diff options
Diffstat (limited to 'drivers')
45 files changed, 764 insertions, 634 deletions
diff --git a/drivers/acpi/acpi_tad.c b/drivers/acpi/acpi_tad.c index c9487c5bb7b3..6d870d97ada6 100644 --- a/drivers/acpi/acpi_tad.c +++ b/drivers/acpi/acpi_tad.c @@ -90,8 +90,8 @@ static int acpi_tad_set_real_time(struct device *dev, struct acpi_tad_rt *rt) args[0].buffer.pointer = (u8 *)rt; args[0].buffer.length = sizeof(*rt); - ACQUIRE(pm_runtime_active_try, pm)(dev); - if (ACQUIRE_ERR(pm_runtime_active_try, &pm)) + PM_RUNTIME_ACQUIRE(dev, pm); + if (PM_RUNTIME_ACQUIRE_ERR(&pm)) return -ENXIO; status = acpi_evaluate_integer(handle, "_SRT", &arg_list, &retval); @@ -137,8 +137,8 @@ static int acpi_tad_get_real_time(struct device *dev, struct acpi_tad_rt *rt) { int ret; - ACQUIRE(pm_runtime_active_try, pm)(dev); - if (ACQUIRE_ERR(pm_runtime_active_try, &pm)) + PM_RUNTIME_ACQUIRE(dev, pm); + if (PM_RUNTIME_ACQUIRE_ERR(&pm)) return -ENXIO; ret = acpi_tad_evaluate_grt(dev, rt); @@ -275,8 +275,8 @@ static int acpi_tad_wake_set(struct device *dev, char *method, u32 timer_id, args[0].integer.value = timer_id; args[1].integer.value = value; - ACQUIRE(pm_runtime_active_try, pm)(dev); - if (ACQUIRE_ERR(pm_runtime_active_try, &pm)) + PM_RUNTIME_ACQUIRE(dev, pm); + if (PM_RUNTIME_ACQUIRE_ERR(&pm)) return -ENXIO; status = acpi_evaluate_integer(handle, method, &arg_list, &retval); @@ -322,8 +322,8 @@ static ssize_t acpi_tad_wake_read(struct device *dev, char *buf, char *method, args[0].integer.value = timer_id; - ACQUIRE(pm_runtime_active_try, pm)(dev); - if (ACQUIRE_ERR(pm_runtime_active_try, &pm)) + PM_RUNTIME_ACQUIRE(dev, pm); + if (PM_RUNTIME_ACQUIRE_ERR(&pm)) return -ENXIO; status = acpi_evaluate_integer(handle, method, &arg_list, &retval); @@ -377,8 +377,8 @@ static int acpi_tad_clear_status(struct device *dev, u32 timer_id) args[0].integer.value = timer_id; - ACQUIRE(pm_runtime_active_try, pm)(dev); - if (ACQUIRE_ERR(pm_runtime_active_try, &pm)) + PM_RUNTIME_ACQUIRE(dev, pm); + if (PM_RUNTIME_ACQUIRE_ERR(&pm)) return -ENXIO; status = acpi_evaluate_integer(handle, "_CWS", &arg_list, &retval); @@ -417,8 +417,8 @@ static ssize_t acpi_tad_status_read(struct device *dev, char *buf, u32 timer_id) args[0].integer.value = timer_id; - ACQUIRE(pm_runtime_active_try, pm)(dev); - if (ACQUIRE_ERR(pm_runtime_active_try, &pm)) + PM_RUNTIME_ACQUIRE(dev, pm); + if (PM_RUNTIME_ACQUIRE_ERR(&pm)) return -ENXIO; status = acpi_evaluate_integer(handle, "_GWS", &arg_list, &retval); diff --git a/drivers/base/power/generic_ops.c b/drivers/base/power/generic_ops.c index 6502720bb564..af99bbcf281c 100644 --- a/drivers/base/power/generic_ops.c +++ b/drivers/base/power/generic_ops.c @@ -8,6 +8,13 @@ #include <linux/pm_runtime.h> #include <linux/export.h> +#define CALL_PM_OP(dev, op) \ +({ \ + struct device *_dev = (dev); \ + const struct dev_pm_ops *pm = _dev->driver ? _dev->driver->pm : NULL; \ + pm && pm->op ? pm->op(_dev) : 0; \ +}) + #ifdef CONFIG_PM /** * pm_generic_runtime_suspend - Generic runtime suspend callback for subsystems. @@ -19,12 +26,7 @@ */ int pm_generic_runtime_suspend(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - int ret; - - ret = pm && pm->runtime_suspend ? pm->runtime_suspend(dev) : 0; - - return ret; + return CALL_PM_OP(dev, runtime_suspend); } EXPORT_SYMBOL_GPL(pm_generic_runtime_suspend); @@ -38,12 +40,7 @@ EXPORT_SYMBOL_GPL(pm_generic_runtime_suspend); */ int pm_generic_runtime_resume(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - int ret; - - ret = pm && pm->runtime_resume ? pm->runtime_resume(dev) : 0; - - return ret; + return CALL_PM_OP(dev, runtime_resume); } EXPORT_SYMBOL_GPL(pm_generic_runtime_resume); #endif /* CONFIG_PM */ @@ -72,9 +69,7 @@ int pm_generic_prepare(struct device *dev) */ int pm_generic_suspend_noirq(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->suspend_noirq ? pm->suspend_noirq(dev) : 0; + return CALL_PM_OP(dev, suspend_noirq); } EXPORT_SYMBOL_GPL(pm_generic_suspend_noirq); @@ -84,9 +79,7 @@ EXPORT_SYMBOL_GPL(pm_generic_suspend_noirq); */ int pm_generic_suspend_late(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->suspend_late ? pm->suspend_late(dev) : 0; + return CALL_PM_OP(dev, suspend_late); } EXPORT_SYMBOL_GPL(pm_generic_suspend_late); @@ -96,9 +89,7 @@ EXPORT_SYMBOL_GPL(pm_generic_suspend_late); */ int pm_generic_suspend(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->suspend ? pm->suspend(dev) : 0; + return CALL_PM_OP(dev, suspend); } EXPORT_SYMBOL_GPL(pm_generic_suspend); @@ -108,9 +99,7 @@ EXPORT_SYMBOL_GPL(pm_generic_suspend); */ int pm_generic_freeze_noirq(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->freeze_noirq ? pm->freeze_noirq(dev) : 0; + return CALL_PM_OP(dev, freeze_noirq); } EXPORT_SYMBOL_GPL(pm_generic_freeze_noirq); @@ -120,9 +109,7 @@ EXPORT_SYMBOL_GPL(pm_generic_freeze_noirq); */ int pm_generic_freeze(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->freeze ? pm->freeze(dev) : 0; + return CALL_PM_OP(dev, freeze); } EXPORT_SYMBOL_GPL(pm_generic_freeze); @@ -132,9 +119,7 @@ EXPORT_SYMBOL_GPL(pm_generic_freeze); */ int pm_generic_poweroff_noirq(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->poweroff_noirq ? pm->poweroff_noirq(dev) : 0; + return CALL_PM_OP(dev, poweroff_noirq); } EXPORT_SYMBOL_GPL(pm_generic_poweroff_noirq); @@ -144,9 +129,7 @@ EXPORT_SYMBOL_GPL(pm_generic_poweroff_noirq); */ int pm_generic_poweroff_late(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->poweroff_late ? pm->poweroff_late(dev) : 0; + return CALL_PM_OP(dev, poweroff_late); } EXPORT_SYMBOL_GPL(pm_generic_poweroff_late); @@ -156,9 +139,7 @@ EXPORT_SYMBOL_GPL(pm_generic_poweroff_late); */ int pm_generic_poweroff(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->poweroff ? pm->poweroff(dev) : 0; + return CALL_PM_OP(dev, poweroff); } EXPORT_SYMBOL_GPL(pm_generic_poweroff); @@ -168,9 +149,7 @@ EXPORT_SYMBOL_GPL(pm_generic_poweroff); */ int pm_generic_thaw_noirq(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->thaw_noirq ? pm->thaw_noirq(dev) : 0; + return CALL_PM_OP(dev, thaw_noirq); } EXPORT_SYMBOL_GPL(pm_generic_thaw_noirq); @@ -180,9 +159,7 @@ EXPORT_SYMBOL_GPL(pm_generic_thaw_noirq); */ int pm_generic_thaw(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->thaw ? pm->thaw(dev) : 0; + return CALL_PM_OP(dev, thaw); } EXPORT_SYMBOL_GPL(pm_generic_thaw); @@ -192,9 +169,7 @@ EXPORT_SYMBOL_GPL(pm_generic_thaw); */ int pm_generic_resume_noirq(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->resume_noirq ? pm->resume_noirq(dev) : 0; + return CALL_PM_OP(dev, resume_noirq); } EXPORT_SYMBOL_GPL(pm_generic_resume_noirq); @@ -204,9 +179,7 @@ EXPORT_SYMBOL_GPL(pm_generic_resume_noirq); */ int pm_generic_resume_early(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->resume_early ? pm->resume_early(dev) : 0; + return CALL_PM_OP(dev, resume_early); } EXPORT_SYMBOL_GPL(pm_generic_resume_early); @@ -216,9 +189,7 @@ EXPORT_SYMBOL_GPL(pm_generic_resume_early); */ int pm_generic_resume(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->resume ? pm->resume(dev) : 0; + return CALL_PM_OP(dev, resume); } EXPORT_SYMBOL_GPL(pm_generic_resume); @@ -228,9 +199,7 @@ EXPORT_SYMBOL_GPL(pm_generic_resume); */ int pm_generic_restore_noirq(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->restore_noirq ? pm->restore_noirq(dev) : 0; + return CALL_PM_OP(dev, restore_noirq); } EXPORT_SYMBOL_GPL(pm_generic_restore_noirq); @@ -240,9 +209,7 @@ EXPORT_SYMBOL_GPL(pm_generic_restore_noirq); */ int pm_generic_restore_early(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->restore_early ? pm->restore_early(dev) : 0; + return CALL_PM_OP(dev, restore_early); } EXPORT_SYMBOL_GPL(pm_generic_restore_early); @@ -252,9 +219,7 @@ EXPORT_SYMBOL_GPL(pm_generic_restore_early); */ int pm_generic_restore(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->restore ? pm->restore(dev) : 0; + return CALL_PM_OP(dev, restore); } EXPORT_SYMBOL_GPL(pm_generic_restore); diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 1de1cd72b616..a0225a83f50c 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -34,6 +34,7 @@ #include <linux/cpufreq.h> #include <linux/devfreq.h> #include <linux/timer.h> +#include <linux/nmi.h> #include "../base.h" #include "power.h" @@ -95,6 +96,8 @@ static const char *pm_verb(int event) return "restore"; case PM_EVENT_RECOVER: return "recover"; + case PM_EVENT_POWEROFF: + return "poweroff"; default: return "(unknown PM event)"; } @@ -367,6 +370,7 @@ static pm_callback_t pm_op(const struct dev_pm_ops *ops, pm_message_t state) case PM_EVENT_FREEZE: case PM_EVENT_QUIESCE: return ops->freeze; + case PM_EVENT_POWEROFF: case PM_EVENT_HIBERNATE: return ops->poweroff; case PM_EVENT_THAW: @@ -401,6 +405,7 @@ static pm_callback_t pm_late_early_op(const struct dev_pm_ops *ops, case PM_EVENT_FREEZE: case PM_EVENT_QUIESCE: return ops->freeze_late; + case PM_EVENT_POWEROFF: case PM_EVENT_HIBERNATE: return ops->poweroff_late; case PM_EVENT_THAW: @@ -435,6 +440,7 @@ static pm_callback_t pm_noirq_op(const struct dev_pm_ops *ops, pm_message_t stat case PM_EVENT_FREEZE: case PM_EVENT_QUIESCE: return ops->freeze_noirq; + case PM_EVENT_POWEROFF: case PM_EVENT_HIBERNATE: return ops->poweroff_noirq; case PM_EVENT_THAW: @@ -515,6 +521,11 @@ struct dpm_watchdog { #define DECLARE_DPM_WATCHDOG_ON_STACK(wd) \ struct dpm_watchdog wd +static bool __read_mostly dpm_watchdog_all_cpu_backtrace; +module_param(dpm_watchdog_all_cpu_backtrace, bool, 0644); +MODULE_PARM_DESC(dpm_watchdog_all_cpu_backtrace, + "Backtrace all CPUs on DPM watchdog timeout"); + /** * dpm_watchdog_handler - Driver suspend / resume watchdog handler. * @t: The timer that PM watchdog depends on. @@ -530,8 +541,12 @@ static void dpm_watchdog_handler(struct timer_list *t) unsigned int time_left; if (wd->fatal) { + unsigned int this_cpu = smp_processor_id(); + dev_emerg(wd->dev, "**** DPM device timeout ****\n"); show_stack(wd->tsk, NULL, KERN_EMERG); + if (dpm_watchdog_all_cpu_backtrace) + trigger_allbutcpu_cpu_backtrace(this_cpu); panic("%s %s: unrecoverable failure\n", dev_driver_string(wd->dev), dev_name(wd->dev)); } diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 1b11a3cd4acc..62707738caa4 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -90,7 +90,7 @@ static void update_pm_runtime_accounting(struct device *dev) /* * Because ktime_get_mono_fast_ns() is not monotonic during * timekeeping updates, ensure that 'now' is after the last saved - * timesptamp. + * timestamp. */ if (now < last) return; @@ -217,7 +217,7 @@ static int dev_memalloc_noio(struct device *dev, void *data) * resume/suspend callback of any one of its ancestors(or the * block device itself), the deadlock may be triggered inside the * memory allocation since it might not complete until the block - * device becomes active and the involed page I/O finishes. The + * device becomes active and the involved page I/O finishes. The * situation is pointed out first by Alan Stern. Network device * are involved in iSCSI kind of situation. * @@ -1210,7 +1210,7 @@ EXPORT_SYMBOL_GPL(__pm_runtime_resume); * * 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 + * nonzero, 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. @@ -1664,9 +1664,12 @@ EXPORT_SYMBOL_GPL(devm_pm_runtime_get_noresume); * pm_runtime_forbid - Block runtime PM of a device. * @dev: Device to handle. * - * Increase the device's usage count and clear its power.runtime_auto flag, - * so that it cannot be suspended at run time until pm_runtime_allow() is called - * for it. + * Resume @dev if already suspended and block runtime suspend of @dev in such + * a way that it can be unblocked via the /sys/devices/.../power/control + * interface, or otherwise by calling pm_runtime_allow(). + * + * Calling this function many times in a row has the same effect as calling it + * once. */ void pm_runtime_forbid(struct device *dev) { @@ -1687,7 +1690,13 @@ EXPORT_SYMBOL_GPL(pm_runtime_forbid); * pm_runtime_allow - Unblock runtime PM of a device. * @dev: Device to handle. * - * Decrease the device's usage count and set its power.runtime_auto flag. + * Unblock runtime suspend of @dev after it has been blocked by + * pm_runtime_forbid() (for instance, if it has been blocked via the + * /sys/devices/.../power/control interface), check if @dev can be + * suspended and suspend it in that case. + * + * Calling this function many times in a row has the same effect as calling it + * once. */ void pm_runtime_allow(struct device *dev) { diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c index cd6e559648b2..d8da7195bb00 100644 --- a/drivers/base/power/trace.c +++ b/drivers/base/power/trace.c @@ -238,10 +238,8 @@ int show_trace_dev_match(char *buf, size_t size) unsigned int hash = hash_string(DEVSEED, dev_name(dev), DEVHASH); if (hash == value) { - int len = snprintf(buf, size, "%s\n", + int len = scnprintf(buf, size, "%s\n", dev_driver_string(dev)); - if (len > size) - len = size; buf += len; ret += len; size -= len; diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c index d1283ff1080b..1e1a0e7eeac5 100644 --- a/drivers/base/power/wakeup.c +++ b/drivers/base/power/wakeup.c @@ -189,17 +189,16 @@ static void wakeup_source_remove(struct wakeup_source *ws) if (WARN_ON(!ws)) return; + /* + * After shutting down the timer, wakeup_source_activate() will warn if + * the given wakeup source is passed to it. + */ + timer_shutdown_sync(&ws->timer); + raw_spin_lock_irqsave(&events_lock, flags); list_del_rcu(&ws->entry); raw_spin_unlock_irqrestore(&events_lock, flags); synchronize_srcu(&wakeup_srcu); - - timer_delete_sync(&ws->timer); - /* - * Clear timer.function to make wakeup_source_not_registered() treat - * this wakeup source as not registered. - */ - ws->timer.function = NULL; } /** @@ -506,14 +505,14 @@ int device_set_wakeup_enable(struct device *dev, bool enable) EXPORT_SYMBOL_GPL(device_set_wakeup_enable); /** - * wakeup_source_not_registered - validate the given wakeup source. + * wakeup_source_not_usable - validate the given wakeup source. * @ws: Wakeup source to be validated. */ -static bool wakeup_source_not_registered(struct wakeup_source *ws) +static bool wakeup_source_not_usable(struct wakeup_source *ws) { /* - * Use timer struct to check if the given source is initialized - * by wakeup_source_add. + * Use the timer struct to check if the given wakeup source has been + * initialized by wakeup_source_add() and it is not going away. */ return ws->timer.function != pm_wakeup_timer_fn; } @@ -558,8 +557,7 @@ static void wakeup_source_activate(struct wakeup_source *ws) { unsigned int cec; - if (WARN_ONCE(wakeup_source_not_registered(ws), - "unregistered wakeup source\n")) + if (WARN_ONCE(wakeup_source_not_usable(ws), "unusable wakeup source\n")) return; ws->active = true; diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index 083d8369a591..e73a66785d69 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -395,7 +395,7 @@ static unsigned int check_freqs(struct cpufreq_policy *policy, cur_freq = extract_freq(policy, get_cur_val(mask, data)); if (cur_freq == freq) return 1; - udelay(10); + usleep_range(10, 15); } return 0; } diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index b44f0f7a5ba1..c45bc98721d2 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -65,13 +65,13 @@ static const char * const amd_pstate_mode_string[] = { [AMD_PSTATE_PASSIVE] = "passive", [AMD_PSTATE_ACTIVE] = "active", [AMD_PSTATE_GUIDED] = "guided", - NULL, }; +static_assert(ARRAY_SIZE(amd_pstate_mode_string) == AMD_PSTATE_MAX); const char *amd_pstate_get_mode_string(enum amd_pstate_mode mode) { - if (mode < 0 || mode >= AMD_PSTATE_MAX) - return NULL; + if (mode < AMD_PSTATE_UNDEFINED || mode >= AMD_PSTATE_MAX) + mode = AMD_PSTATE_UNDEFINED; return amd_pstate_mode_string[mode]; } EXPORT_SYMBOL_GPL(amd_pstate_get_mode_string); @@ -110,6 +110,7 @@ enum energy_perf_value_index { EPP_INDEX_BALANCE_PERFORMANCE, EPP_INDEX_BALANCE_POWERSAVE, EPP_INDEX_POWERSAVE, + EPP_INDEX_MAX, }; static const char * const energy_perf_strings[] = { @@ -118,8 +119,8 @@ static const char * const energy_perf_strings[] = { [EPP_INDEX_BALANCE_PERFORMANCE] = "balance_performance", [EPP_INDEX_BALANCE_POWERSAVE] = "balance_power", [EPP_INDEX_POWERSAVE] = "power", - NULL }; +static_assert(ARRAY_SIZE(energy_perf_strings) == EPP_INDEX_MAX); static unsigned int epp_values[] = { [EPP_INDEX_DEFAULT] = 0, @@ -127,7 +128,8 @@ static unsigned int epp_values[] = { [EPP_INDEX_BALANCE_PERFORMANCE] = AMD_CPPC_EPP_BALANCE_PERFORMANCE, [EPP_INDEX_BALANCE_POWERSAVE] = AMD_CPPC_EPP_BALANCE_POWERSAVE, [EPP_INDEX_POWERSAVE] = AMD_CPPC_EPP_POWERSAVE, - }; +}; +static_assert(ARRAY_SIZE(epp_values) == EPP_INDEX_MAX); typedef int (*cppc_mode_transition_fn)(int); @@ -183,7 +185,7 @@ static inline int get_mode_idx_from_str(const char *str, size_t size) { int i; - for (i=0; i < AMD_PSTATE_MAX; i++) { + for (i = 0; i < AMD_PSTATE_MAX; i++) { if (!strncmp(str, amd_pstate_mode_string[i], size)) return i; } @@ -1137,16 +1139,15 @@ static ssize_t show_amd_pstate_hw_prefcore(struct cpufreq_policy *policy, static ssize_t show_energy_performance_available_preferences( struct cpufreq_policy *policy, char *buf) { - int i = 0; - int offset = 0; + int offset = 0, i; struct amd_cpudata *cpudata = policy->driver_data; if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) return sysfs_emit_at(buf, offset, "%s\n", energy_perf_strings[EPP_INDEX_PERFORMANCE]); - while (energy_perf_strings[i] != NULL) - offset += sysfs_emit_at(buf, offset, "%s ", energy_perf_strings[i++]); + for (i = 0; i < ARRAY_SIZE(energy_perf_strings); i++) + offset += sysfs_emit_at(buf, offset, "%s ", energy_perf_strings[i]); offset += sysfs_emit_at(buf, offset, "\n"); @@ -1157,15 +1158,10 @@ static ssize_t store_energy_performance_preference( struct cpufreq_policy *policy, const char *buf, size_t count) { struct amd_cpudata *cpudata = policy->driver_data; - char str_preference[21]; ssize_t ret; u8 epp; - ret = sscanf(buf, "%20s", str_preference); - if (ret != 1) - return -EINVAL; - - ret = match_string(energy_perf_strings, -1, str_preference); + ret = sysfs_match_string(energy_perf_strings, buf); if (ret < 0) return -EINVAL; @@ -1282,7 +1278,7 @@ static int amd_pstate_change_mode_without_dvr_change(int mode) if (cpu_feature_enabled(X86_FEATURE_CPPC) || cppc_state == AMD_PSTATE_ACTIVE) return 0; - for_each_present_cpu(cpu) { + for_each_online_cpu(cpu) { cppc_set_auto_sel(cpu, (cppc_state == AMD_PSTATE_PASSIVE) ? 0 : 1); } @@ -1353,9 +1349,8 @@ int amd_pstate_update_status(const char *buf, size_t size) return -EINVAL; mode_idx = get_mode_idx_from_str(buf, size); - - if (mode_idx < 0 || mode_idx >= AMD_PSTATE_MAX) - return -EINVAL; + if (mode_idx < 0) + return mode_idx; if (mode_state_machine[cppc_state][mode_idx]) { guard(mutex)(&amd_pstate_driver_lock); diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index e23d9abea135..9eac77c4f294 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -142,16 +142,15 @@ static void cppc_cpufreq_cpu_fie_init(struct cpufreq_policy *policy) init_irq_work(&cppc_fi->irq_work, cppc_irq_work); ret = cppc_get_perf_ctrs(cpu, &cppc_fi->prev_perf_fb_ctrs); - if (ret) { - pr_warn("%s: failed to read perf counters for cpu:%d: %d\n", - __func__, cpu, ret); - /* - * Don't abort if the CPU was offline while the driver - * was getting registered. - */ - if (cpu_online(cpu)) - return; + /* + * Don't abort as the CPU was offline while the driver was + * getting registered. + */ + if (ret && cpu_online(cpu)) { + pr_debug("%s: failed to read perf counters for cpu:%d: %d\n", + __func__, cpu, ret); + return; } } diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c index cd1816a12bb9..dc11b62399ad 100644 --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -87,6 +87,7 @@ static const struct of_device_id allowlist[] __initconst = { { .compatible = "st-ericsson,u9540", }, { .compatible = "starfive,jh7110", }, + { .compatible = "starfive,jh7110s", }, { .compatible = "ti,omap2", }, { .compatible = "ti,omap4", }, diff --git a/drivers/cpufreq/cpufreq-nforce2.c b/drivers/cpufreq/cpufreq-nforce2.c index fedad1081973..fbbbe501cf2d 100644 --- a/drivers/cpufreq/cpufreq-nforce2.c +++ b/drivers/cpufreq/cpufreq-nforce2.c @@ -145,6 +145,8 @@ static unsigned int nforce2_fsb_read(int bootfsb) pci_read_config_dword(nforce2_sub5, NFORCE2_BOOTFSB, &fsb); fsb /= 1000000; + pci_dev_put(nforce2_sub5); + /* Check if PLL register is already set */ pci_read_config_byte(nforce2_dev, NFORCE2_PLLENABLE, (u8 *)&temp); @@ -426,6 +428,7 @@ static int __init nforce2_init(void) static void __exit nforce2_exit(void) { cpufreq_unregister_driver(&nforce2_driver); + pci_dev_put(nforce2_dev); } module_init(nforce2_init); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 852e024facc3..4472bb1ec83c 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1421,9 +1421,12 @@ static int cpufreq_policy_online(struct cpufreq_policy *policy, * If there is a problem with its frequency table, take it * offline and drop it. */ - ret = cpufreq_table_validate_and_sort(policy); - if (ret) - goto out_offline_policy; + if (policy->freq_table_sorted != CPUFREQ_TABLE_SORTED_ASCENDING && + policy->freq_table_sorted != CPUFREQ_TABLE_SORTED_DESCENDING) { + ret = cpufreq_table_validate_and_sort(policy); + if (ret) + goto out_offline_policy; + } /* related_cpus should at least include policy->cpus. */ cpumask_copy(policy->related_cpus, policy->cpus); @@ -2550,7 +2553,7 @@ void cpufreq_unregister_governor(struct cpufreq_governor *governor) for_each_inactive_policy(policy) { if (!strcmp(policy->last_governor, governor->name)) { policy->governor = NULL; - strcpy(policy->last_governor, "\0"); + policy->last_governor[0] = '\0'; } } read_unlock_irqrestore(&cpufreq_driver_lock, flags); diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 492a10f1bdbf..ec4abe374573 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -575,13 +575,18 @@ static void intel_pstate_hybrid_hwp_adjust(struct cpudata *cpu) int scaling = cpu->pstate.scaling; int freq; - pr_debug("CPU%d: perf_ctl_max_phys = %d\n", cpu->cpu, perf_ctl_max_phys); - pr_debug("CPU%d: perf_ctl_turbo = %d\n", cpu->cpu, perf_ctl_turbo); - pr_debug("CPU%d: perf_ctl_scaling = %d\n", cpu->cpu, perf_ctl_scaling); + pr_debug("CPU%d: PERF_CTL max_phys = %d\n", cpu->cpu, perf_ctl_max_phys); + pr_debug("CPU%d: PERF_CTL turbo = %d\n", cpu->cpu, perf_ctl_turbo); + pr_debug("CPU%d: PERF_CTL scaling = %d\n", cpu->cpu, perf_ctl_scaling); pr_debug("CPU%d: HWP_CAP guaranteed = %d\n", cpu->cpu, cpu->pstate.max_pstate); pr_debug("CPU%d: HWP_CAP highest = %d\n", cpu->cpu, cpu->pstate.turbo_pstate); pr_debug("CPU%d: HWP-to-frequency scaling factor: %d\n", cpu->cpu, scaling); + if (scaling == perf_ctl_scaling) + return; + + hwp_is_hybrid = true; + cpu->pstate.turbo_freq = rounddown(cpu->pstate.turbo_pstate * scaling, perf_ctl_scaling); cpu->pstate.max_freq = rounddown(cpu->pstate.max_pstate * scaling, @@ -909,6 +914,11 @@ static struct freq_attr *hwp_cpufreq_attrs[] = { [HWP_CPUFREQ_ATTR_COUNT] = NULL, }; +static u8 hybrid_get_cpu_type(unsigned int cpu) +{ + return cpu_data(cpu).topo.intel_type; +} + static bool no_cas __ro_after_init; static struct cpudata *hybrid_max_perf_cpu __read_mostly; @@ -925,11 +935,8 @@ static int hybrid_active_power(struct device *dev, unsigned long *power, unsigned long *freq) { /* - * Create "utilization bins" of 0-40%, 40%-60%, 60%-80%, and 80%-100% - * of the maximum capacity such that two CPUs of the same type will be - * regarded as equally attractive if the utilization of each of them - * falls into the same bin, which should prevent tasks from being - * migrated between them too often. + * Create four "states" corresponding to 40%, 60%, 80%, and 100% of the + * full capacity. * * For this purpose, return the "frequency" of 2 for the first * performance level and otherwise leave the value set by the caller. @@ -943,38 +950,40 @@ static int hybrid_active_power(struct device *dev, unsigned long *power, return 0; } +static bool hybrid_has_l3(unsigned int cpu) +{ + struct cpu_cacheinfo *cacheinfo = get_cpu_cacheinfo(cpu); + unsigned int i; + + if (!cacheinfo) + return false; + + for (i = 0; i < cacheinfo->num_leaves; i++) { + if (cacheinfo->info_list[i].level == 3) + return true; + } + + return false; +} + static int hybrid_get_cost(struct device *dev, unsigned long freq, unsigned long *cost) { - struct pstate_data *pstate = &all_cpu_data[dev->id]->pstate; - struct cpu_cacheinfo *cacheinfo = get_cpu_cacheinfo(dev->id); - + /* Facilitate load balancing between CPUs of the same type. */ + *cost = freq; /* - * The smaller the perf-to-frequency scaling factor, the larger the IPC - * ratio between the given CPU and the least capable CPU in the system. - * Regard that IPC ratio as the primary cost component and assume that - * the scaling factors for different CPU types will differ by at least - * 5% and they will not be above INTEL_PSTATE_CORE_SCALING. + * Adjust the cost depending on CPU type. * - * Add the freq value to the cost, so that the cost of running on CPUs - * of the same type in different "utilization bins" is different. - */ - *cost = div_u64(100ULL * INTEL_PSTATE_CORE_SCALING, pstate->scaling) + freq; - /* - * Increase the cost slightly for CPUs able to access L3 to avoid - * touching it in case some other CPUs of the same type can do the work - * without it. + * The idea is to start loading up LPE-cores before E-cores and start + * to populate E-cores when LPE-cores are utilized above 60% of the + * capacity. Similarly, P-cores start to be populated when E-cores are + * utilized above 60% of the capacity. */ - if (cacheinfo) { - unsigned int i; - - /* Check if L3 cache is there. */ - for (i = 0; i < cacheinfo->num_leaves; i++) { - if (cacheinfo->info_list[i].level == 3) { - *cost += 2; - break; - } - } + if (hybrid_get_cpu_type(dev->id) == INTEL_CPU_TYPE_ATOM) { + if (hybrid_has_l3(dev->id)) /* E-core */ + *cost += 1; + } else { /* P-core */ + *cost += 2; } return 0; @@ -1037,9 +1046,9 @@ static void hybrid_set_cpu_capacity(struct cpudata *cpu) topology_set_cpu_scale(cpu->cpu, arch_scale_cpu_capacity(cpu->cpu)); - pr_debug("CPU%d: perf = %u, max. perf = %u, base perf = %d\n", cpu->cpu, - cpu->capacity_perf, hybrid_max_perf_cpu->capacity_perf, - cpu->pstate.max_pstate_physical); + pr_debug("CPU%d: capacity perf = %u, base perf = %u, sys max perf = %u\n", + cpu->cpu, cpu->capacity_perf, cpu->pstate.max_pstate_physical, + hybrid_max_perf_cpu->capacity_perf); } static void hybrid_clear_cpu_capacity(unsigned int cpunum) @@ -1384,7 +1393,8 @@ static void set_power_ctl_ee_state(bool input) { u64 power_ctl; - mutex_lock(&intel_pstate_driver_lock); + guard(mutex)(&intel_pstate_driver_lock); + rdmsrq(MSR_IA32_POWER_CTL, power_ctl); if (input) { power_ctl &= ~BIT(MSR_IA32_POWER_CTL_BIT_EE); @@ -1394,7 +1404,6 @@ static void set_power_ctl_ee_state(bool input) power_ctl_ee_state = POWER_CTL_EE_DISABLE; } wrmsrq(MSR_IA32_POWER_CTL, power_ctl); - mutex_unlock(&intel_pstate_driver_lock); } static void intel_pstate_hwp_enable(struct cpudata *cpudata); @@ -1516,13 +1525,9 @@ static int intel_pstate_update_status(const char *buf, size_t size); static ssize_t show_status(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - ssize_t ret; - - mutex_lock(&intel_pstate_driver_lock); - ret = intel_pstate_show_status(buf); - mutex_unlock(&intel_pstate_driver_lock); + guard(mutex)(&intel_pstate_driver_lock); - return ret; + return intel_pstate_show_status(buf); } static ssize_t store_status(struct kobject *a, struct kobj_attribute *b, @@ -1531,11 +1536,13 @@ static ssize_t store_status(struct kobject *a, struct kobj_attribute *b, char *p = memchr(buf, '\n', count); int ret; - mutex_lock(&intel_pstate_driver_lock); + guard(mutex)(&intel_pstate_driver_lock); + ret = intel_pstate_update_status(buf, p ? p - buf : count); - mutex_unlock(&intel_pstate_driver_lock); + if (ret < 0) + return ret; - return ret < 0 ? ret : count; + return count; } static ssize_t show_turbo_pct(struct kobject *kobj, @@ -1545,12 +1552,10 @@ static ssize_t show_turbo_pct(struct kobject *kobj, int total, no_turbo, turbo_pct; uint32_t turbo_fp; - mutex_lock(&intel_pstate_driver_lock); + guard(mutex)(&intel_pstate_driver_lock); - if (!intel_pstate_driver) { - mutex_unlock(&intel_pstate_driver_lock); + if (!intel_pstate_driver) return -EAGAIN; - } cpu = all_cpu_data[0]; @@ -1559,8 +1564,6 @@ static ssize_t show_turbo_pct(struct kobject *kobj, turbo_fp = div_fp(no_turbo, total); turbo_pct = 100 - fp_toint(mul_fp(turbo_fp, int_tofp(100))); - mutex_unlock(&intel_pstate_driver_lock); - return sprintf(buf, "%u\n", turbo_pct); } @@ -1570,38 +1573,26 @@ static ssize_t show_num_pstates(struct kobject *kobj, struct cpudata *cpu; int total; - mutex_lock(&intel_pstate_driver_lock); + guard(mutex)(&intel_pstate_driver_lock); - if (!intel_pstate_driver) { - mutex_unlock(&intel_pstate_driver_lock); + if (!intel_pstate_driver) return -EAGAIN; - } cpu = all_cpu_data[0]; total = cpu->pstate.turbo_pstate - cpu->pstate.min_pstate + 1; - mutex_unlock(&intel_pstate_driver_lock); - return sprintf(buf, "%u\n", total); } static ssize_t show_no_turbo(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - ssize_t ret; + guard(mutex)(&intel_pstate_driver_lock); - mutex_lock(&intel_pstate_driver_lock); - - if (!intel_pstate_driver) { - mutex_unlock(&intel_pstate_driver_lock); + if (!intel_pstate_driver) return -EAGAIN; - } - - ret = sprintf(buf, "%u\n", global.no_turbo); - - mutex_unlock(&intel_pstate_driver_lock); - return ret; + return sprintf(buf, "%u\n", global.no_turbo); } static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b, @@ -1613,29 +1604,25 @@ static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b, if (sscanf(buf, "%u", &input) != 1) return -EINVAL; - mutex_lock(&intel_pstate_driver_lock); + guard(mutex)(&intel_pstate_driver_lock); - if (!intel_pstate_driver) { - count = -EAGAIN; - goto unlock_driver; - } + if (!intel_pstate_driver) + return -EAGAIN; no_turbo = !!clamp_t(int, input, 0, 1); WRITE_ONCE(global.turbo_disabled, turbo_is_disabled()); if (global.turbo_disabled && !no_turbo) { pr_notice("Turbo disabled by BIOS or unavailable on processor\n"); - count = -EPERM; if (global.no_turbo) - goto unlock_driver; - else - no_turbo = 1; - } + return -EPERM; - if (no_turbo == global.no_turbo) { - goto unlock_driver; + no_turbo = 1; } + if (no_turbo == global.no_turbo) + return count; + WRITE_ONCE(global.no_turbo, no_turbo); mutex_lock(&intel_pstate_limits_lock); @@ -1654,9 +1641,6 @@ static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b, intel_pstate_update_limits_for_all(); arch_set_max_freq_ratio(no_turbo); -unlock_driver: - mutex_unlock(&intel_pstate_driver_lock); - return count; } @@ -1706,12 +1690,10 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct kobj_attribute *b, if (ret != 1) return -EINVAL; - mutex_lock(&intel_pstate_driver_lock); + guard(mutex)(&intel_pstate_driver_lock); - if (!intel_pstate_driver) { - mutex_unlock(&intel_pstate_driver_lock); + if (!intel_pstate_driver) return -EAGAIN; - } mutex_lock(&intel_pstate_limits_lock); @@ -1724,8 +1706,6 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct kobj_attribute *b, else update_qos_requests(FREQ_QOS_MAX); - mutex_unlock(&intel_pstate_driver_lock); - return count; } @@ -1739,12 +1719,10 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct kobj_attribute *b, if (ret != 1) return -EINVAL; - mutex_lock(&intel_pstate_driver_lock); + guard(mutex)(&intel_pstate_driver_lock); - if (!intel_pstate_driver) { - mutex_unlock(&intel_pstate_driver_lock); + if (!intel_pstate_driver) return -EAGAIN; - } mutex_lock(&intel_pstate_limits_lock); @@ -1758,8 +1736,6 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct kobj_attribute *b, else update_qos_requests(FREQ_QOS_MIN); - mutex_unlock(&intel_pstate_driver_lock); - return count; } @@ -1780,10 +1756,10 @@ static ssize_t store_hwp_dynamic_boost(struct kobject *a, if (ret) return ret; - mutex_lock(&intel_pstate_driver_lock); + guard(mutex)(&intel_pstate_driver_lock); + hwp_boost = !!input; intel_pstate_update_policies(); - mutex_unlock(&intel_pstate_driver_lock); return count; } @@ -2072,6 +2048,18 @@ static void intel_pstate_hwp_enable(struct cpudata *cpudata) intel_pstate_update_epp_defaults(cpudata); } +static u64 get_perf_ctl_val(int pstate) +{ + u64 val; + + val = (u64)pstate << 8; + if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled) && + cpu_feature_enabled(X86_FEATURE_IDA)) + val |= (u64)1 << 32; + + return val; +} + static int atom_get_min_pstate(int not_used) { u64 value; @@ -2098,15 +2086,10 @@ static int atom_get_turbo_pstate(int not_used) static u64 atom_get_val(struct cpudata *cpudata, int pstate) { - u64 val; + u64 val = get_perf_ctl_val(pstate); int32_t vid_fp; u32 vid; - val = (u64)pstate << 8; - if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled) && - cpu_feature_enabled(X86_FEATURE_IDA)) - val |= (u64)1 << 32; - vid_fp = cpudata->vid.min + mul_fp( int_tofp(pstate - cpudata->pstate.min_pstate), cpudata->vid.ratio); @@ -2266,14 +2249,7 @@ static int core_get_turbo_pstate(int cpu) static u64 core_get_val(struct cpudata *cpudata, int pstate) { - u64 val; - - val = (u64)pstate << 8; - if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled) && - cpu_feature_enabled(X86_FEATURE_IDA)) - val |= (u64)1 << 32; - - return val; + return get_perf_ctl_val(pstate); } static int knl_get_aperf_mperf_shift(void) @@ -2297,18 +2273,14 @@ static int knl_get_turbo_pstate(int cpu) static int hwp_get_cpu_scaling(int cpu) { if (hybrid_scaling_factor) { - struct cpuinfo_x86 *c = &cpu_data(cpu); - u8 cpu_type = c->topo.intel_type; - /* * Return the hybrid scaling factor for P-cores and use the * default core scaling for E-cores. */ - if (cpu_type == INTEL_CPU_TYPE_CORE) + if (hybrid_get_cpu_type(cpu) == INTEL_CPU_TYPE_CORE) return hybrid_scaling_factor; - if (cpu_type == INTEL_CPU_TYPE_ATOM) - return core_get_scaling(); + return core_get_scaling(); } /* Use core scaling on non-hybrid systems. */ @@ -2343,11 +2315,10 @@ static void intel_pstate_set_min_pstate(struct cpudata *cpu) static void intel_pstate_get_cpu_pstates(struct cpudata *cpu) { - int perf_ctl_max_phys = pstate_funcs.get_max_physical(cpu->cpu); int perf_ctl_scaling = pstate_funcs.get_scaling(); + cpu->pstate.max_pstate_physical = pstate_funcs.get_max_physical(cpu->cpu); cpu->pstate.min_pstate = pstate_funcs.get_min(cpu->cpu); - cpu->pstate.max_pstate_physical = perf_ctl_max_phys; cpu->pstate.perf_ctl_scaling = perf_ctl_scaling; if (hwp_active && !hwp_mode_bdw) { @@ -2355,10 +2326,7 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu) if (pstate_funcs.get_cpu_scaling) { cpu->pstate.scaling = pstate_funcs.get_cpu_scaling(cpu->cpu); - if (cpu->pstate.scaling != perf_ctl_scaling) { - intel_pstate_hybrid_hwp_adjust(cpu); - hwp_is_hybrid = true; - } + intel_pstate_hybrid_hwp_adjust(cpu); } else { cpu->pstate.scaling = perf_ctl_scaling; } @@ -2760,6 +2728,7 @@ static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] __initconst = { X86_MATCH(INTEL_ATOM_CRESTMONT, core_funcs), X86_MATCH(INTEL_ATOM_CRESTMONT_X, core_funcs), X86_MATCH(INTEL_ATOM_DARKMONT_X, core_funcs), + X86_MATCH(INTEL_DIAMONDRAPIDS_X, core_funcs), {} }; #endif @@ -3912,9 +3881,9 @@ hwp_cpu_matched: } - mutex_lock(&intel_pstate_driver_lock); - rc = intel_pstate_register_driver(default_driver); - mutex_unlock(&intel_pstate_driver_lock); + scoped_guard(mutex, &intel_pstate_driver_lock) { + rc = intel_pstate_register_driver(default_driver); + } if (rc) { intel_pstate_sysfs_remove(); return rc; diff --git a/drivers/cpufreq/qcom-cpufreq-nvmem.c b/drivers/cpufreq/qcom-cpufreq-nvmem.c index 765a5bb81829..81e16b5a0245 100644 --- a/drivers/cpufreq/qcom-cpufreq-nvmem.c +++ b/drivers/cpufreq/qcom-cpufreq-nvmem.c @@ -256,13 +256,22 @@ len_error: return ret; } +static const struct of_device_id qcom_cpufreq_ipq806x_match_list[] __maybe_unused = { + { .compatible = "qcom,ipq8062", .data = (const void *)QCOM_ID_IPQ8062 }, + { .compatible = "qcom,ipq8064", .data = (const void *)QCOM_ID_IPQ8064 }, + { .compatible = "qcom,ipq8065", .data = (const void *)QCOM_ID_IPQ8065 }, + { .compatible = "qcom,ipq8066", .data = (const void *)QCOM_ID_IPQ8066 }, + { .compatible = "qcom,ipq8068", .data = (const void *)QCOM_ID_IPQ8068 }, + { .compatible = "qcom,ipq8069", .data = (const void *)QCOM_ID_IPQ8069 }, +}; + static int qcom_cpufreq_ipq8064_name_version(struct device *cpu_dev, struct nvmem_cell *speedbin_nvmem, char **pvs_name, struct qcom_cpufreq_drv *drv) { + int msm_id = -1, ret = 0; int speed = 0, pvs = 0; - int msm_id, ret = 0; u8 *speedbin; size_t len; @@ -279,8 +288,30 @@ static int qcom_cpufreq_ipq8064_name_version(struct device *cpu_dev, get_krait_bin_format_a(cpu_dev, &speed, &pvs, speedbin); ret = qcom_smem_get_soc_id(&msm_id); - if (ret) + if (ret == -ENODEV) { + const struct of_device_id *match; + struct device_node *root; + + root = of_find_node_by_path("/"); + if (!root) { + ret = -ENODEV; + goto exit; + } + + /* Fallback to compatible match with no SMEM initialized */ + match = of_match_node(qcom_cpufreq_ipq806x_match_list, root); + of_node_put(root); + if (!match) { + ret = -ENODEV; + goto exit; + } + + /* We found a matching device, get the msm_id from the data entry */ + msm_id = (int)(uintptr_t)match->data; + ret = 0; + } else if (ret) { goto exit; + } switch (msm_id) { case QCOM_ID_IPQ8062: diff --git a/drivers/cpufreq/s5pv210-cpufreq.c b/drivers/cpufreq/s5pv210-cpufreq.c index 4215621deb3f..ba8a1c96427a 100644 --- a/drivers/cpufreq/s5pv210-cpufreq.c +++ b/drivers/cpufreq/s5pv210-cpufreq.c @@ -518,7 +518,7 @@ static int s5pv210_cpu_init(struct cpufreq_policy *policy) if (policy->cpu != 0) { ret = -EINVAL; - goto out_dmc1; + goto out; } /* @@ -530,7 +530,7 @@ static int s5pv210_cpu_init(struct cpufreq_policy *policy) if ((mem_type != LPDDR) && (mem_type != LPDDR2)) { pr_err("CPUFreq doesn't support this memory type\n"); ret = -EINVAL; - goto out_dmc1; + goto out; } /* Find current refresh counter and frequency each DMC */ @@ -544,6 +544,8 @@ static int s5pv210_cpu_init(struct cpufreq_policy *policy) cpufreq_generic_init(policy, s5pv210_freq_table, 40000); return 0; +out: + clk_put(dmc1_clk); out_dmc1: clk_put(dmc0_clk); out_dmc0: diff --git a/drivers/cpufreq/tegra186-cpufreq.c b/drivers/cpufreq/tegra186-cpufreq.c index 136ab102f636..34ed943c5f34 100644 --- a/drivers/cpufreq/tegra186-cpufreq.c +++ b/drivers/cpufreq/tegra186-cpufreq.c @@ -8,6 +8,7 @@ #include <linux/module.h> #include <linux/of.h> #include <linux/platform_device.h> +#include <linux/units.h> #include <soc/tegra/bpmp.h> #include <soc/tegra/bpmp-abi.h> @@ -58,7 +59,7 @@ static const struct tegra186_cpufreq_cpu tegra186_cpus[] = { }; struct tegra186_cpufreq_cluster { - struct cpufreq_frequency_table *table; + struct cpufreq_frequency_table *bpmp_lut; u32 ref_clk_khz; u32 div; }; @@ -66,16 +67,119 @@ struct tegra186_cpufreq_cluster { struct tegra186_cpufreq_data { void __iomem *regs; const struct tegra186_cpufreq_cpu *cpus; + bool icc_dram_bw_scaling; struct tegra186_cpufreq_cluster clusters[]; }; +static int tegra_cpufreq_set_bw(struct cpufreq_policy *policy, unsigned long freq_khz) +{ + struct tegra186_cpufreq_data *data = cpufreq_get_driver_data(); + struct device *dev; + int ret; + + dev = get_cpu_device(policy->cpu); + if (!dev) + return -ENODEV; + + struct dev_pm_opp *opp __free(put_opp) = + dev_pm_opp_find_freq_exact(dev, freq_khz * HZ_PER_KHZ, true); + if (IS_ERR(opp)) + return PTR_ERR(opp); + + ret = dev_pm_opp_set_opp(dev, opp); + if (ret) + data->icc_dram_bw_scaling = false; + + return ret; +} + +static int tegra_cpufreq_init_cpufreq_table(struct cpufreq_policy *policy, + struct cpufreq_frequency_table *bpmp_lut, + struct cpufreq_frequency_table **opp_table) +{ + struct tegra186_cpufreq_data *data = cpufreq_get_driver_data(); + struct cpufreq_frequency_table *freq_table = NULL; + struct cpufreq_frequency_table *pos; + struct device *cpu_dev; + unsigned long rate; + int ret, max_opps; + int j = 0; + + cpu_dev = get_cpu_device(policy->cpu); + if (!cpu_dev) { + pr_err("%s: failed to get cpu%d device\n", __func__, policy->cpu); + return -ENODEV; + } + + /* Initialize OPP table mentioned in operating-points-v2 property in DT */ + ret = dev_pm_opp_of_add_table_indexed(cpu_dev, 0); + if (ret) { + dev_err(cpu_dev, "Invalid or empty opp table in device tree\n"); + data->icc_dram_bw_scaling = false; + return ret; + } + + max_opps = dev_pm_opp_get_opp_count(cpu_dev); + if (max_opps <= 0) { + dev_err(cpu_dev, "Failed to add OPPs\n"); + return max_opps; + } + + /* Disable all opps and cross-validate against LUT later */ + for (rate = 0; ; rate++) { + struct dev_pm_opp *opp __free(put_opp) = + dev_pm_opp_find_freq_ceil(cpu_dev, &rate); + if (IS_ERR(opp)) + break; + + dev_pm_opp_disable(cpu_dev, rate); + } + + freq_table = kcalloc((max_opps + 1), sizeof(*freq_table), GFP_KERNEL); + if (!freq_table) + return -ENOMEM; + + /* + * Cross check the frequencies from BPMP-FW LUT against the OPP's present in DT. + * Enable only those DT OPP's which are present in LUT also. + */ + cpufreq_for_each_valid_entry(pos, bpmp_lut) { + struct dev_pm_opp *opp __free(put_opp) = + dev_pm_opp_find_freq_exact(cpu_dev, pos->frequency * HZ_PER_KHZ, false); + if (IS_ERR(opp)) + continue; + + ret = dev_pm_opp_enable(cpu_dev, pos->frequency * HZ_PER_KHZ); + if (ret < 0) + return ret; + + freq_table[j].driver_data = pos->driver_data; + freq_table[j].frequency = pos->frequency; + j++; + } + + freq_table[j].driver_data = pos->driver_data; + freq_table[j].frequency = CPUFREQ_TABLE_END; + + *opp_table = &freq_table[0]; + + dev_pm_opp_set_sharing_cpus(cpu_dev, policy->cpus); + + /* Prime interconnect data */ + tegra_cpufreq_set_bw(policy, freq_table[j - 1].frequency); + + return ret; +} + static int tegra186_cpufreq_init(struct cpufreq_policy *policy) { struct tegra186_cpufreq_data *data = cpufreq_get_driver_data(); unsigned int cluster = data->cpus[policy->cpu].bpmp_cluster_id; + struct cpufreq_frequency_table *freq_table; + struct cpufreq_frequency_table *bpmp_lut; u32 cpu; + int ret; - policy->freq_table = data->clusters[cluster].table; policy->cpuinfo.transition_latency = 300 * 1000; policy->driver_data = NULL; @@ -85,6 +189,20 @@ static int tegra186_cpufreq_init(struct cpufreq_policy *policy) cpumask_set_cpu(cpu, policy->cpus); } + bpmp_lut = data->clusters[cluster].bpmp_lut; + + if (data->icc_dram_bw_scaling) { + ret = tegra_cpufreq_init_cpufreq_table(policy, bpmp_lut, &freq_table); + if (!ret) { + policy->freq_table = freq_table; + return 0; + } + } + + data->icc_dram_bw_scaling = false; + policy->freq_table = bpmp_lut; + pr_info("OPP tables missing from DT, EMC frequency scaling disabled\n"); + return 0; } @@ -102,6 +220,10 @@ static int tegra186_cpufreq_set_target(struct cpufreq_policy *policy, writel(edvd_val, data->regs + edvd_offset); } + if (data->icc_dram_bw_scaling) + tegra_cpufreq_set_bw(policy, tbl->frequency); + + return 0; } @@ -134,7 +256,7 @@ static struct cpufreq_driver tegra186_cpufreq_driver = { .init = tegra186_cpufreq_init, }; -static struct cpufreq_frequency_table *init_vhint_table( +static struct cpufreq_frequency_table *tegra_cpufreq_bpmp_read_lut( struct platform_device *pdev, struct tegra_bpmp *bpmp, struct tegra186_cpufreq_cluster *cluster, unsigned int cluster_id, int *num_rates) @@ -229,6 +351,7 @@ static int tegra186_cpufreq_probe(struct platform_device *pdev) { struct tegra186_cpufreq_data *data; struct tegra_bpmp *bpmp; + struct device *cpu_dev; unsigned int i = 0, err, edvd_offset; int num_rates = 0; u32 edvd_val, cpu; @@ -254,9 +377,9 @@ static int tegra186_cpufreq_probe(struct platform_device *pdev) for (i = 0; i < TEGRA186_NUM_CLUSTERS; i++) { struct tegra186_cpufreq_cluster *cluster = &data->clusters[i]; - cluster->table = init_vhint_table(pdev, bpmp, cluster, i, &num_rates); - if (IS_ERR(cluster->table)) { - err = PTR_ERR(cluster->table); + cluster->bpmp_lut = tegra_cpufreq_bpmp_read_lut(pdev, bpmp, cluster, i, &num_rates); + if (IS_ERR(cluster->bpmp_lut)) { + err = PTR_ERR(cluster->bpmp_lut); goto put_bpmp; } else if (!num_rates) { err = -EINVAL; @@ -265,7 +388,7 @@ static int tegra186_cpufreq_probe(struct platform_device *pdev) for (cpu = 0; cpu < ARRAY_SIZE(tegra186_cpus); cpu++) { if (data->cpus[cpu].bpmp_cluster_id == i) { - edvd_val = cluster->table[num_rates - 1].driver_data; + edvd_val = cluster->bpmp_lut[num_rates - 1].driver_data; edvd_offset = data->cpus[cpu].edvd_offset; writel(edvd_val, data->regs + edvd_offset); } @@ -274,6 +397,19 @@ static int tegra186_cpufreq_probe(struct platform_device *pdev) tegra186_cpufreq_driver.driver_data = data; + /* Check for optional OPPv2 and interconnect paths on CPU0 to enable ICC scaling */ + cpu_dev = get_cpu_device(0); + if (!cpu_dev) { + err = -EPROBE_DEFER; + goto put_bpmp; + } + + if (dev_pm_opp_of_get_opp_desc_node(cpu_dev)) { + err = dev_pm_opp_of_find_icc_paths(cpu_dev, NULL); + if (!err) + data->icc_dram_bw_scaling = true; + } + err = cpufreq_register_driver(&tegra186_cpufreq_driver); put_bpmp: diff --git a/drivers/cpufreq/tegra194-cpufreq.c b/drivers/cpufreq/tegra194-cpufreq.c index 9b4f516f313e..695599e1001f 100644 --- a/drivers/cpufreq/tegra194-cpufreq.c +++ b/drivers/cpufreq/tegra194-cpufreq.c @@ -750,7 +750,8 @@ static int tegra194_cpufreq_probe(struct platform_device *pdev) if (IS_ERR(bpmp)) return PTR_ERR(bpmp); - read_counters_wq = alloc_workqueue("read_counters_wq", __WQ_LEGACY, 1); + read_counters_wq = alloc_workqueue("read_counters_wq", + __WQ_LEGACY | WQ_PERCPU, 1); if (!read_counters_wq) { dev_err(&pdev->dev, "fail to create_workqueue\n"); err = -EINVAL; diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 56132e843c99..c7876e9e024f 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -184,20 +184,22 @@ static noinstr void enter_s2idle_proper(struct cpuidle_driver *drv, * cpuidle_enter_s2idle - Enter an idle state suitable for suspend-to-idle. * @drv: cpuidle driver for the given CPU. * @dev: cpuidle device for the given CPU. + * @latency_limit_ns: Idle state exit latency limit * * If there are states with the ->enter_s2idle callback, find the deepest of * them and enter it with frozen tick. */ -int cpuidle_enter_s2idle(struct cpuidle_driver *drv, struct cpuidle_device *dev) +int cpuidle_enter_s2idle(struct cpuidle_driver *drv, struct cpuidle_device *dev, + u64 latency_limit_ns) { int index; /* - * Find the deepest state with ->enter_s2idle present, which guarantees - * that interrupts won't be enabled when it exits and allows the tick to - * be frozen safely. + * Find the deepest state with ->enter_s2idle present that meets the + * specified latency limit, which guarantees that interrupts won't be + * enabled when it exits and allows the tick to be frozen safely. */ - index = find_deepest_state(drv, dev, U64_MAX, 0, true); + index = find_deepest_state(drv, dev, latency_limit_ns, 0, true); if (index > 0) { enter_s2idle_proper(drv, dev, index); local_irq_enable(); diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c index 9bbfa594c442..370664c47e65 100644 --- a/drivers/cpuidle/driver.c +++ b/drivers/cpuidle/driver.c @@ -8,6 +8,8 @@ * This code is licenced under the GPL. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/mutex.h> #include <linux/module.h> #include <linux/sched.h> @@ -193,6 +195,14 @@ static void __cpuidle_driver_init(struct cpuidle_driver *drv) s->exit_latency_ns = 0; else s->exit_latency = div_u64(s->exit_latency_ns, NSEC_PER_USEC); + + /* + * Warn if the exit latency of a CPU idle state exceeds its + * target residency which is assumed to never happen in cpuidle + * in multiple places. + */ + if (s->exit_latency_ns > s->target_residency_ns) + pr_warn("Idle state %d target residency too low\n", i); } } diff --git a/drivers/cpuidle/governor.c b/drivers/cpuidle/governor.c index 0d0f9751ff8f..5d0e7f78c6c5 100644 --- a/drivers/cpuidle/governor.c +++ b/drivers/cpuidle/governor.c @@ -111,6 +111,10 @@ s64 cpuidle_governor_latency_req(unsigned int cpu) struct device *device = get_cpu_device(cpu); int device_req = dev_pm_qos_raw_resume_latency(device); int global_req = cpu_latency_qos_limit(); + int global_wake_req = cpu_wakeup_latency_qos_limit(); + + if (global_req > global_wake_req) + global_req = global_wake_req; if (device_req > global_req) device_req = global_req; diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index 23239b0c04f9..64d6f7a1c776 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -317,12 +317,13 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, } /* - * Use a physical idle state, not busy polling, unless a timer - * is going to trigger soon enough or the exit latency of the - * idle state in question is greater than the predicted idle - * duration. + * Use a physical idle state instead of busy polling so long as + * its target residency is below the residency threshold, its + * exit latency is not greater than the predicted idle duration, + * and the next timer doesn't expire soon. */ if ((drv->states[idx].flags & CPUIDLE_FLAG_POLLING) && + s->target_residency_ns < RESIDENCY_THRESHOLD_NS && s->target_residency_ns <= data->next_timer_ns && s->exit_latency_ns <= predicted_ns) { predicted_ns = s->target_residency_ns; diff --git a/drivers/cpuidle/governors/teo.c b/drivers/cpuidle/governors/teo.c index bfa55c1eab5b..81ac5fd58a1c 100644 --- a/drivers/cpuidle/governors/teo.c +++ b/drivers/cpuidle/governors/teo.c @@ -76,7 +76,7 @@ * likely woken up by a non-timer wakeup source). * * 2. If the second sum computed in step 1 is greater than a half of the sum of - * both metrics for the candidate state bin and all subsequent bins(if any), + * both metrics for the candidate state bin and all subsequent bins (if any), * a shallower idle state is likely to be more suitable, so look for it. * * - Traverse the enabled idle states shallower than the candidate one in the @@ -133,21 +133,33 @@ struct teo_bin { * @sleep_length_ns: Time till the closest timer event (at the selection time). * @state_bins: Idle state data bins for this CPU. * @total: Grand total of the "intercepts" and "hits" metrics for all bins. + * @total_tick: Wakeups by the scheduler tick. * @tick_intercepts: "Intercepts" before TICK_NSEC. * @short_idles: Wakeups after short idle periods. - * @artificial_wakeup: Set if the wakeup has been triggered by a safety net. + * @tick_wakeup: Set if the last wakeup was by the scheduler tick. */ struct teo_cpu { s64 sleep_length_ns; struct teo_bin state_bins[CPUIDLE_STATE_MAX]; unsigned int total; + unsigned int total_tick; unsigned int tick_intercepts; unsigned int short_idles; - bool artificial_wakeup; + bool tick_wakeup; }; static DEFINE_PER_CPU(struct teo_cpu, teo_cpus); +static void teo_decay(unsigned int *metric) +{ + unsigned int delta = *metric >> DECAY_SHIFT; + + if (delta) + *metric -= delta; + else + *metric = 0; +} + /** * teo_update - Update CPU metrics after wakeup. * @drv: cpuidle driver containing state data. @@ -155,21 +167,22 @@ static DEFINE_PER_CPU(struct teo_cpu, teo_cpus); */ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) { - struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu); + struct teo_cpu *cpu_data = this_cpu_ptr(&teo_cpus); int i, idx_timer = 0, idx_duration = 0; - s64 target_residency_ns; - u64 measured_ns; + s64 target_residency_ns, measured_ns; + unsigned int total = 0; - cpu_data->short_idles -= cpu_data->short_idles >> DECAY_SHIFT; + teo_decay(&cpu_data->short_idles); - if (cpu_data->artificial_wakeup) { + if (dev->poll_time_limit) { + dev->poll_time_limit = false; /* - * If one of the safety nets has triggered, assume that this + * Polling state timeout has triggered, so assume that this * might have been a long sleep. */ - measured_ns = U64_MAX; + measured_ns = S64_MAX; } else { - u64 lat_ns = drv->states[dev->last_state_idx].exit_latency_ns; + s64 lat_ns = drv->states[dev->last_state_idx].exit_latency_ns; measured_ns = dev->last_residency_ns; /* @@ -196,8 +209,10 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) for (i = 0; i < drv->state_count; i++) { struct teo_bin *bin = &cpu_data->state_bins[i]; - bin->hits -= bin->hits >> DECAY_SHIFT; - bin->intercepts -= bin->intercepts >> DECAY_SHIFT; + teo_decay(&bin->hits); + total += bin->hits; + teo_decay(&bin->intercepts); + total += bin->intercepts; target_residency_ns = drv->states[i].target_residency_ns; @@ -208,7 +223,24 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) } } - cpu_data->tick_intercepts -= cpu_data->tick_intercepts >> DECAY_SHIFT; + cpu_data->total = total + PULSE; + + teo_decay(&cpu_data->tick_intercepts); + + teo_decay(&cpu_data->total_tick); + if (cpu_data->tick_wakeup) { + cpu_data->total_tick += PULSE; + /* + * If tick wakeups dominate the wakeup pattern, count this one + * as a hit on the deepest available idle state to increase the + * likelihood of stopping the tick. + */ + if (3 * cpu_data->total_tick > 2 * cpu_data->total) { + cpu_data->state_bins[drv->state_count-1].hits += PULSE; + return; + } + } + /* * If the measured idle duration falls into the same bin as the sleep * length, this is a "hit", so update the "hits" metric for that bin. @@ -219,18 +251,9 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) cpu_data->state_bins[idx_timer].hits += PULSE; } else { cpu_data->state_bins[idx_duration].intercepts += PULSE; - if (TICK_NSEC <= measured_ns) + if (measured_ns <= TICK_NSEC) cpu_data->tick_intercepts += PULSE; } - - cpu_data->total -= cpu_data->total >> DECAY_SHIFT; - cpu_data->total += PULSE; -} - -static bool teo_state_ok(int i, struct cpuidle_driver *drv) -{ - return !tick_nohz_tick_stopped() || - drv->states[i].target_residency_ns >= TICK_NSEC; } /** @@ -239,17 +262,15 @@ static bool teo_state_ok(int i, struct cpuidle_driver *drv) * @dev: Target CPU. * @state_idx: Index of the capping idle state. * @duration_ns: Idle duration value to match. - * @no_poll: Don't consider polling states. */ static int teo_find_shallower_state(struct cpuidle_driver *drv, struct cpuidle_device *dev, int state_idx, - s64 duration_ns, bool no_poll) + s64 duration_ns) { int i; for (i = state_idx - 1; i >= 0; i--) { - if (dev->states_usage[i].disable || - (no_poll && drv->states[i].flags & CPUIDLE_FLAG_POLLING)) + if (dev->states_usage[i].disable) continue; state_idx = i; @@ -268,7 +289,7 @@ static int teo_find_shallower_state(struct cpuidle_driver *drv, static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, bool *stop_tick) { - struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu); + struct teo_cpu *cpu_data = this_cpu_ptr(&teo_cpus); s64 latency_req = cpuidle_governor_latency_req(dev->cpu); ktime_t delta_tick = TICK_NSEC / 2; unsigned int idx_intercept_sum = 0; @@ -356,7 +377,18 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, * better choice. */ if (2 * idx_intercept_sum > cpu_data->total - idx_hit_sum) { - int first_suitable_idx = idx; + int min_idx = idx0; + + if (tick_nohz_tick_stopped()) { + /* + * Look for the shallowest idle state below the current + * candidate one whose target residency is at least + * equal to the tick period length. + */ + while (min_idx < idx && + drv->states[min_idx].target_residency_ns < TICK_NSEC) + min_idx++; + } /* * Look for the deepest idle state whose target residency had @@ -366,49 +398,14 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, * Take the possible duration limitation present if the tick * has been stopped already into account. */ - intercept_sum = 0; - - for (i = idx - 1; i >= 0; i--) { - struct teo_bin *bin = &cpu_data->state_bins[i]; - - intercept_sum += bin->intercepts; - - if (2 * intercept_sum > idx_intercept_sum) { - /* - * Use the current state unless it is too - * shallow or disabled, in which case take the - * first enabled state that is deep enough. - */ - if (teo_state_ok(i, drv) && - !dev->states_usage[i].disable) { - idx = i; - break; - } - idx = first_suitable_idx; - break; - } + for (i = idx - 1, intercept_sum = 0; i >= min_idx; i--) { + intercept_sum += cpu_data->state_bins[i].intercepts; if (dev->states_usage[i].disable) continue; - if (teo_state_ok(i, drv)) { - /* - * The current state is deep enough, but still - * there may be a better one. - */ - first_suitable_idx = i; - continue; - } - - /* - * The current state is too shallow, so if no suitable - * states other than the initial candidate have been - * found, give up (the remaining states to check are - * shallower still), but otherwise the first suitable - * state other than the initial candidate may turn out - * to be preferable. - */ - if (first_suitable_idx == idx) + idx = i; + if (2 * intercept_sum > idx_intercept_sum) break; } } @@ -458,11 +455,8 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, * If the closest expected timer is before the target residency of the * candidate state, a shallower one needs to be found. */ - if (drv->states[idx].target_residency_ns > duration_ns) { - i = teo_find_shallower_state(drv, dev, idx, duration_ns, false); - if (teo_state_ok(i, drv)) - idx = i; - } + if (drv->states[idx].target_residency_ns > duration_ns) + idx = teo_find_shallower_state(drv, dev, idx, duration_ns); /* * If the selected state's target residency is below the tick length @@ -490,7 +484,7 @@ end: */ if (idx > idx0 && drv->states[idx].target_residency_ns > delta_tick) - idx = teo_find_shallower_state(drv, dev, idx, delta_tick, false); + idx = teo_find_shallower_state(drv, dev, idx, delta_tick); out_tick: *stop_tick = false; @@ -504,20 +498,11 @@ out_tick: */ static void teo_reflect(struct cpuidle_device *dev, int state) { - struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu); + struct teo_cpu *cpu_data = this_cpu_ptr(&teo_cpus); + + cpu_data->tick_wakeup = tick_nohz_idle_got_tick(); dev->last_state_idx = state; - if (dev->poll_time_limit || - (tick_nohz_idle_got_tick() && cpu_data->sleep_length_ns > TICK_NSEC)) { - /* - * The wakeup was not "genuine", but triggered by one of the - * safety nets. - */ - dev->poll_time_limit = false; - cpu_data->artificial_wakeup = true; - } else { - cpu_data->artificial_wakeup = false; - } } /** diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c index 9b6d90a72601..c7524e4c522a 100644 --- a/drivers/cpuidle/poll_state.c +++ b/drivers/cpuidle/poll_state.c @@ -4,9 +4,13 @@ */ #include <linux/cpuidle.h> +#include <linux/export.h> +#include <linux/irqflags.h> #include <linux/sched.h> #include <linux/sched/clock.h> #include <linux/sched/idle.h> +#include <linux/sprintf.h> +#include <linux/types.h> #define POLL_IDLE_RELAX_COUNT 200 diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index 2e8d01d47f69..00979f2e0e27 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -20,6 +20,7 @@ #include <linux/stat.h> #include <linux/pm_opp.h> #include <linux/devfreq.h> +#include <linux/devfreq-governor.h> #include <linux/workqueue.h> #include <linux/platform_device.h> #include <linux/list.h> @@ -28,7 +29,6 @@ #include <linux/of.h> #include <linux/pm_qos.h> #include <linux/units.h> -#include "governor.h" #define CREATE_TRACE_POINTS #include <trace/events/devfreq.h> diff --git a/drivers/devfreq/governor.h b/drivers/devfreq/governor.h deleted file mode 100644 index 0adfebc0467a..000000000000 --- a/drivers/devfreq/governor.h +++ /dev/null @@ -1,127 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * governor.h - internal header for devfreq governors. - * - * Copyright (C) 2011 Samsung Electronics - * MyungJoo Ham <myungjoo.ham@samsung.com> - * - * This header is for devfreq governors in drivers/devfreq/ - */ - -#ifndef _GOVERNOR_H -#define _GOVERNOR_H - -#include <linux/devfreq.h> - -#define DEVFREQ_NAME_LEN 16 - -#define to_devfreq(DEV) container_of((DEV), struct devfreq, dev) - -/* Devfreq events */ -#define DEVFREQ_GOV_START 0x1 -#define DEVFREQ_GOV_STOP 0x2 -#define DEVFREQ_GOV_UPDATE_INTERVAL 0x3 -#define DEVFREQ_GOV_SUSPEND 0x4 -#define DEVFREQ_GOV_RESUME 0x5 - -#define DEVFREQ_MIN_FREQ 0 -#define DEVFREQ_MAX_FREQ ULONG_MAX - -/* - * Definition of the governor feature flags - * - DEVFREQ_GOV_FLAG_IMMUTABLE - * : This governor is never changeable to other governors. - * - DEVFREQ_GOV_FLAG_IRQ_DRIVEN - * : The devfreq won't schedule the work for this governor. - */ -#define DEVFREQ_GOV_FLAG_IMMUTABLE BIT(0) -#define DEVFREQ_GOV_FLAG_IRQ_DRIVEN BIT(1) - -/* - * Definition of governor attribute flags except for common sysfs attributes - * - DEVFREQ_GOV_ATTR_POLLING_INTERVAL - * : Indicate polling_interval sysfs attribute - * - DEVFREQ_GOV_ATTR_TIMER - * : Indicate timer sysfs attribute - */ -#define DEVFREQ_GOV_ATTR_POLLING_INTERVAL BIT(0) -#define DEVFREQ_GOV_ATTR_TIMER BIT(1) - -/** - * struct devfreq_cpu_data - Hold the per-cpu data - * @node: list node - * @dev: reference to cpu device. - * @first_cpu: the cpumask of the first cpu of a policy. - * @opp_table: reference to cpu opp table. - * @cur_freq: the current frequency of the cpu. - * @min_freq: the min frequency of the cpu. - * @max_freq: the max frequency of the cpu. - * - * This structure stores the required cpu_data of a cpu. - * This is auto-populated by the governor. - */ -struct devfreq_cpu_data { - struct list_head node; - - struct device *dev; - unsigned int first_cpu; - - struct opp_table *opp_table; - unsigned int cur_freq; - unsigned int min_freq; - unsigned int max_freq; -}; - -/** - * struct devfreq_governor - Devfreq policy governor - * @node: list node - contains registered devfreq governors - * @name: Governor's name - * @attrs: Governor's sysfs attribute flags - * @flags: Governor's feature flags - * @get_target_freq: Returns desired operating frequency for the device. - * Basically, get_target_freq will run - * devfreq_dev_profile.get_dev_status() to get the - * status of the device (load = busy_time / total_time). - * @event_handler: Callback for devfreq core framework to notify events - * to governors. Events include per device governor - * init and exit, opp changes out of devfreq, suspend - * and resume of per device devfreq during device idle. - * - * Note that the callbacks are called with devfreq->lock locked by devfreq. - */ -struct devfreq_governor { - struct list_head node; - - const char name[DEVFREQ_NAME_LEN]; - const u64 attrs; - const u64 flags; - int (*get_target_freq)(struct devfreq *this, unsigned long *freq); - int (*event_handler)(struct devfreq *devfreq, - unsigned int event, void *data); -}; - -void devfreq_monitor_start(struct devfreq *devfreq); -void devfreq_monitor_stop(struct devfreq *devfreq); -void devfreq_monitor_suspend(struct devfreq *devfreq); -void devfreq_monitor_resume(struct devfreq *devfreq); -void devfreq_update_interval(struct devfreq *devfreq, unsigned int *delay); - -int devfreq_add_governor(struct devfreq_governor *governor); -int devfreq_remove_governor(struct devfreq_governor *governor); - -int devm_devfreq_add_governor(struct device *dev, - struct devfreq_governor *governor); - -int devfreq_update_status(struct devfreq *devfreq, unsigned long freq); -int devfreq_update_target(struct devfreq *devfreq, unsigned long freq); -void devfreq_get_freq_range(struct devfreq *devfreq, unsigned long *min_freq, - unsigned long *max_freq); - -static inline int devfreq_update_stats(struct devfreq *df) -{ - if (!df->profile->get_dev_status) - return -EINVAL; - - return df->profile->get_dev_status(df->dev.parent, &df->last_status); -} -#endif /* _GOVERNOR_H */ diff --git a/drivers/devfreq/governor_passive.c b/drivers/devfreq/governor_passive.c index 953cf9a1e9f7..8cd6f9a59f64 100644 --- a/drivers/devfreq/governor_passive.c +++ b/drivers/devfreq/governor_passive.c @@ -14,8 +14,33 @@ #include <linux/slab.h> #include <linux/device.h> #include <linux/devfreq.h> +#include <linux/devfreq-governor.h> #include <linux/units.h> -#include "governor.h" + +/** + * struct devfreq_cpu_data - Hold the per-cpu data + * @node: list node + * @dev: reference to cpu device. + * @first_cpu: the cpumask of the first cpu of a policy. + * @opp_table: reference to cpu opp table. + * @cur_freq: the current frequency of the cpu. + * @min_freq: the min frequency of the cpu. + * @max_freq: the max frequency of the cpu. + * + * This structure stores the required cpu_data of a cpu. + * This is auto-populated by the governor. + */ +struct devfreq_cpu_data { + struct list_head node; + + struct device *dev; + unsigned int first_cpu; + + struct opp_table *opp_table; + unsigned int cur_freq; + unsigned int min_freq; + unsigned int max_freq; +}; static struct devfreq_cpu_data * get_parent_cpu_data(struct devfreq_passive_data *p_data, diff --git a/drivers/devfreq/governor_performance.c b/drivers/devfreq/governor_performance.c index 2e4e981446fa..fdb22bf512cf 100644 --- a/drivers/devfreq/governor_performance.c +++ b/drivers/devfreq/governor_performance.c @@ -7,8 +7,8 @@ */ #include <linux/devfreq.h> +#include <linux/devfreq-governor.h> #include <linux/module.h> -#include "governor.h" static int devfreq_performance_func(struct devfreq *df, unsigned long *freq) diff --git a/drivers/devfreq/governor_powersave.c b/drivers/devfreq/governor_powersave.c index f059e8814804..ee2d6ec8a512 100644 --- a/drivers/devfreq/governor_powersave.c +++ b/drivers/devfreq/governor_powersave.c @@ -7,8 +7,8 @@ */ #include <linux/devfreq.h> +#include <linux/devfreq-governor.h> #include <linux/module.h> -#include "governor.h" static int devfreq_powersave_func(struct devfreq *df, unsigned long *freq) diff --git a/drivers/devfreq/governor_simpleondemand.c b/drivers/devfreq/governor_simpleondemand.c index c23435736367..ac9c5e9e51a4 100644 --- a/drivers/devfreq/governor_simpleondemand.c +++ b/drivers/devfreq/governor_simpleondemand.c @@ -9,12 +9,12 @@ #include <linux/errno.h> #include <linux/module.h> #include <linux/devfreq.h> +#include <linux/devfreq-governor.h> #include <linux/math64.h> -#include "governor.h" /* Default constants for DevFreq-Simple-Ondemand (DFSO) */ #define DFSO_UPTHRESHOLD (90) -#define DFSO_DOWNDIFFERENCTIAL (5) +#define DFSO_DOWNDIFFERENTIAL (5) static int devfreq_simple_ondemand_func(struct devfreq *df, unsigned long *freq) { @@ -22,7 +22,7 @@ static int devfreq_simple_ondemand_func(struct devfreq *df, struct devfreq_dev_status *stat; unsigned long long a, b; unsigned int dfso_upthreshold = DFSO_UPTHRESHOLD; - unsigned int dfso_downdifferential = DFSO_DOWNDIFFERENCTIAL; + unsigned int dfso_downdifferential = DFSO_DOWNDIFFERENTIAL; struct devfreq_simple_ondemand_data *data = df->data; err = devfreq_update_stats(df); diff --git a/drivers/devfreq/governor_userspace.c b/drivers/devfreq/governor_userspace.c index 175de0c0b50e..395174f93960 100644 --- a/drivers/devfreq/governor_userspace.c +++ b/drivers/devfreq/governor_userspace.c @@ -9,11 +9,11 @@ #include <linux/slab.h> #include <linux/device.h> #include <linux/devfreq.h> +#include <linux/devfreq-governor.h> #include <linux/kstrtox.h> #include <linux/pm.h> #include <linux/mutex.h> #include <linux/module.h> -#include "governor.h" struct userspace_data { unsigned long user_frequency; diff --git a/drivers/devfreq/hisi_uncore_freq.c b/drivers/devfreq/hisi_uncore_freq.c index 96d1815059e3..4d00d813c8ac 100644 --- a/drivers/devfreq/hisi_uncore_freq.c +++ b/drivers/devfreq/hisi_uncore_freq.c @@ -9,6 +9,7 @@ #include <linux/bits.h> #include <linux/cleanup.h> #include <linux/devfreq.h> +#include <linux/devfreq-governor.h> #include <linux/device.h> #include <linux/dev_printk.h> #include <linux/errno.h> @@ -26,8 +27,6 @@ #include <linux/units.h> #include <acpi/pcc.h> -#include "governor.h" - struct hisi_uncore_pcc_data { u16 status; u16 resv; @@ -265,10 +264,11 @@ static int hisi_uncore_target(struct device *dev, unsigned long *freq, 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); + dev_pm_opp_put(opp); + return hisi_uncore_cmd_send(uncore, HUCF_PCC_CMD_SET_FREQ, &data); } diff --git a/drivers/devfreq/tegra30-devfreq.c b/drivers/devfreq/tegra30-devfreq.c index 4a4f0106ab9d..8b57194ac698 100644 --- a/drivers/devfreq/tegra30-devfreq.c +++ b/drivers/devfreq/tegra30-devfreq.c @@ -9,9 +9,11 @@ #include <linux/clk.h> #include <linux/cpufreq.h> #include <linux/devfreq.h> +#include <linux/devfreq-governor.h> #include <linux/interrupt.h> #include <linux/io.h> #include <linux/irq.h> +#include <linux/minmax.h> #include <linux/module.h> #include <linux/of.h> #include <linux/platform_device.h> @@ -21,8 +23,6 @@ #include <soc/tegra/fuse.h> -#include "governor.h" - #define ACTMON_GLB_STATUS 0x0 #define ACTMON_GLB_PERIOD_CTRL 0x4 @@ -326,14 +326,9 @@ static unsigned long actmon_cpu_to_emc_rate(struct tegra_devfreq *tegra, unsigned int i; const struct tegra_actmon_emc_ratio *ratio = actmon_emc_ratios; - for (i = 0; i < ARRAY_SIZE(actmon_emc_ratios); i++, ratio++) { - if (cpu_freq >= ratio->cpu_freq) { - if (ratio->emc_freq >= tegra->max_freq) - return tegra->max_freq; - else - return ratio->emc_freq; - } - } + for (i = 0; i < ARRAY_SIZE(actmon_emc_ratios); i++, ratio++) + if (cpu_freq >= ratio->cpu_freq) + return min(ratio->emc_freq, tegra->max_freq); return 0; } diff --git a/drivers/opp/core.c b/drivers/opp/core.c index bba4f7daff8c..dbebb8c829bc 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -309,9 +309,9 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_is_turbo); */ unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev) { - struct opp_table *opp_table __free(put_opp_table); + struct opp_table *opp_table __free(put_opp_table) = + _find_opp_table(dev); - opp_table = _find_opp_table(dev); if (IS_ERR(opp_table)) return 0; @@ -327,7 +327,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_clock_latency); */ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev) { - struct opp_table *opp_table __free(put_opp_table); struct dev_pm_opp *opp; struct regulator *reg; unsigned long latency_ns = 0; @@ -337,7 +336,9 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev) unsigned long max; } *uV; - opp_table = _find_opp_table(dev); + struct opp_table *opp_table __free(put_opp_table) = + _find_opp_table(dev); + if (IS_ERR(opp_table)) return 0; @@ -409,10 +410,11 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_transition_latency); */ unsigned long dev_pm_opp_get_suspend_opp_freq(struct device *dev) { - struct opp_table *opp_table __free(put_opp_table); unsigned long freq = 0; - opp_table = _find_opp_table(dev); + struct opp_table *opp_table __free(put_opp_table) = + _find_opp_table(dev); + if (IS_ERR(opp_table)) return 0; @@ -447,9 +449,9 @@ int _get_opp_count(struct opp_table *opp_table) */ int dev_pm_opp_get_opp_count(struct device *dev) { - struct opp_table *opp_table __free(put_opp_table); + struct opp_table *opp_table __free(put_opp_table) = + _find_opp_table(dev); - opp_table = _find_opp_table(dev); if (IS_ERR(opp_table)) { dev_dbg(dev, "%s: OPP table not found (%ld)\n", __func__, PTR_ERR(opp_table)); @@ -605,9 +607,9 @@ _find_key(struct device *dev, unsigned long *key, int index, bool available, unsigned long opp_key, unsigned long key), bool (*assert)(struct opp_table *opp_table, unsigned int index)) { - struct opp_table *opp_table __free(put_opp_table); + struct opp_table *opp_table __free(put_opp_table) = + _find_opp_table(dev); - opp_table = _find_opp_table(dev); if (IS_ERR(opp_table)) { dev_err(dev, "%s: OPP table not found (%ld)\n", __func__, PTR_ERR(opp_table)); @@ -1410,12 +1412,13 @@ static int _set_opp(struct device *dev, struct opp_table *opp_table, */ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) { - struct opp_table *opp_table __free(put_opp_table); struct dev_pm_opp *opp __free(put_opp) = NULL; unsigned long freq = 0, temp_freq; bool forced = false; - opp_table = _find_opp_table(dev); + struct opp_table *opp_table __free(put_opp_table) = + _find_opp_table(dev); + if (IS_ERR(opp_table)) { dev_err(dev, "%s: device's opp table doesn't exist\n", __func__); return PTR_ERR(opp_table); @@ -1477,9 +1480,9 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_set_rate); */ int dev_pm_opp_set_opp(struct device *dev, struct dev_pm_opp *opp) { - struct opp_table *opp_table __free(put_opp_table); + struct opp_table *opp_table __free(put_opp_table) = + _find_opp_table(dev); - opp_table = _find_opp_table(dev); if (IS_ERR(opp_table)) { dev_err(dev, "%s: device opp doesn't exist\n", __func__); return PTR_ERR(opp_table); @@ -1794,10 +1797,11 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_put); */ void dev_pm_opp_remove(struct device *dev, unsigned long freq) { - struct opp_table *opp_table __free(put_opp_table); struct dev_pm_opp *opp = NULL, *iter; - opp_table = _find_opp_table(dev); + struct opp_table *opp_table __free(put_opp_table) = + _find_opp_table(dev); + if (IS_ERR(opp_table)) return; @@ -1885,9 +1889,9 @@ bool _opp_remove_all_static(struct opp_table *opp_table) */ void dev_pm_opp_remove_all_dynamic(struct device *dev) { - struct opp_table *opp_table __free(put_opp_table); + struct opp_table *opp_table __free(put_opp_table) = + _find_opp_table(dev); - opp_table = _find_opp_table(dev); if (IS_ERR(opp_table)) return; @@ -2871,10 +2875,11 @@ static int _opp_set_availability(struct device *dev, unsigned long freq, bool availability_req) { struct dev_pm_opp *opp __free(put_opp) = ERR_PTR(-ENODEV), *tmp_opp; - struct opp_table *opp_table __free(put_opp_table); /* Find the opp_table */ - opp_table = _find_opp_table(dev); + struct opp_table *opp_table __free(put_opp_table) = + _find_opp_table(dev); + if (IS_ERR(opp_table)) { dev_warn(dev, "%s: Device OPP not found (%ld)\n", __func__, PTR_ERR(opp_table)); @@ -2932,11 +2937,12 @@ int dev_pm_opp_adjust_voltage(struct device *dev, unsigned long freq, { struct dev_pm_opp *opp __free(put_opp) = ERR_PTR(-ENODEV), *tmp_opp; - struct opp_table *opp_table __free(put_opp_table); int r; /* Find the opp_table */ - opp_table = _find_opp_table(dev); + struct opp_table *opp_table __free(put_opp_table) = + _find_opp_table(dev); + if (IS_ERR(opp_table)) { r = PTR_ERR(opp_table); dev_warn(dev, "%s: Device OPP not found (%d)\n", __func__, r); @@ -2986,12 +2992,13 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_adjust_voltage); */ int dev_pm_opp_sync_regulators(struct device *dev) { - struct opp_table *opp_table __free(put_opp_table); struct regulator *reg; int ret, i; /* Device may not have OPP table */ - opp_table = _find_opp_table(dev); + struct opp_table *opp_table __free(put_opp_table) = + _find_opp_table(dev); + if (IS_ERR(opp_table)) return 0; @@ -3062,9 +3069,9 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_disable); */ int dev_pm_opp_register_notifier(struct device *dev, struct notifier_block *nb) { - struct opp_table *opp_table __free(put_opp_table); + struct opp_table *opp_table __free(put_opp_table) = + _find_opp_table(dev); - opp_table = _find_opp_table(dev); if (IS_ERR(opp_table)) return PTR_ERR(opp_table); @@ -3082,9 +3089,9 @@ EXPORT_SYMBOL(dev_pm_opp_register_notifier); int dev_pm_opp_unregister_notifier(struct device *dev, struct notifier_block *nb) { - struct opp_table *opp_table __free(put_opp_table); + struct opp_table *opp_table __free(put_opp_table) = + _find_opp_table(dev); - opp_table = _find_opp_table(dev); if (IS_ERR(opp_table)) return PTR_ERR(opp_table); @@ -3101,10 +3108,10 @@ EXPORT_SYMBOL(dev_pm_opp_unregister_notifier); */ void dev_pm_opp_remove_table(struct device *dev) { - struct opp_table *opp_table __free(put_opp_table); - /* Check for existing table for 'dev' */ - opp_table = _find_opp_table(dev); + struct opp_table *opp_table __free(put_opp_table) = + _find_opp_table(dev); + if (IS_ERR(opp_table)) { int error = PTR_ERR(opp_table); diff --git a/drivers/opp/cpu.c b/drivers/opp/cpu.c index 97989d4fe336..a6da7ee3ec76 100644 --- a/drivers/opp/cpu.c +++ b/drivers/opp/cpu.c @@ -56,10 +56,10 @@ int dev_pm_opp_init_cpufreq_table(struct device *dev, return -ENOMEM; for (i = 0, rate = 0; i < max_opps; i++, rate++) { - struct dev_pm_opp *opp __free(put_opp); - /* find next rate */ - opp = dev_pm_opp_find_freq_ceil(dev, &rate); + struct dev_pm_opp *opp __free(put_opp) = + dev_pm_opp_find_freq_ceil(dev, &rate); + if (IS_ERR(opp)) { ret = PTR_ERR(opp); goto out; @@ -154,12 +154,13 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_cpumask_remove_table); int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cpumask) { - struct opp_table *opp_table __free(put_opp_table); struct opp_device *opp_dev; struct device *dev; int cpu; - opp_table = _find_opp_table(cpu_dev); + struct opp_table *opp_table __free(put_opp_table) = + _find_opp_table(cpu_dev); + if (IS_ERR(opp_table)) return PTR_ERR(opp_table); @@ -201,10 +202,11 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_set_sharing_cpus); */ int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask) { - struct opp_table *opp_table __free(put_opp_table); struct opp_device *opp_dev; - opp_table = _find_opp_table(cpu_dev); + struct opp_table *opp_table __free(put_opp_table) = + _find_opp_table(cpu_dev); + if (IS_ERR(opp_table)) return PTR_ERR(opp_table); diff --git a/drivers/opp/of.c b/drivers/opp/of.c index 505d79821584..1e0d0adb18e1 100644 --- a/drivers/opp/of.c +++ b/drivers/opp/of.c @@ -45,9 +45,10 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_of_get_opp_desc_node); struct opp_table *_managed_opp(struct device *dev, int index) { struct opp_table *opp_table, *managed_table = NULL; - struct device_node *np __free(device_node); - np = _opp_of_get_opp_desc_node(dev->of_node, index); + struct device_node *np __free(device_node) = + _opp_of_get_opp_desc_node(dev->of_node, index); + if (!np) return NULL; @@ -95,10 +96,11 @@ static struct device_node *of_parse_required_opp(struct device_node *np, /* The caller must call dev_pm_opp_put_opp_table() after the table is used */ static struct opp_table *_find_table_of_opp_np(struct device_node *opp_np) { - struct device_node *opp_table_np __free(device_node); struct opp_table *opp_table; - opp_table_np = of_get_parent(opp_np); + struct device_node *opp_table_np __free(device_node) = + of_get_parent(opp_np); + if (!opp_table_np) return ERR_PTR(-ENODEV); @@ -146,12 +148,13 @@ static void _opp_table_alloc_required_tables(struct opp_table *opp_table, struct device_node *opp_np) { struct opp_table **required_opp_tables; - struct device_node *np __free(device_node); bool lazy = false; int count, i, size; /* Traversing the first OPP node is all we need */ - np = of_get_next_available_child(opp_np, NULL); + struct device_node *np __free(device_node) = + of_get_next_available_child(opp_np, NULL); + if (!np) { dev_warn(dev, "Empty OPP table\n"); return; @@ -171,9 +174,9 @@ static void _opp_table_alloc_required_tables(struct opp_table *opp_table, opp_table->required_opp_count = count; for (i = 0; i < count; i++) { - struct device_node *required_np __free(device_node); + struct device_node *required_np __free(device_node) = + of_parse_required_opp(np, i); - required_np = of_parse_required_opp(np, i); if (!required_np) { _opp_table_free_required_tables(opp_table); return; @@ -199,14 +202,15 @@ static void _opp_table_alloc_required_tables(struct opp_table *opp_table, void _of_init_opp_table(struct opp_table *opp_table, struct device *dev, int index) { - struct device_node *np __free(device_node), *opp_np; + struct device_node *opp_np; u32 val; /* * Only required for backward compatibility with v1 bindings, but isn't * harmful for other cases. And so we do it unconditionally. */ - np = of_node_get(dev->of_node); + struct device_node *np __free(device_node) = of_node_get(dev->of_node); + if (!np) return; @@ -273,9 +277,9 @@ void _of_clear_opp(struct opp_table *opp_table, struct dev_pm_opp *opp) static int _link_required_opps(struct dev_pm_opp *opp, struct opp_table *required_table, int index) { - struct device_node *np __free(device_node); + struct device_node *np __free(device_node) = + of_parse_required_opp(opp->np, index); - np = of_parse_required_opp(opp->np, index); if (unlikely(!np)) return -ENODEV; @@ -349,16 +353,13 @@ static void lazy_link_required_opp_table(struct opp_table *new_table) guard(mutex)(&opp_table_lock); list_for_each_entry_safe(opp_table, temp, &lazy_opp_tables, lazy) { - struct device_node *opp_np __free(device_node); bool lazy = false; /* opp_np can't be invalid here */ - opp_np = of_get_next_available_child(opp_table->np, NULL); + struct device_node *opp_np __free(device_node) = + of_get_next_available_child(opp_table->np, NULL); for (i = 0; i < opp_table->required_opp_count; i++) { - struct device_node *required_np __free(device_node) = NULL; - struct device_node *required_table_np __free(device_node) = NULL; - required_opp_tables = opp_table->required_opp_tables; /* Required opp-table is already parsed */ @@ -366,8 +367,10 @@ static void lazy_link_required_opp_table(struct opp_table *new_table) continue; /* required_np can't be invalid here */ - required_np = of_parse_required_opp(opp_np, i); - required_table_np = of_get_parent(required_np); + struct device_node *required_np __free(device_node) = + of_parse_required_opp(opp_np, i); + struct device_node *required_table_np __free(device_node) = + of_get_parent(required_np); /* * Newly added table isn't the required opp-table for @@ -402,13 +405,12 @@ static void lazy_link_required_opp_table(struct opp_table *new_table) static int _bandwidth_supported(struct device *dev, struct opp_table *opp_table) { struct device_node *opp_np __free(device_node) = NULL; - struct device_node *np __free(device_node) = NULL; struct property *prop; if (!opp_table) { - struct device_node *np __free(device_node); + struct device_node *np __free(device_node) = + of_node_get(dev->of_node); - np = of_node_get(dev->of_node); if (!np) return -ENODEV; @@ -422,7 +424,9 @@ static int _bandwidth_supported(struct device *dev, struct opp_table *opp_table) return 0; /* Checking only first OPP is sufficient */ - np = of_get_next_available_child(opp_np, NULL); + struct device_node *np __free(device_node) = + of_get_next_available_child(opp_np, NULL); + if (!np) { dev_err(dev, "OPP table empty\n"); return -EINVAL; @@ -1269,11 +1273,12 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_of_cpumask_add_table); int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask) { - struct device_node *np __free(device_node); int cpu; /* Get OPP descriptor node */ - np = dev_pm_opp_of_get_opp_desc_node(cpu_dev); + struct device_node *np __free(device_node) = + dev_pm_opp_of_get_opp_desc_node(cpu_dev); + if (!np) { dev_dbg(cpu_dev, "%s: Couldn't find opp node.\n", __func__); return -ENOENT; @@ -1286,13 +1291,12 @@ int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, return 0; for_each_possible_cpu(cpu) { - struct device_node *cpu_np __free(device_node) = NULL; - struct device_node *tmp_np __free(device_node) = NULL; - if (cpu == cpu_dev->id) continue; - cpu_np = of_cpu_device_node_get(cpu); + struct device_node *cpu_np __free(device_node) = + of_cpu_device_node_get(cpu); + if (!cpu_np) { dev_err(cpu_dev, "%s: failed to get cpu%d node\n", __func__, cpu); @@ -1300,7 +1304,9 @@ int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, } /* Get OPP descriptor node */ - tmp_np = _opp_of_get_opp_desc_node(cpu_np, 0); + struct device_node *tmp_np __free(device_node) = + _opp_of_get_opp_desc_node(cpu_np, 0); + if (!tmp_np) { pr_err("%pOF: Couldn't find opp node\n", cpu_np); return -ENOENT; @@ -1328,16 +1334,17 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_of_get_sharing_cpus); */ int of_get_required_opp_performance_state(struct device_node *np, int index) { - struct device_node *required_np __free(device_node); - struct opp_table *opp_table __free(put_opp_table) = NULL; - struct dev_pm_opp *opp __free(put_opp) = NULL; int pstate = -EINVAL; - required_np = of_parse_required_opp(np, index); + struct device_node *required_np __free(device_node) = + of_parse_required_opp(np, index); + if (!required_np) return -ENODEV; - opp_table = _find_table_of_opp_np(required_np); + struct opp_table *opp_table __free(put_opp_table) = + _find_table_of_opp_np(required_np); + if (IS_ERR(opp_table)) { pr_err("%s: Failed to find required OPP table %pOF: %ld\n", __func__, np, PTR_ERR(opp_table)); @@ -1350,7 +1357,9 @@ int of_get_required_opp_performance_state(struct device_node *np, int index) return -EINVAL; } - opp = _find_opp_of_np(opp_table, required_np); + struct dev_pm_opp *opp __free(put_opp) = + _find_opp_of_np(opp_table, required_np); + if (opp) { if (opp->level == OPP_LEVEL_UNSET) { pr_err("%s: OPP levels aren't available for %pOF\n", @@ -1376,14 +1385,17 @@ EXPORT_SYMBOL_GPL(of_get_required_opp_performance_state); */ bool dev_pm_opp_of_has_required_opp(struct device *dev) { - struct device_node *np __free(device_node) = NULL, *opp_np __free(device_node); int count; - opp_np = _opp_of_get_opp_desc_node(dev->of_node, 0); + struct device_node *opp_np __free(device_node) = + _opp_of_get_opp_desc_node(dev->of_node, 0); + if (!opp_np) return false; - np = of_get_next_available_child(opp_np, NULL); + struct device_node *np __free(device_node) = + of_get_next_available_child(opp_np, NULL); + if (!np) { dev_warn(dev, "Empty OPP table\n"); return false; @@ -1425,12 +1437,14 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_of_node); static int __maybe_unused _get_dt_power(struct device *dev, unsigned long *uW, unsigned long *kHz) { - struct dev_pm_opp *opp __free(put_opp); unsigned long opp_freq, opp_power; /* Find the right frequency and related OPP */ opp_freq = *kHz * 1000; - opp = dev_pm_opp_find_freq_ceil(dev, &opp_freq); + + struct dev_pm_opp *opp __free(put_opp) = + dev_pm_opp_find_freq_ceil(dev, &opp_freq); + if (IS_ERR(opp)) return -EINVAL; @@ -1465,14 +1479,13 @@ _get_dt_power(struct device *dev, unsigned long *uW, unsigned long *kHz) int dev_pm_opp_calc_power(struct device *dev, unsigned long *uW, unsigned long *kHz) { - struct dev_pm_opp *opp __free(put_opp) = NULL; - struct device_node *np __free(device_node); unsigned long mV, Hz; u32 cap; u64 tmp; int ret; - np = of_node_get(dev->of_node); + struct device_node *np __free(device_node) = of_node_get(dev->of_node); + if (!np) return -EINVAL; @@ -1481,7 +1494,10 @@ int dev_pm_opp_calc_power(struct device *dev, unsigned long *uW, return -EINVAL; Hz = *kHz * 1000; - opp = dev_pm_opp_find_freq_ceil(dev, &Hz); + + struct dev_pm_opp *opp __free(put_opp) = + dev_pm_opp_find_freq_ceil(dev, &Hz); + if (IS_ERR(opp)) return -EINVAL; @@ -1502,11 +1518,12 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_calc_power); static bool _of_has_opp_microwatt_property(struct device *dev) { - struct dev_pm_opp *opp __free(put_opp); unsigned long freq = 0; /* Check if at least one OPP has needed property */ - opp = dev_pm_opp_find_freq_ceil(dev, &freq); + struct dev_pm_opp *opp __free(put_opp) = + dev_pm_opp_find_freq_ceil(dev, &freq); + if (IS_ERR(opp)) return false; @@ -1526,12 +1543,16 @@ static bool _of_has_opp_microwatt_property(struct device *dev) */ int dev_pm_opp_of_register_em(struct device *dev, struct cpumask *cpus) { - struct device_node *np __free(device_node) = NULL; struct em_data_callback em_cb; int ret, nr_opp; u32 cap; - if (IS_ERR_OR_NULL(dev)) { + if (IS_ERR_OR_NULL(dev)) + return -EINVAL; + + struct device_node *np __free(device_node) = of_node_get(dev->of_node); + + if (!np) { ret = -EINVAL; goto failed; } @@ -1548,12 +1569,6 @@ int dev_pm_opp_of_register_em(struct device *dev, struct cpumask *cpus) goto register_em; } - np = of_node_get(dev->of_node); - if (!np) { - ret = -EINVAL; - goto failed; - } - /* * Register an EM only if the 'dynamic-power-coefficient' property is * set in devicetree. It is assumed the voltage values are known if that diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 9d6f74bd95f8..3881359440b1 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -1517,8 +1517,8 @@ static ssize_t reset_method_store(struct device *dev, return count; } - ACQUIRE(pm_runtime_active_try, pm)(dev); - if (ACQUIRE_ERR(pm_runtime_active_try, &pm)) + PM_RUNTIME_ACQUIRE(dev, pm); + if (PM_RUNTIME_ACQUIRE_ERR(&pm)) return -ENXIO; if (sysfs_streq(buf, "default")) { diff --git a/drivers/pmdomain/core.c b/drivers/pmdomain/core.c index 61c2277c9ce3..4fd546ef0448 100644 --- a/drivers/pmdomain/core.c +++ b/drivers/pmdomain/core.c @@ -1425,8 +1425,14 @@ static void genpd_sync_power_off(struct generic_pm_domain *genpd, bool use_lock, return; } - /* Choose the deepest state when suspending */ - genpd->state_idx = genpd->state_count - 1; + if (genpd->gov && genpd->gov->system_power_down_ok) { + if (!genpd->gov->system_power_down_ok(&genpd->domain)) + return; + } else { + /* Default to the deepest state. */ + genpd->state_idx = genpd->state_count - 1; + } + if (_genpd_power_off(genpd, false)) { genpd->states[genpd->state_idx].rejected++; return; diff --git a/drivers/pmdomain/governor.c b/drivers/pmdomain/governor.c index 39359811a930..05e68680f34b 100644 --- a/drivers/pmdomain/governor.c +++ b/drivers/pmdomain/governor.c @@ -351,7 +351,7 @@ static bool cpu_power_down_ok(struct dev_pm_domain *pd) ktime_t domain_wakeup, next_hrtimer; ktime_t now = ktime_get(); struct device *cpu_dev; - s64 cpu_constraint, global_constraint; + s64 cpu_constraint, global_constraint, wakeup_constraint; s64 idle_duration_ns; int cpu, i; @@ -362,7 +362,11 @@ static bool cpu_power_down_ok(struct dev_pm_domain *pd) if (!(genpd->flags & GENPD_FLAG_CPU_DOMAIN)) return true; + wakeup_constraint = cpu_wakeup_latency_qos_limit(); global_constraint = cpu_latency_qos_limit(); + if (global_constraint > wakeup_constraint) + global_constraint = wakeup_constraint; + /* * Find the next wakeup for any of the online CPUs within the PM domain * and its subdomains. Note, we only need the genpd->cpus, as it already @@ -415,9 +419,36 @@ static bool cpu_power_down_ok(struct dev_pm_domain *pd) return false; } +static bool cpu_system_power_down_ok(struct dev_pm_domain *pd) +{ + s64 constraint_ns = cpu_wakeup_latency_qos_limit() * NSEC_PER_USEC; + struct generic_pm_domain *genpd = pd_to_genpd(pd); + int state_idx = genpd->state_count - 1; + + if (!(genpd->flags & GENPD_FLAG_CPU_DOMAIN)) { + genpd->state_idx = state_idx; + return true; + } + + /* Find the deepest state for the latency constraint. */ + while (state_idx >= 0) { + s64 latency_ns = genpd->states[state_idx].power_off_latency_ns + + genpd->states[state_idx].power_on_latency_ns; + + if (latency_ns <= constraint_ns) { + genpd->state_idx = state_idx; + return true; + } + state_idx--; + } + + return false; +} + struct dev_power_governor pm_domain_cpu_gov = { .suspend_ok = default_suspend_ok, .power_down_ok = cpu_power_down_ok, + .system_power_down_ok = cpu_system_power_down_ok, }; #endif diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c index c7e7f9bf5313..b9d87e56cbbc 100644 --- a/drivers/powercap/intel_rapl_common.c +++ b/drivers/powercap/intel_rapl_common.c @@ -253,7 +253,8 @@ struct rapl_primitive_info { static void rapl_init_domains(struct rapl_package *rp); static int rapl_read_data_raw(struct rapl_domain *rd, enum rapl_primitives prim, - bool xlate, u64 *data); + bool xlate, u64 *data, + bool atomic); static int rapl_write_data_raw(struct rapl_domain *rd, enum rapl_primitives prim, unsigned long long value); @@ -289,7 +290,7 @@ static int get_energy_counter(struct powercap_zone *power_zone, cpus_read_lock(); rd = power_zone_to_rapl_domain(power_zone); - if (!rapl_read_data_raw(rd, ENERGY_COUNTER, true, &energy_now)) { + if (!rapl_read_data_raw(rd, ENERGY_COUNTER, true, &energy_now, false)) { *energy_raw = energy_now; cpus_read_unlock(); @@ -830,7 +831,8 @@ prim_fixups(struct rapl_domain *rd, enum rapl_primitives prim) * 63-------------------------- 31--------------------------- 0 */ static int rapl_read_data_raw(struct rapl_domain *rd, - enum rapl_primitives prim, bool xlate, u64 *data) + enum rapl_primitives prim, bool xlate, u64 *data, + bool atomic) { u64 value; enum rapl_primitives prim_fixed = prim_fixups(rd, prim); @@ -852,7 +854,7 @@ static int rapl_read_data_raw(struct rapl_domain *rd, ra.mask = rpi->mask; - if (rd->rp->priv->read_raw(get_rid(rd->rp), &ra)) { + if (rd->rp->priv->read_raw(get_rid(rd->rp), &ra, atomic)) { pr_debug("failed to read reg 0x%llx for %s:%s\n", ra.reg.val, rd->rp->name, rd->name); return -EIO; } @@ -904,7 +906,7 @@ static int rapl_read_pl_data(struct rapl_domain *rd, int pl, if (!is_pl_valid(rd, pl)) return -EINVAL; - return rapl_read_data_raw(rd, prim, xlate, data); + return rapl_read_data_raw(rd, prim, xlate, data, false); } static int rapl_write_pl_data(struct rapl_domain *rd, int pl, @@ -941,7 +943,7 @@ static int rapl_check_unit_core(struct rapl_domain *rd) ra.reg = rd->regs[RAPL_DOMAIN_REG_UNIT]; ra.mask = ~0; - if (rd->rp->priv->read_raw(get_rid(rd->rp), &ra)) { + if (rd->rp->priv->read_raw(get_rid(rd->rp), &ra, false)) { pr_err("Failed to read power unit REG 0x%llx on %s:%s, exit.\n", ra.reg.val, rd->rp->name, rd->name); return -ENODEV; @@ -969,7 +971,7 @@ static int rapl_check_unit_atom(struct rapl_domain *rd) ra.reg = rd->regs[RAPL_DOMAIN_REG_UNIT]; ra.mask = ~0; - if (rd->rp->priv->read_raw(get_rid(rd->rp), &ra)) { + if (rd->rp->priv->read_raw(get_rid(rd->rp), &ra, false)) { pr_err("Failed to read power unit REG 0x%llx on %s:%s, exit.\n", ra.reg.val, rd->rp->name, rd->name); return -ENODEV; @@ -1156,7 +1158,7 @@ static int rapl_check_unit_tpmi(struct rapl_domain *rd) ra.reg = rd->regs[RAPL_DOMAIN_REG_UNIT]; ra.mask = ~0; - if (rd->rp->priv->read_raw(get_rid(rd->rp), &ra)) { + if (rd->rp->priv->read_raw(get_rid(rd->rp), &ra, false)) { pr_err("Failed to read power unit REG 0x%llx on %s:%s, exit.\n", ra.reg.val, rd->rp->name, rd->name); return -ENODEV; @@ -1284,6 +1286,9 @@ static const struct x86_cpu_id rapl_ids[] __initconst = { X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X, &rapl_defaults_spr_server), X86_MATCH_VFM(INTEL_LUNARLAKE_M, &rapl_defaults_core), X86_MATCH_VFM(INTEL_PANTHERLAKE_L, &rapl_defaults_core), + X86_MATCH_VFM(INTEL_WILDCATLAKE_L, &rapl_defaults_core), + X86_MATCH_VFM(INTEL_NOVALAKE, &rapl_defaults_core), + X86_MATCH_VFM(INTEL_NOVALAKE_L, &rapl_defaults_core), X86_MATCH_VFM(INTEL_ARROWLAKE_H, &rapl_defaults_core), X86_MATCH_VFM(INTEL_ARROWLAKE, &rapl_defaults_core), X86_MATCH_VFM(INTEL_ARROWLAKE_U, &rapl_defaults_core), @@ -1325,7 +1330,7 @@ static void rapl_update_domain_data(struct rapl_package *rp) struct rapl_primitive_info *rpi = get_rpi(rp, prim); if (!rapl_read_data_raw(&rp->domains[dmn], prim, - rpi->unit, &val)) + rpi->unit, &val, false)) rp->domains[dmn].rdd.primitives[prim] = val; } } @@ -1425,7 +1430,7 @@ static int rapl_check_domain(int domain, struct rapl_package *rp) */ ra.mask = ENERGY_STATUS_MASK; - if (rp->priv->read_raw(get_rid(rp), &ra) || !ra.value) + if (rp->priv->read_raw(get_rid(rp), &ra, false) || !ra.value) return -ENODEV; return 0; @@ -1592,11 +1597,11 @@ static int get_pmu_cpu(struct rapl_package *rp) if (!rp->has_pmu) return nr_cpu_ids; - /* Only TPMI RAPL is supported for now */ - if (rp->priv->type != RAPL_IF_TPMI) + /* Only TPMI & MSR RAPL are supported for now */ + if (rp->priv->type != RAPL_IF_TPMI && rp->priv->type != RAPL_IF_MSR) return nr_cpu_ids; - /* TPMI RAPL uses any CPU in the package for PMU */ + /* TPMI/MSR RAPL uses any CPU in the package for PMU */ for_each_online_cpu(cpu) if (topology_physical_package_id(cpu) == rp->id) return cpu; @@ -1609,11 +1614,11 @@ static bool is_rp_pmu_cpu(struct rapl_package *rp, int cpu) if (!rp->has_pmu) return false; - /* Only TPMI RAPL is supported for now */ - if (rp->priv->type != RAPL_IF_TPMI) + /* Only TPMI & MSR RAPL are supported for now */ + if (rp->priv->type != RAPL_IF_TPMI && rp->priv->type != RAPL_IF_MSR) return false; - /* TPMI RAPL uses any CPU in the package for PMU */ + /* TPMI/MSR RAPL uses any CPU in the package for PMU */ return topology_physical_package_id(cpu) == rp->id; } @@ -1636,7 +1641,7 @@ static u64 event_read_counter(struct perf_event *event) if (event->hw.idx < 0) return 0; - ret = rapl_read_data_raw(&rp->domains[event->hw.idx], ENERGY_COUNTER, false, &val); + ret = rapl_read_data_raw(&rp->domains[event->hw.idx], ENERGY_COUNTER, false, &val, true); /* Return 0 for failed read */ if (ret) diff --git a/drivers/powercap/intel_rapl_msr.c b/drivers/powercap/intel_rapl_msr.c index 4ed06c71a3ac..0ce1096b6314 100644 --- a/drivers/powercap/intel_rapl_msr.c +++ b/drivers/powercap/intel_rapl_msr.c @@ -33,6 +33,8 @@ /* private data for RAPL MSR Interface */ static struct rapl_if_priv *rapl_msr_priv; +static bool rapl_msr_pmu __ro_after_init; + static struct rapl_if_priv rapl_msr_priv_intel = { .type = RAPL_IF_MSR, .reg_unit.msr = MSR_RAPL_POWER_UNIT, @@ -79,6 +81,8 @@ static int rapl_cpu_online(unsigned int cpu) rp = rapl_add_package_cpuslocked(cpu, rapl_msr_priv, true); if (IS_ERR(rp)) return PTR_ERR(rp); + if (rapl_msr_pmu) + rapl_package_add_pmu(rp); } cpumask_set_cpu(cpu, &rp->cpumask); return 0; @@ -95,19 +99,37 @@ static int rapl_cpu_down_prep(unsigned int cpu) cpumask_clear_cpu(cpu, &rp->cpumask); lead_cpu = cpumask_first(&rp->cpumask); - if (lead_cpu >= nr_cpu_ids) + if (lead_cpu >= nr_cpu_ids) { + if (rapl_msr_pmu) + rapl_package_remove_pmu(rp); rapl_remove_package_cpuslocked(rp); - else if (rp->lead_cpu == cpu) + } else if (rp->lead_cpu == cpu) { rp->lead_cpu = lead_cpu; + } + return 0; } -static int rapl_msr_read_raw(int cpu, struct reg_action *ra) +static int rapl_msr_read_raw(int cpu, struct reg_action *ra, bool atomic) { + /* + * When called from atomic-context (eg PMU event handler) + * perform MSR read directly using rdmsrq(). + */ + if (atomic) { + if (unlikely(smp_processor_id() != cpu)) + return -EIO; + + rdmsrq(ra->reg.msr, ra->value); + goto out; + } + if (rdmsrq_safe_on_cpu(cpu, ra->reg.msr, &ra->value)) { pr_debug("failed to read msr 0x%x on cpu %d\n", ra->reg.msr, cpu); return -EIO; } + +out: ra->value &= ra->mask; return 0; } @@ -151,6 +173,16 @@ static const struct x86_cpu_id pl4_support_ids[] = { X86_MATCH_VFM(INTEL_ARROWLAKE_U, NULL), X86_MATCH_VFM(INTEL_ARROWLAKE_H, NULL), X86_MATCH_VFM(INTEL_PANTHERLAKE_L, NULL), + X86_MATCH_VFM(INTEL_WILDCATLAKE_L, NULL), + X86_MATCH_VFM(INTEL_NOVALAKE, NULL), + X86_MATCH_VFM(INTEL_NOVALAKE_L, NULL), + {} +}; + +/* List of MSR-based RAPL PMU support CPUs */ +static const struct x86_cpu_id pmu_support_ids[] = { + X86_MATCH_VFM(INTEL_PANTHERLAKE_L, NULL), + X86_MATCH_VFM(INTEL_WILDCATLAKE_L, NULL), {} }; @@ -181,6 +213,11 @@ static int rapl_msr_probe(struct platform_device *pdev) pr_info("PL4 support detected.\n"); } + if (x86_match_cpu(pmu_support_ids)) { + rapl_msr_pmu = true; + pr_info("MSR-based RAPL PMU support enabled\n"); + } + rapl_msr_priv->control_type = powercap_register_control_type(NULL, "intel-rapl", NULL); if (IS_ERR(rapl_msr_priv->control_type)) { pr_debug("failed to register powercap control_type.\n"); diff --git a/drivers/powercap/intel_rapl_tpmi.c b/drivers/powercap/intel_rapl_tpmi.c index 82201bf4685d..0a0b85f4528b 100644 --- a/drivers/powercap/intel_rapl_tpmi.c +++ b/drivers/powercap/intel_rapl_tpmi.c @@ -60,7 +60,7 @@ static DEFINE_MUTEX(tpmi_rapl_lock); static struct powercap_control_type *tpmi_control_type; -static int tpmi_rapl_read_raw(int id, struct reg_action *ra) +static int tpmi_rapl_read_raw(int id, struct reg_action *ra, bool atomic) { if (!ra->reg.mmio) return -EINVAL; diff --git a/drivers/scsi/mesh.c b/drivers/scsi/mesh.c index 1c15cac41d80..768b85eecc8f 100644 --- a/drivers/scsi/mesh.c +++ b/drivers/scsi/mesh.c @@ -1762,6 +1762,7 @@ static int mesh_suspend(struct macio_dev *mdev, pm_message_t mesg) case PM_EVENT_SUSPEND: case PM_EVENT_HIBERNATE: case PM_EVENT_FREEZE: + case PM_EVENT_POWEROFF: break; default: return 0; diff --git a/drivers/scsi/stex.c b/drivers/scsi/stex.c index d8ad02c29320..e6357bc301cb 100644 --- a/drivers/scsi/stex.c +++ b/drivers/scsi/stex.c @@ -1965,6 +1965,7 @@ static int stex_choice_sleep_mic(struct st_hba *hba, pm_message_t state) case PM_EVENT_SUSPEND: return ST_S3; case PM_EVENT_HIBERNATE: + case PM_EVENT_POWEROFF: hba->msi_lock = 0; return ST_S4; default: diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_rapl.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_rapl.c index bde2cc386afd..bf51a17c5be6 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_rapl.c +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_rapl.c @@ -19,7 +19,7 @@ static const struct rapl_mmio_regs rapl_mmio_default = { .limits[RAPL_DOMAIN_DRAM] = BIT(POWER_LIMIT2), }; -static int rapl_mmio_read_raw(int cpu, struct reg_action *ra) +static int rapl_mmio_read_raw(int cpu, struct reg_action *ra, bool atomic) { if (!ra->reg.mmio) return -EINVAL; diff --git a/drivers/usb/host/sl811-hcd.c b/drivers/usb/host/sl811-hcd.c index ea3cab99c5d4..5d6dba681e50 100644 --- a/drivers/usb/host/sl811-hcd.c +++ b/drivers/usb/host/sl811-hcd.c @@ -1748,6 +1748,7 @@ sl811h_suspend(struct platform_device *dev, pm_message_t state) break; case PM_EVENT_SUSPEND: case PM_EVENT_HIBERNATE: + case PM_EVENT_POWEROFF: case PM_EVENT_PRETHAW: /* explicitly discard hw state */ port_power(sl811, 0); break; |