Merge tag 'pm-5.18-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management fixes from Rafael Wysocki:
 "These fix up recent intel_idle driver changes and fix some ARM cpufreq
  driver issues.

  Specifics:

   - Fix issues with the Qualcomm's cpufreq driver (Dmitry Baryshkov,
     Vladimir Zapolskiy).

   - Fix memory leak with the Sun501 driver (Xiaobing Luo).

   - Make intel_idle enable C1E promotion on all CPUs when C1E is
     preferred to C1 (Artem Bityutskiy).

   - Make C6 optimization on Sapphire Rapids added recently work as
     expected if both C1E and C1 are "preferred" (Artem Bityutskiy)"

* tag 'pm-5.18-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  intel_idle: Fix SPR C6 optimization
  intel_idle: Fix the 'preferred_cstates' module parameter
  cpufreq: qcom-cpufreq-hw: Clear dcvs interrupts
  cpufreq: fix memory leak in sun50i_cpufreq_nvmem_probe
  cpufreq: qcom-cpufreq-hw: Fix throttle frequency value on EPSS platforms
  cpufreq: qcom-hw: provide online/offline operations
  cpufreq: qcom-hw: fix the opp entries refcounting
  cpufreq: qcom-hw: fix the race between LMH worker and cpuhp
  cpufreq: qcom-hw: drop affinity hint before freeing the IRQ

Author: torvalds

drivers/cpufreq/qcom-cpufreq-hw.c

@@ -24,13 +24,17 @@
 #define CLK_HW_DIV			2
 #define LUT_TURBO_IND			1
 
+#define GT_IRQ_STATUS			BIT(2)
+
 #define HZ_PER_KHZ			1000
 
 struct qcom_cpufreq_soc_data {
 	u32 reg_enable;
+	u32 reg_domain_state;
 	u32 reg_dcvs_ctrl;
 	u32 reg_freq_lut;
 	u32 reg_volt_lut;
+	u32 reg_intr_clr;
 	u32 reg_current_vote;
 	u32 reg_perf_state;
 	u8 lut_row_size;
@@ -280,37 +284,46 @@ static void qcom_get_related_cpus(int index, struct cpumask *m)
 	}
 }
 
-static unsigned int qcom_lmh_get_throttle_freq(struct qcom_cpufreq_data *data)
+static unsigned long qcom_lmh_get_throttle_freq(struct qcom_cpufreq_data *data)
 {
-	unsigned int val = readl_relaxed(data->base + data->soc_data->reg_current_vote);
+	unsigned int lval;
+
+	if (data->soc_data->reg_current_vote)
+		lval = readl_relaxed(data->base + data->soc_data->reg_current_vote) & 0x3ff;
+	else
+		lval = readl_relaxed(data->base + data->soc_data->reg_domain_state) & 0xff;
 
-	return (val & 0x3FF) * 19200;
+	return lval * xo_rate;
 }
 
 static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data)
 {
 	struct cpufreq_policy *policy = data->policy;
-	int cpu = cpumask_first(policy->cpus);
+	int cpu = cpumask_first(policy->related_cpus);
 	struct device *dev = get_cpu_device(cpu);
 	unsigned long freq_hz, throttled_freq;
 	struct dev_pm_opp *opp;
-	unsigned int freq;
 
 	/*
 	 * Get the h/w throttled frequency, normalize it using the
 	 * registered opp table and use it to calculate thermal pressure.
 	 */
-	freq = qcom_lmh_get_throttle_freq(data);
-	freq_hz = freq * HZ_PER_KHZ;
+	freq_hz = qcom_lmh_get_throttle_freq(data);
 
 	opp = dev_pm_opp_find_freq_floor(dev, &freq_hz);
 	if (IS_ERR(opp) && PTR_ERR(opp) == -ERANGE)
-		dev_pm_opp_find_freq_ceil(dev, &freq_hz);
+		opp = dev_pm_opp_find_freq_ceil(dev, &freq_hz);
+
+	if (IS_ERR(opp)) {
+		dev_warn(dev, "Can't find the OPP for throttling: %pe!\n", opp);
+	} else {
+		throttled_freq = freq_hz / HZ_PER_KHZ;
 
-	throttled_freq = freq_hz / HZ_PER_KHZ;
+		/* Update thermal pressure (the boost frequencies are accepted) */
+		arch_update_thermal_pressure(policy->related_cpus, throttled_freq);
 
-	/* Update thermal pressure (the boost frequencies are accepted) */
-	arch_update_thermal_pressure(policy->related_cpus, throttled_freq);
+		dev_pm_opp_put(opp);
+	}
 
 	/*
 	 * In the unlikely case policy is unregistered do not enable
@@ -350,6 +363,10 @@ static irqreturn_t qcom_lmh_dcvs_handle_irq(int irq, void *data)
 	disable_irq_nosync(c_data->throttle_irq);
 	schedule_delayed_work(&c_data->throttle_work, 0);
 
+	if (c_data->soc_data->reg_intr_clr)
+		writel_relaxed(GT_IRQ_STATUS,
+			       c_data->base + c_data->soc_data->reg_intr_clr);
+
 	return IRQ_HANDLED;
 }
 
@@ -365,9 +382,11 @@ static const struct qcom_cpufreq_soc_data qcom_soc_data = {
 
 static const struct qcom_cpufreq_soc_data epss_soc_data = {
 	.reg_enable = 0x0,
+	.reg_domain_state = 0x20,
 	.reg_dcvs_ctrl = 0xb0,
 	.reg_freq_lut = 0x100,
 	.reg_volt_lut = 0x200,
+	.reg_intr_clr = 0x308,
 	.reg_perf_state = 0x320,
 	.lut_row_size = 4,
 };
@@ -417,16 +436,39 @@ static int qcom_cpufreq_hw_lmh_init(struct cpufreq_policy *policy, int index)
 	return 0;
 }
 
-static void qcom_cpufreq_hw_lmh_exit(struct qcom_cpufreq_data *data)
+static int qcom_cpufreq_hw_cpu_online(struct cpufreq_policy *policy)
+{
+	struct qcom_cpufreq_data *data = policy->driver_data;
+	struct platform_device *pdev = cpufreq_get_driver_data();
+	int ret;
+
+	ret = irq_set_affinity_hint(data->throttle_irq, policy->cpus);
+	if (ret)
+		dev_err(&pdev->dev, "Failed to set CPU affinity of %s[%d]\n",
+			data->irq_name, data->throttle_irq);
+
+	return ret;
+}
+
+static int qcom_cpufreq_hw_cpu_offline(struct cpufreq_policy *policy)
 {
+	struct qcom_cpufreq_data *data = policy->driver_data;
+
 	if (data->throttle_irq <= 0)
-		return;
+		return 0;
 
 	mutex_lock(&data->throttle_lock);
 	data->cancel_throttle = true;
 	mutex_unlock(&data->throttle_lock);
 
 	cancel_delayed_work_sync(&data->throttle_work);
+	irq_set_affinity_hint(data->throttle_irq, NULL);
+
+	return 0;
+}
+
+static void qcom_cpufreq_hw_lmh_exit(struct qcom_cpufreq_data *data)
+{
 	free_irq(data->throttle_irq, data);
 }
 
@@ -583,6 +625,8 @@ static struct cpufreq_driver cpufreq_qcom_hw_driver = {
 	.get		= qcom_cpufreq_hw_get,
 	.init		= qcom_cpufreq_hw_cpu_init,
 	.exit		= qcom_cpufreq_hw_cpu_exit,
+	.online		= qcom_cpufreq_hw_cpu_online,
+	.offline	= qcom_cpufreq_hw_cpu_offline,
 	.register_em	= cpufreq_register_em_with_opp,
 	.fast_switch    = qcom_cpufreq_hw_fast_switch,
 	.name		= "qcom-cpufreq-hw",

drivers/cpufreq/sun50i-cpufreq-nvmem.c

@@ -98,8 +98,10 @@ static int sun50i_cpufreq_nvmem_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	ret = sun50i_cpufreq_get_efuse(&speed);
-	if (ret)
+	if (ret) {
+		kfree(opp_tables);
 		return ret;
+	}
 
 	snprintf(name, MAX_NAME_LEN, "speed%d", speed);
 

drivers/idle/intel_idle.c

@@ -69,7 +69,12 @@ static unsigned int preferred_states_mask;
 static struct cpuidle_device __percpu *intel_idle_cpuidle_devices;
 
 static unsigned long auto_demotion_disable_flags;
-static bool disable_promotion_to_c1e;
+
+static enum {
+	C1E_PROMOTION_PRESERVE,
+	C1E_PROMOTION_ENABLE,
+	C1E_PROMOTION_DISABLE
+} c1e_promotion = C1E_PROMOTION_PRESERVE;
 
 struct idle_cpu {
 	struct cpuidle_state *state_table;
@@ -1398,8 +1403,6 @@ static inline void intel_idle_init_cstates_acpi(struct cpuidle_driver *drv) { }
 static inline bool intel_idle_off_by_default(u32 mwait_hint) { return false; }
 #endif /* !CONFIG_ACPI_PROCESSOR_CSTATE */
 
-static void c1e_promotion_enable(void);
-
 /**
  * ivt_idle_state_table_update - Tune the idle states table for Ivy Town.
  *
@@ -1578,17 +1581,14 @@ static void __init spr_idle_state_table_update(void)
 	unsigned long long msr;
 
 	/* Check if user prefers C1E over C1. */
-	if (preferred_states_mask & BIT(2)) {
-		if (preferred_states_mask & BIT(1))
-			/* Both can't be enabled, stick to the defaults. */
-			return;
-
+	if ((preferred_states_mask & BIT(2)) &&
+	    !(preferred_states_mask & BIT(1))) {
+		/* Disable C1 and enable C1E. */
 		spr_cstates[0].flags |= CPUIDLE_FLAG_UNUSABLE;
 		spr_cstates[1].flags &= ~CPUIDLE_FLAG_UNUSABLE;
 
 		/* Enable C1E using the "C1E promotion" bit. */
-		c1e_promotion_enable();
-		disable_promotion_to_c1e = false;
+		c1e_promotion = C1E_PROMOTION_ENABLE;
 	}
 
 	/*
@@ -1754,7 +1754,9 @@ static int intel_idle_cpu_init(unsigned int cpu)
 	if (auto_demotion_disable_flags)
 		auto_demotion_disable();
 
-	if (disable_promotion_to_c1e)
+	if (c1e_promotion == C1E_PROMOTION_ENABLE)
+		c1e_promotion_enable();
+	else if (c1e_promotion == C1E_PROMOTION_DISABLE)
 		c1e_promotion_disable();
 
 	return 0;
@@ -1833,7 +1835,8 @@ static int __init intel_idle_init(void)
 	if (icpu) {
 		cpuidle_state_table = icpu->state_table;
 		auto_demotion_disable_flags = icpu->auto_demotion_disable_flags;
-		disable_promotion_to_c1e = icpu->disable_promotion_to_c1e;
+		if (icpu->disable_promotion_to_c1e)
+			c1e_promotion = C1E_PROMOTION_DISABLE;
 		if (icpu->use_acpi || force_use_acpi)
 			intel_idle_acpi_cst_extract();
 	} else if (!intel_idle_acpi_cst_extract()) {