Merge tag 'pm-5.9-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull more power management updates from Rafael Wysocki:
 "These are mostly ARM cpufreq driver updates plus a cpufreq core
  cleanup, an ARM-wide change to make schedutil the default scaling
  governor, an intel_pstate driver fix and some runtime PM changes
  regarding kerneldoc comments.

  Specifics:

   - Add adaptive voltage scaling (AVS) support to the brcmstb cpufreq
     driver and clean it up (Florian Fainelli, Markus Mayer).

   - Add a new Tegra cpufreq driver and clean up the existing one (Jon
     Hunter, Sumit Gupta).

   - Add bandwidth level support to the Qcom cpufreq driver along with
     OPP changes (Sibi Sankar).

   - Clean up the sti, cpufreq-dt, ap806, CPPC cpufreq drivers (Viresh
     Kumar, Lee Jones, Ivan Kokshaysky, Sven Auhagen, Xin Hao).

   - Make schedutil the default governor for ARM (Valentin Schneider).

   - Fix dependency issues for the imx cpufreq driver (Walter Lozano).

   - Clean up cached_resolved_idx handlihng in the cpufreq core (Viresh
     Kumar).

   - Fix the intel_pstate driver to use the correct maximum frequency
     value when MSR_TURBO_RATIO_LIMIT is 0 (Srinivas Pandruvada).

   - Provide kenrneldoc comments for multiple runtime PM helpers and
     improve the pm_runtime_get_if_active() kerneldoc (Rafael Wysocki)"

* tag 'pm-5.9-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (22 commits)
  cpufreq: intel_pstate: Fix cpuinfo_max_freq when MSR_TURBO_RATIO_LIMIT is 0
  PM: runtime: Improve kerneldoc of pm_runtime_get_if_active()
  PM: runtime: Add kerneldoc comments to multiple helpers
  cpufreq: make schedutil the default for arm and arm64
  cpufreq: cached_resolved_idx can not be negative
  cpufreq: Add Tegra194 cpufreq driver
  dt-bindings: arm: Add NVIDIA Tegra194 CPU Complex binding
  cpufreq: imx: Select NVMEM_IMX_OCOTP
  cpufreq: sti-cpufreq: Fix some formatting and misspelling issues
  cpufreq: tegra186: Simplify probe return path
  cpufreq: CPPC: Reuse caps variable in few routines
  cpufreq: ap806: fix cpufreq driver needs ap cpu clk
  cpufreq: cppc: Reorder code and remove apply_hisi_workaround variable
  cpufreq: dt: fix oops on armada37xx
  cpufreq: brcmstb-avs-cpufreq: send S2_ENTER / S2_EXIT commands to AVS
  cpufreq: brcmstb-avs-cpufreq: Support polling AVS firmware
  cpufreq: brcmstb-avs-cpufreq: more flexible interface for __issue_avs_command()
  cpufreq: qcom: Disable fast switch when scaling DDR/L3
  cpufreq: qcom: Update the bandwidth levels on frequency change
  OPP: Add and export helper to set bandwidth
  ...

Author: torvalds

Documentation/devicetree/bindings/arm/nvidia,tegra194-ccplex.yaml

@@ -0,0 +1,69 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: "http://devicetree.org/schemas/arm/nvidia,tegra194-ccplex.yaml#"
+$schema: "http://devicetree.org/meta-schemas/core.yaml#"
+
+title: NVIDIA Tegra194 CPU Complex device tree bindings
+
+maintainers:
+  - Thierry Reding <[email protected]>
+  - Jonathan Hunter <[email protected]>
+  - Sumit Gupta <[email protected]>
+
+description: |+
+  Tegra194 SOC has homogeneous architecture where each cluster has two
+  symmetric cores. Compatible string in "cpus" node represents the CPU
+  Complex having all clusters.
+
+properties:
+  $nodename:
+    const: cpus
+
+  compatible:
+    enum:
+      - nvidia,tegra194-ccplex
+
+  nvidia,bpmp:
+    $ref: '/schemas/types.yaml#/definitions/phandle'
+    description: |
+      Specifies the bpmp node that needs to be queried to get
+      operating point data for all CPUs.
+
+examples:
+  - |
+    cpus {
+      compatible = "nvidia,tegra194-ccplex";
+      nvidia,bpmp = <&bpmp>;
+      #address-cells = <1>;
+      #size-cells = <0>;
+
+      cpu0_0: cpu@0 {
+        compatible = "nvidia,tegra194-carmel";
+        device_type = "cpu";
+        reg = <0x0>;
+        enable-method = "psci";
+      };
+
+      cpu0_1: cpu@1 {
+        compatible = "nvidia,tegra194-carmel";
+        device_type = "cpu";
+        reg = <0x001>;
+        enable-method = "psci";
+      };
+
+      cpu1_0: cpu@100 {
+        compatible = "nvidia,tegra194-carmel";
+        device_type = "cpu";
+        reg = <0x100>;
+        enable-method = "psci";
+      };
+
+      cpu1_1: cpu@101 {
+        compatible = "nvidia,tegra194-carmel";
+        device_type = "cpu";
+        reg = <0x101>;
+        enable-method = "psci";
+      };
+    };
+...

drivers/base/power/runtime.c

@@ -1085,24 +1085,26 @@ int __pm_runtime_resume(struct device *dev, int rpmflags)
 EXPORT_SYMBOL_GPL(__pm_runtime_resume);
 
 /**
- * pm_runtime_get_if_active - Conditionally bump up the device's usage counter.
+ * pm_runtime_get_if_active - Conditionally bump up device usage counter.
  * @dev: Device to handle.
+ * @ign_usage_count: Whether or not to look at the current usage counter value.
  *
- * Return -EINVAL if runtime PM is disabled for the device.
+ * Return -EINVAL if runtime PM is disabled for @dev.
  *
- * Otherwise, if the device's runtime PM status is RPM_ACTIVE and either
- * ign_usage_count is true or the device's usage_count is non-zero, increment
- * the counter and return 1. Otherwise return 0 without changing the counter.
+ * Otherwise, if the runtime PM status of @dev is %RPM_ACTIVE and either
+ * @ign_usage_count is %true or the runtime PM usage counter of @dev is not
+ * zero, increment the usage counter of @dev and return 1. Otherwise, return 0
+ * without changing the usage counter.
  *
- * If ign_usage_count is true, the function can be used to prevent suspending
- * the device when its runtime PM status is RPM_ACTIVE.
+ * If @ign_usage_count is %true, this function can be used to prevent suspending
+ * the device when its runtime PM status is %RPM_ACTIVE.
  *
- * If ign_usage_count is false, the function can be used to prevent suspending
- * the device when both its runtime PM status is RPM_ACTIVE and its usage_count
- * is non-zero.
+ * If @ign_usage_count is %false, this function can be used to prevent
+ * suspending the device when both its runtime PM status is %RPM_ACTIVE and its
+ * runtime PM usage counter is not zero.
  *
- * The caller is resposible for putting the device's usage count when ther
- * return value is greater than zero.
+ * The caller is resposible for decrementing the runtime PM usage counter of
+ * @dev after this function has returned a positive value for it.
  */
 int pm_runtime_get_if_active(struct device *dev, bool ign_usage_count)
 {

drivers/cpufreq/Kconfig

@@ -37,7 +37,7 @@ config CPU_FREQ_STAT
 choice
 	prompt "Default CPUFreq governor"
 	default CPU_FREQ_DEFAULT_GOV_USERSPACE if ARM_SA1100_CPUFREQ || ARM_SA1110_CPUFREQ
-	default CPU_FREQ_DEFAULT_GOV_SCHEDUTIL if BIG_LITTLE
+	default CPU_FREQ_DEFAULT_GOV_SCHEDUTIL if ARM64 || ARM
 	default CPU_FREQ_DEFAULT_GOV_SCHEDUTIL if X86_INTEL_PSTATE && SMP
 	default CPU_FREQ_DEFAULT_GOV_PERFORMANCE
 	help

drivers/cpufreq/Kconfig.arm

@@ -41,6 +41,7 @@ config ARM_ARMADA_37XX_CPUFREQ
 config ARM_ARMADA_8K_CPUFREQ
 	tristate "Armada 8K CPUFreq driver"
 	depends on ARCH_MVEBU && CPUFREQ_DT
+	select ARMADA_AP_CPU_CLK
 	help
 	  This enables the CPUFreq driver support for Marvell
 	  Armada8k SOCs.
@@ -93,6 +94,7 @@ config ARM_IMX6Q_CPUFREQ
 	tristate "Freescale i.MX6 cpufreq support"
 	depends on ARCH_MXC
 	depends on REGULATOR_ANATOP
+	select NVMEM_IMX_OCOTP
 	select PM_OPP
 	help
 	  This adds cpufreq driver support for Freescale i.MX6 series SoCs.
@@ -314,6 +316,13 @@ config ARM_TEGRA186_CPUFREQ
 	help
 	  This adds the CPUFreq driver support for Tegra186 SOCs.
 
+config ARM_TEGRA194_CPUFREQ
+	tristate "Tegra194 CPUFreq support"
+	depends on ARCH_TEGRA_194_SOC && TEGRA_BPMP
+	default y
+	help
+	  This adds CPU frequency driver support for Tegra194 SOCs.
+
 config ARM_TI_CPUFREQ
 	bool "Texas Instruments CPUFreq support"
 	depends on ARCH_OMAP2PLUS

drivers/cpufreq/Makefile

@@ -83,6 +83,7 @@ obj-$(CONFIG_ARM_TANGO_CPUFREQ)		+= tango-cpufreq.o
 obj-$(CONFIG_ARM_TEGRA20_CPUFREQ)	+= tegra20-cpufreq.o
 obj-$(CONFIG_ARM_TEGRA124_CPUFREQ)	+= tegra124-cpufreq.o
 obj-$(CONFIG_ARM_TEGRA186_CPUFREQ)	+= tegra186-cpufreq.o
+obj-$(CONFIG_ARM_TEGRA194_CPUFREQ)	+= tegra194-cpufreq.o
 obj-$(CONFIG_ARM_TI_CPUFREQ)		+= ti-cpufreq.o
 obj-$(CONFIG_ARM_VEXPRESS_SPC_CPUFREQ)	+= vexpress-spc-cpufreq.o
 

drivers/cpufreq/armada-37xx-cpufreq.c

@@ -456,6 +456,7 @@ static int __init armada37xx_cpufreq_driver_init(void)
 	/* Now that everything is setup, enable the DVFS at hardware level */
 	armada37xx_cpufreq_enable_dvfs(nb_pm_base);
 
+	memset(&pdata, 0, sizeof(pdata));
 	pdata.suspend = armada37xx_cpufreq_suspend;
 	pdata.resume = armada37xx_cpufreq_resume;
 

drivers/cpufreq/brcmstb-avs-cpufreq.c

@@ -42,6 +42,7 @@
  */
 
 #include <linux/cpufreq.h>
+#include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/module.h>
@@ -178,6 +179,7 @@ struct private_data {
 	struct completion done;
 	struct semaphore sem;
 	struct pmap pmap;
+	int host_irq;
 };
 
 static void __iomem *__map_region(const char *name)
@@ -195,11 +197,36 @@ static void __iomem *__map_region(const char *name)
 	return ptr;
 }
 
-static int __issue_avs_command(struct private_data *priv, int cmd, bool is_send,
+static unsigned long wait_for_avs_command(struct private_data *priv,
+					  unsigned long timeout)
+{
+	unsigned long time_left = 0;
+	u32 val;
+
+	/* Event driven, wait for the command interrupt */
+	if (priv->host_irq >= 0)
+		return wait_for_completion_timeout(&priv->done,
+						   msecs_to_jiffies(timeout));
+
+	/* Polling for command completion */
+	do {
+		time_left = timeout;
+		val = readl(priv->base + AVS_MBOX_STATUS);
+		if (val)
+			break;
+
+		usleep_range(1000, 2000);
+	} while (--timeout);
+
+	return time_left;
+}
+
+static int __issue_avs_command(struct private_data *priv, unsigned int cmd,
+			       unsigned int num_in, unsigned int num_out,
 			       u32 args[])
 {
-	unsigned long time_left = msecs_to_jiffies(AVS_TIMEOUT);
 	void __iomem *base = priv->base;
+	unsigned long time_left;
 	unsigned int i;
 	int ret;
 	u32 val;
@@ -225,11 +252,9 @@ static int __issue_avs_command(struct private_data *priv, int cmd, bool is_send,
 	/* Clear status before we begin. */
 	writel(AVS_STATUS_CLEAR, base + AVS_MBOX_STATUS);
 
-	/* We need to send arguments for this command. */
-	if (args && is_send) {
-		for (i = 0; i < AVS_MAX_CMD_ARGS; i++)
-			writel(args[i], base + AVS_MBOX_PARAM(i));
-	}
+	/* Provide input parameters */
+	for (i = 0; i < num_in; i++)
+		writel(args[i], base + AVS_MBOX_PARAM(i));
 
 	/* Protect from spurious interrupts. */
 	reinit_completion(&priv->done);
@@ -239,7 +264,7 @@ static int __issue_avs_command(struct private_data *priv, int cmd, bool is_send,
 	writel(AVS_CPU_L2_INT_MASK, priv->avs_intr_base + AVS_CPU_L2_SET0);
 
 	/* Wait for AVS co-processor to finish processing the command. */
-	time_left = wait_for_completion_timeout(&priv->done, time_left);
+	time_left = wait_for_avs_command(priv, AVS_TIMEOUT);
 
 	/*
 	 * If the AVS status is not in the expected range, it means AVS didn't
@@ -256,11 +281,9 @@ static int __issue_avs_command(struct private_data *priv, int cmd, bool is_send,
 		goto out;
 	}
 
-	/* This command returned arguments, so we read them back. */
-	if (args && !is_send) {
-		for (i = 0; i < AVS_MAX_CMD_ARGS; i++)
-			args[i] = readl(base + AVS_MBOX_PARAM(i));
-	}
+	/* Process returned values */
+	for (i = 0; i < num_out; i++)
+		args[i] = readl(base + AVS_MBOX_PARAM(i));
 
 	/* Clear status to tell AVS co-processor we are done. */
 	writel(AVS_STATUS_CLEAR, base + AVS_MBOX_STATUS);
@@ -338,7 +361,7 @@ static int brcm_avs_get_pmap(struct private_data *priv, struct pmap *pmap)
 	u32 args[AVS_MAX_CMD_ARGS];
 	int ret;
 
-	ret = __issue_avs_command(priv, AVS_CMD_GET_PMAP, false, args);
+	ret = __issue_avs_command(priv, AVS_CMD_GET_PMAP, 0, 4, args);
 	if (ret || !pmap)
 		return ret;
 
@@ -359,15 +382,15 @@ static int brcm_avs_set_pmap(struct private_data *priv, struct pmap *pmap)
 	args[2] = pmap->p2;
 	args[3] = pmap->state;
 
-	return __issue_avs_command(priv, AVS_CMD_SET_PMAP, true, args);
+	return __issue_avs_command(priv, AVS_CMD_SET_PMAP, 4, 0, args);
 }
 
 static int brcm_avs_get_pstate(struct private_data *priv, unsigned int *pstate)
 {
 	u32 args[AVS_MAX_CMD_ARGS];
 	int ret;
 
-	ret = __issue_avs_command(priv, AVS_CMD_GET_PSTATE, false, args);
+	ret = __issue_avs_command(priv, AVS_CMD_GET_PSTATE, 0, 1, args);
 	if (ret)
 		return ret;
 	*pstate = args[0];
@@ -381,7 +404,8 @@ static int brcm_avs_set_pstate(struct private_data *priv, unsigned int pstate)
 
 	args[0] = pstate;
 
-	return __issue_avs_command(priv, AVS_CMD_SET_PSTATE, true, args);
+	return __issue_avs_command(priv, AVS_CMD_SET_PSTATE, 1, 0, args);
+
 }
 
 static u32 brcm_avs_get_voltage(void __iomem *base)
@@ -482,14 +506,24 @@ static int brcm_avs_suspend(struct cpufreq_policy *policy)
 	 * AVS co-processor, not necessarily the P-state we are running at now.
 	 * So, we get the current P-state explicitly.
 	 */
-	return brcm_avs_get_pstate(priv, &priv->pmap.state);
+	ret = brcm_avs_get_pstate(priv, &priv->pmap.state);
+	if (ret)
+		return ret;
+
+	/* This is best effort. Nothing to do if it fails. */
+	(void)__issue_avs_command(priv, AVS_CMD_S2_ENTER, 0, 0, NULL);
+
+	return 0;
 }
 
 static int brcm_avs_resume(struct cpufreq_policy *policy)
 {
 	struct private_data *priv = policy->driver_data;
 	int ret;
 
+	/* This is best effort. Nothing to do if it fails. */
+	(void)__issue_avs_command(priv, AVS_CMD_S2_EXIT, 0, 0, NULL);
+
 	ret = brcm_avs_set_pmap(priv, &priv->pmap);
 	if (ret == -EEXIST) {
 		struct platform_device *pdev  = cpufreq_get_driver_data();
@@ -511,7 +545,7 @@ static int brcm_avs_prepare_init(struct platform_device *pdev)
 {
 	struct private_data *priv;
 	struct device *dev;
-	int host_irq, ret;
+	int ret;
 
 	dev = &pdev->dev;
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
@@ -538,19 +572,14 @@ static int brcm_avs_prepare_init(struct platform_device *pdev)
 		goto unmap_base;
 	}
 
-	host_irq = platform_get_irq_byname(pdev, BRCM_AVS_HOST_INTR);
-	if (host_irq < 0) {
-		dev_err(dev, "Couldn't find interrupt %s -- %d\n",
-			BRCM_AVS_HOST_INTR, host_irq);
-		ret = host_irq;
-		goto unmap_intr_base;
-	}
+	priv->host_irq = platform_get_irq_byname(pdev, BRCM_AVS_HOST_INTR);
 
-	ret = devm_request_irq(dev, host_irq, irq_handler, IRQF_TRIGGER_RISING,
+	ret = devm_request_irq(dev, priv->host_irq, irq_handler,
+			       IRQF_TRIGGER_RISING,
 			       BRCM_AVS_HOST_INTR, priv);
-	if (ret) {
+	if (ret && priv->host_irq >= 0) {
 		dev_err(dev, "IRQ request failed: %s (%d) -- %d\n",
-			BRCM_AVS_HOST_INTR, host_irq, ret);
+			BRCM_AVS_HOST_INTR, priv->host_irq, ret);
 		goto unmap_intr_base;
 	}
 
@@ -593,7 +622,7 @@ static int brcm_avs_cpufreq_init(struct cpufreq_policy *policy)
 	/* All cores share the same clock and thus the same policy. */
 	cpumask_setall(policy->cpus);
 
-	ret = __issue_avs_command(priv, AVS_CMD_ENABLE, false, NULL);
+	ret = __issue_avs_command(priv, AVS_CMD_ENABLE, 0, 0, NULL);
 	if (!ret) {
 		unsigned int pstate;