Merge tag 'pm-6.13-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management fixes from Rafael Wysocki:
 "These fix some amd-pstate driver issues:

   - Detect preferred core support in amd-pstate before driver
     registration to avoid initialization ordering issues (K Prateek
     Nayak)

   - Fix issues with with boost numerator handling in amd-pstate leading
     to inconsistently programmed CPPC max performance values (Mario
     Limonciello)"

* tag 'pm-6.13-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  cpufreq/amd-pstate: Use boost numerator for upper bound of frequencies
  cpufreq/amd-pstate: Store the boost numerator as highest perf again
  cpufreq/amd-pstate: Detect preferred core support before driver registration

Author: torvalds

Documentation/admin-guide/pm/amd-pstate.rst

@@ -251,9 +251,7 @@ performance supported in `AMD CPPC Performance Capability <perf_cap_>`_).
 In some ASICs, the highest CPPC performance is not the one in the ``_CPC``
 table, so we need to expose it to sysfs. If boost is not active, but
 still supported, this maximum frequency will be larger than the one in
-``cpuinfo``. On systems that support preferred core, the driver will have
-different values for some cores than others and this will reflect the values
-advertised by the platform at bootup.
+``cpuinfo``.
 This attribute is read-only.
 
 ``amd_pstate_lowest_nonlinear_freq``

drivers/cpufreq/amd-pstate.c

@@ -374,15 +374,19 @@ static inline int amd_pstate_cppc_enable(bool enable)
 
 static int msr_init_perf(struct amd_cpudata *cpudata)
 {
-	u64 cap1;
+	u64 cap1, numerator;
 
 	int ret = rdmsrl_safe_on_cpu(cpudata->cpu, MSR_AMD_CPPC_CAP1,
 				     &cap1);
 	if (ret)
 		return ret;
 
-	WRITE_ONCE(cpudata->highest_perf, AMD_CPPC_HIGHEST_PERF(cap1));
-	WRITE_ONCE(cpudata->max_limit_perf, AMD_CPPC_HIGHEST_PERF(cap1));
+	ret = amd_get_boost_ratio_numerator(cpudata->cpu, &numerator);
+	if (ret)
+		return ret;
+
+	WRITE_ONCE(cpudata->highest_perf, numerator);
+	WRITE_ONCE(cpudata->max_limit_perf, numerator);
 	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));
@@ -394,13 +398,18 @@ static int msr_init_perf(struct amd_cpudata *cpudata)
 static int shmem_init_perf(struct amd_cpudata *cpudata)
 {
 	struct cppc_perf_caps cppc_perf;
+	u64 numerator;
 
 	int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf);
 	if (ret)
 		return ret;
 
-	WRITE_ONCE(cpudata->highest_perf, cppc_perf.highest_perf);
-	WRITE_ONCE(cpudata->max_limit_perf, cppc_perf.highest_perf);
+	ret = amd_get_boost_ratio_numerator(cpudata->cpu, &numerator);
+	if (ret)
+		return ret;
+
+	WRITE_ONCE(cpudata->highest_perf, numerator);
+	WRITE_ONCE(cpudata->max_limit_perf, numerator);
 	WRITE_ONCE(cpudata->nominal_perf, cppc_perf.nominal_perf);
 	WRITE_ONCE(cpudata->lowest_nonlinear_perf,
 		   cppc_perf.lowest_nonlinear_perf);
@@ -561,16 +570,13 @@ static int amd_pstate_verify(struct cpufreq_policy_data *policy_data)
 
 static int amd_pstate_update_min_max_limit(struct cpufreq_policy *policy)
 {
-	u32 max_limit_perf, min_limit_perf, lowest_perf, max_perf;
+	u32 max_limit_perf, min_limit_perf, lowest_perf, max_perf, max_freq;
 	struct amd_cpudata *cpudata = policy->driver_data;
 
-	if (cpudata->boost_supported && !policy->boost_enabled)
-		max_perf = READ_ONCE(cpudata->nominal_perf);
-	else
-		max_perf = READ_ONCE(cpudata->highest_perf);
-
-	max_limit_perf = div_u64(policy->max * max_perf, policy->cpuinfo.max_freq);
-	min_limit_perf = div_u64(policy->min * max_perf, policy->cpuinfo.max_freq);
+	max_perf = READ_ONCE(cpudata->highest_perf);
+	max_freq = READ_ONCE(cpudata->max_freq);
+	max_limit_perf = div_u64(policy->max * max_perf, max_freq);
+	min_limit_perf = div_u64(policy->min * max_perf, max_freq);
 
 	lowest_perf = READ_ONCE(cpudata->lowest_perf);
 	if (min_limit_perf < lowest_perf)
@@ -889,7 +895,6 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata)
 {
 	int ret;
 	u32 min_freq, max_freq;
-	u64 numerator;
 	u32 nominal_perf, nominal_freq;
 	u32 lowest_nonlinear_perf, lowest_nonlinear_freq;
 	u32 boost_ratio, lowest_nonlinear_ratio;
@@ -911,10 +916,7 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata)
 
 	nominal_perf = READ_ONCE(cpudata->nominal_perf);
 
-	ret = amd_get_boost_ratio_numerator(cpudata->cpu, &numerator);
-	if (ret)
-		return ret;
-	boost_ratio = div_u64(numerator << SCHED_CAPACITY_SHIFT, nominal_perf);
+	boost_ratio = div_u64(cpudata->highest_perf << SCHED_CAPACITY_SHIFT, nominal_perf);
 	max_freq = (nominal_freq * boost_ratio >> SCHED_CAPACITY_SHIFT) * 1000;
 
 	lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf);
@@ -1869,18 +1871,18 @@ static int __init amd_pstate_init(void)
 		static_call_update(amd_pstate_update_perf, shmem_update_perf);
 	}
 
-	ret = amd_pstate_register_driver(cppc_state);
-	if (ret) {
-		pr_err("failed to register with return %d\n", ret);
-		return ret;
-	}
-
 	if (amd_pstate_prefcore) {
 		ret = amd_detect_prefcore(&amd_pstate_prefcore);
 		if (ret)
 			return ret;
 	}
 
+	ret = amd_pstate_register_driver(cppc_state);
+	if (ret) {
+		pr_err("failed to register with return %d\n", ret);
+		return ret;
+	}
+
 	dev_root = bus_get_dev_root(&cpu_subsys);
 	if (dev_root) {
 		ret = sysfs_create_group(&dev_root->kobj, &amd_pstate_global_attr_group);