Merge tag 'pm-6.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "The amd-pstate cpufreq driver gets the majority of changes this time.
  They are mostly fixes and cleanups, but one of them causes it to
  become the default cpufreq driver on some AMD server platforms.

  Apart from that, the menu cpuidle governor is modified to not use
  iowait any more, the intel_idle gets a custom C-states table for
  Granite Rapids Xeon D, and the intel_pstate driver will use a more
  aggressive Balance- performance default EPP value on Granite Rapids
  now.

  There are also some fixes, cleanups and tooling updates.

  Specifics:

   - Update the amd-pstate driver to set the initial scaling frequency
     policy lower bound to be the lowest non-linear frequency (Dhananjay
     Ugwekar)

   - Enable amd-pstate by default on servers starting with newer AMD
     Epyc processors (Swapnil Sapkal)

   - Align more codepaths between shared memory and MSR designs in
     amd-pstate (Dhananjay Ugwekar)

   - Clean up amd-pstate code to rename functions and remove redundant
     calls (Dhananjay Ugwekar, Mario Limonciello)

   - Do other assorted fixes and cleanups in amd-pstate (Dhananjay
     Ugwekar and Mario Limonciello)

   - Change the Balance-performance EPP value for Granite Rapids in the
     intel_pstate driver to a more performance-biased one (Srinivas
     Pandruvada)

   - Simplify MSR read on the boot CPU in the ACPI cpufreq driver (Chang
     S. Bae)

   - Ensure sugov_eas_rebuild_sd() is always called when sugov_init()
     succeeds to always enforce sched domains rebuild in case EAS needs
     to be enabled (Christian Loehle)

   - Switch cpufreq back to platform_driver::remove() (Uwe Kleine-König)

   - Use proper frequency unit names in cpufreq (Marcin Juszkiewicz)

   - Add a built-in idle states table for Granite Rapids Xeon D to the
     intel_idle driver (Artem Bityutskiy)

   - Fix some typos in comments in the cpuidle core and drivers (Shen
     Lichuan)

   - Remove iowait influence from the menu cpuidle governor (Christian
     Loehle)

   - Add min/max available performance state limits to the Energy Model
     management code (Lukasz Luba)

   - Update pm-graph to v5.13 (Todd Brandt)

   - Add documentation for some recently introduced cpupower utility
     options (Tor Vic)

   - Make cpupower inform users where cpufreq-bench.conf should be
     located when opening it fails (Peng Fan)

   - Allow overriding cross-compiling env params in cpupower (Peng Fan)

   - Add compile_commands.json to .gitignore in cpupower (John B. Wyatt
     IV)

   - Improve disable c_state block in cpupower bindings and add a test
     to confirm that CPU state is disabled to it (John B. Wyatt IV)

   - Add Chinese Simplified translation to cpupower (Kieran Moy)

   - Add checks for xgettext and msgfmt to cpupower (Siddharth Menon)"

* tag 'pm-6.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (38 commits)
  cpufreq: intel_pstate: Update Balance-performance EPP for Granite Rapids
  cpufreq: ACPI: Simplify MSR read on the boot CPU
  sched/cpufreq: Ensure sd is rebuilt for EAS check
  intel_idle: add Granite Rapids Xeon D support
  PM: EM: Add min/max available performance state limits
  cpufreq/amd-pstate: Move registration after static function call update
  cpufreq/amd-pstate: Push adjust_perf vfunc init into cpu_init
  cpufreq/amd-pstate: Align offline flow of shared memory and MSR based systems
  cpufreq/amd-pstate: Call cppc_set_epp_perf in the reenable function
  cpufreq/amd-pstate: Do not attempt to clear MSR_AMD_CPPC_ENABLE
  cpufreq/amd-pstate: Rename functions that enable CPPC
  cpufreq/amd-pstate-ut: Add fix for min freq unit test
  amd-pstate: Switch to amd-pstate by default on some Server platforms
  amd-pstate: Set min_perf to nominal_perf for active mode performance gov
  cpufreq/amd-pstate: Remove the redundant amd_pstate_set_driver() call
  cpufreq/amd-pstate: Remove the switch case in amd_pstate_init()
  cpufreq/amd-pstate: Call amd_pstate_set_driver() in amd_pstate_register_driver()
  cpufreq/amd-pstate: Call amd_pstate_register() in amd_pstate_init()
  cpufreq/amd-pstate: Set the initial min_freq to lowest_nonlinear_freq
  cpufreq/amd-pstate: Remove the redundant verify() function
  ...

30 files changed, 184 insertions, 236 deletions

diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index 0f04feb6cafa..c9ebacf5c88e 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -73,20 +73,17 @@ static unsigned int acpi_pstate_strict;
 
 static bool boost_state(unsigned int cpu)
 {
-	u32 lo, hi;
 	u64 msr;
 
 	switch (boot_cpu_data.x86_vendor) {
 	case X86_VENDOR_INTEL:
 	case X86_VENDOR_CENTAUR:
 	case X86_VENDOR_ZHAOXIN:
-		rdmsr_on_cpu(cpu, MSR_IA32_MISC_ENABLE, &lo, &hi);
-		msr = lo | ((u64)hi << 32);
+		rdmsrl_on_cpu(cpu, MSR_IA32_MISC_ENABLE, &msr);
 		return !(msr & MSR_IA32_MISC_ENABLE_TURBO_DISABLE);
 	case X86_VENDOR_HYGON:
 	case X86_VENDOR_AMD:
-		rdmsr_on_cpu(cpu, MSR_K7_HWCR, &lo, &hi);
-		msr = lo | ((u64)hi << 32);
+		rdmsrl_on_cpu(cpu, MSR_K7_HWCR, &msr);
 		return !(msr & MSR_K7_HWCR_CPB_DIS);
 	}
 	return false;
@@ -1028,7 +1025,7 @@ static struct platform_driver acpi_cpufreq_platdrv = {
 	.driver = {
 		.name	= "acpi-cpufreq",
 	},
-	.remove_new	= acpi_cpufreq_remove,
+	.remove = acpi_cpufreq_remove,
 };
 
 static int __init acpi_cpufreq_init(void)
diff --git a/drivers/cpufreq/amd-pstate-ut.c b/drivers/cpufreq/amd-pstate-ut.c
index f66701514d90..a261d7300951 100644
--- a/drivers/cpufreq/amd-pstate-ut.c
+++ b/drivers/cpufreq/amd-pstate-ut.c
@@ -227,10 +227,10 @@ static void amd_pstate_ut_check_freq(u32 index)
 			goto skip_test;
 		}
 
-		if (cpudata->min_freq != policy->min) {
+		if (cpudata->lowest_nonlinear_freq != policy->min) {
 			amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_FAIL;
-			pr_err("%s cpu%d cpudata_min_freq=%d policy_min=%d, they should be equal!\n",
-				__func__, cpu, cpudata->min_freq, policy->min);
+			pr_err("%s cpu%d cpudata_lowest_nonlinear_freq=%d policy_min=%d, they should be equal!\n",
+				__func__, cpu, cpudata->lowest_nonlinear_freq, policy->min);
 			goto skip_test;
 		}
 
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index b63863f77c67..f834cc8205e2 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -233,7 +233,7 @@ static int amd_pstate_get_energy_pref_index(struct amd_cpudata *cpudata)
 	return index;
 }
 
-static void pstate_update_perf(struct amd_cpudata *cpudata, u32 min_perf,
+static void msr_update_perf(struct amd_cpudata *cpudata, u32 min_perf,
 			       u32 des_perf, u32 max_perf, bool fast_switch)
 {
 	if (fast_switch)
@@ -243,7 +243,7 @@ static void pstate_update_perf(struct amd_cpudata *cpudata, u32 min_perf,
 			      READ_ONCE(cpudata->cppc_req_cached));
 }
 
-DEFINE_STATIC_CALL(amd_pstate_update_perf, pstate_update_perf);
+DEFINE_STATIC_CALL(amd_pstate_update_perf, msr_update_perf);
 
 static inline void amd_pstate_update_perf(struct amd_cpudata *cpudata,
 					  u32 min_perf, u32 des_perf,
@@ -306,11 +306,17 @@ static int amd_pstate_set_energy_pref_index(struct amd_cpudata *cpudata,
 	return ret;
 }
 
-static inline int pstate_enable(bool enable)
+static inline int msr_cppc_enable(bool enable)
 {
 	int ret, cpu;
 	unsigned long logical_proc_id_mask = 0;
 
+       /*
+        * MSR_AMD_CPPC_ENABLE is write-once, once set it cannot be cleared.
+        */
+	if (!enable)
+		return 0;
+
 	if (enable == cppc_enabled)
 		return 0;
 
@@ -332,7 +338,7 @@ static inline int pstate_enable(bool enable)
 	return 0;
 }
 
-static int cppc_enable(bool enable)
+static int shmem_cppc_enable(bool enable)
 {
 	int cpu, ret = 0;
 	struct cppc_perf_ctrls perf_ctrls;
@@ -359,14 +365,14 @@ static int cppc_enable(bool enable)
 	return ret;
 }
 
-DEFINE_STATIC_CALL(amd_pstate_enable, pstate_enable);
+DEFINE_STATIC_CALL(amd_pstate_cppc_enable, msr_cppc_enable);
 
-static inline int amd_pstate_enable(bool enable)
+static inline int amd_pstate_cppc_enable(bool enable)
 {
-	return static_call(amd_pstate_enable)(enable);
+	return static_call(amd_pstate_cppc_enable)(enable);
 }
 
-static int pstate_init_perf(struct amd_cpudata *cpudata)
+static int msr_init_perf(struct amd_cpudata *cpudata)
 {
 	u64 cap1;
 
@@ -385,7 +391,7 @@ static int pstate_init_perf(struct amd_cpudata *cpudata)
 	return 0;
 }
 
-static int cppc_init_perf(struct amd_cpudata *cpudata)
+static int shmem_init_perf(struct amd_cpudata *cpudata)
 {
 	struct cppc_perf_caps cppc_perf;
 
@@ -420,14 +426,14 @@ static int cppc_init_perf(struct amd_cpudata *cpudata)
 	return ret;
 }
 
-DEFINE_STATIC_CALL(amd_pstate_init_perf, pstate_init_perf);
+DEFINE_STATIC_CALL(amd_pstate_init_perf, msr_init_perf);
 
 static inline int amd_pstate_init_perf(struct amd_cpudata *cpudata)
 {
 	return static_call(amd_pstate_init_perf)(cpudata);
 }
 
-static void cppc_update_perf(struct amd_cpudata *cpudata,
+static void shmem_update_perf(struct amd_cpudata *cpudata,
 			     u32 min_perf, u32 des_perf,
 			     u32 max_perf, bool fast_switch)
 {
@@ -527,9 +533,28 @@ cpufreq_policy_put:
 	cpufreq_cpu_put(policy);
 }
 
-static int amd_pstate_verify(struct cpufreq_policy_data *policy)
+static int amd_pstate_verify(struct cpufreq_policy_data *policy_data)
 {
-	cpufreq_verify_within_cpu_limits(policy);
+	/*
+	 * Initialize lower frequency limit (i.e.policy->min) with
+	 * lowest_nonlinear_frequency which is the most energy efficient
+	 * frequency. Override the initial value set by cpufreq core and
+	 * amd-pstate qos_requests.
+	 */
+	if (policy_data->min == FREQ_QOS_MIN_DEFAULT_VALUE) {
+		struct cpufreq_policy *policy = cpufreq_cpu_get(policy_data->cpu);
+		struct amd_cpudata *cpudata;
+
+		if (!policy)
+			return -EINVAL;
+
+		cpudata = policy->driver_data;
+		policy_data->min = cpudata->lowest_nonlinear_freq;
+		cpufreq_cpu_put(policy);
+	}
+
+	cpufreq_verify_within_cpu_limits(policy_data);
+	pr_debug("policy_max =%d, policy_min=%d\n", policy_data->max, policy_data->min);
 
 	return 0;
 }
@@ -665,34 +690,12 @@ static void amd_pstate_adjust_perf(unsigned int cpu,
 static int amd_pstate_cpu_boost_update(struct cpufreq_policy *policy, bool on)
 {
 	struct amd_cpudata *cpudata = policy->driver_data;
-	struct cppc_perf_ctrls perf_ctrls;
-	u32 highest_perf, nominal_perf, nominal_freq, max_freq;
+	u32 nominal_freq, max_freq;
 	int ret = 0;
 
-	highest_perf = READ_ONCE(cpudata->highest_perf);
-	nominal_perf = READ_ONCE(cpudata->nominal_perf);
 	nominal_freq = READ_ONCE(cpudata->nominal_freq);
 	max_freq = READ_ONCE(cpudata->max_freq);
 
-	if (boot_cpu_has(X86_FEATURE_CPPC)) {
-		u64 value = READ_ONCE(cpudata->cppc_req_cached);
-
-		value &= ~GENMASK_ULL(7, 0);
-		value |= on ? highest_perf : nominal_perf;
-		WRITE_ONCE(cpudata->cppc_req_cached, value);
-
-		wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value);
-	} else {
-		perf_ctrls.max_perf = on ? highest_perf : nominal_perf;
-		ret = cppc_set_perf(cpudata->cpu, &perf_ctrls);
-		if (ret) {
-			cpufreq_cpu_release(policy);
-			pr_debug("Failed to set max perf on CPU:%d. ret:%d\n",
-				cpudata->cpu, ret);
-			return ret;
-		}
-	}
-
 	if (on)
 		policy->cpuinfo.max_freq = max_freq;
 	else if (policy->cpuinfo.max_freq > nominal_freq * 1000)
@@ -1001,7 +1004,7 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
 		policy->fast_switch_possible = true;
 
 	ret = freq_qos_add_request(&policy->constraints, &cpudata->req[0],
-				   FREQ_QOS_MIN, policy->cpuinfo.min_freq);
+				   FREQ_QOS_MIN, FREQ_QOS_MIN_DEFAULT_VALUE);
 	if (ret < 0) {
 		dev_err(dev, "Failed to add min-freq constraint (%d)\n", ret);
 		goto free_cpudata1;
@@ -1045,7 +1048,7 @@ static int amd_pstate_cpu_resume(struct cpufreq_policy *policy)
 {
 	int ret;
 
-	ret = amd_pstate_enable(true);
+	ret = amd_pstate_cppc_enable(true);
 	if (ret)
 		pr_err("failed to enable amd-pstate during resume, return %d\n", ret);
 
@@ -1056,7 +1059,7 @@ static int amd_pstate_cpu_suspend(struct cpufreq_policy *policy)
 {
 	int ret;
 
-	ret = amd_pstate_enable(false);
+	ret = amd_pstate_cppc_enable(false);
 	if (ret)
 		pr_err("failed to disable amd-pstate during suspend, return %d\n", ret);
 
@@ -1189,25 +1192,41 @@ static ssize_t show_energy_performance_preference(
 
 static void amd_pstate_driver_cleanup(void)
 {
-	amd_pstate_enable(false);
+	amd_pstate_cppc_enable(false);
 	cppc_state = AMD_PSTATE_DISABLE;
 	current_pstate_driver = NULL;
 }
 
+static int amd_pstate_set_driver(int mode_idx)
+{
+	if (mode_idx >= AMD_PSTATE_DISABLE && mode_idx < AMD_PSTATE_MAX) {
+		cppc_state = mode_idx;
+		if (cppc_state == AMD_PSTATE_DISABLE)
+			pr_info("driver is explicitly disabled\n");
+
+		if (cppc_state == AMD_PSTATE_ACTIVE)
+			current_pstate_driver = &amd_pstate_epp_driver;
+
+		if (cppc_state == AMD_PSTATE_PASSIVE || cppc_state == AMD_PSTATE_GUIDED)
+			current_pstate_driver = &amd_pstate_driver;
+
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
 static int amd_pstate_register_driver(int mode)
 {
 	int ret;
 
-	if (mode == AMD_PSTATE_PASSIVE || mode == AMD_PSTATE_GUIDED)
-		current_pstate_driver = &amd_pstate_driver;
-	else if (mode == AMD_PSTATE_ACTIVE)
-		current_pstate_driver = &amd_pstate_epp_driver;
-	else
-		return -EINVAL;
+	ret = amd_pstate_set_driver(mode);
+	if (ret)
+		return ret;
 
 	cppc_state = mode;
 
-	ret = amd_pstate_enable(true);
+	ret = amd_pstate_cppc_enable(true);
 	if (ret) {
 		pr_err("failed to enable cppc during amd-pstate driver registration, return %d\n",
 		       ret);
@@ -1485,6 +1504,8 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 		WRITE_ONCE(cpudata->cppc_cap1_cached, value);
 	}
 
+	current_pstate_driver->adjust_perf = NULL;
+
 	return 0;
 
 free_cpudata1:
@@ -1507,26 +1528,13 @@ static void amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy)
 static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy)
 {
 	struct amd_cpudata *cpudata = policy->driver_data;
-	u32 max_perf, min_perf, min_limit_perf, max_limit_perf;
+	u32 max_perf, min_perf;
 	u64 value;
 	s16 epp;
 
-	if (cpudata->boost_supported && !policy->boost_enabled)
-		max_perf = READ_ONCE(cpudata->nominal_perf);
-	else
-		max_perf = READ_ONCE(cpudata->highest_perf);
+	max_perf = READ_ONCE(cpudata->highest_perf);
 	min_perf = READ_ONCE(cpudata->lowest_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);
-
-	if (min_limit_perf < min_perf)
-		min_limit_perf = min_perf;
-
-	if (max_limit_perf < min_limit_perf)
-		max_limit_perf = min_limit_perf;
-
-	WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf);
-	WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf);
+	amd_pstate_update_min_max_limit(policy);
 
 	max_perf = clamp_t(unsigned long, max_perf, cpudata->min_limit_perf,
 			cpudata->max_limit_perf);
@@ -1535,7 +1543,7 @@ static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy)
 	value = READ_ONCE(cpudata->cppc_req_cached);
 
 	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
-		min_perf = max_perf;
+		min_perf = min(cpudata->nominal_perf, max_perf);
 
 	/* Initial min/max values for CPPC Performance Controls Register */
 	value &= ~AMD_CPPC_MIN_PERF(~0L);
@@ -1563,12 +1571,6 @@ static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy)
 	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
 		epp = 0;
 
-	/* Set initial EPP value */
-	if (cpu_feature_enabled(X86_FEATURE_CPPC)) {
-		value &= ~GENMASK_ULL(31, 24);
-		value |= (u64)epp << 24;
-	}
-
 	WRITE_ONCE(cpudata->cppc_req_cached, value);
 	return amd_pstate_set_epp(cpudata, epp);
 }
@@ -1605,7 +1607,7 @@ static void amd_pstate_epp_reenable(struct amd_cpudata *cpudata)
 	u64 value, max_perf;
 	int ret;
 
-	ret = amd_pstate_enable(true);
+	ret = amd_pstate_cppc_enable(true);
 	if (ret)
 		pr_err("failed to enable amd pstate during resume, return %d\n", ret);
 
@@ -1616,8 +1618,9 @@ static void amd_pstate_epp_reenable(struct amd_cpudata *cpudata)
 		wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value);
 	} else {
 		perf_ctrls.max_perf = max_perf;
-		perf_ctrls.energy_perf = AMD_CPPC_ENERGY_PERF_PREF(cpudata->epp_cached);
 		cppc_set_perf(cpudata->cpu, &perf_ctrls);
+		perf_ctrls.energy_perf = AMD_CPPC_ENERGY_PERF_PREF(cpudata->epp_cached);
+		cppc_set_epp_perf(cpudata->cpu, &perf_ctrls, 1);
 	}
 }
 
@@ -1657,9 +1660,11 @@ static void amd_pstate_epp_offline(struct cpufreq_policy *policy)
 		wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value);
 	} else {
 		perf_ctrls.desired_perf = 0;
+		perf_ctrls.min_perf = min_perf;
 		perf_ctrls.max_perf = min_perf;
-		perf_ctrls.energy_perf = AMD_CPPC_ENERGY_PERF_PREF(HWP_EPP_BALANCE_POWERSAVE);
 		cppc_set_perf(cpudata->cpu, &perf_ctrls);
+		perf_ctrls.energy_perf = AMD_CPPC_ENERGY_PERF_PREF(HWP_EPP_BALANCE_POWERSAVE);
+		cppc_set_epp_perf(cpudata->cpu, &perf_ctrls, 1);
 	}
 	mutex_unlock(&amd_pstate_limits_lock);
 }
@@ -1679,13 +1684,6 @@ static int amd_pstate_epp_cpu_offline(struct cpufreq_policy *policy)
 	return 0;
 }
 
-static int amd_pstate_epp_verify_policy(struct cpufreq_policy_data *policy)
-{
-	cpufreq_verify_within_cpu_limits(policy);
-	pr_debug("policy_max =%d, policy_min=%d\n", policy->max, policy->min);
-	return 0;
-}
-
 static int amd_pstate_epp_suspend(struct cpufreq_policy *policy)
 {
 	struct amd_cpudata *cpudata = policy->driver_data;
@@ -1699,7 +1697,7 @@ static int amd_pstate_epp_suspend(struct cpufreq_policy *policy)
 	cpudata->suspended = true;
 
 	/* disable CPPC in lowlevel firmware */
-	ret = amd_pstate_enable(false);
+	ret = amd_pstate_cppc_enable(false);
 	if (ret)
 		pr_err("failed to suspend, return %d\n", ret);
 
@@ -1741,7 +1739,7 @@ static struct cpufreq_driver amd_pstate_driver = {
 
 static struct cpufreq_driver amd_pstate_epp_driver = {
 	.flags		= CPUFREQ_CONST_LOOPS,
-	.verify		= amd_pstate_epp_verify_policy,
+	.verify		= amd_pstate_verify,
 	.setpolicy	= amd_pstate_epp_set_policy,
 	.init		= amd_pstate_epp_cpu_init,
 	.exit		= amd_pstate_epp_cpu_exit,
@@ -1755,26 +1753,7 @@ static struct cpufreq_driver amd_pstate_epp_driver = {
 	.attr		= amd_pstate_epp_attr,
 };
 
-static int __init amd_pstate_set_driver(int mode_idx)
-{
-	if (mode_idx >= AMD_PSTATE_DISABLE && mode_idx < AMD_PSTATE_MAX) {
-		cppc_state = mode_idx;
-		if (cppc_state == AMD_PSTATE_DISABLE)
-			pr_info("driver is explicitly disabled\n");
-
-		if (cppc_state == AMD_PSTATE_ACTIVE)
-			current_pstate_driver = &amd_pstate_epp_driver;
-
-		if (cppc_state == AMD_PSTATE_PASSIVE || cppc_state == AMD_PSTATE_GUIDED)
-			current_pstate_driver = &amd_pstate_driver;
-
-		return 0;
-	}
-
-	return -EINVAL;
-}
-
-/**
+/*
  * CPPC function is not supported for family ID 17H with model_ID ranging from 0x10 to 0x2F.
  * show the debug message that helps to check if the CPU has CPPC support for loading issue.
  */
@@ -1864,10 +1843,10 @@ static int __init amd_pstate_init(void)
 	if (cppc_state == AMD_PSTATE_UNDEFINED) {
 		/* Disable on the following configs by default:
 		 * 1. Undefined platforms
-		 * 2. Server platforms
+		 * 2. Server platforms with CPUs older than Family 0x1A.
 		 */
 		if (amd_pstate_acpi_pm_profile_undefined() ||
-		    amd_pstate_acpi_pm_profile_server()) {
+		    (amd_pstate_acpi_pm_profile_server() && boot_cpu_data.x86 < 0x1A)) {
 			pr_info("driver load is disabled, boot with specific mode to enable this\n");
 			return -ENODEV;
 		}
@@ -1875,50 +1854,31 @@ static int __init amd_pstate_init(void)
 		cppc_state = CONFIG_X86_AMD_PSTATE_DEFAULT_MODE;
 	}
 
-	switch (cppc_state) {
-	case AMD_PSTATE_DISABLE:
+	if (cppc_state == AMD_PSTATE_DISABLE) {
 		pr_info("driver load is disabled, boot with specific mode to enable this\n");
 		return -ENODEV;
-	case AMD_PSTATE_PASSIVE:
-	case AMD_PSTATE_ACTIVE:
-	case AMD_PSTATE_GUIDED:
-		ret = amd_pstate_set_driver(cppc_state);
-		if (ret)
-			return ret;
-		break;
-	default:
-		return -EINVAL;
 	}
 
 	/* capability check */
 	if (cpu_feature_enabled(X86_FEATURE_CPPC)) {
 		pr_debug("AMD CPPC MSR based functionality is supported\n");
-		if (cppc_state != AMD_PSTATE_ACTIVE)
-			current_pstate_driver->adjust_perf = amd_pstate_adjust_perf;
 	} else {
 		pr_debug("AMD CPPC shared memory based functionality is supported\n");
-		static_call_update(amd_pstate_enable, cppc_enable);
-		static_call_update(amd_pstate_init_perf, cppc_init_perf);
-		static_call_update(amd_pstate_update_perf, cppc_update_perf);
+		static_call_update(amd_pstate_cppc_enable, shmem_cppc_enable);
+		static_call_update(amd_pstate_init_perf, shmem_init_perf);
+		static_call_update(amd_pstate_update_perf, shmem_update_perf);
 	}
 
-	if (amd_pstate_prefcore) {
-		ret = amd_detect_prefcore(&amd_pstate_prefcore);
-		if (ret)
-			return ret;
-	}
-
-	/* enable amd pstate feature */
-	ret = amd_pstate_enable(true);
+	ret = amd_pstate_register_driver(cppc_state);
 	if (ret) {
-		pr_err("failed to enable driver mode(%d)\n", cppc_state);
+		pr_err("failed to register with return %d\n", ret);
 		return ret;
 	}
 
-	ret = cpufreq_register_driver(current_pstate_driver);
-	if (ret) {
-		pr_err("failed to register with return %d\n", ret);
-		goto disable_driver;
+	if (amd_pstate_prefcore) {
+		ret = amd_detect_prefcore(&amd_pstate_prefcore);
+		if (ret)
+			return ret;
 	}
 
 	dev_root = bus_get_dev_root(&cpu_subsys);
@@ -1935,8 +1895,7 @@ static int __init amd_pstate_init(void)
 
 global_attr_free:
 	cpufreq_unregister_driver(current_pstate_driver);
-disable_driver:
-	amd_pstate_enable(false);
+	amd_pstate_cppc_enable(false);
 	return ret;
 }
 device_initcall(amd_pstate_init);
diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c
index ea8438550b49..5d03a295a085 100644
--- a/drivers/cpufreq/brcmstb-avs-cpufreq.c
+++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c
@@ -777,7 +777,7 @@ static struct platform_driver brcm_avs_cpufreq_platdrv = {
 		.of_match_table = brcm_avs_cpufreq_match,
 	},
 	.probe		= brcm_avs_cpufreq_probe,
-	.remove_new	= brcm_avs_cpufreq_remove,
+	.remove		= brcm_avs_cpufreq_remove,
 };
 module_platform_driver(brcm_avs_cpufreq_platdrv);
 
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index 983443396f8f..3a7c3372bda7 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -345,7 +345,7 @@ static struct platform_driver dt_cpufreq_platdrv = {
 		.name	= "cpufreq-dt",
 	},
 	.probe		= dt_cpufreq_probe,
-	.remove_new	= dt_cpufreq_remove,
+	.remove		= dt_cpufreq_remove,
 };
 module_platform_driver(dt_cpufreq_platdrv);
 
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index f98c9438760c..1a4cae54a01b 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1520,7 +1520,7 @@ static int cpufreq_online(unsigned int cpu)
 			 * frequency for longer duration. Hence, a BUG_ON().
 			 */
 			BUG_ON(ret);
-			pr_info("%s: CPU%d: Running at unlisted initial frequency: %u KHz, changing to: %u KHz\n",
+			pr_info("%s: CPU%d: Running at unlisted initial frequency: %u kHz, changing to: %u kHz\n",
 				__func__, policy->cpu, old_freq, policy->cur);
 		}
 	}
diff --git a/drivers/cpufreq/davinci-cpufreq.c b/drivers/cpufreq/davinci-cpufreq.c
index 7d2754411d8c..8736be3a06ce 100644
--- a/drivers/cpufreq/davinci-cpufreq.c
+++ b/drivers/cpufreq/davinci-cpufreq.c
@@ -145,7 +145,7 @@ static struct platform_driver davinci_cpufreq_driver = {
 	.driver = {
 		.name	 = "cpufreq-davinci",
 	},
-	.remove_new = __exit_p(davinci_cpufreq_remove),
+	.remove = __exit_p(davinci_cpufreq_remove),
 };
 
 int __init davinci_cpufreq_init(void)
diff --git a/drivers/cpufreq/imx-cpufreq-dt.c b/drivers/cpufreq/imx-cpufreq-dt.c
index 577bb9e2f112..1492c92ffc1a 100644
--- a/drivers/cpufreq/imx-cpufreq-dt.c
+++ b/drivers/cpufreq/imx-cpufreq-dt.c
@@ -183,7 +183,7 @@ static void imx_cpufreq_dt_remove(struct platform_device *pdev)
 
 static struct platform_driver imx_cpufreq_dt_driver = {
 	.probe = imx_cpufreq_dt_probe,
-	.remove_new = imx_cpufreq_dt_remove,
+	.remove = imx_cpufreq_dt_remove,
 	.driver = {
 		.name = "imx-cpufreq-dt",
 	},
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index c20d3ecc5a81..f3c99f378ad6 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -522,7 +522,7 @@ static struct platform_driver imx6q_cpufreq_platdrv = {
 		.name	= "imx6q-cpufreq",
 	},
 	.probe		= imx6q_cpufreq_probe,
-	.remove_new	= imx6q_cpufreq_remove,
+	.remove		= imx6q_cpufreq_remove,
 };
 module_platform_driver(imx6q_cpufreq_platdrv);
 
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 400337f3b572..b8e2396a708a 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -3655,6 +3655,8 @@ static const struct x86_cpu_id intel_epp_default[] = {
 	X86_MATCH_VFM(INTEL_ALDERLAKE_L, HWP_SET_DEF_BALANCE_PERF_EPP(102)),
 	X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X, HWP_SET_DEF_BALANCE_PERF_EPP(32)),
 	X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X, HWP_SET_DEF_BALANCE_PERF_EPP(32)),
+	X86_MATCH_VFM(INTEL_GRANITERAPIDS_X, HWP_SET_DEF_BALANCE_PERF_EPP(32)),
+	X86_MATCH_VFM(INTEL_GRANITERAPIDS_D, HWP_SET_DEF_BALANCE_PERF_EPP(32)),
 	X86_MATCH_VFM(INTEL_METEORLAKE_L, HWP_SET_EPP_VALUES(HWP_EPP_POWERSAVE,
 		      179, 64, 16)),
 	X86_MATCH_VFM(INTEL_ARROWLAKE, HWP_SET_EPP_VALUES(HWP_EPP_POWERSAVE,
diff --git a/drivers/cpufreq/kirkwood-cpufreq.c b/drivers/cpufreq/kirkwood-cpufreq.c
index fd20b986d1f2..312f2654d1d5 100644
--- a/drivers/cpufreq/kirkwood-cpufreq.c
+++ b/drivers/cpufreq/kirkwood-cpufreq.c
@@ -189,7 +189,7 @@ static void kirkwood_cpufreq_remove(struct platform_device *pdev)
 
 static struct platform_driver kirkwood_cpufreq_platform_driver = {
 	.probe = kirkwood_cpufreq_probe,
-	.remove_new = kirkwood_cpufreq_remove,
+	.remove = kirkwood_cpufreq_remove,
 	.driver = {
 		.name = "kirkwood-cpufreq",
 	},
diff --git a/drivers/cpufreq/loongson3_cpufreq.c b/drivers/cpufreq/loongson3_cpufreq.c
index 6b5e6798d9a2..61ebebf69455 100644
--- a/drivers/cpufreq/loongson3_cpufreq.c
+++ b/drivers/cpufreq/loongson3_cpufreq.c
@@ -386,7 +386,7 @@ static struct platform_driver loongson3_platform_driver = {
 	},
 	.id_table = cpufreq_id_table,
 	.probe = loongson3_cpufreq_probe,
-	.remove_new = loongson3_cpufreq_remove,
+	.remove = loongson3_cpufreq_remove,
 };
 module_platform_driver(loongson3_platform_driver);
 
diff --git a/drivers/cpufreq/mediatek-cpufreq-hw.c b/drivers/cpufreq/mediatek-cpufreq-hw.c
index 8925e096d5b9..f7db5f4ad306 100644
--- a/drivers/cpufreq/mediatek-cpufreq-hw.c
+++ b/drivers/cpufreq/mediatek-cpufreq-hw.c
@@ -344,7 +344,7 @@ MODULE_DEVICE_TABLE(of, mtk_cpufreq_hw_match);
 
 static struct platform_driver mtk_cpufreq_hw_driver = {
 	.probe = mtk_cpufreq_hw_driver_probe,
-	.remove_new = mtk_cpufreq_hw_driver_remove,
+	.remove = mtk_cpufreq_hw_driver_remove,
 	.driver = {
 		.name = "mtk-cpufreq-hw",
 		.of_match_table = mtk_cpufreq_hw_match,
diff --git a/drivers/cpufreq/omap-cpufreq.c b/drivers/cpufreq/omap-cpufreq.c
index de8be0a8932d..106220c0fd11 100644
--- a/drivers/cpufreq/omap-cpufreq.c
+++ b/drivers/cpufreq/omap-cpufreq.c
@@ -188,7 +188,7 @@ static struct platform_driver omap_cpufreq_platdrv = {
 		.name	= "omap-cpufreq",
 	},
 	.probe		= omap_cpufreq_probe,
-	.remove_new	= omap_cpufreq_remove,
+	.remove		= omap_cpufreq_remove,
 };
 module_platform_driver(omap_cpufreq_platdrv);
 
diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c
index 771efbf51a48..ac2e90a65f0c 100644
--- a/drivers/cpufreq/pcc-cpufreq.c
+++ b/drivers/cpufreq/pcc-cpufreq.c
@@ -615,7 +615,7 @@ static struct platform_driver pcc_cpufreq_platdrv = {
 	.driver = {
 		.name	= "pcc-cpufreq",
 	},
-	.remove_new	= pcc_cpufreq_remove,
+	.remove		= pcc_cpufreq_remove,
 };
 
 static int __init pcc_cpufreq_init(void)
diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
index 900d6844c43d..98129565acb8 100644
--- a/drivers/cpufreq/qcom-cpufreq-hw.c
+++ b/drivers/cpufreq/qcom-cpufreq-hw.c
@@ -736,7 +736,7 @@ static void qcom_cpufreq_hw_driver_remove(struct platform_device *pdev)
 
 static struct platform_driver qcom_cpufreq_hw_driver = {
 	.probe = qcom_cpufreq_hw_driver_probe,
-	.remove_new = qcom_cpufreq_hw_driver_remove,
+	.remove = qcom_cpufreq_hw_driver_remove,
 	.driver = {
 		.name = "qcom-cpufreq-hw",
 		.of_match_table = qcom_cpufreq_hw_match,
diff --git a/drivers/cpufreq/qcom-cpufreq-nvmem.c b/drivers/cpufreq/qcom-cpufreq-nvmem.c
index 703308fb891a..08e518c89fc3 100644
--- a/drivers/cpufreq/qcom-cpufreq-nvmem.c
+++ b/drivers/cpufreq/qcom-cpufreq-nvmem.c
@@ -604,7 +604,7 @@ static DEFINE_SIMPLE_DEV_PM_OPS(qcom_cpufreq_pm_ops, qcom_cpufreq_suspend, NULL)
 
 static struct platform_driver qcom_cpufreq_driver = {
 	.probe = qcom_cpufreq_probe,
-	.remove_new = qcom_cpufreq_remove,
+	.remove = qcom_cpufreq_remove,
 	.driver = {
 		.name = "qcom-cpufreq-nvmem",
 		.pm = pm_sleep_ptr(&qcom_cpufreq_pm_ops),
diff --git a/drivers/cpufreq/qoriq-cpufreq.c b/drivers/cpufreq/qoriq-cpufreq.c
index 3519bf34d397..a37ce051236c 100644
--- a/drivers/cpufreq/qoriq-cpufreq.c
+++ b/drivers/cpufreq/qoriq-cpufreq.c
@@ -296,7 +296,7 @@ static struct platform_driver qoriq_cpufreq_platform_driver = {
 		.name = "qoriq-cpufreq",
 	},
 	.probe = qoriq_cpufreq_probe,
-	.remove_new = qoriq_cpufreq_remove,
+	.remove = qoriq_cpufreq_remove,
 };
 module_platform_driver(qoriq_cpufreq_platform_driver);
 
diff --git a/drivers/cpufreq/raspberrypi-cpufreq.c b/drivers/cpufreq/raspberrypi-cpufreq.c
index e0705cc9a57d..5050932954e3 100644
--- a/drivers/cpufreq/raspberrypi-cpufreq.c
+++ b/drivers/cpufreq/raspberrypi-cpufreq.c
@@ -85,7 +85,7 @@ static struct platform_driver raspberrypi_cpufreq_driver = {
 		.name = "raspberrypi-cpufreq",
 	},
 	.probe          = raspberrypi_cpufreq_probe,
-	.remove_new	= raspberrypi_cpufreq_remove,
+	.remove		= raspberrypi_cpufreq_remove,
 };
 module_platform_driver(raspberrypi_cpufreq_driver);
 
diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c
index 8d73e6e8be2a..cd89c1b9832c 100644
--- a/drivers/cpufreq/scpi-cpufreq.c
+++ b/drivers/cpufreq/scpi-cpufreq.c
@@ -217,7 +217,7 @@ static struct platform_driver scpi_cpufreq_platdrv = {
 		.name	= "scpi-cpufreq",
 	},
 	.probe		= scpi_cpufreq_probe,
-	.remove_new	= scpi_cpufreq_remove,
+	.remove		= scpi_cpufreq_remove,
 };
 module_platform_driver(scpi_cpufreq_platdrv);
 
diff --git a/drivers/cpufreq/sun50i-cpufreq-nvmem.c b/drivers/cpufreq/sun50i-cpufreq-nvmem.c
index 293921acec93..352e1a69a85e 100644
--- a/drivers/cpufreq/sun50i-cpufreq-nvmem.c
+++ b/drivers/cpufreq/sun50i-cpufreq-nvmem.c
@@ -283,7 +283,7 @@ static void sun50i_cpufreq_nvmem_remove(struct platform_device *pdev)
 
 static struct platform_driver sun50i_cpufreq_driver = {
 	.probe = sun50i_cpufreq_nvmem_probe,
-	.remove_new = sun50i_cpufreq_nvmem_remove,
+	.remove = sun50i_cpufreq_nvmem_remove,
 	.driver = {
 		.name = "sun50i-cpufreq-nvmem",
 	},
diff --git a/drivers/cpufreq/tegra186-cpufreq.c b/drivers/cpufreq/tegra186-cpufreq.c
index 7b8fcfa55038..c7761eb99f3c 100644
--- a/drivers/cpufreq/tegra186-cpufreq.c
+++ b/drivers/cpufreq/tegra186-cpufreq.c
@@ -276,7 +276,7 @@ static struct platform_driver tegra186_cpufreq_platform_driver = {
 		.of_match_table = tegra186_cpufreq_of_match,
 	},
 	.probe = tegra186_cpufreq_probe,
-	.remove_new = tegra186_cpufreq_remove,
+	.remove = tegra186_cpufreq_remove,
 };
 module_platform_driver(tegra186_cpufreq_platform_driver);
 
diff --git a/drivers/cpufreq/tegra194-cpufreq.c b/drivers/cpufreq/tegra194-cpufreq.c
index 07ea7ed61b68..9055dd398e7f 100644
--- a/drivers/cpufreq/tegra194-cpufreq.c
+++ b/drivers/cpufreq/tegra194-cpufreq.c
@@ -818,7 +818,7 @@ static struct platform_driver tegra194_ccplex_driver = {
 		.of_match_table = tegra194_cpufreq_of_match,
 	},
 	.probe = tegra194_cpufreq_probe,
-	.remove_new = tegra194_cpufreq_remove,
+	.remove = tegra194_cpufreq_remove,
 };
 module_platform_driver(tegra194_ccplex_driver);
 
diff --git a/drivers/cpufreq/vexpress-spc-cpufreq.c b/drivers/cpufreq/vexpress-spc-cpufreq.c
index 3fadf536c429..0f86cdb7ec8a 100644
--- a/drivers/cpufreq/vexpress-spc-cpufreq.c
+++ b/drivers/cpufreq/vexpress-spc-cpufreq.c
@@ -565,7 +565,7 @@ static struct platform_driver ve_spc_cpufreq_platdrv = {
 		.name	= "vexpress-spc-cpufreq",
 	},
 	.probe		= ve_spc_cpufreq_probe,
-	.remove_new	= ve_spc_cpufreq_remove,
+	.remove		= ve_spc_cpufreq_remove,
 };
 module_platform_driver(ve_spc_cpufreq_platdrv);
 
diff --git a/drivers/cpuidle/cpuidle-arm.c b/drivers/cpuidle/cpuidle-arm.c
index 7cfb980a357d..caba6f4bb1b7 100644
--- a/drivers/cpuidle/cpuidle-arm.c
+++ b/drivers/cpuidle/cpuidle-arm.c
@@ -139,7 +139,7 @@ out_kfree_drv:
  *
  * Initializes arm cpuidle driver for all CPUs, if any CPU fails
  * to register cpuidle driver then rollback to cancel all CPUs
- * registeration.
+ * registration.
  */
 static int __init arm_idle_init(void)
 {
diff --git a/drivers/cpuidle/cpuidle-qcom-spm.c b/drivers/cpuidle/cpuidle-qcom-spm.c
index 1fc9968eae19..3ab240e0e122 100644
--- a/drivers/cpuidle/cpuidle-qcom-spm.c
+++ b/drivers/cpuidle/cpuidle-qcom-spm.c
@@ -48,7 +48,7 @@ static int qcom_cpu_spc(struct spm_driver_data *drv)
 	ret = cpu_suspend(0, qcom_pm_collapse);
 	/*
 	 * ARM common code executes WFI without calling into our driver and
-	 * if the SPM mode is not reset, then we may accidently power down the
+	 * if the SPM mode is not reset, then we may accidentally power down the
 	 * cpu when we intended only to gate the cpu clock.
 	 * Ensure the state is set to standby before returning.
 	 */
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 9e418aec1755..06ace16f9e71 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -406,7 +406,7 @@ void cpuidle_reflect(struct cpuidle_device *dev, int index)
  * Min polling interval of 10usec is a guess. It is assuming that
  * for most users, the time for a single ping-pong workload like
  * perf bench pipe would generally complete within 10usec but
- * this is hardware dependant. Actual time can be estimated with
+ * this is hardware dependent. Actual time can be estimated with
  *
  * perf bench sched pipe -l 10000
  *
diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c
index cf5873cc45dc..9bbfa594c442 100644
--- a/drivers/cpuidle/driver.c
+++ b/drivers/cpuidle/driver.c
@@ -261,7 +261,7 @@ static void __cpuidle_unregister_driver(struct cpuidle_driver *drv)
  * @drv: a pointer to a valid struct cpuidle_driver
  *
  * Register the driver under a lock to prevent concurrent attempts to
- * [un]register the driver from occuring at the same time.
+ * [un]register the driver from occurring at the same time.
  *
  * Returns 0 on success, a negative error code (returned by
  * __cpuidle_register_driver()) otherwise.
@@ -296,7 +296,7 @@ EXPORT_SYMBOL_GPL(cpuidle_register_driver);
  * @drv: a pointer to a valid struct cpuidle_driver
  *
  * Unregisters the cpuidle driver under a lock to prevent concurrent attempts
- * to [un]register the driver from occuring at the same time.  @drv has to
+ * to [un]register the driver from occurring at the same time.  @drv has to
  * match the currently registered driver.
  */
 void cpuidle_unregister_driver(struct cpuidle_driver *drv)
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index f3c9d49f0f2a..28363bfa3e4c 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -19,7 +19,7 @@
 
 #include "gov.h"
 
-#define BUCKETS 12
+#define BUCKETS 6
 #define INTERVAL_SHIFT 3
 #define INTERVALS (1UL << INTERVAL_SHIFT)
 #define RESOLUTION 1024
@@ -29,12 +29,11 @@
 /*
  * Concepts and ideas behind the menu governor
  *
- * For the menu governor, there are 3 decision factors for picking a C
+ * For the menu governor, there are 2 decision factors for picking a C
  * state:
  * 1) Energy break even point
- * 2) Performance impact
- * 3) Latency tolerance (from pmqos infrastructure)
- * These three factors are treated independently.
+ * 2) Latency tolerance (from pmqos infrastructure)
+ * These two factors are treated independently.
  *
  * Energy break even point
  * -----------------------
@@ -75,30 +74,6 @@
  * intervals and if the stand deviation of these 8 intervals is below a
  * threshold value, we use the average of these intervals as prediction.
  *
- * Limiting Performance Impact
- * ---------------------------
- * C states, especially those with large exit latencies, can have a real
- * noticeable impact on workloads, which is not acceptable for most sysadmins,
- * and in addition, less performance has a power price of its own.
- *
- * As a general rule of thumb, menu assumes that the following heuristic
- * holds:
- *     The busier the system, the less impact of C states is acceptable
- *
- * This rule-of-thumb is implemented using a performance-multiplier:
- * If the exit latency times the performance multiplier is longer than
- * the predicted duration, the C state is not considered a candidate
- * for selection due to a too high performance impact. So the higher
- * this multiplier is, the longer we need to be idle to pick a deep C
- * state, and thus the less likely a busy CPU will hit such a deep
- * C state.
- *
- * Currently there is only one value determining the factor:
- * 10 points are added for each process that is waiting for IO on this CPU.
- * (This value was experimentally determined.)
- * Utilization is no longer a factor as it was shown that it never contributed
- * significantly to the performance multiplier in the first place.
- *
  */
 
 struct menu_device {
@@ -112,19 +87,10 @@ struct menu_device {
 	int		interval_ptr;
 };
 
-static inline int which_bucket(u64 duration_ns, unsigned int nr_iowaiters)
+static inline int which_bucket(u64 duration_ns)
 {
 	int bucket = 0;
 
-	/*
-	 * We keep two groups of stats; one with no
-	 * IO pending, one without.
-	 * This allows us to calculate
-	 * E(duration)|iowait
-	 */
-	if (nr_iowaiters)
-		bucket = BUCKETS/2;
-
 	if (duration_ns < 10ULL * NSEC_PER_USEC)
 		return bucket;
 	if (duration_ns < 100ULL * NSEC_PER_USEC)
@@ -138,19 +104,6 @@ static inline int which_bucket(u64 duration_ns, unsigned int nr_iowaiters)
 	return bucket + 5;
 }
 
-/*
- * Return a multiplier for the exit latency that is intended
- * to take performance requirements into account.
- * The more performance critical we estimate the system
- * to be, the higher this multiplier, and thus the higher
- * the barrier to go to an expensive C state.
- */
-static inline int performance_multiplier(unsigned int nr_iowaiters)
-{
-	/* for IO wait tasks (per cpu!) we add 10x each */
-	return 1 + 10 * nr_iowaiters;
-}
-
 static DEFINE_PER_CPU(struct menu_device, menu_devices);
 
 static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev);
@@ -258,8 +211,6 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	struct menu_device *data = this_cpu_ptr(&menu_devices);
 	s64 latency_req = cpuidle_governor_latency_req(dev->cpu);
 	u64 predicted_ns;
-	u64 interactivity_req;
-	unsigned int nr_iowaiters;
 	ktime_t delta, delta_tick;
 	int i, idx;
 
@@ -268,8 +219,6 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		data->needs_update = 0;
 	}
 
-	nr_iowaiters = nr_iowait_cpu(dev->cpu);
-
 	/* Find the shortest expected idle interval. */
 	predicted_ns = get_typical_interval(data) * NSEC_PER_USEC;
 	if (predicted_ns > RESIDENCY_THRESHOLD_NS) {
@@ -283,7 +232,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		}
 
 		data->next_timer_ns = delta;
-		data->bucket = which_bucket(data->next_timer_ns, nr_iowaiters);
+		data->bucket = which_bucket(data->next_timer_ns);
 
 		/* Round up the result for half microseconds. */
 		timer_us = div_u64((RESOLUTION * DECAY * NSEC_PER_USEC) / 2 +
@@ -301,7 +250,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		 */
 		data->next_timer_ns = KTIME_MAX;
 		delta_tick = TICK_NSEC / 2;
-		data->bucket = which_bucket(KTIME_MAX, nr_iowaiters);
+		data->bucket = which_bucket(KTIME_MAX);
 	}
 
 	if (unlikely(drv->state_count <= 1 || latency_req == 0) ||
@@ -328,15 +277,8 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		 */
 		if (predicted_ns < TICK_NSEC)
 			predicted_ns = data->next_timer_ns;
-	} else {
-		/*
-		 * Use the performance multiplier and the user-configurable
-		 * latency_req to determine the maximum exit latency.
-		 */
-		interactivity_req = div64_u64(predicted_ns,
-					      performance_multiplier(nr_iowaiters));
-		if (latency_req > interactivity_req)
-			latency_req = interactivity_req;
+	} else if (latency_req > predicted_ns) {
+		latency_req = predicted_ns;
 	}
 
 	/*
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 67aebfe0fed6..ac4d8faa3886 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -1069,6 +1069,47 @@ static struct cpuidle_state gnr_cstates[] __initdata = {
 		.enter = NULL }
 };
 
+static struct cpuidle_state gnrd_cstates[] __initdata = {
+	{
+		.name = "C1",
+		.desc = "MWAIT 0x00",
+		.flags = MWAIT2flg(0x00),
+		.exit_latency = 1,
+		.target_residency = 1,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C1E",
+		.desc = "MWAIT 0x01",
+		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_ALWAYS_ENABLE,
+		.exit_latency = 4,
+		.target_residency = 4,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C6",
+		.desc = "MWAIT 0x20",
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED |
+					   CPUIDLE_FLAG_INIT_XSTATE |
+					   CPUIDLE_FLAG_PARTIAL_HINT_MATCH,
+		.exit_latency = 220,
+		.target_residency = 650,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C6P",
+		.desc = "MWAIT 0x21",
+		.flags = MWAIT2flg(0x21) | CPUIDLE_FLAG_TLB_FLUSHED |
+					   CPUIDLE_FLAG_INIT_XSTATE |
+					   CPUIDLE_FLAG_PARTIAL_HINT_MATCH,
+		.exit_latency = 240,
+		.target_residency = 750,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.enter = NULL }
+};
+
 static struct cpuidle_state atom_cstates[] __initdata = {
 	{
 		.name = "C1E",
@@ -1508,6 +1549,12 @@ static const struct idle_cpu idle_cpu_gnr __initconst = {
 	.use_acpi = true,
 };
 
+static const struct idle_cpu idle_cpu_gnrd __initconst = {
+	.state_table = gnrd_cstates,
+	.disable_promotion_to_c1e = true,
+	.use_acpi = true,
+};
+
 static const struct idle_cpu idle_cpu_avn __initconst = {
 	.state_table = avn_cstates,
 	.disable_promotion_to_c1e = true,
@@ -1593,6 +1640,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X,	&idle_cpu_spr),
 	X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X,	&idle_cpu_spr),
 	X86_MATCH_VFM(INTEL_GRANITERAPIDS_X,	&idle_cpu_gnr),
+	X86_MATCH_VFM(INTEL_GRANITERAPIDS_D,	&idle_cpu_gnrd),
 	X86_MATCH_VFM(INTEL_XEON_PHI_KNL,	&idle_cpu_knl),
 	X86_MATCH_VFM(INTEL_XEON_PHI_KNM,	&idle_cpu_knl),
 	X86_MATCH_VFM(INTEL_ATOM_GOLDMONT,	&idle_cpu_bxt),