Merge tag 'pm-5.18-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull more power management updates from Rafael Wysocki:
 "These update ARM cpufreq drivers, the OPP (Operating Performance
  Points) library and the power management documentation.

  Specifics:

   - Add per core DVFS support for QCom SoC (Bjorn Andersson), convert
     to yaml binding (Manivannan Sadhasivam) and various other fixes to
     the QCom drivers (Luca Weiss).

   - Add OPP table for imx7s SoC (Denys Drozdov) and minor fixes (Stefan
     Agner).

   - Fix CPPC driver's freq/performance conversions (Pierre Gondois).

   - Minor generic cleanups (Yury Norov).

   - Introduce opp-microwatt property to the OPP core, bindings, etc
     (Lukasz Luba).

   - Convert DT bindings to schema format and various related fixes
     (Yassine Oudjana).

   - Expose OPP's OF node in debugfs (Viresh Kumar).

   - Add Intel uncore frequency scaling documentation file to its
     MAINTAINERS entry (Srinivas Pandruvada).

   - Clean up the AMD P-state driver documentation (Jan Engelhardt)"

* tag 'pm-5.18-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (24 commits)
  Documentation: amd-pstate: grammar and sentence structure updates
  dt-bindings: cpufreq: cpufreq-qcom-hw: Convert to YAML bindings
  dt-bindings: dvfs: Use MediaTek CPUFREQ HW as an example
  Documentation: EM: Describe new registration method using DT
  OPP: Add support of "opp-microwatt" for EM registration
  PM: EM: add macro to set .active_power() callback conditionally
  OPP: Add "opp-microwatt" supporting code
  dt-bindings: opp: Add "opp-microwatt" entry in the OPP
  MAINTAINERS: Add additional file to uncore frequency control
  cpufreq: blocklist Qualcomm sc8280xp and sa8540p in cpufreq-dt-platdev
  cpufreq: qcom-hw: Add support for per-core-dcvs
  dt-bindings: power: avs: qcom,cpr: Convert to DT schema
  arm64: dts: qcom: qcs404: Rename CPU and CPR OPP tables
  arm64: dts: qcom: msm8996: Rename cluster OPP tables
  dt-bindings: opp: Convert qcom-nvmem-cpufreq to DT schema
  dt-bindings: opp: qcom-opp: Convert to DT schema
  arm64: dts: qcom: msm8996-mtp: Add msm8996 compatible
  dt-bindings: arm: qcom: Add msm8996 and apq8096 compatibles
  opp: Expose of-node's name in debugfs
  cpufreq: CPPC: Fix performance/frequency conversion
  ...

9 files changed, 184 insertions, 28 deletions

diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index db17196266e4..82d370ae6a4a 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -303,52 +303,48 @@ static u64 cppc_get_dmi_max_khz(void)
 
 /*
  * If CPPC lowest_freq and nominal_freq registers are exposed then we can
- * use them to convert perf to freq and vice versa
- *
- * If the perf/freq point lies between Nominal and Lowest, we can treat
- * (Low perf, Low freq) and (Nom Perf, Nom freq) as 2D co-ordinates of a line
- * and extrapolate the rest
- * For perf/freq > Nominal, we use the ratio perf:freq at Nominal for conversion
+ * use them to convert perf to freq and vice versa. The conversion is
+ * extrapolated as an affine function passing by the 2 points:
+ *  - (Low perf, Low freq)
+ *  - (Nominal perf, Nominal perf)
  */
 static unsigned int cppc_cpufreq_perf_to_khz(struct cppc_cpudata *cpu_data,
 					     unsigned int perf)
 {
 	struct cppc_perf_caps *caps = &cpu_data->perf_caps;
+	s64 retval, offset = 0;
 	static u64 max_khz;
 	u64 mul, div;
 
 	if (caps->lowest_freq && caps->nominal_freq) {
-		if (perf >= caps->nominal_perf) {
-			mul = caps->nominal_freq;
-			div = caps->nominal_perf;
-		} else {
-			mul = caps->nominal_freq - caps->lowest_freq;
-			div = caps->nominal_perf - caps->lowest_perf;
-		}
+		mul = caps->nominal_freq - caps->lowest_freq;
+		div = caps->nominal_perf - caps->lowest_perf;
+		offset = caps->nominal_freq - div64_u64(caps->nominal_perf * mul, div);
 	} else {
 		if (!max_khz)
 			max_khz = cppc_get_dmi_max_khz();
 		mul = max_khz;
 		div = caps->highest_perf;
 	}
-	return (u64)perf * mul / div;
+
+	retval = offset + div64_u64(perf * mul, div);
+	if (retval >= 0)
+		return retval;
+	return 0;
 }
 
 static unsigned int cppc_cpufreq_khz_to_perf(struct cppc_cpudata *cpu_data,
 					     unsigned int freq)
 {
 	struct cppc_perf_caps *caps = &cpu_data->perf_caps;
+	s64 retval, offset = 0;
 	static u64 max_khz;
 	u64  mul, div;
 
 	if (caps->lowest_freq && caps->nominal_freq) {
-		if (freq >= caps->nominal_freq) {
-			mul = caps->nominal_perf;
-			div = caps->nominal_freq;
-		} else {
-			mul = caps->lowest_perf;
-			div = caps->lowest_freq;
-		}
+		mul = caps->nominal_perf - caps->lowest_perf;
+		div = caps->nominal_freq - caps->lowest_freq;
+		offset = caps->nominal_perf - div64_u64(caps->nominal_freq * mul, div);
 	} else {
 		if (!max_khz)
 			max_khz = cppc_get_dmi_max_khz();
@@ -356,7 +352,10 @@ static unsigned int cppc_cpufreq_khz_to_perf(struct cppc_cpudata *cpu_data,
 		div = max_khz;
 	}
 
-	return (u64)freq * mul / div;
+	retval = offset + div64_u64(freq * mul, div);
+	if (retval >= 0)
+		return retval;
+	return 0;
 }
 
 static int cppc_cpufreq_set_target(struct cpufreq_policy *policy,
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index ca1d103ec449..96de1536e1cb 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -110,6 +110,7 @@ static const struct of_device_id blocklist[] __initconst = {
 
 	{ .compatible = "fsl,imx7ulp", },
 	{ .compatible = "fsl,imx7d", },
+	{ .compatible = "fsl,imx7s", },
 	{ .compatible = "fsl,imx8mq", },
 	{ .compatible = "fsl,imx8mm", },
 	{ .compatible = "fsl,imx8mn", },
@@ -138,9 +139,11 @@ static const struct of_device_id blocklist[] __initconst = {
 	{ .compatible = "qcom,msm8996", },
 	{ .compatible = "qcom,qcs404", },
 	{ .compatible = "qcom,sa8155p" },
+	{ .compatible = "qcom,sa8540p" },
 	{ .compatible = "qcom,sc7180", },
 	{ .compatible = "qcom,sc7280", },
 	{ .compatible = "qcom,sc8180x", },
+	{ .compatible = "qcom,sc8280xp", },
 	{ .compatible = "qcom,sdm845", },
 	{ .compatible = "qcom,sm6350", },
 	{ .compatible = "qcom,sm8150", },
diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
index effbb680b453..f9d593ff4718 100644
--- a/drivers/cpufreq/qcom-cpufreq-hw.c
+++ b/drivers/cpufreq/qcom-cpufreq-hw.c
@@ -28,6 +28,7 @@
 
 struct qcom_cpufreq_soc_data {
 	u32 reg_enable;
+	u32 reg_dcvs_ctrl;
 	u32 reg_freq_lut;
 	u32 reg_volt_lut;
 	u32 reg_current_vote;
@@ -50,6 +51,8 @@ struct qcom_cpufreq_data {
 	bool cancel_throttle;
 	struct delayed_work throttle_work;
 	struct cpufreq_policy *policy;
+
+	bool per_core_dcvs;
 };
 
 static unsigned long cpu_hw_rate, xo_rate;
@@ -102,9 +105,14 @@ static int qcom_cpufreq_hw_target_index(struct cpufreq_policy *policy,
 	struct qcom_cpufreq_data *data = policy->driver_data;
 	const struct qcom_cpufreq_soc_data *soc_data = data->soc_data;
 	unsigned long freq = policy->freq_table[index].frequency;
+	unsigned int i;
 
 	writel_relaxed(index, data->base + soc_data->reg_perf_state);
 
+	if (data->per_core_dcvs)
+		for (i = 1; i < cpumask_weight(policy->related_cpus); i++)
+			writel_relaxed(index, data->base + soc_data->reg_perf_state + i * 4);
+
 	if (icc_scaling_enabled)
 		qcom_cpufreq_set_bw(policy, freq);
 
@@ -137,10 +145,15 @@ static unsigned int qcom_cpufreq_hw_fast_switch(struct cpufreq_policy *policy,
 	struct qcom_cpufreq_data *data = policy->driver_data;
 	const struct qcom_cpufreq_soc_data *soc_data = data->soc_data;
 	unsigned int index;
+	unsigned int i;
 
 	index = policy->cached_resolved_idx;
 	writel_relaxed(index, data->base + soc_data->reg_perf_state);
 
+	if (data->per_core_dcvs)
+		for (i = 1; i < cpumask_weight(policy->related_cpus); i++)
+			writel_relaxed(index, data->base + soc_data->reg_perf_state + i * 4);
+
 	return policy->freq_table[index].frequency;
 }
 
@@ -342,6 +355,7 @@ static irqreturn_t qcom_lmh_dcvs_handle_irq(int irq, void *data)
 
 static const struct qcom_cpufreq_soc_data qcom_soc_data = {
 	.reg_enable = 0x0,
+	.reg_dcvs_ctrl = 0xbc,
 	.reg_freq_lut = 0x110,
 	.reg_volt_lut = 0x114,
 	.reg_current_vote = 0x704,
@@ -351,6 +365,7 @@ static const struct qcom_cpufreq_soc_data qcom_soc_data = {
 
 static const struct qcom_cpufreq_soc_data epss_soc_data = {
 	.reg_enable = 0x0,
+	.reg_dcvs_ctrl = 0xb0,
 	.reg_freq_lut = 0x100,
 	.reg_volt_lut = 0x200,
 	.reg_perf_state = 0x320,
@@ -481,8 +496,11 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy)
 		goto error;
 	}
 
+	if (readl_relaxed(base + data->soc_data->reg_dcvs_ctrl) & 0x1)
+		data->per_core_dcvs = true;
+
 	qcom_get_related_cpus(index, policy->cpus);
-	if (!cpumask_weight(policy->cpus)) {
+	if (cpumask_empty(policy->cpus)) {
 		dev_err(dev, "Domain-%d failed to get related CPUs\n", index);
 		ret = -ENOENT;
 		goto error;
diff --git a/drivers/cpufreq/qcom-cpufreq-nvmem.c b/drivers/cpufreq/qcom-cpufreq-nvmem.c
index d1744b5d9619..6dfa86971a75 100644
--- a/drivers/cpufreq/qcom-cpufreq-nvmem.c
+++ b/drivers/cpufreq/qcom-cpufreq-nvmem.c
@@ -130,7 +130,7 @@ static void get_krait_bin_format_b(struct device *cpu_dev,
 	}
 
 	/* Check PVS_BLOW_STATUS */
-	pte_efuse = *(((u32 *)buf) + 4);
+	pte_efuse = *(((u32 *)buf) + 1);
 	pte_efuse &= BIT(21);
 	if (pte_efuse) {
 		dev_dbg(cpu_dev, "PVS bin: %d\n", *pvs);
diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c
index 1e0cd4d165f0..919fa6e3f462 100644
--- a/drivers/cpufreq/scmi-cpufreq.c
+++ b/drivers/cpufreq/scmi-cpufreq.c
@@ -154,7 +154,7 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 	 * table and opp-shared.
 	 */
 	ret = dev_pm_opp_of_get_sharing_cpus(cpu_dev, priv->opp_shared_cpus);
-	if (ret || !cpumask_weight(priv->opp_shared_cpus)) {
+	if (ret || cpumask_empty(priv->opp_shared_cpus)) {
 		/*
 		 * Either opp-table is not set or no opp-shared was found.
 		 * Use the CPU mask from SCMI to designate CPUs sharing an OPP
diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index 3057beabd370..740407252298 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -114,6 +114,31 @@ unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp)
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_voltage);
 
 /**
+ * dev_pm_opp_get_power() - Gets the power corresponding to an opp
+ * @opp:	opp for which power has to be returned for
+ *
+ * Return: power in micro watt corresponding to the opp, else
+ * return 0
+ *
+ * This is useful only for devices with single power supply.
+ */
+unsigned long dev_pm_opp_get_power(struct dev_pm_opp *opp)
+{
+	unsigned long opp_power = 0;
+	int i;
+
+	if (IS_ERR_OR_NULL(opp)) {
+		pr_err("%s: Invalid parameters\n", __func__);
+		return 0;
+	}
+	for (i = 0; i < opp->opp_table->regulator_count; i++)
+		opp_power += opp->supplies[i].u_watt;
+
+	return opp_power;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_power);
+
+/**
  * dev_pm_opp_get_freq() - Gets the frequency corresponding to an available opp
  * @opp:	opp for which frequency has to be returned for
  *
diff --git a/drivers/opp/debugfs.c b/drivers/opp/debugfs.c
index 596c185b5dda..3fcc1f97f2d1 100644
--- a/drivers/opp/debugfs.c
+++ b/drivers/opp/debugfs.c
@@ -10,6 +10,7 @@
 #include <linux/debugfs.h>
 #include <linux/device.h>
 #include <linux/err.h>
+#include <linux/of.h>
 #include <linux/init.h>
 #include <linux/limits.h>
 #include <linux/slab.h>
@@ -99,6 +100,9 @@ static void opp_debug_create_supplies(struct dev_pm_opp *opp,
 
 		debugfs_create_ulong("u_amp", S_IRUGO, d,
 				     &opp->supplies[i].u_amp);
+
+		debugfs_create_ulong("u_watt", S_IRUGO, d,
+				     &opp->supplies[i].u_watt);
 	}
 }
 
@@ -131,9 +135,13 @@ void opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table)
 	debugfs_create_bool("suspend", S_IRUGO, d, &opp->suspend);
 	debugfs_create_u32("performance_state", S_IRUGO, d, &opp->pstate);
 	debugfs_create_ulong("rate_hz", S_IRUGO, d, &opp->rate);
+	debugfs_create_u32("level", S_IRUGO, d, &opp->level);
 	debugfs_create_ulong("clock_latency_ns", S_IRUGO, d,
 			     &opp->clock_latency_ns);
 
+	opp->of_name = of_node_full_name(opp->np);
+	debugfs_create_str("of_name", S_IRUGO, d, (char **)&opp->of_name);
+
 	opp_debug_create_supplies(opp, opp_table, d);
 	opp_debug_create_bw(opp, opp_table, d);
 
diff --git a/drivers/opp/of.c b/drivers/opp/of.c
index 2f40afa4e65c..440ab5a03df9 100644
--- a/drivers/opp/of.c
+++ b/drivers/opp/of.c
@@ -575,8 +575,9 @@ static bool _opp_is_supported(struct device *dev, struct opp_table *opp_table,
 static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev,
 			      struct opp_table *opp_table)
 {
-	u32 *microvolt, *microamp = NULL;
-	int supplies = opp_table->regulator_count, vcount, icount, ret, i, j;
+	u32 *microvolt, *microamp = NULL, *microwatt = NULL;
+	int supplies = opp_table->regulator_count;
+	int vcount, icount, pcount, ret, i, j;
 	struct property *prop = NULL;
 	char name[NAME_MAX];
 
@@ -688,6 +689,43 @@ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev,
 		}
 	}
 
+	/* Search for "opp-microwatt" */
+	sprintf(name, "opp-microwatt");
+	prop = of_find_property(opp->np, name, NULL);
+
+	if (prop) {
+		pcount = of_property_count_u32_elems(opp->np, name);
+		if (pcount < 0) {
+			dev_err(dev, "%s: Invalid %s property (%d)\n", __func__,
+				name, pcount);
+			ret = pcount;
+			goto free_microamp;
+		}
+
+		if (pcount != supplies) {
+			dev_err(dev, "%s: Invalid number of elements in %s property (%d) with supplies (%d)\n",
+				__func__, name, pcount, supplies);
+			ret = -EINVAL;
+			goto free_microamp;
+		}
+
+		microwatt = kmalloc_array(pcount, sizeof(*microwatt),
+					  GFP_KERNEL);
+		if (!microwatt) {
+			ret = -EINVAL;
+			goto free_microamp;
+		}
+
+		ret = of_property_read_u32_array(opp->np, name, microwatt,
+						 pcount);
+		if (ret) {
+			dev_err(dev, "%s: error parsing %s: %d\n", __func__,
+				name, ret);
+			ret = -EINVAL;
+			goto free_microwatt;
+		}
+	}
+
 	for (i = 0, j = 0; i < supplies; i++) {
 		opp->supplies[i].u_volt = microvolt[j++];
 
@@ -701,8 +739,13 @@ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev,
 
 		if (microamp)
 			opp->supplies[i].u_amp = microamp[i];
+
+		if (microwatt)
+			opp->supplies[i].u_watt = microwatt[i];
 	}
 
+free_microwatt:
+	kfree(microwatt);
 free_microamp:
 	kfree(microamp);
 free_microvolt:
@@ -1397,6 +1440,38 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_of_node);
 
 /*
  * Callback function provided to the Energy Model framework upon registration.
+ * It provides the power used by @dev at @kHz if it is the frequency of an
+ * existing OPP, or at the frequency of the first OPP above @kHz otherwise
+ * (see dev_pm_opp_find_freq_ceil()). This function updates @kHz to the ceiled
+ * frequency and @mW to the associated power.
+ *
+ * Returns 0 on success or a proper -EINVAL value in case of error.
+ */
+static int __maybe_unused
+_get_dt_power(unsigned long *mW, unsigned long *kHz, struct device *dev)
+{
+	struct dev_pm_opp *opp;
+	unsigned long opp_freq, opp_power;
+
+	/* Find the right frequency and related OPP */
+	opp_freq = *kHz * 1000;
+	opp = dev_pm_opp_find_freq_ceil(dev, &opp_freq);
+	if (IS_ERR(opp))
+		return -EINVAL;
+
+	opp_power = dev_pm_opp_get_power(opp);
+	dev_pm_opp_put(opp);
+	if (!opp_power)
+		return -EINVAL;
+
+	*kHz = opp_freq / 1000;
+	*mW = opp_power / 1000;
+
+	return 0;
+}
+
+/*
+ * Callback function provided to the Energy Model framework upon registration.
  * This computes the power estimated by @dev at @kHz if it is the frequency
  * of an existing OPP, or at the frequency of the first OPP above @kHz otherwise
  * (see dev_pm_opp_find_freq_ceil()). This function updates @kHz to the ceiled
@@ -1445,6 +1520,24 @@ static int __maybe_unused _get_power(unsigned long *mW, unsigned long *kHz,
 	return 0;
 }
 
+static bool _of_has_opp_microwatt_property(struct device *dev)
+{
+	unsigned long power, freq = 0;
+	struct dev_pm_opp *opp;
+
+	/* Check if at least one OPP has needed property */
+	opp = dev_pm_opp_find_freq_ceil(dev, &freq);
+	if (IS_ERR(opp))
+		return false;
+
+	power = dev_pm_opp_get_power(opp);
+	dev_pm_opp_put(opp);
+	if (!power)
+		return false;
+
+	return true;
+}
+
 /**
  * dev_pm_opp_of_register_em() - Attempt to register an Energy Model
  * @dev		: Device for which an Energy Model has to be registered
@@ -1458,7 +1551,7 @@ static int __maybe_unused _get_power(unsigned long *mW, unsigned long *kHz,
  */
 int dev_pm_opp_of_register_em(struct device *dev, struct cpumask *cpus)
 {
-	struct em_data_callback em_cb = EM_DATA_CB(_get_power);
+	struct em_data_callback em_cb;
 	struct device_node *np;
 	int ret, nr_opp;
 	u32 cap;
@@ -1474,6 +1567,12 @@ int dev_pm_opp_of_register_em(struct device *dev, struct cpumask *cpus)
 		goto failed;
 	}
 
+	/* First, try to find more precised Energy Model in DT */
+	if (_of_has_opp_microwatt_property(dev)) {
+		EM_SET_ACTIVE_POWER_CB(em_cb, _get_dt_power);
+		goto register_em;
+	}
+
 	np = of_node_get(dev->of_node);
 	if (!np) {
 		ret = -EINVAL;
@@ -1495,6 +1594,9 @@ int dev_pm_opp_of_register_em(struct device *dev, struct cpumask *cpus)
 		goto failed;
 	}
 
+	EM_SET_ACTIVE_POWER_CB(em_cb, _get_power);
+
+register_em:
 	ret = em_dev_register_perf_domain(dev, nr_opp, &em_cb, cpus, true);
 	if (ret)
 		goto failed;
diff --git a/drivers/opp/opp.h b/drivers/opp/opp.h
index 407c3bfe51d9..45e3a55239a1 100644
--- a/drivers/opp/opp.h
+++ b/drivers/opp/opp.h
@@ -96,6 +96,7 @@ struct dev_pm_opp {
 
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *dentry;
+	const char *of_name;
 #endif
 };