Merge tag 'pm-6.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These add support for some new hardware, extend the existing hardware
  support, fix some issues and clean up code

  Specifics:

   - Add isupport for Tiger Lake in no-HWP mode to intel_pstate (Doug
     Smythies)

   - Update the AMD P-state driver (Perry Yuan):
      - Fix wrong lowest perf fetch
      - Map desired perf into pstate scope for powersave governor
      - Update pstate frequency transition delay time
      - Fix initial highest_perf value
      - Clean up

   - Move max CPU capacity to sugov_policy in the schedutil cpufreq
     governor (Lukasz Luba)

   - Add SM6115 to cpufreq-dt blocklist (Adam Skladowski)

   - Add support for Tegra239 and minor cleanups (Sumit Gupta, ye
     xingchen, and Yang Yingliang)

   - Add freq qos for qcom cpufreq driver and minor cleanups (Xuewen
     Yan, and Viresh Kumar)

   - Minor cleanups around functions called at module_init() (Xiu
     Jianfeng)

   - Use module_init and add module_exit for bmips driver (Zhang
     Jianhua)

   - Add AlderLake-N support to intel_idle (Zhang Rui)

   - Replace strlcpy() with unused retval with strscpy() in intel_idle
     (Wolfram Sang)

   - Remove redundant check from cpuidle_switch_governor() (Yu Liao)

   - Replace strlcpy() with unused retval with strscpy() in the powernv
     cpuidle driver (Wolfram Sang)

   - Drop duplicate word from a comment in the coupled cpuidle driver
     (Jason Wang)

   - Make rpm_resume() return -EINPROGRESS if RPM_NOWAIT is passed to it
     in the flags and the device is about to resume (Rafael Wysocki)

   - Add extra debugging statement for multiple active IRQs to system
     wakeup handling code (Mario Limonciello)

   - Replace strlcpy() with unused retval with strscpy() in the core
     system suspend support code (Wolfram Sang)

   - Update the intel_rapl power capping driver:
      - Use standard Energy Unit for SPR Dram RAPL domain (Zhang Rui).
      - Add support for RAPTORLAKE_S (Zhang Rui).
      - Fix UBSAN shift-out-of-bounds issue (Chao Qin)

   - Handle -EPROBE_DEFER when regulator is not probed on
     mtk-ci-devfreq.c (AngeloGioacchino Del Regno)

   - Fix message typo and use dev_err_probe() in rockchip-dfi.c
     (Christophe JAILLET)"

* tag 'pm-6.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (29 commits)
  cpufreq: qcom-cpufreq-hw: Add cpufreq qos for LMh
  cpufreq: Add __init annotation to module init funcs
  cpufreq: tegra194: change tegra239_cpufreq_soc to static
  PM / devfreq: rockchip-dfi: Fix an error message
  PM / devfreq: mtk-cci: Handle sram regulator probe deferral
  powercap: intel_rapl: Use standard Energy Unit for SPR Dram RAPL domain
  PM: runtime: Return -EINPROGRESS from rpm_resume() in the RPM_NOWAIT case
  intel_idle: Add AlderLake-N support
  powercap: intel_rapl: fix UBSAN shift-out-of-bounds issue
  cpufreq: tegra194: Add support for Tegra239
  cpufreq: qcom-cpufreq-hw: Fix uninitialized throttled_freq warning
  cpufreq: intel_pstate: Add Tigerlake support in no-HWP mode
  powercap: intel_rapl: Add support for RAPTORLAKE_S
  cpufreq: amd-pstate: Fix initial highest_perf value
  cpuidle: Remove redundant check in cpuidle_switch_governor()
  PM: wakeup: Add extra debugging statement for multiple active IRQs
  cpufreq: tegra194: Remove the unneeded result variable
  PM: suspend: move from strlcpy() with unused retval to strscpy()
  intel_idle: move from strlcpy() with unused retval to strscpy()
  cpuidle: powernv: move from strlcpy() with unused retval to strscpy()
  ...

Author: torvalds

drivers/base/power/runtime.c

@@ -792,10 +792,13 @@ static int rpm_resume(struct device *dev, int rpmflags)
 		DEFINE_WAIT(wait);
 
 		if (rpmflags & (RPM_ASYNC | RPM_NOWAIT)) {
-			if (dev->power.runtime_status == RPM_SUSPENDING)
+			if (dev->power.runtime_status == RPM_SUSPENDING) {
 				dev->power.deferred_resume = true;
-			else
+				if (rpmflags & RPM_NOWAIT)
+					retval = -EINPROGRESS;
+			} else {
 				retval = -EINPROGRESS;
+			}
 			goto out;
 		}
 

drivers/base/power/wakeup.c

@@ -944,6 +944,8 @@ void pm_system_irq_wakeup(unsigned int irq_number)
 	else
 		irq_number = 0;
 
+	pm_pr_dbg("Triggering wakeup from IRQ %d\n", irq_number);
+
 	raw_spin_unlock_irqrestore(&wakeup_irq_lock, flags);
 
 	if (irq_number)

drivers/cpufreq/amd-pstate.c

@@ -46,8 +46,8 @@
 #include <asm/cpu_device_id.h>
 #include "amd-pstate-trace.h"
 
-#define AMD_PSTATE_TRANSITION_LATENCY	0x20000
-#define AMD_PSTATE_TRANSITION_DELAY	500
+#define AMD_PSTATE_TRANSITION_LATENCY	20000
+#define AMD_PSTATE_TRANSITION_DELAY	1000
 
 /*
  * TODO: We need more time to fine tune processors with shared memory solution
@@ -120,7 +120,7 @@ struct amd_cpudata {
 	struct amd_aperf_mperf cur;
 	struct amd_aperf_mperf prev;
 
-	u64 freq;
+	u64 	freq;
 	bool	boost_supported;
 };
 
@@ -152,6 +152,7 @@ static inline int amd_pstate_enable(bool enable)
 static int pstate_init_perf(struct amd_cpudata *cpudata)
 {
 	u64 cap1;
+	u32 highest_perf;
 
 	int ret = rdmsrl_safe_on_cpu(cpudata->cpu, MSR_AMD_CPPC_CAP1,
 				     &cap1);
@@ -163,7 +164,11 @@ static int pstate_init_perf(struct amd_cpudata *cpudata)
 	 *
 	 * CPPC entry doesn't indicate the highest performance in some ASICs.
 	 */
-	WRITE_ONCE(cpudata->highest_perf, amd_get_highest_perf());
+	highest_perf = amd_get_highest_perf();
+	if (highest_perf > AMD_CPPC_HIGHEST_PERF(cap1))
+		highest_perf = AMD_CPPC_HIGHEST_PERF(cap1);
+
+	WRITE_ONCE(cpudata->highest_perf, highest_perf);
 
 	WRITE_ONCE(cpudata->nominal_perf, AMD_CPPC_NOMINAL_PERF(cap1));
 	WRITE_ONCE(cpudata->lowest_nonlinear_perf, AMD_CPPC_LOWNONLIN_PERF(cap1));
@@ -175,12 +180,17 @@ static int pstate_init_perf(struct amd_cpudata *cpudata)
 static int cppc_init_perf(struct amd_cpudata *cpudata)
 {
 	struct cppc_perf_caps cppc_perf;
+	u32 highest_perf;
 
 	int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf);
 	if (ret)
 		return ret;
 
-	WRITE_ONCE(cpudata->highest_perf, amd_get_highest_perf());
+	highest_perf = amd_get_highest_perf();
+	if (highest_perf > cppc_perf.highest_perf)
+		highest_perf = cppc_perf.highest_perf;
+
+	WRITE_ONCE(cpudata->highest_perf, highest_perf);
 
 	WRITE_ONCE(cpudata->nominal_perf, cppc_perf.nominal_perf);
 	WRITE_ONCE(cpudata->lowest_nonlinear_perf,
@@ -269,6 +279,7 @@ static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf,
 	u64 prev = READ_ONCE(cpudata->cppc_req_cached);
 	u64 value = prev;
 
+	des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf);
 	value &= ~AMD_CPPC_MIN_PERF(~0L);
 	value |= AMD_CPPC_MIN_PERF(min_perf);
 
@@ -312,7 +323,7 @@ static int amd_pstate_target(struct cpufreq_policy *policy,
 		return -ENODEV;
 
 	cap_perf = READ_ONCE(cpudata->highest_perf);
-	min_perf = READ_ONCE(cpudata->lowest_nonlinear_perf);
+	min_perf = READ_ONCE(cpudata->lowest_perf);
 	max_perf = cap_perf;
 
 	freqs.old = policy->cur;
@@ -357,8 +368,6 @@ static void amd_pstate_adjust_perf(unsigned int cpu,
 	if (max_perf < min_perf)
 		max_perf = min_perf;
 
-	des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf);
-
 	amd_pstate_update(cpudata, min_perf, des_perf, max_perf, true);
 }
 
@@ -555,9 +564,7 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
 
 static int amd_pstate_cpu_exit(struct cpufreq_policy *policy)
 {
-	struct amd_cpudata *cpudata;
-
-	cpudata = policy->driver_data;
+	struct amd_cpudata *cpudata = policy->driver_data;
 
 	freq_qos_remove_request(&cpudata->req[1]);
 	freq_qos_remove_request(&cpudata->req[0]);
@@ -599,9 +606,7 @@ static ssize_t show_amd_pstate_max_freq(struct cpufreq_policy *policy,
 					char *buf)
 {
 	int max_freq;
-	struct amd_cpudata *cpudata;
-
-	cpudata = policy->driver_data;
+	struct amd_cpudata *cpudata = policy->driver_data;
 
 	max_freq = amd_get_max_freq(cpudata);
 	if (max_freq < 0)
@@ -614,9 +619,7 @@ static ssize_t show_amd_pstate_lowest_nonlinear_freq(struct cpufreq_policy *poli
 						     char *buf)
 {
 	int freq;
-	struct amd_cpudata *cpudata;
-
-	cpudata = policy->driver_data;
+	struct amd_cpudata *cpudata = policy->driver_data;
 
 	freq = amd_get_lowest_nonlinear_freq(cpudata);
 	if (freq < 0)
@@ -662,7 +665,7 @@ static struct cpufreq_driver amd_pstate_driver = {
 	.resume		= amd_pstate_cpu_resume,
 	.set_boost	= amd_pstate_set_boost,
 	.name		= "amd-pstate",
-	.attr           = amd_pstate_attr,
+	.attr		= amd_pstate_attr,
 };
 
 static int __init amd_pstate_init(void)

drivers/cpufreq/bmips-cpufreq.c

@@ -156,7 +156,7 @@ static struct cpufreq_driver bmips_cpufreq_driver = {
 	.name		= BMIPS_CPUFREQ_PREFIX,
 };
 
-static int __init bmips_cpufreq_probe(void)
+static int __init bmips_cpufreq_driver_init(void)
 {
 	struct cpufreq_compat *cc;
 	struct device_node *np;
@@ -176,7 +176,13 @@ static int __init bmips_cpufreq_probe(void)
 
 	return cpufreq_register_driver(&bmips_cpufreq_driver);
 }
-device_initcall(bmips_cpufreq_probe);
+module_init(bmips_cpufreq_driver_init);
+
+static void __exit bmips_cpufreq_driver_exit(void)
+{
+	cpufreq_unregister_driver(&bmips_cpufreq_driver);
+}
+module_exit(bmips_cpufreq_driver_exit);
 
 MODULE_AUTHOR("Markus Mayer <[email protected]>");
 MODULE_DESCRIPTION("CPUfreq driver for Broadcom BMIPS SoCs");

drivers/cpufreq/cpufreq-dt-platdev.c

@@ -146,6 +146,7 @@ static const struct of_device_id blocklist[] __initconst = {
 	{ .compatible = "qcom,sc8180x", },
 	{ .compatible = "qcom,sc8280xp", },
 	{ .compatible = "qcom,sdm845", },
+	{ .compatible = "qcom,sm6115", },
 	{ .compatible = "qcom,sm6350", },
 	{ .compatible = "qcom,sm8150", },
 	{ .compatible = "qcom,sm8250", },

drivers/cpufreq/highbank-cpufreq.c

@@ -55,7 +55,7 @@ static struct notifier_block hb_cpufreq_clk_nb = {
 	.notifier_call = hb_cpufreq_clk_notify,
 };
 
-static int hb_cpufreq_driver_init(void)
+static int __init hb_cpufreq_driver_init(void)
 {
 	struct platform_device_info devinfo = { .name = "cpufreq-dt", };
 	struct device *cpu_dev;

drivers/cpufreq/intel_pstate.c

@@ -2416,6 +2416,7 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
 	X86_MATCH(SKYLAKE_X,		core_funcs),
 	X86_MATCH(COMETLAKE,		core_funcs),
 	X86_MATCH(ICELAKE_X,		core_funcs),
+	X86_MATCH(TIGERLAKE,		core_funcs),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);

drivers/cpufreq/qcom-cpufreq-hw.c

@@ -13,6 +13,7 @@
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
 #include <linux/pm_opp.h>
+#include <linux/pm_qos.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/units.h>
@@ -56,6 +57,8 @@ struct qcom_cpufreq_data {
 	struct cpufreq_policy *policy;
 
 	bool per_core_dcvs;
+
+	struct freq_qos_request throttle_freq_req;
 };
 
 static unsigned long cpu_hw_rate, xo_rate;
@@ -316,14 +319,16 @@ static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data)
 	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;
-
-		/* Update thermal pressure (the boost frequencies are accepted) */
-		arch_update_thermal_pressure(policy->related_cpus, throttled_freq);
-
 		dev_pm_opp_put(opp);
 	}
 
+	throttled_freq = freq_hz / HZ_PER_KHZ;
+
+	freq_qos_update_request(&data->throttle_freq_req, throttled_freq);
+
+	/* Update thermal pressure (the boost frequencies are accepted) */
+	arch_update_thermal_pressure(policy->related_cpus, throttled_freq);
+
 	/*
 	 * In the unlikely case policy is unregistered do not enable
 	 * polling or h/w interrupt
@@ -413,6 +418,14 @@ static int qcom_cpufreq_hw_lmh_init(struct cpufreq_policy *policy, int index)
 	if (data->throttle_irq < 0)
 		return data->throttle_irq;
 
+	ret = freq_qos_add_request(&policy->constraints,
+				   &data->throttle_freq_req, FREQ_QOS_MAX,
+				   FREQ_QOS_MAX_DEFAULT_VALUE);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to add freq constraint (%d)\n", ret);
+		return ret;
+	}
+
 	data->cancel_throttle = false;
 	data->policy = policy;
 
@@ -479,6 +492,7 @@ static void qcom_cpufreq_hw_lmh_exit(struct qcom_cpufreq_data *data)
 	if (data->throttle_irq <= 0)
 		return;
 
+	freq_qos_remove_request(&data->throttle_freq_req);
 	free_irq(data->throttle_irq, data);
 }
 

drivers/cpufreq/sti-cpufreq.c

@@ -252,7 +252,7 @@ static int sti_cpufreq_fetch_syscon_registers(void)
 	return 0;
 }
 
-static int sti_cpufreq_init(void)
+static int __init sti_cpufreq_init(void)
 {
 	int ret;
 

drivers/cpufreq/tegra194-cpufreq.c

@@ -38,14 +38,6 @@
 /* cpufreq transisition latency */
 #define TEGRA_CPUFREQ_TRANSITION_LATENCY (300 * 1000) /* unit in nanoseconds */
 
-enum cluster {
-	CLUSTER0,
-	CLUSTER1,
-	CLUSTER2,
-	CLUSTER3,
-	MAX_CLUSTERS,
-};
-
 struct tegra_cpu_ctr {
 	u32 cpu;
 	u32 coreclk_cnt, last_coreclk_cnt;
@@ -67,12 +59,12 @@ struct tegra_cpufreq_ops {
 struct tegra_cpufreq_soc {
 	struct tegra_cpufreq_ops *ops;
 	int maxcpus_per_cluster;
+	unsigned int num_clusters;
 	phys_addr_t actmon_cntr_base;
 };
 
 struct tegra194_cpufreq_data {
 	void __iomem *regs;
-	size_t num_clusters;
 	struct cpufreq_frequency_table **tables;
 	const struct tegra_cpufreq_soc *soc;
 };
@@ -166,6 +158,14 @@ static const struct tegra_cpufreq_soc tegra234_cpufreq_soc = {
 	.ops = &tegra234_cpufreq_ops,
 	.actmon_cntr_base = 0x9000,
 	.maxcpus_per_cluster = 4,
+	.num_clusters = 3,
+};
+
+static const struct tegra_cpufreq_soc tegra239_cpufreq_soc = {
+	.ops = &tegra234_cpufreq_ops,
+	.actmon_cntr_base = 0x4000,
+	.maxcpus_per_cluster = 8,
+	.num_clusters = 1,
 };
 
 static void tegra194_get_cpu_cluster_id(u32 cpu, u32 *cpuid, u32 *clusterid)
@@ -314,11 +314,7 @@ static void tegra194_get_cpu_ndiv_sysreg(void *ndiv)
 
 static int tegra194_get_cpu_ndiv(u32 cpu, u32 cpuid, u32 clusterid, u64 *ndiv)
 {
-	int ret;
-
-	ret = smp_call_function_single(cpu, tegra194_get_cpu_ndiv_sysreg, &ndiv, true);
-
-	return ret;
+	return smp_call_function_single(cpu, tegra194_get_cpu_ndiv_sysreg, &ndiv, true);
 }
 
 static void tegra194_set_cpu_ndiv_sysreg(void *data)
@@ -382,7 +378,7 @@ static int tegra194_cpufreq_init(struct cpufreq_policy *policy)
 
 	data->soc->ops->get_cpu_cluster_id(policy->cpu, NULL, &clusterid);
 
-	if (clusterid >= data->num_clusters || !data->tables[clusterid])
+	if (clusterid >= data->soc->num_clusters || !data->tables[clusterid])
 		return -EINVAL;
 
 	start_cpu = rounddown(policy->cpu, maxcpus_per_cluster);
@@ -433,6 +429,7 @@ static struct tegra_cpufreq_ops tegra194_cpufreq_ops = {
 static const struct tegra_cpufreq_soc tegra194_cpufreq_soc = {
 	.ops = &tegra194_cpufreq_ops,
 	.maxcpus_per_cluster = 2,
+	.num_clusters = 4,
 };
 
 static void tegra194_cpufreq_free_resources(void)
@@ -525,15 +522,14 @@ static int tegra194_cpufreq_probe(struct platform_device *pdev)
 
 	soc = of_device_get_match_data(&pdev->dev);
 
-	if (soc->ops && soc->maxcpus_per_cluster) {
+	if (soc->ops && soc->maxcpus_per_cluster && soc->num_clusters) {
 		data->soc = soc;
 	} else {
 		dev_err(&pdev->dev, "soc data missing\n");
 		return -EINVAL;
 	}
 
-	data->num_clusters = MAX_CLUSTERS;
-	data->tables = devm_kcalloc(&pdev->dev, data->num_clusters,
+	data->tables = devm_kcalloc(&pdev->dev, data->soc->num_clusters,
 				    sizeof(*data->tables), GFP_KERNEL);
 	if (!data->tables)
 		return -ENOMEM;
@@ -558,7 +554,7 @@ static int tegra194_cpufreq_probe(struct platform_device *pdev)
 		goto put_bpmp;
 	}
 
-	for (i = 0; i < data->num_clusters; i++) {
+	for (i = 0; i < data->soc->num_clusters; i++) {
 		data->tables[i] = init_freq_table(pdev, bpmp, i);
 		if (IS_ERR(data->tables[i])) {
 			err = PTR_ERR(data->tables[i]);
@@ -590,6 +586,7 @@ static int tegra194_cpufreq_remove(struct platform_device *pdev)
 static const struct of_device_id tegra194_cpufreq_of_match[] = {
 	{ .compatible = "nvidia,tegra194-ccplex", .data = &tegra194_cpufreq_soc },
 	{ .compatible = "nvidia,tegra234-ccplex-cluster", .data = &tegra234_cpufreq_soc },
+	{ .compatible = "nvidia,tegra239-ccplex-cluster", .data = &tegra239_cpufreq_soc },
 	{ /* sentinel */ }
 };
 

drivers/cpufreq/ti-cpufreq.c

@@ -398,7 +398,7 @@ static int ti_cpufreq_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int ti_cpufreq_init(void)
+static int __init ti_cpufreq_init(void)
 {
 	const struct of_device_id *match;
 

drivers/cpuidle/coupled.c

@@ -54,7 +54,7 @@
  * variable is not locked.  It is only written from the cpu that
  * it stores (or by the on/offlining cpu if that cpu is offline),
  * and only read after all the cpus are ready for the coupled idle
- * state are are no longer updating it.
+ * state are no longer updating it.
  *
  * Three atomic counters are used.  alive_count tracks the number
  * of cpus in the coupled set that are currently or soon will be