init(struct cpufreq_policy *policy) @@ -208,7 +199,7 @@ static int dt_cpufreq_early_init(struct device *dev, int cpu) if (!priv) return -ENOMEM; - if (!alloc_cpumask_var(&priv->cpus, GFP_KERNEL)) + if (!zalloc_cpumask_var(&priv->cpus, GFP_KERNEL)) return -ENOMEM; cpumask_set_cpu(cpu, priv->cpus); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 44db4f59c4cc..a45aac17c20f 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -576,17 +576,26 @@ unsigned int cpufreq_policy_transition_delay_us(struct cpufreq_policy *policy) latency = policy->cpuinfo.transition_latency / NSEC_PER_USEC; if (latency) { + unsigned int max_delay_us = 2 * MSEC_PER_SEC; + + /* + * If the platform already has high transition_latency, use it + * as-is. + */ + if (latency > max_delay_us) + return latency; + /* - * For platforms that can change the frequency very fast (< 10 + * For platforms that can change the frequency very fast (< 2 * us), the above formula gives a decent transition delay. But * for platforms where transition_latency is in milliseconds, it * ends up giving unrealistic values. * - * Cap the default transition delay to 10 ms, which seems to be + * Cap the default transition delay to 2 ms, which seems to be * a reasonable amount of time after which we should reevaluate * the frequency. */ - return min(latency * LATENCY_MULTIPLIER, (unsigned int)10000); + return min(latency * LATENCY_MULTIPLIER, max_delay_us); } return LATENCY_MULTIPLIER; @@ -644,14 +653,16 @@ static ssize_t store_local_boost(struct cpufreq_policy *policy, if (policy->boost_enabled == enable) return count; + policy->boost_enabled = enable; + cpus_read_lock(); ret = cpufreq_driver->set_boost(policy, enable); cpus_read_unlock(); - if (ret) + if (ret) { + policy->boost_enabled = !policy->boost_enabled; return ret; - - policy->boost_enabled = enable; + } return count; } @@ -1419,6 +1430,9 @@ static int cpufreq_online(unsigned int cpu) goto out_free_policy; } + /* Let the per-policy boost flag mirror the cpufreq_driver boost during init */ + policy->boost_enabled = cpufreq_boost_enabled() && policy_has_boost_freq(policy); + /* * The initialization has succeeded and the policy is online. * If there is a problem with its frequency table, take it @@ -1571,7 +1585,8 @@ static int cpufreq_online(unsigned int cpu) if (cpufreq_driver->ready) cpufreq_driver->ready(policy); - if (cpufreq_thermal_control_enabled(cpufreq_driver)) + /* Register cpufreq cooling only for a new policy */ + if (new_policy && cpufreq_thermal_control_enabled(cpufreq_driver)) policy->cdev = of_cpufreq_cooling_register(policy); pr_debug("initialization complete\n"); @@ -1655,11 +1670,6 @@ static void __cpufreq_offline(unsigned int cpu, struct cpufreq_policy *policy) else policy->last_policy = policy->policy; - if (cpufreq_thermal_control_enabled(cpufreq_driver)) { - cpufreq_cooling_unregister(policy->cdev); - policy->cdev = NULL; - } - if (has_target()) cpufreq_exit_governor(policy); @@ -1669,10 +1679,13 @@ static void __cpufreq_offline(unsigned int cpu, struct cpufreq_policy *policy) */ if (cpufreq_driver->offline) { cpufreq_driver->offline(policy); - } else if (cpufreq_driver->exit) { - cpufreq_driver->exit(policy); - policy->freq_table = NULL; + return; } + + if (cpufreq_driver->exit) + cpufreq_driver->exit(policy); + + policy->freq_table = NULL; } static int cpufreq_offline(unsigned int cpu) @@ -1720,8 +1733,17 @@ static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif) return; } + /* + * Unregister cpufreq cooling once all the CPUs of the policy are + * removed. + */ + if (cpufreq_thermal_control_enabled(cpufreq_driver)) { + cpufreq_cooling_unregister(policy->cdev); + policy->cdev = NULL; + } + /* We did light-weight exit earlier, do full tear down now */ - if (cpufreq_driver->offline) + if (cpufreq_driver->offline && cpufreq_driver->exit) cpufreq_driver->exit(policy); up_write(&policy->rwsem); @@ -2563,6 +2585,40 @@ int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu) } EXPORT_SYMBOL(cpufreq_get_policy); +DEFINE_PER_CPU(unsigned long, cpufreq_pressure); + +/** + * cpufreq_update_pressure() - Update cpufreq pressure for CPUs + * @policy: cpufreq policy of the CPUs. + * + * Update the value of cpufreq pressure for all @cpus in the policy. + */ +static void cpufreq_update_pressure(struct cpufreq_policy *policy) +{ + unsigned long max_capacity, capped_freq, pressure; + u32 max_freq; + int cpu; + + cpu = cpumask_first(policy->related_cpus); + max_freq = arch_scale_freq_ref(cpu); + capped_freq = policy->max; + + /* + * Handle properly the boost frequencies, which should simply clean + * the cpufreq pressure value. + */ + if (max_freq <= capped_freq) { + pressure = 0; + } else { + max_capacity = arch_scale_cpu_capacity(cpu); + pressure = max_capacity - + mult_frac(max_capacity, capped_freq, max_freq); + } + + for_each_cpu(cpu, policy->related_cpus) + WRITE_ONCE(per_cpu(cpufreq_pressure, cpu), pressure); +} + /** * cpufreq_set_policy - Modify cpufreq policy parameters. * @policy: Policy object to modify. @@ -2618,6 +2674,8 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy, policy->max = __resolve_freq(policy, policy->max, CPUFREQ_RELATION_H); trace_cpu_frequency_limits(policy); + cpufreq_update_pressure(policy); + policy->cached_target_freq = UINT_MAX; pr_debug("new min and max freqs are %u - %u kHz\n", @@ -2755,11 +2813,12 @@ int cpufreq_boost_trigger_state(int state) cpus_read_lock(); for_each_active_policy(policy) { + policy->boost_enabled = state; ret = cpufreq_driver->set_boost(policy, state); - if (ret) + if (ret) { + policy->boost_enabled = !policy->boost_enabled; goto err_reset_state; - - policy->boost_enabled = state; + } } cpus_read_unlock(); diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c index c52d19d67557..a7c38b8b3e78 100644 --- a/drivers/cpufreq/cpufreq_ondemand.c +++ b/drivers/cpufreq/cpufreq_ondemand.c @@ -22,7 +22,6 @@ #define DEF_SAMPLING_DOWN_FACTOR (1) #define MAX_SAMPLING_DOWN_FACTOR (100000) #define MICRO_FREQUENCY_UP_THRESHOLD (95) -#define MICRO_FREQUENCY_MIN_SAMPLE_RATE (10000) #define MIN_FREQUENCY_UP_THRESHOLD (1) #define MAX_FREQUENCY_UP_THRESHOLD (100) diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c index c4d4643b6ca6..10e80d912b8d 100644 --- a/drivers/cpufreq/freq_table.c +++ b/drivers/cpufreq/freq_table.c @@ -40,7 +40,7 @@ int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy, cpufreq_for_each_valid_entry(pos, table) { freq = pos->frequency; - if (!cpufreq_boost_enabled() + if ((!cpufreq_boost_enabled() || !policy->boost_enabled) && (pos->flags & CPUFREQ_BOOST_FREQ)) continue; @@ -70,7 +70,7 @@ int cpufreq_frequency_table_verify(struct cpufreq_policy_data *policy, struct cpufreq_frequency_table *table) { struct cpufreq_frequency_table *pos; - unsigned int freq, next_larger = ~0; + unsigned int freq, prev_smaller = 0; bool found = false; pr_debug("request for verification of policy (%u - %u kHz) for cpu %u\n", @@ -86,12 +86,12 @@ int cpufreq_frequency_table_verify(struct cpufreq_policy_data *policy, break; } - if ((next_larger > freq) && (freq > policy->max)) - next_larger = freq; + if ((prev_smaller < freq) && (freq <= policy->max)) + prev_smaller = freq; } if (!found) { - policy->max = next_larger; + policy->max = prev_smaller; cpufreq_verify_within_cpu_limits(policy); } @@ -194,7 +194,7 @@ int cpufreq_table_index_unsorted(struct cpufreq_policy *policy, } if (optimal.driver_data > i) { if (suboptimal.driver_data > i) { - WARN(1, "Invalid frequency table: %d\n", policy->cpu); + WARN(1, "Invalid frequency table: %u\n", policy->cpu); return 0; } @@ -254,7 +254,7 @@ static ssize_t show_available_freqs(struct cpufreq_policy *policy, char *buf, if (show_boost ^ (pos->flags & CPUFREQ_BOOST_FREQ)) continue; - count += sprintf(&buf[count], "%d ", pos->frequency); + count += sprintf(&buf[count], "%u ", pos->frequency); } count += sprintf(&buf[count], "\n"); diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c index 33728c242f66..c20d3ecc5a81 100644 --- a/drivers/cpufreq/imx6q-cpufreq.c +++ b/drivers/cpufreq/imx6q-cpufreq.c @@ -14,6 +14,8 @@ #include <linux/pm_opp.h> #include <linux/platform_device.h> #include <linux/regulator/consumer.h> +#include <linux/mfd/syscon.h> +#include <linux/regmap.h> #define PU_SOC_VOLTAGE_NORMAL 1250000 #define PU_SOC_VOLTAGE_HIGH 1275000 @@ -225,8 +227,6 @@ static void imx6x_disable_freq_in_opp(struct device *dev, unsigned long freq) static int imx6q_opp_check_speed_grading(struct device *dev) { - struct device_node *np; - void __iomem *base; u32 val; int ret; @@ -235,16 +235,11 @@ static int imx6q_opp_check_speed_grading(struct device *dev) if (ret) return ret; } else { - np = of_find_compatible_node(NULL, NULL, "fsl,imx6q-ocotp"); - if (!np) - return -ENOENT; + struct regmap *ocotp; - base = of_iomap(np, 0); - of_node_put(np); - if (!base) { - dev_err(dev, "failed to map ocotp\n"); - return -EFAULT; - } + ocotp = syscon_regmap_lookup_by_compatible("fsl,imx6q-ocotp"); + if (IS_ERR(ocotp)) + return -ENOENT; /* * SPEED_GRADING[1:0] defines the max speed of ARM: @@ -254,8 +249,7 @@ static int imx6q_opp_check_speed_grading(struct device *dev) * 2b'00: 792000000Hz; * We need to set the max speed of ARM according to fuse map. */ - val = readl_relaxed(base + OCOTP_CFG3); - iounmap(base); + regmap_read(ocotp, OCOTP_CFG3, &val); } val >>= OCOTP_CFG3_SPEED_SHIFT; @@ -290,25 +284,16 @@ static int imx6ul_opp_check_speed_grading(struct device *dev) if (ret) return ret; } else { - struct device_node *np; - void __iomem *base; - - np = of_find_compatible_node(NULL, NULL, "fsl,imx6ul-ocotp"); - if (!np) - np = of_find_compatible_node(NULL, NULL, - "fsl,imx6ull-ocotp"); - if (!np) - return -ENOENT; + struct regmap *ocotp; - base = of_iomap(np, 0); - of_node_put(np); - if (!base) { - dev_err(dev, "failed to map ocotp\n"); - return -EFAULT; - } + ocotp = syscon_regmap_lookup_by_compatible("fsl,imx6ul-ocotp"); + if (IS_ERR(ocotp)) + ocotp = syscon_regmap_lookup_by_compatible("fsl,imx6ull-ocotp"); + + if (IS_ERR(ocotp)) + return -ENOENT; - val = readl_relaxed(base + OCOTP_CFG3); - iounmap(base); + regmap_read(ocotp, OCOTP_CFG3, &val); } /* diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 79619227ea51..4b986c044741 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -25,6 +25,7 @@ #include <linux/acpi.h> #include <linux/vmalloc.h> #include <linux/pm_qos.h> +#include <linux/bitfield.h> #include <trace/events/power.h> #include <asm/cpu.h> @@ -172,7 +173,6 @@ struct vid_data { * based on the MSR_IA32_MISC_ENABLE value and whether or * not the maximum reported turbo P-state is different from * the maximum reported non-turbo one. - * @turbo_disabled_mf: The @turbo_disabled value reflected by cpuinfo.max_freq. * @min_perf_pct: Minimum capacity limit in percent of the maximum turbo * P-state capacity. * @max_perf_pct: Maximum capacity limit in percent of the maximum turbo @@ -181,7 +181,6 @@ struct vid_data { struct global_params { bool no_turbo; bool turbo_disabled; - bool turbo_disabled_mf; int max_perf_pct; int min_perf_pct; }; @@ -201,8 +200,6 @@ struct global_params { * @prev_aperf: Last APERF value read from APERF MSR * @prev_mperf: Last MPERF value read from MPERF MSR * @prev_tsc: Last timestamp counter (TSC) value - * @prev_cummulative_iowait: IO Wait time difference from last and - * current sample * @sample: Storage for storing last Sample data * @min_perf_ratio: Minimum capacity in terms of PERF or HWP ratios * @max_perf_ratio: Maximum capacity in terms of PERF or HWP ratios @@ -214,7 +211,7 @@ struct global_params { * @epp_policy: Last saved policy used to set EPP/EPB * @epp_default: Power on default HWP energy performance * preference/bias - * @epp_cached Cached HWP energy-performance preference value + * @epp_cached: Cached HWP energy-performance preference value * @hwp_req_cached: Cached value of the last HWP Request MSR * @hwp_cap_cached: Cached value of the last HWP Capabilities MSR * @last_io_update: Last time when IO wake flag was set @@ -241,7 +238,6 @@ struct cpudata { u64 prev_aperf; u64 prev_mperf; u64 prev_tsc; - u64 prev_cummulative_iowait; struct sample sample; int32_t min_perf_ratio; int32_t max_perf_ratio; @@ -294,11 +290,11 @@ struct pstate_funcs { static struct pstate_funcs pstate_funcs __read_mostly; -static int hwp_active __read_mostly; -static int hwp_mode_bdw __read_mostly; -static bool per_cpu_limits __read_mostly; +static bool hwp_active __ro_after_init; +static int hwp_mode_bdw __ro_after_init; +static bool per_cpu_limits __ro_after_init; +static bool hwp_forced __ro_after_init; static bool hwp_boost __read_mostly; -static bool hwp_forced __read_mostly; static struct cpufreq_driver *intel_pstate_driver __read_mostly; @@ -596,12 +592,13 @@ static void intel_pstate_hybrid_hwp_adjust(struct cpudata *cpu) cpu->pstate.min_pstate = intel_pstate_freq_to_hwp(cpu, freq); } -static inline void update_turbo_state(void) +static bool turbo_is_disabled(void) { u64 misc_en; rdmsrl(MSR_IA32_MISC_ENABLE, misc_en); - global.turbo_disabled = misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE; + + return !!(misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE); } static int min_perf_pct_min(void) @@ -1156,12 +1153,15 @@ static void intel_pstate_update_policies(void) static void __intel_pstate_update_max_freq(struct cpudata *cpudata, struct cpufreq_policy *policy) { - policy->cpuinfo.max_freq = global.turbo_disabled_mf ? + intel_pstate_get_hwp_cap(cpudata); + + policy->cpuinfo.max_freq = READ_ONCE(global.no_turbo) ? cpudata->pstate.max_freq : cpudata->pstate.turbo_freq; + refresh_frequency_limits(policy); } -static void intel_pstate_update_max_freq(unsigned int cpu) +static void intel_pstate_update_limits(unsigned int cpu) { struct cpufreq_policy *policy = cpufreq_cpu_acquire(cpu); @@ -1173,25 +1173,12 @@ static void intel_pstate_update_max_freq(unsigned int cpu) cpufreq_cpu_release(policy); } -static void intel_pstate_update_limits(unsigned int cpu) +static void intel_pstate_update_limits_for_all(void) { - mutex_lock(&intel_pstate_driver_lock); - - update_turbo_state(); - /* - * If turbo has been turned on or off globally, policy limits for - * all CPUs need to be updated to reflect that. - */ - if (global.turbo_disabled_mf != global.turbo_disabled) { - global.turbo_disabled_mf = global.turbo_disabled; - arch_set_max_freq_ratio(global.turbo_disabled); - for_each_possible_cpu(cpu) - intel_pstate_update_max_freq(cpu); - } else { - cpufreq_update_policy(cpu); - } + int cpu; - mutex_unlock(&intel_pstate_driver_lock); + for_each_possible_cpu(cpu) + intel_pstate_update_limits(cpu); } /************************** sysfs begin ************************/ @@ -1289,11 +1276,7 @@ static ssize_t show_no_turbo(struct kobject *kobj, return -EAGAIN; } - update_turbo_state(); - if (global.turbo_disabled) - ret = sprintf(buf, "%u\n", global.turbo_disabled); - else - ret = sprintf(buf, "%u\n", global.no_turbo); + ret = sprintf(buf, "%u\n", global.no_turbo); mutex_unlock(&intel_pstate_driver_lock); @@ -1304,32 +1287,34 @@ static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b, const char *buf, size_t count) { unsigned int input; - int ret; + bool no_turbo; - ret = sscanf(buf, "%u", &input); - if (ret != 1) + if (sscanf(buf, "%u", &input) != 1) return -EINVAL; mutex_lock(&intel_pstate_driver_lock); if (!intel_pstate_driver) { - mutex_unlock(&intel_pstate_driver_lock); - return -EAGAIN; + count = -EAGAIN; + goto unlock_driver; } - mutex_lock(&intel_pstate_limits_lock); + no_turbo = !!clamp_t(int, input, 0, 1); + + if (no_turbo == global.no_turbo) + goto unlock_driver; - update_turbo_state(); if (global.turbo_disabled) { pr_notice_once("Turbo disabled by BIOS or unavailable on processor\n"); - mutex_unlock(&intel_pstate_limits_lock); - mutex_unlock(&intel_pstate_driver_lock); - return -EPERM; + count = -EPERM; + goto unlock_driver; } - global.no_turbo = clamp_t(int, input, 0, 1); + WRITE_ONCE(global.no_turbo, no_turbo); - if (global.no_turbo) { + mutex_lock(&intel_pstate_limits_lock); + + if (no_turbo) { struct cpudata *cpu = all_cpu_data[0]; int pct = cpu->pstate.max_pstate * 100 / cpu->pstate.turbo_pstate; @@ -1340,9 +1325,10 @@ static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b, mutex_unlock(&intel_pstate_limits_lock); - intel_pstate_update_policies(); - arch_set_max_freq_ratio(global.no_turbo); + intel_pstate_update_limits_for_all(); + arch_set_max_freq_ratio(no_turbo); +unlock_driver: mutex_unlock(&intel_pstate_driver_lock); return count; @@ -1623,7 +1609,6 @@ static void intel_pstate_notify_work(struct work_struct *work) struct cpufreq_policy *policy = cpufreq_cpu_acquire(cpudata->cpu); if (policy) { - intel_pstate_get_hwp_cap(cpudata); __intel_pstate_update_max_freq(cpudata, policy); cpufreq_cpu_release(policy); @@ -1638,11 +1623,10 @@ static cpumask_t hwp_intr_enable_mask; void notify_hwp_interrupt(void) { unsigned int this_cpu = smp_processor_id(); - struct cpudata *cpudata; unsigned long flags; u64 value; - if (!READ_ONCE(hwp_active) || !boot_cpu_has(X86_FEATURE_HWP_NOTIFY)) + if (!hwp_active || !boot_cpu_has(X86_FEATURE_HWP_NOTIFY)) return; rdmsrl_safe(MSR_HWP_STATUS, &value); @@ -1654,24 +1638,8 @@ void notify_hwp_interrupt(void) if (!cpumask_test_cpu(this_cpu, &hwp_intr_enable_mask)) goto ack_intr; - /* - * Currently we never free all_cpu_data. And we can't reach here - * without this allocated. But for safety for future changes, added - * check. - */ - if (unlikely(!READ_ONCE(all_cpu_data))) - goto ack_intr; - - /* - * The free is done during cleanup, when cpufreq registry is failed. - * We wouldn't be here if it fails on init or switch status. But for - * future changes, added check. - */ - cpudata = READ_ONCE(all_cpu_data[this_cpu]); - if (unlikely(!cpudata)) - goto ack_intr; - - schedule_delayed_work(&cpudata->hwp_notify_work, msecs_to_jiffies(10)); + schedule_delayed_work(&all_cpu_data[this_cpu]->hwp_notify_work, + msecs_to_jiffies(10)); spin_unlock_irqrestore(&hwp_notify_lock, flags); @@ -1684,7 +1652,7 @@ ack_intr: static void intel_pstate_disable_hwp_interrupt(struct cpudata *cpudata) { - unsigned long flags; + bool cancel_work; if (!boot_cpu_has(X86_FEATURE_HWP_NOTIFY)) return; @@ -1692,22 +1660,22 @@ static void intel_pstate_disable_hwp_interrupt(struct cpudata *cpudata) /* wrmsrl_on_cpu has to be outside spinlock as this can result in IPC */ wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x00); - spin_lock_irqsave(&hwp_notify_lock, flags); - if (cpumask_test_and_clear_cpu(cpudata->cpu, &hwp_intr_enable_mask)) - cancel_delayed_work(&cpudata->hwp_notify_work); - spin_unlock_irqrestore(&hwp_notify_lock, flags); + spin_lock_irq(&hwp_notify_lock); + cancel_work = cpumask_test_and_clear_cpu(cpudata->cpu, &hwp_intr_enable_mask); + spin_unlock_irq(&hwp_notify_lock); + + if (cancel_work) + cancel_delayed_work_sync(&cpudata->hwp_notify_work); } static void intel_pstate_enable_hwp_interrupt(struct cpudata *cpudata) { /* Enable HWP notification interrupt for guaranteed performance change */ if (boot_cpu_has(X86_FEATURE_HWP_NOTIFY)) { - unsigned long flags; - - spin_lock_irqsave(&hwp_notify_lock, flags); + spin_lock_irq(&hwp_notify_lock); INIT_DELAYED_WORK(&cpudata->hwp_notify_work, intel_pstate_notify_work); cpumask_set_cpu(cpudata->cpu, &hwp_intr_enable_mask); - spin_unlock_irqrestore(&hwp_notify_lock, flags); + spin_unlock_irq(&hwp_notify_lock); /* wrmsrl_on_cpu has to be outside spinlock as this can result in IPC */ wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x01); @@ -1793,7 +1761,7 @@ static u64 atom_get_val(struct cpudata *cpudata, int pstate) u32 vid; val = (u64)pstate << 8; - if (global.no_turbo && !global.turbo_disabled) + if (READ_ONCE(global.no_turbo) && !global.turbo_disabled) val |= (u64)1 << 32; vid_fp = cpudata->vid.min + mul_fp( @@ -1958,7 +1926,7 @@ static u64 core_get_val(struct cpudata *cpudata, int pstate) u64 val; val = (u64)pstate << 8; - if (global.no_turbo && !global.turbo_disabled) + if (READ_ONCE(global.no_turbo) && !global.turbo_disabled) val |= (u64)1 << 32; return val; @@ -2031,14 +1999,6 @@ static void intel_pstate_set_min_pstate(struct cpudata *cpu) intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate); } -static void intel_pstate_max_within_limits(struct cpudata *cpu) -{ - int pstate = max(cpu->pstate.min_pstate, cpu->max_perf_ratio); - - update_turbo_state(); - intel_pstate_set_pstate(cpu, pstate); -} - static void intel_pstate_get_cpu_pstates(struct cpudata *cpu) { int perf_ctl_max_phys = pstate_funcs.get_max_physical(cpu->cpu); @@ -2264,7 +2224,7 @@ static inline int32_t get_target_pstate(struct cpudata *cpu) sample->busy_scaled = busy_frac * 100; - target = global.no_turbo || global.turbo_disabled ? + target = READ_ONCE(global.no_turbo) ? cpu->pstate.max_pstate : cpu->pstate.turbo_pstate; target += target >> 2; target = mul_fp(target, busy_frac); @@ -2308,8 +2268,6 @@ static void intel_pstate_adjust_pstate(struct cpudata *cpu) struct sample *sample; int target_pstate; - update_turbo_state(); - target_pstate = get_target_pstate(cpu); target_pstate = intel_pstate_prepare_request(cpu, target_pstate); trace_cpu_frequency(target_pstate * cpu->pstate.scaling, cpu->cpu); @@ -2439,6 +2397,7 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = { }; MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids); +#ifdef CONFIG_ACPI static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] __initconst = { X86_MATCH(BROADWELL_D, core_funcs), X86_MATCH(BROADWELL_X, core_funcs), @@ -2447,6 +2406,7 @@ static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] __initconst = { X86_MATCH(SAPPHIRERAPIDS_X, core_funcs), {} }; +#endif static const struct x86_cpu_id intel_pstate_cpu_ee_disable_ids[] = { X86_MATCH(KABYLAKE, core_funcs), @@ -2528,7 +2488,7 @@ static void intel_pstate_clear_update_util_hook(unsigned int cpu) static int intel_pstate_get_max_freq(struct cpudata *cpu) { - return global.turbo_disabled || global.no_turbo ? + return READ_ONCE(global.no_turbo) ? cpu->pstate.max_freq : cpu->pstate.turbo_freq; } @@ -2613,12 +2573,14 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) intel_pstate_update_perf_limits(cpu, policy->min, policy->max); if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) { + int pstate = max(cpu->pstate.min_pstate, cpu->max_perf_ratio); + /* * NOHZ_FULL CPUs need this as the governor callback may not * be invoked on them. */ intel_pstate_clear_update_util_hook(policy->cpu); - intel_pstate_max_within_limits(cpu); + intel_pstate_set_pstate(cpu, pstate); } else { intel_pstate_set_update_util_hook(policy->cpu); } @@ -2661,10 +2623,9 @@ static void intel_pstate_verify_cpu_policy(struct cpudata *cpu, { int max_freq; - update_turbo_state(); if (hwp_active) { intel_pstate_get_hwp_cap(cpu); - max_freq = global.no_turbo || global.turbo_disabled ? + max_freq = READ_ONCE(global.no_turbo) ? cpu->pstate.max_freq : cpu->pstate.turbo_freq; } else { max_freq = intel_pstate_get_max_freq(cpu); @@ -2758,9 +2719,7 @@ static int __intel_pstate_cpu_init(struct cpufreq_policy *policy) /* cpuinfo and default policy values */ policy->cpuinfo.min_freq = cpu->pstate.min_freq; - update_turbo_state(); - global.turbo_disabled_mf = global.turbo_disabled; - policy->cpuinfo.max_freq = global.turbo_disabled ? + policy->cpuinfo.max_freq = READ_ONCE(global.no_turbo) ? cpu->pstate.max_freq : cpu->pstate.turbo_freq; policy->min = policy->cpuinfo.min_freq; @@ -2925,8 +2884,6 @@ static int intel_cpufreq_target(struct cpufreq_policy *policy, struct cpufreq_freqs freqs; int target_pstate; - update_turbo_state(); - freqs.old = policy->cur; freqs.new = target_freq; @@ -2948,8 +2905,6 @@ static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy, struct cpudata *cpu = all_cpu_data[policy->cpu]; int target_pstate; - update_turbo_state(); - target_pstate = intel_pstate_freq_to_hwp(cpu, target_freq); target_pstate = intel_cpufreq_update_pstate(policy, target_pstate, true); @@ -2967,9 +2922,9 @@ static void intel_cpufreq_adjust_perf(unsigned int cpunum, int old_pstate = cpu->pstate.current_pstate; int cap_pstate, min_pstate, max_pstate, target_pstate; - update_turbo_state(); - cap_pstate = global.turbo_disabled ? HWP_GUARANTEED_PERF(hwp_cap) : - HWP_HIGHEST_PERF(hwp_cap); + cap_pstate = READ_ONCE(global.no_turbo) ? + HWP_GUARANTEED_PERF(hwp_cap) : + HWP_HIGHEST_PERF(hwp_cap); /* Optimization: Avoid unnecessary divisions. */ @@ -3137,10 +3092,8 @@ static void intel_pstate_driver_cleanup(void) if (intel_pstate_driver == &intel_pstate) intel_pstate_clear_update_util_hook(cpu); - spin_lock(&hwp_notify_lock); kfree(all_cpu_data[cpu]); WRITE_ONCE(all_cpu_data[cpu], NULL); - spin_unlock(&hwp_notify_lock); } } cpus_read_unlock(); @@ -3157,6 +3110,10 @@ static int intel_pstate_register_driver(struct cpufreq_driver *driver) memset(&global, 0, sizeof(global)); global.max_perf_pct = 100; + global.turbo_disabled = turbo_is_disabled(); + global.no_turbo = global.turbo_disabled; + + arch_set_max_freq_ratio(global.turbo_disabled); intel_pstate_driver = driver; ret = cpufreq_register_driver(intel_pstate_driver); @@ -3407,14 +3364,31 @@ static bool intel_pstate_hwp_is_enabled(void) return !!(value & 0x1); } -static const struct x86_cpu_id intel_epp_balance_perf[] = { +#define POWERSAVE_MASK GENMASK(7, 0) +#define BALANCE_POWER_MASK GENMASK(15, 8) +#define BALANCE_PERFORMANCE_MASK GENMASK(23, 16) +#define PERFORMANCE_MASK GENMASK(31, 24) + +#define HWP_SET_EPP_VALUES(powersave, balance_power, balance_perf, performance) \ + (FIELD_PREP_CONST(POWERSAVE_MASK, powersave) |\ + FIELD_PREP_CONST(BALANCE_POWER_MASK, balance_power) |\ + FIELD_PREP_CONST(BALANCE_PERFORMANCE_MASK, balance_perf) |\ + FIELD_PREP_CONST(PERFORMANCE_MASK, performance)) + +#define HWP_SET_DEF_BALANCE_PERF_EPP(balance_perf) \ + (HWP_SET_EPP_VALUES(HWP_EPP_POWERSAVE, HWP_EPP_BALANCE_POWERSAVE,\ + balance_perf, HWP_EPP_PERFORMANCE)) + +static const struct x86_cpu_id intel_epp_default[] = { /* * Set EPP value as 102, this is the max suggested EPP * which can result in one core turbo frequency for * AlderLake Mobile CPUs. */ - X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, 102), - X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, 32), + X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, HWP_SET_DEF_BALANCE_PERF_EPP(102)), + X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, HWP_SET_DEF_BALANCE_PERF_EPP(32)), + X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, HWP_SET_EPP_VALUES(HWP_EPP_POWERSAVE, + HWP_EPP_BALANCE_POWERSAVE, 115, 16)), {} }; @@ -3451,7 +3425,7 @@ static int __init intel_pstate_init(void) * deal with it. */ if ((!no_hwp && boot_cpu_has(X86_FEATURE_HWP_EPP)) || hwp_forced) { - WRITE_ONCE(hwp_active, 1); + hwp_active = true; hwp_mode_bdw = id->driver_data; intel_pstate.attr = hwp_cpufreq_attrs; intel_cpufreq.attr = hwp_cpufreq_attrs; @@ -3512,11 +3486,24 @@ hwp_cpu_matched: intel_pstate_sysfs_expose_params(); if (hwp_active) { - const struct x86_cpu_id *id = x86_match_cpu(intel_epp_balance_perf); + const struct x86_cpu_id *id = x86_match_cpu(intel_epp_default); const struct x86_cpu_id *hybrid_id = x86_match_cpu(intel_hybrid_scaling_factor); - if (id) - epp_values[EPP_INDEX_BALANCE_PERFORMANCE] = id->driver_data; + if (id) { + epp_values[EPP_INDEX_POWERSAVE] = + FIELD_GET(POWERSAVE_MASK, id->driver_data); + epp_values[EPP_INDEX_BALANCE_POWERSAVE] = + FIELD_GET(BALANCE_POWER_MASK, id->driver_data); + epp_values[EPP_INDEX_BALANCE_PERFORMANCE] = + FIELD_GET(BALANCE_PERFORMANCE_MASK, id->driver_data); + epp_values[EPP_INDEX_PERFORMANCE] = + FIELD_GET(PERFORMANCE_MASK, id->driver_data); + pr_debug("Updated EPPs powersave:%x balanced power:%x balanced perf:%x performance:%x\n", + epp_values[EPP_INDEX_POWERSAVE], + epp_values[EPP_INDEX_BALANCE_POWERSAVE], + epp_values[EPP_INDEX_BALANCE_PERFORMANCE], + epp_values[EPP_INDEX_PERFORMANCE]); + } if (hybrid_id) { hybrid_scaling_factor = hybrid_id->driver_data; diff --git a/drivers/cpufreq/mediatek-cpufreq-hw.c b/drivers/cpufreq/mediatek-cpufreq-hw.c index d46afb3c0092..8d097dcddda4 100644 --- a/drivers/cpufreq/mediatek-cpufreq-hw.c +++ b/drivers/cpufreq/mediatek-cpufreq-hw.c @@ -13,6 +13,7 @@ #include <linux/of.h> #include <linux/of_platform.h> #include <linux/platform_device.h> +#include <linux/regulator/consumer.h> #include <linux/slab.h> #define LUT_MAX_ENTRIES 32U @@ -300,7 +301,23 @@ static struct cpufreq_driver cpufreq_mtk_hw_driver = { static int mtk_cpufreq_hw_driver_probe(struct platform_device *pdev) { const void *data; - int ret; + int ret, cpu; + struct device *cpu_dev; + struct regulator *cpu_reg; + + /* Make sure that all CPU supplies are available before proceeding. */ + for_each_possible_cpu(cpu) { + cpu_dev = get_cpu_device(cpu); + if (!cpu_dev) + return dev_err_probe(&pdev->dev, -EPROBE_DEFER, + "Failed to get cpu%d device\n", cpu); + + cpu_reg = devm_regulator_get(cpu_dev, "cpu"); + if (IS_ERR(cpu_reg)) + return dev_err_probe(&pdev->dev, PTR_ERR(cpu_reg), + "CPU%d regulator get failed\n", cpu); + } + data = of_device_get_match_data(&pdev->dev); if (!data) diff --git a/drivers/cpufreq/mediatek-cpufreq.c b/drivers/cpufreq/mediatek-cpufreq.c index a0a61919bc4c..518606adf14e 100644 --- a/drivers/cpufreq/mediatek-cpufreq.c +++ b/drivers/cpufreq/mediatek-cpufreq.c @@ -707,6 +707,15 @@ static const struct mtk_cpufreq_platform_data mt7623_platform_data = { .ccifreq_supported = false, }; +static const struct mtk_cpufreq_platform_data mt7988_platform_data = { + .min_volt_shift = 100000, + .max_volt_shift = 200000, + .proc_max_volt = 900000, + .sram_min_volt = 0, + .sram_max_volt = 1150000, + .ccifreq_supported = true, +}; + static const struct mtk_cpufreq_platform_data mt8183_platform_data = { .min_volt_shift = 100000, .max_volt_shift = 200000, @@ -740,6 +749,7 @@ static const struct of_device_id mtk_cpufreq_machines[] __initconst = { { .compatible = "mediatek,mt2712", .data = &mt2701_platform_data }, { .compatible = "mediatek,mt7622", .data = &mt7622_platform_data }, { .compatible = "mediatek,mt7623", .data = &mt7623_platform_data }, + { .compatible = "mediatek,mt7988a", .data = &mt7988_platform_data }, { .compatible = "mediatek,mt8167", .data = &mt8516_platform_data }, { .compatible = "mediatek,mt817x", .data = &mt2701_platform_data }, { .compatible = "mediatek,mt8173", .data = &mt2701_platform_data }, diff --git a/drivers/cpufreq/pmac32-cpufreq.c b/drivers/cpufreq/pmac32-cpufreq.c index df3567c1e93b..6c9f0888a2a7 100644 --- a/drivers/cpufreq/pmac32-cpufreq.c +++ b/drivers/cpufreq/pmac32-cpufreq.c @@ -120,9 +120,9 @@ static int cpu_750fx_cpu_speed(int low_speed) /* tweak L2 for high voltage */ if (has_cpu_l2lve) { - hid2 = mfspr(SPRN_HID2); + hid2 = mfspr(SPRN_HID2_750FX); hid2 &= ~0x2000; - mtspr(SPRN_HID2, hid2); + mtspr(SPRN_HID2_750FX, hid2); } } #ifdef CONFIG_PPC_BOOK3S_32 @@ -131,9 +131,9 @@ static int cpu_750fx_cpu_speed(int low_speed) if (low_speed == 1) { /* tweak L2 for low voltage */ if (has_cpu_l2lve) { - hid2 = mfspr(SPRN_HID2); + hid2 = mfspr(SPRN_HID2_750FX); hid2 |= 0x2000; - mtspr(SPRN_HID2, hid2); + mtspr(SPRN_HID2_750FX, hid2); } /* ramping down, set voltage last */ diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c index 70b0f21968a0..ec8df5496a0c 100644 --- a/drivers/cpufreq/qcom-cpufreq-hw.c +++ b/drivers/cpufreq/qcom-cpufreq-hw.c @@ -347,8 +347,8 @@ static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data) throttled_freq = freq_hz / HZ_PER_KHZ; - /* Update thermal pressure (the boost frequencies are accepted) */ - arch_update_thermal_pressure(policy->related_cpus, throttled_freq); + /* Update HW pressure (the boost frequencies are accepted) */ + arch_update_hw_pressure(policy->related_cpus, throttled_freq); /* * In the unlikely case policy is unregistered do not enable diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c index 4ee23f4ebf4a..3b4f6bfb2f4c 100644 --- a/drivers/cpufreq/scmi-cpufreq.c +++ b/drivers/cpufreq/scmi-cpufreq.c @@ -30,6 +30,7 @@ struct scmi_data { static struct scmi_protocol_handle *ph; static const struct scmi_perf_proto_ops *perf_ops; +static struct cpufreq_driver scmi_cpufreq_driver; static unsigned int scmi_cpufreq_get_rate(unsigned int cpu) { @@ -144,6 +145,35 @@ scmi_get_cpu_power(struct device *cpu_dev, unsigned long *power, return 0; } +static int +scmi_get_rate_limit(u32 domain, bool has_fast_switch) +{ + int ret, rate_limit; + + if (has_fast_switch) { + /* + * Fast channels are used whenever available, + * so use their rate_limit value if populated. + */ + ret = perf_ops->fast_switch_rate_limit(ph, domain, + &rate_limit); + if (!ret && rate_limit) + return rate_limit; + } + + ret = perf_ops->rate_limit_get(ph, domain, &rate_limit); + if (ret) + return 0; + + return rate_limit; +} + +static struct freq_attr *scmi_cpufreq_hw_attr[] = { + &cpufreq_freq_attr_scaling_available_freqs, + NULL, + NULL, +}; + static int scmi_cpufreq_init(struct cpufreq_policy *policy) { int ret, nr_opp, domain; @@ -250,6 +280,20 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy) policy->fast_switch_possible = perf_ops->fast_switch_possible(ph, domain); + policy->transition_delay_us = + scmi_get_rate_limit(domain, policy->fast_switch_possible); + + if (policy_has_boost_freq(policy)) { + ret = cpufreq_enable_boost_support(); + if (ret) { + dev_warn(cpu_dev, "failed to enable boost: %d\n", ret); + goto out_free_opp; + } else { + scmi_cpufreq_hw_attr[1] = &cpufreq_freq_attr_scaling_boost_freqs; + scmi_cpufreq_driver.boost_enabled = true; + } + } + return 0; out_free_opp: @@ -308,7 +352,7 @@ static struct cpufreq_driver scmi_cpufreq_driver = { CPUFREQ_NEED_INITIAL_FREQ_CHECK | CPUFREQ_IS_COOLING_DEV, .verify = cpufreq_generic_frequency_table_verify, - .attr = cpufreq_generic_attr, + .attr = scmi_cpufreq_hw_attr, .target_index = scmi_cpufreq_set_target, .fast_switch = scmi_cpufreq_fast_switch, .get = scmi_cpufreq_get_rate, diff --git a/drivers/cpufreq/sun50i-cpufreq-nvmem.c b/drivers/cpufreq/sun50i-cpufreq-nvmem.c index 32a9c88f8ff6..0b882765cd66 100644 --- a/drivers/cpufreq/sun50i-cpufreq-nvmem.c +++ b/drivers/cpufreq/sun50i-cpufreq-nvmem.c @@ -10,6 +10,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/arm-smccc.h> #include <linux/cpu.h> #include <linux/module.h> #include <linux/nvmem-consumer.h> @@ -18,26 +19,155 @@ #include <linux/pm_opp.h> #include <linux/slab.h> -#define MAX_NAME_LEN 7 - #define NVMEM_MASK 0x7 #define NVMEM_SHIFT 5 static struct platform_device *cpufreq_dt_pdev, *sun50i_cpufreq_pdev; +struct sunxi_cpufreq_data { + u32 (*efuse_xlate)(u32 speedbin); +}; + +static u32 sun50i_h6_efuse_xlate(u32 speedbin) +{ + u32 efuse_value; + + efuse_value = (speedbin >> NVMEM_SHIFT) & NVMEM_MASK; + + /* + * We treat unexpected efuse values as if the SoC was from + * the slowest bin. Expected efuse values are 1-3, slowest + * to fastest. + */ + if (efuse_value >= 1 && efuse_value <= 3) + return efuse_value - 1; + else + return 0; +} + +static int get_soc_id_revision(void) +{ +#ifdef CONFIG_HAVE_ARM_SMCCC_DISCOVERY + return arm_smccc_get_soc_id_revision(); +#else + return SMCCC_RET_NOT_SUPPORTED; +#endif +} + +/* + * Judging by the OPP tables in the vendor BSP, the quality order of the + * returned speedbin index is 4 -> 0/2 -> 3 -> 1, from worst to best. + * 0 and 2 seem identical from the OPP tables' point of view. + */ +static u32 sun50i_h616_efuse_xlate(u32 speedbin) +{ + int ver_bits = get_soc_id_revision(); + u32 value = 0; + + switch (speedbin & 0xffff) { + case 0x2000: + value = 0; + break; + case 0x2400: + case 0x7400: + case 0x2c00: + case 0x7c00: + if (ver_bits != SMCCC_RET_NOT_SUPPORTED && ver_bits <= 1) { + /* ic version A/B */ + value = 1; + } else { + /* ic version C and later version */ + value = 2; + } + break; + case 0x5000: + case 0x5400: + case 0x6000: + value = 3; + break; + case 0x5c00: + value = 4; + break; + case 0x5d00: + value = 0; + break; + default: + pr_warn("sun50i-cpufreq-nvmem: unknown speed bin 0x%x, using default bin 0\n", + speedbin & 0xffff); + value = 0; + break; + } + + return value; +} + +static struct sunxi_cpufreq_data sun50i_h6_cpufreq_data = { + .efuse_xlate = sun50i_h6_efuse_xlate, +}; + +static struct sunxi_cpufreq_data sun50i_h616_cpufreq_data = { + .efuse_xlate = sun50i_h616_efuse_xlate, +}; + +static const struct of_device_id cpu_opp_match_list[] = { + { .compatible = "allwinner,sun50i-h6-operating-points", + .data = &sun50i_h6_cpufreq_data, + }, + { .compatible = "allwinner,sun50i-h616-operating-points", + .data = &sun50i_h616_cpufreq_data, + }, + {} +}; + +/** + * dt_has_supported_hw() - Check if any OPPs use opp-supported-hw + * + * If we ask the cpufreq framework to use the opp-supported-hw feature, it + * will ignore every OPP node without that DT property. If none of the OPPs + * have it, the driver will fail probing, due to the lack of OPPs. + * + * Returns true if we have at least one OPP with the opp-supported-hw property. + */ +static bool dt_has_supported_hw(void) +{ + bool has_opp_supported_hw = false; + struct device_node *np, *opp; + struct device *cpu_dev; + + cpu_dev = get_cpu_device(0); + if (!cpu_dev) + return false; + + np = dev_pm_opp_of_get_opp_desc_node(cpu_dev); + if (!np) + return false; + + for_each_child_of_node(np, opp) { + if (of_find_property(opp, "opp-supported-hw", NULL)) { + has_opp_supported_hw = true; + break; + } + } + + of_node_put(np); + + return has_opp_supported_hw; +} + /** * sun50i_cpufreq_get_efuse() - Determine speed grade from efuse value - * @versions: Set to the value parsed from efuse * - * Returns 0 if success. + * Returns non-negative speed bin index on success, a negative error + * value otherwise. */ -static int sun50i_cpufreq_get_efuse(u32 *versions) +static int sun50i_cpufreq_get_efuse(void) { + const struct sunxi_cpufreq_data *opp_data; struct nvmem_cell *speedbin_nvmem; + const struct of_device_id *match; struct device_node *np; struct device *cpu_dev; - u32 *speedbin, efuse_value; - size_t len; + u32 *speedbin; int ret; cpu_dev = get_cpu_device(0); @@ -48,12 +178,12 @@ static int sun50i_cpufreq_get_efuse(u32 *versions) if (!np) return -ENOENT; - ret = of_device_is_compatible(np, - "allwinner,sun50i-h6-operating-points"); - if (!ret) { + match = of_match_node(cpu_opp_match_list, np); + if (!match) { of_node_put(np); return -ENOENT; } + opp_data = match->data; speedbin_nvmem = of_nvmem_cell_get(np, NULL); of_node_put(np); @@ -61,33 +191,25 @@ static int sun50i_cpufreq_get_efuse(u32 *versions) return dev_err_probe(cpu_dev, PTR_ERR(speedbin_nvmem), "Could not get nvmem cell\n"); - speedbin = nvmem_cell_read(speedbin_nvmem, &len); + speedbin = nvmem_cell_read(speedbin_nvmem, NULL); nvmem_cell_put(speedbin_nvmem); if (IS_ERR(speedbin)) return PTR_ERR(speedbin); - efuse_value = (*speedbin >> NVMEM_SHIFT) & NVMEM_MASK; - - /* - * We treat unexpected efuse values as if the SoC was from - * the slowest bin. Expected efuse values are 1-3, slowest - * to fastest. - */ - if (efuse_value >= 1 && efuse_value <= 3) - *versions = efuse_value - 1; - else - *versions = 0; + ret = opp_data->efuse_xlate(*speedbin); kfree(speedbin); - return 0; + + return ret; }; static int sun50i_cpufreq_nvmem_probe(struct platform_device *pdev) { int *opp_tokens; - char name[MAX_NAME_LEN]; - unsigned int cpu; - u32 speed = 0; + char name[] = "speedXXXXXXXXXXX"; /* Integers can take 11 chars max */ + unsigned int cpu, supported_hw; + struct dev_pm_opp_config config = {}; + int speed; int ret; opp_tokens = kcalloc(num_possible_cpus(), sizeof(*opp_tokens), @@ -95,13 +217,24 @@ static int sun50i_cpufreq_nvmem_probe(struct platform_device *pdev) if (!opp_tokens) return -ENOMEM; - ret = sun50i_cpufreq_get_efuse(&speed); - if (ret) { + speed = sun50i_cpufreq_get_efuse(); + if (speed < 0) { kfree(opp_tokens); - return ret; + return speed; } - snprintf(name, MAX_NAME_LEN, "speed%d", speed); + /* + * We need at least one OPP with the "opp-supported-hw" property, + * or else the upper layers will ignore every OPP and will bail out. + */ + if (dt_has_supported_hw()) { + supported_hw = 1U << speed; + config.supported_hw = &supported_hw; + config.supported_hw_count = 1; + } + + snprintf(name, sizeof(name), "speed%d", speed); + config.prop_name = name; for_each_possible_cpu(cpu) { struct device *cpu_dev = get_cpu_device(cpu); @@ -111,12 +244,11 @@ static int sun50i_cpufreq_nvmem_probe(struct platform_device *pdev) goto free_opp; } - opp_tokens[cpu] = dev_pm_opp_set_prop_name(cpu_dev, name); - if (opp_tokens[cpu] < 0) { - ret = opp_tokens[cpu]; - pr_err("Failed to set prop name\n"); + ret = dev_pm_opp_set_config(cpu_dev, &config); + if (ret < 0) goto free_opp; - } + + opp_tokens[cpu] = ret; } cpufreq_dt_pdev = platform_device_register_simple("cpufreq-dt", -1, @@ -131,7 +263,7 @@ static int sun50i_cpufreq_nvmem_probe(struct platform_device *pdev) free_opp: for_each_possible_cpu(cpu) - dev_pm_opp_put_prop_name(opp_tokens[cpu]); + dev_pm_opp_clear_config(opp_tokens[cpu]); kfree(opp_tokens); return ret; @@ -145,7 +277,7 @@ static void sun50i_cpufreq_nvmem_remove(struct platform_device *pdev) platform_device_unregister(cpufreq_dt_pdev); for_each_possible_cpu(cpu) - dev_pm_opp_put_prop_name(opp_tokens[cpu]); + dev_pm_opp_clear_config(opp_tokens[cpu]); kfree(opp_tokens); } @@ -160,6 +292,9 @@ static struct platform_driver sun50i_cpufreq_driver = { static const struct of_device_id sun50i_cpufreq_match_list[] = { { .compatible = "allwinner,sun50i-h6" }, + { .compatible = "allwinner,sun50i-h616" }, + { .compatible = "allwinner,sun50i-h618" }, + { .compatible = "allwinner,sun50i-h700" }, {} }; MODULE_DEVICE_TABLE(of, sun50i_cpufreq_match_list); diff --git a/drivers/cpufreq/tegra124-cpufreq.c b/drivers/cpufreq/tegra124-cpufreq.c index aae951d4e77c..514146d98bca 100644 --- a/drivers/cpufreq/tegra124-cpufreq.c +++ b/drivers/cpufreq/tegra124-cpufreq.c @@ -52,12 +52,15 @@ out: static int tegra124_cpufreq_probe(struct platform_device *pdev) { + struct device_node *np __free(device_node) = of_cpu_device_node_get(0); struct tegra124_cpufreq_priv *priv; - struct device_node *np; struct device *cpu_dev; struct platform_device_info cpufreq_dt_devinfo = {}; int ret; + if (!np) + return -ENODEV; + priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; @@ -66,15 +69,9 @@ static int tegra124_cpufreq_probe(struct platform_device *pdev) if (!cpu_dev) return -ENODEV; - np = of_cpu_device_node_get(0); - if (!np) - return -ENODEV; - priv->cpu_clk = of_clk_get_by_name(np, "cpu_g"); - if (IS_ERR(priv->cpu_clk)) { - ret = PTR_ERR(priv->cpu_clk); - goto out_put_np; - } + if (IS_ERR(priv->cpu_clk)) + return PTR_ERR(priv->cpu_clk); priv->dfll_clk = of_clk_get_by_name(np, "dfll"); if (IS_ERR(priv->dfll_clk)) { @@ -110,8 +107,6 @@ static int tegra124_cpufreq_probe(struct platform_device *pdev) platform_set_drvdata(pdev, priv); - of_node_put(np); - return 0; out_put_pllp_clk: @@ -122,8 +117,6 @@ out_put_dfll_clk: clk_put(priv->dfll_clk); out_put_cpu_clk: clk_put(priv->cpu_clk); -out_put_np: - of_node_put(np); return ret; } diff --git a/drivers/cpufreq/ti-cpufreq.c b/drivers/cpufreq/ti-cpufreq.c index 46c41e2ca727..714ed53753fa 100644 --- a/drivers/cpufreq/ti-cpufreq.c +++ b/drivers/cpufreq/ti-cpufreq.c @@ -347,12 +347,10 @@ static const struct of_device_id ti_cpufreq_of_match[] = { static const struct of_device_id *ti_cpufreq_match_node(void) { - struct device_node *np; + struct device_node *np __free(device_node) = of_find_node_by_path("/"); const struct of_device_id *match; - np = of_find_node_by_path("/"); match = of_match_node(ti_cpufreq_of_match, np); - of_node_put(np); return match; } |