Merge tag 'pm-6.13-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull more power management updates from Rafael Wysocki:
 "These mostly are updates of cpufreq drivers used on ARM platforms plus
  one new DT-based cpufreq driver for virtualized guests and two cpuidle
  changes that should not make any difference on systems currently in
  the field, but will be needed for future development:

   - Add virtual cpufreq driver for guest kernels (David Dai)

   - Minor cleanup to various cpufreq drivers (Andy Shevchenko, Dhruva
     Gole, Jie Zhan, Jinjie Ruan, Shuosheng Huang, Sibi Sankar, and Yuan
     Can)

   - Revert "cpufreq: brcmstb-avs-cpufreq: Fix initial command check"
     (Colin Ian King)

   - Improve DT bindings for qcom-hw driver (Dmitry Baryshkov, Konrad
     Dybcio, and Nikunj Kela)

   - Make cpuidle_play_dead() try all idle states with :enter_dead()
     callbacks and change their return type to void (Rafael Wysocki)"

* tag 'pm-6.13-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (22 commits)
  cpuidle: Change :enter_dead() driver callback return type to void
  cpuidle: Do not return from cpuidle_play_dead() on callback failures
  arm64: dts: qcom: sc8180x: Add a SoC-specific compatible to cpufreq-hw
  dt-bindings: cpufreq: cpufreq-qcom-hw: Add SC8180X compatible
  cpufreq: sun50i: add a100 cpufreq support
  cpufreq: mediatek-hw: Fix wrong return value in mtk_cpufreq_get_cpu_power()
  cpufreq: CPPC: Fix wrong return value in cppc_get_cpu_power()
  cpufreq: CPPC: Fix wrong return value in cppc_get_cpu_cost()
  cpufreq: loongson3: Check for error code from devm_mutex_init() call
  cpufreq: scmi: Fix cleanup path when boost enablement fails
  cpufreq: CPPC: Fix possible null-ptr-deref for cppc_get_cpu_cost()
  cpufreq: CPPC: Fix possible null-ptr-deref for cpufreq_cpu_get_raw()
  Revert "cpufreq: brcmstb-avs-cpufreq: Fix initial command check"
  dt-bindings: cpufreq: cpufreq-qcom-hw: Add SAR2130P compatible
  cpufreq: add virtual-cpufreq driver
  dt-bindings: cpufreq: add virtual cpufreq device
  cpufreq: loongson2: Unregister platform_driver on failure
  cpufreq: ti-cpufreq: Remove revision offsets in AM62 family
  cpufreq: ti-cpufreq: Allow backward compatibility for efuse syscon
  cppc_cpufreq: Remove HiSilicon CPPC workaround
  ...

Author: torvalds

Documentation/devicetree/bindings/cpufreq/cpufreq-qcom-hw.yaml

@@ -23,6 +23,7 @@ properties:
           - enum:
               - qcom,qcm2290-cpufreq-hw
               - qcom,sc7180-cpufreq-hw
+              - qcom,sc8180x-cpufreq-hw
               - qcom,sdm670-cpufreq-hw
               - qcom,sdm845-cpufreq-hw
               - qcom,sm6115-cpufreq-hw
@@ -34,7 +35,9 @@ properties:
         items:
           - enum:
               - qcom,qdu1000-cpufreq-epss
+              - qcom,sa8255p-cpufreq-epss
               - qcom,sa8775p-cpufreq-epss
+              - qcom,sar2130p-cpufreq-epss
               - qcom,sc7280-cpufreq-epss
               - qcom,sc8280xp-cpufreq-epss
               - qcom,sdx75-cpufreq-epss
@@ -107,6 +110,7 @@ allOf:
           contains:
             enum:
               - qcom,qcm2290-cpufreq-hw
+              - qcom,sar2130p-cpufreq-epss
     then:
       properties:
         reg:
@@ -130,7 +134,9 @@ allOf:
           contains:
             enum:
               - qcom,qdu1000-cpufreq-epss
+              - qcom,sa8255p-cpufreq-epss
               - qcom,sc7180-cpufreq-hw
+              - qcom,sc8180x-cpufreq-hw
               - qcom,sc8280xp-cpufreq-epss
               - qcom,sdm670-cpufreq-hw
               - qcom,sdm845-cpufreq-hw

Documentation/devicetree/bindings/cpufreq/qemu,virtual-cpufreq.yaml

@@ -0,0 +1,48 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/cpufreq/qemu,virtual-cpufreq.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Virtual CPUFreq
+
+maintainers:
+  - David Dai <davidai@google.com>
+  - Saravana Kannan <saravanak@google.com>
+
+description:
+  Virtual CPUFreq is a virtualized driver in guest kernels that sends performance
+  selection of its vCPUs as a hint to the host through MMIO regions. Each vCPU
+  is associated with a performance domain which can be shared with other vCPUs.
+  Each performance domain has its own set of registers for performance controls.
+
+properties:
+  compatible:
+    const: qemu,virtual-cpufreq
+
+  reg:
+    maxItems: 1
+    description:
+      Address and size of region containing performance controls for each of the
+      performance domains. Regions for each performance domain is placed
+      contiguously and contain registers for controlling DVFS(Dynamic Frequency
+      and Voltage) characteristics. The size of the region is proportional to
+      total number of performance domains.
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    soc {
+      #address-cells = <1>;
+      #size-cells = <1>;
+
+      cpufreq@1040000 {
+        compatible = "qemu,virtual-cpufreq";
+        reg = <0x1040000 0x2000>;
+      };
+    };

arch/arm64/boot/dts/qcom/sc8180x.dtsi

@@ -3889,7 +3889,7 @@
 		};
 
 		cpufreq_hw: cpufreq@18323000 {
-			compatible = "qcom,cpufreq-hw";
+			compatible = "qcom,sc8180x-cpufreq-hw", "qcom,cpufreq-hw";
 			reg = <0 0x18323000 0 0x1400>, <0 0x18325800 0 0x1400>;
 			reg-names = "freq-domain0", "freq-domain1";
 

drivers/acpi/processor_idle.c

@@ -578,7 +578,7 @@ static void __cpuidle acpi_idle_do_entry(struct acpi_processor_cx *cx)
  * @dev: the target CPU
  * @index: the index of suggested state
  */
-static int acpi_idle_play_dead(struct cpuidle_device *dev, int index)
+static void acpi_idle_play_dead(struct cpuidle_device *dev, int index)
 {
 	struct acpi_processor_cx *cx = per_cpu(acpi_cstate[index], dev->cpu);
 
@@ -591,11 +591,8 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index)
 		else if (cx->entry_method == ACPI_CSTATE_SYSTEMIO) {
 			io_idle(cx->address);
 		} else
-			return -ENODEV;
+			return;
 	}
-
-	/* Never reached */
-	return 0;
 }
 
 static __always_inline bool acpi_idle_fallback_to_c1(struct acpi_processor *pr)

drivers/cpufreq/Kconfig

@@ -217,6 +217,20 @@ config CPUFREQ_DT
 
 	  If in doubt, say N.
 
+config CPUFREQ_VIRT
+	tristate "Virtual cpufreq driver"
+	depends on GENERIC_ARCH_TOPOLOGY
+	help
+	  This adds a virtualized cpufreq driver for guest kernels that
+	  read/writes to a MMIO region for a virtualized cpufreq device to
+	  communicate with the host. It sends performance requests to the host
+	  which gets used as a hint to schedule vCPU threads and select CPU
+	  frequency. If a VM does not support a virtualized FIE such as AMUs,
+	  it updates the frequency scaling factor by polling host CPU frequency
+	  to enable accurate Per-Entity Load Tracking for tasks running in the guest.
+
+	  If in doubt, say N.
+
 config CPUFREQ_DT_PLATDEV
 	tristate "Generic DT based cpufreq platdev driver"
 	depends on OF

drivers/cpufreq/Makefile

@@ -16,6 +16,7 @@ obj-$(CONFIG_CPU_FREQ_GOV_ATTR_SET)	+= cpufreq_governor_attr_set.o
 
 obj-$(CONFIG_CPUFREQ_DT)		+= cpufreq-dt.o
 obj-$(CONFIG_CPUFREQ_DT_PLATDEV)	+= cpufreq-dt-platdev.o
+obj-$(CONFIG_CPUFREQ_VIRT)		+= virtual-cpufreq.o
 
 # Traces
 CFLAGS_amd-pstate-trace.o               := -I$(src)

drivers/cpufreq/brcmstb-avs-cpufreq.c

@@ -474,8 +474,8 @@ static bool brcm_avs_is_firmware_loaded(struct private_data *priv)
 	rc = brcm_avs_get_pmap(priv, NULL);
 	magic = readl(priv->base + AVS_MBOX_MAGIC);
 
-	return (magic == AVS_FIRMWARE_MAGIC) && ((rc != -ENOTSUPP) ||
-		(rc != -EINVAL));
+	return (magic == AVS_FIRMWARE_MAGIC) && (rc != -ENOTSUPP) &&
+		(rc != -EINVAL);
 }
 
 static unsigned int brcm_avs_cpufreq_get(unsigned int cpu)

drivers/cpufreq/cppc_cpufreq.c

@@ -36,33 +36,15 @@ static LIST_HEAD(cpu_data_list);
 
 static bool boost_supported;
 
-struct cppc_workaround_oem_info {
-	char oem_id[ACPI_OEM_ID_SIZE + 1];
-	char oem_table_id[ACPI_OEM_TABLE_ID_SIZE + 1];
-	u32 oem_revision;
-};
-
-static struct cppc_workaround_oem_info wa_info[] = {
-	{
-		.oem_id		= "HISI  ",
-		.oem_table_id	= "HIP07   ",
-		.oem_revision	= 0,
-	}, {
-		.oem_id		= "HISI  ",
-		.oem_table_id	= "HIP08   ",
-		.oem_revision	= 0,
-	}
-};
-
 static struct cpufreq_driver cppc_cpufreq_driver;
 
+#ifdef CONFIG_ACPI_CPPC_CPUFREQ_FIE
 static enum {
 	FIE_UNSET = -1,
 	FIE_ENABLED,
 	FIE_DISABLED
 } fie_disabled = FIE_UNSET;
 
-#ifdef CONFIG_ACPI_CPPC_CPUFREQ_FIE
 module_param(fie_disabled, int, 0444);
 MODULE_PARM_DESC(fie_disabled, "Disable Frequency Invariance Engine (FIE)");
 
@@ -78,7 +60,6 @@ struct cppc_freq_invariance {
 static DEFINE_PER_CPU(struct cppc_freq_invariance, cppc_freq_inv);
 static struct kthread_worker *kworker_fie;
 
-static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpu);
 static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data,
 				 struct cppc_perf_fb_ctrs *fb_ctrs_t0,
 				 struct cppc_perf_fb_ctrs *fb_ctrs_t1);
@@ -118,6 +99,9 @@ static void cppc_scale_freq_workfn(struct kthread_work *work)
 
 	perf = cppc_perf_from_fbctrs(cpu_data, &cppc_fi->prev_perf_fb_ctrs,
 				     &fb_ctrs);
+	if (!perf)
+		return;
+
 	cppc_fi->prev_perf_fb_ctrs = fb_ctrs;
 
 	perf <<= SCHED_CAPACITY_SHIFT;
@@ -420,6 +404,9 @@ static int cppc_get_cpu_power(struct device *cpu_dev,
 	struct cppc_cpudata *cpu_data;
 
 	policy = cpufreq_cpu_get_raw(cpu_dev->id);
+	if (!policy)
+		return -EINVAL;
+
 	cpu_data = policy->driver_data;
 	perf_caps = &cpu_data->perf_caps;
 	max_cap = arch_scale_cpu_capacity(cpu_dev->id);
@@ -487,6 +474,9 @@ static int cppc_get_cpu_cost(struct device *cpu_dev, unsigned long KHz,
 	int step;
 
 	policy = cpufreq_cpu_get_raw(cpu_dev->id);
+	if (!policy)
+		return -EINVAL;
+
 	cpu_data = policy->driver_data;
 	perf_caps = &cpu_data->perf_caps;
 	max_cap = arch_scale_cpu_capacity(cpu_dev->id);
@@ -724,13 +714,31 @@ static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data,
 	delta_delivered = get_delta(fb_ctrs_t1->delivered,
 				    fb_ctrs_t0->delivered);
 
-	/* Check to avoid divide-by zero and invalid delivered_perf */
+	/*
+	 * Avoid divide-by zero and unchanged feedback counters.
+	 * Leave it for callers to handle.
+	 */
 	if (!delta_reference || !delta_delivered)
-		return cpu_data->perf_ctrls.desired_perf;
+		return 0;
 
 	return (reference_perf * delta_delivered) / delta_reference;
 }
 
+static int cppc_get_perf_ctrs_sample(int cpu,
+				     struct cppc_perf_fb_ctrs *fb_ctrs_t0,
+				     struct cppc_perf_fb_ctrs *fb_ctrs_t1)
+{
+	int ret;
+
+	ret = cppc_get_perf_ctrs(cpu, fb_ctrs_t0);
+	if (ret)
+		return ret;
+
+	udelay(2); /* 2usec delay between sampling */
+
+	return cppc_get_perf_ctrs(cpu, fb_ctrs_t1);
+}
+
 static unsigned int cppc_cpufreq_get_rate(unsigned int cpu)
 {
 	struct cppc_perf_fb_ctrs fb_ctrs_t0 = {0}, fb_ctrs_t1 = {0};
@@ -746,18 +754,32 @@ static unsigned int cppc_cpufreq_get_rate(unsigned int cpu)
 
 	cpufreq_cpu_put(policy);
 
-	ret = cppc_get_perf_ctrs(cpu, &fb_ctrs_t0);
-	if (ret)
-		return 0;
-
-	udelay(2); /* 2usec delay between sampling */
-
-	ret = cppc_get_perf_ctrs(cpu, &fb_ctrs_t1);
-	if (ret)
-		return 0;
+	ret = cppc_get_perf_ctrs_sample(cpu, &fb_ctrs_t0, &fb_ctrs_t1);
+	if (ret) {
+		if (ret == -EFAULT)
+			/* Any of the associated CPPC regs is 0. */
+			goto out_invalid_counters;
+		else
+			return 0;
+	}
 
 	delivered_perf = cppc_perf_from_fbctrs(cpu_data, &fb_ctrs_t0,
 					       &fb_ctrs_t1);
+	if (!delivered_perf)
+		goto out_invalid_counters;
+
+	return cppc_perf_to_khz(&cpu_data->perf_caps, delivered_perf);
+
+out_invalid_counters:
+	/*
+	 * Feedback counters could be unchanged or 0 when a cpu enters a
+	 * low-power idle state, e.g. clock-gated or power-gated.
+	 * Use desired perf for reflecting frequency.  Get the latest register
+	 * value first as some platforms may update the actual delivered perf
+	 * there; if failed, resort to the cached desired perf.
+	 */
+	if (cppc_get_desired_perf(cpu, &delivered_perf))
+		delivered_perf = cpu_data->perf_ctrls.desired_perf;
 
 	return cppc_perf_to_khz(&cpu_data->perf_caps, delivered_perf);
 }
@@ -812,65 +834,13 @@ static struct cpufreq_driver cppc_cpufreq_driver = {
 	.name = "cppc_cpufreq",
 };
 
-/*
- * HISI platform does not support delivered performance counter and
- * reference performance counter. It can calculate the performance using the
- * platform specific mechanism. We reuse the desired performance register to
- * store the real performance calculated by the platform.
- */
-static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpu)
-{
-	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
-	struct cppc_cpudata *cpu_data;
-	u64 desired_perf;
-	int ret;
-
-	if (!policy)
-		return -ENODEV;
-
-	cpu_data = policy->driver_data;
-
-	cpufreq_cpu_put(policy);
-
-	ret = cppc_get_desired_perf(cpu, &desired_perf);
-	if (ret < 0)
-		return -EIO;
-
-	return cppc_perf_to_khz(&cpu_data->perf_caps, desired_perf);
-}
-
-static void cppc_check_hisi_workaround(void)
-{
-	struct acpi_table_header *tbl;
-	acpi_status status = AE_OK;
-	int i;
-
-	status = acpi_get_table(ACPI_SIG_PCCT, 0, &tbl);
-	if (ACPI_FAILURE(status) || !tbl)
-		return;
-
-	for (i = 0; i < ARRAY_SIZE(wa_info); i++) {
-		if (!memcmp(wa_info[i].oem_id, tbl->oem_id, ACPI_OEM_ID_SIZE) &&
-		    !memcmp(wa_info[i].oem_table_id, tbl->oem_table_id, ACPI_OEM_TABLE_ID_SIZE) &&
-		    wa_info[i].oem_revision == tbl->oem_revision) {
-			/* Overwrite the get() callback */
-			cppc_cpufreq_driver.get = hisi_cppc_cpufreq_get_rate;
-			fie_disabled = FIE_DISABLED;
-			break;
-		}
-	}
-
-	acpi_put_table(tbl);
-}
-
 static int __init cppc_cpufreq_init(void)
 {
 	int ret;
 
 	if (!acpi_cpc_valid())
 		return -ENODEV;
 
-	cppc_check_hisi_workaround();
 	cppc_freq_invariance_init();
 	populate_efficiency_class();
 

drivers/cpufreq/cpufreq-dt-platdev.c

@@ -103,6 +103,7 @@ static const struct of_device_id allowlist[] __initconst = {
  * platforms using "operating-points-v2" property.
  */
 static const struct of_device_id blocklist[] __initconst = {
+	{ .compatible = "allwinner,sun50i-a100" },
 	{ .compatible = "allwinner,sun50i-h6", },
 	{ .compatible = "allwinner,sun50i-h616", },
 	{ .compatible = "allwinner,sun50i-h618", },

drivers/cpufreq/loongson2_cpufreq.c

@@ -148,7 +148,9 @@ static int __init cpufreq_init(void)
 
 	ret = cpufreq_register_driver(&loongson2_cpufreq_driver);
 
-	if (!ret && !nowait) {
+	if (ret) {
+		platform_driver_unregister(&platform_driver);
+	} else if (!nowait) {
 		saved_cpu_wait = cpu_wait;
 		cpu_wait = loongson2_cpu_wait;
 	}