cpufreq: amd-pstate: Update amd-pstate preferred core ranking dynamically

Preferred core rankings can be changed dynamically by the
platform based on the workload and platform conditions and
accounting for thermals and aging.
When this occurs, cpu priority need to be set.
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Wyes Karny <wyes.karny@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Perry Yuan <perry.yuan@amd.com>
Signed-off-by: Meng Li <li.meng@amd.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

drivers/cpufreq/amd-pstate.c

@@ -315,6 +315,7 @@ static int pstate_init_perf(struct amd_cpudata *cpudata)
 	WRITE_ONCE(cpudata->nominal_perf, AMD_CPPC_NOMINAL_PERF(cap1));
 	WRITE_ONCE(cpudata->lowest_nonlinear_perf, AMD_CPPC_LOWNONLIN_PERF(cap1));
 	WRITE_ONCE(cpudata->lowest_perf, AMD_CPPC_LOWEST_PERF(cap1));
+	WRITE_ONCE(cpudata->prefcore_ranking, AMD_CPPC_HIGHEST_PERF(cap1));
 	WRITE_ONCE(cpudata->min_limit_perf, AMD_CPPC_LOWEST_PERF(cap1));
 	return 0;
 }
@@ -339,6 +340,7 @@ static int cppc_init_perf(struct amd_cpudata *cpudata)
 	WRITE_ONCE(cpudata->lowest_nonlinear_perf,
 		   cppc_perf.lowest_nonlinear_perf);
 	WRITE_ONCE(cpudata->lowest_perf, cppc_perf.lowest_perf);
+	WRITE_ONCE(cpudata->prefcore_ranking, cppc_perf.highest_perf);
 	WRITE_ONCE(cpudata->min_limit_perf, cppc_perf.lowest_perf);
 
 	if (cppc_state == AMD_PSTATE_ACTIVE)
@@ -785,6 +787,40 @@ static void amd_pstate_init_prefcore(struct amd_cpudata *cpudata)
 	schedule_work(&sched_prefcore_work);
 }
 
+static void amd_pstate_update_limits(unsigned int cpu)
+{
+	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+	struct amd_cpudata *cpudata = policy->driver_data;
+	u32 prev_high = 0, cur_high = 0;
+	int ret;
+	bool highest_perf_changed = false;
+
+	mutex_lock(&amd_pstate_driver_lock);
+	if ((!amd_pstate_prefcore) || (!cpudata->hw_prefcore))
+		goto free_cpufreq_put;
+
+	ret = amd_pstate_get_highest_perf(cpu, &cur_high);
+	if (ret)
+		goto free_cpufreq_put;
+
+	prev_high = READ_ONCE(cpudata->prefcore_ranking);
+	if (prev_high != cur_high) {
+		highest_perf_changed = true;
+		WRITE_ONCE(cpudata->prefcore_ranking, cur_high);
+
+		if (cur_high < CPPC_MAX_PERF)
+			sched_set_itmt_core_prio((int)cur_high, cpu);
+	}
+
+free_cpufreq_put:
+	cpufreq_cpu_put(policy);
+
+	if (!highest_perf_changed)
+		cpufreq_update_policy(cpu);
+
+	mutex_unlock(&amd_pstate_driver_lock);
+}
+
 static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
 {
 	int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret;
@@ -958,6 +994,17 @@ static ssize_t show_amd_pstate_highest_perf(struct cpufreq_policy *policy,
 	return sysfs_emit(buf, "%u\n", perf);
 }
 
+static ssize_t show_amd_pstate_prefcore_ranking(struct cpufreq_policy *policy,
+						char *buf)
+{
+	u32 perf;
+	struct amd_cpudata *cpudata = policy->driver_data;
+
+	perf = READ_ONCE(cpudata->prefcore_ranking);
+
+	return sysfs_emit(buf, "%u\n", perf);
+}
+
 static ssize_t show_amd_pstate_hw_prefcore(struct cpufreq_policy *policy,
 					   char *buf)
 {
@@ -1176,6 +1223,7 @@ cpufreq_freq_attr_ro(amd_pstate_max_freq);
 cpufreq_freq_attr_ro(amd_pstate_lowest_nonlinear_freq);
 
 cpufreq_freq_attr_ro(amd_pstate_highest_perf);
+cpufreq_freq_attr_ro(amd_pstate_prefcore_ranking);
 cpufreq_freq_attr_ro(amd_pstate_hw_prefcore);
 cpufreq_freq_attr_rw(energy_performance_preference);
 cpufreq_freq_attr_ro(energy_performance_available_preferences);
@@ -1186,6 +1234,7 @@ static struct freq_attr *amd_pstate_attr[] = {
 	&amd_pstate_max_freq,
 	&amd_pstate_lowest_nonlinear_freq,
 	&amd_pstate_highest_perf,
+	&amd_pstate_prefcore_ranking,
 	&amd_pstate_hw_prefcore,
 	NULL,
 };
@@ -1194,6 +1243,7 @@ static struct freq_attr *amd_pstate_epp_attr[] = {
 	&amd_pstate_max_freq,
 	&amd_pstate_lowest_nonlinear_freq,
 	&amd_pstate_highest_perf,
+	&amd_pstate_prefcore_ranking,
 	&amd_pstate_hw_prefcore,
 	&energy_performance_preference,
 	&energy_performance_available_preferences,
@@ -1537,6 +1587,7 @@ static struct cpufreq_driver amd_pstate_driver = {
 	.suspend	= amd_pstate_cpu_suspend,
 	.resume		= amd_pstate_cpu_resume,
 	.set_boost	= amd_pstate_set_boost,
+	.update_limits	= amd_pstate_update_limits,
 	.name		= "amd-pstate",
 	.attr		= amd_pstate_attr,
 };
@@ -1551,6 +1602,7 @@ static struct cpufreq_driver amd_pstate_epp_driver = {
 	.online		= amd_pstate_epp_cpu_online,
 	.suspend	= amd_pstate_epp_suspend,
 	.resume		= amd_pstate_epp_resume,
+	.update_limits	= amd_pstate_update_limits,
 	.name		= "amd-pstate-epp",
 	.attr		= amd_pstate_epp_attr,
 };

include/linux/amd-pstate.h

@@ -39,11 +39,16 @@ struct amd_aperf_mperf {
  * @cppc_req_cached: cached performance request hints
  * @highest_perf: the maximum performance an individual processor may reach,
  *		  assuming ideal conditions
+ *		  For platforms that do not support the preferred core feature, the
+ *		  highest_pef may be configured with 166 or 255, to avoid max frequency
+ *		  calculated wrongly. we take the fixed value as the highest_perf.
  * @nominal_perf: the maximum sustained performance level of the processor,
  *		  assuming ideal operating conditions
  * @lowest_nonlinear_perf: the lowest performance level at which nonlinear power
  *			   savings are achieved
  * @lowest_perf: the absolute lowest performance level of the processor
+ * @prefcore_ranking: the preferred core ranking, the higher value indicates a higher
+ * 		  priority.
  * @max_freq: the frequency that mapped to highest_perf
  * @min_freq: the frequency that mapped to lowest_perf
  * @nominal_freq: the frequency that mapped to nominal_perf
@@ -73,6 +78,7 @@ struct amd_cpudata {
 	u32	nominal_perf;
 	u32	lowest_nonlinear_perf;
 	u32	lowest_perf;
+	u32     prefcore_ranking;
 	u32     min_limit_perf;
 	u32     max_limit_perf;
 	u32     min_limit_freq;