diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 77dd6bb48c3d..b69482b29625 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1651,10 +1651,6 @@ Kernel parameters very early in the boot process. For early debugging via a serial port see kgdboc_earlycon instead. - elanfreq= [X86-32] - See comment before function elanfreq_setup() in - arch/x86/kernel/cpu/cpufreq/elanfreq.c. - elfcorehdr=[size[KMG]@]offset[KMG] [PPC,SH,X86,S390,EARLY] Specifies physical address of start of kernel core image elf header and optionally the size. Generally diff --git a/Documentation/admin-guide/pm/cpufreq.rst b/Documentation/admin-guide/pm/cpufreq.rst index dbe6d23a5d67..8831cface585 100644 --- a/Documentation/admin-guide/pm/cpufreq.rst +++ b/Documentation/admin-guide/pm/cpufreq.rst @@ -516,7 +516,7 @@ This governor exposes the following tunables: of those tasks above 0 and set this attribute to 1. ``sampling_down_factor`` - Temporary multiplier, between 1 (default) and 100 inclusive, to apply to + Temporary multiplier, between 1 (default) and 100000 inclusive, to apply to the ``sampling_rate`` value if the CPU load goes above ``up_threshold``. This causes the next execution of the governor's worker routine (after @@ -586,8 +586,8 @@ This governor exposes the following tunables: 100 (5 by default). This is how much the frequency is allowed to change in one go. Setting - it to 0 will cause the default frequency step (5 percent) to be used - and setting it to 100 effectively causes the governor to periodically + it to 0 disables frequency changes by the governor entirely and setting + it to 100 effectively causes the governor to periodically switch the frequency between the ``scaling_min_freq`` and ``scaling_max_freq`` policy limits. diff --git a/Documentation/cpu-freq/cpu-drivers.rst b/Documentation/cpu-freq/cpu-drivers.rst index c5635ac3de54..17c69f83691e 100644 --- a/Documentation/cpu-freq/cpu-drivers.rst +++ b/Documentation/cpu-freq/cpu-drivers.rst @@ -114,8 +114,13 @@ Then, the driver must fill in the following values: |policy->cur | The current operating frequency of | | | this CPU (if appropriate) | +-----------------------------------+--------------------------------------+ -|policy->min, | | -|policy->max, | | +|policy->min, | The min/max scaling frequency. | +|policy->max | If set by the driver in ->init(), | +| | used as the lower/upper bound for | +| | policy frequency QoS requests; | +| | otherwise, reflects the min/max | +| | frequency the driver can set | ++-----------------------------------+--------------------------------------+ |policy->policy and, if necessary, | | |policy->governor | must contain the "default policy" for| | | this CPU. A few moments later, | diff --git a/Documentation/devicetree/bindings/cpufreq/qcom,shikra-epss.yaml b/Documentation/devicetree/bindings/cpufreq/qcom,shikra-epss.yaml new file mode 100644 index 000000000000..1a3105e86980 --- /dev/null +++ b/Documentation/devicetree/bindings/cpufreq/qcom,shikra-epss.yaml @@ -0,0 +1,96 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/cpufreq/qcom,shikra-epss.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm Shikra SoC EPSS + +maintainers: + - Imran Shaik + - Taniya Das + +description: | + EPSS is a hardware engine used by some Qualcomm SoCs to manage + frequency in hardware. It is capable of controlling frequency for + multiple clusters. + + The Qualcomm Shikra SoC EPSS supports up to 12 frequency lookup table + (LUT) entries. + +properties: + compatible: + enum: + - qcom,shikra-epss + + reg: + items: + - description: Frequency domain 0 register region + - description: Frequency domain 1 register region + + reg-names: + items: + - const: freq-domain0 + - const: freq-domain1 + + clocks: + items: + - description: XO Clock + - description: GPLL0 Clock + + clock-names: + items: + - const: xo + - const: alternate + + interrupts: + items: + - description: IRQ line for DCVSH 0 + - description: IRQ line for DCVSH 1 + + interrupt-names: + items: + - const: dcvsh-irq-0 + - const: dcvsh-irq-1 + + '#freq-domain-cells': + const: 1 + + '#clock-cells': + const: 1 + +required: + - compatible + - reg + - clocks + - clock-names + - interrupts + - interrupt-names + - '#freq-domain-cells' + - '#clock-cells' + +additionalProperties: false + +examples: + - | + #include + #include + + soc { + #address-cells = <1>; + #size-cells = <1>; + + cpufreq@fd91000 { + compatible = "qcom,shikra-epss"; + reg = <0x0fd91000 0x1000>, <0x0fd92000 0x1000>; + reg-names = "freq-domain0", "freq-domain1"; + clocks = <&rpmcc RPM_SMD_XO_CLK_SRC>, <&gpll0>; + clock-names = "xo", "alternate"; + interrupts = , + ; + interrupt-names = "dcvsh-irq-0", "dcvsh-irq-1"; + #freq-domain-cells = <1>; + #clock-cells = <1>; + }; + }; +... diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index e1b550664bab..f71467f6ada4 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include #include @@ -115,7 +116,7 @@ void device_pm_sleep_init(struct device *dev) dev->power.is_noirq_suspended = false; dev->power.is_late_suspended = false; init_completion(&dev->power.completion); - complete_all(&dev->power.completion); + complete(&dev->power.completion); dev->power.wakeup = NULL; INIT_LIST_HEAD(&dev->power.entry); } @@ -252,6 +253,10 @@ static void dpm_wait(struct device *dev, bool async) if (!dev) return; + /* Devices with no PM support don't use the completion. */ + if (dev->power.no_pm) + return; + if (async || (pm_async_enabled && dev->power.async_suspend)) wait_for_completion(&dev->power.completion); } @@ -527,6 +532,58 @@ module_param(dpm_watchdog_all_cpu_backtrace, bool, 0644); MODULE_PARM_DESC(dpm_watchdog_all_cpu_backtrace, "Backtrace all CPUs on DPM watchdog timeout"); +static unsigned int __read_mostly dpm_watchdog_timeout = CONFIG_DPM_WATCHDOG_TIMEOUT; +static unsigned int __read_mostly dpm_watchdog_warning_timeout = + CONFIG_DPM_WATCHDOG_WARNING_TIMEOUT; +static const unsigned int dpm_watchdog_timeout_max = CONFIG_DPM_WATCHDOG_TIMEOUT; + +static int proc_dodpm_watchdog_timeout_secs(const struct ctl_table *table, + int write, void *buffer, + size_t *lenp, loff_t *ppos) +{ + struct ctl_table ctl = *table; + unsigned int val = dpm_watchdog_timeout; + int ret; + + ctl.data = &val; + ret = proc_douintvec_minmax(&ctl, write, buffer, lenp, ppos); + if (ret || !write) + return ret; + + if (val < dpm_watchdog_warning_timeout) + dpm_watchdog_warning_timeout = val; + dpm_watchdog_timeout = val; + + return 0; +} + +static const struct ctl_table dpm_watchdog_sysctls[] = { + { + .procname = "dpm_watchdog_timeout_secs", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dodpm_watchdog_timeout_secs, + .extra1 = SYSCTL_ONE, + .extra2 = (void *)&dpm_watchdog_timeout_max, + }, + { + .procname = "dpm_watchdog_warning_timeout_secs", + .data = &dpm_watchdog_warning_timeout, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_douintvec_minmax, + .extra1 = SYSCTL_ONE, + .extra2 = (void *)&dpm_watchdog_timeout, + }, +}; + +static int __init dpm_watchdog_sysctl_init(void) +{ + register_sysctl_init("kernel", dpm_watchdog_sysctls); + return 0; +} +subsys_initcall(dpm_watchdog_sysctl_init); + /** * dpm_watchdog_handler - Driver suspend / resume watchdog handler. * @t: The timer that PM watchdog depends on. @@ -552,9 +609,9 @@ static void dpm_watchdog_handler(struct timer_list *t) dev_driver_string(wd->dev), dev_name(wd->dev)); } - time_left = CONFIG_DPM_WATCHDOG_TIMEOUT - CONFIG_DPM_WATCHDOG_WARNING_TIMEOUT; + time_left = dpm_watchdog_timeout - 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); + dpm_watchdog_warning_timeout, time_left); show_stack(wd->tsk, NULL, KERN_WARNING); wd->fatal = true; @@ -572,11 +629,11 @@ 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; + wd->fatal = dpm_watchdog_timeout == 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_WARNING_TIMEOUT; + timer->expires = jiffies + HZ * dpm_watchdog_warning_timeout; add_timer(timer); } diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index 47c9b031f1b3..a441668f9e0c 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -153,7 +153,7 @@ config ARM_QCOM_CPUFREQ_NVMEM If in doubt, say N. config ARM_QCOM_CPUFREQ_HW - tristate "QCOM CPUFreq HW driver" + tristate "Qualcomm CPUFreq HW driver" depends on ARCH_QCOM || COMPILE_TEST depends on COMMON_CLK help diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86 index a9093cd5e5d1..46b9742a1688 100644 --- a/drivers/cpufreq/Kconfig.x86 +++ b/drivers/cpufreq/Kconfig.x86 @@ -5,7 +5,6 @@ config X86_INTEL_PSTATE bool "Intel P state control" - depends on X86 select ACPI_PROCESSOR if ACPI select ACPI_CPPC_LIB if X86_64 && ACPI && SCHED_MC_PRIO select CPU_FREQ_GOV_PERFORMANCE @@ -36,7 +35,7 @@ config X86_PCC_CPUFREQ config X86_AMD_PSTATE bool "AMD Processor P-State driver" - depends on X86 && ACPI + depends on ACPI select ACPI_PROCESSOR select ACPI_CPPC_LIB if X86_64 select CPU_FREQ_GOV_SCHEDUTIL if SMP @@ -72,7 +71,7 @@ config X86_AMD_PSTATE_DEFAULT_MODE config X86_AMD_PSTATE_UT tristate "selftest for AMD Processor P-State driver" - depends on X86 && ACPI_PROCESSOR + depends on ACPI_PROCESSOR depends on X86_AMD_PSTATE default n help @@ -114,21 +113,6 @@ config X86_ACPI_CPUFREQ_CPB By enabling this option the acpi_cpufreq driver provides the old entry in addition to the new boost ones, for compatibility reasons. -config ELAN_CPUFREQ - tristate "AMD Elan SC400 and SC410" - depends on MELAN - help - This adds the CPUFreq driver for AMD Elan SC400 and SC410 - processors. - - You need to specify the processor maximum speed as boot - parameter: elanfreq=maxspeed (in kHz) or as module - parameter "max_freq". - - For details, take a look at . - - If in doubt, say N. - config SC520_CPUFREQ tristate "AMD Elan SC520" depends on MELAN diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile index 385c9fcc65c6..8056b8f2200b 100644 --- a/drivers/cpufreq/Makefile +++ b/drivers/cpufreq/Makefile @@ -40,7 +40,6 @@ obj-$(CONFIG_X86_POWERNOW_K6) += powernow-k6.o obj-$(CONFIG_X86_POWERNOW_K7) += powernow-k7.o obj-$(CONFIG_X86_LONGHAUL) += longhaul.o obj-$(CONFIG_X86_E_POWERSAVER) += e_powersaver.o -obj-$(CONFIG_ELAN_CPUFREQ) += elanfreq.o obj-$(CONFIG_SC520_CPUFREQ) += sc520_freq.o obj-$(CONFIG_X86_LONGRUN) += longrun.o obj-$(CONFIG_X86_GX_SUSPMOD) += gx-suspmod.o diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 72df461e7b39..f5154c77c31b 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -242,12 +242,10 @@ static int msr_update_perf(struct cpufreq_policy *policy, u8 min_perf, 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); + FIELD_MODIFY(AMD_CPPC_MAX_PERF_MASK, &value, max_perf); + FIELD_MODIFY(AMD_CPPC_DES_PERF_MASK, &value, des_perf); + FIELD_MODIFY(AMD_CPPC_MIN_PERF_MASK, &value, min_perf); + FIELD_MODIFY(AMD_CPPC_EPP_PERF_MASK, &value, epp); if (trace_amd_pstate_epp_perf_enabled()) { union perf_cached perf = READ_ONCE(cpudata->perf); @@ -296,8 +294,7 @@ static int msr_set_epp(struct cpufreq_policy *policy, u8 epp) int ret; value = prev = READ_ONCE(cpudata->cppc_req_cached); - value &= ~AMD_CPPC_EPP_PERF_MASK; - value |= FIELD_PREP(AMD_CPPC_EPP_PERF_MASK, epp); + FIELD_MODIFY(AMD_CPPC_EPP_PERF_MASK, &value, epp); if (trace_amd_pstate_epp_perf_enabled()) { union perf_cached perf = cpudata->perf; @@ -437,8 +434,7 @@ static int shmem_set_epp(struct cpufreq_policy *policy, u8 epp) } value = READ_ONCE(cpudata->cppc_req_cached); - value &= ~AMD_CPPC_EPP_PERF_MASK; - value |= FIELD_PREP(AMD_CPPC_EPP_PERF_MASK, epp); + FIELD_MODIFY(AMD_CPPC_EPP_PERF_MASK, &value, epp); WRITE_ONCE(cpudata->cppc_req_cached, value); return ret; @@ -571,12 +567,10 @@ static int shmem_update_perf(struct cpufreq_policy *policy, u8 min_perf, 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); + FIELD_MODIFY(AMD_CPPC_MAX_PERF_MASK, &value, max_perf); + FIELD_MODIFY(AMD_CPPC_DES_PERF_MASK, &value, des_perf); + FIELD_MODIFY(AMD_CPPC_MIN_PERF_MASK, &value, min_perf); + FIELD_MODIFY(AMD_CPPC_EPP_PERF_MASK, &value, epp); if (trace_amd_pstate_epp_perf_enabled()) { union perf_cached perf = READ_ONCE(cpudata->perf); @@ -1086,10 +1080,9 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy) perf = READ_ONCE(cpudata->perf); - policy->cpuinfo.min_freq = policy->min = perf_to_freq(perf, - cpudata->nominal_freq, - perf.lowest_perf); - policy->cpuinfo.max_freq = policy->max = cpudata->max_freq; + policy->cpuinfo.min_freq = perf_to_freq(perf, cpudata->nominal_freq, + perf.lowest_perf); + policy->cpuinfo.max_freq = cpudata->max_freq; policy->driver_data = cpudata; ret = amd_pstate_cppc_enable(policy); @@ -1915,10 +1908,9 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) perf = READ_ONCE(cpudata->perf); - policy->cpuinfo.min_freq = policy->min = perf_to_freq(perf, - cpudata->nominal_freq, - perf.lowest_perf); - policy->cpuinfo.max_freq = policy->max = cpudata->max_freq; + policy->cpuinfo.min_freq = perf_to_freq(perf, cpudata->nominal_freq, + perf.lowest_perf); + policy->cpuinfo.max_freq = cpudata->max_freq; policy->driver_data = cpudata; ret = amd_pstate_cppc_enable(policy); diff --git a/drivers/cpufreq/apple-soc-cpufreq.c b/drivers/cpufreq/apple-soc-cpufreq.c index 9396034167e5..638e5bf72185 100644 --- a/drivers/cpufreq/apple-soc-cpufreq.c +++ b/drivers/cpufreq/apple-soc-cpufreq.c @@ -187,10 +187,8 @@ static int apple_soc_cpufreq_set_target(struct cpufreq_policy *policy, 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); - } + if (priv->info->has_ps2) + FIELD_MODIFY(APPLE_DVFS_CMD_PS2, ®, pstate); reg |= APPLE_DVFS_CMD_SET; writeq_relaxed(reg, priv->reg_base + APPLE_DVFS_CMD); diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index 7e7f9dfb7a24..f6cea0c54dd9 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -660,8 +660,6 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy) * Section 8.4.7.1.1.5 of ACPI 6.1 spec) */ policy->min = cppc_perf_to_khz(caps, caps->lowest_nonlinear_perf); - policy->max = cppc_perf_to_khz(caps, policy->boost_enabled ? - caps->highest_perf : caps->nominal_perf); /* * Set cpuinfo.min_freq to Lowest to make the full range of performance @@ -669,7 +667,8 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy) * nonlinear perf */ policy->cpuinfo.min_freq = cppc_perf_to_khz(caps, caps->lowest_perf); - policy->cpuinfo.max_freq = policy->max; + policy->cpuinfo.max_freq = cppc_perf_to_khz(caps, policy->boost_enabled ? + caps->highest_perf : caps->nominal_perf); policy->transition_delay_us = cppc_cpufreq_get_transition_delay_us(cpu); policy->shared_type = cpu_data->shared_type; @@ -982,7 +981,34 @@ store_energy_performance_preference_val(struct cpufreq_policy *policy, return count; } -CPPC_CPUFREQ_ATTR_RW_U64(perf_limited, cppc_get_perf_limited, +static int cppc_get_perf_limited_filtered(int cpu, u64 *perf_limited) +{ + struct cpufreq_policy *policy; + struct cppc_cpudata *cpu_data; + int ret; + + ret = cppc_get_perf_limited(cpu, perf_limited); + if (ret) + return ret; + + policy = cpufreq_cpu_get_raw(cpu); + if (!policy) + return -EINVAL; + + cpu_data = policy->driver_data; + + /* + * Desired Excursion is ignored when autonomous selection is + * enabled. Clear the bit to avoid exposing meaningless state + * to userspace. + */ + if (cpu_data && cpu_data->perf_ctrls.auto_sel) + *perf_limited &= ~CPPC_PERF_LIMITED_DESIRED_EXCURSION; + + return 0; +} + +CPPC_CPUFREQ_ATTR_RW_U64(perf_limited, cppc_get_perf_limited_filtered, cppc_set_perf_limited) cpufreq_freq_attr_ro(freqdomain_cpus); diff --git a/drivers/cpufreq/cpufreq-nforce2.c b/drivers/cpufreq/cpufreq-nforce2.c index fbbbe501cf2d..831102522ad6 100644 --- a/drivers/cpufreq/cpufreq-nforce2.c +++ b/drivers/cpufreq/cpufreq-nforce2.c @@ -355,8 +355,8 @@ static int nforce2_cpu_init(struct cpufreq_policy *policy) min_fsb = NFORCE2_MIN_FSB; /* cpuinfo and default policy values */ - policy->min = policy->cpuinfo.min_freq = min_fsb * fid * 100; - policy->max = policy->cpuinfo.max_freq = max_fsb * fid * 100; + policy->cpuinfo.min_freq = min_fsb * fid * 100; + policy->cpuinfo.max_freq = max_fsb * fid * 100; return 0; } diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 44eb1b7e7fc1..a81d40f12029 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1397,6 +1397,40 @@ static void cpufreq_policy_free(struct cpufreq_policy *policy) kfree(policy); } +static int cpufreq_policy_init_qos(struct cpufreq_policy *policy) +{ + unsigned int min_freq, max_freq; + int ret; + + /* Use policy->min/max set by the driver as QoS requests. */ + min_freq = max(FREQ_QOS_MIN_DEFAULT_VALUE, policy->min); + if (policy->max) + max_freq = min(FREQ_QOS_MAX_DEFAULT_VALUE, policy->max); + else + max_freq = FREQ_QOS_MAX_DEFAULT_VALUE; + + if (policy->boost_supported) { + ret = freq_qos_add_request(&policy->constraints, + &policy->boost_freq_req, + FREQ_QOS_MAX, + policy->cpuinfo.max_freq); + if (ret < 0) + return ret; + } + + ret = freq_qos_add_request(&policy->constraints, &policy->min_freq_req, + FREQ_QOS_MIN, min_freq); + if (ret < 0) + return ret; + + ret = freq_qos_add_request(&policy->constraints, &policy->max_freq_req, + FREQ_QOS_MAX, max_freq); + if (ret < 0) + return ret; + + return 0; +} + static int cpufreq_policy_online(struct cpufreq_policy *policy, unsigned int cpu, bool new_policy) { @@ -1442,6 +1476,19 @@ static int cpufreq_policy_online(struct cpufreq_policy *policy, if (ret) goto out_offline_policy; + if (new_policy) { + ret = cpufreq_policy_init_qos(policy); + if (ret < 0) + goto out_offline_policy; + } + + /* + * If the driver hasn't set policy->min/max, set them as they + * are used for clamping frequency requests. + */ + policy->min = policy->min ? policy->min : policy->cpuinfo.min_freq; + policy->max = policy->max ? policy->max : policy->cpuinfo.max_freq; + /* related_cpus should at least include policy->cpus. */ cpumask_copy(policy->related_cpus, policy->cpus); } @@ -1458,27 +1505,6 @@ static int cpufreq_policy_online(struct cpufreq_policy *policy, add_cpu_dev_symlink(policy, j, get_cpu_device(j)); } - if (policy->boost_supported) { - ret = freq_qos_add_request(&policy->constraints, - &policy->boost_freq_req, - FREQ_QOS_MAX, - policy->cpuinfo.max_freq); - if (ret < 0) - goto out_destroy_policy; - } - - ret = freq_qos_add_request(&policy->constraints, - &policy->min_freq_req, FREQ_QOS_MIN, - FREQ_QOS_MIN_DEFAULT_VALUE); - if (ret < 0) - goto out_destroy_policy; - - ret = freq_qos_add_request(&policy->constraints, - &policy->max_freq_req, FREQ_QOS_MAX, - FREQ_QOS_MAX_DEFAULT_VALUE); - if (ret < 0) - goto out_destroy_policy; - blocking_notifier_call_chain(&cpufreq_policy_notifier_list, CPUFREQ_CREATE_POLICY, policy); } @@ -1972,6 +1998,7 @@ void cpufreq_suspend(void) if (!cpufreq_driver) return; + cpus_read_lock(); if (!has_target() && !cpufreq_driver->suspend) goto suspend; @@ -1991,6 +2018,7 @@ void cpufreq_suspend(void) suspend: cpufreq_suspended = true; + cpus_read_unlock(); } /** @@ -2366,9 +2394,13 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy, * exactly same freq is called again and so we can save on few function * calls. */ - if (target_freq == policy->cur && - !(cpufreq_driver->flags & CPUFREQ_NEED_UPDATE_LIMITS)) - return 0; + if (target_freq == policy->cur) { + if (!(cpufreq_driver->flags & CPUFREQ_NEED_UPDATE_LIMITS) || + !policy->update_limits) + return 0; + + policy->update_limits = false; + } if (cpufreq_driver->target) { /* @@ -2620,6 +2652,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy, { struct cpufreq_policy_data new_data; struct cpufreq_governor *old_gov; + unsigned int freq; int ret; memcpy(&new_data.cpuinfo, &policy->cpuinfo, sizeof(policy->cpuinfo)); @@ -2652,12 +2685,20 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy, * compiler optimizations around them because they may be accessed * concurrently by cpufreq_driver_resolve_freq() during the update. */ - WRITE_ONCE(policy->max, __resolve_freq(policy, new_data.max, - new_data.min, new_data.max, - CPUFREQ_RELATION_H)); - new_data.min = __resolve_freq(policy, new_data.min, new_data.min, - new_data.max, CPUFREQ_RELATION_L); - WRITE_ONCE(policy->min, new_data.min > policy->max ? policy->max : new_data.min); + freq = __resolve_freq(policy, new_data.max, new_data.min, new_data.max, + CPUFREQ_RELATION_H); + if (freq != policy->max) { + WRITE_ONCE(policy->max, freq); + policy->update_limits = true; + } + + freq = __resolve_freq(policy, new_data.min, new_data.min, new_data.max, + CPUFREQ_RELATION_L); + freq = min(freq, policy->max); + if (freq != policy->min) { + WRITE_ONCE(policy->min, freq); + policy->update_limits = true; + } trace_cpu_frequency_limits(policy); diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c index df01d33993d8..0b32ae28ec85 100644 --- a/drivers/cpufreq/cpufreq_conservative.c +++ b/drivers/cpufreq/cpufreq_conservative.c @@ -103,10 +103,6 @@ static unsigned int cs_dbs_update(struct cpufreq_policy *policy) if (load > dbs_data->up_threshold) { dbs_info->down_skip = 0; - /* if we are already at full speed then break out early */ - if (requested_freq == policy->max) - goto out; - requested_freq += freq_step; if (requested_freq > policy->max) requested_freq = policy->max; @@ -124,13 +120,7 @@ static unsigned int cs_dbs_update(struct cpufreq_policy *policy) /* Check for frequency decrease */ if (load < cs_tuners->down_threshold) { - /* - * if we cannot reduce the frequency anymore, break out early - */ - if (requested_freq == policy->min) - goto out; - - if (requested_freq > freq_step) + if (requested_freq > policy->min + freq_step) requested_freq -= freq_step; else requested_freq = policy->min; diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c index 86f35e451914..8a85bd32defe 100644 --- a/drivers/cpufreq/cpufreq_governor.c +++ b/drivers/cpufreq/cpufreq_governor.c @@ -90,7 +90,14 @@ EXPORT_SYMBOL_GPL(sampling_rate_store); * (that may be a single policy or a bunch of them if governor tunables are * system-wide). * - * Call under the @dbs_data mutex. + * Call under the @dbs_data->attr_set.update_lock. The per-policy + * update_mutex is acquired and released internally for each policy. + * + * Note: prev_cpu_nice is reset here unconditionally alongside prev_cpu_idle. + * When io_is_busy changes, both baselines must be advanced to the same + * timestamp so that the next dbs_update() computes idle_time and nice_delta + * over the same interval, preventing an artificially inflated idle_time when + * ignore_nice_load is enabled. */ void gov_update_cpu_data(struct dbs_data *dbs_data) { @@ -99,14 +106,15 @@ void gov_update_cpu_data(struct dbs_data *dbs_data) list_for_each_entry(policy_dbs, &dbs_data->attr_set.policy_list, list) { unsigned int j; + mutex_lock(&policy_dbs->update_mutex); for_each_cpu(j, policy_dbs->policy->cpus) { struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j); j_cdbs->prev_cpu_idle = get_cpu_idle_time(j, &j_cdbs->prev_update_time, dbs_data->io_is_busy); - if (dbs_data->ignore_nice_load) - j_cdbs->prev_cpu_nice = kcpustat_field(&kcpustat_cpu(j), CPUTIME_NICE, j); + j_cdbs->prev_cpu_nice = kcpustat_field(&kcpustat_cpu(j), CPUTIME_NICE, j); } + mutex_unlock(&policy_dbs->update_mutex); } } EXPORT_SYMBOL_GPL(gov_update_cpu_data); @@ -118,6 +126,7 @@ unsigned int dbs_update(struct cpufreq_policy *policy) unsigned int ignore_nice = dbs_data->ignore_nice_load; unsigned int max_load = 0, idle_periods = UINT_MAX; unsigned int sampling_rate, io_busy, j; + u64 cur_nice; /* * Sometimes governors may use an additional multiplier to increase @@ -164,12 +173,18 @@ unsigned int dbs_update(struct cpufreq_policy *policy) j_cdbs->prev_cpu_idle = cur_idle_time; - if (ignore_nice) { - u64 cur_nice = kcpustat_field(&kcpustat_cpu(j), CPUTIME_NICE, j); - + /* + * Always sample cur_nice and advance prev_cpu_nice, regardless + * of ignore_nice. This keeps prev_cpu_nice current so that + * enabling ignore_nice_load via sysfs never produces a + * stale-baseline spike (the delta will be at most one sampling + * interval of accumulated nice time, not since boot). + */ + cur_nice = kcpustat_field(&kcpustat_cpu(j), CPUTIME_NICE, j); + if (ignore_nice) idle_time += div_u64(cur_nice - j_cdbs->prev_cpu_nice, NSEC_PER_USEC); - j_cdbs->prev_cpu_nice = cur_nice; - } + + j_cdbs->prev_cpu_nice = cur_nice; if (unlikely(!time_elapsed)) { /* @@ -516,7 +531,7 @@ int cpufreq_dbs_governor_start(struct cpufreq_policy *policy) struct dbs_governor *gov = dbs_governor_of(policy); struct policy_dbs_info *policy_dbs = policy->governor_data; struct dbs_data *dbs_data = policy_dbs->dbs_data; - unsigned int sampling_rate, ignore_nice, j; + unsigned int sampling_rate, j; unsigned int io_busy; if (!policy->cur) @@ -526,9 +541,9 @@ int cpufreq_dbs_governor_start(struct cpufreq_policy *policy) policy_dbs->rate_mult = 1; sampling_rate = dbs_data->sampling_rate; - ignore_nice = dbs_data->ignore_nice_load; - io_busy = dbs_data->io_is_busy; + mutex_lock(&policy_dbs->update_mutex); + io_busy = dbs_data->io_is_busy; for_each_cpu(j, policy->cpus) { struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j); @@ -537,10 +552,9 @@ int cpufreq_dbs_governor_start(struct cpufreq_policy *policy) * Make the first invocation of dbs_update() compute the load. */ j_cdbs->prev_load = 0; - - if (ignore_nice) - j_cdbs->prev_cpu_nice = kcpustat_field(&kcpustat_cpu(j), CPUTIME_NICE, j); + j_cdbs->prev_cpu_nice = kcpustat_field(&kcpustat_cpu(j), CPUTIME_NICE, j); } + mutex_unlock(&policy_dbs->update_mutex); gov->start(policy); diff --git a/drivers/cpufreq/elanfreq.c b/drivers/cpufreq/elanfreq.c deleted file mode 100644 index fc5a58088b35..000000000000 --- a/drivers/cpufreq/elanfreq.c +++ /dev/null @@ -1,226 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * elanfreq: cpufreq driver for the AMD ELAN family - * - * (c) Copyright 2002 Robert Schwebel - * - * Parts of this code are (c) Sven Geggus - * - * All Rights Reserved. - * - * 2002-02-13: - initial revision for 2.4.18-pre9 by Robert Schwebel - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include -#include -#include - -#include -#include - -#include -#include -#include - -#define REG_CSCIR 0x22 /* Chip Setup and Control Index Register */ -#define REG_CSCDR 0x23 /* Chip Setup and Control Data Register */ - -/* Module parameter */ -static int max_freq; - -struct s_elan_multiplier { - int clock; /* frequency in kHz */ - int val40h; /* PMU Force Mode register */ - int val80h; /* CPU Clock Speed Register */ -}; - -/* - * It is important that the frequencies - * are listed in ascending order here! - */ -static struct s_elan_multiplier elan_multiplier[] = { - {1000, 0x02, 0x18}, - {2000, 0x02, 0x10}, - {4000, 0x02, 0x08}, - {8000, 0x00, 0x00}, - {16000, 0x00, 0x02}, - {33000, 0x00, 0x04}, - {66000, 0x01, 0x04}, - {99000, 0x01, 0x05} -}; - -static struct cpufreq_frequency_table elanfreq_table[] = { - {0, 0, 1000}, - {0, 1, 2000}, - {0, 2, 4000}, - {0, 3, 8000}, - {0, 4, 16000}, - {0, 5, 33000}, - {0, 6, 66000}, - {0, 7, 99000}, - {0, 0, CPUFREQ_TABLE_END}, -}; - - -/** - * elanfreq_get_cpu_frequency: determine current cpu speed - * - * Finds out at which frequency the CPU of the Elan SOC runs - * at the moment. Frequencies from 1 to 33 MHz are generated - * the normal way, 66 and 99 MHz are called "Hyperspeed Mode" - * and have the rest of the chip running with 33 MHz. - */ - -static unsigned int elanfreq_get_cpu_frequency(unsigned int cpu) -{ - u8 clockspeed_reg; /* Clock Speed Register */ - - local_irq_disable(); - outb_p(0x80, REG_CSCIR); - clockspeed_reg = inb_p(REG_CSCDR); - local_irq_enable(); - - if ((clockspeed_reg & 0xE0) == 0xE0) - return 0; - - /* Are we in CPU clock multiplied mode (66/99 MHz)? */ - if ((clockspeed_reg & 0xE0) == 0xC0) { - if ((clockspeed_reg & 0x01) == 0) - return 66000; - else - return 99000; - } - - /* 33 MHz is not 32 MHz... */ - if ((clockspeed_reg & 0xE0) == 0xA0) - return 33000; - - return (1<<((clockspeed_reg & 0xE0) >> 5)) * 1000; -} - - -static int elanfreq_target(struct cpufreq_policy *policy, - unsigned int state) -{ - /* - * Access to the Elan's internal registers is indexed via - * 0x22: Chip Setup & Control Register Index Register (CSCI) - * 0x23: Chip Setup & Control Register Data Register (CSCD) - * - */ - - /* - * 0x40 is the Power Management Unit's Force Mode Register. - * Bit 6 enables Hyperspeed Mode (66/100 MHz core frequency) - */ - - local_irq_disable(); - outb_p(0x40, REG_CSCIR); /* Disable hyperspeed mode */ - outb_p(0x00, REG_CSCDR); - local_irq_enable(); /* wait till internal pipelines and */ - udelay(1000); /* buffers have cleaned up */ - - local_irq_disable(); - - /* now, set the CPU clock speed register (0x80) */ - outb_p(0x80, REG_CSCIR); - outb_p(elan_multiplier[state].val80h, REG_CSCDR); - - /* now, the hyperspeed bit in PMU Force Mode Register (0x40) */ - outb_p(0x40, REG_CSCIR); - outb_p(elan_multiplier[state].val40h, REG_CSCDR); - udelay(10000); - local_irq_enable(); - - return 0; -} -/* - * Module init and exit code - */ - -static int elanfreq_cpu_init(struct cpufreq_policy *policy) -{ - struct cpuinfo_x86 *c = &cpu_data(0); - struct cpufreq_frequency_table *pos; - - /* capability check */ - if ((c->x86_vendor != X86_VENDOR_AMD) || - (c->x86 != 4) || (c->x86_model != 10)) - return -ENODEV; - - /* max freq */ - if (!max_freq) - max_freq = elanfreq_get_cpu_frequency(0); - - /* table init */ - cpufreq_for_each_entry(pos, elanfreq_table) - if (pos->frequency > max_freq) - pos->frequency = CPUFREQ_ENTRY_INVALID; - - policy->freq_table = elanfreq_table; - return 0; -} - - -#ifndef MODULE -/** - * elanfreq_setup - elanfreq command line parameter parsing - * - * elanfreq command line parameter. Use: - * elanfreq=66000 - * to set the maximum CPU frequency to 66 MHz. Note that in - * case you do not give this boot parameter, the maximum - * frequency will fall back to _current_ CPU frequency which - * might be lower. If you build this as a module, use the - * max_freq module parameter instead. - */ -static int __init elanfreq_setup(char *str) -{ - max_freq = simple_strtoul(str, &str, 0); - pr_warn("You're using the deprecated elanfreq command line option. Use elanfreq.max_freq instead, please!\n"); - return 1; -} -__setup("elanfreq=", elanfreq_setup); -#endif - - -static struct cpufreq_driver elanfreq_driver = { - .get = elanfreq_get_cpu_frequency, - .flags = CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING, - .verify = cpufreq_generic_frequency_table_verify, - .target_index = elanfreq_target, - .init = elanfreq_cpu_init, - .name = "elanfreq", -}; - -static const struct x86_cpu_id elan_id[] = { - X86_MATCH_VENDOR_FAM_MODEL(AMD, 4, 10, NULL), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, elan_id); - -static int __init elanfreq_init(void) -{ - if (!x86_match_cpu(elan_id)) - return -ENODEV; - return cpufreq_register_driver(&elanfreq_driver); -} - - -static void __exit elanfreq_exit(void) -{ - cpufreq_unregister_driver(&elanfreq_driver); -} - - -module_param(max_freq, int, 0444); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Robert Schwebel , " - "Sven Geggus "); -MODULE_DESCRIPTION("cpufreq driver for AMD's Elan CPUs"); - -module_init(elanfreq_init); -module_exit(elanfreq_exit); diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c index 5b364d8da4f9..ea994647abc8 100644 --- a/drivers/cpufreq/freq_table.c +++ b/drivers/cpufreq/freq_table.c @@ -49,16 +49,15 @@ int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy) max_freq = freq; } - policy->min = policy->cpuinfo.min_freq = min_freq; - policy->max = max_freq; + policy->cpuinfo.min_freq = min_freq; /* * If the driver has set its own cpuinfo.max_freq above max_freq, leave * it as is. */ if (policy->cpuinfo.max_freq < max_freq) - policy->max = policy->cpuinfo.max_freq = max_freq; + policy->cpuinfo.max_freq = max_freq; - if (policy->min == ~0) + if (min_freq == ~0) return -EINVAL; else return 0; diff --git a/drivers/cpufreq/gx-suspmod.c b/drivers/cpufreq/gx-suspmod.c index d269a4f26f98..d40c9e0bbb74 100644 --- a/drivers/cpufreq/gx-suspmod.c +++ b/drivers/cpufreq/gx-suspmod.c @@ -421,7 +421,7 @@ static int cpufreq_gx_cpu_init(struct cpufreq_policy *policy) policy->min = maxfreq / max_duration; else policy->min = maxfreq / POLICY_MIN_DIV; - policy->max = maxfreq; + policy->cpuinfo.min_freq = maxfreq / max_duration; policy->cpuinfo.max_freq = maxfreq; diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 1f093e346430..5a0eeb84d382 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -2984,10 +2984,12 @@ static int intel_cpufreq_cpu_offline(struct cpufreq_policy *policy) * from getting to lower performance levels, so force the minimum * performance on CPU offline to prevent that from happening. */ - if (hwp_active) + if (hwp_active) { intel_pstate_hwp_offline(cpu); - else + } else { intel_pstate_set_min_pstate(cpu); + policy->cur = cpu->pstate.min_freq; + } intel_pstate_exit_perf_limits(policy); @@ -3049,9 +3051,6 @@ static int __intel_pstate_cpu_init(struct cpufreq_policy *policy) policy->cpuinfo.max_freq = READ_ONCE(global.no_turbo) ? cpu->pstate.max_freq : cpu->pstate.turbo_freq; - policy->min = policy->cpuinfo.min_freq; - policy->max = policy->cpuinfo.max_freq; - intel_pstate_init_acpi_perf_limits(policy); policy->fast_switch_possible = true; @@ -3824,6 +3823,12 @@ static int __init intel_pstate_init(void) if (no_load) return -ENODEV; + id = x86_match_cpu(intel_hybrid_scaling_factor); + if (id) { + pr_info("HWP-disabled hybrid CPU is not supported\n"); + return -ENODEV; + } + id = x86_match_cpu(intel_pstate_cpu_ids); if (!id) { pr_info("CPU model not supported\n"); diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c index ac2e90a65f0c..83e6f73dc9a4 100644 --- a/drivers/cpufreq/pcc-cpufreq.c +++ b/drivers/cpufreq/pcc-cpufreq.c @@ -352,6 +352,8 @@ static int __init pcc_cpufreq_do_osc(acpi_handle *handle) } kfree(output.pointer); + output.pointer = NULL; + output.length = ACPI_ALLOCATE_BUFFER; capabilities[0] = 0x0; capabilities[1] = 0x1; @@ -551,13 +553,11 @@ static int pcc_cpufreq_cpu_init(struct cpufreq_policy *policy) goto out; } - policy->max = policy->cpuinfo.max_freq = - ioread32(&pcch_hdr->nominal) * 1000; - policy->min = policy->cpuinfo.min_freq = - ioread32(&pcch_hdr->minimum_frequency) * 1000; + policy->cpuinfo.max_freq = ioread32(&pcch_hdr->nominal) * 1000; + policy->cpuinfo.min_freq = ioread32(&pcch_hdr->minimum_frequency) * 1000; - pr_debug("init: policy->max is %d, policy->min is %d\n", - policy->max, policy->min); + pr_debug("init: max_freq is %d, min_freq is %d\n", + policy->cpuinfo.max_freq, policy->cpuinfo.min_freq); out: return result; } diff --git a/drivers/cpufreq/pxa3xx-cpufreq.c b/drivers/cpufreq/pxa3xx-cpufreq.c index 50ff3b6a6900..06b27cbc59d6 100644 --- a/drivers/cpufreq/pxa3xx-cpufreq.c +++ b/drivers/cpufreq/pxa3xx-cpufreq.c @@ -185,9 +185,8 @@ static int pxa3xx_cpufreq_init(struct cpufreq_policy *policy) int ret = -EINVAL; /* set default policy and cpuinfo */ - policy->min = policy->cpuinfo.min_freq = 104000; - policy->max = policy->cpuinfo.max_freq = - (cpu_is_pxa320()) ? 806000 : 624000; + policy->cpuinfo.min_freq = 104000; + policy->cpuinfo.max_freq = (cpu_is_pxa320()) ? 806000 : 624000; policy->cpuinfo.transition_latency = 1000; /* FIXME: 1 ms, assumed */ if (cpu_is_pxa300() || cpu_is_pxa310()) diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c index ea9a20d27b8f..874ff3fb9d97 100644 --- a/drivers/cpufreq/qcom-cpufreq-hw.c +++ b/drivers/cpufreq/qcom-cpufreq-hw.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2018, The Linux Foundation. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #include @@ -40,6 +41,7 @@ struct qcom_cpufreq_soc_data { u32 reg_intr_clr; u32 reg_current_vote; u32 reg_perf_state; + u32 lut_max_entries; u8 lut_row_size; }; @@ -156,7 +158,7 @@ static unsigned int qcom_cpufreq_get_freq(struct cpufreq_policy *policy) soc_data = qcom_cpufreq.soc_data; index = readl_relaxed(data->base + soc_data->reg_perf_state); - index = min(index, LUT_MAX_ENTRIES - 1); + index = min(index, soc_data->lut_max_entries - 1); return policy->freq_table[index].frequency; } @@ -211,7 +213,7 @@ static int qcom_cpufreq_hw_read_lut(struct device *cpu_dev, struct qcom_cpufreq_data *drv_data = policy->driver_data; const struct qcom_cpufreq_soc_data *soc_data = qcom_cpufreq.soc_data; - table = kzalloc_objs(*table, LUT_MAX_ENTRIES + 1); + table = kzalloc_objs(*table, soc_data->lut_max_entries + 1); if (!table) return -ENOMEM; @@ -236,7 +238,7 @@ static int qcom_cpufreq_hw_read_lut(struct device *cpu_dev, icc_scaling_enabled = false; } - for (i = 0; i < LUT_MAX_ENTRIES; i++) { + for (i = 0; i < soc_data->lut_max_entries; i++) { data = readl_relaxed(drv_data->base + soc_data->reg_freq_lut + i * soc_data->lut_row_size); src = FIELD_GET(LUT_SRC, data); @@ -405,6 +407,7 @@ static const struct qcom_cpufreq_soc_data qcom_soc_data = { .reg_current_vote = 0x704, .reg_perf_state = 0x920, .lut_row_size = 32, + .lut_max_entries = LUT_MAX_ENTRIES, }; static const struct qcom_cpufreq_soc_data epss_soc_data = { @@ -416,11 +419,25 @@ static const struct qcom_cpufreq_soc_data epss_soc_data = { .reg_intr_clr = 0x308, .reg_perf_state = 0x320, .lut_row_size = 4, + .lut_max_entries = LUT_MAX_ENTRIES, +}; + +static const struct qcom_cpufreq_soc_data shikra_epss_soc_data = { + .reg_enable = 0x0, + .reg_domain_state = 0x20, + .reg_dcvs_ctrl = 0xb0, + .reg_freq_lut = 0x100, + .reg_volt_lut = 0x200, + .reg_intr_clr = 0x308, + .reg_perf_state = 0x320, + .lut_row_size = 4, + .lut_max_entries = 12, }; static const struct of_device_id qcom_cpufreq_hw_match[] = { { .compatible = "qcom,cpufreq-hw", .data = &qcom_soc_data }, { .compatible = "qcom,cpufreq-epss", .data = &epss_soc_data }, + { .compatible = "qcom,shikra-epss", .data = &shikra_epss_soc_data }, {} }; MODULE_DEVICE_TABLE(of, qcom_cpufreq_hw_match); @@ -578,7 +595,6 @@ static void qcom_cpufreq_hw_cpu_exit(struct cpufreq_policy *policy) dev_pm_opp_of_cpumask_remove_table(policy->related_cpus); qcom_cpufreq_hw_lmh_exit(data); kfree(policy->freq_table); - kfree(data); } static void qcom_cpufreq_ready(struct cpufreq_policy *policy) diff --git a/drivers/cpufreq/sh-cpufreq.c b/drivers/cpufreq/sh-cpufreq.c index 642ddb9ea217..3c99d7009cbe 100644 --- a/drivers/cpufreq/sh-cpufreq.c +++ b/drivers/cpufreq/sh-cpufreq.c @@ -124,10 +124,8 @@ static int sh_cpufreq_cpu_init(struct cpufreq_policy *policy) dev_notice(dev, "no frequency table found, falling back " "to rate rounding.\n"); - policy->min = policy->cpuinfo.min_freq = - (clk_round_rate(cpuclk, 1) + 500) / 1000; - policy->max = policy->cpuinfo.max_freq = - (clk_round_rate(cpuclk, ~0UL) + 500) / 1000; + policy->cpuinfo.min_freq = (clk_round_rate(cpuclk, 1) + 500) / 1000; + policy->cpuinfo.max_freq = (clk_round_rate(cpuclk, ~0UL) + 500) / 1000; } return 0; diff --git a/drivers/cpufreq/ti-cpufreq.c b/drivers/cpufreq/ti-cpufreq.c index a01abc1622eb..0f96492341f2 100644 --- a/drivers/cpufreq/ti-cpufreq.c +++ b/drivers/cpufreq/ti-cpufreq.c @@ -99,6 +99,7 @@ struct ti_cpufreq_soc_data { unsigned long efuse_shift; unsigned long rev_offset; bool multi_regulator; + bool needs_k3_socinfo; /* Backward compatibility hack: Might have missing syscon */ #define TI_QUIRK_SYSCON_MAY_BE_MISSING 0x1 /* Backward compatibility hack: new syscon size is 1 register wide */ @@ -347,6 +348,7 @@ static struct ti_cpufreq_soc_data am625_soc_data = { .efuse_mask = 0x07c0, .efuse_shift = 0x6, .multi_regulator = false, + .needs_k3_socinfo = true, .quirks = TI_QUIRK_SYSCON_IS_SINGLE_REG, }; @@ -356,6 +358,7 @@ static struct ti_cpufreq_soc_data am62a7_soc_data = { .efuse_mask = 0x07c0, .efuse_shift = 0x6, .multi_regulator = false, + .needs_k3_socinfo = true, }; static struct ti_cpufreq_soc_data am62l3_soc_data = { @@ -364,6 +367,7 @@ static struct ti_cpufreq_soc_data am62l3_soc_data = { .efuse_mask = 0x07c0, .efuse_shift = 0x6, .multi_regulator = false, + .needs_k3_socinfo = true, }; static struct ti_cpufreq_soc_data am62p5_soc_data = { @@ -372,6 +376,7 @@ static struct ti_cpufreq_soc_data am62p5_soc_data = { .efuse_mask = 0x07c0, .efuse_shift = 0x6, .multi_regulator = false, + .needs_k3_socinfo = true, }; /** @@ -443,6 +448,11 @@ static int ti_cpufreq_get_rev(struct ti_cpufreq_data *opp_data, goto done; } + /* Defer if k3-socinfo hasn't registered the SoC device yet */ + if (opp_data->soc_data->needs_k3_socinfo) + return dev_err_probe(opp_data->cpu_dev, -EPROBE_DEFER, + "SoC device not registered by k3-socinfo\n"); + ret = regmap_read(opp_data->syscon, opp_data->soc_data->rev_offset, &revision); if (opp_data->soc_data->quirks & TI_QUIRK_SYSCON_MAY_BE_MISSING && ret == -EIO) { diff --git a/drivers/cpufreq/virtual-cpufreq.c b/drivers/cpufreq/virtual-cpufreq.c index 4159f31349b1..dc78b74409af 100644 --- a/drivers/cpufreq/virtual-cpufreq.c +++ b/drivers/cpufreq/virtual-cpufreq.c @@ -164,10 +164,7 @@ static int virt_cpufreq_get_freq_info(struct cpufreq_policy *policy) policy->cpuinfo.min_freq = 1; policy->cpuinfo.max_freq = virt_cpufreq_get_perftbl_entry(policy->cpu, 0); - policy->min = policy->cpuinfo.min_freq; - policy->max = policy->cpuinfo.max_freq; - - policy->cur = policy->max; + policy->cur = policy->cpuinfo.max_freq; return 0; } diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index f49354e37777..b2705d79a4ee 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -81,6 +81,11 @@ static bool ibrs_off __read_mostly; /* Maximum allowed C-state target residency */ #define MAX_CMDLINE_RESIDENCY_US (100 * USEC_PER_MSEC) +/* The Package C-State Limit bits in MSR_PKG_CST_CONFIG_CONTROL */ +#define SKX_PKG_CST_LIMIT_MASK GENMASK(2, 0) +/* PC6 is enabled when Package C-State Limit >= this value */ +#define SKX_PKG_CST_LIMIT_PC6 2 + static char cmdline_table_str[MAX_CMDLINE_TABLE_LEN] __read_mostly; static struct cpuidle_device __percpu *intel_idle_cpuidle_devices; @@ -2074,12 +2079,13 @@ static void __init sklh_idle_state_table_update(void) } /** - * skx_idle_state_table_update - Adjust the Sky Lake/Cascade Lake - * idle states table. + * skx_is_pc6_disabled() - Check if PC6 is disabled in BIOS. + * + * Return: %true if PC6 is disabled, %false otherwise. */ -static void __init skx_idle_state_table_update(void) +static bool __init skx_is_pc6_disabled(void) { - unsigned long long msr; + u64 msr; rdmsrq(MSR_PKG_CST_CONFIG_CONTROL, msr); @@ -2090,40 +2096,86 @@ static void __init skx_idle_state_table_update(void) * 011b: C6 (retention) * 111b: No Package C state limits. */ - if ((msr & 0x7) < 2) { - /* - * Uses the CC6 + PC0 latency and 3 times of - * latency for target_residency if the PC6 - * is disabled in BIOS. This is consistent - * with how intel_idle driver uses _CST - * to set the target_residency. - */ + return (msr & SKX_PKG_CST_LIMIT_MASK) < SKX_PKG_CST_LIMIT_PC6; +} + +/** + * skx_idle_state_table_update - Adjust the SKX/CLX idle states table. + * + * Adjust Sky Lake or Cascade Lake Xeon idle states if PC6 is disabled in BIOS. + * Use the CC6 + PC0 latency and 3 times of that latency for target_residency. + * This is consistent with how the intel_idle driver uses _CST to set the + * target_residency. + */ +static void __init skx_idle_state_table_update(void) +{ + if (skx_is_pc6_disabled()) { skx_cstates[2].exit_latency = 92; skx_cstates[2].target_residency = 276; } } /** - * spr_idle_state_table_update - Adjust Sapphire Rapids idle states table. + * spr_idle_state_table_update - Adjust Sapphire Rapids Xeon idle states table. + * + * By default, the C6 state assumes the worst-case scenario of package C6. + * However, if PC6 is disabled in BIOS, update the numbers to match core C6. */ static void __init spr_idle_state_table_update(void) { - unsigned long long msr; - - /* - * By default, the C6 state assumes the worst-case scenario of package - * C6. However, if PC6 is disabled, we update the numbers to match - * core C6. - */ - rdmsrq(MSR_PKG_CST_CONFIG_CONTROL, msr); - - /* Limit value 2 and above allow for PC6. */ - if ((msr & 0x7) < 2) { + if (skx_is_pc6_disabled()) { spr_cstates[2].exit_latency = 190; spr_cstates[2].target_residency = 600; } } +/** + * drop_pc6_redundant_cstates() - Drop C-states redundant when PC6 is disabled. + * @states: Idle states table to modify. + * + * When PC6 is disabled in BIOS, C-states that exist solely to enable PC6 + * entry (such as C6P or C6SP) become identical to shallower C-states like + * C6, and are therefore redundant. Should be called only on systems with + * multiple C6 flavors. + */ +static void __init drop_pc6_redundant_cstates(struct cpuidle_state *states) +{ + int count; + + if (!skx_is_pc6_disabled()) + /* PC6 is not disabled, nothing to do */ + return; + + for (count = 0; states[count].enter; count++) + continue; + + if (count < 2) { + pr_debug("Too few idle states to drop PC6-redundant states\n"); + return; + } + + /* + * Sanity check: At this point all platforms with multiple C6 flavors + * use the CPUIDLE_FLAG_PARTIAL_HINT_MATCH flag. And the last state in + * the table is the one that becomes redundant when PC6 is disabled. + */ + if (!(states[count - 1].flags & CPUIDLE_FLAG_PARTIAL_HINT_MATCH)) { + pr_debug("Can't drop PC6-redundant states: unexpected flags\n"); + return; + } + + /* + * On all current platforms with multiple C6 flavors, there is only one + * C-state that becomes redundant when PC6 is disabled. This state is + * the last one in the table. Drop it by marking it with + * CPUIDLE_FLAG_UNUSABLE so that cpuidle excludes it when registering + * idle states. + */ + pr_info("Dropping idle state %s because PC6 is disabled\n", + states[count - 1].name); + states[count - 1].flags |= CPUIDLE_FLAG_UNUSABLE; +} + /** * byt_cht_auto_demotion_disable - Disable Bay/Cherry Trail auto-demotion. */ @@ -2213,6 +2265,12 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv) case INTEL_ATOM_AIRMONT: byt_cht_auto_demotion_disable(); break; + case INTEL_GRANITERAPIDS_D: + case INTEL_GRANITERAPIDS_X: + case INTEL_ATOM_CRESTMONT_X: + case INTEL_ATOM_DARKMONT_X: + drop_pc6_redundant_cstates(cpuidle_state_table); + break; } for (cstate = 0; cstate < CPUIDLE_STATE_MAX; ++cstate) { diff --git a/drivers/opp/core.c b/drivers/opp/core.c index da3f5eba4341..ab0b0a2f85a1 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -2088,11 +2088,10 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, return ret; list_add(&new_opp->node, head); + new_opp->opp_table = opp_table; + kref_init(&new_opp->kref); } - new_opp->opp_table = opp_table; - kref_init(&new_opp->kref); - opp_debug_create_one(new_opp, opp_table); if (!_opp_supported_by_regulators(new_opp, opp_table)) { diff --git a/drivers/opp/of.c b/drivers/opp/of.c index f96adfd5b219..c02e20632fa6 100644 --- a/drivers/opp/of.c +++ b/drivers/opp/of.c @@ -673,7 +673,7 @@ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev, */ if (unlikely(opp_table->regulator_count == -1)) { opp_table->regulator_count = 0; - return 0; + goto free_microwatt; } for (i = 0, j = 0; i < opp_table->regulator_count; i++) { @@ -696,6 +696,7 @@ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev, opp->supplies[i].u_watt = microwatt[i]; } +free_microwatt: kfree(microwatt); free_microamp: kfree(microamp); diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c index a8dd02dff0a0..1006d183d508 100644 --- a/drivers/powercap/intel_rapl_common.c +++ b/drivers/powercap/intel_rapl_common.c @@ -1441,7 +1441,7 @@ static ssize_t cpumask_show(struct device *dev, } cpus_read_unlock(); - ret = cpumap_print_to_pagebuf(true, buf, cpu_mask); + ret = sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpu_mask)); free_cpumask_var(cpu_mask); @@ -1770,7 +1770,8 @@ struct rapl_package *rapl_add_package_cpuslocked(int id, struct rapl_if_priv *pr topology_physical_package_id(id) : topology_logical_die_id(id); if ((int)(rp->id) < 0) { pr_err("topology_logical_(package/die)_id() returned a negative value"); - return ERR_PTR(-EINVAL); + ret = -EINVAL; + goto err_free_package; } rp->lead_cpu = id; if (!rapl_msrs_are_pkg_scope() && topology_max_dies_per_package() > 1) diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 2ab691828e48..ae9d1ce4f49c 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -146,6 +146,9 @@ struct cpufreq_policy { /* Per policy boost supported flag. */ bool boost_supported; + /* Pending policy->min/max update for the driver */ + bool update_limits; + /* Cached frequency lookup from cpufreq_driver_resolve_freq. */ unsigned int cached_target_freq; unsigned int cached_resolved_idx; @@ -434,7 +437,7 @@ struct cpufreq_driver { /* * Set by drivers that need to update internal upper and lower boundaries along * with the target frequency and so the core and governors should also invoke - * the diver if the target frequency does not change, but the policy min or max + * the driver if the target frequency does not change, but the policy min or max * may have changed. */ #define CPUFREQ_NEED_UPDATE_LIMITS BIT(0) diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 05337f437cca..530c897311d4 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -42,6 +42,7 @@ config HIBERNATION select CRC32 select CRYPTO select CRYPTO_LZO + select CRYPTO_LZ4 help Enable the suspend to disk (STD) functionality, which is usually called "hibernation" in user interfaces. STD checkpoints the diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index af8d07bafe02..d2479c69d71a 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -392,23 +392,6 @@ static int create_image(int platform_mode) return error; } -static void shrink_shmem_memory(void) -{ - struct sysinfo info; - unsigned long nr_shmem_pages, nr_freed_pages; - - si_meminfo(&info); - nr_shmem_pages = info.sharedram; /* current page count used for shmem */ - /* - * The intent is to reclaim all shmem pages. Though shrink_all_memory() can - * only reclaim about half of them, it's enough for creating the hibernation - * image. - */ - nr_freed_pages = shrink_all_memory(nr_shmem_pages); - pr_debug("requested to reclaim %lu shmem pages, actually freed %lu pages\n", - nr_shmem_pages, nr_freed_pages); -} - /** * hibernation_snapshot - Quiesce devices and create a hibernation image. * @platform_mode: If set, use platform driver to prepare for the transition. @@ -425,14 +408,9 @@ int hibernation_snapshot(int platform_mode) if (error) goto Close; - /* Preallocate image memory before shutting down devices. */ - error = hibernate_preallocate_memory(); - if (error) - goto Close; - error = freeze_kernel_threads(); if (error) - goto Cleanup; + goto Close; if (hibernation_test(TEST_FREEZER)) { @@ -445,19 +423,13 @@ int hibernation_snapshot(int platform_mode) } error = dpm_prepare(PMSG_FREEZE); - if (error) { - dpm_complete(PMSG_RECOVER); - goto Thaw; - } + if (error) + goto Complete; - /* - * Device drivers may move lots of data to shmem in dpm_prepare(). The shmem - * pages will use lots of system memory, causing hibernation image creation - * fail due to insufficient free memory. - * This call is to force flush the shmem pages to swap disk and reclaim - * the system memory so that image creation can succeed. - */ - shrink_shmem_memory(); + /* Preallocate image memory before shutting down devices. */ + error = hibernate_preallocate_memory(); + if (error) + goto Complete; console_suspend_all(); pm_restrict_gfp_mask(); @@ -492,10 +464,10 @@ int hibernation_snapshot(int platform_mode) platform_end(platform_mode); return error; + Complete: + dpm_complete(PMSG_RECOVER); Thaw: thaw_kernel_threads(); - Cleanup: - swsusp_free(); goto Close; } diff --git a/kernel/power/qos.c b/kernel/power/qos.c index 398b994b73aa..1944dbeb0d4c 100644 --- a/kernel/power/qos.c +++ b/kernel/power/qos.c @@ -519,18 +519,23 @@ static int __init cpu_latency_qos_init(void) int ret; ret = misc_register(&cpu_latency_qos_miscdev); - if (ret < 0) + if (ret < 0) { pr_err("%s: %s setup failed\n", __func__, cpu_latency_qos_miscdev.name); + return ret; + } #ifdef CONFIG_PM_QOS_CPU_SYSTEM_WAKEUP ret = misc_register(&cpu_wakeup_latency_qos_miscdev); - if (ret < 0) + if (ret < 0) { pr_err("%s: %s setup failed\n", __func__, cpu_wakeup_latency_qos_miscdev.name); + misc_deregister(&cpu_latency_qos_miscdev); + return ret; + } #endif - return ret; + return 0; } late_initcall(cpu_latency_qos_init); #endif /* CONFIG_CPU_IDLE */ diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 2e64869bb5a0..b28233b8d00e 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -570,29 +570,23 @@ struct crc_data { wait_queue_head_t done; /* crc update done */ u32 *crc32; /* points to handle's crc32 */ size_t **unc_len; /* uncompressed lengths */ - unsigned char **unc; /* uncompressed data */ + unsigned char *unc[]; /* uncompressed data */ }; static struct crc_data *alloc_crc_data(int nr_threads) { struct crc_data *crc; - crc = kzalloc_obj(*crc); + crc = kzalloc_flex(*crc, unc, nr_threads); if (!crc) return NULL; - crc->unc = kcalloc(nr_threads, sizeof(*crc->unc), GFP_KERNEL); - if (!crc->unc) - goto err_free_crc; - crc->unc_len = kzalloc_objs(*crc->unc_len, nr_threads); if (!crc->unc_len) - goto err_free_unc; + goto err_free_crc; return crc; -err_free_unc: - kfree(crc->unc); err_free_crc: kfree(crc); return NULL; @@ -607,7 +601,6 @@ static void free_crc_data(struct crc_data *crc) kthread_stop(crc->thr); kfree(crc->unc_len); - kfree(crc->unc); kfree(crc); } diff --git a/rust/kernel/opp.rs b/rust/kernel/opp.rs index a760fac28765..62e44676125d 100644 --- a/rust/kernel/opp.rs +++ b/rust/kernel/opp.rs @@ -1042,11 +1042,13 @@ unsafe impl Sync for OPP {} /// SAFETY: The type invariants guarantee that [`OPP`] is always refcounted. unsafe impl AlwaysRefCounted for OPP { + #[inline] fn inc_ref(&self) { // SAFETY: The existence of a shared reference means that the refcount is nonzero. unsafe { bindings::dev_pm_opp_get(self.0.get()) }; } + #[inline] unsafe fn dec_ref(obj: ptr::NonNull) { // SAFETY: The safety requirements guarantee that the refcount is nonzero. unsafe { bindings::dev_pm_opp_put(obj.cast().as_ptr()) } @@ -1095,6 +1097,7 @@ fn as_raw(&self) -> *mut bindings::dev_pm_opp { } /// Returns the frequency of an [`OPP`]. + #[inline] pub fn freq(&self, index: Option) -> Hertz { let index = index.unwrap_or(0); diff --git a/tools/power/pm-graph/sleepgraph.py b/tools/power/pm-graph/sleepgraph.py index 1555b51a7d55..f6d172254829 100755 --- a/tools/power/pm-graph/sleepgraph.py +++ b/tools/power/pm-graph/sleepgraph.py @@ -3155,7 +3155,7 @@ class TestProps: dev = f[0] props[dev] = DevProps() props[dev].altname = f[1] - if int(f[2]): + if len(f) > 2 and f[2] and int(f[2]): props[dev].isasync = True else: props[dev].isasync = False