Merge tag 'pm-5.20-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These are mostly minor improvements all over including new CPU IDs for
  the Intel RAPL driver, an Energy Model rework to use micro-Watt as the
  power unit, cpufreq fixes and cleanus, cpuidle updates, devfreq
  updates, documentation cleanups and a new version of the pm-graph
  suite of utilities.

  Specifics:

   - Make cpufreq_show_cpus() more straightforward (Viresh Kumar).

   - Drop unnecessary CPU hotplug locking from store() used by cpufreq
     sysfs attributes (Viresh Kumar).

   - Make the ACPI cpufreq driver support the boost control interface on
     Zhaoxin/Centaur processors (Tony W Wang-oc).

   - Print a warning message on attempts to free an active cpufreq
     policy which should never happen (Viresh Kumar).

   - Fix grammar in the Kconfig help text for the loongson2 cpufreq
     driver (Randy Dunlap).

   - Use cpumask_var_t for an on-stack CPU mask in the ondemand cpufreq
     governor (Zhao Liu).

   - Add trace points for guest_halt_poll_ns grow/shrink to the haltpoll
     cpuidle driver (Eiichi Tsukata).

   - Modify intel_idle to treat C1 and C1E as independent idle states on
     Sapphire Rapids (Artem Bityutskiy).

   - Extend support for wakeirq to callback wrappers used during system
     suspend and resume (Ulf Hansson).

   - Defer waiting for device probe before loading a hibernation image
     till the first actual device access to avoid possible deadlocks
     reported by syzbot (Tetsuo Handa).

   - Unify device_init_wakeup() for PM_SLEEP and !PM_SLEEP (Bjorn
     Helgaas).

   - Add Raptor Lake-P to the list of processors supported by the Intel
     RAPL driver (George D Sworo).

   - Add Alder Lake-N and Raptor Lake-P to the list of processors for
     which Power Limit4 is supported in the Intel RAPL driver (Sumeet
     Pawnikar).

   - Make pm_genpd_remove() check genpd_debugfs_dir against NULL before
     attempting to remove it (Hsin-Yi Wang).

   - Change the Energy Model code to represent power in micro-Watts and
     adjust its users accordingly (Lukasz Luba).

   - Add new devfreq driver for Mediatek CCI (Cache Coherent
     Interconnect) (Johnson Wang).

   - Convert the Samsung Exynos SoC Bus bindings to DT schema of
     exynos-bus.c (Krzysztof Kozlowski).

   - Address kernel-doc warnings by adding the description for unused
     function parameters in devfreq core (Mauro Carvalho Chehab).

   - Use NULL to pass a null pointer rather than zero according to the
     function propotype in imx-bus.c (Colin Ian King).

   - Print error message instead of error interger value in
     tegra30-devfreq.c (Dmitry Osipenko).

   - Add checks to prevent setting negative frequency QoS limits for
     CPUs (Shivnandan Kumar).

   - Update the pm-graph suite of utilities to the latest revision 5.9
     including multiple improvements (Todd Brandt).

   - Drop pme_interrupt reference from the PCI power management
     documentation (Mario Limonciello)"

* tag 'pm-5.20-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (27 commits)
  powercap: RAPL: Add Power Limit4 support for Alder Lake-N and Raptor Lake-P
  PM: QoS: Add check to make sure CPU freq is non-negative
  PM: hibernate: defer device probing when resuming from hibernation
  intel_idle: make SPR C1 and C1E be independent
  cpufreq: ondemand: Use cpumask_var_t for on-stack cpu mask
  cpufreq: loongson2: fix Kconfig "its" grammar
  pm-graph v5.9
  cpufreq: Warn users while freeing active policy
  cpufreq: scmi: Support the power scale in micro-Watts in SCMI v3.1
  firmware: arm_scmi: Get detailed power scale from perf
  Documentation: EM: Switch to micro-Watts scale
  PM: EM: convert power field to micro-Watts precision and align drivers
  PM / devfreq: tegra30: Add error message for devm_devfreq_add_device()
  PM / devfreq: imx-bus: use NULL to pass a null pointer rather than zero
  PM / devfreq: shut up kernel-doc warnings
  dt-bindings: interconnect: samsung,exynos-bus: convert to dtschema
  PM / devfreq: mediatek: Introduce MediaTek CCI devfreq driver
  dt-bindings: interconnect: Add MediaTek CCI dt-bindings
  PM: domains: Ensure genpd_debugfs_dir exists before remove
  PM: runtime: Extend support for wakeirq for force_suspend|resume
  ...

4 files changed, 97 insertions, 25 deletions

diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
index 8419bffb4398..b9caa01dfac4 100644
--- a/include/linux/energy_model.h
+++ b/include/linux/energy_model.h
@@ -62,7 +62,7 @@ struct em_perf_domain {
 /*
  *  em_perf_domain flags:
  *
- *  EM_PERF_DOMAIN_MILLIWATTS: The power values are in milli-Watts or some
+ *  EM_PERF_DOMAIN_MICROWATTS: The power values are in micro-Watts or some
  *  other scale.
  *
  *  EM_PERF_DOMAIN_SKIP_INEFFICIENCIES: Skip inefficient states when estimating
@@ -71,7 +71,7 @@ struct em_perf_domain {
  *  EM_PERF_DOMAIN_ARTIFICIAL: The power values are artificial and might be
  *  created by platform missing real power information
  */
-#define EM_PERF_DOMAIN_MILLIWATTS BIT(0)
+#define EM_PERF_DOMAIN_MICROWATTS BIT(0)
 #define EM_PERF_DOMAIN_SKIP_INEFFICIENCIES BIT(1)
 #define EM_PERF_DOMAIN_ARTIFICIAL BIT(2)
 
@@ -79,22 +79,44 @@ struct em_perf_domain {
 #define em_is_artificial(em) ((em)->flags & EM_PERF_DOMAIN_ARTIFICIAL)
 
 #ifdef CONFIG_ENERGY_MODEL
-#define EM_MAX_POWER 0xFFFF
+/*
+ * The max power value in micro-Watts. The limit of 64 Watts is set as
+ * a safety net to not overflow multiplications on 32bit platforms. The
+ * 32bit value limit for total Perf Domain power implies a limit of
+ * maximum CPUs in such domain to 64.
+ */
+#define EM_MAX_POWER (64000000) /* 64 Watts */
+
+/*
+ * To avoid possible energy estimation overflow on 32bit machines add
+ * limits to number of CPUs in the Perf. Domain.
+ * We are safe on 64bit machine, thus some big number.
+ */
+#ifdef CONFIG_64BIT
+#define EM_MAX_NUM_CPUS 4096
+#else
+#define EM_MAX_NUM_CPUS 16
+#endif
 
 /*
- * Increase resolution of energy estimation calculations for 64-bit
- * architectures. The extra resolution improves decision made by EAS for the
- * task placement when two Performance Domains might provide similar energy
- * estimation values (w/o better resolution the values could be equal).
+ * To avoid an overflow on 32bit machines while calculating the energy
+ * use a different order in the operation. First divide by the 'cpu_scale'
+ * which would reduce big value stored in the 'cost' field, then multiply by
+ * the 'sum_util'. This would allow to handle existing platforms, which have
+ * e.g. power ~1.3 Watt at max freq, so the 'cost' value > 1mln micro-Watts.
+ * In such scenario, where there are 4 CPUs in the Perf. Domain the 'sum_util'
+ * could be 4096, then multiplication: 'cost' * 'sum_util'  would overflow.
+ * This reordering of operations has some limitations, we lose small
+ * precision in the estimation (comparing to 64bit platform w/o reordering).
  *
- * We increase resolution only if we have enough bits to allow this increased
- * resolution (i.e. 64-bit). The costs for increasing resolution when 32-bit
- * are pretty high and the returns do not justify the increased costs.
+ * We are safe on 64bit machine.
  */
 #ifdef CONFIG_64BIT
-#define em_scale_power(p) ((p) * 1000)
+#define em_estimate_energy(cost, sum_util, scale_cpu) \
+	(((cost) * (sum_util)) / (scale_cpu))
 #else
-#define em_scale_power(p) (p)
+#define em_estimate_energy(cost, sum_util, scale_cpu) \
+	(((cost) / (scale_cpu)) * (sum_util))
 #endif
 
 struct em_data_callback {
@@ -112,7 +134,7 @@ struct em_data_callback {
 	 * and frequency.
 	 *
 	 * In case of CPUs, the power is the one of a single CPU in the domain,
-	 * expressed in milli-Watts or an abstract scale. It is expected to
+	 * expressed in micro-Watts or an abstract scale. It is expected to
 	 * fit in the [0, EM_MAX_POWER] range.
 	 *
 	 * Return 0 on success.
@@ -148,7 +170,7 @@ struct em_perf_domain *em_cpu_get(int cpu);
 struct em_perf_domain *em_pd_get(struct device *dev);
 int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
 				struct em_data_callback *cb, cpumask_t *span,
-				bool milliwatts);
+				bool microwatts);
 void em_dev_unregister_perf_domain(struct device *dev);
 
 /**
@@ -273,7 +295,7 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd,
 	 *   pd_nrg = ------------------------                       (4)
 	 *                  scale_cpu
 	 */
-	return ps->cost * sum_util / scale_cpu;
+	return em_estimate_energy(ps->cost, sum_util, scale_cpu);
 }
 
 /**
@@ -297,7 +319,7 @@ struct em_data_callback {};
 static inline
 int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
 				struct em_data_callback *cb, cpumask_t *span,
-				bool milliwatts)
+				bool microwatts)
 {
 	return -EINVAL;
 }
diff --git a/include/linux/pm_wakeup.h b/include/linux/pm_wakeup.h
index 196a157456aa..77f4849e3418 100644
--- a/include/linux/pm_wakeup.h
+++ b/include/linux/pm_wakeup.h
@@ -109,7 +109,6 @@ extern struct wakeup_source *wakeup_sources_walk_next(struct wakeup_source *ws);
 extern int device_wakeup_enable(struct device *dev);
 extern int device_wakeup_disable(struct device *dev);
 extern void device_set_wakeup_capable(struct device *dev, bool capable);
-extern int device_init_wakeup(struct device *dev, bool val);
 extern int device_set_wakeup_enable(struct device *dev, bool enable);
 extern void __pm_stay_awake(struct wakeup_source *ws);
 extern void pm_stay_awake(struct device *dev);
@@ -167,13 +166,6 @@ static inline int device_set_wakeup_enable(struct device *dev, bool enable)
 	return 0;
 }
 
-static inline int device_init_wakeup(struct device *dev, bool val)
-{
-	device_set_wakeup_capable(dev, val);
-	device_set_wakeup_enable(dev, val);
-	return 0;
-}
-
 static inline bool device_may_wakeup(struct device *dev)
 {
 	return dev->power.can_wakeup && dev->power.should_wakeup;
@@ -217,4 +209,27 @@ static inline void pm_wakeup_hard_event(struct device *dev)
 	return pm_wakeup_dev_event(dev, 0, true);
 }
 
+/**
+ * device_init_wakeup - Device wakeup initialization.
+ * @dev: Device to handle.
+ * @enable: Whether or not to enable @dev as a wakeup device.
+ *
+ * By default, most devices should leave wakeup disabled.  The exceptions are
+ * devices that everyone expects to be wakeup sources: keyboards, power buttons,
+ * possibly network interfaces, etc.  Also, devices that don't generate their
+ * own wakeup requests but merely forward requests from one bus to another
+ * (like PCI bridges) should have wakeup enabled by default.
+ */
+static inline int device_init_wakeup(struct device *dev, bool enable)
+{
+	if (enable) {
+		device_set_wakeup_capable(dev, true);
+		return device_wakeup_enable(dev);
+	} else {
+		device_wakeup_disable(dev);
+		device_set_wakeup_capable(dev, false);
+		return 0;
+	}
+}
+
 #endif /* _LINUX_PM_WAKEUP_H */
diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index 7f4f9df1b20f..a193884ecf2b 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -60,6 +60,12 @@ struct scmi_clock_info {
 	};
 };
 
+enum scmi_power_scale {
+	SCMI_POWER_BOGOWATTS,
+	SCMI_POWER_MILLIWATTS,
+	SCMI_POWER_MICROWATTS
+};
+
 struct scmi_handle;
 struct scmi_device;
 struct scmi_protocol_handle;
@@ -135,7 +141,7 @@ struct scmi_perf_proto_ops {
 			     unsigned long *rate, unsigned long *power);
 	bool (*fast_switch_possible)(const struct scmi_protocol_handle *ph,
 				     struct device *dev);
-	bool (*power_scale_mw_get)(const struct scmi_protocol_handle *ph);
+	enum scmi_power_scale (*power_scale_get)(const struct scmi_protocol_handle *ph);
 };
 
 /**
diff --git a/include/trace/events/power.h b/include/trace/events/power.h
index af5018aa9517..c708521e4ed5 100644
--- a/include/trace/events/power.h
+++ b/include/trace/events/power.h
@@ -500,6 +500,35 @@ DEFINE_EVENT(dev_pm_qos_request, dev_pm_qos_remove_request,
 
 	TP_ARGS(name, type, new_value)
 );
+
+TRACE_EVENT(guest_halt_poll_ns,
+
+	TP_PROTO(bool grow, unsigned int new, unsigned int old),
+
+	TP_ARGS(grow, new, old),
+
+	TP_STRUCT__entry(
+		__field(bool, grow)
+		__field(unsigned int, new)
+		__field(unsigned int, old)
+	),
+
+	TP_fast_assign(
+		__entry->grow   = grow;
+		__entry->new    = new;
+		__entry->old    = old;
+	),
+
+	TP_printk("halt_poll_ns %u (%s %u)",
+		__entry->new,
+		__entry->grow ? "grow" : "shrink",
+		__entry->old)
+);
+
+#define trace_guest_halt_poll_ns_grow(new, old) \
+	trace_guest_halt_poll_ns(true, new, old)
+#define trace_guest_halt_poll_ns_shrink(new, old) \
+	trace_guest_halt_poll_ns(false, new, old)
 #endif /* _TRACE_POWER_H */
 
 /* This part must be outside protection */