cpufreq: intel_pstate: Support highest performance change interrupt

On some systems, the HWP (Hardware P-states) highest performance level
can change from the value set at boot-up. This behavior can lead to two
issues:

- The 'cpuinfo_max_freq' within the 'cpufreq' sysfs will not reflect
the CPU's highest achievable performance.
- Even if the CPU's highest performance level is increased after booting,
the CPU may not reach the full expected performance.

The availability of this feature is indicated by the CPUID instruction:
if CPUID[6].EAX[15] is set to 1, the feature is supported. When supported,
setting bit 2 of the MSR_HWP_INTERRUPT register enables notifications of
the highest performance level changes. Therefore, as part of enabling the
HWP interrupt, bit 2 of the MSR_HWP_INTERRUPT should also be set when this
feature is supported.

Upon a change in the highest performance level, a new HWP interrupt is
generated, with bit 3 of the MSR_HWP_STATUS register set, and the
MSR_HWP_CAPABILITIES register is updated with the new highest performance
limit.

The processing of the interrupt is the same as the guaranteed performance
change. Notify change to cpufreq core and update MSR_HWP_REQUEST with new
performance limits.

The current driver implementation already takes care of the highest
performance change as part of:
commit dfeeedc ("cpufreq: intel_pstate: Update cpuinfo.max_freq
on HWP_CAP changes")

For example:
Before highest performance change interrupt:
cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_max_freq
3700000
cat /sys/devices/system/cpu/cpu0/cpufreq/cpuinfo_max_freq
3700000

After highest performance changes interrupt:
cat /sys/devices/system/cpu/cpu0/cpufreq/cpuinfo_max_freq
3900000
cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_max_freq
3900000

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Link: https://patch.msgid.link/20240624161109.1427640-3-srinivas.pandruvada@linux.intel.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

Author: spandruvada

drivers/cpufreq/intel_pstate.c

@@ -1626,17 +1626,24 @@ static void intel_pstate_notify_work(struct work_struct *work)
 static DEFINE_SPINLOCK(hwp_notify_lock);
 static cpumask_t hwp_intr_enable_mask;
 
+#define HWP_GUARANTEED_PERF_CHANGE_STATUS      BIT(0)
+#define HWP_HIGHEST_PERF_CHANGE_STATUS         BIT(3)
+
 void notify_hwp_interrupt(void)
 {
 	unsigned int this_cpu = smp_processor_id();
+	u64 value, status_mask;
 	unsigned long flags;
-	u64 value;
 
 	if (!hwp_active || !cpu_feature_enabled(X86_FEATURE_HWP_NOTIFY))
 		return;
 
+	status_mask = HWP_GUARANTEED_PERF_CHANGE_STATUS;
+	if (cpu_feature_enabled(X86_FEATURE_HWP_HIGHEST_PERF_CHANGE))
+		status_mask |= HWP_HIGHEST_PERF_CHANGE_STATUS;
+
 	rdmsrl_safe(MSR_HWP_STATUS, &value);
-	if (!(value & 0x01))
+	if (!(value & status_mask))
 		return;
 
 	spin_lock_irqsave(&hwp_notify_lock, flags);
@@ -1674,17 +1681,25 @@ static void intel_pstate_disable_hwp_interrupt(struct cpudata *cpudata)
 		cancel_delayed_work_sync(&cpudata->hwp_notify_work);
 }
 
+#define HWP_GUARANTEED_PERF_CHANGE_REQ BIT(0)
+#define HWP_HIGHEST_PERF_CHANGE_REQ    BIT(2)
+
 static void intel_pstate_enable_hwp_interrupt(struct cpudata *cpudata)
 {
-	/* Enable HWP notification interrupt for guaranteed performance change */
+	/* Enable HWP notification interrupt for performance change */
 	if (boot_cpu_has(X86_FEATURE_HWP_NOTIFY)) {
+		u64 interrupt_mask = HWP_GUARANTEED_PERF_CHANGE_REQ;
+
 		spin_lock_irq(&hwp_notify_lock);
 		INIT_DELAYED_WORK(&cpudata->hwp_notify_work, intel_pstate_notify_work);
 		cpumask_set_cpu(cpudata->cpu, &hwp_intr_enable_mask);
 		spin_unlock_irq(&hwp_notify_lock);
 
+		if (cpu_feature_enabled(X86_FEATURE_HWP_HIGHEST_PERF_CHANGE))
+			interrupt_mask |= HWP_HIGHEST_PERF_CHANGE_REQ;
+
 		/* wrmsrl_on_cpu has to be outside spinlock as this can result in IPC */
-		wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x01);
+		wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, interrupt_mask);
 		wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_STATUS, 0);
 	}
 }