Merge tag 'pm-5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These address some PCI device power management issues, add new
  hardware support to the RAPL power capping driver, add HWP guaranteed
  performance change notification support to the intel_pstate driver,
  replace deprecated CPU-hotplug functions in a few places, update CPU
  PM notifiers to use raw spinlocks, update the PM domains framework
  (new DT property support, Kconfig fix), do a couple of cleanups in
  code related to system sleep, and improve the energy model and the
  schedutil cpufreq governor.

  Specifics:

   - Address 3 PCI device power management issues (Rafael Wysocki).

   - Add Power Limit4 support for Alder Lake to the Intel RAPL power
     capping driver (Sumeet Pawnikar).

   - Add HWP guaranteed performance change notification support to the
     intel_pstate driver (Srinivas Pandruvada).

   - Replace deprecated CPU-hotplug functions in code related to power
     management (Sebastian Andrzej Siewior).

   - Update CPU PM notifiers to use raw spinlocks (Valentin Schneider).

   - Add support for 'required-opps' DT property to the generic power
     domains (genpd) framework and use this property for I2C on ARM64
     sc7180 (Rajendra Nayak).

   - Fix Kconfig issue related to genpd (Geert Uytterhoeven).

   - Increase energy calculation precision in the Energy Model (Lukasz
     Luba).

   - Fix kobject deletion in the exit code of the schedutil cpufreq
     governor (Kevin Hao).

   - Unmark some functions as kernel-doc in the PM core to avoid
     false-positive documentation build warnings (Randy Dunlap).

   - Check RTC features instead of ops in suspend_test Alexandre
     Belloni)"

* tag 'pm-5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  PM: domains: Fix domain attach for CONFIG_PM_OPP=n
  powercap: Add Power Limit4 support for Alder Lake SoC
  cpufreq: intel_pstate: Process HWP Guaranteed change notification
  thermal: intel: Allow processing of HWP interrupt
  notifier: Remove atomic_notifier_call_chain_robust()
  PM: cpu: Make notifier chain use a raw_spinlock_t
  PM: sleep: unmark 'state' functions as kernel-doc
  arm64: dts: sc7180: Add required-opps for i2c
  PM: domains: Add support for 'required-opps' to set default perf state
  opp: Don't print an error if required-opps is missing
  cpufreq: schedutil: Use kobject release() method to free sugov_tunables
  PM: EM: Increase energy calculation precision
  PM: sleep: check RTC features instead of ops in suspend_test
  PM: sleep: s2idle: Replace deprecated CPU-hotplug functions
  cpufreq: Replace deprecated CPU-hotplug functions
  powercap: intel_rapl: Replace deprecated CPU-hotplug functions
  PCI: PM: Enable PME if it can be signaled from D3cold
  PCI: PM: Avoid forcing PCI_D0 for wakeup reasons inconsistently
  PCI: Use pci_update_current_state() in pci_enable_device_flags()

1 files changed, 41 insertions, 2 deletions

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index bb4549959b11..b4ffe6c8a0d0 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -32,6 +32,7 @@
 #include <asm/cpu_device_id.h>
 #include <asm/cpufeature.h>
 #include <asm/intel-family.h>
+#include "../drivers/thermal/intel/thermal_interrupt.h"
 
 #define INTEL_PSTATE_SAMPLING_INTERVAL	(10 * NSEC_PER_MSEC)
 
@@ -219,6 +220,7 @@ struct global_params {
  * @sched_flags:	Store scheduler flags for possible cross CPU update
  * @hwp_boost_min:	Last HWP boosted min performance
  * @suspended:		Whether or not the driver has been suspended.
+ * @hwp_notify_work:	workqueue for HWP notifications.
  *
  * This structure stores per CPU instance data for all CPUs.
  */
@@ -257,6 +259,7 @@ struct cpudata {
 	unsigned int sched_flags;
 	u32 hwp_boost_min;
 	bool suspended;
+	struct delayed_work hwp_notify_work;
 };
 
 static struct cpudata **all_cpu_data;
@@ -1625,6 +1628,40 @@ static void intel_pstate_sysfs_hide_hwp_dynamic_boost(void)
 
 /************************** sysfs end ************************/
 
+static void intel_pstate_notify_work(struct work_struct *work)
+{
+	mutex_lock(&intel_pstate_driver_lock);
+	cpufreq_update_policy(smp_processor_id());
+	wrmsrl(MSR_HWP_STATUS, 0);
+	mutex_unlock(&intel_pstate_driver_lock);
+}
+
+void notify_hwp_interrupt(void)
+{
+	unsigned int this_cpu = smp_processor_id();
+	struct cpudata *cpudata;
+	u64 value;
+
+	if (!hwp_active || !boot_cpu_has(X86_FEATURE_HWP_NOTIFY))
+		return;
+
+	rdmsrl(MSR_HWP_STATUS, value);
+	if (!(value & 0x01))
+		return;
+
+	cpudata = all_cpu_data[this_cpu];
+	schedule_delayed_work_on(this_cpu, &cpudata->hwp_notify_work, msecs_to_jiffies(10));
+}
+
+static void intel_pstate_enable_hwp_interrupt(struct cpudata *cpudata)
+{
+	/* Enable HWP notification interrupt for guaranteed performance change */
+	if (boot_cpu_has(X86_FEATURE_HWP_NOTIFY)) {
+		INIT_DELAYED_WORK(&cpudata->hwp_notify_work, intel_pstate_notify_work);
+		wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x01);
+	}
+}
+
 static void intel_pstate_hwp_enable(struct cpudata *cpudata)
 {
 	/* First disable HWP notification interrupt as we don't process them */
@@ -1634,6 +1671,8 @@ static void intel_pstate_hwp_enable(struct cpudata *cpudata)
 	wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1);
 	if (cpudata->epp_default == -EINVAL)
 		cpudata->epp_default = intel_pstate_get_epp(cpudata, 0);
+
+	intel_pstate_enable_hwp_interrupt(cpudata);
 }
 
 static int atom_get_min_pstate(void)
@@ -2969,7 +3008,7 @@ static void intel_pstate_driver_cleanup(void)
 {
 	unsigned int cpu;
 
-	get_online_cpus();
+	cpus_read_lock();
 	for_each_online_cpu(cpu) {
 		if (all_cpu_data[cpu]) {
 			if (intel_pstate_driver == &intel_pstate)
@@ -2979,7 +3018,7 @@ static void intel_pstate_driver_cleanup(void)
 			all_cpu_data[cpu] = NULL;
 		}
 	}
-	put_online_cpus();
+	cpus_read_unlock();
 
 	intel_pstate_driver = NULL;
 }