Merge branches 'pm-sleep', 'pm-cpuidle' and 'pm-em'

rafaeljw · rafaeljw · commit 1225bb42b8ce · 2025-01-20T19:14:15.000+01:00
Merge updates related to system sleep, a cpuidle update and an Energy
Model handling code update for 6.14-rc1:

 - Allow configuring the system suspend-resume (DPM) watchdog to warn
   earlier than panic (Douglas Anderson).

 - Implement devm_device_init_wakeup() helper and introduce a device-
   managed variant of dev_pm_set_wake_irq() (Joe Hattori, Peng Fan).

 - Remove direct inclusions of 'pm_wakeup.h' which should be only
   included via 'device.h' (Wolfram Sang).

 - Clean up two comments in the core system-wide PM code (Rafael
   Wysocki, Randy Dunlap).

 - Add Clearwater Forest processor support to the intel_idle cpuidle
   driver (Artem Bityutskiy).

 - Move sched domains rebuild function from the schedutil cpufreq
   governor to the Energy Model handling code (Rafael Wysocki).

* pm-sleep:
  PM: sleep: wakeirq: Introduce device-managed variant of dev_pm_set_wake_irq()
  PM: sleep: Allow configuring the DPM watchdog to warn earlier than panic
  PM: sleep: convert comment from kernel-doc to plain comment
  PM: wakeup: implement devm_device_init_wakeup() helper
  PM: sleep: sysfs: don't include 'pm_wakeup.h' directly
  PM: sleep: autosleep: don't include 'pm_wakeup.h' directly
  PM: sleep: Update stale comment in device_resume()

* pm-cpuidle:
  intel_idle: add Clearwater Forest SoC support

* pm-em:
  PM: EM: Move sched domains rebuild function from schedutil to EM
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
@@ -496,6 +496,7 @@ struct dpm_watchdog {
 	struct device		*dev;
 	struct task_struct	*tsk;
 	struct timer_list	timer;
+	bool			fatal;
 };
 
 #define DECLARE_DPM_WATCHDOG_ON_STACK(wd) \
@@ -512,11 +513,23 @@ struct dpm_watchdog {
 static void dpm_watchdog_handler(struct timer_list *t)
 {
 	struct dpm_watchdog *wd = from_timer(wd, t, timer);
+	struct timer_list *timer = &wd->timer;
+	unsigned int time_left;
+
+	if (wd->fatal) {
+		dev_emerg(wd->dev, "**** DPM device timeout ****\n");
+		show_stack(wd->tsk, NULL, KERN_EMERG);
+		panic("%s %s: unrecoverable failure\n",
+			dev_driver_string(wd->dev), dev_name(wd->dev));
+	}
+
+	time_left = CONFIG_DPM_WATCHDOG_TIMEOUT - CONFIG_DPM_WATCHDOG_WARNING_TIMEOUT;
+	dev_warn(wd->dev, "**** DPM device timeout after %u seconds; %u seconds until panic ****\n",
+		 CONFIG_DPM_WATCHDOG_WARNING_TIMEOUT, time_left);
+	show_stack(wd->tsk, NULL, KERN_WARNING);
 
-	dev_emerg(wd->dev, "**** DPM device timeout ****\n");
-	show_stack(wd->tsk, NULL, KERN_EMERG);
-	panic("%s %s: unrecoverable failure\n",
-		dev_driver_string(wd->dev), dev_name(wd->dev));
+	wd->fatal = true;
+	mod_timer(timer, jiffies + HZ * time_left);
 }
 
 /**
@@ -530,10 +543,11 @@ static void dpm_watchdog_set(struct dpm_watchdog *wd, struct device *dev)
 
 	wd->dev = dev;
 	wd->tsk = current;
+	wd->fatal = CONFIG_DPM_WATCHDOG_TIMEOUT == CONFIG_DPM_WATCHDOG_WARNING_TIMEOUT;
 
 	timer_setup_on_stack(timer, dpm_watchdog_handler, 0);
 	/* use same timeout value for both suspend and resume */
-	timer->expires = jiffies + HZ * CONFIG_DPM_WATCHDOG_TIMEOUT;
+	timer->expires = jiffies + HZ * CONFIG_DPM_WATCHDOG_WARNING_TIMEOUT;
 	add_timer(timer);
 }
 
@@ -914,7 +928,7 @@ static void device_resume(struct device *dev, pm_message_t state, bool async)
 		goto Complete;
 
 	if (dev->power.direct_complete) {
-		/* Match the pm_runtime_disable() in __device_suspend(). */
+		/* Match the pm_runtime_disable() in device_suspend(). */
 		pm_runtime_enable(dev);
 		goto Complete;
 	}
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
@@ -6,7 +6,6 @@
 #include <linux/export.h>
 #include <linux/pm_qos.h>
 #include <linux/pm_runtime.h>
-#include <linux/pm_wakeup.h>
 #include <linux/atomic.h>
 #include <linux/jiffies.h>
 #include "power.h"
diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c
@@ -103,6 +103,32 @@ void dev_pm_clear_wake_irq(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(dev_pm_clear_wake_irq);
 
+static void devm_pm_clear_wake_irq(void *dev)
+{
+	dev_pm_clear_wake_irq(dev);
+}
+
+/**
+ * devm_pm_set_wake_irq - device-managed variant of dev_pm_set_wake_irq
+ * @dev: Device entry
+ * @irq: Device IO interrupt
+ *
+ *
+ * Attach a device IO interrupt as a wake IRQ, same with dev_pm_set_wake_irq,
+ * but the device will be auto clear wake capability on driver detach.
+ */
+int devm_pm_set_wake_irq(struct device *dev, int irq)
+{
+	int ret;
+
+	ret = dev_pm_set_wake_irq(dev, irq);
+	if (ret)
+		return ret;
+
+	return devm_add_action_or_reset(dev, devm_pm_clear_wake_irq, dev);
+}
+EXPORT_SYMBOL_GPL(devm_pm_set_wake_irq);
+
 /**
  * handle_threaded_wake_irq - Handler for dedicated wake-up interrupts
  * @irq: Device specific dedicated wake-up interrupt
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
@@ -1538,7 +1538,7 @@ static int cpufreq_online(unsigned int cpu)
 
 		/*
 		 * Register with the energy model before
-		 * sugov_eas_rebuild_sd() is called, which will result
+		 * em_rebuild_sched_domains() is called, which will result
 		 * in rebuilding of the sched domains, which should only be done
 		 * once the energy model is properly initialized for the policy
 		 * first.
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
@@ -1651,6 +1651,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	X86_MATCH_VFM(INTEL_ATOM_TREMONT_D,	&idle_cpu_snr),
 	X86_MATCH_VFM(INTEL_ATOM_CRESTMONT,	&idle_cpu_grr),
 	X86_MATCH_VFM(INTEL_ATOM_CRESTMONT_X,	&idle_cpu_srf),
+	X86_MATCH_VFM(INTEL_ATOM_DARKMONT_X,	&idle_cpu_srf),
 	{}
 };
 
diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
@@ -179,6 +179,7 @@ int em_dev_compute_costs(struct device *dev, struct em_perf_state *table,
 int em_dev_update_chip_binning(struct device *dev);
 int em_update_performance_limits(struct em_perf_domain *pd,
 		unsigned long freq_min_khz, unsigned long freq_max_khz);
+void em_rebuild_sched_domains(void);
 
 /**
  * em_pd_get_efficient_state() - Get an efficient performance state from the EM
@@ -404,6 +405,7 @@ int em_update_performance_limits(struct em_perf_domain *pd,
 {
 	return -EINVAL;
 }
+static inline void em_rebuild_sched_domains(void) {}
 #endif
 
 #endif
diff --git a/include/linux/pm_wakeirq.h b/include/linux/pm_wakeirq.h
@@ -10,6 +10,7 @@ extern int dev_pm_set_wake_irq(struct device *dev, int irq);
 extern int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq);
 extern int dev_pm_set_dedicated_wake_irq_reverse(struct device *dev, int irq);
 extern void dev_pm_clear_wake_irq(struct device *dev);
+extern int devm_pm_set_wake_irq(struct device *dev, int irq);
 
 #else	/* !CONFIG_PM */
 
@@ -32,5 +33,10 @@ static inline void dev_pm_clear_wake_irq(struct device *dev)
 {
 }
 
+static inline int devm_pm_set_wake_irq(struct device *dev, int irq)
+{
+	return 0;
+}
+
 #endif	/* CONFIG_PM */
 #endif	/* _LINUX_PM_WAKEIRQ_H */
diff --git a/include/linux/pm_wakeup.h b/include/linux/pm_wakeup.h
@@ -240,4 +240,21 @@ static inline int device_init_wakeup(struct device *dev, bool enable)
 	return 0;
 }
 
+static void device_disable_wakeup(void *dev)
+{
+	device_init_wakeup(dev, false);
+}
+
+/**
+ * devm_device_init_wakeup - Resource managed device wakeup initialization.
+ * @dev: Device to handle.
+ *
+ * This function is the devm managed version of device_init_wakeup(dev, true).
+ */
+static inline int devm_device_init_wakeup(struct device *dev)
+{
+	device_init_wakeup(dev, true);
+	return devm_add_action_or_reset(dev, device_disable_wakeup, dev);
+}
+
 #endif /* _LINUX_PM_WAKEUP_H */
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
@@ -257,11 +257,30 @@ config DPM_WATCHDOG
 	  boot session.
 
 config DPM_WATCHDOG_TIMEOUT
-	int "Watchdog timeout in seconds"
+	int "Watchdog timeout to panic in seconds"
 	range 1 120
 	default 120
 	depends on DPM_WATCHDOG
 
+config DPM_WATCHDOG_WARNING_TIMEOUT
+	int "Watchdog timeout to warn in seconds"
+	range 1 DPM_WATCHDOG_TIMEOUT
+	default DPM_WATCHDOG_TIMEOUT
+	depends on DPM_WATCHDOG
+	help
+	  If the DPM watchdog warning timeout and main timeout are
+	  different then a non-fatal warning (with a stack trace of
+	  the stuck suspend routine) will be printed when the warning
+	  timeout expires. If the suspend routine gets un-stuck
+	  before the main timeout expires then no other action is
+	  taken. If the routine continues to be stuck and the main
+	  timeout expires then an emergency-level message and stack
+	  trace will be printed and the system will panic.
+
+	  If the warning timeout is equal to the main timeout (the
+	  default) then the warning will never happen and the system
+	  will jump straight to panic when the main timeout expires.
+
 config PM_TRACE
 	bool
 	help
diff --git a/kernel/power/autosleep.c b/kernel/power/autosleep.c
@@ -9,7 +9,6 @@
 
 #include <linux/device.h>
 #include <linux/mutex.h>
-#include <linux/pm_wakeup.h>
 
 #include "power.h"
 
diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
@@ -908,3 +908,20 @@ int em_update_performance_limits(struct em_perf_domain *pd,
 	return 0;
 }
 EXPORT_SYMBOL_GPL(em_update_performance_limits);
+
+static void rebuild_sd_workfn(struct work_struct *work)
+{
+	rebuild_sched_domains_energy();
+}
+
+void em_rebuild_sched_domains(void)
+{
+	static DECLARE_WORK(rebuild_sd_work, rebuild_sd_workfn);
+
+	/*
+	 * When called from the cpufreq_register_driver() path, the
+	 * cpu_hotplug_lock is already held, so use a work item to
+	 * avoid nested locking in rebuild_sched_domains().
+	 */
+	schedule_work(&rebuild_sd_work);
+}
diff --git a/kernel/power/power.h b/kernel/power/power.h
@@ -110,7 +110,7 @@ extern int hibernate_preallocate_memory(void);
 
 extern void clear_or_poison_free_pages(void);
 
-/**
+/*
  *	Auxiliary structure used for reading the snapshot image data and
  *	metadata from and writing them to the list of page backup entries
  *	(PBEs) which is the main data structure of swsusp.
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
@@ -604,31 +604,6 @@ static const struct kobj_type sugov_tunables_ktype = {
 
 /********************** cpufreq governor interface *********************/
 
-#ifdef CONFIG_ENERGY_MODEL
-static void rebuild_sd_workfn(struct work_struct *work)
-{
-	rebuild_sched_domains_energy();
-}
-
-static DECLARE_WORK(rebuild_sd_work, rebuild_sd_workfn);
-
-/*
- * EAS shouldn't be attempted without sugov, so rebuild the sched_domains
- * on governor changes to make sure the scheduler knows about it.
- */
-static void sugov_eas_rebuild_sd(void)
-{
-	/*
-	 * When called from the cpufreq_register_driver() path, the
-	 * cpu_hotplug_lock is already held, so use a work item to
-	 * avoid nested locking in rebuild_sched_domains().
-	 */
-	schedule_work(&rebuild_sd_work);
-}
-#else
-static inline void sugov_eas_rebuild_sd(void) { };
-#endif
-
 struct cpufreq_governor schedutil_gov;
 
 static struct sugov_policy *sugov_policy_alloc(struct cpufreq_policy *policy)
@@ -784,7 +759,11 @@ static int sugov_init(struct cpufreq_policy *policy)
 		goto fail;
 
 out:
-	sugov_eas_rebuild_sd();
+	/*
+	 * Schedutil is the preferred governor for EAS, so rebuild sched domains
+	 * on governor changes to make sure the scheduler knows about them.
+	 */
+	em_rebuild_sched_domains();
 	mutex_unlock(&global_tunables_lock);
 	return 0;
 
@@ -826,7 +805,7 @@ static void sugov_exit(struct cpufreq_policy *policy)
 	sugov_policy_free(sg_policy);
 	cpufreq_disable_fast_switch(policy);
 
-	sugov_eas_rebuild_sd();
+	em_rebuild_sched_domains();
 }
 
 static int sugov_start(struct cpufreq_policy *policy)

Original file line number	Diff line number	Diff line change
`@@ -179,6 +179,7 @@ int em_dev_compute_costs(struct device dev, struct em_perf_state table,`
`179`	`179`	`int em_dev_update_chip_binning(struct device *dev);`
`180`	`180`	`int em_update_performance_limits(struct em_perf_domain *pd,`
`181`	`181`	`unsigned long freq_min_khz, unsigned long freq_max_khz);`
	`182`	`+void em_rebuild_sched_domains(void);`
`182`	`183`
`183`	`184`	`/**`
`184`	`185`	`* em_pd_get_efficient_state() - Get an efficient performance state from the EM`
`@@ -404,6 +405,7 @@ int em_update_performance_limits(struct em_perf_domain *pd,`
`404`	`405`	`{`
`405`	`406`	`return -EINVAL;`
`406`	`407`	`}`
	`408`	`+static inline void em_rebuild_sched_domains(void) {}`
`407`	`409`	`#endif`
`408`	`410`
`409`	`411`	`#endif`