diff options
Diffstat (limited to 'drivers/thermal/intel')
19 files changed, 1000 insertions, 1039 deletions
diff --git a/drivers/thermal/intel/Kconfig b/drivers/thermal/intel/Kconfig index f0c845679250..cb7e7697cf1e 100644 --- a/drivers/thermal/intel/Kconfig +++ b/drivers/thermal/intel/Kconfig @@ -3,6 +3,9 @@ config INTEL_POWERCLAMP tristate "Intel PowerClamp idle injection driver" depends on X86 depends on CPU_SUP_INTEL + depends on CPU_IDLE + select POWERCAP + select IDLE_INJECT help Enable this to enable Intel PowerClamp idle injection driver. This enforce idle time which results in more package C-state residency. The @@ -12,11 +15,16 @@ config X86_THERMAL_VECTOR def_bool y depends on X86 && CPU_SUP_INTEL && X86_LOCAL_APIC +config INTEL_TCC + bool + depends on X86 + config X86_PKG_TEMP_THERMAL tristate "X86 package temperature thermal driver" depends on X86_THERMAL_VECTOR select THERMAL_GOV_USER_SPACE select THERMAL_WRITABLE_TRIPS + select INTEL_TCC default m help Enable this to register CPU digital sensor for package temperature as @@ -28,6 +36,7 @@ config INTEL_SOC_DTS_IOSF_CORE tristate depends on X86 && PCI select IOSF_MBI + select INTEL_TCC help This is becoming a common feature for Intel SoCs to expose the additional digital temperature sensors (DTSs) using side band interface (IOSF). This @@ -64,7 +73,8 @@ endmenu config INTEL_BXT_PMIC_THERMAL tristate "Intel Broxton PMIC thermal driver" - depends on X86 && INTEL_SOC_PMIC_BXTWC && REGMAP + depends on X86 && INTEL_SOC_PMIC_BXTWC + select REGMAP help Select this driver for Intel Broxton PMIC with ADC channels monitoring system temperature measurements and alerts. @@ -75,6 +85,7 @@ config INTEL_BXT_PMIC_THERMAL config INTEL_PCH_THERMAL tristate "Intel PCH Thermal Reporting Driver" depends on X86 && PCI + select THERMAL_ACPI if ACPI help Enable this to support thermal reporting on certain intel PCHs. Thermal reporting device will provide temperature reading, @@ -83,6 +94,7 @@ config INTEL_PCH_THERMAL config INTEL_TCC_COOLING tristate "Intel TCC offset cooling Driver" depends on X86 + select INTEL_TCC help Enable this to support system cooling by adjusting the effective TCC activation temperature via the TCC Offset register, which is widely diff --git a/drivers/thermal/intel/Makefile b/drivers/thermal/intel/Makefile index 9a8d8054f316..5d8833c82ab6 100644 --- a/drivers/thermal/intel/Makefile +++ b/drivers/thermal/intel/Makefile @@ -2,6 +2,7 @@ # # Makefile for various Intel thermal drivers. +obj-$(CONFIG_INTEL_TCC) += intel_tcc.o obj-$(CONFIG_INTEL_POWERCLAMP) += intel_powerclamp.o obj-$(CONFIG_X86_PKG_TEMP_THERMAL) += x86_pkg_temp_thermal.o obj-$(CONFIG_INTEL_SOC_DTS_IOSF_CORE) += intel_soc_dts_iosf.o diff --git a/drivers/thermal/intel/int340x_thermal/Kconfig b/drivers/thermal/intel/int340x_thermal/Kconfig index 5d046de96a5d..300ea53e9b33 100644 --- a/drivers/thermal/intel/int340x_thermal/Kconfig +++ b/drivers/thermal/intel/int340x_thermal/Kconfig @@ -9,7 +9,9 @@ config INT340X_THERMAL select THERMAL_GOV_USER_SPACE select ACPI_THERMAL_REL select ACPI_FAN + select THERMAL_ACPI select INTEL_SOC_DTS_IOSF_CORE + select INTEL_TCC select PROC_THERMAL_MMIO_RAPL if POWERCAP help Newer laptops and tablets that use ACPI may have thermal sensors and diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c index db8a6f63657d..d0295123cc3e 100644 --- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c +++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c @@ -60,6 +60,7 @@ struct int3400_thermal_priv { int odvp_count; int *odvp; u32 os_uuid_mask; + int production_mode; struct odvp_attr *odvp_attrs; }; @@ -130,10 +131,7 @@ static ssize_t available_uuids_show(struct device *dev, for (i = 0; i < INT3400_THERMAL_MAXIMUM_UUID; i++) { if (priv->uuid_bitmap & (1 << i)) - length += scnprintf(&buf[length], - PAGE_SIZE - length, - "%s\n", - int3400_thermal_uuids[i]); + length += sysfs_emit_at(buf, length, int3400_thermal_uuids[i]); } return length; @@ -151,10 +149,7 @@ static ssize_t current_uuid_show(struct device *dev, for (i = 0; i <= INT3400_THERMAL_CRITICAL; i++) { if (priv->os_uuid_mask & BIT(i)) - length += scnprintf(&buf[length], - PAGE_SIZE - length, - "%s\n", - int3400_thermal_uuids[i]); + length += sysfs_emit_at(buf, length, int3400_thermal_uuids[i]); } if (length) @@ -315,6 +310,44 @@ end: return result; } +static ssize_t production_mode_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct int3400_thermal_priv *priv = dev_get_drvdata(dev); + + return sysfs_emit(buf, "%d\n", priv->production_mode); +} + +static DEVICE_ATTR_RO(production_mode); + +static int production_mode_init(struct int3400_thermal_priv *priv) +{ + unsigned long long mode; + acpi_status status; + int ret; + + priv->production_mode = -1; + + status = acpi_evaluate_integer(priv->adev->handle, "DCFG", NULL, &mode); + /* If the method is not present, this is not an error */ + if (ACPI_FAILURE(status)) + return 0; + + ret = sysfs_create_file(&priv->pdev->dev.kobj, &dev_attr_production_mode.attr); + if (ret) + return ret; + + priv->production_mode = mode; + + return 0; +} + +static void production_mode_exit(struct int3400_thermal_priv *priv) +{ + if (priv->production_mode >= 0) + sysfs_remove_file(&priv->pdev->dev.kobj, &dev_attr_production_mode.attr); +} + static ssize_t odvp_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -610,8 +643,15 @@ static int int3400_thermal_probe(struct platform_device *pdev) if (result) goto free_sysfs; + result = production_mode_init(priv); + if (result) + goto free_notify; + return 0; +free_notify: + acpi_remove_notify_handler(priv->adev->handle, ACPI_DEVICE_NOTIFY, + int3400_notify); free_sysfs: cleanup_odvp(priv); if (!ZERO_OR_NULL_PTR(priv->data_vault)) { @@ -638,6 +678,8 @@ static int int3400_thermal_remove(struct platform_device *pdev) { struct int3400_thermal_priv *priv = platform_get_drvdata(pdev); + production_mode_exit(priv); + acpi_remove_notify_handler( priv->adev->handle, ACPI_DEVICE_NOTIFY, int3400_notify); diff --git a/drivers/thermal/intel/int340x_thermal/int3403_thermal.c b/drivers/thermal/intel/int340x_thermal/int3403_thermal.c index 71d084c4c456..e418d270bc76 100644 --- a/drivers/thermal/intel/int340x_thermal/int3403_thermal.c +++ b/drivers/thermal/intel/int340x_thermal/int3403_thermal.c @@ -69,7 +69,7 @@ static void int3403_notify(acpi_handle handle, THERMAL_TRIP_VIOLATED); break; case INT3403_PERF_TRIP_POINT_CHANGED: - int340x_thermal_read_trips(obj->int340x_zone); + int340x_thermal_update_trips(obj->int340x_zone); int340x_thermal_zone_device_update(obj->int340x_zone, THERMAL_TRIP_CHANGED); break; diff --git a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c index 62c0aa5d0783..00665967ca52 100644 --- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c +++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c @@ -18,9 +18,6 @@ static int int340x_thermal_get_zone_temp(struct thermal_zone_device *zone, unsigned long long tmp; acpi_status status; - if (d->override_ops && d->override_ops->get_temp) - return d->override_ops->get_temp(zone, temp); - status = acpi_evaluate_integer(d->adev->handle, "_TMP", NULL, &tmp); if (ACPI_FAILURE(status)) return -EIO; @@ -32,117 +29,30 @@ static int int340x_thermal_get_zone_temp(struct thermal_zone_device *zone, if (conv_temp < 0) return conv_temp; - *temp = (unsigned long)conv_temp * 10; - } else + *temp = conv_temp * 10; + } else { /* _TMP returns the temperature in tenths of degrees Kelvin */ *temp = deci_kelvin_to_millicelsius(tmp); - - return 0; -} - -static int int340x_thermal_get_trip_temp(struct thermal_zone_device *zone, - int trip, int *temp) -{ - struct int34x_thermal_zone *d = zone->devdata; - int i; - - if (d->override_ops && d->override_ops->get_trip_temp) - return d->override_ops->get_trip_temp(zone, trip, temp); - - if (trip < d->aux_trip_nr) - *temp = d->aux_trips[trip]; - else if (trip == d->crt_trip_id) - *temp = d->crt_temp; - else if (trip == d->psv_trip_id) - *temp = d->psv_temp; - else if (trip == d->hot_trip_id) - *temp = d->hot_temp; - else { - for (i = 0; i < INT340X_THERMAL_MAX_ACT_TRIP_COUNT; i++) { - if (d->act_trips[i].valid && - d->act_trips[i].id == trip) { - *temp = d->act_trips[i].temp; - break; - } - } - if (i == INT340X_THERMAL_MAX_ACT_TRIP_COUNT) - return -EINVAL; - } - - return 0; -} - -static int int340x_thermal_get_trip_type(struct thermal_zone_device *zone, - int trip, - enum thermal_trip_type *type) -{ - struct int34x_thermal_zone *d = zone->devdata; - int i; - - if (d->override_ops && d->override_ops->get_trip_type) - return d->override_ops->get_trip_type(zone, trip, type); - - if (trip < d->aux_trip_nr) - *type = THERMAL_TRIP_PASSIVE; - else if (trip == d->crt_trip_id) - *type = THERMAL_TRIP_CRITICAL; - else if (trip == d->hot_trip_id) - *type = THERMAL_TRIP_HOT; - else if (trip == d->psv_trip_id) - *type = THERMAL_TRIP_PASSIVE; - else { - for (i = 0; i < INT340X_THERMAL_MAX_ACT_TRIP_COUNT; i++) { - if (d->act_trips[i].valid && - d->act_trips[i].id == trip) { - *type = THERMAL_TRIP_ACTIVE; - break; - } - } - if (i == INT340X_THERMAL_MAX_ACT_TRIP_COUNT) - return -EINVAL; } return 0; } static int int340x_thermal_set_trip_temp(struct thermal_zone_device *zone, - int trip, int temp) + int trip, int temp) { struct int34x_thermal_zone *d = zone->devdata; + char name[] = {'P', 'A', 'T', '0' + trip, '\0'}; acpi_status status; - char name[10]; - if (d->override_ops && d->override_ops->set_trip_temp) - return d->override_ops->set_trip_temp(zone, trip, temp); + if (trip > 9) + return -EINVAL; - snprintf(name, sizeof(name), "PAT%d", trip); status = acpi_execute_simple_method(d->adev->handle, name, - millicelsius_to_deci_kelvin(temp)); + millicelsius_to_deci_kelvin(temp)); if (ACPI_FAILURE(status)) return -EIO; - d->aux_trips[trip] = temp; - - return 0; -} - - -static int int340x_thermal_get_trip_hyst(struct thermal_zone_device *zone, - int trip, int *temp) -{ - struct int34x_thermal_zone *d = zone->devdata; - acpi_status status; - unsigned long long hyst; - - if (d->override_ops && d->override_ops->get_trip_hyst) - return d->override_ops->get_trip_hyst(zone, trip, temp); - - status = acpi_evaluate_integer(d->adev->handle, "GTSH", NULL, &hyst); - if (ACPI_FAILURE(status)) - *temp = 0; - else - *temp = hyst * 100; - return 0; } @@ -153,63 +63,49 @@ static void int340x_thermal_critical(struct thermal_zone_device *zone) static struct thermal_zone_device_ops int340x_thermal_zone_ops = { .get_temp = int340x_thermal_get_zone_temp, - .get_trip_temp = int340x_thermal_get_trip_temp, - .get_trip_type = int340x_thermal_get_trip_type, .set_trip_temp = int340x_thermal_set_trip_temp, - .get_trip_hyst = int340x_thermal_get_trip_hyst, .critical = int340x_thermal_critical, }; -static int int340x_thermal_get_trip_config(acpi_handle handle, char *name, - int *temp) +static int int340x_thermal_read_trips(struct acpi_device *zone_adev, + struct thermal_trip *zone_trips, + int trip_cnt) { - unsigned long long r; - acpi_status status; - - status = acpi_evaluate_integer(handle, name, NULL, &r); - if (ACPI_FAILURE(status)) - return -EIO; - - *temp = deci_kelvin_to_millicelsius(r); + int i, ret; - return 0; -} - -int int340x_thermal_read_trips(struct int34x_thermal_zone *int34x_zone) -{ - int trip_cnt = int34x_zone->aux_trip_nr; - int i; - - int34x_zone->crt_trip_id = -1; - if (!int340x_thermal_get_trip_config(int34x_zone->adev->handle, "_CRT", - &int34x_zone->crt_temp)) - int34x_zone->crt_trip_id = trip_cnt++; + ret = thermal_acpi_critical_trip_temp(zone_adev, + &zone_trips[trip_cnt].temperature); + if (!ret) { + zone_trips[trip_cnt].type = THERMAL_TRIP_CRITICAL; + trip_cnt++; + } - int34x_zone->hot_trip_id = -1; - if (!int340x_thermal_get_trip_config(int34x_zone->adev->handle, "_HOT", - &int34x_zone->hot_temp)) - int34x_zone->hot_trip_id = trip_cnt++; + ret = thermal_acpi_hot_trip_temp(zone_adev, + &zone_trips[trip_cnt].temperature); + if (!ret) { + zone_trips[trip_cnt].type = THERMAL_TRIP_HOT; + trip_cnt++; + } - int34x_zone->psv_trip_id = -1; - if (!int340x_thermal_get_trip_config(int34x_zone->adev->handle, "_PSV", - &int34x_zone->psv_temp)) - int34x_zone->psv_trip_id = trip_cnt++; + ret = thermal_acpi_passive_trip_temp(zone_adev, + &zone_trips[trip_cnt].temperature); + if (!ret) { + zone_trips[trip_cnt].type = THERMAL_TRIP_PASSIVE; + trip_cnt++; + } for (i = 0; i < INT340X_THERMAL_MAX_ACT_TRIP_COUNT; i++) { - char name[5] = { '_', 'A', 'C', '0' + i, '\0' }; - - if (int340x_thermal_get_trip_config(int34x_zone->adev->handle, - name, - &int34x_zone->act_trips[i].temp)) + ret = thermal_acpi_active_trip_temp(zone_adev, i, + &zone_trips[trip_cnt].temperature); + if (ret) break; - int34x_zone->act_trips[i].id = trip_cnt++; - int34x_zone->act_trips[i].valid = true; + zone_trips[trip_cnt].type = THERMAL_TRIP_ACTIVE; + trip_cnt++; } return trip_cnt; } -EXPORT_SYMBOL_GPL(int340x_thermal_read_trips); static struct thermal_zone_params int340x_thermal_params = { .governor_name = "user_space", @@ -217,85 +113,147 @@ static struct thermal_zone_params int340x_thermal_params = { }; struct int34x_thermal_zone *int340x_thermal_zone_add(struct acpi_device *adev, - struct thermal_zone_device_ops *override_ops) + int (*get_temp) (struct thermal_zone_device *, int *)) { - struct int34x_thermal_zone *int34x_thermal_zone; - acpi_status status; - unsigned long long trip_cnt; + struct int34x_thermal_zone *int34x_zone; + struct thermal_trip *zone_trips; + unsigned long long trip_cnt = 0; + unsigned long long hyst; int trip_mask = 0; - int ret; + acpi_status status; + int i, ret; - int34x_thermal_zone = kzalloc(sizeof(*int34x_thermal_zone), - GFP_KERNEL); - if (!int34x_thermal_zone) + int34x_zone = kzalloc(sizeof(*int34x_zone), GFP_KERNEL); + if (!int34x_zone) return ERR_PTR(-ENOMEM); - int34x_thermal_zone->adev = adev; - int34x_thermal_zone->override_ops = override_ops; + int34x_zone->adev = adev; + + int34x_zone->ops = kmemdup(&int340x_thermal_zone_ops, + sizeof(int340x_thermal_zone_ops), GFP_KERNEL); + if (!int34x_zone->ops) { + ret = -ENOMEM; + goto err_ops_alloc; + } + + if (get_temp) + int34x_zone->ops->get_temp = get_temp; status = acpi_evaluate_integer(adev->handle, "PATC", NULL, &trip_cnt); - if (ACPI_FAILURE(status)) - trip_cnt = 0; - else { - int i; - - int34x_thermal_zone->aux_trips = - kcalloc(trip_cnt, - sizeof(*int34x_thermal_zone->aux_trips), - GFP_KERNEL); - if (!int34x_thermal_zone->aux_trips) { - ret = -ENOMEM; - goto err_trip_alloc; - } + if (ACPI_SUCCESS(status)) { + int34x_zone->aux_trip_nr = trip_cnt; trip_mask = BIT(trip_cnt) - 1; - int34x_thermal_zone->aux_trip_nr = trip_cnt; - for (i = 0; i < trip_cnt; ++i) - int34x_thermal_zone->aux_trips[i] = THERMAL_TEMP_INVALID; } - trip_cnt = int340x_thermal_read_trips(int34x_thermal_zone); + zone_trips = kzalloc(sizeof(*zone_trips) * (trip_cnt + INT340X_THERMAL_MAX_TRIP_COUNT), + GFP_KERNEL); + if (!zone_trips) { + ret = -ENOMEM; + goto err_trips_alloc; + } + + for (i = 0; i < trip_cnt; i++) { + zone_trips[i].type = THERMAL_TRIP_PASSIVE; + zone_trips[i].temperature = THERMAL_TEMP_INVALID; + } + + trip_cnt = int340x_thermal_read_trips(adev, zone_trips, trip_cnt); - int34x_thermal_zone->lpat_table = acpi_lpat_get_conversion_table( - adev->handle); + status = acpi_evaluate_integer(adev->handle, "GTSH", NULL, &hyst); + if (ACPI_SUCCESS(status)) + hyst *= 100; + else + hyst = 0; + + for (i = 0; i < trip_cnt; ++i) + zone_trips[i].hysteresis = hyst; + + int34x_zone->trips = zone_trips; - int34x_thermal_zone->zone = thermal_zone_device_register( - acpi_device_bid(adev), - trip_cnt, - trip_mask, int34x_thermal_zone, - &int340x_thermal_zone_ops, - &int340x_thermal_params, - 0, 0); - if (IS_ERR(int34x_thermal_zone->zone)) { - ret = PTR_ERR(int34x_thermal_zone->zone); + int34x_zone->lpat_table = acpi_lpat_get_conversion_table(adev->handle); + + int34x_zone->zone = thermal_zone_device_register_with_trips( + acpi_device_bid(adev), + zone_trips, trip_cnt, + trip_mask, int34x_zone, + int34x_zone->ops, + &int340x_thermal_params, + 0, 0); + if (IS_ERR(int34x_zone->zone)) { + ret = PTR_ERR(int34x_zone->zone); goto err_thermal_zone; } - ret = thermal_zone_device_enable(int34x_thermal_zone->zone); + ret = thermal_zone_device_enable(int34x_zone->zone); if (ret) goto err_enable; - return int34x_thermal_zone; + return int34x_zone; err_enable: - thermal_zone_device_unregister(int34x_thermal_zone->zone); + thermal_zone_device_unregister(int34x_zone->zone); err_thermal_zone: - acpi_lpat_free_conversion_table(int34x_thermal_zone->lpat_table); - kfree(int34x_thermal_zone->aux_trips); -err_trip_alloc: - kfree(int34x_thermal_zone); + kfree(int34x_zone->trips); + acpi_lpat_free_conversion_table(int34x_zone->lpat_table); +err_trips_alloc: + kfree(int34x_zone->ops); +err_ops_alloc: + kfree(int34x_zone); return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(int340x_thermal_zone_add); -void int340x_thermal_zone_remove(struct int34x_thermal_zone - *int34x_thermal_zone) +void int340x_thermal_zone_remove(struct int34x_thermal_zone *int34x_zone) { - thermal_zone_device_unregister(int34x_thermal_zone->zone); - acpi_lpat_free_conversion_table(int34x_thermal_zone->lpat_table); - kfree(int34x_thermal_zone->aux_trips); - kfree(int34x_thermal_zone); + thermal_zone_device_unregister(int34x_zone->zone); + acpi_lpat_free_conversion_table(int34x_zone->lpat_table); + kfree(int34x_zone->trips); + kfree(int34x_zone->ops); + kfree(int34x_zone); } EXPORT_SYMBOL_GPL(int340x_thermal_zone_remove); +void int340x_thermal_update_trips(struct int34x_thermal_zone *int34x_zone) +{ + struct acpi_device *zone_adev = int34x_zone->adev; + struct thermal_trip *zone_trips = int34x_zone->trips; + int trip_cnt = int34x_zone->zone->num_trips; + int act_trip_nr = 0; + int i; + + mutex_lock(&int34x_zone->zone->lock); + + for (i = int34x_zone->aux_trip_nr; i < trip_cnt; i++) { + int temp, err; + + switch (zone_trips[i].type) { + case THERMAL_TRIP_CRITICAL: + err = thermal_acpi_critical_trip_temp(zone_adev, &temp); + break; + case THERMAL_TRIP_HOT: + err = thermal_acpi_hot_trip_temp(zone_adev, &temp); + break; + case THERMAL_TRIP_PASSIVE: + err = thermal_acpi_passive_trip_temp(zone_adev, &temp); + break; + case THERMAL_TRIP_ACTIVE: + err = thermal_acpi_active_trip_temp(zone_adev, act_trip_nr++, + &temp); + break; + default: + err = -ENODEV; + } + if (err) { + zone_trips[i].temperature = THERMAL_TEMP_INVALID; + continue; + } + + zone_trips[i].temperature = temp; + } + + mutex_unlock(&int34x_zone->zone->lock); +} +EXPORT_SYMBOL_GPL(int340x_thermal_update_trips); + MODULE_AUTHOR("Aaron Lu <aaron.lu@intel.com>"); MODULE_AUTHOR("Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>"); MODULE_DESCRIPTION("Intel INT340x common thermal zone handler"); diff --git a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.h b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.h index 3b4971df1b33..e0df6271facc 100644 --- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.h +++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.h @@ -10,6 +10,7 @@ #include <acpi/acpi_lpat.h> #define INT340X_THERMAL_MAX_ACT_TRIP_COUNT 10 +#define INT340X_THERMAL_MAX_TRIP_COUNT INT340X_THERMAL_MAX_ACT_TRIP_COUNT + 3 struct active_trip { int temp; @@ -19,25 +20,18 @@ struct active_trip { struct int34x_thermal_zone { struct acpi_device *adev; - struct active_trip act_trips[INT340X_THERMAL_MAX_ACT_TRIP_COUNT]; - unsigned long *aux_trips; + struct thermal_trip *trips; int aux_trip_nr; - int psv_temp; - int psv_trip_id; - int crt_temp; - int crt_trip_id; - int hot_temp; - int hot_trip_id; struct thermal_zone_device *zone; - struct thermal_zone_device_ops *override_ops; + struct thermal_zone_device_ops *ops; void *priv_data; struct acpi_lpat_conversion_table *lpat_table; }; struct int34x_thermal_zone *int340x_thermal_zone_add(struct acpi_device *, - struct thermal_zone_device_ops *override_ops); + int (*get_temp) (struct thermal_zone_device *, int *)); void int340x_thermal_zone_remove(struct int34x_thermal_zone *); -int int340x_thermal_read_trips(struct int34x_thermal_zone *int34x_zone); +void int340x_thermal_update_trips(struct int34x_thermal_zone *int34x_zone); static inline void int340x_thermal_zone_set_priv_data( struct int34x_thermal_zone *tzone, void *priv_data) diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c index a8d98f1bd6c6..a1dc18be7609 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c @@ -4,6 +4,7 @@ * Copyright (c) 2014, Intel Corporation. */ #include <linux/acpi.h> +#include <linux/intel_tcc.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/pci.h> @@ -68,54 +69,17 @@ static const struct attribute_group power_limit_attribute_group = { .name = "power_limits" }; -static int tcc_get_offset(void) -{ - u64 val; - int err; - - err = rdmsrl_safe(MSR_IA32_TEMPERATURE_TARGET, &val); - if (err) - return err; - - return (val >> 24) & 0x3f; -} - static ssize_t tcc_offset_degree_celsius_show(struct device *dev, struct device_attribute *attr, char *buf) { - int tcc; - - tcc = tcc_get_offset(); - if (tcc < 0) - return tcc; - - return sprintf(buf, "%d\n", tcc); -} - -static int tcc_offset_update(unsigned int tcc) -{ - u64 val; - int err; + int offset; - if (tcc > 63) - return -EINVAL; - - err = rdmsrl_safe(MSR_IA32_TEMPERATURE_TARGET, &val); - if (err) - return err; + offset = intel_tcc_get_offset(-1); + if (offset < 0) + return offset; - if (val & BIT(31)) - return -EPERM; - - val &= ~GENMASK_ULL(29, 24); - val |= (tcc & 0x3f) << 24; - - err = wrmsrl_safe(MSR_IA32_TEMPERATURE_TARGET, val); - if (err) - return err; - - return 0; + return sprintf(buf, "%d\n", offset); } static ssize_t tcc_offset_degree_celsius_store(struct device *dev, @@ -136,7 +100,7 @@ static ssize_t tcc_offset_degree_celsius_store(struct device *dev, if (kstrtouint(buf, 0, &tcc)) return -EINVAL; - err = tcc_offset_update(tcc); + err = intel_tcc_set_offset(-1, tcc); if (err) return err; @@ -145,72 +109,27 @@ static ssize_t tcc_offset_degree_celsius_store(struct device *dev, static DEVICE_ATTR_RW(tcc_offset_degree_celsius); -static int stored_tjmax; /* since it is fixed, we can have local storage */ - -static int get_tjmax(void) -{ - u32 eax, edx; - u32 val; - int err; - - err = rdmsr_safe(MSR_IA32_TEMPERATURE_TARGET, &eax, &edx); - if (err) - return err; - - val = (eax >> 16) & 0xff; - if (val) - return val; - - return -EINVAL; -} - -static int read_temp_msr(int *temp) +static int proc_thermal_get_zone_temp(struct thermal_zone_device *zone, + int *temp) { int cpu; - u32 eax, edx; - int err; - unsigned long curr_temp_off = 0; + int curr_temp; *temp = 0; for_each_online_cpu(cpu) { - err = rdmsr_safe_on_cpu(cpu, MSR_IA32_THERM_STATUS, &eax, - &edx); - if (err) - goto err_ret; - else { - if (eax & 0x80000000) { - curr_temp_off = (eax >> 16) & 0x7f; - if (!*temp || curr_temp_off < *temp) - *temp = curr_temp_off; - } else { - err = -EINVAL; - goto err_ret; - } - } + curr_temp = intel_tcc_get_temp(cpu, false); + if (curr_temp < 0) + return curr_temp; + if (!*temp || curr_temp > *temp) + *temp = curr_temp; } - return 0; -err_ret: - return err; -} + *temp *= 1000; -static int proc_thermal_get_zone_temp(struct thermal_zone_device *zone, - int *temp) -{ - int ret; - - ret = read_temp_msr(temp); - if (!ret) - *temp = (stored_tjmax - *temp) * 1000; - - return ret; + return 0; } -static struct thermal_zone_device_ops proc_thermal_local_ops = { - .get_temp = proc_thermal_get_zone_temp, -}; - static int proc_thermal_read_ppcc(struct proc_thermal_device *proc_priv) { int i; @@ -285,7 +204,7 @@ int proc_thermal_add(struct device *dev, struct proc_thermal_device *proc_priv) struct acpi_device *adev; acpi_status status; unsigned long long tmp; - struct thermal_zone_device_ops *ops = NULL; + int (*get_temp) (struct thermal_zone_device *, int *) = NULL; int ret; adev = ACPI_COMPANION(dev); @@ -302,12 +221,11 @@ int proc_thermal_add(struct device *dev, struct proc_thermal_device *proc_priv) status = acpi_evaluate_integer(adev->handle, "_TMP", NULL, &tmp); if (ACPI_FAILURE(status)) { /* there is no _TMP method, add local method */ - stored_tjmax = get_tjmax(); - if (stored_tjmax > 0) - ops = &proc_thermal_local_ops; + if (intel_tcc_get_tjmax(-1) > 0) + get_temp = proc_thermal_get_zone_temp; } - proc_priv->int340x_zone = int340x_thermal_zone_add(adev, ops); + proc_priv->int340x_zone = int340x_thermal_zone_add(adev, get_temp); if (IS_ERR(proc_priv->int340x_zone)) { return PTR_ERR(proc_priv->int340x_zone); } else @@ -356,7 +274,7 @@ static int tcc_offset_save = -1; int proc_thermal_suspend(struct device *dev) { - tcc_offset_save = tcc_get_offset(); + tcc_offset_save = intel_tcc_get_offset(-1); if (tcc_offset_save < 0) dev_warn(dev, "failed to save offset (%d)\n", tcc_offset_save); @@ -373,7 +291,7 @@ int proc_thermal_resume(struct device *dev) /* Do not update if saving failed */ if (tcc_offset_save >= 0) - tcc_offset_update(tcc_offset_save); + intel_tcc_set_offset(-1, tcc_offset_save); return 0; } @@ -460,6 +378,7 @@ void proc_thermal_mmio_remove(struct pci_dev *pdev, struct proc_thermal_device * } EXPORT_SYMBOL_GPL(proc_thermal_mmio_remove); +MODULE_IMPORT_NS(INTEL_TCC); MODULE_AUTHOR("Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>"); MODULE_DESCRIPTION("Processor Thermal Reporting Device Driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c index bf1b1cdfade4..40725cbc6eb0 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c @@ -144,34 +144,6 @@ static int sys_get_curr_temp(struct thermal_zone_device *tzd, int *temp) return 0; } -static int sys_get_trip_temp(struct thermal_zone_device *tzd, - int trip, int *temp) -{ - struct proc_thermal_pci *pci_info = tzd->devdata; - u32 _temp; - - proc_thermal_mmio_read(pci_info, PROC_THERMAL_MMIO_THRES_0, &_temp); - if (!_temp) { - *temp = THERMAL_TEMP_INVALID; - } else { - int tjmax; - - proc_thermal_mmio_read(pci_info, PROC_THERMAL_MMIO_TJMAX, &tjmax); - _temp = tjmax - _temp; - *temp = (unsigned long)_temp * 1000; - } - - return 0; -} - -static int sys_get_trip_type(struct thermal_zone_device *tzd, int trip, - enum thermal_trip_type *type) -{ - *type = THERMAL_TRIP_PASSIVE; - - return 0; -} - static int sys_set_trip_temp(struct thermal_zone_device *tzd, int trip, int temp) { struct proc_thermal_pci *pci_info = tzd->devdata; @@ -200,10 +172,26 @@ static int sys_set_trip_temp(struct thermal_zone_device *tzd, int trip, int temp return 0; } +static int get_trip_temp(struct proc_thermal_pci *pci_info) +{ + int temp, tjmax; + + proc_thermal_mmio_read(pci_info, PROC_THERMAL_MMIO_THRES_0, &temp); + if (!temp) + return THERMAL_TEMP_INVALID; + + proc_thermal_mmio_read(pci_info, PROC_THERMAL_MMIO_TJMAX, &tjmax); + temp = (tjmax - temp) * 1000; + + return temp; +} + +static struct thermal_trip psv_trip = { + .type = THERMAL_TRIP_PASSIVE, +}; + static struct thermal_zone_device_ops tzone_ops = { .get_temp = sys_get_curr_temp, - .get_trip_temp = sys_get_trip_temp, - .get_trip_type = sys_get_trip_type, .set_trip_temp = sys_set_trip_temp, }; @@ -251,7 +239,10 @@ static int proc_thermal_pci_probe(struct pci_dev *pdev, const struct pci_device_ if (ret) goto err_ret_thermal; - pci_info->tzone = thermal_zone_device_register("TCPU_PCI", 1, 1, pci_info, + psv_trip.temperature = get_trip_temp(pci_info); + + pci_info->tzone = thermal_zone_device_register_with_trips("TCPU_PCI", &psv_trip, + 1, 1, pci_info, &tzone_ops, &tzone_params, 0, 0); if (IS_ERR(pci_info->tzone)) { diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c index 8c42e7662033..92ed1213fe37 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c @@ -172,6 +172,7 @@ static const struct attribute_group fivr_attribute_group = { RFIM_SHOW(rfi_restriction_run_busy, 1) RFIM_SHOW(rfi_restriction_err_code, 1) RFIM_SHOW(rfi_restriction_data_rate, 1) +RFIM_SHOW(rfi_restriction_data_rate_base, 1) RFIM_SHOW(ddr_data_rate_point_0, 1) RFIM_SHOW(ddr_data_rate_point_1, 1) RFIM_SHOW(ddr_data_rate_point_2, 1) @@ -181,11 +182,13 @@ RFIM_SHOW(rfi_disable, 1) RFIM_STORE(rfi_restriction_run_busy, 1) RFIM_STORE(rfi_restriction_err_code, 1) RFIM_STORE(rfi_restriction_data_rate, 1) +RFIM_STORE(rfi_restriction_data_rate_base, 1) RFIM_STORE(rfi_disable, 1) static DEVICE_ATTR_RW(rfi_restriction_run_busy); static DEVICE_ATTR_RW(rfi_restriction_err_code); static DEVICE_ATTR_RW(rfi_restriction_data_rate); +static DEVICE_ATTR_RW(rfi_restriction_data_rate_base); static DEVICE_ATTR_RO(ddr_data_rate_point_0); static DEVICE_ATTR_RO(ddr_data_rate_point_1); static DEVICE_ATTR_RO(ddr_data_rate_point_2); @@ -248,6 +251,7 @@ static struct attribute *dvfs_attrs[] = { &dev_attr_rfi_restriction_run_busy.attr, &dev_attr_rfi_restriction_err_code.attr, &dev_attr_rfi_restriction_data_rate.attr, + &dev_attr_rfi_restriction_data_rate_base.attr, &dev_attr_ddr_data_rate_point_0.attr, &dev_attr_ddr_data_rate_point_1.attr, &dev_attr_ddr_data_rate_point_2.attr, diff --git a/drivers/thermal/intel/intel_hfi.c b/drivers/thermal/intel/intel_hfi.c index 6e604bda2b93..c69db6c90869 100644 --- a/drivers/thermal/intel/intel_hfi.c +++ b/drivers/thermal/intel/intel_hfi.c @@ -40,10 +40,11 @@ #include <asm/msr.h> -#include "../thermal_core.h" #include "intel_hfi.h" #include "thermal_interrupt.h" +#include "../thermal_netlink.h" + /* Hardware Feedback Interface MSR configuration bits */ #define HW_FEEDBACK_PTR_VALID_BIT BIT(0) #define HW_FEEDBACK_CONFIG_HFI_ENABLE_BIT BIT(0) diff --git a/drivers/thermal/intel/intel_menlow.c b/drivers/thermal/intel/intel_menlow.c index 3f885b08a490..5a6ad0552311 100644 --- a/drivers/thermal/intel/intel_menlow.c +++ b/drivers/thermal/intel/intel_menlow.c @@ -232,9 +232,9 @@ static DEFINE_MUTEX(intel_menlow_attr_lock); /* * sensor_get_auxtrip - get the current auxtrip value from sensor - * @name: Thermalzone name - * @auxtype : AUX0/AUX1 - * @buf: syfs buffer + * @handle: Object handle + * @index : GET_AUX1/GET_AUX0 + * @value : The address will be fill by the value */ static int sensor_get_auxtrip(acpi_handle handle, int index, unsigned long long *value) @@ -254,9 +254,9 @@ static int sensor_get_auxtrip(acpi_handle handle, int index, /* * sensor_set_auxtrip - set the new auxtrip value to sensor - * @name: Thermalzone name - * @auxtype : AUX0/AUX1 - * @buf: syfs buffer + * @handle: Object handle + * @index : GET_AUX1/GET_AUX0 + * @value : The value will be set */ static int sensor_set_auxtrip(acpi_handle handle, int index, int value) { diff --git a/drivers/thermal/intel/intel_pch_thermal.c b/drivers/thermal/intel/intel_pch_thermal.c index dabf11a687a1..b855d031a855 100644 --- a/drivers/thermal/intel/intel_pch_thermal.c +++ b/drivers/thermal/intel/intel_pch_thermal.c @@ -29,6 +29,7 @@ #define PCH_THERMAL_DID_CNL_LP 0x02F9 /* CNL-LP PCH */ #define PCH_THERMAL_DID_CML_H 0X06F9 /* CML-H PCH */ #define PCH_THERMAL_DID_LWB 0xA1B1 /* Lewisburg PCH */ +#define PCH_THERMAL_DID_WBG 0x8D24 /* Wellsburg PCH */ /* Wildcat Point-LP PCH Thermal registers */ #define WPT_TEMP 0x0000 /* Temperature */ @@ -65,6 +66,8 @@ #define WPT_TEMP_OFFSET (PCH_TEMP_OFFSET * MILLIDEGREE_PER_DEGREE) #define GET_PCH_TEMP(x) (((x) / 2) + PCH_TEMP_OFFSET) +#define PCH_MAX_TRIPS 3 /* critical, hot, passive */ + /* Amount of time for each cooling delay, 100ms by default for now */ static unsigned int delay_timeout = 100; module_param(delay_timeout, int, 0644); @@ -79,66 +82,114 @@ static char driver_name[] = "Intel PCH thermal driver"; struct pch_thermal_device { void __iomem *hw_base; - const struct pch_dev_ops *ops; struct pci_dev *pdev; struct thermal_zone_device *tzd; - int crt_trip_id; - unsigned long crt_temp; - int hot_trip_id; - unsigned long hot_temp; - int psv_trip_id; - unsigned long psv_temp; + struct thermal_trip trips[PCH_MAX_TRIPS]; bool bios_enabled; }; #ifdef CONFIG_ACPI - /* * On some platforms, there is a companion ACPI device, which adds * passive trip temperature using _PSV method. There is no specific * passive temperature setting in MMIO interface of this PCI device. */ -static void pch_wpt_add_acpi_psv_trip(struct pch_thermal_device *ptd, - int *nr_trips) +static int pch_wpt_add_acpi_psv_trip(struct pch_thermal_device *ptd, int trip) { struct acpi_device *adev; - - ptd->psv_trip_id = -1; + int temp; adev = ACPI_COMPANION(&ptd->pdev->dev); - if (adev) { - unsigned long long r; - acpi_status status; - - status = acpi_evaluate_integer(adev->handle, "_PSV", NULL, - &r); - if (ACPI_SUCCESS(status)) { - unsigned long trip_temp; - - trip_temp = deci_kelvin_to_millicelsius(r); - if (trip_temp) { - ptd->psv_temp = trip_temp; - ptd->psv_trip_id = *nr_trips; - ++(*nr_trips); - } - } - } + if (!adev) + return 0; + + if (thermal_acpi_passive_trip_temp(adev, &temp) || temp <= 0) + return 0; + + ptd->trips[trip].type = THERMAL_TRIP_PASSIVE; + ptd->trips[trip].temperature = temp; + return 1; } #else -static void pch_wpt_add_acpi_psv_trip(struct pch_thermal_device *ptd, - int *nr_trips) +static int pch_wpt_add_acpi_psv_trip(struct pch_thermal_device *ptd, int trip) { - ptd->psv_trip_id = -1; - + return 0; } #endif -static int pch_wpt_init(struct pch_thermal_device *ptd, int *nr_trips) +static int pch_thermal_get_temp(struct thermal_zone_device *tzd, int *temp) { - u8 tsel; + struct pch_thermal_device *ptd = tzd->devdata; + + *temp = GET_WPT_TEMP(WPT_TEMP_TSR & readw(ptd->hw_base + WPT_TEMP)); + return 0; +} + +static void pch_critical(struct thermal_zone_device *tzd) +{ + dev_dbg(&tzd->device, "%s: critical temperature reached\n", tzd->type); +} + +static struct thermal_zone_device_ops tzd_ops = { + .get_temp = pch_thermal_get_temp, + .critical = pch_critical, +}; + +enum pch_board_ids { + PCH_BOARD_HSW = 0, + PCH_BOARD_WPT, + PCH_BOARD_SKL, + PCH_BOARD_CNL, + PCH_BOARD_CML, + PCH_BOARD_LWB, + PCH_BOARD_WBG, +}; + +static const char *board_names[] = { + [PCH_BOARD_HSW] = "pch_haswell", + [PCH_BOARD_WPT] = "pch_wildcat_point", + [PCH_BOARD_SKL] = "pch_skylake", + [PCH_BOARD_CNL] = "pch_cannonlake", + [PCH_BOARD_CML] = "pch_cometlake", + [PCH_BOARD_LWB] = "pch_lewisburg", + [PCH_BOARD_WBG] = "pch_wellsburg", +}; + +static int intel_pch_thermal_probe(struct pci_dev *pdev, + const struct pci_device_id *id) +{ + enum pch_board_ids board_id = id->driver_data; + struct pch_thermal_device *ptd; + int nr_trips = 0; u16 trip_temp; + u8 tsel; + int err; + + ptd = devm_kzalloc(&pdev->dev, sizeof(*ptd), GFP_KERNEL); + if (!ptd) + return -ENOMEM; + + pci_set_drvdata(pdev, ptd); + ptd->pdev = pdev; + + err = pci_enable_device(pdev); + if (err) { + dev_err(&pdev->dev, "failed to enable pci device\n"); + return err; + } + + err = pci_request_regions(pdev, driver_name); + if (err) { + dev_err(&pdev->dev, "failed to request pci region\n"); + goto error_disable; + } - *nr_trips = 0; + ptd->hw_base = pci_ioremap_bar(pdev, 0); + if (!ptd->hw_base) { + err = -ENOMEM; + dev_err(&pdev->dev, "failed to map mem base\n"); + goto error_release; + } /* Check if BIOS has already enabled thermal sensor */ if (WPT_TSEL_ETS & readb(ptd->hw_base + WPT_TSEL)) { @@ -153,52 +204,79 @@ static int pch_wpt_init(struct pch_thermal_device *ptd, int *nr_trips) */ if (tsel & WPT_TSEL_PLDB) { dev_err(&ptd->pdev->dev, "Sensor can't be enabled\n"); - return -ENODEV; + err = -ENODEV; + goto error_cleanup; } writeb(tsel|WPT_TSEL_ETS, ptd->hw_base + WPT_TSEL); if (!(WPT_TSEL_ETS & readb(ptd->hw_base + WPT_TSEL))) { dev_err(&ptd->pdev->dev, "Sensor can't be enabled\n"); - return -ENODEV; + err = -ENODEV; + goto error_cleanup; } read_trips: - ptd->crt_trip_id = -1; trip_temp = readw(ptd->hw_base + WPT_CTT); trip_temp &= 0x1FF; if (trip_temp) { - ptd->crt_temp = GET_WPT_TEMP(trip_temp); - ptd->crt_trip_id = 0; - ++(*nr_trips); + ptd->trips[nr_trips].temperature = GET_WPT_TEMP(trip_temp); + ptd->trips[nr_trips++].type = THERMAL_TRIP_CRITICAL; } - ptd->hot_trip_id = -1; trip_temp = readw(ptd->hw_base + WPT_PHL); trip_temp &= 0x1FF; if (trip_temp) { - ptd->hot_temp = GET_WPT_TEMP(trip_temp); - ptd->hot_trip_id = *nr_trips; - ++(*nr_trips); + ptd->trips[nr_trips].temperature = GET_WPT_TEMP(trip_temp); + ptd->trips[nr_trips++].type = THERMAL_TRIP_HOT; } - pch_wpt_add_acpi_psv_trip(ptd, nr_trips); + nr_trips += pch_wpt_add_acpi_psv_trip(ptd, nr_trips); + + ptd->tzd = thermal_zone_device_register_with_trips(board_names[board_id], + ptd->trips, nr_trips, + 0, ptd, &tzd_ops, + NULL, 0, 0); + if (IS_ERR(ptd->tzd)) { + dev_err(&pdev->dev, "Failed to register thermal zone %s\n", + board_names[board_id]); + err = PTR_ERR(ptd->tzd); + goto error_cleanup; + } + err = thermal_zone_device_enable(ptd->tzd); + if (err) + goto err_unregister; return 0; + +err_unregister: + thermal_zone_device_unregister(ptd->tzd); +error_cleanup: + iounmap(ptd->hw_base); +error_release: + pci_release_regions(pdev); +error_disable: + pci_disable_device(pdev); + dev_err(&pdev->dev, "pci device failed to probe\n"); + return err; } -static int pch_wpt_get_temp(struct pch_thermal_device *ptd, int *temp) +static void intel_pch_thermal_remove(struct pci_dev *pdev) { - *temp = GET_WPT_TEMP(WPT_TEMP_TSR & readw(ptd->hw_base + WPT_TEMP)); + struct pch_thermal_device *ptd = pci_get_drvdata(pdev); - return 0; + thermal_zone_device_unregister(ptd->tzd); + iounmap(ptd->hw_base); + pci_set_drvdata(pdev, NULL); + pci_release_regions(pdev); + pci_disable_device(pdev); } -/* Cool the PCH when it's overheat in .suspend_noirq phase */ -static int pch_wpt_suspend(struct pch_thermal_device *ptd) +static int intel_pch_thermal_suspend_noirq(struct device *device) { - u8 tsel; - int pch_delay_cnt = 0; + struct pch_thermal_device *ptd = dev_get_drvdata(device); u16 pch_thr_temp, pch_cur_temp; + int pch_delay_cnt = 0; + u8 tsel; /* Shutdown the thermal sensor if it is not enabled by BIOS */ if (!ptd->bios_enabled) { @@ -261,8 +339,9 @@ static int pch_wpt_suspend(struct pch_thermal_device *ptd) return 0; } -static int pch_wpt_resume(struct pch_thermal_device *ptd) +static int intel_pch_thermal_resume(struct device *device) { + struct pch_thermal_device *ptd = dev_get_drvdata(device); u8 tsel; if (ptd->bios_enabled) @@ -275,226 +354,29 @@ static int pch_wpt_resume(struct pch_thermal_device *ptd) return 0; } -struct pch_dev_ops { - int (*hw_init)(struct pch_thermal_device *ptd, int *nr_trips); - int (*get_temp)(struct pch_thermal_device *ptd, int *temp); - int (*suspend)(struct pch_thermal_device *ptd); - int (*resume)(struct pch_thermal_device *ptd); -}; - - -/* dev ops for Wildcat Point */ -static const struct pch_dev_ops pch_dev_ops_wpt = { - .hw_init = pch_wpt_init, - .get_temp = pch_wpt_get_temp, - .suspend = pch_wpt_suspend, - .resume = pch_wpt_resume, -}; - -static int pch_thermal_get_temp(struct thermal_zone_device *tzd, int *temp) -{ - struct pch_thermal_device *ptd = tzd->devdata; - - return ptd->ops->get_temp(ptd, temp); -} - -static int pch_get_trip_type(struct thermal_zone_device *tzd, int trip, - enum thermal_trip_type *type) -{ - struct pch_thermal_device *ptd = tzd->devdata; - - if (ptd->crt_trip_id == trip) - *type = THERMAL_TRIP_CRITICAL; - else if (ptd->hot_trip_id == trip) - *type = THERMAL_TRIP_HOT; - else if (ptd->psv_trip_id == trip) - *type = THERMAL_TRIP_PASSIVE; - else - return -EINVAL; - - return 0; -} - -static int pch_get_trip_temp(struct thermal_zone_device *tzd, int trip, int *temp) -{ - struct pch_thermal_device *ptd = tzd->devdata; - - if (ptd->crt_trip_id == trip) - *temp = ptd->crt_temp; - else if (ptd->hot_trip_id == trip) - *temp = ptd->hot_temp; - else if (ptd->psv_trip_id == trip) - *temp = ptd->psv_temp; - else - return -EINVAL; - - return 0; -} - -static void pch_critical(struct thermal_zone_device *tzd) -{ - dev_dbg(&tzd->device, "%s: critical temperature reached\n", tzd->type); -} - -static struct thermal_zone_device_ops tzd_ops = { - .get_temp = pch_thermal_get_temp, - .get_trip_type = pch_get_trip_type, - .get_trip_temp = pch_get_trip_temp, - .critical = pch_critical, -}; - -enum board_ids { - board_hsw, - board_wpt, - board_skl, - board_cnl, - board_cml, - board_lwb, -}; - -static const struct board_info { - const char *name; - const struct pch_dev_ops *ops; -} board_info[] = { - [board_hsw] = { - .name = "pch_haswell", - .ops = &pch_dev_ops_wpt, - }, - [board_wpt] = { - .name = "pch_wildcat_point", - .ops = &pch_dev_ops_wpt, - }, - [board_skl] = { - .name = "pch_skylake", - .ops = &pch_dev_ops_wpt, - }, - [board_cnl] = { - .name = "pch_cannonlake", - .ops = &pch_dev_ops_wpt, - }, - [board_cml] = { - .name = "pch_cometlake", - .ops = &pch_dev_ops_wpt, - }, - [board_lwb] = { - .name = "pch_lewisburg", - .ops = &pch_dev_ops_wpt, - }, -}; - -static int intel_pch_thermal_probe(struct pci_dev *pdev, - const struct pci_device_id *id) -{ - enum board_ids board_id = id->driver_data; - const struct board_info *bi = &board_info[board_id]; - struct pch_thermal_device *ptd; - int err; - int nr_trips; - - ptd = devm_kzalloc(&pdev->dev, sizeof(*ptd), GFP_KERNEL); - if (!ptd) - return -ENOMEM; - - ptd->ops = bi->ops; - - pci_set_drvdata(pdev, ptd); - ptd->pdev = pdev; - - err = pci_enable_device(pdev); - if (err) { - dev_err(&pdev->dev, "failed to enable pci device\n"); - return err; - } - - err = pci_request_regions(pdev, driver_name); - if (err) { - dev_err(&pdev->dev, "failed to request pci region\n"); - goto error_disable; - } - - ptd->hw_base = pci_ioremap_bar(pdev, 0); - if (!ptd->hw_base) { - err = -ENOMEM; - dev_err(&pdev->dev, "failed to map mem base\n"); - goto error_release; - } - - err = ptd->ops->hw_init(ptd, &nr_trips); - if (err) - goto error_cleanup; - - ptd->tzd = thermal_zone_device_register(bi->name, nr_trips, 0, ptd, - &tzd_ops, NULL, 0, 0); - if (IS_ERR(ptd->tzd)) { - dev_err(&pdev->dev, "Failed to register thermal zone %s\n", - bi->name); - err = PTR_ERR(ptd->tzd); - goto error_cleanup; - } - err = thermal_zone_device_enable(ptd->tzd); - if (err) - goto err_unregister; - - return 0; - -err_unregister: - thermal_zone_device_unregister(ptd->tzd); -error_cleanup: - iounmap(ptd->hw_base); -error_release: - pci_release_regions(pdev); -error_disable: - pci_disable_device(pdev); - dev_err(&pdev->dev, "pci device failed to probe\n"); - return err; -} - -static void intel_pch_thermal_remove(struct pci_dev *pdev) -{ - struct pch_thermal_device *ptd = pci_get_drvdata(pdev); - - thermal_zone_device_unregister(ptd->tzd); - iounmap(ptd->hw_base); - pci_set_drvdata(pdev, NULL); - pci_release_regions(pdev); - pci_disable_device(pdev); -} - -static int intel_pch_thermal_suspend_noirq(struct device *device) -{ - struct pch_thermal_device *ptd = dev_get_drvdata(device); - - return ptd->ops->suspend(ptd); -} - -static int intel_pch_thermal_resume(struct device *device) -{ - struct pch_thermal_device *ptd = dev_get_drvdata(device); - - return ptd->ops->resume(ptd); -} - static const struct pci_device_id intel_pch_thermal_id[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_HSW_1), - .driver_data = board_hsw, }, + .driver_data = PCH_BOARD_HSW, }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_HSW_2), - .driver_data = board_hsw, }, + .driver_data = PCH_BOARD_HSW, }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_WPT), - .driver_data = board_wpt, }, + .driver_data = PCH_BOARD_WPT, }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_SKL), - .driver_data = board_skl, }, + .driver_data = PCH_BOARD_SKL, }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_SKL_H), - .driver_data = board_skl, }, + .driver_data = PCH_BOARD_SKL, }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_CNL), - .driver_data = board_cnl, }, + .driver_data = PCH_BOARD_CNL, }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_CNL_H), - .driver_data = board_cnl, }, + .driver_data = PCH_BOARD_CNL, }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_CNL_LP), - .driver_data = board_cnl, }, + .driver_data = PCH_BOARD_CNL, }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_CML_H), - .driver_data = board_cml, }, + .driver_data = PCH_BOARD_CML, }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_LWB), - .driver_data = board_lwb, }, + .driver_data = PCH_BOARD_LWB, }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_WBG), + .driver_data = PCH_BOARD_WBG, }, { 0, }, }; MODULE_DEVICE_TABLE(pci, intel_pch_thermal_id); diff --git a/drivers/thermal/intel/intel_powerclamp.c b/drivers/thermal/intel/intel_powerclamp.c index b80e25ec1261..c7ba5680cd48 100644 --- a/drivers/thermal/intel/intel_powerclamp.c +++ b/drivers/thermal/intel/intel_powerclamp.c @@ -2,7 +2,7 @@ /* * intel_powerclamp.c - package c-state idle injection * - * Copyright (c) 2012, Intel Corporation. + * Copyright (c) 2012-2023, Intel Corporation. * * Authors: * Arjan van de Ven <arjan@linux.intel.com> @@ -27,23 +27,17 @@ #include <linux/module.h> #include <linux/kernel.h> #include <linux/delay.h> -#include <linux/kthread.h> #include <linux/cpu.h> #include <linux/thermal.h> -#include <linux/slab.h> -#include <linux/tick.h> #include <linux/debugfs.h> #include <linux/seq_file.h> -#include <linux/sched/rt.h> -#include <uapi/linux/sched/types.h> +#include <linux/idle_inject.h> -#include <asm/nmi.h> #include <asm/msr.h> #include <asm/mwait.h> #include <asm/cpu_device_id.h> -#include <asm/hardirq.h> -#define MAX_TARGET_RATIO (50U) +#define MAX_TARGET_RATIO (100U) /* For each undisturbed clamping period (no extra wake ups during idle time), * we increment the confidence counter for the given target ratio. * CONFIDENCE_OK defines the level where runtime calibration results are @@ -57,37 +51,30 @@ static unsigned int target_mwait; static struct dentry *debug_dir; +static bool poll_pkg_cstate_enable; -/* user selected target */ -static unsigned int set_target_ratio; +/* Idle ratio observed using package C-state counters */ static unsigned int current_ratio; -static bool should_skip; -static unsigned int control_cpu; /* The cpu assigned to collect stat and update - * control parameters. default to BSP but BSP - * can be offlined. - */ -static bool clamping; +/* Skip the idle injection till set to true */ +static bool should_skip; -struct powerclamp_worker_data { - struct kthread_worker *worker; - struct kthread_work balancing_work; - struct kthread_delayed_work idle_injection_work; +struct powerclamp_data { unsigned int cpu; unsigned int count; unsigned int guard; unsigned int window_size_now; unsigned int target_ratio; - unsigned int duration_jiffies; bool clamping; }; -static struct powerclamp_worker_data __percpu *worker_data; +static struct powerclamp_data powerclamp_data; + static struct thermal_cooling_device *cooling_dev; -static unsigned long *cpu_clamping_mask; /* bit map for tracking per cpu - * clamping kthread worker - */ +static DEFINE_MUTEX(powerclamp_lock); + +/* This duration is in microseconds */ static unsigned int duration; static unsigned int pkg_cstate_ratio_cur; static unsigned int window_size; @@ -104,25 +91,171 @@ static int duration_set(const char *arg, const struct kernel_param *kp) pr_err("Out of recommended range %lu, between 6-25ms\n", new_duration); ret = -EINVAL; + goto exit; } - duration = clamp(new_duration, 6ul, 25ul); - smp_mb(); - + mutex_lock(&powerclamp_lock); + duration = clamp(new_duration, 6ul, 25ul) * 1000; + mutex_unlock(&powerclamp_lock); exit: return ret; } +static int duration_get(char *buf, const struct kernel_param *kp) +{ + int ret; + + mutex_lock(&powerclamp_lock); + ret = sysfs_emit(buf, "%d\n", duration / 1000); + mutex_unlock(&powerclamp_lock); + + return ret; +} + static const struct kernel_param_ops duration_ops = { .set = duration_set, - .get = param_get_int, + .get = duration_get, }; - -module_param_cb(duration, &duration_ops, &duration, 0644); +module_param_cb(duration, &duration_ops, NULL, 0644); MODULE_PARM_DESC(duration, "forced idle time for each attempt in msec."); +#define DEFAULT_MAX_IDLE 50 +#define MAX_ALL_CPU_IDLE 75 + +static u8 max_idle = DEFAULT_MAX_IDLE; + +static cpumask_var_t idle_injection_cpu_mask; + +static int allocate_copy_idle_injection_mask(const struct cpumask *copy_mask) +{ + if (cpumask_available(idle_injection_cpu_mask)) + goto copy_mask; + + /* This mask is allocated only one time and freed during module exit */ + if (!alloc_cpumask_var(&idle_injection_cpu_mask, GFP_KERNEL)) + return -ENOMEM; + +copy_mask: + cpumask_copy(idle_injection_cpu_mask, copy_mask); + + return 0; +} + +/* Return true if the cpumask and idle percent combination is invalid */ +static bool check_invalid(cpumask_var_t mask, u8 idle) +{ + if (cpumask_equal(cpu_present_mask, mask) && idle > MAX_ALL_CPU_IDLE) + return true; + + return false; +} + +static int cpumask_set(const char *arg, const struct kernel_param *kp) +{ + cpumask_var_t new_mask; + int ret; + + mutex_lock(&powerclamp_lock); + + /* Can't set mask when cooling device is in use */ + if (powerclamp_data.clamping) { + ret = -EAGAIN; + goto skip_cpumask_set; + } + + ret = alloc_cpumask_var(&new_mask, GFP_KERNEL); + if (!ret) + goto skip_cpumask_set; + + ret = bitmap_parse(arg, strlen(arg), cpumask_bits(new_mask), + nr_cpumask_bits); + if (ret) + goto free_cpumask_set; + + if (cpumask_empty(new_mask) || check_invalid(new_mask, max_idle)) { + ret = -EINVAL; + goto free_cpumask_set; + } + + /* + * When module parameters are passed from kernel command line + * during insmod, the module parameter callback is called + * before powerclamp_init(), so we can't assume that some + * cpumask can be allocated and copied before here. Also + * in this case this cpumask is used as the default mask. + */ + ret = allocate_copy_idle_injection_mask(new_mask); + +free_cpumask_set: + free_cpumask_var(new_mask); +skip_cpumask_set: + mutex_unlock(&powerclamp_lock); + + return ret; +} + +static int cpumask_get(char *buf, const struct kernel_param *kp) +{ + if (!cpumask_available(idle_injection_cpu_mask)) + return -ENODEV; + + return bitmap_print_to_pagebuf(false, buf, cpumask_bits(idle_injection_cpu_mask), + nr_cpumask_bits); +} + +static const struct kernel_param_ops cpumask_ops = { + .set = cpumask_set, + .get = cpumask_get, +}; + +module_param_cb(cpumask, &cpumask_ops, NULL, 0644); +MODULE_PARM_DESC(cpumask, "Mask of CPUs to use for idle injection."); + +static int max_idle_set(const char *arg, const struct kernel_param *kp) +{ + u8 new_max_idle; + int ret = 0; + + mutex_lock(&powerclamp_lock); + + /* Can't set mask when cooling device is in use */ + if (powerclamp_data.clamping) { + ret = -EAGAIN; + goto skip_limit_set; + } + + ret = kstrtou8(arg, 10, &new_max_idle); + if (ret) + goto skip_limit_set; + + if (new_max_idle > MAX_TARGET_RATIO) { + ret = -EINVAL; + goto skip_limit_set; + } + + if (check_invalid(idle_injection_cpu_mask, new_max_idle)) { + ret = -EINVAL; + goto skip_limit_set; + } + + max_idle = new_max_idle; + +skip_limit_set: + mutex_unlock(&powerclamp_lock); + + return ret; +} + +static const struct kernel_param_ops max_idle_ops = { + .set = max_idle_set, + .get = param_get_int, +}; + +module_param_cb(max_idle, &max_idle_ops, &max_idle, 0644); +MODULE_PARM_DESC(max_idle, "maximum injected idle time to the total CPU time ratio in percent range:1-100"); + struct powerclamp_calibration_data { unsigned long confidence; /* used for calibration, basically a counter * gets incremented each time a clamping @@ -261,6 +394,9 @@ static unsigned int get_compensation(int ratio) { unsigned int comp = 0; + if (!poll_pkg_cstate_enable) + return 0; + /* we only use compensation if all adjacent ones are good */ if (ratio == 1 && cal_data[ratio].confidence >= CONFIDENCE_OK && @@ -302,7 +438,7 @@ static void adjust_compensation(int target_ratio, unsigned int win) if (d->confidence >= CONFIDENCE_OK) return; - delta = set_target_ratio - current_ratio; + delta = powerclamp_data.target_ratio - current_ratio; /* filter out bad data */ if (delta >= 0 && delta <= (1+target_ratio/10)) { if (d->steady_comp) @@ -341,82 +477,39 @@ static bool powerclamp_adjust_controls(unsigned int target_ratio, adjust_compensation(target_ratio, win); /* if we are above target+guard, skip */ - return set_target_ratio + guard <= current_ratio; + return powerclamp_data.target_ratio + guard <= current_ratio; } -static void clamp_balancing_func(struct kthread_work *work) +/* + * This function calculates runtime from the current target ratio. + * This function gets called under powerclamp_lock. + */ +static unsigned int get_run_time(void) { - struct powerclamp_worker_data *w_data; - int sleeptime; - unsigned long target_jiffies; unsigned int compensated_ratio; - int interval; /* jiffies to sleep for each attempt */ - - w_data = container_of(work, struct powerclamp_worker_data, - balancing_work); + unsigned int runtime; /* * make sure user selected ratio does not take effect until * the next round. adjust target_ratio if user has changed * target such that we can converge quickly. */ - w_data->target_ratio = READ_ONCE(set_target_ratio); - w_data->guard = 1 + w_data->target_ratio / 20; - w_data->window_size_now = window_size; - w_data->duration_jiffies = msecs_to_jiffies(duration); - w_data->count++; + powerclamp_data.guard = 1 + powerclamp_data.target_ratio / 20; + powerclamp_data.window_size_now = window_size; /* * systems may have different ability to enter package level * c-states, thus we need to compensate the injected idle ratio * to achieve the actual target reported by the HW. */ - compensated_ratio = w_data->target_ratio + - get_compensation(w_data->target_ratio); + compensated_ratio = powerclamp_data.target_ratio + + get_compensation(powerclamp_data.target_ratio); if (compensated_ratio <= 0) compensated_ratio = 1; - interval = w_data->duration_jiffies * 100 / compensated_ratio; - - /* align idle time */ - target_jiffies = roundup(jiffies, interval); - sleeptime = target_jiffies - jiffies; - if (sleeptime <= 0) - sleeptime = 1; - - if (clamping && w_data->clamping && cpu_online(w_data->cpu)) - kthread_queue_delayed_work(w_data->worker, - &w_data->idle_injection_work, - sleeptime); -} -static void clamp_idle_injection_func(struct kthread_work *work) -{ - struct powerclamp_worker_data *w_data; - - w_data = container_of(work, struct powerclamp_worker_data, - idle_injection_work.work); - - /* - * only elected controlling cpu can collect stats and update - * control parameters. - */ - if (w_data->cpu == control_cpu && - !(w_data->count % w_data->window_size_now)) { - should_skip = - powerclamp_adjust_controls(w_data->target_ratio, - w_data->guard, - w_data->window_size_now); - smp_mb(); - } + runtime = duration * 100 / compensated_ratio - duration; - if (should_skip) - goto balance; - - play_idle(jiffies_to_usecs(w_data->duration_jiffies)); - -balance: - if (clamping && w_data->clamping && cpu_online(w_data->cpu)) - kthread_queue_work(w_data->worker, &w_data->balancing_work); + return runtime; } /* @@ -452,126 +545,129 @@ static void poll_pkg_cstate(struct work_struct *dummy) msr_last = msr_now; tsc_last = tsc_now; - if (true == clamping) + mutex_lock(&powerclamp_lock); + if (powerclamp_data.clamping) schedule_delayed_work(&poll_pkg_cstate_work, HZ); + mutex_unlock(&powerclamp_lock); } -static void start_power_clamp_worker(unsigned long cpu) +static struct idle_inject_device *ii_dev; + +/* + * This function is called from idle injection core on timer expiry + * for the run duration. This allows powerclamp to readjust or skip + * injecting idle for this cycle. + */ +static bool idle_inject_update(void) { - struct powerclamp_worker_data *w_data = per_cpu_ptr(worker_data, cpu); - struct kthread_worker *worker; + bool update = false; - worker = kthread_create_worker_on_cpu(cpu, 0, "kidle_inj/%ld", cpu); - if (IS_ERR(worker)) - return; + /* We can't sleep in this callback */ + if (!mutex_trylock(&powerclamp_lock)) + return true; - w_data->worker = worker; - w_data->count = 0; - w_data->cpu = cpu; - w_data->clamping = true; - set_bit(cpu, cpu_clamping_mask); - sched_set_fifo(worker->task); - kthread_init_work(&w_data->balancing_work, clamp_balancing_func); - kthread_init_delayed_work(&w_data->idle_injection_work, - clamp_idle_injection_func); - kthread_queue_work(w_data->worker, &w_data->balancing_work); -} + if (!(powerclamp_data.count % powerclamp_data.window_size_now)) { -static void stop_power_clamp_worker(unsigned long cpu) -{ - struct powerclamp_worker_data *w_data = per_cpu_ptr(worker_data, cpu); + should_skip = powerclamp_adjust_controls(powerclamp_data.target_ratio, + powerclamp_data.guard, + powerclamp_data.window_size_now); + update = true; + } - if (!w_data->worker) - return; + if (update) { + unsigned int runtime = get_run_time(); - w_data->clamping = false; - /* - * Make sure that all works that get queued after this point see - * the clamping disabled. The counter part is not needed because - * there is an implicit memory barrier when the queued work - * is proceed. - */ - smp_wmb(); - kthread_cancel_work_sync(&w_data->balancing_work); - kthread_cancel_delayed_work_sync(&w_data->idle_injection_work); - /* - * The balancing work still might be queued here because - * the handling of the "clapming" variable, cancel, and queue - * operations are not synchronized via a lock. But it is not - * a big deal. The balancing work is fast and destroy kthread - * will wait for it. - */ - clear_bit(w_data->cpu, cpu_clamping_mask); - kthread_destroy_worker(w_data->worker); + idle_inject_set_duration(ii_dev, runtime, duration); + } + + powerclamp_data.count++; + + mutex_unlock(&powerclamp_lock); + + if (should_skip) + return false; - w_data->worker = NULL; + return true; } -static int start_power_clamp(void) +/* This function starts idle injection by calling idle_inject_start() */ +static void trigger_idle_injection(void) { - unsigned long cpu; - - set_target_ratio = clamp(set_target_ratio, 0U, MAX_TARGET_RATIO - 1); - /* prevent cpu hotplug */ - cpus_read_lock(); + unsigned int runtime = get_run_time(); - /* prefer BSP */ - control_cpu = cpumask_first(cpu_online_mask); + idle_inject_set_duration(ii_dev, runtime, duration); + idle_inject_start(ii_dev); + powerclamp_data.clamping = true; +} - clamping = true; - schedule_delayed_work(&poll_pkg_cstate_work, 0); +/* + * This function is called from start_power_clamp() to register + * CPUS with powercap idle injection register and set default + * idle duration and latency. + */ +static int powerclamp_idle_injection_register(void) +{ + poll_pkg_cstate_enable = false; + if (cpumask_equal(cpu_present_mask, idle_injection_cpu_mask)) { + ii_dev = idle_inject_register_full(idle_injection_cpu_mask, idle_inject_update); + if (topology_max_packages() == 1 && topology_max_die_per_package() == 1) + poll_pkg_cstate_enable = true; + } else { + ii_dev = idle_inject_register(idle_injection_cpu_mask); + } - /* start one kthread worker per online cpu */ - for_each_online_cpu(cpu) { - start_power_clamp_worker(cpu); + if (!ii_dev) { + pr_err("powerclamp: idle_inject_register failed\n"); + return -EAGAIN; } - cpus_read_unlock(); + + idle_inject_set_duration(ii_dev, TICK_USEC, duration); + idle_inject_set_latency(ii_dev, UINT_MAX); return 0; } -static void end_power_clamp(void) +/* + * This function is called from end_power_clamp() to stop idle injection + * and unregister CPUS from powercap idle injection core. + */ +static void remove_idle_injection(void) { - int i; + if (!powerclamp_data.clamping) + return; - /* - * Block requeuing in all the kthread workers. They will flush and - * stop faster. - */ - clamping = false; - for_each_set_bit(i, cpu_clamping_mask, num_possible_cpus()) { - pr_debug("clamping worker for cpu %d alive, destroy\n", i); - stop_power_clamp_worker(i); - } + powerclamp_data.clamping = false; + idle_inject_stop(ii_dev); } -static int powerclamp_cpu_online(unsigned int cpu) +/* + * This function is called when user change the cooling device + * state from zero to some other value. + */ +static int start_power_clamp(void) { - if (clamping == false) - return 0; - start_power_clamp_worker(cpu); - /* prefer BSP as controlling CPU */ - if (cpu == 0) { - control_cpu = 0; - smp_mb(); + int ret; + + ret = powerclamp_idle_injection_register(); + if (!ret) { + trigger_idle_injection(); + if (poll_pkg_cstate_enable) + schedule_delayed_work(&poll_pkg_cstate_work, 0); } - return 0; + + return ret; } -static int powerclamp_cpu_predown(unsigned int cpu) +/* + * This function is called when user change the cooling device + * state from non zero value zero. + */ +static void end_power_clamp(void) { - if (clamping == false) - return 0; - - stop_power_clamp_worker(cpu); - if (cpu != control_cpu) - return 0; - - control_cpu = cpumask_first(cpu_online_mask); - if (control_cpu == cpu) - control_cpu = cpumask_next(cpu, cpu_online_mask); - smp_mb(); - return 0; + if (powerclamp_data.clamping) { + remove_idle_injection(); + idle_inject_unregister(ii_dev); + } } static int powerclamp_get_max_state(struct thermal_cooling_device *cdev, @@ -585,11 +681,9 @@ static int powerclamp_get_max_state(struct thermal_cooling_device *cdev, static int powerclamp_get_cur_state(struct thermal_cooling_device *cdev, unsigned long *state) { - if (true == clamping) - *state = pkg_cstate_ratio_cur; - else - /* to save power, do not poll idle ratio while not clamping */ - *state = -1; /* indicates invalid state */ + mutex_lock(&powerclamp_lock); + *state = powerclamp_data.target_ratio; + mutex_unlock(&powerclamp_lock); return 0; } @@ -599,24 +693,32 @@ static int powerclamp_set_cur_state(struct thermal_cooling_device *cdev, { int ret = 0; + mutex_lock(&powerclamp_lock); + new_target_ratio = clamp(new_target_ratio, 0UL, - (unsigned long) (MAX_TARGET_RATIO-1)); - if (set_target_ratio == 0 && new_target_ratio > 0) { + (unsigned long) (max_idle - 1)); + if (!powerclamp_data.target_ratio && new_target_ratio > 0) { pr_info("Start idle injection to reduce power\n"); - set_target_ratio = new_target_ratio; + powerclamp_data.target_ratio = new_target_ratio; ret = start_power_clamp(); + if (ret) + powerclamp_data.target_ratio = 0; goto exit_set; - } else if (set_target_ratio > 0 && new_target_ratio == 0) { + } else if (powerclamp_data.target_ratio > 0 && new_target_ratio == 0) { pr_info("Stop forced idle injection\n"); end_power_clamp(); - set_target_ratio = 0; + powerclamp_data.target_ratio = 0; } else /* adjust currently running */ { - set_target_ratio = new_target_ratio; - /* make new set_target_ratio visible to other cpus */ - smp_mb(); + unsigned int runtime; + + powerclamp_data.target_ratio = new_target_ratio; + runtime = get_run_time(); + idle_inject_set_duration(ii_dev, runtime, duration); } exit_set: + mutex_unlock(&powerclamp_lock); + return ret; } @@ -657,7 +759,6 @@ static int powerclamp_debug_show(struct seq_file *m, void *unused) { int i = 0; - seq_printf(m, "controlling cpu: %d\n", control_cpu); seq_printf(m, "pct confidence steady dynamic (compensation)\n"); for (i = 0; i < MAX_TARGET_RATIO; i++) { seq_printf(m, "%d\t%lu\t%lu\t%lu\n", @@ -680,75 +781,57 @@ static inline void powerclamp_create_debug_files(void) &powerclamp_debug_fops); } -static enum cpuhp_state hp_state; - static int __init powerclamp_init(void) { int retval; - cpu_clamping_mask = bitmap_zalloc(num_possible_cpus(), GFP_KERNEL); - if (!cpu_clamping_mask) - return -ENOMEM; - /* probe cpu features and ids here */ retval = powerclamp_probe(); if (retval) - goto exit_free; + return retval; + + mutex_lock(&powerclamp_lock); + retval = allocate_copy_idle_injection_mask(cpu_present_mask); + mutex_unlock(&powerclamp_lock); + + if (retval) + return retval; /* set default limit, maybe adjusted during runtime based on feedback */ window_size = 2; - retval = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, - "thermal/intel_powerclamp:online", - powerclamp_cpu_online, - powerclamp_cpu_predown); - if (retval < 0) - goto exit_free; - - hp_state = retval; - - worker_data = alloc_percpu(struct powerclamp_worker_data); - if (!worker_data) { - retval = -ENOMEM; - goto exit_unregister; - } cooling_dev = thermal_cooling_device_register("intel_powerclamp", NULL, - &powerclamp_cooling_ops); - if (IS_ERR(cooling_dev)) { - retval = -ENODEV; - goto exit_free_thread; - } + &powerclamp_cooling_ops); + if (IS_ERR(cooling_dev)) + return -ENODEV; if (!duration) - duration = jiffies_to_msecs(DEFAULT_DURATION_JIFFIES); + duration = jiffies_to_usecs(DEFAULT_DURATION_JIFFIES); powerclamp_create_debug_files(); return 0; - -exit_free_thread: - free_percpu(worker_data); -exit_unregister: - cpuhp_remove_state_nocalls(hp_state); -exit_free: - bitmap_free(cpu_clamping_mask); - return retval; } module_init(powerclamp_init); static void __exit powerclamp_exit(void) { + mutex_lock(&powerclamp_lock); end_power_clamp(); - cpuhp_remove_state_nocalls(hp_state); - free_percpu(worker_data); + mutex_unlock(&powerclamp_lock); + thermal_cooling_device_unregister(cooling_dev); - bitmap_free(cpu_clamping_mask); cancel_delayed_work_sync(&poll_pkg_cstate_work); debugfs_remove_recursive(debug_dir); + + if (cpumask_available(idle_injection_cpu_mask)) + free_cpumask_var(idle_injection_cpu_mask); } module_exit(powerclamp_exit); +MODULE_IMPORT_NS(IDLE_INJECT); + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>"); MODULE_AUTHOR("Jacob Pan <jacob.jun.pan@linux.intel.com>"); diff --git a/drivers/thermal/intel/intel_quark_dts_thermal.c b/drivers/thermal/intel/intel_quark_dts_thermal.c index 3eafc6b0e6c3..ffdc95047838 100644 --- a/drivers/thermal/intel/intel_quark_dts_thermal.c +++ b/drivers/thermal/intel/intel_quark_dts_thermal.c @@ -84,6 +84,7 @@ #define QRK_DTS_MASK_TP_THRES 0xFF #define QRK_DTS_SHIFT_TP 8 #define QRK_DTS_ID_TP_CRITICAL 0 +#define QRK_DTS_ID_TP_HOT 1 #define QRK_DTS_SAFE_TP_THRES 105 /* Thermal Sensor Register Lock */ @@ -104,6 +105,7 @@ struct soc_sensor_entry { u32 store_ptps; u32 store_dts_enable; struct thermal_zone_device *tzone; + struct thermal_trip trips[QRK_MAX_DTS_TRIPS]; }; static struct soc_sensor_entry *soc_dts; @@ -172,9 +174,9 @@ static int soc_dts_disable(struct thermal_zone_device *tzd) return ret; } -static int _get_trip_temp(int trip, int *temp) +static int get_trip_temp(int trip) { - int status; + int status, temp; u32 out; mutex_lock(&dts_update_mutex); @@ -183,7 +185,7 @@ static int _get_trip_temp(int trip, int *temp) mutex_unlock(&dts_update_mutex); if (status) - return status; + return THERMAL_TEMP_INVALID; /* * Thermal Sensor Programmable Trip Point Register has 8-bit @@ -191,21 +193,10 @@ static int _get_trip_temp(int trip, int *temp) * thresholds. The threshold value is always offset by its * temperature base (50 degree Celsius). */ - *temp = (out >> (trip * QRK_DTS_SHIFT_TP)) & QRK_DTS_MASK_TP_THRES; - *temp -= QRK_DTS_TEMP_BASE; + temp = (out >> (trip * QRK_DTS_SHIFT_TP)) & QRK_DTS_MASK_TP_THRES; + temp -= QRK_DTS_TEMP_BASE; - return 0; -} - -static inline int sys_get_trip_temp(struct thermal_zone_device *tzd, - int trip, int *temp) -{ - return _get_trip_temp(trip, temp); -} - -static inline int sys_get_crit_temp(struct thermal_zone_device *tzd, int *temp) -{ - return _get_trip_temp(QRK_DTS_ID_TP_CRITICAL, temp); + return temp; } static int update_trip_temp(struct soc_sensor_entry *aux_entry, @@ -262,17 +253,6 @@ static inline int sys_set_trip_temp(struct thermal_zone_device *tzd, int trip, return update_trip_temp(tzd->devdata, trip, temp); } -static int sys_get_trip_type(struct thermal_zone_device *thermal, - int trip, enum thermal_trip_type *type) -{ - if (trip) - *type = THERMAL_TRIP_HOT; - else - *type = THERMAL_TRIP_CRITICAL; - - return 0; -} - static int sys_get_curr_temp(struct thermal_zone_device *tzd, int *temp) { @@ -315,10 +295,7 @@ static int sys_change_mode(struct thermal_zone_device *tzd, static struct thermal_zone_device_ops tzone_ops = { .get_temp = sys_get_curr_temp, - .get_trip_temp = sys_get_trip_temp, - .get_trip_type = sys_get_trip_type, .set_trip_temp = sys_set_trip_temp, - .get_crit_temp = sys_get_crit_temp, .change_mode = sys_change_mode, }; @@ -385,10 +362,18 @@ static struct soc_sensor_entry *alloc_soc_dts(void) goto err_ret; } - aux_entry->tzone = thermal_zone_device_register("quark_dts", - QRK_MAX_DTS_TRIPS, - wr_mask, - aux_entry, &tzone_ops, NULL, 0, polling_delay); + aux_entry->trips[QRK_DTS_ID_TP_CRITICAL].temperature = get_trip_temp(QRK_DTS_ID_TP_CRITICAL); + aux_entry->trips[QRK_DTS_ID_TP_CRITICAL].type = THERMAL_TRIP_CRITICAL; + + aux_entry->trips[QRK_DTS_ID_TP_HOT].temperature = get_trip_temp(QRK_DTS_ID_TP_HOT); + aux_entry->trips[QRK_DTS_ID_TP_HOT].type = THERMAL_TRIP_HOT; + + aux_entry->tzone = thermal_zone_device_register_with_trips("quark_dts", + aux_entry->trips, + QRK_MAX_DTS_TRIPS, + wr_mask, + aux_entry, &tzone_ops, + NULL, 0, polling_delay); if (IS_ERR(aux_entry->tzone)) { err = PTR_ERR(aux_entry->tzone); goto err_ret; @@ -415,22 +400,14 @@ MODULE_DEVICE_TABLE(x86cpu, qrk_thermal_ids); static int __init intel_quark_thermal_init(void) { - int err = 0; - if (!x86_match_cpu(qrk_thermal_ids) || !iosf_mbi_available()) return -ENODEV; soc_dts = alloc_soc_dts(); - if (IS_ERR(soc_dts)) { - err = PTR_ERR(soc_dts); - goto err_free; - } + if (IS_ERR(soc_dts)) + return PTR_ERR(soc_dts); return 0; - -err_free: - free_soc_dts(soc_dts); - return err; } static void __exit intel_quark_thermal_exit(void) diff --git a/drivers/thermal/intel/intel_soc_dts_iosf.c b/drivers/thermal/intel/intel_soc_dts_iosf.c index 342b0bb5a56d..8c26f7b2316b 100644 --- a/drivers/thermal/intel/intel_soc_dts_iosf.c +++ b/drivers/thermal/intel/intel_soc_dts_iosf.c @@ -7,6 +7,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/bitops.h> +#include <linux/intel_tcc.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/interrupt.h> @@ -45,32 +46,6 @@ /* DTS0 and DTS 1 */ #define SOC_MAX_DTS_SENSORS 2 -static int get_tj_max(u32 *tj_max) -{ - u32 eax, edx; - u32 val; - int err; - - err = rdmsr_safe(MSR_IA32_TEMPERATURE_TARGET, &eax, &edx); - if (err) - goto err_ret; - else { - val = (eax >> 16) & 0xff; - if (val) - *tj_max = val * 1000; - else { - err = -EINVAL; - goto err_ret; - } - } - - return 0; -err_ret: - *tj_max = 0; - - return err; -} - static int sys_get_trip_temp(struct thermal_zone_device *tzd, int trip, int *temp) { @@ -405,7 +380,7 @@ struct intel_soc_dts_sensors *intel_soc_dts_iosf_init( { struct intel_soc_dts_sensors *sensors; bool notification; - u32 tj_max; + int tj_max; int ret; int i; @@ -415,8 +390,9 @@ struct intel_soc_dts_sensors *intel_soc_dts_iosf_init( if (!trip_count || read_only_trip_count > trip_count) return ERR_PTR(-EINVAL); - if (get_tj_max(&tj_max)) - return ERR_PTR(-EINVAL); + tj_max = intel_tcc_get_tjmax(-1); + if (tj_max < 0) + return ERR_PTR(tj_max); sensors = kzalloc(sizeof(*sensors), GFP_KERNEL); if (!sensors) @@ -475,4 +451,5 @@ void intel_soc_dts_iosf_exit(struct intel_soc_dts_sensors *sensors) } EXPORT_SYMBOL_GPL(intel_soc_dts_iosf_exit); +MODULE_IMPORT_NS(INTEL_TCC); MODULE_LICENSE("GPL v2"); diff --git a/drivers/thermal/intel/intel_tcc.c b/drivers/thermal/intel/intel_tcc.c new file mode 100644 index 000000000000..2e5c741c41ca --- /dev/null +++ b/drivers/thermal/intel/intel_tcc.c @@ -0,0 +1,139 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * intel_tcc.c - Library for Intel TCC (thermal control circuitry) MSR access + * Copyright (c) 2022, Intel Corporation. + */ + +#include <linux/errno.h> +#include <linux/intel_tcc.h> +#include <asm/msr.h> + +/** + * intel_tcc_get_tjmax() - returns the default TCC activation Temperature + * @cpu: cpu that the MSR should be run on, nagative value means any cpu. + * + * Get the TjMax value, which is the default thermal throttling or TCC + * activation temperature in degrees C. + * + * Return: Tjmax value in degrees C on success, negative error code otherwise. + */ +int intel_tcc_get_tjmax(int cpu) +{ + u32 low, high; + int val, err; + + if (cpu < 0) + err = rdmsr_safe(MSR_IA32_TEMPERATURE_TARGET, &low, &high); + else + err = rdmsr_safe_on_cpu(cpu, MSR_IA32_TEMPERATURE_TARGET, &low, &high); + if (err) + return err; + + val = (low >> 16) & 0xff; + + return val ? val : -ENODATA; +} +EXPORT_SYMBOL_NS_GPL(intel_tcc_get_tjmax, INTEL_TCC); + +/** + * intel_tcc_get_offset() - returns the TCC Offset value to Tjmax + * @cpu: cpu that the MSR should be run on, nagative value means any cpu. + * + * Get the TCC offset value to Tjmax. The effective thermal throttling or TCC + * activation temperature equals "Tjmax" - "TCC Offset", in degrees C. + * + * Return: Tcc offset value in degrees C on success, negative error code otherwise. + */ +int intel_tcc_get_offset(int cpu) +{ + u32 low, high; + int err; + + if (cpu < 0) + err = rdmsr_safe(MSR_IA32_TEMPERATURE_TARGET, &low, &high); + else + err = rdmsr_safe_on_cpu(cpu, MSR_IA32_TEMPERATURE_TARGET, &low, &high); + if (err) + return err; + + return (low >> 24) & 0x3f; +} +EXPORT_SYMBOL_NS_GPL(intel_tcc_get_offset, INTEL_TCC); + +/** + * intel_tcc_set_offset() - set the TCC offset value to Tjmax + * @cpu: cpu that the MSR should be run on, nagative value means any cpu. + * @offset: TCC offset value in degree C + * + * Set the TCC Offset value to Tjmax. The effective thermal throttling or TCC + * activation temperature equals "Tjmax" - "TCC Offset", in degree C. + * + * Return: On success returns 0, negative error code otherwise. + */ + +int intel_tcc_set_offset(int cpu, int offset) +{ + u32 low, high; + int err; + + if (offset < 0 || offset > 0x3f) + return -EINVAL; + + if (cpu < 0) + err = rdmsr_safe(MSR_IA32_TEMPERATURE_TARGET, &low, &high); + else + err = rdmsr_safe_on_cpu(cpu, MSR_IA32_TEMPERATURE_TARGET, &low, &high); + if (err) + return err; + + /* MSR Locked */ + if (low & BIT(31)) + return -EPERM; + + low &= ~(0x3f << 24); + low |= offset << 24; + + if (cpu < 0) + return wrmsr_safe(MSR_IA32_TEMPERATURE_TARGET, low, high); + else + return wrmsr_safe_on_cpu(cpu, MSR_IA32_TEMPERATURE_TARGET, low, high); +} +EXPORT_SYMBOL_NS_GPL(intel_tcc_set_offset, INTEL_TCC); + +/** + * intel_tcc_get_temp() - returns the current temperature + * @cpu: cpu that the MSR should be run on, nagative value means any cpu. + * @pkg: true: Package Thermal Sensor. false: Core Thermal Sensor. + * + * Get the current temperature returned by the CPU core/package level + * thermal sensor, in degrees C. + * + * Return: Temperature in degrees C on success, negative error code otherwise. + */ +int intel_tcc_get_temp(int cpu, bool pkg) +{ + u32 low, high; + u32 msr = pkg ? MSR_IA32_PACKAGE_THERM_STATUS : MSR_IA32_THERM_STATUS; + int tjmax, temp, err; + + tjmax = intel_tcc_get_tjmax(cpu); + if (tjmax < 0) + return tjmax; + + if (cpu < 0) + err = rdmsr_safe(msr, &low, &high); + else + err = rdmsr_safe_on_cpu(cpu, msr, &low, &high); + if (err) + return err; + + /* Temperature is beyond the valid thermal sensor range */ + if (!(low & BIT(31))) + return -ENODATA; + + temp = tjmax - ((low >> 16) & 0x7f); + + /* Do not allow negative CPU temperature */ + return temp >= 0 ? temp : -ENODATA; +} +EXPORT_SYMBOL_NS_GPL(intel_tcc_get_temp, INTEL_TCC); diff --git a/drivers/thermal/intel/intel_tcc_cooling.c b/drivers/thermal/intel/intel_tcc_cooling.c index a89e7e1890e4..e95f799454fe 100644 --- a/drivers/thermal/intel/intel_tcc_cooling.c +++ b/drivers/thermal/intel/intel_tcc_cooling.c @@ -7,12 +7,11 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/device.h> +#include <linux/intel_tcc.h> #include <linux/module.h> #include <linux/thermal.h> #include <asm/cpu_device_id.h> -#define TCC_SHIFT 24 -#define TCC_MASK (0x3fULL<<24) #define TCC_PROGRAMMABLE BIT(30) #define TCC_LOCKED BIT(31) @@ -21,47 +20,26 @@ static struct thermal_cooling_device *tcc_cdev; static int tcc_get_max_state(struct thermal_cooling_device *cdev, unsigned long *state) { - *state = TCC_MASK >> TCC_SHIFT; - return 0; -} - -static int tcc_offset_update(int tcc) -{ - u64 val; - int err; - - err = rdmsrl_safe(MSR_IA32_TEMPERATURE_TARGET, &val); - if (err) - return err; - - val &= ~TCC_MASK; - val |= tcc << TCC_SHIFT; - - err = wrmsrl_safe(MSR_IA32_TEMPERATURE_TARGET, val); - if (err) - return err; - + *state = 0x3f; return 0; } static int tcc_get_cur_state(struct thermal_cooling_device *cdev, unsigned long *state) { - u64 val; - int err; + int offset = intel_tcc_get_offset(-1); - err = rdmsrl_safe(MSR_IA32_TEMPERATURE_TARGET, &val); - if (err) - return err; + if (offset < 0) + return offset; - *state = (val & TCC_MASK) >> TCC_SHIFT; + *state = offset; return 0; } static int tcc_set_cur_state(struct thermal_cooling_device *cdev, unsigned long state) { - return tcc_offset_update(state); + return intel_tcc_set_offset(-1, (int)state); } static const struct thermal_cooling_device_ops tcc_cooling_ops = { @@ -140,6 +118,7 @@ static void __exit tcc_cooling_exit(void) module_exit(tcc_cooling_exit) +MODULE_IMPORT_NS(INTEL_TCC); MODULE_DESCRIPTION("TCC offset cooling device Driver"); MODULE_AUTHOR("Zhang Rui <rui.zhang@intel.com>"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/thermal/intel/x86_pkg_temp_thermal.c b/drivers/thermal/intel/x86_pkg_temp_thermal.c index 84c3a116ed04..1c2de84742df 100644 --- a/drivers/thermal/intel/x86_pkg_temp_thermal.c +++ b/drivers/thermal/intel/x86_pkg_temp_thermal.c @@ -7,6 +7,7 @@ #include <linux/module.h> #include <linux/init.h> +#include <linux/intel_tcc.h> #include <linux/err.h> #include <linux/param.h> #include <linux/device.h> @@ -48,11 +49,11 @@ MODULE_PARM_DESC(notify_delay_ms, struct zone_device { int cpu; bool work_scheduled; - u32 tj_max; u32 msr_pkg_therm_low; u32 msr_pkg_therm_high; struct delayed_work work; struct thermal_zone_device *tzone; + struct thermal_trip *trips; struct cpumask cpumask; }; @@ -104,71 +105,17 @@ static struct zone_device *pkg_temp_thermal_get_dev(unsigned int cpu) return NULL; } -/* -* tj-max is interesting because threshold is set relative to this -* temperature. -*/ -static int get_tj_max(int cpu, u32 *tj_max) -{ - u32 eax, edx, val; - int err; - - err = rdmsr_safe_on_cpu(cpu, MSR_IA32_TEMPERATURE_TARGET, &eax, &edx); - if (err) - return err; - - val = (eax >> 16) & 0xff; - *tj_max = val * 1000; - - return val ? 0 : -EINVAL; -} - static int sys_get_curr_temp(struct thermal_zone_device *tzd, int *temp) { struct zone_device *zonedev = tzd->devdata; - u32 eax, edx; - - rdmsr_on_cpu(zonedev->cpu, MSR_IA32_PACKAGE_THERM_STATUS, - &eax, &edx); - if (eax & 0x80000000) { - *temp = zonedev->tj_max - ((eax >> 16) & 0x7f) * 1000; - pr_debug("sys_get_curr_temp %d\n", *temp); - return 0; - } - return -EINVAL; -} - -static int sys_get_trip_temp(struct thermal_zone_device *tzd, - int trip, int *temp) -{ - struct zone_device *zonedev = tzd->devdata; - unsigned long thres_reg_value; - u32 mask, shift, eax, edx; - int ret; - - if (trip >= MAX_NUMBER_OF_TRIPS) - return -EINVAL; - - if (trip) { - mask = THERM_MASK_THRESHOLD1; - shift = THERM_SHIFT_THRESHOLD1; - } else { - mask = THERM_MASK_THRESHOLD0; - shift = THERM_SHIFT_THRESHOLD0; - } - - ret = rdmsr_on_cpu(zonedev->cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, - &eax, &edx); - if (ret < 0) - return ret; + int val; - thres_reg_value = (eax & mask) >> shift; - if (thres_reg_value) - *temp = zonedev->tj_max - thres_reg_value * 1000; - else - *temp = THERMAL_TEMP_INVALID; - pr_debug("sys_get_trip_temp %d\n", *temp); + val = intel_tcc_get_temp(zonedev->cpu, true); + if (val < 0) + return val; + *temp = val * 1000; + pr_debug("sys_get_curr_temp %d\n", *temp); return 0; } @@ -177,9 +124,14 @@ sys_set_trip_temp(struct thermal_zone_device *tzd, int trip, int temp) { struct zone_device *zonedev = tzd->devdata; u32 l, h, mask, shift, intr; - int ret; + int tj_max, ret; + + tj_max = intel_tcc_get_tjmax(zonedev->cpu); + if (tj_max < 0) + return tj_max; + tj_max *= 1000; - if (trip >= MAX_NUMBER_OF_TRIPS || temp >= zonedev->tj_max) + if (trip >= MAX_NUMBER_OF_TRIPS || temp >= tj_max) return -EINVAL; ret = rdmsr_on_cpu(zonedev->cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, @@ -204,7 +156,7 @@ sys_set_trip_temp(struct thermal_zone_device *tzd, int trip, int temp) if (!temp) { l &= ~intr; } else { - l |= (zonedev->tj_max - temp)/1000 << shift; + l |= (tj_max - temp)/1000 << shift; l |= intr; } @@ -212,18 +164,9 @@ sys_set_trip_temp(struct thermal_zone_device *tzd, int trip, int temp) l, h); } -static int sys_get_trip_type(struct thermal_zone_device *thermal, int trip, - enum thermal_trip_type *type) -{ - *type = THERMAL_TRIP_PASSIVE; - return 0; -} - /* Thermal zone callback registry */ static struct thermal_zone_device_ops tzone_ops = { .get_temp = sys_get_curr_temp, - .get_trip_temp = sys_get_trip_temp, - .get_trip_type = sys_get_trip_type, .set_trip_temp = sys_set_trip_temp, }; @@ -323,12 +266,55 @@ static int pkg_thermal_notify(u64 msr_val) return 0; } +static struct thermal_trip *pkg_temp_thermal_trips_init(int cpu, int tj_max, int num_trips) +{ + struct thermal_trip *trips; + unsigned long thres_reg_value; + u32 mask, shift, eax, edx; + int ret, i; + + trips = kzalloc(sizeof(*trips) * num_trips, GFP_KERNEL); + if (!trips) + return ERR_PTR(-ENOMEM); + + for (i = 0; i < num_trips; i++) { + + if (i) { + mask = THERM_MASK_THRESHOLD1; + shift = THERM_SHIFT_THRESHOLD1; + } else { + mask = THERM_MASK_THRESHOLD0; + shift = THERM_SHIFT_THRESHOLD0; + } + + ret = rdmsr_on_cpu(cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, + &eax, &edx); + if (ret < 0) { + kfree(trips); + return ERR_PTR(ret); + } + + thres_reg_value = (eax & mask) >> shift; + + trips[i].temperature = thres_reg_value ? + tj_max - thres_reg_value * 1000 : THERMAL_TEMP_INVALID; + + trips[i].type = THERMAL_TRIP_PASSIVE; + + pr_debug("%s: cpu=%d, trip=%d, temp=%d\n", + __func__, cpu, i, trips[i].temperature); + } + + return trips; +} + static int pkg_temp_thermal_device_add(unsigned int cpu) { int id = topology_logical_die_id(cpu); - u32 tj_max, eax, ebx, ecx, edx; + u32 eax, ebx, ecx, edx; struct zone_device *zonedev; int thres_count, err; + int tj_max; if (id >= max_id) return -ENOMEM; @@ -340,32 +326,34 @@ static int pkg_temp_thermal_device_add(unsigned int cpu) thres_count = clamp_val(thres_count, 0, MAX_NUMBER_OF_TRIPS); - err = get_tj_max(cpu, &tj_max); - if (err) - return err; + tj_max = intel_tcc_get_tjmax(cpu); + if (tj_max < 0) + return tj_max; zonedev = kzalloc(sizeof(*zonedev), GFP_KERNEL); if (!zonedev) return -ENOMEM; + zonedev->trips = pkg_temp_thermal_trips_init(cpu, tj_max, thres_count); + if (IS_ERR(zonedev->trips)) { + err = PTR_ERR(zonedev->trips); + goto out_kfree_zonedev; + } + INIT_DELAYED_WORK(&zonedev->work, pkg_temp_thermal_threshold_work_fn); zonedev->cpu = cpu; - zonedev->tj_max = tj_max; - zonedev->tzone = thermal_zone_device_register("x86_pkg_temp", - thres_count, + zonedev->tzone = thermal_zone_device_register_with_trips("x86_pkg_temp", + zonedev->trips, thres_count, (thres_count == MAX_NUMBER_OF_TRIPS) ? 0x03 : 0x01, zonedev, &tzone_ops, &pkg_temp_tz_params, 0, 0); if (IS_ERR(zonedev->tzone)) { err = PTR_ERR(zonedev->tzone); - kfree(zonedev); - return err; + goto out_kfree_trips; } err = thermal_zone_device_enable(zonedev->tzone); - if (err) { - thermal_zone_device_unregister(zonedev->tzone); - kfree(zonedev); - return err; - } + if (err) + goto out_unregister_tz; + /* Store MSR value for package thermal interrupt, to restore at exit */ rdmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, zonedev->msr_pkg_therm_low, zonedev->msr_pkg_therm_high); @@ -374,7 +362,16 @@ static int pkg_temp_thermal_device_add(unsigned int cpu) raw_spin_lock_irq(&pkg_temp_lock); zones[id] = zonedev; raw_spin_unlock_irq(&pkg_temp_lock); + return 0; + +out_unregister_tz: + thermal_zone_device_unregister(zonedev->tzone); +out_kfree_trips: + kfree(zonedev->trips); +out_kfree_zonedev: + kfree(zonedev); + return err; } static int pkg_thermal_cpu_offline(unsigned int cpu) @@ -458,8 +455,10 @@ static int pkg_thermal_cpu_offline(unsigned int cpu) raw_spin_unlock_irq(&pkg_temp_lock); /* Final cleanup if this is the last cpu */ - if (lastcpu) + if (lastcpu) { + kfree(zonedev->trips); kfree(zonedev); + } return 0; } @@ -531,6 +530,7 @@ static void __exit pkg_temp_thermal_exit(void) } module_exit(pkg_temp_thermal_exit) +MODULE_IMPORT_NS(INTEL_TCC); MODULE_DESCRIPTION("X86 PKG TEMP Thermal Driver"); MODULE_AUTHOR("Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>"); MODULE_LICENSE("GPL v2"); |