Merge: cpufreq/amd-pstate: Updates to support for the "Requested CPU Min frequency" BIOS option

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-10/-/merge_requests/1491

Description:
updates for the "Requested CPU Min frequency" BIOS option

JIRA: https://issues.redhat.com/browse/RHEL-106954

Build Info: 68963996

Tested: Successful platform test results on AMD (amd-turin-volcano-06) system.

Signed-off-by: Steve Best <sbest@redhat.com>

Approved-by: Lenny Szubowicz <lszubowi@redhat.com>
Approved-by: David Arcari <darcari@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: Scott Weaver <scweaver@redhat.com>

Author: swvrrh

drivers/cpufreq/amd-pstate.c

@@ -389,7 +389,8 @@ static inline int amd_pstate_cppc_enable(struct cpufreq_policy *policy)
 static int msr_init_perf(struct amd_cpudata *cpudata)
 {
 	union perf_cached perf = READ_ONCE(cpudata->perf);
-	u64 cap1, numerator;
+	u64 cap1, numerator, cppc_req;
+	u8 min_perf;
 
 	int ret = rdmsrl_safe_on_cpu(cpudata->cpu, MSR_AMD_CPPC_CAP1,
 				     &cap1);
@@ -400,6 +401,22 @@ static int msr_init_perf(struct amd_cpudata *cpudata)
 	if (ret)
 		return ret;
 
+	ret = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, &cppc_req);
+	if (ret)
+		return ret;
+
+	WRITE_ONCE(cpudata->cppc_req_cached, cppc_req);
+	min_perf = FIELD_GET(AMD_CPPC_MIN_PERF_MASK, cppc_req);
+
+	/*
+	 * Clear out the min_perf part to check if the rest of the MSR is 0, if yes, this is an
+	 * indication that the min_perf value is the one specified through the BIOS option
+	 */
+	cppc_req &= ~(AMD_CPPC_MIN_PERF_MASK);
+
+	if (!cppc_req)
+		perf.bios_min_perf = min_perf;
+
 	perf.highest_perf = numerator;
 	perf.max_limit_perf = numerator;
 	perf.min_limit_perf = FIELD_GET(AMD_CPPC_LOWEST_PERF_MASK, cap1);
@@ -581,20 +598,26 @@ static int amd_pstate_verify(struct cpufreq_policy_data *policy_data)
 {
 	/*
 	 * Initialize lower frequency limit (i.e.policy->min) with
-	 * lowest_nonlinear_frequency which is the most energy efficient
-	 * frequency. Override the initial value set by cpufreq core and
-	 * amd-pstate qos_requests.
+	 * lowest_nonlinear_frequency or the min frequency (if) specified in BIOS,
+	 * Override the initial value set by cpufreq core and amd-pstate qos_requests.
 	 */
 	if (policy_data->min == FREQ_QOS_MIN_DEFAULT_VALUE) {
 		struct cpufreq_policy *policy __free(put_cpufreq_policy) =
 					      cpufreq_cpu_get(policy_data->cpu);
 		struct amd_cpudata *cpudata;
+		union perf_cached perf;
 
 		if (!policy)
 			return -EINVAL;
 
 		cpudata = policy->driver_data;
-		policy_data->min = cpudata->lowest_nonlinear_freq;
+		perf = READ_ONCE(cpudata->perf);
+
+		if (perf.bios_min_perf)
+			policy_data->min = perf_to_freq(perf, cpudata->nominal_freq,
+							perf.bios_min_perf);
+		else
+			policy_data->min = cpudata->lowest_nonlinear_freq;
 	}
 
 	cpufreq_verify_within_cpu_limits(policy_data);
@@ -1027,6 +1050,10 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
 static void amd_pstate_cpu_exit(struct cpufreq_policy *policy)
 {
 	struct amd_cpudata *cpudata = policy->driver_data;
+	union perf_cached perf = READ_ONCE(cpudata->perf);
+
+	/* Reset CPPC_REQ MSR to the BIOS value */
+	amd_pstate_update_perf(policy, perf.bios_min_perf, 0U, 0U, 0U, false);
 
 	freq_qos_remove_request(&cpudata->req[1]);
 	freq_qos_remove_request(&cpudata->req[0]);
@@ -1422,7 +1449,6 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 	struct amd_cpudata *cpudata;
 	union perf_cached perf;
 	struct device *dev;
-	u64 value;
 	int ret;
 
 	/*
@@ -1487,12 +1513,6 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 		cpudata->epp_default = AMD_CPPC_EPP_BALANCE_PERFORMANCE;
 	}
 
-	if (cpu_feature_enabled(X86_FEATURE_CPPC)) {
-		ret = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, &value);
-		if (ret)
-			return ret;
-		WRITE_ONCE(cpudata->cppc_req_cached, value);
-	}
 	ret = amd_pstate_set_epp(policy, cpudata->epp_default);
 	if (ret)
 		return ret;
@@ -1512,6 +1532,11 @@ static void amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy)
 	struct amd_cpudata *cpudata = policy->driver_data;
 
 	if (cpudata) {
+		union perf_cached perf = READ_ONCE(cpudata->perf);
+
+		/* Reset CPPC_REQ MSR to the BIOS value */
+		amd_pstate_update_perf(policy, perf.bios_min_perf, 0U, 0U, 0U, false);
+
 		kfree(cpudata);
 		policy->driver_data = NULL;
 	}
@@ -1562,31 +1587,60 @@ static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy)
 	return 0;
 }
 
-static int amd_pstate_epp_cpu_online(struct cpufreq_policy *policy)
+static int amd_pstate_cpu_online(struct cpufreq_policy *policy)
 {
-	pr_debug("AMD CPU Core %d going online\n", policy->cpu);
-
 	return amd_pstate_cppc_enable(policy);
 }
 
-static int amd_pstate_epp_cpu_offline(struct cpufreq_policy *policy)
+static int amd_pstate_cpu_offline(struct cpufreq_policy *policy)
 {
-	return 0;
+	struct amd_cpudata *cpudata = policy->driver_data;
+	union perf_cached perf = READ_ONCE(cpudata->perf);
+
+	/*
+	 * Reset CPPC_REQ MSR to the BIOS value, this will allow us to retain the BIOS specified
+	 * min_perf value across kexec reboots. If this CPU is just onlined normally after this, the
+	 * limits, epp and desired perf will get reset to the cached values in cpudata struct
+	 */
+	return amd_pstate_update_perf(policy, perf.bios_min_perf, 0U, 0U, 0U, false);
 }
 
-static int amd_pstate_epp_suspend(struct cpufreq_policy *policy)
+static int amd_pstate_suspend(struct cpufreq_policy *policy)
 {
 	struct amd_cpudata *cpudata = policy->driver_data;
+	union perf_cached perf = READ_ONCE(cpudata->perf);
+	int ret;
 
-	/* invalidate to ensure it's rewritten during resume */
-	cpudata->cppc_req_cached = 0;
+	/*
+	 * Reset CPPC_REQ MSR to the BIOS value, this will allow us to retain the BIOS specified
+	 * min_perf value across kexec reboots. If this CPU is just resumed back without kexec,
+	 * the limits, epp and desired perf will get reset to the cached values in cpudata struct
+	 */
+	ret = amd_pstate_update_perf(policy, perf.bios_min_perf,
+				     FIELD_GET(AMD_CPPC_DES_PERF_MASK, cpudata->cppc_req_cached),
+				     FIELD_GET(AMD_CPPC_MAX_PERF_MASK, cpudata->cppc_req_cached),
+				     FIELD_GET(AMD_CPPC_EPP_PERF_MASK, cpudata->cppc_req_cached),
+				     false);
+	if (ret)
+		return ret;
 
 	/* set this flag to avoid setting core offline*/
 	cpudata->suspended = true;
 
 	return 0;
 }
 
+static int amd_pstate_resume(struct cpufreq_policy *policy)
+{
+	struct amd_cpudata *cpudata = policy->driver_data;
+	union perf_cached perf = READ_ONCE(cpudata->perf);
+	int cur_perf = freq_to_perf(perf, cpudata->nominal_freq, policy->cur);
+
+	/* Set CPPC_REQ to last sane value until the governor updates it */
+	return amd_pstate_update_perf(policy, perf.min_limit_perf, cur_perf, perf.max_limit_perf,
+				      0U, false);
+}
+
 static int amd_pstate_epp_resume(struct cpufreq_policy *policy)
 {
 	struct amd_cpudata *cpudata = policy->driver_data;
@@ -1612,6 +1666,10 @@ static struct cpufreq_driver amd_pstate_driver = {
 	.fast_switch    = amd_pstate_fast_switch,
 	.init		= amd_pstate_cpu_init,
 	.exit		= amd_pstate_cpu_exit,
+	.online		= amd_pstate_cpu_online,
+	.offline	= amd_pstate_cpu_offline,
+	.suspend	= amd_pstate_suspend,
+	.resume		= amd_pstate_resume,
 	.set_boost	= amd_pstate_set_boost,
 	.update_limits	= amd_pstate_update_limits,
 	.name		= "amd-pstate",
@@ -1624,9 +1682,9 @@ static struct cpufreq_driver amd_pstate_epp_driver = {
 	.setpolicy	= amd_pstate_epp_set_policy,
 	.init		= amd_pstate_epp_cpu_init,
 	.exit		= amd_pstate_epp_cpu_exit,
-	.offline	= amd_pstate_epp_cpu_offline,
-	.online		= amd_pstate_epp_cpu_online,
-	.suspend	= amd_pstate_epp_suspend,
+	.offline	= amd_pstate_cpu_offline,
+	.online		= amd_pstate_cpu_online,
+	.suspend	= amd_pstate_suspend,
 	.resume		= amd_pstate_epp_resume,
 	.update_limits	= amd_pstate_update_limits,
 	.set_boost	= amd_pstate_set_boost,

drivers/cpufreq/amd-pstate.h

@@ -30,6 +30,7 @@
  * @lowest_perf: the absolute lowest performance level of the processor
  * @min_limit_perf: Cached value of the performance corresponding to policy->min
  * @max_limit_perf: Cached value of the performance corresponding to policy->max
+ * @bios_min_perf: Cached perf value corresponding to the "Requested CPU Min Frequency" BIOS option
  */
 union perf_cached {
 	struct {
@@ -39,6 +40,7 @@ union perf_cached {
 		u8	lowest_perf;
 		u8	min_limit_perf;
 		u8	max_limit_perf;
+		u8	bios_min_perf;
 	};
 	u64	val;
 };