diff options
Diffstat (limited to 'drivers')
38 files changed, 1034 insertions, 277 deletions
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index dbd4446025ec..9a4d059f1d23 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -1119,6 +1119,8 @@ int acpi_subsys_prepare(struct device *dev) { struct acpi_device *adev = ACPI_COMPANION(dev); + dev_pm_set_strict_midlayer(dev, true); + if (dev->driver && dev->driver->pm && dev->driver->pm->prepare) { int ret = dev->driver->pm->prepare(dev); @@ -1147,6 +1149,8 @@ void acpi_subsys_complete(struct device *dev) */ if (pm_runtime_suspended(dev) && pm_resume_via_firmware()) pm_request_resume(dev); + + dev_pm_set_strict_midlayer(dev, false); } EXPORT_SYMBOL_GPL(acpi_subsys_complete); diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c index 71482d639a6d..74e34a07ef72 100644 --- a/drivers/amba/bus.c +++ b/drivers/amba/bus.c @@ -138,7 +138,7 @@ static int amba_read_periphid(struct amba_device *dev) void __iomem *tmp; int i, ret; - ret = dev_pm_domain_attach(&dev->dev, true); + ret = dev_pm_domain_attach(&dev->dev, PD_FLAG_ATTACH_POWER_ON); if (ret) { dev_dbg(&dev->dev, "can't get PM domain: %d\n", ret); goto err_out; @@ -291,7 +291,7 @@ static int amba_probe(struct device *dev) if (ret < 0) break; - ret = dev_pm_domain_attach(dev, true); + ret = dev_pm_domain_attach(dev, PD_FLAG_ATTACH_POWER_ON); if (ret) break; diff --git a/drivers/base/auxiliary.c b/drivers/base/auxiliary.c index dba7c8e13a53..44cd3f85b659 100644 --- a/drivers/base/auxiliary.c +++ b/drivers/base/auxiliary.c @@ -217,7 +217,7 @@ static int auxiliary_bus_probe(struct device *dev) struct auxiliary_device *auxdev = to_auxiliary_dev(dev); int ret; - ret = dev_pm_domain_attach(dev, true); + ret = dev_pm_domain_attach(dev, PD_FLAG_ATTACH_POWER_ON); if (ret) { dev_warn(dev, "Failed to attach to PM Domain : %d\n", ret); return ret; diff --git a/drivers/base/dd.c b/drivers/base/dd.c index b526e0e0f52d..13ab98e033ea 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -25,6 +25,7 @@ #include <linux/kthread.h> #include <linux/wait.h> #include <linux/async.h> +#include <linux/pm_domain.h> #include <linux/pm_runtime.h> #include <linux/pinctrl/devinfo.h> #include <linux/slab.h> @@ -552,6 +553,7 @@ static void device_unbind_cleanup(struct device *dev) dev->dma_range_map = NULL; device_set_driver(dev, NULL); dev_set_drvdata(dev, NULL); + dev_pm_domain_detach(dev, dev->power.detach_power_off); if (dev->pm_domain && dev->pm_domain->dismiss) dev->pm_domain->dismiss(dev); pm_runtime_reinit(dev); diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 075ec1d1b73a..09450349cf32 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -1396,15 +1396,13 @@ static int platform_probe(struct device *_dev) if (ret < 0) return ret; - ret = dev_pm_domain_attach(_dev, true); + ret = dev_pm_domain_attach(_dev, PD_FLAG_ATTACH_POWER_ON | + PD_FLAG_DETACH_POWER_OFF); if (ret) goto out; - if (drv->probe) { + if (drv->probe) ret = drv->probe(dev); - if (ret) - dev_pm_domain_detach(_dev, true); - } out: if (drv->prevent_deferred_probe && ret == -EPROBE_DEFER) { @@ -1422,7 +1420,6 @@ static void platform_remove(struct device *_dev) if (drv->remove) drv->remove(dev); - dev_pm_domain_detach(_dev, true); } static void platform_shutdown(struct device *_dev) diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c index 781968a128ff..6ecf9ce4a4e6 100644 --- a/drivers/base/power/common.c +++ b/drivers/base/power/common.c @@ -83,7 +83,7 @@ EXPORT_SYMBOL_GPL(dev_pm_put_subsys_data); /** * dev_pm_domain_attach - Attach a device to its PM domain. * @dev: Device to attach. - * @power_on: Used to indicate whether we should power on the device. + * @flags: indicate whether we should power on/off the device on attach/detach * * The @dev may only be attached to a single PM domain. By iterating through * the available alternatives we try to find a valid PM domain for the device. @@ -100,17 +100,20 @@ EXPORT_SYMBOL_GPL(dev_pm_put_subsys_data); * Returns 0 on successfully attached PM domain, or when it is found that the * device doesn't need a PM domain, else a negative error code. */ -int dev_pm_domain_attach(struct device *dev, bool power_on) +int dev_pm_domain_attach(struct device *dev, u32 flags) { int ret; if (dev->pm_domain) return 0; - ret = acpi_dev_pm_attach(dev, power_on); + ret = acpi_dev_pm_attach(dev, !!(flags & PD_FLAG_ATTACH_POWER_ON)); if (!ret) ret = genpd_dev_pm_attach(dev); + if (dev->pm_domain) + dev->power.detach_power_off = !!(flags & PD_FLAG_DETACH_POWER_OFF); + return ret < 0 ? ret : 0; } EXPORT_SYMBOL_GPL(dev_pm_domain_attach); diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 7a50af416cac..8aa06d59a2ee 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -647,14 +647,27 @@ static void dpm_async_resume_children(struct device *dev, async_func_t func) /* * Start processing "async" children of the device unless it's been * started already for them. - * - * This could have been done for the device's "async" consumers too, but - * they either need to wait for their parents or the processing has - * already started for them after their parents were processed. */ device_for_each_child(dev, func, dpm_async_with_cleanup); } +static void dpm_async_resume_subordinate(struct device *dev, async_func_t func) +{ + struct device_link *link; + int idx; + + dpm_async_resume_children(dev, func); + + idx = device_links_read_lock(); + + /* Start processing the device's "async" consumers. */ + list_for_each_entry_rcu(link, &dev->links.consumers, s_node) + if (READ_ONCE(link->status) != DL_STATE_DORMANT) + dpm_async_with_cleanup(link->consumer, func); + + device_links_read_unlock(idx); +} + static void dpm_clear_async_state(struct device *dev) { reinit_completion(&dev->power.completion); @@ -663,7 +676,14 @@ static void dpm_clear_async_state(struct device *dev) static bool dpm_root_device(struct device *dev) { - return !dev->parent; + lockdep_assert_held(&dpm_list_mtx); + + /* + * Since this function is required to run under dpm_list_mtx, the + * list_empty() below will only return true if the device's list of + * consumers is actually empty before calling it. + */ + return !dev->parent && list_empty(&dev->links.suppliers); } static void async_resume_noirq(void *data, async_cookie_t cookie); @@ -747,12 +767,12 @@ Out: TRACE_RESUME(error); if (error) { - async_error = error; + WRITE_ONCE(async_error, error); dpm_save_failed_dev(dev_name(dev)); pm_dev_err(dev, state, async ? " async noirq" : " noirq", error); } - dpm_async_resume_children(dev, async_resume_noirq); + dpm_async_resume_subordinate(dev, async_resume_noirq); } static void async_resume_noirq(void *data, async_cookie_t cookie) @@ -804,7 +824,7 @@ static void dpm_noirq_resume_devices(pm_message_t state) mutex_unlock(&dpm_list_mtx); async_synchronize_full(); dpm_show_time(starttime, state, 0, "noirq"); - if (async_error) + if (READ_ONCE(async_error)) dpm_save_failed_step(SUSPEND_RESUME_NOIRQ); trace_suspend_resume(TPS("dpm_resume_noirq"), state.event, false); @@ -890,12 +910,12 @@ Out: complete_all(&dev->power.completion); if (error) { - async_error = error; + WRITE_ONCE(async_error, error); dpm_save_failed_dev(dev_name(dev)); pm_dev_err(dev, state, async ? " async early" : " early", error); } - dpm_async_resume_children(dev, async_resume_early); + dpm_async_resume_subordinate(dev, async_resume_early); } static void async_resume_early(void *data, async_cookie_t cookie) @@ -951,7 +971,7 @@ void dpm_resume_early(pm_message_t state) mutex_unlock(&dpm_list_mtx); async_synchronize_full(); dpm_show_time(starttime, state, 0, "early"); - if (async_error) + if (READ_ONCE(async_error)) dpm_save_failed_step(SUSPEND_RESUME_EARLY); trace_suspend_resume(TPS("dpm_resume_early"), state.event, false); @@ -1066,12 +1086,12 @@ static void device_resume(struct device *dev, pm_message_t state, bool async) TRACE_RESUME(error); if (error) { - async_error = error; + WRITE_ONCE(async_error, error); dpm_save_failed_dev(dev_name(dev)); pm_dev_err(dev, state, async ? " async" : "", error); } - dpm_async_resume_children(dev, async_resume); + dpm_async_resume_subordinate(dev, async_resume); } static void async_resume(void *data, async_cookie_t cookie) @@ -1095,7 +1115,6 @@ void dpm_resume(pm_message_t state) ktime_t starttime = ktime_get(); trace_suspend_resume(TPS("dpm_resume"), state.event, true); - might_sleep(); pm_transition = state; async_error = 0; @@ -1131,7 +1150,7 @@ void dpm_resume(pm_message_t state) mutex_unlock(&dpm_list_mtx); async_synchronize_full(); dpm_show_time(starttime, state, 0, NULL); - if (async_error) + if (READ_ONCE(async_error)) dpm_save_failed_step(SUSPEND_RESUME); cpufreq_resume(); @@ -1198,7 +1217,6 @@ void dpm_complete(pm_message_t state) struct list_head list; trace_suspend_resume(TPS("dpm_complete"), state.event, true); - might_sleep(); INIT_LIST_HEAD(&list); mutex_lock(&dpm_list_mtx); @@ -1258,10 +1276,15 @@ static bool dpm_leaf_device(struct device *dev) return false; } - return true; + /* + * Since this function is required to run under dpm_list_mtx, the + * list_empty() below will only return true if the device's list of + * consumers is actually empty before calling it. + */ + return list_empty(&dev->links.consumers); } -static void dpm_async_suspend_parent(struct device *dev, async_func_t func) +static bool dpm_async_suspend_parent(struct device *dev, async_func_t func) { guard(mutex)(&dpm_list_mtx); @@ -1273,11 +1296,31 @@ static void dpm_async_suspend_parent(struct device *dev, async_func_t func) * deleted before it. */ if (!device_pm_initialized(dev)) - return; + return false; /* Start processing the device's parent if it is "async". */ if (dev->parent) dpm_async_with_cleanup(dev->parent, func); + + return true; +} + +static void dpm_async_suspend_superior(struct device *dev, async_func_t func) +{ + struct device_link *link; + int idx; + + if (!dpm_async_suspend_parent(dev, func)) + return; + + idx = device_links_read_lock(); + + /* Start processing the device's "async" suppliers. */ + list_for_each_entry_rcu(link, &dev->links.suppliers, c_node) + if (READ_ONCE(link->status) != DL_STATE_DORMANT) + dpm_async_with_cleanup(link->supplier, func); + + device_links_read_unlock(idx); } static void dpm_async_suspend_complete_all(struct list_head *device_list) @@ -1344,7 +1387,7 @@ static void async_suspend_noirq(void *data, async_cookie_t cookie); * The driver of @dev will not receive interrupts while this function is being * executed. */ -static int device_suspend_noirq(struct device *dev, pm_message_t state, bool async) +static void device_suspend_noirq(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; @@ -1355,7 +1398,7 @@ static int device_suspend_noirq(struct device *dev, pm_message_t state, bool asy dpm_wait_for_subordinate(dev, async); - if (async_error) + if (READ_ONCE(async_error)) goto Complete; if (dev->power.syscore || dev->power.direct_complete) @@ -1388,7 +1431,7 @@ static int device_suspend_noirq(struct device *dev, pm_message_t state, bool asy Run: error = dpm_run_callback(callback, dev, state, info); if (error) { - async_error = error; + WRITE_ONCE(async_error, error); dpm_save_failed_dev(dev_name(dev)); pm_dev_err(dev, state, async ? " async noirq" : " noirq", error); goto Complete; @@ -1414,12 +1457,10 @@ Complete: complete_all(&dev->power.completion); TRACE_SUSPEND(error); - if (error || async_error) - return error; - - dpm_async_suspend_parent(dev, async_suspend_noirq); + if (error || READ_ONCE(async_error)) + return; - return 0; + dpm_async_suspend_superior(dev, async_suspend_noirq); } static void async_suspend_noirq(void *data, async_cookie_t cookie) @@ -1434,7 +1475,7 @@ static int dpm_noirq_suspend_devices(pm_message_t state) { ktime_t starttime = ktime_get(); struct device *dev; - int error = 0; + int error; trace_suspend_resume(TPS("dpm_suspend_noirq"), state.event, true); @@ -1465,13 +1506,13 @@ static int dpm_noirq_suspend_devices(pm_message_t state) mutex_unlock(&dpm_list_mtx); - error = device_suspend_noirq(dev, state, false); + device_suspend_noirq(dev, state, false); put_device(dev); mutex_lock(&dpm_list_mtx); - if (error || async_error) { + if (READ_ONCE(async_error)) { dpm_async_suspend_complete_all(&dpm_late_early_list); /* * Move all devices to the target list to resume them @@ -1485,9 +1526,8 @@ static int dpm_noirq_suspend_devices(pm_message_t state) mutex_unlock(&dpm_list_mtx); async_synchronize_full(); - if (!error) - error = async_error; + error = READ_ONCE(async_error); if (error) dpm_save_failed_step(SUSPEND_SUSPEND_NOIRQ); @@ -1542,7 +1582,7 @@ static void async_suspend_late(void *data, async_cookie_t cookie); * * Runtime PM is disabled for @dev while this function is being executed. */ -static int device_suspend_late(struct device *dev, pm_message_t state, bool async) +static void device_suspend_late(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; @@ -1559,11 +1599,11 @@ static int device_suspend_late(struct device *dev, pm_message_t state, bool asyn dpm_wait_for_subordinate(dev, async); - if (async_error) + if (READ_ONCE(async_error)) goto Complete; if (pm_wakeup_pending()) { - async_error = -EBUSY; + WRITE_ONCE(async_error, -EBUSY); goto Complete; } @@ -1597,7 +1637,7 @@ static int device_suspend_late(struct device *dev, pm_message_t state, bool asyn Run: error = dpm_run_callback(callback, dev, state, info); if (error) { - async_error = error; + WRITE_ONCE(async_error, error); dpm_save_failed_dev(dev_name(dev)); pm_dev_err(dev, state, async ? " async late" : " late", error); goto Complete; @@ -1611,12 +1651,10 @@ Complete: TRACE_SUSPEND(error); complete_all(&dev->power.completion); - if (error || async_error) - return error; - - dpm_async_suspend_parent(dev, async_suspend_late); + if (error || READ_ONCE(async_error)) + return; - return 0; + dpm_async_suspend_superior(dev, async_suspend_late); } static void async_suspend_late(void *data, async_cookie_t cookie) @@ -1635,7 +1673,7 @@ int dpm_suspend_late(pm_message_t state) { ktime_t starttime = ktime_get(); struct device *dev; - int error = 0; + int error; trace_suspend_resume(TPS("dpm_suspend_late"), state.event, true); @@ -1668,13 +1706,13 @@ int dpm_suspend_late(pm_message_t state) mutex_unlock(&dpm_list_mtx); - error = device_suspend_late(dev, state, false); + device_suspend_late(dev, state, false); put_device(dev); mutex_lock(&dpm_list_mtx); - if (error || async_error) { + if (READ_ONCE(async_error)) { dpm_async_suspend_complete_all(&dpm_suspended_list); /* * Move all devices to the target list to resume them @@ -1688,9 +1726,8 @@ int dpm_suspend_late(pm_message_t state) mutex_unlock(&dpm_list_mtx); async_synchronize_full(); - if (!error) - error = async_error; + error = READ_ONCE(async_error); if (error) { dpm_save_failed_step(SUSPEND_SUSPEND_LATE); dpm_resume_early(resume_event(state)); @@ -1779,7 +1816,7 @@ static void async_suspend(void *data, async_cookie_t cookie); * @state: PM transition of the system being carried out. * @async: If true, the device is being suspended asynchronously. */ -static int device_suspend(struct device *dev, pm_message_t state, bool async) +static void device_suspend(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; @@ -1791,7 +1828,7 @@ static int device_suspend(struct device *dev, pm_message_t state, bool async) dpm_wait_for_subordinate(dev, async); - if (async_error) { + if (READ_ONCE(async_error)) { dev->power.direct_complete = false; goto Complete; } @@ -1811,7 +1848,7 @@ static int device_suspend(struct device *dev, pm_message_t state, bool async) if (pm_wakeup_pending()) { dev->power.direct_complete = false; - async_error = -EBUSY; + WRITE_ONCE(async_error, -EBUSY); goto Complete; } @@ -1895,7 +1932,7 @@ static int device_suspend(struct device *dev, pm_message_t state, bool async) Complete: if (error) { - async_error = error; + WRITE_ONCE(async_error, error); dpm_save_failed_dev(dev_name(dev)); pm_dev_err(dev, state, async ? " async" : "", error); } @@ -1903,12 +1940,10 @@ static int device_suspend(struct device *dev, pm_message_t state, bool async) complete_all(&dev->power.completion); TRACE_SUSPEND(error); - if (error || async_error) - return error; - - dpm_async_suspend_parent(dev, async_suspend); + if (error || READ_ONCE(async_error)) + return; - return 0; + dpm_async_suspend_superior(dev, async_suspend); } static void async_suspend(void *data, async_cookie_t cookie) @@ -1927,7 +1962,7 @@ int dpm_suspend(pm_message_t state) { ktime_t starttime = ktime_get(); struct device *dev; - int error = 0; + int error; trace_suspend_resume(TPS("dpm_suspend"), state.event, true); might_sleep(); @@ -1962,13 +1997,13 @@ int dpm_suspend(pm_message_t state) mutex_unlock(&dpm_list_mtx); - error = device_suspend(dev, state, false); + device_suspend(dev, state, false); put_device(dev); mutex_lock(&dpm_list_mtx); - if (error || async_error) { + if (READ_ONCE(async_error)) { dpm_async_suspend_complete_all(&dpm_prepared_list); /* * Move all devices to the target list to resume them @@ -1982,9 +2017,8 @@ int dpm_suspend(pm_message_t state) mutex_unlock(&dpm_list_mtx); async_synchronize_full(); - if (!error) - error = async_error; + error = READ_ONCE(async_error); if (error) dpm_save_failed_step(SUSPEND_SUSPEND); @@ -2129,7 +2163,6 @@ int dpm_prepare(pm_message_t state) int error = 0; trace_suspend_resume(TPS("dpm_prepare"), state.event, true); - might_sleep(); /* * Give a chance for the known devices to complete their probes, before diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index c55a7c70bc1a..f835b85bd4d9 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -19,10 +19,24 @@ typedef int (*pm_callback_t)(struct device *); +static inline pm_callback_t get_callback_ptr(const void *start, size_t offset) +{ + return *(pm_callback_t *)(start + offset); +} + +static pm_callback_t __rpm_get_driver_callback(struct device *dev, + size_t cb_offset) +{ + if (dev->driver && dev->driver->pm) + return get_callback_ptr(dev->driver->pm, cb_offset); + + return NULL; +} + static pm_callback_t __rpm_get_callback(struct device *dev, size_t cb_offset) { - pm_callback_t cb; const struct dev_pm_ops *ops; + pm_callback_t cb = NULL; if (dev->pm_domain) ops = &dev->pm_domain->ops; @@ -36,12 +50,10 @@ static pm_callback_t __rpm_get_callback(struct device *dev, size_t cb_offset) ops = NULL; if (ops) - cb = *(pm_callback_t *)((void *)ops + cb_offset); - else - cb = NULL; + cb = get_callback_ptr(ops, cb_offset); - if (!cb && dev->driver && dev->driver->pm) - cb = *(pm_callback_t *)((void *)dev->driver->pm + cb_offset); + if (!cb) + cb = __rpm_get_driver_callback(dev, cb_offset); return cb; } @@ -1191,10 +1203,12 @@ EXPORT_SYMBOL_GPL(__pm_runtime_resume); * * Return -EINVAL if runtime PM is disabled for @dev. * - * Otherwise, if the runtime PM status of @dev is %RPM_ACTIVE and either - * @ign_usage_count is %true or the runtime PM usage counter of @dev is not - * zero, increment the usage counter of @dev and return 1. Otherwise, return 0 - * without changing the usage counter. + * Otherwise, if its runtime PM status is %RPM_ACTIVE and (1) @ign_usage_count + * is set, or (2) @dev is not ignoring children and its active child count is + * nonero, or (3) the runtime PM usage counter of @dev is not zero, increment + * the usage counter of @dev and return 1. + * + * Otherwise, return 0 without changing the usage counter. * * If @ign_usage_count is %true, this function can be used to prevent suspending * the device when its runtime PM status is %RPM_ACTIVE. @@ -1216,7 +1230,8 @@ static int pm_runtime_get_conditional(struct device *dev, bool ign_usage_count) retval = -EINVAL; } else if (dev->power.runtime_status != RPM_ACTIVE) { retval = 0; - } else if (ign_usage_count) { + } else if (ign_usage_count || (!dev->power.ignore_children && + atomic_read(&dev->power.child_count) > 0)) { retval = 1; atomic_inc(&dev->power.usage_count); } else { @@ -1249,10 +1264,16 @@ EXPORT_SYMBOL_GPL(pm_runtime_get_if_active); * @dev: Target device. * * Increment the runtime PM usage counter of @dev if its runtime PM status is - * %RPM_ACTIVE and its runtime PM usage counter is greater than 0, in which case - * it returns 1. If the device is in a different state or its usage_count is 0, - * 0 is returned. -EINVAL is returned if runtime PM is disabled for the device, - * in which case also the usage_count will remain unmodified. + * %RPM_ACTIVE and its runtime PM usage counter is greater than 0 or it is not + * ignoring children and its active child count is nonzero. 1 is returned in + * this case. + * + * If @dev is in a different state or it is not in use (that is, its usage + * counter is 0, or it is ignoring children, or its active child count is 0), + * 0 is returned. + * + * -EINVAL is returned if runtime PM is disabled for the device, in which case + * also the usage counter of @dev is not updated. */ int pm_runtime_get_if_in_use(struct device *dev) { @@ -1827,7 +1848,7 @@ void pm_runtime_init(struct device *dev) dev->power.request_pending = false; dev->power.request = RPM_REQ_NONE; dev->power.deferred_resume = false; - dev->power.needs_force_resume = 0; + dev->power.needs_force_resume = false; INIT_WORK(&dev->power.work, pm_runtime_work); dev->power.timer_expires = 0; @@ -1854,6 +1875,11 @@ void pm_runtime_reinit(struct device *dev) pm_runtime_put(dev->parent); } } + /* + * Clear power.needs_force_resume in case it has been set by + * pm_runtime_force_suspend() invoked from a driver remove callback. + */ + dev->power.needs_force_resume = false; } /** @@ -1941,13 +1967,23 @@ void pm_runtime_drop_link(struct device_link *link) pm_request_idle(link->supplier); } -bool pm_runtime_need_not_resume(struct device *dev) +static pm_callback_t get_callback(struct device *dev, size_t cb_offset) { - return atomic_read(&dev->power.usage_count) <= 1 && - (atomic_read(&dev->power.child_count) == 0 || - dev->power.ignore_children); + /* + * Setting power.strict_midlayer means that the middle layer + * code does not want its runtime PM callbacks to be invoked via + * pm_runtime_force_suspend() and pm_runtime_force_resume(), so + * return a direct pointer to the driver callback in that case. + */ + if (dev_pm_strict_midlayer_is_set(dev)) + return __rpm_get_driver_callback(dev, cb_offset); + + return __rpm_get_callback(dev, cb_offset); } +#define GET_CALLBACK(dev, callback) \ + get_callback(dev, offsetof(struct dev_pm_ops, callback)) + /** * pm_runtime_force_suspend - Force a device into suspend state if needed. * @dev: Device to suspend. @@ -1964,10 +2000,6 @@ bool pm_runtime_need_not_resume(struct device *dev) * sure the device is put into low power state and it should only be used during * system-wide PM transitions to sleep states. It assumes that the analogous * pm_runtime_force_resume() will be used to resume the device. - * - * Do not use with DPM_FLAG_SMART_SUSPEND as this can lead to an inconsistent - * state where this function has called the ->runtime_suspend callback but the - * PM core marks the driver as runtime active. */ int pm_runtime_force_suspend(struct device *dev) { @@ -1975,10 +2007,10 @@ int pm_runtime_force_suspend(struct device *dev) int ret; pm_runtime_disable(dev); - if (pm_runtime_status_suspended(dev)) + if (pm_runtime_status_suspended(dev) || dev->power.needs_force_resume) return 0; - callback = RPM_GET_CALLBACK(dev, runtime_suspend); + callback = GET_CALLBACK(dev, runtime_suspend); dev_pm_enable_wake_irq_check(dev, true); ret = callback ? callback(dev) : 0; @@ -1990,15 +2022,16 @@ int pm_runtime_force_suspend(struct device *dev) /* * If the device can stay in suspend after the system-wide transition * to the working state that will follow, drop the children counter of - * its parent, but set its status to RPM_SUSPENDED anyway in case this - * function will be called again for it in the meantime. + * its parent and the usage counters of its suppliers. Otherwise, set + * power.needs_force_resume to let pm_runtime_force_resume() know that + * the device needs to be taken care of and to prevent this function + * from handling the device again in case the device is passed to it + * once more subsequently. */ - if (pm_runtime_need_not_resume(dev)) { + if (pm_runtime_need_not_resume(dev)) pm_runtime_set_suspended(dev); - } else { - __update_runtime_status(dev, RPM_SUSPENDED); - dev->power.needs_force_resume = 1; - } + else + dev->power.needs_force_resume = true; return 0; @@ -2009,33 +2042,37 @@ err: } EXPORT_SYMBOL_GPL(pm_runtime_force_suspend); +#ifdef CONFIG_PM_SLEEP + /** * pm_runtime_force_resume - Force a device into resume state if needed. * @dev: Device to resume. * - * Prior invoking this function we expect the user to have brought the device - * into low power state by a call to pm_runtime_force_suspend(). Here we reverse - * those actions and bring the device into full power, if it is expected to be - * used on system resume. In the other case, we defer the resume to be managed - * via runtime PM. + * This function expects that either pm_runtime_force_suspend() has put the + * device into a low-power state prior to calling it, or the device had been + * runtime-suspended before the preceding system-wide suspend transition and it + * was left in suspend during that transition. * - * Typically this function may be invoked from a system resume callback. + * The actions carried out by pm_runtime_force_suspend(), or by a runtime + * suspend in general, are reversed and the device is brought back into full + * power if it is expected to be used on system resume, which is the case when + * its needs_force_resume flag is set or when its smart_suspend flag is set and + * its runtime PM status is "active". + * + * In other cases, the resume is deferred to be managed via runtime PM. + * + * Typically, this function may be invoked from a system resume callback. */ int pm_runtime_force_resume(struct device *dev) { int (*callback)(struct device *); int ret = 0; - if (!dev->power.needs_force_resume) + if (!dev->power.needs_force_resume && (!dev_pm_smart_suspend(dev) || + pm_runtime_status_suspended(dev))) goto out; - /* - * The value of the parent's children counter is correct already, so - * just update the status of the device. - */ - __update_runtime_status(dev, RPM_ACTIVE); - - callback = RPM_GET_CALLBACK(dev, runtime_resume); + callback = GET_CALLBACK(dev, runtime_resume); dev_pm_disable_wake_irq_check(dev, false); ret = callback ? callback(dev) : 0; @@ -2046,9 +2083,30 @@ int pm_runtime_force_resume(struct device *dev) } pm_runtime_mark_last_busy(dev); + out: - dev->power.needs_force_resume = 0; + /* + * The smart_suspend flag can be cleared here because it is not going + * to be necessary until the next system-wide suspend transition that + * will update it again. + */ + dev->power.smart_suspend = false; + /* + * Also clear needs_force_resume to make this function skip devices that + * have been seen by it once. + */ + dev->power.needs_force_resume = false; + pm_runtime_enable(dev); return ret; } EXPORT_SYMBOL_GPL(pm_runtime_force_resume); + +bool pm_runtime_need_not_resume(struct device *dev) +{ + return atomic_read(&dev->power.usage_count) <= 1 && + (atomic_read(&dev->power.child_count) == 0 || + dev->power.ignore_children); +} + +#endif /* CONFIG_PM_SLEEP */ diff --git a/drivers/clk/qcom/apcs-sdx55.c b/drivers/clk/qcom/apcs-sdx55.c index 3ba01622d8f0..90dd1f1855c2 100644 --- a/drivers/clk/qcom/apcs-sdx55.c +++ b/drivers/clk/qcom/apcs-sdx55.c @@ -111,7 +111,7 @@ static int qcom_apcs_sdx55_clk_probe(struct platform_device *pdev) * driver, there seems to be no better place to do this. So do it here! */ cpu_dev = get_cpu_device(0); - ret = dev_pm_domain_attach(cpu_dev, true); + ret = dev_pm_domain_attach(cpu_dev, PD_FLAG_ATTACH_POWER_ON); if (ret) { dev_err_probe(dev, ret, "can't get PM domain: %d\n", ret); goto err; diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index 0d46402e3094..9be0503df55a 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -28,7 +28,6 @@ config ARM_APPLE_SOC_CPUFREQ tristate "Apple Silicon SoC CPUFreq support" depends on ARCH_APPLE || (COMPILE_TEST && 64BIT) select PM_OPP - default ARCH_APPLE help This adds the CPUFreq driver for Apple Silicon machines (e.g. Apple M1). @@ -238,7 +237,7 @@ config ARM_TEGRA20_CPUFREQ This adds the CPUFreq driver support for Tegra20/30 SOCs. config ARM_TEGRA124_CPUFREQ - bool "Tegra124 CPUFreq support" + tristate "Tegra124 CPUFreq support" depends on ARCH_TEGRA || COMPILE_TEST depends on CPUFREQ_DT default ARCH_TEGRA diff --git a/drivers/cpufreq/armada-8k-cpufreq.c b/drivers/cpufreq/armada-8k-cpufreq.c index 5a3545bd0d8d..d96c1718f7f8 100644 --- a/drivers/cpufreq/armada-8k-cpufreq.c +++ b/drivers/cpufreq/armada-8k-cpufreq.c @@ -103,7 +103,7 @@ static void armada_8k_cpufreq_free_table(struct freq_table *freq_tables) { int opps_index, nb_cpus = num_possible_cpus(); - for (opps_index = 0 ; opps_index <= nb_cpus; opps_index++) { + for (opps_index = 0 ; opps_index < nb_cpus; opps_index++) { int i; /* If cpu_dev is NULL then we reached the end of the array */ @@ -132,7 +132,7 @@ static int __init armada_8k_cpufreq_init(void) int ret = 0, opps_index = 0, cpu, nb_cpus; struct freq_table *freq_tables; struct device_node *node; - static struct cpumask cpus; + static struct cpumask cpus, shared_cpus; node = of_find_matching_node_and_match(NULL, armada_8k_cpufreq_of_match, NULL); @@ -154,7 +154,6 @@ static int __init armada_8k_cpufreq_init(void) * divisions of it). */ for_each_cpu(cpu, &cpus) { - struct cpumask shared_cpus; struct device *cpu_dev; struct clk *clk; diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c index 7b841a086acc..5940d262374f 100644 --- a/drivers/cpufreq/brcmstb-avs-cpufreq.c +++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c @@ -765,7 +765,7 @@ static void brcm_avs_cpufreq_remove(struct platform_device *pdev) } static const struct of_device_id brcm_avs_cpufreq_match[] = { - { .compatible = BRCM_AVS_CPU_DATA }, + { .compatible = "brcm,avs-cpu-data-mem" }, { } }; MODULE_DEVICE_TABLE(of, brcm_avs_cpufreq_match); diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index b7c688a5659c..4a17162a392d 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -26,14 +26,6 @@ #include <acpi/cppc_acpi.h> -/* - * This list contains information parsed from per CPU ACPI _CPC and _PSD - * structures: e.g. the highest and lowest supported performance, capabilities, - * desired performance, level requested etc. Depending on the share_type, not - * all CPUs will have an entry in the list. - */ -static LIST_HEAD(cpu_data_list); - static struct cpufreq_driver cppc_cpufreq_driver; #ifdef CONFIG_ACPI_CPPC_CPUFREQ_FIE @@ -352,7 +344,6 @@ static unsigned int cppc_cpufreq_get_transition_delay_us(unsigned int cpu) #if defined(CONFIG_ARM64) && defined(CONFIG_ENERGY_MODEL) static DEFINE_PER_CPU(unsigned int, efficiency_class); -static void cppc_cpufreq_register_em(struct cpufreq_policy *policy); /* Create an artificial performance state every CPPC_EM_CAP_STEP capacity unit. */ #define CPPC_EM_CAP_STEP (20) @@ -488,7 +479,19 @@ static int cppc_get_cpu_cost(struct device *cpu_dev, unsigned long KHz, return 0; } -static int populate_efficiency_class(void) +static void cppc_cpufreq_register_em(struct cpufreq_policy *policy) +{ + struct cppc_cpudata *cpu_data; + struct em_data_callback em_cb = + EM_ADV_DATA_CB(cppc_get_cpu_power, cppc_get_cpu_cost); + + cpu_data = policy->driver_data; + em_dev_register_perf_domain(get_cpu_device(policy->cpu), + get_perf_level_count(policy), &em_cb, + cpu_data->shared_cpu_map, 0); +} + +static void populate_efficiency_class(void) { struct acpi_madt_generic_interrupt *gicc; DECLARE_BITMAP(used_classes, 256) = {}; @@ -503,7 +506,7 @@ static int populate_efficiency_class(void) if (bitmap_weight(used_classes, 256) <= 1) { pr_debug("Efficiency classes are all equal (=%d). " "No EM registered", class); - return -EINVAL; + return; } /* @@ -520,26 +523,11 @@ static int populate_efficiency_class(void) index++; } cppc_cpufreq_driver.register_em = cppc_cpufreq_register_em; - - return 0; -} - -static void cppc_cpufreq_register_em(struct cpufreq_policy *policy) -{ - struct cppc_cpudata *cpu_data; - struct em_data_callback em_cb = - EM_ADV_DATA_CB(cppc_get_cpu_power, cppc_get_cpu_cost); - - cpu_data = policy->driver_data; - em_dev_register_perf_domain(get_cpu_device(policy->cpu), - get_perf_level_count(policy), &em_cb, - cpu_data->shared_cpu_map, 0); } #else -static int populate_efficiency_class(void) +static void populate_efficiency_class(void) { - return 0; } #endif @@ -567,8 +555,6 @@ static struct cppc_cpudata *cppc_cpufreq_get_cpu_data(unsigned int cpu) goto free_mask; } - list_add(&cpu_data->node, &cpu_data_list); - return cpu_data; free_mask: @@ -583,7 +569,6 @@ static void cppc_cpufreq_put_cpu_data(struct cpufreq_policy *policy) { struct cppc_cpudata *cpu_data = policy->driver_data; - list_del(&cpu_data->node); free_cpumask_var(cpu_data->shared_cpu_map); kfree(cpu_data); policy->driver_data = NULL; @@ -925,7 +910,7 @@ static struct freq_attr *cppc_cpufreq_attr[] = { }; static struct cpufreq_driver cppc_cpufreq_driver = { - .flags = CPUFREQ_CONST_LOOPS, + .flags = CPUFREQ_CONST_LOOPS | CPUFREQ_NEED_UPDATE_LIMITS, .verify = cppc_verify_policy, .target = cppc_cpufreq_set_target, .get = cppc_cpufreq_get_rate, @@ -954,24 +939,10 @@ static int __init cppc_cpufreq_init(void) return ret; } -static inline void free_cpu_data(void) -{ - struct cppc_cpudata *iter, *tmp; - - list_for_each_entry_safe(iter, tmp, &cpu_data_list, node) { - free_cpumask_var(iter->shared_cpu_map); - list_del(&iter->node); - kfree(iter); - } - -} - static void __exit cppc_cpufreq_exit(void) { cpufreq_unregister_driver(&cppc_cpufreq_driver); cppc_freq_invariance_exit(); - - free_cpu_data(); } module_exit(cppc_cpufreq_exit); diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c index a010da0f6337..015dd393eaba 100644 --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -143,6 +143,7 @@ static const struct of_device_id blocklist[] __initconst = { { .compatible = "nvidia,tegra20", }, { .compatible = "nvidia,tegra30", }, + { .compatible = "nvidia,tegra114", }, { .compatible = "nvidia,tegra124", }, { .compatible = "nvidia,tegra210", }, { .compatible = "nvidia,tegra234", }, diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c index e80dd982a3e2..506437489b4d 100644 --- a/drivers/cpufreq/cpufreq-dt.c +++ b/drivers/cpufreq/cpufreq-dt.c @@ -329,6 +329,17 @@ static struct platform_driver dt_cpufreq_platdrv = { }; module_platform_driver(dt_cpufreq_platdrv); +struct platform_device *cpufreq_dt_pdev_register(struct device *dev) +{ + struct platform_device_info cpufreq_dt_devinfo = {}; + + cpufreq_dt_devinfo.name = "cpufreq-dt"; + cpufreq_dt_devinfo.parent = dev; + + return platform_device_register_full(&cpufreq_dt_devinfo); +} +EXPORT_SYMBOL_GPL(cpufreq_dt_pdev_register); + MODULE_ALIAS("platform:cpufreq-dt"); MODULE_AUTHOR("Viresh Kumar <viresh.kumar@linaro.org>"); MODULE_AUTHOR("Shawn Guo <shawn.guo@linaro.org>"); diff --git a/drivers/cpufreq/cpufreq-dt.h b/drivers/cpufreq/cpufreq-dt.h index 28c8af7ec5ef..fc1889aeb4f1 100644 --- a/drivers/cpufreq/cpufreq-dt.h +++ b/drivers/cpufreq/cpufreq-dt.h @@ -22,4 +22,6 @@ struct cpufreq_dt_platform_data { int (*resume)(struct cpufreq_policy *policy); }; +struct platform_device *cpufreq_dt_pdev_register(struct device *dev); + #endif /* __CPUFREQ_DT_H__ */ diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index d7426e1d8bdd..fc7eace8b65b 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -109,6 +109,8 @@ void disable_cpufreq(void) { off = 1; } +EXPORT_SYMBOL_GPL(disable_cpufreq); + static DEFINE_MUTEX(cpufreq_governor_mutex); bool have_governor_per_policy(void) @@ -967,6 +969,7 @@ static struct attribute *cpufreq_attrs[] = { &cpuinfo_min_freq.attr, &cpuinfo_max_freq.attr, &cpuinfo_transition_latency.attr, + &scaling_cur_freq.attr, &scaling_min_freq.attr, &scaling_max_freq.attr, &affected_cpus.attr, @@ -1095,10 +1098,6 @@ static int cpufreq_add_dev_interface(struct cpufreq_policy *policy) return ret; } - ret = sysfs_create_file(&policy->kobj, &scaling_cur_freq.attr); - if (ret) - return ret; - if (cpufreq_driver->bios_limit) { ret = sysfs_create_file(&policy->kobj, &bios_limit.attr); if (ret) @@ -1284,6 +1283,8 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu) goto err_free_real_cpus; } + init_rwsem(&policy->rwsem); + freq_constraints_init(&policy->constraints); policy->nb_min.notifier_call = cpufreq_notifier_min; @@ -1306,7 +1307,6 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu) } INIT_LIST_HEAD(&policy->policy_list); - init_rwsem(&policy->rwsem); spin_lock_init(&policy->transition_lock); init_waitqueue_head(&policy->transition_wait); INIT_WORK(&policy->update, handle_update); @@ -1694,14 +1694,13 @@ static void __cpufreq_offline(unsigned int cpu, struct cpufreq_policy *policy) return; } - if (has_target()) + if (has_target()) { strscpy(policy->last_governor, policy->governor->name, CPUFREQ_NAME_LEN); - else - policy->last_policy = policy->policy; - - if (has_target()) cpufreq_exit_governor(policy); + } else { + policy->last_policy = policy->policy; + } /* * Perform the ->offline() during light-weight tear-down, as @@ -1803,6 +1802,9 @@ static unsigned int cpufreq_verify_current_freq(struct cpufreq_policy *policy, b { unsigned int new_freq; + if (!cpufreq_driver->get) + return 0; + new_freq = cpufreq_driver->get(policy->cpu); if (!new_freq) return 0; @@ -1925,10 +1927,7 @@ unsigned int cpufreq_get(unsigned int cpu) guard(cpufreq_policy_read)(policy); - if (cpufreq_driver->get) - return __cpufreq_get(policy); - - return 0; + return __cpufreq_get(policy); } EXPORT_SYMBOL(cpufreq_get); @@ -2482,8 +2481,7 @@ int cpufreq_start_governor(struct cpufreq_policy *policy) pr_debug("%s: for CPU %u\n", __func__, policy->cpu); - if (cpufreq_driver->get) - cpufreq_verify_current_freq(policy, false); + cpufreq_verify_current_freq(policy, false); if (policy->governor->start) { ret = policy->governor->start(policy); @@ -2715,10 +2713,12 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy, pr_debug("starting governor %s failed\n", policy->governor->name); if (old_gov) { policy->governor = old_gov; - if (cpufreq_init_governor(policy)) + if (cpufreq_init_governor(policy)) { policy->governor = NULL; - else - cpufreq_start_governor(policy); + } else if (cpufreq_start_governor(policy)) { + cpufreq_exit_governor(policy); + policy->governor = NULL; + } } return ret; @@ -2944,15 +2944,6 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) cpufreq_driver = driver_data; write_unlock_irqrestore(&cpufreq_driver_lock, flags); - /* - * Mark support for the scheduler's frequency invariance engine for - * drivers that implement target(), target_index() or fast_switch(). - */ - if (!cpufreq_driver->setpolicy) { - static_branch_enable_cpuslocked(&cpufreq_freq_invariance); - pr_debug("supports frequency invariance"); - } - if (driver_data->setpolicy) driver_data->flags |= CPUFREQ_CONST_LOOPS; @@ -2983,6 +2974,15 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) hp_online = ret; ret = 0; + /* + * Mark support for the scheduler's frequency invariance engine for + * drivers that implement target(), target_index() or fast_switch(). + */ + if (!cpufreq_driver->setpolicy) { + static_branch_enable_cpuslocked(&cpufreq_freq_invariance); + pr_debug("supports frequency invariance"); + } + pr_debug("driver %s up and running\n", driver_data->name); goto out; diff --git a/drivers/cpufreq/cpufreq_userspace.c b/drivers/cpufreq/cpufreq_userspace.c index 2c42fee76daa..77d62152cd38 100644 --- a/drivers/cpufreq/cpufreq_userspace.c +++ b/drivers/cpufreq/cpufreq_userspace.c @@ -134,6 +134,7 @@ static struct cpufreq_governor cpufreq_gov_userspace = { .store_setspeed = cpufreq_set, .show_setspeed = show_speed, .owner = THIS_MODULE, + .flags = CPUFREQ_GOV_STRICT_TARGET, }; MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>, " diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 64587d318267..06a1c7dd081f 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -2775,6 +2775,8 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = { X86_MATCH(INTEL_TIGERLAKE, core_funcs), X86_MATCH(INTEL_SAPPHIRERAPIDS_X, core_funcs), X86_MATCH(INTEL_EMERALDRAPIDS_X, core_funcs), + X86_MATCH(INTEL_GRANITERAPIDS_D, core_funcs), + X86_MATCH(INTEL_GRANITERAPIDS_X, core_funcs), {} }; MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids); @@ -3249,8 +3251,8 @@ static int intel_cpufreq_update_pstate(struct cpufreq_policy *policy, int max_pstate = policy->strict_target ? target_pstate : cpu->max_perf_ratio; - intel_cpufreq_hwp_update(cpu, target_pstate, max_pstate, 0, - fast_switch); + intel_cpufreq_hwp_update(cpu, target_pstate, max_pstate, + target_pstate, fast_switch); } else if (target_pstate != old_pstate) { intel_cpufreq_perf_ctl_update(cpu, target_pstate, fast_switch); } diff --git a/drivers/cpufreq/tegra124-cpufreq.c b/drivers/cpufreq/tegra124-cpufreq.c index 514146d98bca..f8a76bbecef9 100644 --- a/drivers/cpufreq/tegra124-cpufreq.c +++ b/drivers/cpufreq/tegra124-cpufreq.c @@ -16,6 +16,10 @@ #include <linux/pm_opp.h> #include <linux/types.h> +#include "cpufreq-dt.h" + +static struct platform_device *tegra124_cpufreq_pdev; + struct tegra124_cpufreq_priv { struct clk *cpu_clk; struct clk *pllp_clk; @@ -55,7 +59,6 @@ static int tegra124_cpufreq_probe(struct platform_device *pdev) struct device_node *np __free(device_node) = of_cpu_device_node_get(0); struct tegra124_cpufreq_priv *priv; struct device *cpu_dev; - struct platform_device_info cpufreq_dt_devinfo = {}; int ret; if (!np) @@ -95,11 +98,7 @@ static int tegra124_cpufreq_probe(struct platform_device *pdev) if (ret) goto out_put_pllp_clk; - cpufreq_dt_devinfo.name = "cpufreq-dt"; - cpufreq_dt_devinfo.parent = &pdev->dev; - - priv->cpufreq_dt_pdev = - platform_device_register_full(&cpufreq_dt_devinfo); + priv->cpufreq_dt_pdev = cpufreq_dt_pdev_register(&pdev->dev); if (IS_ERR(priv->cpufreq_dt_pdev)) { ret = PTR_ERR(priv->cpufreq_dt_pdev); goto out_put_pllp_clk; @@ -173,6 +172,21 @@ disable_cpufreq: return err; } +static void tegra124_cpufreq_remove(struct platform_device *pdev) +{ + struct tegra124_cpufreq_priv *priv = dev_get_drvdata(&pdev->dev); + + if (!IS_ERR(priv->cpufreq_dt_pdev)) { + platform_device_unregister(priv->cpufreq_dt_pdev); + priv->cpufreq_dt_pdev = ERR_PTR(-ENODEV); + } + + clk_put(priv->pllp_clk); + clk_put(priv->pllx_clk); + clk_put(priv->dfll_clk); + clk_put(priv->cpu_clk); +} + static const struct dev_pm_ops tegra124_cpufreq_pm_ops = { SET_SYSTEM_SLEEP_PM_OPS(tegra124_cpufreq_suspend, tegra124_cpufreq_resume) @@ -182,15 +196,16 @@ static struct platform_driver tegra124_cpufreq_platdrv = { .driver.name = "cpufreq-tegra124", .driver.pm = &tegra124_cpufreq_pm_ops, .probe = tegra124_cpufreq_probe, + .remove = tegra124_cpufreq_remove, }; static int __init tegra_cpufreq_init(void) { int ret; - struct platform_device *pdev; - if (!(of_machine_is_compatible("nvidia,tegra124") || - of_machine_is_compatible("nvidia,tegra210"))) + if (!(of_machine_is_compatible("nvidia,tegra114") || + of_machine_is_compatible("nvidia,tegra124") || + of_machine_is_compatible("nvidia,tegra210"))) return -ENODEV; /* @@ -201,15 +216,25 @@ static int __init tegra_cpufreq_init(void) if (ret) return ret; - pdev = platform_device_register_simple("cpufreq-tegra124", -1, NULL, 0); - if (IS_ERR(pdev)) { + tegra124_cpufreq_pdev = platform_device_register_simple("cpufreq-tegra124", -1, NULL, 0); + if (IS_ERR(tegra124_cpufreq_pdev)) { platform_driver_unregister(&tegra124_cpufreq_platdrv); - return PTR_ERR(pdev); + return PTR_ERR(tegra124_cpufreq_pdev); } return 0; } module_init(tegra_cpufreq_init); +static void __exit tegra_cpufreq_module_exit(void) +{ + if (!IS_ERR_OR_NULL(tegra124_cpufreq_pdev)) + platform_device_unregister(tegra124_cpufreq_pdev); + + platform_driver_unregister(&tegra124_cpufreq_platdrv); +} +module_exit(tegra_cpufreq_module_exit); + MODULE_AUTHOR("Tuomas Tynkkynen <ttynkkynen@nvidia.com>"); MODULE_DESCRIPTION("cpufreq driver for NVIDIA Tegra124"); +MODULE_LICENSE("GPL"); diff --git a/drivers/cpuidle/dt_idle_states.c b/drivers/cpuidle/dt_idle_states.c index 97feb7d8fb23..558d49838990 100644 --- a/drivers/cpuidle/dt_idle_states.c +++ b/drivers/cpuidle/dt_idle_states.c @@ -98,7 +98,6 @@ static bool idle_state_valid(struct device_node *state_node, unsigned int idx, { int cpu; struct device_node *cpu_node, *curr_state_node; - bool valid = true; /* * Compare idle state phandles for index idx on all CPUs in the @@ -107,20 +106,17 @@ static bool idle_state_valid(struct device_node *state_node, unsigned int idx, * retrieved from. If a mismatch is found bail out straight * away since we certainly hit a firmware misconfiguration. */ - for (cpu = cpumask_next(cpumask_first(cpumask), cpumask); - cpu < nr_cpu_ids; cpu = cpumask_next(cpu, cpumask)) { + cpu = cpumask_first(cpumask) + 1; + for_each_cpu_from(cpu, cpumask) { cpu_node = of_cpu_device_node_get(cpu); curr_state_node = of_get_cpu_state_node(cpu_node, idx); - if (state_node != curr_state_node) - valid = false; - of_node_put(curr_state_node); of_node_put(cpu_node); - if (!valid) - break; + if (state_node != curr_state_node) + return false; } - return valid; + return true; } /** diff --git a/drivers/devfreq/Kconfig b/drivers/devfreq/Kconfig index 3c4862a752b5..c999c4a1e567 100644 --- a/drivers/devfreq/Kconfig +++ b/drivers/devfreq/Kconfig @@ -90,6 +90,17 @@ config ARM_EXYNOS_BUS_DEVFREQ and adjusts the operating frequencies and voltages with OPP support. This does not yet operate with optimal voltages. +config ARM_HISI_UNCORE_DEVFREQ + tristate "HiSilicon uncore DEVFREQ Driver" + depends on ACPI && ACPI_PPTT && PCC + select DEVFREQ_GOV_PERFORMANCE + select DEVFREQ_GOV_USERSPACE + help + This adds a DEVFREQ driver that manages uncore frequency scaling for + HiSilicon Kunpeng SoCs. This enables runtime management of uncore + frequency scaling from kernel and userspace. The uncore domain + contains system interconnects and L3 cache. + config ARM_IMX_BUS_DEVFREQ tristate "i.MX Generic Bus DEVFREQ Driver" depends on ARCH_MXC || COMPILE_TEST diff --git a/drivers/devfreq/Makefile b/drivers/devfreq/Makefile index bf40d04928d0..404179d79a9d 100644 --- a/drivers/devfreq/Makefile +++ b/drivers/devfreq/Makefile @@ -9,6 +9,7 @@ obj-$(CONFIG_DEVFREQ_GOV_PASSIVE) += governor_passive.o # DEVFREQ Drivers obj-$(CONFIG_ARM_EXYNOS_BUS_DEVFREQ) += exynos-bus.o +obj-$(CONFIG_ARM_HISI_UNCORE_DEVFREQ) += hisi_uncore_freq.o obj-$(CONFIG_ARM_IMX_BUS_DEVFREQ) += imx-bus.o obj-$(CONFIG_ARM_IMX8M_DDRC_DEVFREQ) += imx8m-ddrc.o obj-$(CONFIG_ARM_MEDIATEK_CCI_DEVFREQ) += mtk-cci-devfreq.o diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index 98657d3b9435..2e8d01d47f69 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -152,11 +152,8 @@ void devfreq_get_freq_range(struct devfreq *devfreq, (unsigned long)HZ_PER_KHZ * qos_max_freq); /* Apply constraints from OPP interface */ - *min_freq = max(*min_freq, devfreq->scaling_min_freq); - *max_freq = min(*max_freq, devfreq->scaling_max_freq); - - if (*min_freq > *max_freq) - *min_freq = *max_freq; + *max_freq = clamp(*max_freq, devfreq->scaling_min_freq, devfreq->scaling_max_freq); + *min_freq = clamp(*min_freq, devfreq->scaling_min_freq, *max_freq); } EXPORT_SYMBOL(devfreq_get_freq_range); @@ -807,7 +804,6 @@ struct devfreq *devfreq_add_device(struct device *dev, { struct devfreq *devfreq; struct devfreq_governor *governor; - unsigned long min_freq, max_freq; int err = 0; if (!dev || !profile || !governor_name) { @@ -835,6 +831,7 @@ struct devfreq *devfreq_add_device(struct device *dev, mutex_lock(&devfreq->lock); devfreq->dev.parent = dev; devfreq->dev.class = devfreq_class; + devfreq->dev.groups = profile->dev_groups; devfreq->dev.release = devfreq_dev_release; INIT_LIST_HEAD(&devfreq->node); devfreq->profile = profile; @@ -875,8 +872,6 @@ struct devfreq *devfreq_add_device(struct device *dev, goto err_dev; } - devfreq_get_freq_range(devfreq, &min_freq, &max_freq); - devfreq->suspend_freq = dev_pm_opp_get_suspend_opp_freq(dev); devfreq->opp_table = dev_pm_opp_get_opp_table(dev); if (IS_ERR(devfreq->opp_table)) @@ -1382,15 +1377,11 @@ int devfreq_remove_governor(struct devfreq_governor *governor) int ret; struct device *dev = devfreq->dev.parent; + if (!devfreq->governor) + continue; + if (!strncmp(devfreq->governor->name, governor->name, DEVFREQ_NAME_LEN)) { - /* we should have a devfreq governor! */ - if (!devfreq->governor) { - dev_warn(dev, "%s: Governor %s NOT present\n", - __func__, governor->name); - continue; - /* Fall through */ - } ret = devfreq->governor->event_handler(devfreq, DEVFREQ_GOV_STOP, NULL); if (ret) { @@ -1743,7 +1734,7 @@ static ssize_t trans_stat_show(struct device *dev, for (i = 0; i < max_state; i++) { if (len >= PAGE_SIZE - 1) break; - if (df->freq_table[2] == df->previous_freq) + if (df->freq_table[i] == df->previous_freq) len += sysfs_emit_at(buf, len, "*"); else len += sysfs_emit_at(buf, len, " "); diff --git a/drivers/devfreq/governor_userspace.c b/drivers/devfreq/governor_userspace.c index d1aa6806b683..175de0c0b50e 100644 --- a/drivers/devfreq/governor_userspace.c +++ b/drivers/devfreq/governor_userspace.c @@ -9,6 +9,7 @@ #include <linux/slab.h> #include <linux/device.h> #include <linux/devfreq.h> +#include <linux/kstrtox.h> #include <linux/pm.h> #include <linux/mutex.h> #include <linux/module.h> @@ -39,10 +40,13 @@ static ssize_t set_freq_store(struct device *dev, struct device_attribute *attr, unsigned long wanted; int err = 0; + err = kstrtoul(buf, 0, &wanted); + if (err) + return err; + mutex_lock(&devfreq->lock); data = devfreq->governor_data; - sscanf(buf, "%lu", &wanted); data->user_frequency = wanted; data->valid = true; err = update_devfreq(devfreq); diff --git a/drivers/devfreq/hisi_uncore_freq.c b/drivers/devfreq/hisi_uncore_freq.c new file mode 100644 index 000000000000..96d1815059e3 --- /dev/null +++ b/drivers/devfreq/hisi_uncore_freq.c @@ -0,0 +1,658 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * HiSilicon uncore frequency scaling driver + * + * Copyright (c) 2025 HiSilicon Co., Ltd + */ + +#include <linux/acpi.h> +#include <linux/bits.h> +#include <linux/cleanup.h> +#include <linux/devfreq.h> +#include <linux/device.h> +#include <linux/dev_printk.h> +#include <linux/errno.h> +#include <linux/iopoll.h> +#include <linux/kernel.h> +#include <linux/ktime.h> +#include <linux/mailbox_client.h> +#include <linux/module.h> +#include <linux/mod_devicetable.h> +#include <linux/mutex.h> +#include <linux/platform_device.h> +#include <linux/pm_opp.h> +#include <linux/property.h> +#include <linux/topology.h> +#include <linux/units.h> +#include <acpi/pcc.h> + +#include "governor.h" + +struct hisi_uncore_pcc_data { + u16 status; + u16 resv; + u32 data; +}; + +struct hisi_uncore_pcc_shmem { + struct acpi_pcct_shared_memory head; + struct hisi_uncore_pcc_data pcc_data; +}; + +enum hisi_uncore_pcc_cmd_type { + HUCF_PCC_CMD_GET_CAP = 0, + HUCF_PCC_CMD_GET_FREQ, + HUCF_PCC_CMD_SET_FREQ, + HUCF_PCC_CMD_GET_MODE, + HUCF_PCC_CMD_SET_MODE, + HUCF_PCC_CMD_GET_PLAT_FREQ_NUM, + HUCF_PCC_CMD_GET_PLAT_FREQ_BY_IDX, + HUCF_PCC_CMD_MAX = 256 +}; + +static int hisi_platform_gov_usage; +static DEFINE_MUTEX(hisi_platform_gov_usage_lock); + +enum hisi_uncore_freq_mode { + HUCF_MODE_PLATFORM = 0, + HUCF_MODE_OS, + HUCF_MODE_MAX +}; + +#define HUCF_CAP_PLATFORM_CTRL BIT(0) + +/** + * struct hisi_uncore_freq - hisi uncore frequency scaling device data + * @dev: device of this frequency scaling driver + * @cl: mailbox client object + * @pchan: PCC mailbox channel + * @chan_id: PCC channel ID + * @last_cmd_cmpl_time: timestamp of the last completed PCC command + * @pcc_lock: PCC channel lock + * @devfreq: devfreq data of this hisi_uncore_freq device + * @related_cpus: CPUs whose performance is majorly affected by this + * uncore frequency domain + * @cap: capability flag + */ +struct hisi_uncore_freq { + struct device *dev; + struct mbox_client cl; + struct pcc_mbox_chan *pchan; + int chan_id; + ktime_t last_cmd_cmpl_time; + struct mutex pcc_lock; + struct devfreq *devfreq; + struct cpumask related_cpus; + u32 cap; +}; + +/* PCC channel timeout = PCC nominal latency * NUM */ +#define HUCF_PCC_POLL_TIMEOUT_NUM 1000 +#define HUCF_PCC_POLL_INTERVAL_US 5 + +/* Default polling interval in ms for devfreq governors*/ +#define HUCF_DEFAULT_POLLING_MS 100 + +static void hisi_uncore_free_pcc_chan(struct hisi_uncore_freq *uncore) +{ + guard(mutex)(&uncore->pcc_lock); + pcc_mbox_free_channel(uncore->pchan); + uncore->pchan = NULL; +} + +static void devm_hisi_uncore_free_pcc_chan(void *data) +{ + hisi_uncore_free_pcc_chan(data); +} + +static int hisi_uncore_request_pcc_chan(struct hisi_uncore_freq *uncore) +{ + struct device *dev = uncore->dev; + struct pcc_mbox_chan *pcc_chan; + + uncore->cl = (struct mbox_client) { + .dev = dev, + .tx_block = false, + .knows_txdone = true, + }; + + pcc_chan = pcc_mbox_request_channel(&uncore->cl, uncore->chan_id); + if (IS_ERR(pcc_chan)) + return dev_err_probe(dev, PTR_ERR(pcc_chan), + "Failed to request PCC channel %u\n", uncore->chan_id); + + if (!pcc_chan->shmem_base_addr) { + pcc_mbox_free_channel(pcc_chan); + return dev_err_probe(dev, -EINVAL, + "Invalid PCC shared memory address\n"); + } + + if (pcc_chan->shmem_size < sizeof(struct hisi_uncore_pcc_shmem)) { + pcc_mbox_free_channel(pcc_chan); + return dev_err_probe(dev, -EINVAL, + "Invalid PCC shared memory size (%lluB)\n", + pcc_chan->shmem_size); + } + + uncore->pchan = pcc_chan; + + return devm_add_action_or_reset(uncore->dev, + devm_hisi_uncore_free_pcc_chan, uncore); +} + +static acpi_status hisi_uncore_pcc_reg_scan(struct acpi_resource *res, + void *ctx) +{ + struct acpi_resource_generic_register *reg; + struct hisi_uncore_freq *uncore; + + if (!res || res->type != ACPI_RESOURCE_TYPE_GENERIC_REGISTER) + return AE_OK; + + reg = &res->data.generic_reg; + if (reg->space_id != ACPI_ADR_SPACE_PLATFORM_COMM) + return AE_OK; + + if (!ctx) + return AE_ERROR; + + uncore = ctx; + /* PCC subspace ID stored in Access Size */ + uncore->chan_id = reg->access_size; + + return AE_CTRL_TERMINATE; +} + +static int hisi_uncore_init_pcc_chan(struct hisi_uncore_freq *uncore) +{ + acpi_handle handle = ACPI_HANDLE(uncore->dev); + acpi_status status; + int rc; + + uncore->chan_id = -1; + status = acpi_walk_resources(handle, METHOD_NAME__CRS, + hisi_uncore_pcc_reg_scan, uncore); + if (ACPI_FAILURE(status) || uncore->chan_id < 0) + return dev_err_probe(uncore->dev, -ENODEV, + "Failed to get a PCC channel\n"); + + + rc = devm_mutex_init(uncore->dev, &uncore->pcc_lock); + if (rc) + return rc; + + return hisi_uncore_request_pcc_chan(uncore); +} + +static int hisi_uncore_cmd_send(struct hisi_uncore_freq *uncore, + u8 cmd, u32 *data) +{ + struct hisi_uncore_pcc_shmem __iomem *addr; + struct hisi_uncore_pcc_shmem shmem; + struct pcc_mbox_chan *pchan; + unsigned int mrtt; + s64 time_delta; + u16 status; + int rc; + + guard(mutex)(&uncore->pcc_lock); + + pchan = uncore->pchan; + if (!pchan) + return -ENODEV; + + addr = (struct hisi_uncore_pcc_shmem __iomem *)pchan->shmem; + if (!addr) + return -EINVAL; + + /* Handle the Minimum Request Turnaround Time (MRTT) */ + mrtt = pchan->min_turnaround_time; + time_delta = ktime_us_delta(ktime_get(), uncore->last_cmd_cmpl_time); + if (mrtt > time_delta) + udelay(mrtt - time_delta); + + /* Copy data */ + shmem.head = (struct acpi_pcct_shared_memory) { + .signature = PCC_SIGNATURE | uncore->chan_id, + .command = cmd, + }; + shmem.pcc_data.data = *data; + memcpy_toio(addr, &shmem, sizeof(shmem)); + + /* Ring doorbell */ + rc = mbox_send_message(pchan->mchan, &cmd); + if (rc < 0) { + dev_err(uncore->dev, "Failed to send mbox message, %d\n", rc); + return rc; + } + + /* Wait status */ + rc = readw_poll_timeout(&addr->head.status, status, + status & (PCC_STATUS_CMD_COMPLETE | + PCC_STATUS_ERROR), + HUCF_PCC_POLL_INTERVAL_US, + pchan->latency * HUCF_PCC_POLL_TIMEOUT_NUM); + if (rc) { + dev_err(uncore->dev, "PCC channel response timeout, cmd=%u\n", cmd); + } else if (status & PCC_STATUS_ERROR) { + dev_err(uncore->dev, "PCC cmd error, cmd=%u\n", cmd); + rc = -EIO; + } + + uncore->last_cmd_cmpl_time = ktime_get(); + + /* Copy data back */ + memcpy_fromio(data, &addr->pcc_data.data, sizeof(*data)); + + /* Clear mailbox active req */ + mbox_client_txdone(pchan->mchan, rc); + + return rc; +} + +static int hisi_uncore_target(struct device *dev, unsigned long *freq, + u32 flags) +{ + struct hisi_uncore_freq *uncore = dev_get_drvdata(dev); + struct dev_pm_opp *opp; + u32 data; + + if (WARN_ON(!uncore || !uncore->pchan)) + return -ENODEV; + + opp = devfreq_recommended_opp(dev, freq, flags); + if (IS_ERR(opp)) { + dev_err(dev, "Failed to get opp for freq %lu hz\n", *freq); + return PTR_ERR(opp); + } + dev_pm_opp_put(opp); + + data = (u32)(dev_pm_opp_get_freq(opp) / HZ_PER_MHZ); + + return hisi_uncore_cmd_send(uncore, HUCF_PCC_CMD_SET_FREQ, &data); +} + +static int hisi_uncore_get_dev_status(struct device *dev, + struct devfreq_dev_status *stat) +{ + /* Not used */ + return 0; +} + +static int hisi_uncore_get_cur_freq(struct device *dev, unsigned long *freq) +{ + struct hisi_uncore_freq *uncore = dev_get_drvdata(dev); + u32 data = 0; + int rc; + + if (WARN_ON(!uncore || !uncore->pchan)) + return -ENODEV; + + rc = hisi_uncore_cmd_send(uncore, HUCF_PCC_CMD_GET_FREQ, &data); + + /* + * Upon a failure, 'data' remains 0 and 'freq' is set to 0 rather than a + * random value. devfreq shouldn't use 'freq' in that case though. + */ + *freq = data * HZ_PER_MHZ; + + return rc; +} + +static void devm_hisi_uncore_remove_opp(void *data) +{ + struct hisi_uncore_freq *uncore = data; + + dev_pm_opp_remove_all_dynamic(uncore->dev); +} + +static int hisi_uncore_init_opp(struct hisi_uncore_freq *uncore) +{ + struct device *dev = uncore->dev; + unsigned long freq_mhz; + u32 num, index; + u32 data = 0; + int rc; + + rc = hisi_uncore_cmd_send(uncore, HUCF_PCC_CMD_GET_PLAT_FREQ_NUM, + &data); + if (rc) + return dev_err_probe(dev, rc, "Failed to get plat freq num\n"); + + num = data; + + for (index = 0; index < num; index++) { + data = index; + rc = hisi_uncore_cmd_send(uncore, + HUCF_PCC_CMD_GET_PLAT_FREQ_BY_IDX, + &data); + if (rc) { + dev_pm_opp_remove_all_dynamic(dev); + return dev_err_probe(dev, rc, + "Failed to get plat freq at index %u\n", index); + } + freq_mhz = data; + + /* Don't care OPP voltage, take 1V as default */ + rc = dev_pm_opp_add(dev, freq_mhz * HZ_PER_MHZ, 1000000); + if (rc) { + dev_pm_opp_remove_all_dynamic(dev); + return dev_err_probe(dev, rc, + "Add OPP %lu failed\n", freq_mhz); + } + } + + return devm_add_action_or_reset(dev, devm_hisi_uncore_remove_opp, + uncore); +} + +static int hisi_platform_gov_func(struct devfreq *df, unsigned long *freq) +{ + /* + * Platform-controlled mode doesn't care the frequency issued from + * devfreq, so just pick the max freq. + */ + *freq = DEVFREQ_MAX_FREQ; + + return 0; +} + +static int hisi_platform_gov_handler(struct devfreq *df, unsigned int event, + void *val) +{ + struct hisi_uncore_freq *uncore = dev_get_drvdata(df->dev.parent); + int rc = 0; + u32 data; + + if (WARN_ON(!uncore || !uncore->pchan)) + return -ENODEV; + + switch (event) { + case DEVFREQ_GOV_START: + data = HUCF_MODE_PLATFORM; + rc = hisi_uncore_cmd_send(uncore, HUCF_PCC_CMD_SET_MODE, &data); + if (rc) + dev_err(uncore->dev, "Failed to set platform mode (%d)\n", rc); + break; + case DEVFREQ_GOV_STOP: + data = HUCF_MODE_OS; + rc = hisi_uncore_cmd_send(uncore, HUCF_PCC_CMD_SET_MODE, &data); + if (rc) + dev_err(uncore->dev, "Failed to set os mode (%d)\n", rc); + break; + default: + break; + } + + return rc; +} + +/* + * In the platform-controlled mode, the platform decides the uncore frequency + * and ignores the frequency issued from the driver. + * Thus, create a pseudo 'hisi_platform' governor that stops devfreq monitor + * from working so as to save meaningless overhead. + */ +static struct devfreq_governor hisi_platform_governor = { + .name = "hisi_platform", + /* + * Set interrupt_driven to skip the devfreq monitor mechanism, though + * this governor is not interrupt-driven. + */ + .flags = DEVFREQ_GOV_FLAG_IRQ_DRIVEN, + .get_target_freq = hisi_platform_gov_func, + .event_handler = hisi_platform_gov_handler, +}; + +static void hisi_uncore_remove_platform_gov(struct hisi_uncore_freq *uncore) +{ + u32 data = HUCF_MODE_PLATFORM; + int rc; + + if (!(uncore->cap & HUCF_CAP_PLATFORM_CTRL)) + return; + + guard(mutex)(&hisi_platform_gov_usage_lock); + + if (--hisi_platform_gov_usage == 0) { + rc = devfreq_remove_governor(&hisi_platform_governor); + if (rc) + dev_err(uncore->dev, "Failed to remove hisi_platform gov (%d)\n", rc); + } + + /* + * Set to the platform-controlled mode on exit if supported, so as to + * have a certain behaviour when the driver is detached. + */ + rc = hisi_uncore_cmd_send(uncore, HUCF_PCC_CMD_SET_MODE, &data); + if (rc) + dev_err(uncore->dev, "Failed to set platform mode on exit (%d)\n", rc); +} + +static void devm_hisi_uncore_remove_platform_gov(void *data) +{ + hisi_uncore_remove_platform_gov(data); +} + +static int hisi_uncore_add_platform_gov(struct hisi_uncore_freq *uncore) +{ + if (!(uncore->cap & HUCF_CAP_PLATFORM_CTRL)) + return 0; + + guard(mutex)(&hisi_platform_gov_usage_lock); + + if (hisi_platform_gov_usage == 0) { + int rc = devfreq_add_governor(&hisi_platform_governor); + if (rc) + return rc; + } + hisi_platform_gov_usage++; + + return devm_add_action_or_reset(uncore->dev, + devm_hisi_uncore_remove_platform_gov, + uncore); +} + +/* + * Returns: + * 0 if success, uncore->related_cpus is set. + * -EINVAL if property not found, or property found but without elements in it, + * or invalid arguments received in any of the subroutine. + * Other error codes if it goes wrong. + */ +static int hisi_uncore_mark_related_cpus(struct hisi_uncore_freq *uncore, + char *property, int (*get_topo_id)(int cpu), + const struct cpumask *(*get_cpumask)(int cpu)) +{ + unsigned int i, cpu; + size_t len; + int rc; + + rc = device_property_count_u32(uncore->dev, property); + if (rc < 0) + return rc; + if (rc == 0) + return -EINVAL; + + len = rc; + u32 *num __free(kfree) = kcalloc(len, sizeof(*num), GFP_KERNEL); + if (!num) + return -ENOMEM; + + rc = device_property_read_u32_array(uncore->dev, property, num, len); + if (rc) + return rc; + + for (i = 0; i < len; i++) { + for_each_possible_cpu(cpu) { + if (get_topo_id(cpu) != num[i]) + continue; + + cpumask_or(&uncore->related_cpus, + &uncore->related_cpus, get_cpumask(cpu)); + break; + } + } + + return 0; +} + +static int get_package_id(int cpu) +{ + return topology_physical_package_id(cpu); +} + +static const struct cpumask *get_package_cpumask(int cpu) +{ + return topology_core_cpumask(cpu); +} + +static int get_cluster_id(int cpu) +{ + return topology_cluster_id(cpu); +} + +static const struct cpumask *get_cluster_cpumask(int cpu) +{ + return topology_cluster_cpumask(cpu); +} + +static int hisi_uncore_mark_related_cpus_wrap(struct hisi_uncore_freq *uncore) +{ + int rc; + + cpumask_clear(&uncore->related_cpus); + + rc = hisi_uncore_mark_related_cpus(uncore, "related-package", + get_package_id, + get_package_cpumask); + /* Success, or firmware probably broken */ + if (!rc || rc != -EINVAL) + return rc; + + /* Try another property name if rc == -EINVAL */ + return hisi_uncore_mark_related_cpus(uncore, "related-cluster", + get_cluster_id, + get_cluster_cpumask); +} + +static ssize_t related_cpus_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct hisi_uncore_freq *uncore = dev_get_drvdata(dev->parent); + + return cpumap_print_to_pagebuf(true, buf, &uncore->related_cpus); +} + +static DEVICE_ATTR_RO(related_cpus); + +static struct attribute *hisi_uncore_freq_attrs[] = { + &dev_attr_related_cpus.attr, + NULL +}; +ATTRIBUTE_GROUPS(hisi_uncore_freq); + +static int hisi_uncore_devfreq_register(struct hisi_uncore_freq *uncore) +{ + struct devfreq_dev_profile *profile; + struct device *dev = uncore->dev; + unsigned long freq; + u32 data; + int rc; + + rc = hisi_uncore_get_cur_freq(dev, &freq); + if (rc) + return dev_err_probe(dev, rc, "Failed to get plat init freq\n"); + + profile = devm_kzalloc(dev, sizeof(*profile), GFP_KERNEL); + if (!profile) + return -ENOMEM; + + *profile = (struct devfreq_dev_profile) { + .initial_freq = freq, + .polling_ms = HUCF_DEFAULT_POLLING_MS, + .timer = DEVFREQ_TIMER_DELAYED, + .target = hisi_uncore_target, + .get_dev_status = hisi_uncore_get_dev_status, + .get_cur_freq = hisi_uncore_get_cur_freq, + .dev_groups = hisi_uncore_freq_groups, + }; + + rc = hisi_uncore_cmd_send(uncore, HUCF_PCC_CMD_GET_MODE, &data); + if (rc) + return dev_err_probe(dev, rc, "Failed to get operate mode\n"); + + if (data == HUCF_MODE_PLATFORM) + uncore->devfreq = devm_devfreq_add_device(dev, profile, + hisi_platform_governor.name, NULL); + else + uncore->devfreq = devm_devfreq_add_device(dev, profile, + DEVFREQ_GOV_PERFORMANCE, NULL); + if (IS_ERR(uncore->devfreq)) + return dev_err_probe(dev, PTR_ERR(uncore->devfreq), + "Failed to add devfreq device\n"); + + return 0; +} + +static int hisi_uncore_freq_probe(struct platform_device *pdev) +{ + struct hisi_uncore_freq *uncore; + struct device *dev = &pdev->dev; + u32 cap; + int rc; + + uncore = devm_kzalloc(dev, sizeof(*uncore), GFP_KERNEL); + if (!uncore) + return -ENOMEM; + + uncore->dev = dev; + platform_set_drvdata(pdev, uncore); + + rc = hisi_uncore_init_pcc_chan(uncore); + if (rc) + return dev_err_probe(dev, rc, "Failed to init PCC channel\n"); + + rc = hisi_uncore_init_opp(uncore); + if (rc) + return dev_err_probe(dev, rc, "Failed to init OPP\n"); + + rc = hisi_uncore_cmd_send(uncore, HUCF_PCC_CMD_GET_CAP, &cap); + if (rc) + return dev_err_probe(dev, rc, "Failed to get capability\n"); + + uncore->cap = cap; + + rc = hisi_uncore_add_platform_gov(uncore); + if (rc) + return dev_err_probe(dev, rc, "Failed to add hisi_platform governor\n"); + + rc = hisi_uncore_mark_related_cpus_wrap(uncore); + if (rc) + return dev_err_probe(dev, rc, "Failed to mark related cpus\n"); + + rc = hisi_uncore_devfreq_register(uncore); + if (rc) + return dev_err_probe(dev, rc, "Failed to register devfreq\n"); + + return 0; +} + +static const struct acpi_device_id hisi_uncore_freq_acpi_match[] = { + { "HISI04F1", }, + { } +}; +MODULE_DEVICE_TABLE(acpi, hisi_uncore_freq_acpi_match); + +static struct platform_driver hisi_uncore_freq_drv = { + .probe = hisi_uncore_freq_probe, + .driver = { + .name = "hisi_uncore_freq", + .acpi_match_table = hisi_uncore_freq_acpi_match, + }, +}; +module_platform_driver(hisi_uncore_freq_drv); + +MODULE_DESCRIPTION("HiSilicon uncore frequency scaling driver"); +MODULE_AUTHOR("Jie Zhan <zhanjie9@hisilicon.com>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/devfreq/sun8i-a33-mbus.c b/drivers/devfreq/sun8i-a33-mbus.c index 7c6ae91ede1f..4bd5657558d6 100644 --- a/drivers/devfreq/sun8i-a33-mbus.c +++ b/drivers/devfreq/sun8i-a33-mbus.c @@ -360,7 +360,7 @@ static int sun8i_a33_mbus_probe(struct platform_device *pdev) if (IS_ERR(priv->reg_mbus)) return PTR_ERR(priv->reg_mbus); - priv->clk_bus = devm_clk_get(dev, "bus"); + priv->clk_bus = devm_clk_get_enabled(dev, "bus"); if (IS_ERR(priv->clk_bus)) return dev_err_probe(dev, PTR_ERR(priv->clk_bus), "failed to get bus clock\n"); @@ -375,24 +375,15 @@ static int sun8i_a33_mbus_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(priv->clk_mbus), "failed to get mbus clock\n"); - ret = clk_prepare_enable(priv->clk_bus); - if (ret) - return dev_err_probe(dev, ret, - "failed to enable bus clock\n"); - /* Lock the DRAM clock rate to keep priv->nominal_bw in sync. */ - ret = clk_rate_exclusive_get(priv->clk_dram); - if (ret) { - err = "failed to lock dram clock rate\n"; - goto err_disable_bus; - } + ret = devm_clk_rate_exclusive_get(dev, priv->clk_dram); + if (ret) + return dev_err_probe(dev, ret, "failed to lock dram clock rate\n"); /* Lock the MBUS clock rate to keep MBUS_TMR_PERIOD in sync. */ - ret = clk_rate_exclusive_get(priv->clk_mbus); - if (ret) { - err = "failed to lock mbus clock rate\n"; - goto err_unlock_dram; - } + ret = devm_clk_rate_exclusive_get(dev, priv->clk_mbus); + if (ret) + return dev_err_probe(dev, ret, "failed to lock mbus clock rate\n"); priv->gov_data.upthreshold = 10; priv->gov_data.downdifferential = 5; @@ -405,10 +396,8 @@ static int sun8i_a33_mbus_probe(struct platform_device *pdev) priv->profile.max_state = max_state; ret = devm_pm_opp_set_clkname(dev, "dram"); - if (ret) { - err = "failed to add OPP table\n"; - goto err_unlock_mbus; - } + if (ret) + return dev_err_probe(dev, ret, "failed to add OPP table\n"); base_freq = clk_get_rate(clk_get_parent(priv->clk_dram)); for (i = 0; i < max_state; ++i) { @@ -448,12 +437,6 @@ static int sun8i_a33_mbus_probe(struct platform_device *pdev) err_remove_opps: dev_pm_opp_remove_all_dynamic(dev); -err_unlock_mbus: - clk_rate_exclusive_put(priv->clk_mbus); -err_unlock_dram: - clk_rate_exclusive_put(priv->clk_dram); -err_disable_bus: - clk_disable_unprepare(priv->clk_bus); return dev_err_probe(dev, ret, err); } @@ -472,9 +455,6 @@ static void sun8i_a33_mbus_remove(struct platform_device *pdev) dev_warn(dev, "failed to restore DRAM frequency: %d\n", ret); dev_pm_opp_remove_all_dynamic(dev); - clk_rate_exclusive_put(priv->clk_mbus); - clk_rate_exclusive_put(priv->clk_dram); - clk_disable_unprepare(priv->clk_bus); } static const struct sun8i_a33_mbus_variant sun50i_a64_mbus = { diff --git a/drivers/gpu/drm/display/drm_dp_aux_bus.c b/drivers/gpu/drm/display/drm_dp_aux_bus.c index ec7eac6b595f..718c9122bc3a 100644 --- a/drivers/gpu/drm/display/drm_dp_aux_bus.c +++ b/drivers/gpu/drm/display/drm_dp_aux_bus.c @@ -57,7 +57,7 @@ static int dp_aux_ep_probe(struct device *dev) container_of(aux_ep, struct dp_aux_ep_device_with_data, aux_ep); int ret; - ret = dev_pm_domain_attach(dev, true); + ret = dev_pm_domain_attach(dev, PD_FLAG_ATTACH_POWER_ON); if (ret) return dev_err_probe(dev, ret, "Failed to attach to PM Domain\n"); diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 2ad2b1838f0f..38eabf1173da 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -573,7 +573,7 @@ static int i2c_device_probe(struct device *dev) goto err_clear_wakeup_irq; do_power_on = !i2c_acpi_waive_d0_probe(dev); - status = dev_pm_domain_attach(&client->dev, do_power_on); + status = dev_pm_domain_attach(&client->dev, do_power_on ? PD_FLAG_ATTACH_POWER_ON : 0); if (status) goto err_clear_wakeup_irq; diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c index b66b637e2d57..656601754966 100644 --- a/drivers/mmc/core/sdio_bus.c +++ b/drivers/mmc/core/sdio_bus.c @@ -161,7 +161,7 @@ static int sdio_bus_probe(struct device *dev) if (!id) return -ENODEV; - ret = dev_pm_domain_attach(dev, false); + ret = dev_pm_domain_attach(dev, 0); if (ret) return ret; diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 67db34fd10ee..b853585cb1f8 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -708,6 +708,8 @@ static int pci_pm_prepare(struct device *dev) struct pci_dev *pci_dev = to_pci_dev(dev); const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; + dev_pm_set_strict_midlayer(dev, true); + if (pm && pm->prepare) { int error = pm->prepare(dev); if (error < 0) @@ -749,6 +751,8 @@ static void pci_pm_complete(struct device *dev) if (pci_dev->current_state < pre_sleep_state) pm_request_resume(dev); } + + dev_pm_set_strict_midlayer(dev, false); } #else /* !CONFIG_PM_SLEEP */ diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c index 6b6f51b21550..99390ec1481f 100644 --- a/drivers/powercap/dtpm_cpu.c +++ b/drivers/powercap/dtpm_cpu.c @@ -96,6 +96,8 @@ static u64 get_pd_power_uw(struct dtpm *dtpm) int i; pd = em_cpu_get(dtpm_cpu->cpu); + if (!pd) + return 0; pd_mask = em_span_cpus(pd); diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c index faa0b6bc5b53..c7e7f9bf5313 100644 --- a/drivers/powercap/intel_rapl_common.c +++ b/drivers/powercap/intel_rapl_common.c @@ -1277,6 +1277,7 @@ static const struct x86_cpu_id rapl_ids[] __initconst = { X86_MATCH_VFM(INTEL_RAPTORLAKE, &rapl_defaults_core), X86_MATCH_VFM(INTEL_RAPTORLAKE_P, &rapl_defaults_core), X86_MATCH_VFM(INTEL_RAPTORLAKE_S, &rapl_defaults_core), + X86_MATCH_VFM(INTEL_BARTLETTLAKE, &rapl_defaults_core), X86_MATCH_VFM(INTEL_METEORLAKE, &rapl_defaults_core), X86_MATCH_VFM(INTEL_METEORLAKE_L, &rapl_defaults_core), X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X, &rapl_defaults_spr_server), diff --git a/drivers/powercap/intel_rapl_msr.c b/drivers/powercap/intel_rapl_msr.c index 8ad2115d65f6..4ed06c71a3ac 100644 --- a/drivers/powercap/intel_rapl_msr.c +++ b/drivers/powercap/intel_rapl_msr.c @@ -150,6 +150,7 @@ static const struct x86_cpu_id pl4_support_ids[] = { X86_MATCH_VFM(INTEL_METEORLAKE_L, NULL), X86_MATCH_VFM(INTEL_ARROWLAKE_U, NULL), X86_MATCH_VFM(INTEL_ARROWLAKE_H, NULL), + X86_MATCH_VFM(INTEL_PANTHERLAKE_L, NULL), {} }; diff --git a/drivers/rpmsg/rpmsg_core.c b/drivers/rpmsg/rpmsg_core.c index 6ee36adcbdba..bece5e635ee9 100644 --- a/drivers/rpmsg/rpmsg_core.c +++ b/drivers/rpmsg/rpmsg_core.c @@ -479,7 +479,7 @@ static int rpmsg_dev_probe(struct device *dev) struct rpmsg_endpoint *ept = NULL; int err; - err = dev_pm_domain_attach(dev, true); + err = dev_pm_domain_attach(dev, PD_FLAG_ATTACH_POWER_ON); if (err) goto out; diff --git a/drivers/soundwire/bus_type.c b/drivers/soundwire/bus_type.c index 75d6f16efced..bc1e653080d9 100644 --- a/drivers/soundwire/bus_type.c +++ b/drivers/soundwire/bus_type.c @@ -101,7 +101,7 @@ static int sdw_drv_probe(struct device *dev) /* * attach to power domain but don't turn on (last arg) */ - ret = dev_pm_domain_attach(dev, false); + ret = dev_pm_domain_attach(dev, 0); if (ret) return ret; diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 0ffa3f9f2870..79d2f5d625d6 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -427,7 +427,7 @@ static int spi_probe(struct device *dev) if (spi->irq < 0) spi->irq = 0; - ret = dev_pm_domain_attach(dev, true); + ret = dev_pm_domain_attach(dev, PD_FLAG_ATTACH_POWER_ON); if (ret) return ret; diff --git a/drivers/tty/serdev/core.c b/drivers/tty/serdev/core.c index 0213381fa358..d16c207a1a9b 100644 --- a/drivers/tty/serdev/core.c +++ b/drivers/tty/serdev/core.c @@ -399,7 +399,7 @@ static int serdev_drv_probe(struct device *dev) const struct serdev_device_driver *sdrv = to_serdev_device_driver(dev->driver); int ret; - ret = dev_pm_domain_attach(dev, true); + ret = dev_pm_domain_attach(dev, PD_FLAG_ATTACH_POWER_ON); if (ret) return ret; |