From 6cc3d0e9a097981c8a0317c65b8a2278593bd2b0 Mon Sep 17 00:00:00 2001 From: Mian Yousaf Kaukab Date: Wed, 23 Oct 2019 11:27:03 +0200 Subject: [PATCH 1/4] cpufreq: tegra186: add CPUFREQ_NEED_INITIAL_FREQ_CHECK flag The driver doesn't provide ->get() method to read current frequency and the frequency is set to 0 at initialization which makes the driver fail at initialization time. Set the CPUFREQ_NEED_INITIAL_FREQ_CHECK flag for the driver, so the cpufreq core checks for the unlisted frequency and sets the CPU to a valid frequency from the frequency table. Signed-off-by: Mian Yousaf Kaukab [ Viresh: Massaged change log ] Signed-off-by: Viresh Kumar --- drivers/cpufreq/tegra186-cpufreq.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/cpufreq/tegra186-cpufreq.c b/drivers/cpufreq/tegra186-cpufreq.c index 2e233ad72758..3d2f143748ef 100644 --- a/drivers/cpufreq/tegra186-cpufreq.c +++ b/drivers/cpufreq/tegra186-cpufreq.c @@ -93,7 +93,8 @@ static int tegra186_cpufreq_set_target(struct cpufreq_policy *policy, static struct cpufreq_driver tegra186_cpufreq_driver = { .name = "tegra186", - .flags = CPUFREQ_STICKY | CPUFREQ_HAVE_GOVERNOR_PER_POLICY, + .flags = CPUFREQ_STICKY | CPUFREQ_HAVE_GOVERNOR_PER_POLICY | + CPUFREQ_NEED_INITIAL_FREQ_CHECK, .verify = cpufreq_generic_frequency_table_verify, .target_index = tegra186_cpufreq_set_target, .init = tegra186_cpufreq_init, From cf6fada71543ceea0f6228ffdc0b85778f3f5a6e Mon Sep 17 00:00:00 2001 From: Xiongfeng Wang Date: Sat, 30 May 2020 10:08:30 +0800 Subject: [PATCH 2/4] cpufreq: change '.set_boost' to act on one policy Macro 'for_each_active_policy()' is defined internally. To avoid some cpufreq driver needing this macro to iterate over all the policies in '.set_boost' callback, we redefine '.set_boost' to act on only one policy and pass the policy as an argument. 'cpufreq_boost_trigger_state()' iterates over all the policies to set boost for the system. This is preparation for adding SW BOOST support for CPPC. To protect Boost enable/disable by sysfs from CPU online/offline, add 'cpu_hotplug_lock' before calling '.set_boost' for each CPU. Also move the lock from 'set_boost()' to 'store_cpb()' in acpi_cpufreq. Signed-off-by: Xiongfeng Wang Suggested-by: Viresh Kumar Acked-by: Viresh Kumar [ rjw: Subject & changelog ] Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/acpi-cpufreq.c | 14 +++++---- drivers/cpufreq/cpufreq.c | 57 ++++++++++++++++++---------------- include/linux/cpufreq.h | 2 +- 3 files changed, 40 insertions(+), 33 deletions(-) diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index 289e8ce3fd13..429e5a36c08a 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -126,12 +126,12 @@ static void boost_set_msr_each(void *p_en) boost_set_msr(enable); } -static int set_boost(int val) +static int set_boost(struct cpufreq_policy *policy, int val) { - get_online_cpus(); - on_each_cpu(boost_set_msr_each, (void *)(long)val, 1); - put_online_cpus(); - pr_debug("Core Boosting %sabled.\n", val ? "en" : "dis"); + on_each_cpu_mask(policy->cpus, boost_set_msr_each, + (void *)(long)val, 1); + pr_debug("CPU %*pbl: Core Boosting %sabled.\n", + cpumask_pr_args(policy->cpus), val ? "en" : "dis"); return 0; } @@ -162,7 +162,9 @@ static ssize_t store_cpb(struct cpufreq_policy *policy, const char *buf, if (ret || val > 1) return -EINVAL; - set_boost(val); + get_online_cpus(); + set_boost(policy, val); + put_online_cpus(); return count; } diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index d03f250f68e4..0128de3603df 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -2532,34 +2532,29 @@ EXPORT_SYMBOL_GPL(cpufreq_update_limits); /********************************************************************* * BOOST * *********************************************************************/ -static int cpufreq_boost_set_sw(int state) +static int cpufreq_boost_set_sw(struct cpufreq_policy *policy, int state) { - struct cpufreq_policy *policy; + int ret; - for_each_active_policy(policy) { - int ret; + if (!policy->freq_table) + return -ENXIO; - if (!policy->freq_table) - return -ENXIO; - - ret = cpufreq_frequency_table_cpuinfo(policy, - policy->freq_table); - if (ret) { - pr_err("%s: Policy frequency update failed\n", - __func__); - return ret; - } - - ret = freq_qos_update_request(policy->max_freq_req, policy->max); - if (ret < 0) - return ret; + ret = cpufreq_frequency_table_cpuinfo(policy, policy->freq_table); + if (ret) { + pr_err("%s: Policy frequency update failed\n", __func__); + return ret; } + ret = freq_qos_update_request(policy->max_freq_req, policy->max); + if (ret < 0) + return ret; + return 0; } int cpufreq_boost_trigger_state(int state) { + struct cpufreq_policy *policy; unsigned long flags; int ret = 0; @@ -2570,15 +2565,25 @@ int cpufreq_boost_trigger_state(int state) cpufreq_driver->boost_enabled = state; write_unlock_irqrestore(&cpufreq_driver_lock, flags); - ret = cpufreq_driver->set_boost(state); - if (ret) { - write_lock_irqsave(&cpufreq_driver_lock, flags); - cpufreq_driver->boost_enabled = !state; - write_unlock_irqrestore(&cpufreq_driver_lock, flags); - - pr_err("%s: Cannot %s BOOST\n", - __func__, state ? "enable" : "disable"); + get_online_cpus(); + for_each_active_policy(policy) { + ret = cpufreq_driver->set_boost(policy, state); + if (ret) + goto err_reset_state; } + put_online_cpus(); + + return 0; + +err_reset_state: + put_online_cpus(); + + write_lock_irqsave(&cpufreq_driver_lock, flags); + cpufreq_driver->boost_enabled = !state; + write_unlock_irqrestore(&cpufreq_driver_lock, flags); + + pr_err("%s: Cannot %s BOOST\n", + __func__, state ? "enable" : "disable"); return ret; } diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 67d5950bd878..3494f6763597 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -367,7 +367,7 @@ struct cpufreq_driver { /* platform specific boost support code */ bool boost_enabled; - int (*set_boost)(int state); + int (*set_boost)(struct cpufreq_policy *policy, int state); }; /* flags */ From 54e74df5d76dea824c7c0c9d1b97150bf9b33793 Mon Sep 17 00:00:00 2001 From: Xiongfeng Wang Date: Sat, 30 May 2020 10:08:31 +0800 Subject: [PATCH 3/4] cpufreq: CPPC: add SW BOOST support To add SW BOOST support for CPPC, we need to get the max frequency of boost mode and non-boost mode. ACPI spec 6.2 section 8.4.7.1 describes the following two CPC registers. "Highest performance is the absolute maximum performance an individual processor may reach, assuming ideal conditions. This performance level may not be sustainable for long durations, and may only be achievable if other platform components are in a specific state; for example, it may require other processors be in an idle state. Nominal Performance is the maximum sustained performance level of the processor, assuming ideal operating conditions. In absence of an external constraint (power, thermal, etc.) this is the performance level the platform is expected to be able to maintain continuously. All processors are expected to be able to sustain their nominal performance state simultaneously." To add SW BOOST support for CPPC, we can use Highest Performance as the max performance in boost mode and Nominal Performance as the max performance in non-boost mode. If the Highest Performance is greater than the Nominal Performance, we assume SW BOOST is supported. The current CPPC driver does not support SW BOOST and use 'Highest Performance' as the max performance the CPU can achieve. 'Nominal Performance' is used to convert 'performance' to 'frequency'. That means, if firmware enable boost and provide a value for Highest Performance which is greater than Nominal Performance, boost feature is enabled by default. Because SW BOOST is disabled by default, so, after this patch, boost feature is disabled by default even if boost is enabled by firmware. Signed-off-by: Xiongfeng Wang Suggested-by: Viresh Kumar Acked-by: Viresh Kumar [ rjw: Subject ] Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/cppc_cpufreq.c | 39 ++++++++++++++++++++++++++++++++-- 1 file changed, 37 insertions(+), 2 deletions(-) diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index bda0b2406fba..257d726a4456 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -37,6 +37,7 @@ * requested etc. */ static struct cppc_cpudata **all_cpu_data; +static bool boost_supported; struct cppc_workaround_oem_info { char oem_id[ACPI_OEM_ID_SIZE + 1]; @@ -310,7 +311,7 @@ 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_cpufreq_perf_to_khz(cpu, cpu->perf_caps.lowest_nonlinear_perf); - policy->max = cppc_cpufreq_perf_to_khz(cpu, cpu->perf_caps.highest_perf); + policy->max = cppc_cpufreq_perf_to_khz(cpu, cpu->perf_caps.nominal_perf); /* * Set cpuinfo.min_freq to Lowest to make the full range of performance @@ -318,7 +319,7 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy) * nonlinear perf */ policy->cpuinfo.min_freq = cppc_cpufreq_perf_to_khz(cpu, cpu->perf_caps.lowest_perf); - policy->cpuinfo.max_freq = cppc_cpufreq_perf_to_khz(cpu, cpu->perf_caps.highest_perf); + policy->cpuinfo.max_freq = cppc_cpufreq_perf_to_khz(cpu, cpu->perf_caps.nominal_perf); policy->transition_delay_us = cppc_cpufreq_get_transition_delay_us(cpu_num); policy->shared_type = cpu->shared_type; @@ -343,6 +344,13 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy) cpu->cur_policy = policy; + /* + * If 'highest_perf' is greater than 'nominal_perf', we assume CPU Boost + * is supported. + */ + if (cpu->perf_caps.highest_perf > cpu->perf_caps.nominal_perf) + boost_supported = true; + /* Set policy->cur to max now. The governors will adjust later. */ policy->cur = cppc_cpufreq_perf_to_khz(cpu, cpu->perf_caps.highest_perf); @@ -410,6 +418,32 @@ static unsigned int cppc_cpufreq_get_rate(unsigned int cpunum) return cppc_get_rate_from_fbctrs(cpu, fb_ctrs_t0, fb_ctrs_t1); } +static int cppc_cpufreq_set_boost(struct cpufreq_policy *policy, int state) +{ + struct cppc_cpudata *cpudata; + int ret; + + if (!boost_supported) { + pr_err("BOOST not supported by CPU or firmware\n"); + return -EINVAL; + } + + cpudata = all_cpu_data[policy->cpu]; + if (state) + policy->max = cppc_cpufreq_perf_to_khz(cpudata, + cpudata->perf_caps.highest_perf); + else + policy->max = cppc_cpufreq_perf_to_khz(cpudata, + cpudata->perf_caps.nominal_perf); + policy->cpuinfo.max_freq = policy->max; + + ret = freq_qos_update_request(policy->max_freq_req, policy->max); + if (ret < 0) + return ret; + + return 0; +} + static struct cpufreq_driver cppc_cpufreq_driver = { .flags = CPUFREQ_CONST_LOOPS, .verify = cppc_verify_policy, @@ -417,6 +451,7 @@ static struct cpufreq_driver cppc_cpufreq_driver = { .get = cppc_cpufreq_get_rate, .init = cppc_cpufreq_cpu_init, .stop_cpu = cppc_cpufreq_stop_cpu, + .set_boost = cppc_cpufreq_set_boost, .name = "cppc_cpufreq", }; From 956ad9d98b73f59e442cc119c98ba1e04e94fe6d Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 4 Jun 2020 19:22:26 +0200 Subject: [PATCH 4/4] ACPI: PM: Avoid using power resources if there are none for D0 As recently reported, some platforms provide a list of power resources for device power state D3hot, through the _PR3 object, but they do not provide a list of power resources for device power state D0. Among other things, this causes acpi_device_get_power() to return D3hot as the current state of the device in question if all of the D3hot power resources are "on", because it sees the power_resources flag set and calls acpi_power_get_inferred_state() which finds that D3hot is the shallowest power state with all of the associated power resources turned "on", so that's what it returns. Moreover, that value takes precedence over the acpi_dev_pm_explicit_get() return value, because it means a deeper power state. The device may very well be in D0 physically at that point, however. Moreover, the presence of _PR3 without _PR0 for a given device means that only one D3-level power state can be supported by it. Namely, because there are no power resources to turn "off" when transitioning the device from D0 into D3cold (which should be supported since _PR3 is present), the evaluation of _PS3 should be sufficient to put it straight into D3cold, but this means that the effect of turning "on" the _PR3 power resources is unclear, so it is better to avoid doing that altogether. Consequently, there is no practical way do distinguish D3cold from D3hot for the device in question and the power states of it can be labeled so that D3hot is the deepest supported one (and Linux assumes that putting a device into D3hot via ACPI may cause power to be removed from it anyway, for legacy reasons). To work around the problem described above modify the ACPI enumeration of devices so that power resources are only used for device power management if the list of D0 power resources is not empty and make it mart D3cold as supported only if that is the case and the D3hot list of power resources is not empty too. Fixes: ef85bdbec444 ("ACPI / scan: Consolidate extraction of power resources lists") Link: https://bugzilla.kernel.org/show_bug.cgi?id=205057 Link: https://lore.kernel.org/linux-acpi/20200603194659.185757-1-hdegoede@redhat.com/ Reported-by: Hans de Goede Tested-by: Hans de Goede Tested-by: youling257@gmail.com Cc: 3.10+ # 3.10+ Signed-off-by: Rafael J. Wysocki Reviewed-by: Hans de Goede --- drivers/acpi/device_pm.c | 2 +- drivers/acpi/scan.c | 28 +++++++++++++++++++--------- 2 files changed, 20 insertions(+), 10 deletions(-) diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index 5832bc10aca8..95e200b618bd 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -186,7 +186,7 @@ int acpi_device_set_power(struct acpi_device *device, int state) * possibly drop references to the power resources in use. */ state = ACPI_STATE_D3_HOT; - /* If _PR3 is not available, use D3hot as the target state. */ + /* If D3cold is not supported, use D3hot as the target state. */ if (!device->power.states[ACPI_STATE_D3_COLD].flags.valid) target_state = state; } else if (!device->power.states[state].flags.valid) { diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 6d3448895382..1b255e98de4d 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -919,12 +919,9 @@ static void acpi_bus_init_power_state(struct acpi_device *device, int state) if (buffer.length && package && package->type == ACPI_TYPE_PACKAGE - && package->package.count) { - int err = acpi_extract_power_resources(package, 0, - &ps->resources); - if (!err) - device->power.flags.power_resources = 1; - } + && package->package.count) + acpi_extract_power_resources(package, 0, &ps->resources); + ACPI_FREE(buffer.pointer); } @@ -971,14 +968,27 @@ static void acpi_bus_get_power_flags(struct acpi_device *device) acpi_bus_init_power_state(device, i); INIT_LIST_HEAD(&device->power.states[ACPI_STATE_D3_COLD].resources); - if (!list_empty(&device->power.states[ACPI_STATE_D3_HOT].resources)) - device->power.states[ACPI_STATE_D3_COLD].flags.valid = 1; - /* Set defaults for D0 and D3hot states (always valid) */ + /* Set the defaults for D0 and D3hot (always supported). */ device->power.states[ACPI_STATE_D0].flags.valid = 1; device->power.states[ACPI_STATE_D0].power = 100; device->power.states[ACPI_STATE_D3_HOT].flags.valid = 1; + /* + * Use power resources only if the D0 list of them is populated, because + * some platforms may provide _PR3 only to indicate D3cold support and + * in those cases the power resources list returned by it may be bogus. + */ + if (!list_empty(&device->power.states[ACPI_STATE_D0].resources)) { + device->power.flags.power_resources = 1; + /* + * D3cold is supported if the D3hot list of power resources is + * not empty. + */ + if (!list_empty(&device->power.states[ACPI_STATE_D3_HOT].resources)) + device->power.states[ACPI_STATE_D3_COLD].flags.valid = 1; + } + if (acpi_bus_init_power(device)) device->flags.power_manageable = 0; }