File _service:download_files:0001-amd-6.3-Implement-... of Package linux-px

Overview Repositories Revisions Requests Users Attributes Meta

File _service:download_files:0001-amd-6.3-Implement-AMD-Pstate-EPP-Driver-with-guided-.patch of Package linux-px (Revision b56ed79f7c7a2208faf9c9ffe2664cf6)

Currently displaying revision b56ed79f7c7a2208faf9c9ffe2664cf6 , Show latest

From b9ad1703a80f787432ad93e80ecb9fb136917826 Mon Sep 17 00:00:00 2001
From: Piotr Gorski <lucjan.lucjanov@gmail.com>
Date: Tue, 30 May 2023 18:44:21 +0200
Subject: [PATCH] amd-6.3: Implement AMD Pstate EPP Driver with guided
 autonomous mode support

Signed-off-by: Piotr Gorski <lucjan.lucjanov@gmail.com>
---
 .../admin-guide/kernel-parameters.txt         |  40 +--
 Documentation/admin-guide/pm/amd-pstate.rst   |  31 ++-
 drivers/acpi/cppc_acpi.c                      | 121 ++++++++-
 drivers/cpufreq/amd-pstate.c                  | 243 +++++++++++++-----
 drivers/cpufreq/cpufreq.c                     |   3 +-
 include/acpi/cppc_acpi.h                      |  11 +
 include/linux/amd-pstate.h                    |   2 +
 include/linux/cpufreq.h                       |   5 +-
 8 files changed, 354 insertions(+), 102 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 7016cb12d..744ac443d 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -339,6 +339,29 @@
 			             This mode requires kvm-amd.avic=1.
 			             (Default when IOMMU HW support is present.)
 
+	amd_pstate=	[X86]
+			disable
+			  Do not enable amd_pstate as the default
+			  scaling driver for the supported processors
+			passive
+			  Use amd_pstate with passive mode as a scaling driver.
+			  In this mode autonomous selection is disabled.
+			  Driver requests a desired performance level and platform
+			  tries to match the same performance level if it is
+			  satisfied by guaranteed performance level.
+			active
+			  Use amd_pstate_epp driver instance as the scaling driver,
+			  driver provides a hint to the hardware if software wants
+			  to bias toward performance (0x0) or energy efficiency (0xff)
+			  to the CPPC firmware. then CPPC power algorithm will
+			  calculate the runtime workload and adjust the realtime cores
+			  frequency.
+			guided
+			  Activate guided autonomous mode. Driver requests minimum and
+			  maximum performance level and the platform autonomously
+			  selects a performance level in this range and appropriate
+			  to the current workload.
+
 	amijoy.map=	[HW,JOY] Amiga joystick support
 			Map of devices attached to JOY0DAT and JOY1DAT
 			Format: <a>,<b>
@@ -7065,20 +7088,3 @@
 				xmon commands.
 			off	xmon is disabled.
 
-	amd_pstate=	[X86]
-			disable
-			  Do not enable amd_pstate as the default
-			  scaling driver for the supported processors
-			passive
-			  Use amd_pstate as a scaling driver, driver requests a
-			  desired performance on this abstract scale and the power
-			  management firmware translates the requests into actual
-			  hardware states (core frequency, data fabric and memory
-			  clocks etc.)
-			active
-			  Use amd_pstate_epp driver instance as the scaling driver,
-			  driver provides a hint to the hardware if software wants
-			  to bias toward performance (0x0) or energy efficiency (0xff)
-			  to the CPPC firmware. then CPPC power algorithm will
-			  calculate the runtime workload and adjust the realtime cores
-			  frequency.
diff --git a/Documentation/admin-guide/pm/amd-pstate.rst b/Documentation/admin-guide/pm/amd-pstate.rst
index 6e5298b52..1cf40f692 100644
--- a/Documentation/admin-guide/pm/amd-pstate.rst
+++ b/Documentation/admin-guide/pm/amd-pstate.rst
@@ -303,13 +303,18 @@ efficiency frequency management method on AMD processors.
 AMD Pstate Driver Operation Modes
 =================================
 
-``amd_pstate`` CPPC has two operation modes: CPPC Autonomous(active) mode and
-CPPC non-autonomous(passive) mode.
-active mode and passive mode can be chosen by different kernel parameters.
-When in Autonomous mode, CPPC ignores requests done in the Desired Performance
-Target register and takes into account only the values set to the Minimum requested
-performance, Maximum requested performance, and Energy Performance Preference
-registers. When Autonomous is disabled, it only considers the Desired Performance Target.
+``amd_pstate`` CPPC has 3 operation modes: autonomous (active) mode,
+non-autonomous (passive) mode and guided autonomous (guided) mode.
+Active/passive/guided mode can be chosen by different kernel parameters.
+
+- In autonomous mode, platform ignores the desired performance level request
+  and takes into account only the values set to the minimum, maximum and energy
+  performance preference registers.
+- In non-autonomous mode, platform gets desired performance level
+  from OS directly through Desired Performance Register.
+- In guided-autonomous mode, platform sets operating performance level
+  autonomously according to the current workload and within the limits set by
+  OS through min and max performance registers.
 
 Active Mode
 ------------
@@ -338,6 +343,15 @@ to the Performance Reduction Tolerance register. Above the nominal performance l
 processor must provide at least nominal performance requested and go higher if current
 operating conditions allow.
 
+Guided Mode
+-----------
+
+``amd_pstate=guided``
+
+If ``amd_pstate=guided`` is passed to kernel command line option then this mode
+is activated.  In this mode, driver requests minimum and maximum performance
+level and the platform autonomously selects a performance level in this range
+and appropriate to the current workload.
 
 User Space Interface in ``sysfs`` - General
 ===========================================
@@ -358,6 +372,9 @@ control its functionality at the system level.  They are located in the
 	"passive"
 		The driver is functional and in the ``passive mode``
 
+	"guided"
+		The driver is functional and in the ``guided mode``
+
 	"disable"
 		The driver is unregistered and not functional now.
 
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index c51d3ccb4..02a4bfb54 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -1433,6 +1433,103 @@ int cppc_set_epp_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls, bool enable)
 }
 EXPORT_SYMBOL_GPL(cppc_set_epp_perf);
 
+/*
+ * cppc_get_auto_sel_caps - Read autonomous selection register.
+ * @cpunum : CPU from which to read register.
+ * @perf_caps : struct where autonomous selection register value is updated.
+ */
+int cppc_get_auto_sel_caps(int cpunum, struct cppc_perf_caps *perf_caps)
+{
+	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpunum);
+	struct cpc_register_resource *auto_sel_reg;
+	u64  auto_sel;
+
+	if (!cpc_desc) {
+		pr_debug("No CPC descriptor for CPU:%d\n", cpunum);
+		return -ENODEV;
+	}
+
+	auto_sel_reg = &cpc_desc->cpc_regs[AUTO_SEL_ENABLE];
+
+	if (!CPC_SUPPORTED(auto_sel_reg))
+		pr_warn_once("Autonomous mode is not unsupported!\n");
+
+	if (CPC_IN_PCC(auto_sel_reg)) {
+		int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpunum);
+		struct cppc_pcc_data *pcc_ss_data = NULL;
+		int ret = 0;
+
+		if (pcc_ss_id < 0)
+			return -ENODEV;
+
+		pcc_ss_data = pcc_data[pcc_ss_id];
+
+		down_write(&pcc_ss_data->pcc_lock);
+
+		if (send_pcc_cmd(pcc_ss_id, CMD_READ) >= 0) {
+			cpc_read(cpunum, auto_sel_reg, &auto_sel);
+			perf_caps->auto_sel = (bool)auto_sel;
+		} else {
+			ret = -EIO;
+		}
+
+		up_write(&pcc_ss_data->pcc_lock);
+
+		return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cppc_get_auto_sel_caps);
+
+/*
+ * cppc_set_auto_sel - Write autonomous selection register.
+ * @cpu    : CPU to which to write register.
+ * @enable : the desired value of autonomous selection resiter to be updated.
+ */
+int cppc_set_auto_sel(int cpu, bool enable)
+{
+	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu);
+	struct cpc_register_resource *auto_sel_reg;
+	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpu);
+	struct cppc_pcc_data *pcc_ss_data = NULL;
+	int ret = -EINVAL;
+
+	if (!cpc_desc) {
+		pr_debug("No CPC descriptor for CPU:%d\n", cpu);
+		return -ENODEV;
+	}
+
+	auto_sel_reg = &cpc_desc->cpc_regs[AUTO_SEL_ENABLE];
+
+	if (CPC_IN_PCC(auto_sel_reg)) {
+		if (pcc_ss_id < 0) {
+			pr_debug("Invalid pcc_ss_id\n");
+			return -ENODEV;
+		}
+
+		if (CPC_SUPPORTED(auto_sel_reg)) {
+			ret = cpc_write(cpu, auto_sel_reg, enable);
+			if (ret)
+				return ret;
+		}
+
+		pcc_ss_data = pcc_data[pcc_ss_id];
+
+		down_write(&pcc_ss_data->pcc_lock);
+		/* after writing CPC, transfer the ownership of PCC to platform */
+		ret = send_pcc_cmd(pcc_ss_id, CMD_WRITE);
+		up_write(&pcc_ss_data->pcc_lock);
+	} else {
+		ret = -ENOTSUPP;
+		pr_debug("_CPC in PCC is not supported\n");
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(cppc_set_auto_sel);
+
+
 /**
  * cppc_set_enable - Set to enable CPPC on the processor by writing the
  * Continuous Performance Control package EnableRegister field.
@@ -1488,7 +1585,7 @@ EXPORT_SYMBOL_GPL(cppc_set_enable);
 int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls)
 {
 	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpu);
-	struct cpc_register_resource *desired_reg;
+	struct cpc_register_resource *desired_reg, *min_perf_reg, *max_perf_reg;
 	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu);
 	struct cppc_pcc_data *pcc_ss_data = NULL;
 	int ret = 0;
@@ -1499,6 +1596,8 @@ int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls)
 	}
 
 	desired_reg = &cpc_desc->cpc_regs[DESIRED_PERF];
+	min_perf_reg = &cpc_desc->cpc_regs[MIN_PERF];
+	max_perf_reg = &cpc_desc->cpc_regs[MAX_PERF];
 
 	/*
 	 * This is Phase-I where we want to write to CPC registers
@@ -1507,7 +1606,7 @@ int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls)
 	 * Since read_lock can be acquired by multiple CPUs simultaneously we
 	 * achieve that goal here
 	 */
-	if (CPC_IN_PCC(desired_reg)) {
+	if (CPC_IN_PCC(desired_reg) || CPC_IN_PCC(min_perf_reg) || CPC_IN_PCC(max_perf_reg)) {
 		if (pcc_ss_id < 0) {
 			pr_debug("Invalid pcc_ss_id\n");
 			return -ENODEV;
@@ -1530,13 +1629,19 @@ int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls)
 		cpc_desc->write_cmd_status = 0;
 	}
 
-	/*
-	 * Skip writing MIN/MAX until Linux knows how to come up with
-	 * useful values.
-	 */
 	cpc_write(cpu, desired_reg, perf_ctrls->desired_perf);
 
-	if (CPC_IN_PCC(desired_reg))
+	/**
+	 * Only write if min_perf and max_perf not zero. Some drivers pass zero
+	 * value to min and max perf, but they don't mean to set the zero value,
+	 * they just don't want to write to those registers.
+	 */
+	if (perf_ctrls->min_perf)
+		cpc_write(cpu, min_perf_reg, perf_ctrls->min_perf);
+	if (perf_ctrls->max_perf)
+		cpc_write(cpu, max_perf_reg, perf_ctrls->max_perf);
+
+	if (CPC_IN_PCC(desired_reg) || CPC_IN_PCC(min_perf_reg) || CPC_IN_PCC(max_perf_reg))
 		up_read(&pcc_ss_data->pcc_lock);	/* END Phase-I */
 	/*
 	 * This is Phase-II where we transfer the ownership of PCC to Platform
@@ -1584,7 +1689,7 @@ int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls)
 	 * case during a CMD_READ and if there are pending writes it delivers
 	 * the write command before servicing the read command
 	 */
-	if (CPC_IN_PCC(desired_reg)) {
+	if (CPC_IN_PCC(desired_reg) || CPC_IN_PCC(min_perf_reg) || CPC_IN_PCC(max_perf_reg)) {
 		if (down_write_trylock(&pcc_ss_data->pcc_lock)) {/* BEGIN Phase-II */
 			/* Update only if there are pending write commands */
 			if (pcc_ss_data->pending_pcc_write_cmd)
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 8dd46fad1..ddd346a23 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -63,7 +63,6 @@ static struct cpufreq_driver *current_pstate_driver;
 static struct cpufreq_driver amd_pstate_driver;
 static struct cpufreq_driver amd_pstate_epp_driver;
 static int cppc_state = AMD_PSTATE_DISABLE;
-struct kobject *amd_pstate_kobj;
 
 /*
  * AMD Energy Preference Performance (EPP)
@@ -106,6 +105,8 @@ static unsigned int epp_values[] = {
 	[EPP_INDEX_POWERSAVE] = AMD_CPPC_EPP_POWERSAVE,
  };
 
+typedef int (*cppc_mode_transition_fn)(int);
+
 static inline int get_mode_idx_from_str(const char *str, size_t size)
 {
 	int i;
@@ -308,7 +309,22 @@ static int cppc_init_perf(struct amd_cpudata *cpudata)
 		   cppc_perf.lowest_nonlinear_perf);
 	WRITE_ONCE(cpudata->lowest_perf, cppc_perf.lowest_perf);
 
-	return 0;
+	if (cppc_state == AMD_PSTATE_ACTIVE)
+		return 0;
+
+	ret = cppc_get_auto_sel_caps(cpudata->cpu, &cppc_perf);
+	if (ret) {
+		pr_warn("failed to get auto_sel, ret: %d\n", ret);
+		return 0;
+	}
+
+	ret = cppc_set_auto_sel(cpudata->cpu,
+			(cppc_state == AMD_PSTATE_PASSIVE) ? 0 : 1);
+
+	if (ret)
+		pr_warn("failed to set auto_sel, ret: %d\n", ret);
+
+	return ret;
 }
 
 DEFINE_STATIC_CALL(amd_pstate_init_perf, pstate_init_perf);
@@ -385,12 +401,18 @@ static inline bool amd_pstate_sample(struct amd_cpudata *cpudata)
 }
 
 static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf,
-			      u32 des_perf, u32 max_perf, bool fast_switch)
+			      u32 des_perf, u32 max_perf, bool fast_switch, int gov_flags)
 {
 	u64 prev = READ_ONCE(cpudata->cppc_req_cached);
 	u64 value = prev;
 
 	des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf);
+
+	if ((cppc_state == AMD_PSTATE_GUIDED) && (gov_flags & CPUFREQ_GOV_DYNAMIC_SWITCHING)) {
+		min_perf = des_perf;
+		des_perf = 0;
+	}
+
 	value &= ~AMD_CPPC_MIN_PERF(~0L);
 	value |= AMD_CPPC_MIN_PERF(min_perf);
 
@@ -422,9 +444,8 @@ static int amd_pstate_verify(struct cpufreq_policy_data *policy)
 	return 0;
 }
 
-static int amd_pstate_target(struct cpufreq_policy *policy,
-			     unsigned int target_freq,
-			     unsigned int relation)
+static int amd_pstate_update_freq(struct cpufreq_policy *policy,
+				  unsigned int target_freq, bool fast_switch)
 {
 	struct cpufreq_freqs freqs;
 	struct amd_cpudata *cpudata = policy->driver_data;
@@ -443,26 +464,51 @@ static int amd_pstate_target(struct cpufreq_policy *policy,
 	des_perf = DIV_ROUND_CLOSEST(target_freq * cap_perf,
 				     cpudata->max_freq);
 
-	cpufreq_freq_transition_begin(policy, &freqs);
+	WARN_ON(fast_switch && !policy->fast_switch_enabled);
+	/*
+	 * If fast_switch is desired, then there aren't any registered
+	 * transition notifiers. See comment for
+	 * cpufreq_enable_fast_switch().
+	 */
+	if (!fast_switch)
+		cpufreq_freq_transition_begin(policy, &freqs);
+
 	amd_pstate_update(cpudata, min_perf, des_perf,
-			  max_perf, false);
-	cpufreq_freq_transition_end(policy, &freqs, false);
+			max_perf, fast_switch, policy->governor->flags);
+
+	if (!fast_switch)
+		cpufreq_freq_transition_end(policy, &freqs, false);
 
 	return 0;
 }
 
+static int amd_pstate_target(struct cpufreq_policy *policy,
+			     unsigned int target_freq,
+			     unsigned int relation)
+{
+	return amd_pstate_update_freq(policy, target_freq, false);
+}
+
+static unsigned int amd_pstate_fast_switch(struct cpufreq_policy *policy,
+				  unsigned int target_freq)
+{
+	return amd_pstate_update_freq(policy, target_freq, true);
+}
+
 static void amd_pstate_adjust_perf(unsigned int cpu,
 				   unsigned long _min_perf,
 				   unsigned long target_perf,
 				   unsigned long capacity)
 {
 	unsigned long max_perf, min_perf, des_perf,
-		      cap_perf, lowest_nonlinear_perf;
+		      cap_perf, lowest_nonlinear_perf, max_freq;
 	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
 	struct amd_cpudata *cpudata = policy->driver_data;
+	unsigned int target_freq;
 
 	cap_perf = READ_ONCE(cpudata->highest_perf);
 	lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf);
+	max_freq = READ_ONCE(cpudata->max_freq);
 
 	des_perf = cap_perf;
 	if (target_perf < capacity)
@@ -479,7 +525,12 @@ static void amd_pstate_adjust_perf(unsigned int cpu,
 	if (max_perf < min_perf)
 		max_perf = min_perf;
 
-	amd_pstate_update(cpudata, min_perf, des_perf, max_perf, true);
+	des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf);
+	target_freq = div_u64(des_perf * max_freq, max_perf);
+	policy->cur = target_freq;
+
+	amd_pstate_update(cpudata, min_perf, des_perf, max_perf, true,
+			policy->governor->flags);
 	cpufreq_cpu_put(policy);
 }
 
@@ -692,6 +743,7 @@ static int amd_pstate_cpu_exit(struct cpufreq_policy *policy)
 
 	freq_qos_remove_request(&cpudata->req[1]);
 	freq_qos_remove_request(&cpudata->req[0]);
+	policy->fast_switch_possible = false;
 	kfree(cpudata);
 
 	return 0;
@@ -816,6 +868,98 @@ static ssize_t show_energy_performance_preference(
 	return sysfs_emit(buf, "%s\n", energy_perf_strings[preference]);
 }
 
+static void amd_pstate_driver_cleanup(void)
+{
+	amd_pstate_enable(false);
+	cppc_state = AMD_PSTATE_DISABLE;
+	current_pstate_driver = NULL;
+}
+
+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;
+
+	cppc_state = mode;
+	ret = cpufreq_register_driver(current_pstate_driver);
+	if (ret) {
+		amd_pstate_driver_cleanup();
+		return ret;
+	}
+	return 0;
+}
+
+static int amd_pstate_unregister_driver(int dummy)
+{
+	cpufreq_unregister_driver(current_pstate_driver);
+	amd_pstate_driver_cleanup();
+	return 0;
+}
+
+static int amd_pstate_change_mode_without_dvr_change(int mode)
+{
+	int cpu = 0;
+
+	cppc_state = mode;
+
+	if (boot_cpu_has(X86_FEATURE_CPPC) || cppc_state == AMD_PSTATE_ACTIVE)
+		return 0;
+
+	for_each_present_cpu(cpu) {
+		cppc_set_auto_sel(cpu, (cppc_state == AMD_PSTATE_PASSIVE) ? 0 : 1);
+	}
+
+	return 0;
+}
+
+static int amd_pstate_change_driver_mode(int mode)
+{
+	int ret;
+
+	ret = amd_pstate_unregister_driver(0);
+	if (ret)
+		return ret;
+
+	ret = amd_pstate_register_driver(mode);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static cppc_mode_transition_fn mode_state_machine[AMD_PSTATE_MAX][AMD_PSTATE_MAX] = {
+	[AMD_PSTATE_DISABLE]         = {
+		[AMD_PSTATE_DISABLE]     = NULL,
+		[AMD_PSTATE_PASSIVE]     = amd_pstate_register_driver,
+		[AMD_PSTATE_ACTIVE]      = amd_pstate_register_driver,
+		[AMD_PSTATE_GUIDED]      = amd_pstate_register_driver,
+	},
+	[AMD_PSTATE_PASSIVE]         = {
+		[AMD_PSTATE_DISABLE]     = amd_pstate_unregister_driver,
+		[AMD_PSTATE_PASSIVE]     = NULL,
+		[AMD_PSTATE_ACTIVE]      = amd_pstate_change_driver_mode,
+		[AMD_PSTATE_GUIDED]      = amd_pstate_change_mode_without_dvr_change,
+	},
+	[AMD_PSTATE_ACTIVE]          = {
+		[AMD_PSTATE_DISABLE]     = amd_pstate_unregister_driver,
+		[AMD_PSTATE_PASSIVE]     = amd_pstate_change_driver_mode,
+		[AMD_PSTATE_ACTIVE]      = NULL,
+		[AMD_PSTATE_GUIDED]      = amd_pstate_change_driver_mode,
+	},
+	[AMD_PSTATE_GUIDED]          = {
+		[AMD_PSTATE_DISABLE]     = amd_pstate_unregister_driver,
+		[AMD_PSTATE_PASSIVE]     = amd_pstate_change_mode_without_dvr_change,
+		[AMD_PSTATE_ACTIVE]      = amd_pstate_change_driver_mode,
+		[AMD_PSTATE_GUIDED]      = NULL,
+	},
+};
+
 static ssize_t amd_pstate_show_status(char *buf)
 {
 	if (!current_pstate_driver)
@@ -824,55 +968,22 @@ static ssize_t amd_pstate_show_status(char *buf)
 	return sysfs_emit(buf, "%s\n", amd_pstate_mode_string[cppc_state]);
 }
 
-static void amd_pstate_driver_cleanup(void)
-{
-	current_pstate_driver = NULL;
-}
-
 static int amd_pstate_update_status(const char *buf, size_t size)
 {
-	int ret = 0;
 	int mode_idx;
 
-	if (size > 7 || size < 6)
+	if (size > strlen("passive") || size < strlen("active"))
 		return -EINVAL;
-	mode_idx = get_mode_idx_from_str(buf, size);
 
-	switch(mode_idx) {
-	case AMD_PSTATE_DISABLE:
-		if (current_pstate_driver) {
-			cpufreq_unregister_driver(current_pstate_driver);
-			amd_pstate_driver_cleanup();
-		}
-		break;
-	case AMD_PSTATE_PASSIVE:
-		if (current_pstate_driver) {
-			if (current_pstate_driver == &amd_pstate_driver)
-				return 0;
-			cpufreq_unregister_driver(current_pstate_driver);
-		}
+	mode_idx = get_mode_idx_from_str(buf, size);
 
-		current_pstate_driver = &amd_pstate_driver;
-		cppc_state = AMD_PSTATE_PASSIVE;
-		ret = cpufreq_register_driver(current_pstate_driver);
-		break;
-	case AMD_PSTATE_ACTIVE:
-		if (current_pstate_driver) {
-			if (current_pstate_driver == &amd_pstate_epp_driver)
-				return 0;
-			cpufreq_unregister_driver(current_pstate_driver);
-		}
+	if (mode_idx < 0 || mode_idx >= AMD_PSTATE_MAX)
+		return -EINVAL;
 
-		current_pstate_driver = &amd_pstate_epp_driver;
-		cppc_state = AMD_PSTATE_ACTIVE;
-		ret = cpufreq_register_driver(current_pstate_driver);
-		break;
-	default:
-		ret = -EINVAL;
-		break;
-	}
+	if (mode_state_machine[cppc_state][mode_idx])
+		return mode_state_machine[cppc_state][mode_idx](mode_idx);
 
-	return ret;
+	return 0;
 }
 
 static ssize_t show_status(struct kobject *kobj,
@@ -930,6 +1041,7 @@ static struct attribute *pstate_global_attributes[] = {
 };
 
 static const struct attribute_group amd_pstate_global_attr_group = {
+	.name = "amd_pstate",
 	.attrs = pstate_global_attributes,
 };
 
@@ -996,7 +1108,6 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 	policy->policy = CPUFREQ_POLICY_POWERSAVE;
 
 	if (boot_cpu_has(X86_FEATURE_CPPC)) {
-		policy->fast_switch_possible = true;
 		ret = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, &value);
 		if (ret)
 			return ret;
@@ -1019,7 +1130,6 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 static int amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy)
 {
 	pr_debug("CPU %d exiting\n", policy->cpu);
-	policy->fast_switch_possible = false;
 	return 0;
 }
 
@@ -1226,6 +1336,7 @@ static struct cpufreq_driver amd_pstate_driver = {
 	.flags		= CPUFREQ_CONST_LOOPS | CPUFREQ_NEED_UPDATE_LIMITS,
 	.verify		= amd_pstate_verify,
 	.target		= amd_pstate_target,
+	.fast_switch    = amd_pstate_fast_switch,
 	.init		= amd_pstate_cpu_init,
 	.exit		= amd_pstate_cpu_exit,
 	.suspend	= amd_pstate_cpu_suspend,
@@ -1251,6 +1362,7 @@ static struct cpufreq_driver amd_pstate_epp_driver = {
 
 static int __init amd_pstate_init(void)
 {
+	struct device *dev_root;
 	int ret;
 
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
@@ -1277,7 +1389,7 @@ static int __init amd_pstate_init(void)
 	/* capability check */
 	if (boot_cpu_has(X86_FEATURE_CPPC)) {
 		pr_debug("AMD CPPC MSR based functionality is supported\n");
-		if (cppc_state == AMD_PSTATE_PASSIVE)
+		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");
@@ -1297,24 +1409,19 @@ static int __init amd_pstate_init(void)
 	if (ret)
 		pr_err("failed to register with return %d\n", ret);
 
-	amd_pstate_kobj = kobject_create_and_add("amd_pstate", &cpu_subsys.dev_root->kobj);
-	if (!amd_pstate_kobj) {
-		ret = -EINVAL;
-		pr_err("global sysfs registration failed.\n");
-		goto kobject_free;
-	}
-
-	ret = sysfs_create_group(amd_pstate_kobj, &amd_pstate_global_attr_group);
-	if (ret) {
-		pr_err("sysfs attribute export failed with error %d.\n", ret);
-		goto global_attr_free;
+	dev_root = bus_get_dev_root(&cpu_subsys);
+	if (dev_root) {
+		ret = sysfs_create_group(&dev_root->kobj, &amd_pstate_global_attr_group);
+		put_device(dev_root);
+		if (ret) {
+			pr_err("sysfs attribute export failed with error %d.\n", ret);
+			goto global_attr_free;
+		}
 	}
 
 	return ret;
 
 global_attr_free:
-	kobject_put(amd_pstate_kobj);
-kobject_free:
 	cpufreq_unregister_driver(current_pstate_driver);
 	return ret;
 }
@@ -1339,7 +1446,7 @@ static int __init amd_pstate_param(char *str)
 		if (cppc_state == AMD_PSTATE_ACTIVE)
 			current_pstate_driver = &amd_pstate_epp_driver;
 
-		if (cppc_state == AMD_PSTATE_PASSIVE)
+		if (cppc_state == AMD_PSTATE_PASSIVE || cppc_state == AMD_PSTATE_GUIDED)
 			current_pstate_driver = &amd_pstate_driver;
 
 		return 0;
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index a0742c787..a575dfa4b 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -2823,7 +2823,8 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 	     (driver_data->setpolicy && (driver_data->target_index ||
 		    driver_data->target)) ||
 	     (!driver_data->get_intermediate != !driver_data->target_intermediate) ||
-	     (!driver_data->online != !driver_data->offline))
+	     (!driver_data->online != !driver_data->offline) ||
+		 (driver_data->adjust_perf && !driver_data->fast_switch))
 		return -EINVAL;
 
 	pr_debug("trying to register driver %s\n", driver_data->name);
diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h
index 6b487a5bd..6126c977e 100644
--- a/include/acpi/cppc_acpi.h
+++ b/include/acpi/cppc_acpi.h
@@ -109,6 +109,7 @@ struct cppc_perf_caps {
 	u32 lowest_freq;
 	u32 nominal_freq;
 	u32 energy_perf;
+	bool auto_sel;
 };
 
 struct cppc_perf_ctrls {
@@ -153,6 +154,8 @@ extern int cpc_read_ffh(int cpunum, struct cpc_reg *reg, u64 *val);
 extern int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val);
 extern int cppc_get_epp_perf(int cpunum, u64 *epp_perf);
 extern int cppc_set_epp_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls, bool enable);
+extern int cppc_get_auto_sel_caps(int cpunum, struct cppc_perf_caps *perf_caps);
+extern int cppc_set_auto_sel(int cpu, bool enable);
 #else /* !CONFIG_ACPI_CPPC_LIB */
 static inline int cppc_get_desired_perf(int cpunum, u64 *desired_perf)
 {
@@ -214,6 +217,14 @@ static inline int cppc_get_epp_perf(int cpunum, u64 *epp_perf)
 {
 	return -ENOTSUPP;
 }
+static inline int cppc_set_auto_sel(int cpu, bool enable)
+{
+	return -ENOTSUPP;
+}
+static inline int cppc_get_auto_sel_caps(int cpunum, struct cppc_perf_caps *perf_caps)
+{
+	return -ENOTSUPP;
+}
 #endif /* !CONFIG_ACPI_CPPC_LIB */
 
 #endif /* _CPPC_ACPI_H*/
diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h
index f5f22418e..c10ebf8c4 100644
--- a/include/linux/amd-pstate.h
+++ b/include/linux/amd-pstate.h
@@ -97,6 +97,7 @@ enum amd_pstate_mode {
 	AMD_PSTATE_DISABLE = 0,
 	AMD_PSTATE_PASSIVE,
 	AMD_PSTATE_ACTIVE,
+	AMD_PSTATE_GUIDED,
 	AMD_PSTATE_MAX,
 };
 
@@ -104,6 +105,7 @@ static const char * const amd_pstate_mode_string[] = {
 	[AMD_PSTATE_DISABLE]     = "disable",
 	[AMD_PSTATE_PASSIVE]     = "passive",
 	[AMD_PSTATE_ACTIVE]      = "active",
+	[AMD_PSTATE_GUIDED]      = "guided",
 	NULL,
 };
 #endif /* _LINUX_AMD_PSTATE_H */
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 65623233a..b5d734b0f 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -340,7 +340,10 @@ struct cpufreq_driver {
 	/*
 	 * ->fast_switch() replacement for drivers that use an internal
 	 * representation of performance levels and can pass hints other than
-	 * the target performance level to the hardware.
+	 * the target performance level to the hardware. This can only be set
+	 * if ->fast_switch is set too, because in those cases (under specific
+	 * conditions) scale invariance can be disabled, which causes the
+	 * schedutil governor to fall back to the latter.
 	 */
 	void		(*adjust_perf)(unsigned int cpu,
 				       unsigned long min_perf,
-- 
2.40.1.445.gf85cd430b1

Places

File _service:download_files:0001-amd-6.3-Implement-AMD-Pstate-EPP-Driver-with-guided-.patch of Package linux-px (Revision b56ed79f7c7a2208faf9c9ffe2664cf6)

Places