Merge branch 'pm-cpufreq'

Merge cpufreq changes for 6.9-rc1:

 - Enable preferred core support in the amd-pstate cpufreq driver (Meng
   Li).

 - Fix min_perf assignment in amd_pstate_adjust_perf() and make the
   min/max limit perf values in amd-pstate always stay within the
   (highest perf, lowest perf) range (Tor Vic, Meng Li).

 - Change default transition delay in cpufreq to 2ms (Qais Yousef).

 - Drop long-unused cpudata::prev_cummulative_iowait from the
   intel_pstate cpufreq driver (Jiri Slaby).

 - Allow intel_pstate to assign model-specific values to strings used in
   the EPP sysfs interface and make it do so on Meteor Lake (Srinivas
   Pandruvada).

 - Remove references to 10ms minimum sampling rate from comments in the
   cpufreq code (Pierre Gondois).

 - Prevent scaling_cur_freq from exceeding scaling_max_freq when the
   latter is an inefficient frequency (Shivnandan Kumar).

 - Honour transition_latency over transition_delay_us in cpufreq (Qais
   Yousef).

 - Stop unregistering cpufreq cooling on CPU hot-remove (Viresh Kumar).

 - General enhancements / cleanups to ARM cpufreq drivers (tianyu2,
   Nícolas F. R. A. Prado, Erick Archer, Arnd Bergmann, Anastasia
   Belova).

 - Update cpufreq-dt-platdev to block/approve devices (Richard Acayan).

 - Make the SCMI cpufreq driver get a transition delay value from
   firmware (Pierre Gondois).

* pm-cpufreq: (28 commits)
  cpufreq: scmi: Set transition_delay_us
  firmware: arm_scmi: Populate fast channel rate_limit
  firmware: arm_scmi: Populate perf commands rate_limit
  cpufreq: Don't unregister cpufreq cooling on CPU hotplug
  cpufreq: Honour transition_latency over transition_delay_us
  cpufreq: Limit resolving a frequency to policy min/max
  cpufreq: amd-pstate: adjust min/max limit perf
  cpufreq: Remove references to 10ms min sampling rate
  cpufreq: intel_pstate: Update default EPPs for Meteor Lake
  cpufreq: intel_pstate: Allow model specific EPPs
  cpufreq: qcom-hw: add CONFIG_COMMON_CLK dependency
  cpufreq: dt-platdev: block SDM670 in cpufreq-dt-platdev
  cpufreq: intel_pstate: remove cpudata::prev_cummulative_iowait
  cpufreq: Change default transition delay to 2ms
  cpufreq: amd-pstate: Fix min_perf assignment in amd_pstate_adjust_perf()
  Documentation: PM: amd-pstate: Fix section title underline
  Documentation: introduce amd-pstate preferrd core mode kernel command line options
  Documentation: amd-pstate: introduce amd-pstate preferred core
  cpufreq: amd-pstate: Update amd-pstate preferred core ranking dynamically
  ACPI: cpufreq: Add highest perf change notification
  ...

4 files changed, 39 insertions, 4 deletions

diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h
index 3a0995f8bce8..930b6afba6f4 100644
--- a/include/acpi/cppc_acpi.h
+++ b/include/acpi/cppc_acpi.h
@@ -139,6 +139,7 @@ struct cppc_cpudata {
 #ifdef CONFIG_ACPI_CPPC_LIB
 extern int cppc_get_desired_perf(int cpunum, u64 *desired_perf);
 extern int cppc_get_nominal_perf(int cpunum, u64 *nominal_perf);
+extern int cppc_get_highest_perf(int cpunum, u64 *highest_perf);
 extern int cppc_get_perf_ctrs(int cpu, struct cppc_perf_fb_ctrs *perf_fb_ctrs);
 extern int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls);
 extern int cppc_set_enable(int cpu, bool enable);
@@ -167,6 +168,10 @@ static inline int cppc_get_nominal_perf(int cpunum, u64 *nominal_perf)
 {
 	return -ENOTSUPP;
 }
+static inline int cppc_get_highest_perf(int cpunum, u64 *highest_perf)
+{
+	return -ENOTSUPP;
+}
 static inline int cppc_get_perf_ctrs(int cpu, struct cppc_perf_fb_ctrs *perf_fb_ctrs)
 {
 	return -ENOTSUPP;
diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h
index 6ad02ad9c7b4..d21838835abd 100644
--- a/include/linux/amd-pstate.h
+++ b/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
@@ -52,6 +57,9 @@ struct amd_aperf_mperf {
  * @prev: Last Aperf/Mperf/tsc count value read from register
  * @freq: current cpu frequency value
  * @boost_supported: check whether the Processor or SBIOS supports boost mode
+ * @hw_prefcore: check whether HW supports preferred core featue.
+ * 		  Only when hw_prefcore and early prefcore param are true,
+ * 		  AMD P-State driver supports preferred core featue.
  * @epp_policy: Last saved policy used to set energy-performance preference
  * @epp_cached: Cached CPPC energy-performance preference value
  * @policy: Cpufreq policy value
@@ -70,6 +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;
@@ -85,6 +94,7 @@ struct amd_cpudata {
 
 	u64	freq;
 	bool	boost_supported;
+	bool	hw_prefcore;
 
 	/* EPP feature related attributes*/
 	s16	epp_policy;
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index afda5f24d3dd..692ea6e55129 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -263,6 +263,7 @@ static inline bool cpufreq_supports_freq_invariance(void)
 	return false;
 }
 static inline void disable_cpufreq(void) { }
+static inline void cpufreq_update_limits(unsigned int cpu) { }
 #endif
 
 #ifdef CONFIG_CPU_FREQ_STAT
@@ -568,9 +569,7 @@ static inline unsigned long cpufreq_scale(unsigned long old, u_int div,
 
 /*
  * The polling frequency depends on the capability of the processor. Default
- * polling frequency is 1000 times the transition latency of the processor. The
- * ondemand governor will work on any processor with transition latency <= 10ms,
- * using appropriate sampling rate.
+ * polling frequency is 1000 times the transition latency of the processor.
  */
 #define LATENCY_MULTIPLIER		(1000)
 
@@ -1021,6 +1020,18 @@ static inline int cpufreq_table_find_index_c(struct cpufreq_policy *policy,
 						   efficiencies);
 }
 
+static inline bool cpufreq_is_in_limits(struct cpufreq_policy *policy, int idx)
+{
+	unsigned int freq;
+
+	if (idx < 0)
+		return false;
+
+	freq = policy->freq_table[idx].frequency;
+
+	return freq == clamp_val(freq, policy->min, policy->max);
+}
+
 static inline int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
 						 unsigned int target_freq,
 						 unsigned int relation)
@@ -1054,7 +1065,8 @@ retry:
 		return 0;
 	}
 
-	if (idx < 0 && efficiencies) {
+	/* Limit frequency index to honor policy->min/max */
+	if (!cpufreq_is_in_limits(policy, idx) && efficiencies) {
 		efficiencies = false;
 		goto retry;
 	}
diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index f2f05fb42d28..fafedb3b6604 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -128,6 +128,8 @@ struct scmi_perf_domain_info {
  * @level_set: sets the performance level of a domain
  * @level_get: gets the performance level of a domain
  * @transition_latency_get: gets the DVFS transition latency for a given device
+ * @rate_limit_get: gets the minimum time (us) required between successive
+ *	requests
  * @device_opps_add: adds all the OPPs for a given device
  * @freq_set: sets the frequency for a given device using sustained frequency
  *	to sustained performance level mapping
@@ -137,6 +139,8 @@ struct scmi_perf_domain_info {
  *	at a given frequency
  * @fast_switch_possible: indicates if fast DVFS switching is possible or not
  *	for a given device
+ * @fast_switch_rate_limit: gets the minimum time (us) required between
+ *	successive fast_switching requests
  * @power_scale_mw_get: indicates if the power values provided are in milliWatts
  *	or in some other (abstract) scale
  */
@@ -154,6 +158,8 @@ struct scmi_perf_proto_ops {
 			 u32 *level, bool poll);
 	int (*transition_latency_get)(const struct scmi_protocol_handle *ph,
 				      u32 domain);
+	int (*rate_limit_get)(const struct scmi_protocol_handle *ph,
+			      u32 domain, u32 *rate_limit);
 	int (*device_opps_add)(const struct scmi_protocol_handle *ph,
 			       struct device *dev, u32 domain);
 	int (*freq_set)(const struct scmi_protocol_handle *ph, u32 domain,
@@ -164,6 +170,8 @@ struct scmi_perf_proto_ops {
 			     unsigned long *rate, unsigned long *power);
 	bool (*fast_switch_possible)(const struct scmi_protocol_handle *ph,
 				     u32 domain);
+	int (*fast_switch_rate_limit)(const struct scmi_protocol_handle *ph,
+				      u32 domain, u32 *rate_limit);
 	enum scmi_power_scale (*power_scale_get)(const struct scmi_protocol_handle *ph);
 };