Merge: Update intel_pstate to upstream 6.17

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/7314

JIRA: https://issues.redhat.com/browse/RHEL-112493

intel_pstate is the cpu frequency driver for intel processors and
needs to be updated regularly.

Signed-off-by: David Arcari <darcari@redhat.com>

Approved-by: Rafael Aquini <raquini@redhat.com>
Approved-by: Lenny Szubowicz <lszubowi@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: CKI GitLab Kmaint Pipeline Bot <26919896-cki-kmaint-pipeline-bot@users.noreply.gitlab.com>

Author: CKI KWF Bot

drivers/base/arch_topology.c

@@ -152,14 +152,6 @@ void topology_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq,
 		per_cpu(arch_freq_scale, i) = scale;
 }
 
-DEFINE_PER_CPU(unsigned long, cpu_scale) = SCHED_CAPACITY_SCALE;
-EXPORT_PER_CPU_SYMBOL_GPL(cpu_scale);
-
-void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity)
-{
-	per_cpu(cpu_scale, cpu) = capacity;
-}
-
 DEFINE_PER_CPU(unsigned long, hw_pressure);
 
 /**
@@ -205,39 +197,9 @@ void topology_update_hw_pressure(const struct cpumask *cpus,
 }
 EXPORT_SYMBOL_GPL(topology_update_hw_pressure);
 
-static ssize_t cpu_capacity_show(struct device *dev,
-				 struct device_attribute *attr,
-				 char *buf)
-{
-	struct cpu *cpu = container_of(dev, struct cpu, dev);
-
-	return sysfs_emit(buf, "%lu\n", topology_get_cpu_scale(cpu->dev.id));
-}
-
 static void update_topology_flags_workfn(struct work_struct *work);
 static DECLARE_WORK(update_topology_flags_work, update_topology_flags_workfn);
 
-static DEVICE_ATTR_RO(cpu_capacity);
-
-static int register_cpu_capacity_sysctl(void)
-{
-	int i;
-	struct device *cpu;
-
-	for_each_possible_cpu(i) {
-		cpu = get_cpu_device(i);
-		if (!cpu) {
-			pr_err("%s: too early to get CPU%d device!\n",
-			       __func__, i);
-			continue;
-		}
-		device_create_file(cpu, &dev_attr_cpu_capacity);
-	}
-
-	return 0;
-}
-subsys_initcall(register_cpu_capacity_sysctl);
-
 static int update_topology;
 
 int topology_update_cpu_topology(void)

drivers/base/topology.c

@@ -208,3 +208,55 @@ static int __init topology_sysfs_init(void)
 }
 
 device_initcall(topology_sysfs_init);
+
+DEFINE_PER_CPU(unsigned long, cpu_scale) = SCHED_CAPACITY_SCALE;
+EXPORT_PER_CPU_SYMBOL_GPL(cpu_scale);
+
+void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity)
+{
+	per_cpu(cpu_scale, cpu) = capacity;
+}
+
+static ssize_t cpu_capacity_show(struct device *dev,
+				 struct device_attribute *attr,
+				 char *buf)
+{
+	struct cpu *cpu = container_of(dev, struct cpu, dev);
+
+	return sysfs_emit(buf, "%lu\n", topology_get_cpu_scale(cpu->dev.id));
+}
+
+static DEVICE_ATTR_RO(cpu_capacity);
+
+static int cpu_capacity_sysctl_add(unsigned int cpu)
+{
+	struct device *cpu_dev = get_cpu_device(cpu);
+
+	if (!cpu_dev)
+		return -ENOENT;
+
+	device_create_file(cpu_dev, &dev_attr_cpu_capacity);
+
+	return 0;
+}
+
+static int cpu_capacity_sysctl_remove(unsigned int cpu)
+{
+	struct device *cpu_dev = get_cpu_device(cpu);
+
+	if (!cpu_dev)
+		return -ENOENT;
+
+	device_remove_file(cpu_dev, &dev_attr_cpu_capacity);
+
+	return 0;
+}
+
+static int register_cpu_capacity_sysctl(void)
+{
+	cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "topology/cpu-capacity",
+			  cpu_capacity_sysctl_add, cpu_capacity_sysctl_remove);
+
+	return 0;
+}
+subsys_initcall(register_cpu_capacity_sysctl);

drivers/cpufreq/cpufreq.c

@@ -1587,7 +1587,7 @@ static int cpufreq_online(unsigned int cpu)
 
 		/*
 		 * Register with the energy model before
-		 * sugov_eas_rebuild_sd() is called, which will result
+		 * em_rebuild_sched_domains() is called, which will result
 		 * in rebuilding of the sched domains, which should only be done
 		 * once the energy model is properly initialized for the policy
 		 * first.

drivers/cpufreq/intel_pstate.c

@@ -29,6 +29,7 @@
 #include <linux/bitfield.h>
 #include <trace/events/power.h>
 #include <linux/units.h>
+#include <linux/cacheinfo.h>
 
 #include <asm/cpu.h>
 #include <asm/div64.h>
@@ -221,6 +222,7 @@ struct global_params {
  * @sched_flags:	Store scheduler flags for possible cross CPU update
  * @hwp_boost_min:	Last HWP boosted min performance
  * @suspended:		Whether or not the driver has been suspended.
+ * @pd_registered:	Set when a perf domain is registered for this CPU.
  * @hwp_notify_work:	workqueue for HWP notifications.
  *
  * This structure stores per CPU instance data for all CPUs.
@@ -260,6 +262,9 @@ struct cpudata {
 	unsigned int sched_flags;
 	u32 hwp_boost_min;
 	bool suspended;
+#ifdef CONFIG_ENERGY_MODEL
+	bool pd_registered;
+#endif
 	struct delayed_work hwp_notify_work;
 };
 
@@ -303,6 +308,7 @@ static bool hwp_is_hybrid;
 
 static struct cpufreq_driver *intel_pstate_driver __read_mostly;
 
+#define INTEL_PSTATE_CORE_SCALING	100000
 #define HYBRID_SCALING_FACTOR_ADL	78741
 #define HYBRID_SCALING_FACTOR_MTL	80000
 #define HYBRID_SCALING_FACTOR_LNL	86957
@@ -311,7 +317,7 @@ static int hybrid_scaling_factor;
 
 static inline int core_get_scaling(void)
 {
-	return 100000;
+	return INTEL_PSTATE_CORE_SCALING;
 }
 
 #ifdef CONFIG_ACPI
@@ -948,12 +954,124 @@ static struct cpudata *hybrid_max_perf_cpu __read_mostly;
  */
 static DEFINE_MUTEX(hybrid_capacity_lock);
 
+#ifdef CONFIG_ENERGY_MODEL
+#define HYBRID_EM_STATE_COUNT	4
+
+static int hybrid_active_power(struct device *dev, unsigned long *power,
+			       unsigned long *freq)
+{
+	/*
+	 * Create "utilization bins" of 0-40%, 40%-60%, 60%-80%, and 80%-100%
+	 * of the maximum capacity such that two CPUs of the same type will be
+	 * regarded as equally attractive if the utilization of each of them
+	 * falls into the same bin, which should prevent tasks from being
+	 * migrated between them too often.
+	 *
+	 * For this purpose, return the "frequency" of 2 for the first
+	 * performance level and otherwise leave the value set by the caller.
+	 */
+	if (!*freq)
+		*freq = 2;
+
+	/* No power information. */
+	*power = EM_MAX_POWER;
+
+	return 0;
+}
+
+static int hybrid_get_cost(struct device *dev, unsigned long freq,
+			   unsigned long *cost)
+{
+	struct pstate_data *pstate = &all_cpu_data[dev->id]->pstate;
+	struct cpu_cacheinfo *cacheinfo = get_cpu_cacheinfo(dev->id);
+
+	/*
+	 * The smaller the perf-to-frequency scaling factor, the larger the IPC
+	 * ratio between the given CPU and the least capable CPU in the system.
+	 * Regard that IPC ratio as the primary cost component and assume that
+	 * the scaling factors for different CPU types will differ by at least
+	 * 5% and they will not be above INTEL_PSTATE_CORE_SCALING.
+	 *
+	 * Add the freq value to the cost, so that the cost of running on CPUs
+	 * of the same type in different "utilization bins" is different.
+	 */
+	*cost = div_u64(100ULL * INTEL_PSTATE_CORE_SCALING, pstate->scaling) + freq;
+	/*
+	 * Increase the cost slightly for CPUs able to access L3 to avoid
+	 * touching it in case some other CPUs of the same type can do the work
+	 * without it.
+	 */
+	if (cacheinfo) {
+		unsigned int i;
+
+		/* Check if L3 cache is there. */
+		for (i = 0; i < cacheinfo->num_leaves; i++) {
+			if (cacheinfo->info_list[i].level == 3) {
+				*cost += 2;
+				break;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static bool hybrid_register_perf_domain(unsigned int cpu)
+{
+	static const struct em_data_callback cb
+			= EM_ADV_DATA_CB(hybrid_active_power, hybrid_get_cost);
+	struct cpudata *cpudata = all_cpu_data[cpu];
+	struct device *cpu_dev;
+
+	/*
+	 * Registering EM perf domains without enabling asymmetric CPU capacity
+	 * support is not really useful and one domain should not be registered
+	 * more than once.
+	 */
+	if (!hybrid_max_perf_cpu || cpudata->pd_registered)
+		return false;
+
+	cpu_dev = get_cpu_device(cpu);
+	if (!cpu_dev)
+		return false;
+
+	if (em_dev_register_pd_no_update(cpu_dev, HYBRID_EM_STATE_COUNT, &cb,
+					 cpumask_of(cpu), false))
+		return false;
+
+	cpudata->pd_registered = true;
+
+	return true;
+}
+
+static void hybrid_register_all_perf_domains(void)
+{
+	unsigned int cpu;
+
+	for_each_online_cpu(cpu)
+		hybrid_register_perf_domain(cpu);
+}
+
+static void hybrid_update_perf_domain(struct cpudata *cpu)
+{
+	if (cpu->pd_registered)
+		em_adjust_cpu_capacity(cpu->cpu);
+}
+#else /* !CONFIG_ENERGY_MODEL */
+static inline bool hybrid_register_perf_domain(unsigned int cpu) { return false; }
+static inline void hybrid_register_all_perf_domains(void) {}
+static inline void hybrid_update_perf_domain(struct cpudata *cpu) {}
+#endif /* CONFIG_ENERGY_MODEL */
+
 static void hybrid_set_cpu_capacity(struct cpudata *cpu)
 {
 	arch_set_cpu_capacity(cpu->cpu, cpu->capacity_perf,
 			      hybrid_max_perf_cpu->capacity_perf,
 			      cpu->capacity_perf,
 			      cpu->pstate.max_pstate_physical);
+	hybrid_update_perf_domain(cpu);
+
+	topology_set_cpu_scale(cpu->cpu, arch_scale_cpu_capacity(cpu->cpu));
 
 	pr_debug("CPU%d: perf = %u, max. perf = %u, base perf = %d\n", cpu->cpu,
 		 cpu->capacity_perf, hybrid_max_perf_cpu->capacity_perf,
@@ -1042,6 +1160,11 @@ static void hybrid_refresh_cpu_capacity_scaling(void)
 	guard(mutex)(&hybrid_capacity_lock);
 
 	__hybrid_refresh_cpu_capacity_scaling();
+	/*
+	 * Perf domains are not registered before setting hybrid_max_perf_cpu,
+	 * so register them all after setting up CPU capacity scaling.
+	 */
+	hybrid_register_all_perf_domains();
 }
 
 static void hybrid_init_cpu_capacity_scaling(bool refresh)
@@ -1069,7 +1192,7 @@ static void hybrid_init_cpu_capacity_scaling(bool refresh)
 		hybrid_refresh_cpu_capacity_scaling();
 		/*
 		 * Disabling ITMT causes sched domains to be rebuilt to disable asym
-		 * packing and enable asym capacity.
+		 * packing and enable asym capacity and EAS.
 		 */
 		sched_clear_itmt_support();
 	}
@@ -1147,6 +1270,14 @@ static void hybrid_update_capacity(struct cpudata *cpu)
 	}
 
 	hybrid_set_cpu_capacity(cpu);
+	/*
+	 * If the CPU was offline to start with and it is going online for the
+	 * first time, a perf domain needs to be registered for it if hybrid
+	 * capacity scaling has been enabled already.  In that case, sched
+	 * domains need to be rebuilt to take the new perf domain into account.
+	 */
+	if (hybrid_register_perf_domain(cpu->cpu))
+		em_rebuild_sched_domains();
 
 unlock:
 	mutex_unlock(&hybrid_capacity_lock);
@@ -2656,6 +2787,8 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
 	X86_MATCH(INTEL_TIGERLAKE,		core_funcs),
 	X86_MATCH(INTEL_SAPPHIRERAPIDS_X,	core_funcs),
 	X86_MATCH(INTEL_EMERALDRAPIDS_X,	core_funcs),
+	X86_MATCH(INTEL_GRANITERAPIDS_D,	core_funcs),
+	X86_MATCH(INTEL_GRANITERAPIDS_X,	core_funcs),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);
@@ -2672,6 +2805,7 @@ static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] __initconst = {
 	X86_MATCH(INTEL_GRANITERAPIDS_X,	core_funcs),
 	X86_MATCH(INTEL_ATOM_CRESTMONT,		core_funcs),
 	X86_MATCH(INTEL_ATOM_CRESTMONT_X,	core_funcs),
+	X86_MATCH(INTEL_ATOM_DARKMONT_X,	core_funcs),
 	{}
 };
 #endif
@@ -3130,8 +3264,8 @@ static int intel_cpufreq_update_pstate(struct cpufreq_policy *policy,
 		int max_pstate = policy->strict_target ?
 					target_pstate : cpu->max_perf_ratio;
 
-		intel_cpufreq_hwp_update(cpu, target_pstate, max_pstate, 0,
-					 fast_switch);
+		intel_cpufreq_hwp_update(cpu, target_pstate, max_pstate,
+					 target_pstate, fast_switch);
 	} else if (target_pstate != old_pstate) {
 		intel_cpufreq_perf_ctl_update(cpu, target_pstate, fast_switch);
 	}

include/linux/arch_topology.h

@@ -14,14 +14,6 @@ int topology_update_cpu_topology(void);
 struct device_node;
 bool topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu);
 
-DECLARE_PER_CPU(unsigned long, cpu_scale);
-
-static inline unsigned long topology_get_cpu_scale(int cpu)
-{
-	return per_cpu(cpu_scale, cpu);
-}
-
-void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity);
 
 DECLARE_PER_CPU(unsigned long, capacity_freq_ref);