Merge tag 'pm-7.1-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pmHEADmaster

Pull power management fixes from Rafael Wysocki:
 "These fix maximum frequency computation in the intel_pstate driver for
  two processor models, update its documentation and fix issues related
  to the dynamic EPP support (added during the current development
  cycle) in the amd-pstate driver:

   - Fix maximum frequency computation in the intel_pstate driver for
     Raptor Lake-E and Bartlett Lake that are SMP platforms derived from
     hybrid ones (Rafael Wysocki, Henry Tseng)

   - Fix the description of asymmetric packing with SMT in the
     intel_pstate driver documentation (Ricardo Neri)

   - Fix multiple amd-pstate driver issues related to dynamic EPP
     support added recently, including making it opt-in only (K Prateek
     Nayak, Mario Limonciello)"

* tag 'pm-7.1-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  cpufreq/amd-pstate: Drop Kconfig option for dynamic EPP
  cpufreq: intel_pstate: Use HYBRID_SCALING_FACTOR_ADL for Bartlett Lake
  cpufreq: intel_pstate: Use correct scaling factor on Raptor Lake-E
  Documentation: intel_pstate: Fix description of asymmetric packing with SMT
  cpufreq/amd-pstate-ut: Drop policy reference before driver switch
  cpufreq/amd-pstate: Use "epp_default_dc" as default when dynamic_epp is disabled
  cpufreq/amd-pstate: Reorder notifier unregistration and floor perf reset
  cpufreq/amd-pstate: Allow writes to dynamic_epp when state isn't modified
  cpufreq/amd-pstate: Return -ENOMEM on failure to allocate profile_name
  cpufreq/amd-pstate: Grab "amd_pstate_driver_lock" when toggling dynamic_epp

6 files changed, 60 insertions, 40 deletions

diff --git a/Documentation/admin-guide/pm/amd-pstate.rst b/Documentation/admin-guide/pm/amd-pstate.rst
index f8e7050fc762..a95e2ebce005 100644
--- a/Documentation/admin-guide/pm/amd-pstate.rst
+++ b/Documentation/admin-guide/pm/amd-pstate.rst
@@ -358,9 +358,9 @@ Dynamic energy performance profile
 The amd-pstate driver supports dynamically selecting the energy performance
 profile based on whether the machine is running on AC or DC power.
 
-Whether this behavior is enabled by default depends on the kernel
-config option `CONFIG_X86_AMD_PSTATE_DYNAMIC_EPP`. This behavior can also be overridden
-at runtime by the sysfs file ``/sys/devices/system/cpu/cpufreq/policyX/dynamic_epp``.
+Whether this behavior is enabled by default depends on the kernel command line option
+``amd_dynamic_epp`` is set. This behavior can also be overridden
+at runtime by the sysfs file ``/sys/devices/system/cpu/amd_pstate/dynamic_epp``.
 
 When set to enabled, the driver will select a different energy performance
 profile when the machine is running on battery or AC power. The driver will
@@ -485,9 +485,8 @@ kernel parameter ``amd_prefcore=disable``.
 ``amd_dynamic_epp``
 
 When AMD pstate is in auto mode, dynamic EPP will control whether the kernel
-autonomously changes the EPP mode. The default is configured by
-``CONFIG_X86_AMD_PSTATE_DYNAMIC_EPP`` but can be explicitly enabled with
-``amd_dynamic_epp=enable`` or disabled with ``amd_dynamic_epp=disable``.
+autonomously changes the EPP mode. The default is disabled. It can be enabled
+with the kernel parameter ``amd_dynamic_epp=enable``.
 
 User Space Interface in ``sysfs`` - General
 ===========================================
diff --git a/Documentation/admin-guide/pm/intel_pstate.rst b/Documentation/admin-guide/pm/intel_pstate.rst
index fde967b0c2e0..25fe5d88fea6 100644
--- a/Documentation/admin-guide/pm/intel_pstate.rst
+++ b/Documentation/admin-guide/pm/intel_pstate.rst
@@ -355,11 +355,12 @@ HyperThreading (HT) in the context of Intel processors, is enabled on at least
 one core, ``intel_pstate`` assigns performance-based priorities to CPUs.  Namely,
 the priority of a given CPU reflects its highest HWP performance level which
 causes the CPU scheduler to generally prefer more performant CPUs, so the less
-performant CPUs are used when the other ones are fully loaded.  However, SMT
-siblings (that is, logical CPUs sharing one physical core) are treated in a
-special way such that if one of them is in use, the effective priority of the
-other ones is lowered below the priorities of the CPUs located in the other
-physical cores.
+performant CPUs are used when the other ones are fully loaded.  SMT siblings
+(that is, logical CPUs sharing one physical core) are given the same priority.
+The scheduler can pull tasks from lower-priority cores and place them on any
+sibling.  Since the scheduler spreads tasks among physical cores, tasks will be
+placed on the SMT siblings of physical cores only after all physical cores are
+busy.
 
 This approach maximizes performance in the majority of cases, but unfortunately
 it also leads to excessive energy usage in some important scenarios, like video
diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86
index 027e6ea2e038..a9093cd5e5d1 100644
--- a/drivers/cpufreq/Kconfig.x86
+++ b/drivers/cpufreq/Kconfig.x86
@@ -70,18 +70,6 @@ config X86_AMD_PSTATE_DEFAULT_MODE
 	  For details, take a look at:
 	  <file:Documentation/admin-guide/pm/amd-pstate.rst>.
 
-config X86_AMD_PSTATE_DYNAMIC_EPP
-	bool "AMD Processor P-State dynamic EPP support"
-	depends on X86_AMD_PSTATE
-	default n
-	help
-	  Allow the kernel to dynamically change the energy performance
-	  value from events like ACPI platform profile and AC adapter plug
-	  events.
-
-	  This feature can also be changed at runtime, this configuration
-	  option only sets the kernel default value behavior.
-
 config X86_AMD_PSTATE_UT
 	tristate "selftest for AMD Processor P-State driver"
 	depends on X86 && ACPI_PROCESSOR
diff --git a/drivers/cpufreq/amd-pstate-ut.c b/drivers/cpufreq/amd-pstate-ut.c
index aa8a464fab47..13a23dac477d 100644
--- a/drivers/cpufreq/amd-pstate-ut.c
+++ b/drivers/cpufreq/amd-pstate-ut.c
@@ -274,20 +274,21 @@ static int amd_pstate_set_mode(enum amd_pstate_mode mode)
 
 static int amd_pstate_ut_epp(u32 index)
 {
-	struct cpufreq_policy *policy __free(put_cpufreq_policy) = NULL;
-	char *buf __free(cleanup_page) = NULL;
 	static const char * const epp_strings[] = {
-		"performance",
-		"balance_performance",
-		"balance_power",
 		"power",
+		"balance_power",
+		"balance_performance",
+		"performance",
 	};
-	struct amd_cpudata *cpudata;
+	char *buf __free(cleanup_page) = NULL;
+	struct cpufreq_policy *policy = NULL;
 	enum amd_pstate_mode orig_mode;
+	struct amd_cpudata *cpudata;
+	unsigned long orig_policy;
 	bool orig_dynamic_epp;
 	int ret, cpu = 0;
-	int i;
 	u16 epp;
+	int i;
 
 	policy = cpufreq_cpu_get(cpu);
 	if (!policy)
@@ -297,6 +298,10 @@ static int amd_pstate_ut_epp(u32 index)
 	orig_mode = amd_pstate_get_status();
 	orig_dynamic_epp = cpudata->dynamic_epp;
 
+	/* Drop reference before potential driver change. */
+	cpufreq_cpu_put(policy);
+	policy = NULL;
+
 	/* disable dynamic EPP before running test */
 	if (cpudata->dynamic_epp) {
 		pr_debug("Dynamic EPP is enabled, disabling it\n");
@@ -311,6 +316,17 @@ static int amd_pstate_ut_epp(u32 index)
 	if (ret)
 		goto out;
 
+	policy = cpufreq_cpu_get(cpu);
+	if (!policy) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	down_write(&policy->rwsem);
+	cpudata = policy->driver_data;
+	orig_policy = cpudata->policy;
+	cpudata->policy = CPUFREQ_POLICY_POWERSAVE;
+
 	for (epp = 0; epp <= U8_MAX; epp++) {
 		u8 val;
 
@@ -358,6 +374,12 @@ static int amd_pstate_ut_epp(u32 index)
 	ret = 0;
 
 out:
+	if (policy) {
+		cpudata->policy = orig_policy;
+		up_write(&policy->rwsem);
+		cpufreq_cpu_put(policy);
+	}
+
 	if (orig_dynamic_epp) {
 		int ret2;
 
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 453084c67327..62b5d995281d 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -87,11 +87,7 @@ static struct cpufreq_driver amd_pstate_driver;
 static struct cpufreq_driver amd_pstate_epp_driver;
 static int cppc_state = AMD_PSTATE_UNDEFINED;
 static bool amd_pstate_prefcore = true;
-#ifdef CONFIG_X86_AMD_PSTATE_DYNAMIC_EPP
-static bool dynamic_epp = CONFIG_X86_AMD_PSTATE_DYNAMIC_EPP;
-#else
 static bool dynamic_epp;
-#endif
 static struct quirk_entry *quirks;
 
 /*
@@ -1291,6 +1287,8 @@ static int amd_pstate_set_dynamic_epp(struct cpufreq_policy *policy)
 		return ret;
 
 	cpudata->profile_name = kasprintf(GFP_KERNEL, "amd-pstate-epp-cpu%d", cpudata->cpu);
+	if (!cpudata->profile_name)
+		return -ENOMEM;
 
 	cpudata->ppdev = platform_profile_register(get_cpu_device(policy->cpu),
 						   cpudata->profile_name,
@@ -1427,7 +1425,7 @@ ssize_t store_energy_performance_preference(struct cpufreq_policy *policy,
 		if (ret)
 			epp = epp_values[ret];
 		else
-			epp = amd_pstate_get_balanced_epp(policy);
+			epp = cpudata->epp_default_dc;
 	}
 
 	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) {
@@ -1707,6 +1705,8 @@ static int amd_pstate_change_driver_mode(int mode)
 {
 	int ret;
 
+	lockdep_assert_held(&amd_pstate_driver_lock);
+
 	ret = amd_pstate_unregister_driver(0);
 	if (ret)
 		return ret;
@@ -1821,8 +1821,16 @@ static ssize_t dynamic_epp_store(struct device *a, struct device_attribute *b,
 	if (ret)
 		return ret;
 
-	if (dynamic_epp == enabled)
+	guard(mutex)(&amd_pstate_driver_lock);
+
+	if (cppc_state != AMD_PSTATE_ACTIVE) {
+		pr_debug("dynamic_epp can only be toggled in active mode\n");
 		return -EINVAL;
+	}
+
+	/* Nothing to do */
+	if (dynamic_epp == enabled)
+		return count;
 
 	/* reinitialize with desired dynamic EPP value */
 	dynamic_epp = enabled;
@@ -1942,7 +1950,7 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 	if (dynamic_epp)
 		ret = amd_pstate_set_dynamic_epp(policy);
 	else
-		ret = amd_pstate_set_epp(policy, amd_pstate_get_balanced_epp(policy));
+		ret = amd_pstate_set_epp(policy, cpudata->epp_default_dc);
 	if (ret)
 		goto free_cpudata1;
 
@@ -1970,12 +1978,13 @@ static void amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy)
 	if (cpudata) {
 		union perf_cached perf = READ_ONCE(cpudata->perf);
 
+		if (cpudata->dynamic_epp)
+			amd_pstate_clear_dynamic_epp(policy);
+
 		/* Reset CPPC_REQ MSR to the BIOS value */
 		amd_pstate_update_perf(policy, perf.bios_min_perf, 0U, 0U, 0U, false);
 		amd_pstate_set_floor_perf(policy, cpudata->bios_floor_perf);
 
-		if (cpudata->dynamic_epp)
-			amd_pstate_clear_dynamic_epp(policy);
 		kfree(cpudata);
 		policy->driver_data = NULL;
 	}
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 1292da53e5fc..1f093e346430 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -2279,7 +2279,7 @@ static int hwp_get_cpu_scaling(int cpu)
 		 * Return the hybrid scaling factor for P-cores and use the
 		 * default core scaling for E-cores.
 		 */
-		if (hybrid_get_cpu_type(cpu) == INTEL_CPU_TYPE_CORE)
+		if (hybrid_get_cpu_type(cpu) != INTEL_CPU_TYPE_ATOM)
 			return hybrid_scaling_factor;
 
 		return core_get_scaling();
@@ -3734,6 +3734,7 @@ static const struct x86_cpu_id intel_hybrid_scaling_factor[] = {
 	X86_MATCH_VFM(INTEL_RAPTORLAKE, HYBRID_SCALING_FACTOR_ADL),
 	X86_MATCH_VFM(INTEL_RAPTORLAKE_P, HYBRID_SCALING_FACTOR_ADL),
 	X86_MATCH_VFM(INTEL_RAPTORLAKE_S, HYBRID_SCALING_FACTOR_ADL),
+	X86_MATCH_VFM(INTEL_BARTLETTLAKE, HYBRID_SCALING_FACTOR_ADL),
 	X86_MATCH_VFM(INTEL_METEORLAKE_L, HYBRID_SCALING_FACTOR_MTL),
 	X86_MATCH_VFM(INTEL_LUNARLAKE_M, HYBRID_SCALING_FACTOR_LNL),
 	{}