Merge: Update amd-pstate cpufrequency driver

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/1745

Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2150425
Tested: TBD

The main impetus for this patchset is to change the driver from
a loadable module to a builtin.  The builtin will not load by
default but requires a kernel command line option to load.

At the same time it makes sense to update the driver to match
upstream, which I have done here.

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

Approved-by: Dean Nelson <dnelson@redhat.com>
Approved-by: Prarit Bhargava <prarit@redhat.com>
Approved-by: Mark Langsdorf <mlangsdo@redhat.com>

Signed-off-by: Herton R. Krzesinski <herton@redhat.com>

Author: Herton R. Krzesinski

Documentation/admin-guide/acpi/cppc_sysfs.rst

@@ -4,6 +4,8 @@
 Collaborative Processor Performance Control (CPPC)
 ==================================================
 
+.. _cppc_sysfs:
+
 CPPC
 ====
 

Documentation/admin-guide/pm/amd-pstate.rst

@@ -11,6 +11,7 @@ Working-State Power Management
    intel_idle
    cpufreq
    intel_pstate
+   amd-pstate
    cpufreq_drivers
    intel_epb
    intel-speed-select

Documentation/admin-guide/pm/working-state.rst

@@ -1016,6 +1016,14 @@ S:	Supported
 T:	git https://gitlab.freedesktop.org/agd5f/linux.git
 F:	drivers/gpu/drm/amd/pm/powerplay/
 
+AMD PSTATE DRIVER
+M:	Huang Rui <ray.huang@amd.com>
+L:	linux-pm@vger.kernel.org
+S:	Supported
+F:	Documentation/admin-guide/pm/amd-pstate.rst
+F:	drivers/cpufreq/amd-pstate*
+F:	include/linux/amd-pstate.h
+
 AMD PTDMA DRIVER
 M:	Sanjay R Mehta <sanju.mehta@amd.com>
 L:	dmaengine@vger.kernel.org

MAINTAINERS

@@ -424,6 +424,9 @@ bool acpi_cpc_valid(void)
 	struct cpc_desc *cpc_ptr;
 	int cpu;
 
+	if (acpi_disabled)
+		return false;
+
 	for_each_present_cpu(cpu) {
 		cpc_ptr = per_cpu(cpc_desc_ptr, cpu);
 		if (!cpc_ptr)

drivers/acpi/cppc_acpi.c

@@ -346,7 +346,7 @@ void topology_init_cpu_capacity_cppc(void)
 	struct cppc_perf_caps perf_caps;
 	int cpu;
 
-	if (likely(acpi_disabled || !acpi_cpc_valid()))
+	if (likely(!acpi_cpc_valid()))
 		return;
 
 	raw_capacity = kcalloc(num_possible_cpus(), sizeof(*raw_capacity),

drivers/base/arch_topology.c

@@ -35,7 +35,7 @@ config X86_PCC_CPUFREQ
 	  If in doubt, say N.
 
 config X86_AMD_PSTATE
-	tristate "AMD Processor P-State driver"
+	bool "AMD Processor P-State driver"
 	depends on X86 && ACPI
 	select ACPI_PROCESSOR
 	select ACPI_CPPC_LIB if X86_64

drivers/cpufreq/Kconfig.x86

@@ -36,6 +36,7 @@
 #include <linux/delay.h>
 #include <linux/uaccess.h>
 #include <linux/static_call.h>
+#include <linux/amd-pstate.h>
 
 #include <acpi/processor.h>
 #include <acpi/cppc_acpi.h>
@@ -46,8 +47,8 @@
 #include <asm/cpu_device_id.h>
 #include "amd-pstate-trace.h"
 
-#define AMD_PSTATE_TRANSITION_LATENCY	0x20000
-#define AMD_PSTATE_TRANSITION_DELAY	500
+#define AMD_PSTATE_TRANSITION_LATENCY	20000
+#define AMD_PSTATE_TRANSITION_DELAY	1000
 
 /*
  * TODO: We need more time to fine tune processors with shared memory solution
@@ -58,71 +59,8 @@
  * we disable it by default to go acpi-cpufreq on these processors and add a
  * module parameter to be able to enable it manually for debugging.
  */
-static bool shared_mem = false;
-module_param(shared_mem, bool, 0444);
-MODULE_PARM_DESC(shared_mem,
-		 "enable amd-pstate on processors with shared memory solution (false = disabled (default), true = enabled)");
-
 static struct cpufreq_driver amd_pstate_driver;
-
-/**
- * struct  amd_aperf_mperf
- * @aperf: actual performance frequency clock count
- * @mperf: maximum performance frequency clock count
- * @tsc:   time stamp counter
- */
-struct amd_aperf_mperf {
-	u64 aperf;
-	u64 mperf;
-	u64 tsc;
-};
-
-/**
- * struct amd_cpudata - private CPU data for AMD P-State
- * @cpu: CPU number
- * @req: constraint request to apply
- * @cppc_req_cached: cached performance request hints
- * @highest_perf: the maximum performance an individual processor may reach,
- *		  assuming ideal conditions
- * @nominal_perf: the maximum sustained performance level of the processor,
- *		  assuming ideal operating conditions
- * @lowest_nonlinear_perf: the lowest performance level at which nonlinear power
- *			   savings are achieved
- * @lowest_perf: the absolute lowest performance level of the processor
- * @max_freq: the frequency that mapped to highest_perf
- * @min_freq: the frequency that mapped to lowest_perf
- * @nominal_freq: the frequency that mapped to nominal_perf
- * @lowest_nonlinear_freq: the frequency that mapped to lowest_nonlinear_perf
- * @cur: Difference of Aperf/Mperf/tsc count between last and current sample
- * @prev: Last Aperf/Mperf/tsc count value read from register
- * @freq: current cpu frequency value
- * @boost_supported: check whether the Processor or SBIOS supports boost mode
- *
- * The amd_cpudata is key private data for each CPU thread in AMD P-State, and
- * represents all the attributes and goals that AMD P-State requests at runtime.
- */
-struct amd_cpudata {
-	int	cpu;
-
-	struct	freq_qos_request req[2];
-	u64	cppc_req_cached;
-
-	u32	highest_perf;
-	u32	nominal_perf;
-	u32	lowest_nonlinear_perf;
-	u32	lowest_perf;
-
-	u32	max_freq;
-	u32	min_freq;
-	u32	nominal_freq;
-	u32	lowest_nonlinear_freq;
-
-	struct amd_aperf_mperf cur;
-	struct amd_aperf_mperf prev;
-
-	u64 freq;
-	bool	boost_supported;
-};
+static int cppc_load __initdata;
 
 static inline int pstate_enable(bool enable)
 {
@@ -152,6 +90,7 @@ static inline int amd_pstate_enable(bool enable)
 static int pstate_init_perf(struct amd_cpudata *cpudata)
 {
 	u64 cap1;
+	u32 highest_perf;
 
 	int ret = rdmsrl_safe_on_cpu(cpudata->cpu, MSR_AMD_CPPC_CAP1,
 				     &cap1);
@@ -163,7 +102,11 @@ static int pstate_init_perf(struct amd_cpudata *cpudata)
 	 *
 	 * CPPC entry doesn't indicate the highest performance in some ASICs.
 	 */
-	WRITE_ONCE(cpudata->highest_perf, amd_get_highest_perf());
+	highest_perf = amd_get_highest_perf();
+	if (highest_perf > AMD_CPPC_HIGHEST_PERF(cap1))
+		highest_perf = AMD_CPPC_HIGHEST_PERF(cap1);
+
+	WRITE_ONCE(cpudata->highest_perf, highest_perf);
 
 	WRITE_ONCE(cpudata->nominal_perf, AMD_CPPC_NOMINAL_PERF(cap1));
 	WRITE_ONCE(cpudata->lowest_nonlinear_perf, AMD_CPPC_LOWNONLIN_PERF(cap1));
@@ -175,12 +118,17 @@ static int pstate_init_perf(struct amd_cpudata *cpudata)
 static int cppc_init_perf(struct amd_cpudata *cpudata)
 {
 	struct cppc_perf_caps cppc_perf;
+	u32 highest_perf;
 
 	int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf);
 	if (ret)
 		return ret;
 
-	WRITE_ONCE(cpudata->highest_perf, amd_get_highest_perf());
+	highest_perf = amd_get_highest_perf();
+	if (highest_perf > cppc_perf.highest_perf)
+		highest_perf = cppc_perf.highest_perf;
+
+	WRITE_ONCE(cpudata->highest_perf, highest_perf);
 
 	WRITE_ONCE(cpudata->nominal_perf, cppc_perf.nominal_perf);
 	WRITE_ONCE(cpudata->lowest_nonlinear_perf,
@@ -269,6 +217,7 @@ static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf,
 	u64 prev = READ_ONCE(cpudata->cppc_req_cached);
 	u64 value = prev;
 
+	des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf);
 	value &= ~AMD_CPPC_MIN_PERF(~0L);
 	value |= AMD_CPPC_MIN_PERF(min_perf);
 
@@ -312,7 +261,7 @@ static int amd_pstate_target(struct cpufreq_policy *policy,
 		return -ENODEV;
 
 	cap_perf = READ_ONCE(cpudata->highest_perf);
-	min_perf = READ_ONCE(cpudata->lowest_nonlinear_perf);
+	min_perf = READ_ONCE(cpudata->lowest_perf);
 	max_perf = cap_perf;
 
 	freqs.old = policy->cur;
@@ -357,8 +306,6 @@ static void amd_pstate_adjust_perf(unsigned int cpu,
 	if (max_perf < min_perf)
 		max_perf = min_perf;
 
-	des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf);
-
 	amd_pstate_update(cpudata, min_perf, des_perf, max_perf, true);
 }
 
@@ -473,12 +420,22 @@ static void amd_pstate_boost_init(struct amd_cpudata *cpudata)
 	amd_pstate_driver.boost_enabled = true;
 }
 
+static void amd_perf_ctl_reset(unsigned int cpu)
+{
+	wrmsrl_on_cpu(cpu, MSR_AMD_PERF_CTL, 0);
+}
+
 static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
 {
 	int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret;
 	struct device *dev;
 	struct amd_cpudata *cpudata;
 
+	/*
+	 * Resetting PERF_CTL_MSR will put the CPU in P0 frequency,
+	 * which is ideal for initialization process.
+	 */
+	amd_perf_ctl_reset(policy->cpu);
 	dev = get_cpu_device(policy->cpu);
 	if (!dev)
 		return -ENODEV;
@@ -555,9 +512,7 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
 
 static int amd_pstate_cpu_exit(struct cpufreq_policy *policy)
 {
-	struct amd_cpudata *cpudata;
-
-	cpudata = policy->driver_data;
+	struct amd_cpudata *cpudata = policy->driver_data;
 
 	freq_qos_remove_request(&cpudata->req[1]);
 	freq_qos_remove_request(&cpudata->req[0]);
@@ -566,6 +521,28 @@ static int amd_pstate_cpu_exit(struct cpufreq_policy *policy)
 	return 0;
 }
 
+static int amd_pstate_cpu_resume(struct cpufreq_policy *policy)
+{
+	int ret;
+
+	ret = amd_pstate_enable(true);
+	if (ret)
+		pr_err("failed to enable amd-pstate during resume, return %d\n", ret);
+
+	return ret;
+}
+
+static int amd_pstate_cpu_suspend(struct cpufreq_policy *policy)
+{
+	int ret;
+
+	ret = amd_pstate_enable(false);
+	if (ret)
+		pr_err("failed to disable amd-pstate during suspend, return %d\n", ret);
+
+	return ret;
+}
+
 /* Sysfs attributes */
 
 /*
@@ -577,9 +554,7 @@ static ssize_t show_amd_pstate_max_freq(struct cpufreq_policy *policy,
 					char *buf)
 {
 	int max_freq;
-	struct amd_cpudata *cpudata;
-
-	cpudata = policy->driver_data;
+	struct amd_cpudata *cpudata = policy->driver_data;
 
 	max_freq = amd_get_max_freq(cpudata);
 	if (max_freq < 0)
@@ -592,9 +567,7 @@ static ssize_t show_amd_pstate_lowest_nonlinear_freq(struct cpufreq_policy *poli
 						     char *buf)
 {
 	int freq;
-	struct amd_cpudata *cpudata;
-
-	cpudata = policy->driver_data;
+	struct amd_cpudata *cpudata = policy->driver_data;
 
 	freq = amd_get_lowest_nonlinear_freq(cpudata);
 	if (freq < 0)
@@ -636,9 +609,11 @@ static struct cpufreq_driver amd_pstate_driver = {
 	.target		= amd_pstate_target,
 	.init		= amd_pstate_cpu_init,
 	.exit		= amd_pstate_cpu_exit,
+	.suspend	= amd_pstate_cpu_suspend,
+	.resume		= amd_pstate_cpu_resume,
 	.set_boost	= amd_pstate_set_boost,
 	.name		= "amd-pstate",
-	.attr           = amd_pstate_attr,
+	.attr		= amd_pstate_attr,
 };
 
 static int __init amd_pstate_init(void)
@@ -647,9 +622,18 @@ static int __init amd_pstate_init(void)
 
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
 		return -ENODEV;
+	/*
+	 * by default the pstate driver is disabled to load
+	 * enable the amd_pstate passive mode driver explicitly
+	 * with amd_pstate=passive in kernel command line
+	 */
+	if (!cppc_load) {
+		pr_debug("driver load is disabled, boot with amd_pstate=passive to enable this\n");
+		return -ENODEV;
+	}
 
 	if (!acpi_cpc_valid()) {
-		pr_debug("the _CPC object is not present in SBIOS\n");
+		pr_warn_once("the _CPC object is not present in SBIOS or ACPI disabled\n");
 		return -ENODEV;
 	}
 
@@ -661,13 +645,11 @@ static int __init amd_pstate_init(void)
 	if (boot_cpu_has(X86_FEATURE_CPPC)) {
 		pr_debug("AMD CPPC MSR based functionality is supported\n");
 		amd_pstate_driver.adjust_perf = amd_pstate_adjust_perf;
-	} else if (shared_mem) {
+	} 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);
-	} else {
-		pr_info("This processor supports shared memory solution, you can enable it with amd_pstate.shared_mem=1\n");
-		return -ENODEV;
 	}
 
 	/* enable amd pstate feature */
@@ -684,16 +666,22 @@ static int __init amd_pstate_init(void)
 
 	return ret;
 }
+device_initcall(amd_pstate_init);
 
-static void __exit amd_pstate_exit(void)
+static int __init amd_pstate_param(char *str)
 {
-	cpufreq_unregister_driver(&amd_pstate_driver);
+	if (!str)
+		return -EINVAL;
 
-	amd_pstate_enable(false);
-}
+	if (!strcmp(str, "disable")) {
+		cppc_load = 0;
+		pr_info("driver is explicitly disabled\n");
+	} else if (!strcmp(str, "passive"))
+		cppc_load = 1;
 
-module_init(amd_pstate_init);
-module_exit(amd_pstate_exit);
+	return 0;
+}
+early_param("amd_pstate", amd_pstate_param);
 
 MODULE_AUTHOR("Huang Rui <ray.huang@amd.com>");
 MODULE_DESCRIPTION("AMD Processor P-state Frequency Driver");

drivers/cpufreq/amd-pstate.c

@@ -761,7 +761,7 @@ static int __init cppc_cpufreq_init(void)
 {
 	int ret;
 
-	if ((acpi_disabled) || !acpi_cpc_valid())
+	if (!acpi_cpc_valid())
 		return -ENODEV;
 
 	cppc_check_hisi_workaround();