Merge branch 'pm-cpufreq'

Merge cpufreq changes for 6.1-rc1:

 - 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).

* pm-cpufreq:
  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
  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
  cpufreq: amd-pstate: Fix initial highest_perf value
  cpufreq: tegra194: Remove the unneeded result variable
  cpufreq: amd-pstate: update pstate frequency transition delay time
  cpufreq: amd_pstate: map desired perf into pstate scope for powersave governor
  cpufreq: amd_pstate: fix wrong lowest perf fetch
  cpufreq: amd-pstate: fix white-space
  cpufreq: amd-pstate: simplify cpudata pointer assignment
  cpufreq: bmips-cpufreq: Use module_init and add module_exit
  cpufreq: schedutil: Move max CPU capacity to sugov_policy
  cpufreq: Add SM6115 to cpufreq-dt-platdev blocklist

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
@@ -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)

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 <mmayer@broadcom.com>");
 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 {
+		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);
 
-		dev_pm_opp_put(opp);
-	}
-
 	/*
 	 * 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;
 

kernel/sched/cpufreq_schedutil.c

@@ -25,6 +25,9 @@ struct sugov_policy {
 	unsigned int		next_freq;
 	unsigned int		cached_raw_freq;
 
+	/* max CPU capacity, which is equal for all CPUs in freq. domain */
+	unsigned long		max;
+
 	/* The next fields are only needed if fast switch cannot be used: */
 	struct			irq_work irq_work;
 	struct			kthread_work work;
@@ -48,7 +51,6 @@ struct sugov_cpu {
 
 	unsigned long		util;
 	unsigned long		bw_dl;
-	unsigned long		max;
 
 	/* The field below is for single-CPU policies only: */
 #ifdef CONFIG_NO_HZ_COMMON
@@ -158,7 +160,6 @@ static void sugov_get_util(struct sugov_cpu *sg_cpu)
 {
 	struct rq *rq = cpu_rq(sg_cpu->cpu);
 
-	sg_cpu->max = arch_scale_cpu_capacity(sg_cpu->cpu);
 	sg_cpu->bw_dl = cpu_bw_dl(rq);
 	sg_cpu->util = effective_cpu_util(sg_cpu->cpu, cpu_util_cfs(sg_cpu->cpu),
 					  FREQUENCY_UTIL, NULL);
@@ -253,6 +254,7 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
  */
 static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time)
 {
+	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
 	unsigned long boost;
 
 	/* No boost currently required */
@@ -280,7 +282,8 @@ static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time)
 	 * sg_cpu->util is already in capacity scale; convert iowait_boost
 	 * into the same scale so we can compare.
 	 */
-	boost = (sg_cpu->iowait_boost * sg_cpu->max) >> SCHED_CAPACITY_SHIFT;
+	boost = sg_cpu->iowait_boost * sg_policy->max;
+	boost >>= SCHED_CAPACITY_SHIFT;
 	boost = uclamp_rq_util_with(cpu_rq(sg_cpu->cpu), boost, NULL);
 	if (sg_cpu->util < boost)
 		sg_cpu->util = boost;
@@ -337,7 +340,7 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
 	if (!sugov_update_single_common(sg_cpu, time, flags))
 		return;
 
-	next_f = get_next_freq(sg_policy, sg_cpu->util, sg_cpu->max);
+	next_f = get_next_freq(sg_policy, sg_cpu->util, sg_policy->max);
 	/*
 	 * Do not reduce the frequency if the CPU has not been idle
 	 * recently, as the reduction is likely to be premature then.
@@ -373,6 +376,7 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time,
 				     unsigned int flags)
 {
 	struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util);
+	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
 	unsigned long prev_util = sg_cpu->util;
 
 	/*
@@ -399,7 +403,8 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time,
 		sg_cpu->util = prev_util;
 
 	cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl),
-				   map_util_perf(sg_cpu->util), sg_cpu->max);
+				   map_util_perf(sg_cpu->util),
+				   sg_policy->max);
 
 	sg_cpu->sg_policy->last_freq_update_time = time;
 }
@@ -408,25 +413,19 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
 {
 	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
 	struct cpufreq_policy *policy = sg_policy->policy;
-	unsigned long util = 0, max = 1;
+	unsigned long util = 0;
 	unsigned int j;
 
 	for_each_cpu(j, policy->cpus) {
 		struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j);
-		unsigned long j_util, j_max;
 
 		sugov_get_util(j_sg_cpu);
 		sugov_iowait_apply(j_sg_cpu, time);
-		j_util = j_sg_cpu->util;
-		j_max = j_sg_cpu->max;
 
-		if (j_util * max > j_max * util) {
-			util = j_util;
-			max = j_max;
-		}
+		util = max(j_sg_cpu->util, util);
 	}
 
-	return get_next_freq(sg_policy, util, max);
+	return get_next_freq(sg_policy, util, sg_policy->max);
 }
 
 static void
@@ -752,7 +751,7 @@ static int sugov_start(struct cpufreq_policy *policy)
 {
 	struct sugov_policy *sg_policy = policy->governor_data;
 	void (*uu)(struct update_util_data *data, u64 time, unsigned int flags);
-	unsigned int cpu;
+	unsigned int cpu = cpumask_first(policy->cpus);
 
 	sg_policy->freq_update_delay_ns	= sg_policy->tunables->rate_limit_us * NSEC_PER_USEC;
 	sg_policy->last_freq_update_time	= 0;
@@ -760,6 +759,7 @@ static int sugov_start(struct cpufreq_policy *policy)
 	sg_policy->work_in_progress		= false;
 	sg_policy->limits_changed		= false;
 	sg_policy->cached_raw_freq		= 0;
+	sg_policy->max				= arch_scale_cpu_capacity(cpu);
 
 	sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS);