Rust-for-Linux
diff --git a/‎Documentation/admin-guide/pm/amd-pstate.rst
Lines changed: 14 additions & 1 deletion b/‎Documentation/admin-guide/pm/amd-pstate.rst
Lines changed: 14 additions & 1 deletion
diff --git a/‎Documentation/devicetree/bindings/opp/operating-points-v2-ti-cpu.yaml
Lines changed: 1 addition & 1 deletion b/‎Documentation/devicetree/bindings/opp/operating-points-v2-ti-cpu.yaml
Lines changed: 1 addition & 1 deletion
diff --git a/‎Documentation/power/pci.rst
Lines changed: 5 additions & 6 deletions b/‎Documentation/power/pci.rst
Lines changed: 5 additions & 6 deletions
diff --git a/‎Documentation/power/runtime_pm.rst
Lines changed: 2 additions & 2 deletions b/‎Documentation/power/runtime_pm.rst
Lines changed: 2 additions & 2 deletions
diff --git a/‎MAINTAINERS
Lines changed: 3 additions & 0 deletions b/‎MAINTAINERS
Lines changed: 3 additions & 0 deletions
diff --git a/‎arch/x86/include/asm/processor.h
Lines changed: 0 additions & 3 deletions b/‎arch/x86/include/asm/processor.h
Lines changed: 0 additions & 3 deletions
diff --git a/‎arch/x86/include/asm/topology.h
Lines changed: 13 additions & 0 deletions b/‎arch/x86/include/asm/topology.h
Lines changed: 13 additions & 0 deletions
diff --git a/‎arch/x86/kernel/acpi/cppc.c
Lines changed: 161 additions & 11 deletions b/‎arch/x86/kernel/acpi/cppc.c
Lines changed: 161 additions & 11 deletions
diff --git a/‎arch/x86/kernel/cpu/amd.c
Lines changed: 0 additions & 16 deletions b/‎arch/x86/kernel/cpu/amd.c
Lines changed: 0 additions & 16 deletions
@@ -251,7 +251,9 @@ 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``.
+``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.
 This attribute is read-only.
 
 ``amd_pstate_lowest_nonlinear_freq``
@@ -262,6 +264,17 @@ lowest non-linear performance in `AMD CPPC Performance Capability
 <perf_cap_>`_.)
 This attribute is read-only.
 
+``amd_pstate_hw_prefcore``
+
+Whether the platform supports the preferred core feature and it has been
+enabled. This attribute is read-only.
+
+``amd_pstate_prefcore_ranking``
+
+The performance ranking of the core. This number doesn't have any unit, but
+larger numbers are preferred at the time of reading. This can change at
+runtime based on platform conditions. This attribute is read-only.
+
 ``energy_performance_available_preferences``
 
 A list of all the supported EPP preferences that could be used for
 
@@ -19,7 +19,7 @@ description:
   the hardware description for the scheme mentioned above.
 
 maintainers:
-  - Nishanth Menon <nm@ti.com>
+  - Dhruva Gole <d-gole@ti.com>
 
 allOf:
   - $ref: opp-v2-base.yaml#
 
@@ -979,18 +979,17 @@ subsections can be defined as a separate function, it often is convenient to
 point two or more members of struct dev_pm_ops to the same routine.  There are
 a few convenience macros that can be used for this purpose.
 
-The SIMPLE_DEV_PM_OPS macro declares a struct dev_pm_ops object with one
+The DEFINE_SIMPLE_DEV_PM_OPS() declares a struct dev_pm_ops object with one
 suspend routine pointed to by the .suspend(), .freeze(), and .poweroff()
 members and one resume routine pointed to by the .resume(), .thaw(), and
 .restore() members.  The other function pointers in this struct dev_pm_ops are
 unset.
 
-The UNIVERSAL_DEV_PM_OPS macro is similar to SIMPLE_DEV_PM_OPS, but it
-additionally sets the .runtime_resume() pointer to the same value as
-.resume() (and .thaw(), and .restore()) and the .runtime_suspend() pointer to
-the same value as .suspend() (and .freeze() and .poweroff()).
+The DEFINE_RUNTIME_DEV_PM_OPS() is similar to DEFINE_SIMPLE_DEV_PM_OPS(), but it
+additionally sets the .runtime_resume() pointer to pm_runtime_force_resume()
+and the .runtime_suspend() pointer to pm_runtime_force_suspend().
 
-The SET_SYSTEM_SLEEP_PM_OPS can be used inside of a declaration of struct
+The SYSTEM_SLEEP_PM_OPS() can be used inside of a declaration of struct
 dev_pm_ops to indicate that one suspend routine is to be pointed to by the
 .suspend(), .freeze(), and .poweroff() members and one resume routine is to
 be pointed to by the .resume(), .thaw(), and .restore() members.
 
@@ -811,8 +811,8 @@ subsystem-level dev_pm_ops structure.
 
 Device drivers that wish to use the same function as a system suspend, freeze,
 poweroff and runtime suspend callback, and similarly for system resume, thaw,
-restore, and runtime resume, can achieve this with the help of the
-UNIVERSAL_DEV_PM_OPS macro defined in include/linux/pm.h (possibly setting its
+restore, and runtime resume, can achieve similar behaviour with the help of the
+DEFINE_RUNTIME_DEV_PM_OPS() defined in include/linux/pm_runtime.h (possibly setting its
 last argument to NULL).
 
 8. "No-Callback" Devices
 
@@ -5851,6 +5851,9 @@ CPU POWER MONITORING SUBSYSTEM
 M:	Thomas Renninger <[email protected]>
 M:	Shuah Khan <[email protected]>
 M:	Shuah Khan <[email protected]>
+M:	John B. Wyatt IV <[email protected]>
+M:	John B. Wyatt IV <[email protected]>
+M:	John Kacur <[email protected]>
 L:	[email protected]
 S:	Maintained
 F:	tools/power/cpupower/
 
@@ -691,8 +691,6 @@ static inline u32 per_cpu_l2c_id(unsigned int cpu)
 }
 
 #ifdef CONFIG_CPU_SUP_AMD
-extern u32 amd_get_highest_perf(void);
-
 /*
  * Issue a DIV 0/1 insn to clear any division data from previous DIV
  * operations.
@@ -705,7 +703,6 @@ static __always_inline void amd_clear_divider(void)
 
 extern void amd_check_microcode(void);
 #else
-static inline u32 amd_get_highest_perf(void)		{ return 0; }
 static inline void amd_clear_divider(void)		{ }
 static inline void amd_check_microcode(void)		{ }
 #endif
 
@@ -282,9 +282,22 @@ static inline long arch_scale_freq_capacity(int cpu)
 }
 #define arch_scale_freq_capacity arch_scale_freq_capacity
 
+bool arch_enable_hybrid_capacity_scale(void);
+void arch_set_cpu_capacity(int cpu, unsigned long cap, unsigned long max_cap,
+			   unsigned long cap_freq, unsigned long base_freq);
+
+unsigned long arch_scale_cpu_capacity(int cpu);
+#define arch_scale_cpu_capacity arch_scale_cpu_capacity
+
 extern void arch_set_max_freq_ratio(bool turbo_disabled);
 extern void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled);
 #else
+static inline bool arch_enable_hybrid_capacity_scale(void) { return false; }
+static inline void arch_set_cpu_capacity(int cpu, unsigned long cap,
+					 unsigned long max_cap,
+					 unsigned long cap_freq,
+					 unsigned long base_freq) { }
+
 static inline void arch_set_max_freq_ratio(bool turbo_disabled) { }
 static inline void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled) { }
 #endif
 
@@ -9,6 +9,17 @@
 #include <asm/processor.h>
 #include <asm/topology.h>
 
+#define CPPC_HIGHEST_PERF_PERFORMANCE	196
+#define CPPC_HIGHEST_PERF_PREFCORE	166
+
+enum amd_pref_core {
+	AMD_PREF_CORE_UNKNOWN = 0,
+	AMD_PREF_CORE_SUPPORTED,
+	AMD_PREF_CORE_UNSUPPORTED,
+};
+static enum amd_pref_core amd_pref_core_detected;
+static u64 boost_numerator;
+
 /* Refer to drivers/acpi/cppc_acpi.c for the description of functions */
 
 bool cpc_supported_by_cpu(void)
@@ -69,31 +80,30 @@ int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val)
 static void amd_set_max_freq_ratio(void)
 {
 	struct cppc_perf_caps perf_caps;
-	u64 highest_perf, nominal_perf;
+	u64 numerator, nominal_perf;
 	u64 perf_ratio;
 	int rc;
 
 	rc = cppc_get_perf_caps(0, &perf_caps);
 	if (rc) {
-		pr_debug("Could not retrieve perf counters (%d)\n", rc);
+		pr_warn("Could not retrieve perf counters (%d)\n", rc);
 		return;
 	}
 
-	highest_perf = amd_get_highest_perf();
+	rc = amd_get_boost_ratio_numerator(0, &numerator);
+	if (rc) {
+		pr_warn("Could not retrieve highest performance (%d)\n", rc);
+		return;
+	}
 	nominal_perf = perf_caps.nominal_perf;
 
-	if (!highest_perf || !nominal_perf) {
-		pr_debug("Could not retrieve highest or nominal performance\n");
+	if (!nominal_perf) {
+		pr_warn("Could not retrieve nominal performance\n");
 		return;
 	}
 
-	perf_ratio = div_u64(highest_perf * SCHED_CAPACITY_SCALE, nominal_perf);
 	/* midpoint between max_boost and max_P */
-	perf_ratio = (perf_ratio + SCHED_CAPACITY_SCALE) >> 1;
-	if (!perf_ratio) {
-		pr_debug("Non-zero highest/nominal perf values led to a 0 ratio\n");
-		return;
-	}
+	perf_ratio = (div_u64(numerator * SCHED_CAPACITY_SCALE, nominal_perf) + SCHED_CAPACITY_SCALE) >> 1;
 
 	freq_invariance_set_perf_ratio(perf_ratio, false);
 }
@@ -116,3 +126,143 @@ void init_freq_invariance_cppc(void)
 	init_done = true;
 	mutex_unlock(&freq_invariance_lock);
 }
+
+/*
+ * Get the highest performance register value.
+ * @cpu: CPU from which to get highest performance.
+ * @highest_perf: Return address for highest performance value.
+ *
+ * Return: 0 for success, negative error code otherwise.
+ */
+int amd_get_highest_perf(unsigned int cpu, u32 *highest_perf)
+{
+	u64 val;
+	int ret;
+
+	if (cpu_feature_enabled(X86_FEATURE_CPPC)) {
+		ret = rdmsrl_safe_on_cpu(cpu, MSR_AMD_CPPC_CAP1, &val);
+		if (ret)
+			goto out;
+
+		val = AMD_CPPC_HIGHEST_PERF(val);
+	} else {
+		ret = cppc_get_highest_perf(cpu, &val);
+		if (ret)
+			goto out;
+	}
+
+	WRITE_ONCE(*highest_perf, (u32)val);
+out:
+	return ret;
+}
+EXPORT_SYMBOL_GPL(amd_get_highest_perf);
+
+/**
+ * amd_detect_prefcore: Detect if CPUs in the system support preferred cores
+ * @detected: Output variable for the result of the detection.
+ *
+ * Determine whether CPUs in the system support preferred cores. On systems
+ * that support preferred cores, different highest perf values will be found
+ * on different cores. On other systems, the highest perf value will be the
+ * same on all cores.
+ *
+ * The result of the detection will be stored in the 'detected' parameter.
+ *
+ * Return: 0 for success, negative error code otherwise
+ */
+int amd_detect_prefcore(bool *detected)
+{
+	int cpu, count = 0;
+	u64 highest_perf[2] = {0};
+
+	if (WARN_ON(!detected))
+		return -EINVAL;
+
+	switch (amd_pref_core_detected) {
+	case AMD_PREF_CORE_SUPPORTED:
+		*detected = true;
+		return 0;
+	case AMD_PREF_CORE_UNSUPPORTED:
+		*detected = false;
+		return 0;
+	default:
+		break;
+	}
+
+	for_each_present_cpu(cpu) {
+		u32 tmp;
+		int ret;
+
+		ret = amd_get_highest_perf(cpu, &tmp);
+		if (ret)
+			return ret;
+
+		if (!count || (count == 1 && tmp != highest_perf[0]))
+			highest_perf[count++] = tmp;
+
+		if (count == 2)
+			break;
+	}
+
+	*detected = (count == 2);
+	boost_numerator = highest_perf[0];
+
+	amd_pref_core_detected = *detected ? AMD_PREF_CORE_SUPPORTED :
+					     AMD_PREF_CORE_UNSUPPORTED;
+
+	pr_debug("AMD CPPC preferred core is %ssupported (highest perf: 0x%llx)\n",
+		 *detected ? "" : "un", highest_perf[0]);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(amd_detect_prefcore);
+
+/**
+ * amd_get_boost_ratio_numerator: Get the numerator to use for boost ratio calculation
+ * @cpu: CPU to get numerator for.
+ * @numerator: Output variable for numerator.
+ *
+ * Determine the numerator to use for calculating the boost ratio on
+ * a CPU. On systems that support preferred cores, this will be a hardcoded
+ * value. On other systems this will the highest performance register value.
+ *
+ * If booting the system with amd-pstate enabled but preferred cores disabled then
+ * the correct boost numerator will be returned to match hardware capabilities
+ * even if the preferred cores scheduling hints are not enabled.
+ *
+ * Return: 0 for success, negative error code otherwise.
+ */
+int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator)
+{
+	bool prefcore;
+	int ret;
+
+	ret = amd_detect_prefcore(&prefcore);
+	if (ret)
+		return ret;
+
+	/* without preferred cores, return the highest perf register value */
+	if (!prefcore) {
+		*numerator = boost_numerator;
+		return 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 (cpu_feature_enabled(X86_FEATURE_ZEN4)) {
+		switch (boot_cpu_data.x86_model) {
+		case 0x70 ... 0x7f:
+			*numerator = CPPC_HIGHEST_PERF_PERFORMANCE;
+			return 0;
+		default:
+			break;
+		}
+	}
+	*numerator = CPPC_HIGHEST_PERF_PREFCORE;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(amd_get_boost_ratio_numerator);
@@ -1190,22 +1190,6 @@ unsigned long amd_get_dr_addr_mask(unsigned int dr)
 }
 EXPORT_SYMBOL_GPL(amd_get_dr_addr_mask);
 
-u32 amd_get_highest_perf(void)
-{
-	struct cpuinfo_x86 *c = &boot_cpu_data;
-
-	if (c->x86 == 0x17 && ((c->x86_model >= 0x30 && c->x86_model < 0x40) ||
-			       (c->x86_model >= 0x70 && c->x86_model < 0x80)))
-		return 166;
-
-	if (c->x86 == 0x19 && ((c->x86_model >= 0x20 && c->x86_model < 0x30) ||
-			       (c->x86_model >= 0x40 && c->x86_model < 0x70)))
-		return 166;
-
-	return 255;
-}
-EXPORT_SYMBOL_GPL(amd_get_highest_perf);
-
 static void zenbleed_check_cpu(void *unused)
 {
 	struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());