Merging upstream version 6.9.2.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 205 insertions, 9 deletions

diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 07f341995..28166df81 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -37,6 +37,7 @@
 #include <linux/uaccess.h>
 #include <linux/static_call.h>
 #include <linux/amd-pstate.h>
+#include <linux/topology.h>
 
 #include <acpi/processor.h>
 #include <acpi/cppc_acpi.h>
@@ -49,6 +50,8 @@
 
 #define AMD_PSTATE_TRANSITION_LATENCY	20000
 #define AMD_PSTATE_TRANSITION_DELAY	1000
+#define CPPC_HIGHEST_PERF_PERFORMANCE	196
+#define CPPC_HIGHEST_PERF_DEFAULT	166
 
 /*
  * TODO: We need more time to fine tune processors with shared memory solution
@@ -64,6 +67,7 @@ static struct cpufreq_driver amd_pstate_driver;
 static struct cpufreq_driver amd_pstate_epp_driver;
 static int cppc_state = AMD_PSTATE_UNDEFINED;
 static bool cppc_enabled;
+static bool amd_pstate_prefcore = true;
 
 /*
  * AMD Energy Preference Performance (EPP)
@@ -287,6 +291,21 @@ static inline int amd_pstate_enable(bool enable)
 	return static_call(amd_pstate_enable)(enable);
 }
 
+static u32 amd_pstate_highest_perf_set(struct amd_cpudata *cpudata)
+{
+	struct cpuinfo_x86 *c = &cpu_data(0);
+
+	/*
+	 * For AMD CPUs with Family ID 19H and Model ID range 0x70 to 0x7f,
+	 * the highest performance level is set to 196.
+	 * https://bugzilla.kernel.org/show_bug.cgi?id=218759
+	 */
+	if (c->x86 == 0x19 && (c->x86_model >= 0x70 && c->x86_model <= 0x7f))
+		return CPPC_HIGHEST_PERF_PERFORMANCE;
+
+	return CPPC_HIGHEST_PERF_DEFAULT;
+}
+
 static int pstate_init_perf(struct amd_cpudata *cpudata)
 {
 	u64 cap1;
@@ -297,13 +316,14 @@ static int pstate_init_perf(struct amd_cpudata *cpudata)
 	if (ret)
 		return ret;
 
-	/*
-	 * TODO: Introduce AMD specific power feature.
-	 *
-	 * CPPC entry doesn't indicate the highest performance in some ASICs.
+	/* 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 AMD_CPPC_HIGHEST_PERF(cap1) value as
+	 * the default max perf.
 	 */
-	highest_perf = amd_get_highest_perf();
-	if (highest_perf > AMD_CPPC_HIGHEST_PERF(cap1))
+	if (cpudata->hw_prefcore)
+		highest_perf = amd_pstate_highest_perf_set(cpudata);
+	else
 		highest_perf = AMD_CPPC_HIGHEST_PERF(cap1);
 
 	WRITE_ONCE(cpudata->highest_perf, highest_perf);
@@ -311,6 +331,7 @@ 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;
 }
@@ -324,8 +345,9 @@ static int cppc_init_perf(struct amd_cpudata *cpudata)
 	if (ret)
 		return ret;
 
-	highest_perf = amd_get_highest_perf();
-	if (highest_perf > cppc_perf.highest_perf)
+	if (cpudata->hw_prefcore)
+		highest_perf = amd_pstate_highest_perf_set(cpudata);
+	else
 		highest_perf = cppc_perf.highest_perf;
 
 	WRITE_ONCE(cpudata->highest_perf, highest_perf);
@@ -334,6 +356,7 @@ 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)
@@ -477,12 +500,19 @@ static int amd_pstate_verify(struct cpufreq_policy_data *policy)
 
 static int amd_pstate_update_min_max_limit(struct cpufreq_policy *policy)
 {
-	u32 max_limit_perf, min_limit_perf;
+	u32 max_limit_perf, min_limit_perf, lowest_perf;
 	struct amd_cpudata *cpudata = policy->driver_data;
 
 	max_limit_perf = div_u64(policy->max * cpudata->highest_perf, cpudata->max_freq);
 	min_limit_perf = div_u64(policy->min * cpudata->highest_perf, cpudata->max_freq);
 
+	lowest_perf = READ_ONCE(cpudata->lowest_perf);
+	if (min_limit_perf < lowest_perf)
+		min_limit_perf = lowest_perf;
+
+	if (max_limit_perf < min_limit_perf)
+		max_limit_perf = min_limit_perf;
+
 	WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf);
 	WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf);
 	WRITE_ONCE(cpudata->max_limit_freq, policy->max);
@@ -706,6 +736,114 @@ static void amd_perf_ctl_reset(unsigned int cpu)
 	wrmsrl_on_cpu(cpu, MSR_AMD_PERF_CTL, 0);
 }
 
+/*
+ * Set amd-pstate preferred core enable can't be done directly from cpufreq callbacks
+ * due to locking, so queue the work for later.
+ */
+static void amd_pstste_sched_prefcore_workfn(struct work_struct *work)
+{
+	sched_set_itmt_support();
+}
+static DECLARE_WORK(sched_prefcore_work, amd_pstste_sched_prefcore_workfn);
+
+/*
+ * Get the highest performance register value.
+ * @cpu: CPU from which to get highest performance.
+ * @highest_perf: Return address.
+ *
+ * Return: 0 for success, -EIO otherwise.
+ */
+static int amd_pstate_get_highest_perf(int cpu, u32 *highest_perf)
+{
+	int ret;
+
+	if (boot_cpu_has(X86_FEATURE_CPPC)) {
+		u64 cap1;
+
+		ret = rdmsrl_safe_on_cpu(cpu, MSR_AMD_CPPC_CAP1, &cap1);
+		if (ret)
+			return ret;
+		WRITE_ONCE(*highest_perf, AMD_CPPC_HIGHEST_PERF(cap1));
+	} else {
+		u64 cppc_highest_perf;
+
+		ret = cppc_get_highest_perf(cpu, &cppc_highest_perf);
+		if (ret)
+			return ret;
+		WRITE_ONCE(*highest_perf, cppc_highest_perf);
+	}
+
+	return (ret);
+}
+
+#define CPPC_MAX_PERF	U8_MAX
+
+static void amd_pstate_init_prefcore(struct amd_cpudata *cpudata)
+{
+	int ret, prio;
+	u32 highest_perf;
+
+	ret = amd_pstate_get_highest_perf(cpudata->cpu, &highest_perf);
+	if (ret)
+		return;
+
+	cpudata->hw_prefcore = true;
+	/* check if CPPC preferred core feature is enabled*/
+	if (highest_perf < CPPC_MAX_PERF)
+		prio = (int)highest_perf;
+	else {
+		pr_debug("AMD CPPC preferred core is unsupported!\n");
+		cpudata->hw_prefcore = false;
+		return;
+	}
+
+	if (!amd_pstate_prefcore)
+		return;
+
+	/*
+	 * The priorities can be set regardless of whether or not
+	 * sched_set_itmt_support(true) has been called and it is valid to
+	 * update them at any time after it has been called.
+	 */
+	sched_set_itmt_core_prio(prio, cpudata->cpu);
+
+	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;
@@ -727,6 +865,8 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
 
 	cpudata->cpu = policy->cpu;
 
+	amd_pstate_init_prefcore(cpudata);
+
 	ret = amd_pstate_init_perf(cpudata);
 	if (ret)
 		goto free_cpudata1;
@@ -877,6 +1017,28 @@ 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)
+{
+	bool hw_prefcore;
+	struct amd_cpudata *cpudata = policy->driver_data;
+
+	hw_prefcore = READ_ONCE(cpudata->hw_prefcore);
+
+	return sysfs_emit(buf, "%s\n", str_enabled_disabled(hw_prefcore));
+}
+
 static ssize_t show_energy_performance_available_preferences(
 				struct cpufreq_policy *policy, char *buf)
 {
@@ -1074,18 +1236,29 @@ static ssize_t status_store(struct device *a, struct device_attribute *b,
 	return ret < 0 ? ret : count;
 }
 
+static ssize_t prefcore_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%s\n", str_enabled_disabled(amd_pstate_prefcore));
+}
+
 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);
 static DEVICE_ATTR_RW(status);
+static DEVICE_ATTR_RO(prefcore);
 
 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,
 };
 
@@ -1093,6 +1266,8 @@ 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,
 	NULL,
@@ -1100,6 +1275,7 @@ static struct freq_attr *amd_pstate_epp_attr[] = {
 
 static struct attribute *pstate_global_attributes[] = {
 	&dev_attr_status.attr,
+	&dev_attr_prefcore.attr,
 	NULL
 };
 
@@ -1151,6 +1327,8 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 	cpudata->cpu = policy->cpu;
 	cpudata->epp_policy = 0;
 
+	amd_pstate_init_prefcore(cpudata);
+
 	ret = amd_pstate_init_perf(cpudata);
 	if (ret)
 		goto free_cpudata1;
@@ -1232,6 +1410,12 @@ static void amd_pstate_epp_update_limit(struct cpufreq_policy *policy)
 	max_limit_perf = div_u64(policy->max * cpudata->highest_perf, cpudata->max_freq);
 	min_limit_perf = div_u64(policy->min * cpudata->highest_perf, cpudata->max_freq);
 
+	if (min_limit_perf < min_perf)
+		min_limit_perf = min_perf;
+
+	if (max_limit_perf < min_limit_perf)
+		max_limit_perf = min_limit_perf;
+
 	WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf);
 	WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf);
 
@@ -1432,6 +1616,7 @@ 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,
 };
@@ -1446,6 +1631,7 @@ 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,
 };
@@ -1567,7 +1753,17 @@ static int __init amd_pstate_param(char *str)
 
 	return amd_pstate_set_driver(mode_idx);
 }
+
+static int __init amd_prefcore_param(char *str)
+{
+	if (!strcmp(str, "disable"))
+		amd_pstate_prefcore = false;
+
+	return 0;
+}
+
 early_param("amd_pstate", amd_pstate_param);
+early_param("amd_prefcore", amd_prefcore_param);
 
 MODULE_AUTHOR("Huang Rui <ray.huang@amd.com>");
 MODULE_DESCRIPTION("AMD Processor P-state Frequency Driver");