Adding upstream version 6.9.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

6 files changed, 274 insertions, 77 deletions

diff --git a/drivers/cpufreq/amd-pstate-ut.c b/drivers/cpufreq/amd-pstate-ut.c
index f04ae67dda..fc275d41d5 100644
--- a/drivers/cpufreq/amd-pstate-ut.c
+++ b/drivers/cpufreq/amd-pstate-ut.c
@@ -26,10 +26,11 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/fs.h>
-#include <linux/amd-pstate.h>
 
 #include <acpi/cppc_acpi.h>
 
+#include "amd-pstate.h"
+
 /*
  * Abbreviations:
  * amd_pstate_ut: used as a shortform for AMD P-State unit test.
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 28166df81c..6af175e6c0 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -36,7 +36,6 @@
 #include <linux/delay.h>
 #include <linux/uaccess.h>
 #include <linux/static_call.h>
-#include <linux/amd-pstate.h>
 #include <linux/topology.h>
 
 #include <acpi/processor.h>
@@ -46,6 +45,8 @@
 #include <asm/processor.h>
 #include <asm/cpufeature.h>
 #include <asm/cpu_device_id.h>
+
+#include "amd-pstate.h"
 #include "amd-pstate-trace.h"
 
 #define AMD_PSTATE_TRANSITION_LATENCY	20000
@@ -53,6 +54,37 @@
 #define CPPC_HIGHEST_PERF_PERFORMANCE	196
 #define CPPC_HIGHEST_PERF_DEFAULT	166
 
+#define AMD_CPPC_EPP_PERFORMANCE		0x00
+#define AMD_CPPC_EPP_BALANCE_PERFORMANCE	0x80
+#define AMD_CPPC_EPP_BALANCE_POWERSAVE		0xBF
+#define AMD_CPPC_EPP_POWERSAVE			0xFF
+
+/*
+ * enum amd_pstate_mode - driver working mode of amd pstate
+ */
+enum amd_pstate_mode {
+	AMD_PSTATE_UNDEFINED = 0,
+	AMD_PSTATE_DISABLE,
+	AMD_PSTATE_PASSIVE,
+	AMD_PSTATE_ACTIVE,
+	AMD_PSTATE_GUIDED,
+	AMD_PSTATE_MAX,
+};
+
+static const char * const amd_pstate_mode_string[] = {
+	[AMD_PSTATE_UNDEFINED]   = "undefined",
+	[AMD_PSTATE_DISABLE]     = "disable",
+	[AMD_PSTATE_PASSIVE]     = "passive",
+	[AMD_PSTATE_ACTIVE]      = "active",
+	[AMD_PSTATE_GUIDED]      = "guided",
+	NULL,
+};
+
+struct quirk_entry {
+	u32 nominal_freq;
+	u32 lowest_freq;
+};
+
 /*
  * TODO: We need more time to fine tune processors with shared memory solution
  * with community together.
@@ -68,6 +100,7 @@ static struct cpufreq_driver amd_pstate_epp_driver;
 static int cppc_state = AMD_PSTATE_UNDEFINED;
 static bool cppc_enabled;
 static bool amd_pstate_prefcore = true;
+static struct quirk_entry *quirks;
 
 /*
  * AMD Energy Preference Performance (EPP)
@@ -112,6 +145,41 @@ static unsigned int epp_values[] = {
 
 typedef int (*cppc_mode_transition_fn)(int);
 
+static struct quirk_entry quirk_amd_7k62 = {
+	.nominal_freq = 2600,
+	.lowest_freq = 550,
+};
+
+static int __init dmi_matched_7k62_bios_bug(const struct dmi_system_id *dmi)
+{
+	/**
+	 * match the broken bios for family 17h processor support CPPC V2
+	 * broken BIOS lack of nominal_freq and lowest_freq capabilities
+	 * definition in ACPI tables
+	 */
+	if (boot_cpu_has(X86_FEATURE_ZEN2)) {
+		quirks = dmi->driver_data;
+		pr_info("Overriding nominal and lowest frequencies for %s\n", dmi->ident);
+		return 1;
+	}
+
+	return 0;
+}
+
+static const struct dmi_system_id amd_pstate_quirks_table[] __initconst = {
+	{
+		.callback = dmi_matched_7k62_bios_bug,
+		.ident = "AMD EPYC 7K62",
+		.matches = {
+			DMI_MATCH(DMI_BIOS_VERSION, "5.14"),
+			DMI_MATCH(DMI_BIOS_RELEASE, "12/12/2019"),
+		},
+		.driver_data = &quirk_amd_7k62,
+	},
+	{}
+};
+MODULE_DEVICE_TABLE(dmi, amd_pstate_quirks_table);
+
 static inline int get_mode_idx_from_str(const char *str, size_t size)
 {
 	int i;
@@ -622,74 +690,22 @@ static void amd_pstate_adjust_perf(unsigned int cpu,
 
 static int amd_get_min_freq(struct amd_cpudata *cpudata)
 {
-	struct cppc_perf_caps cppc_perf;
-
-	int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf);
-	if (ret)
-		return ret;
-
-	/* Switch to khz */
-	return cppc_perf.lowest_freq * 1000;
+	return READ_ONCE(cpudata->min_freq);
 }
 
 static int amd_get_max_freq(struct amd_cpudata *cpudata)
 {
-	struct cppc_perf_caps cppc_perf;
-	u32 max_perf, max_freq, nominal_freq, nominal_perf;
-	u64 boost_ratio;
-
-	int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf);
-	if (ret)
-		return ret;
-
-	nominal_freq = cppc_perf.nominal_freq;
-	nominal_perf = READ_ONCE(cpudata->nominal_perf);
-	max_perf = READ_ONCE(cpudata->highest_perf);
-
-	boost_ratio = div_u64(max_perf << SCHED_CAPACITY_SHIFT,
-			      nominal_perf);
-
-	max_freq = nominal_freq * boost_ratio >> SCHED_CAPACITY_SHIFT;
-
-	/* Switch to khz */
-	return max_freq * 1000;
+	return READ_ONCE(cpudata->max_freq);
 }
 
 static int amd_get_nominal_freq(struct amd_cpudata *cpudata)
 {
-	struct cppc_perf_caps cppc_perf;
-
-	int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf);
-	if (ret)
-		return ret;
-
-	/* Switch to khz */
-	return cppc_perf.nominal_freq * 1000;
+	return READ_ONCE(cpudata->nominal_freq);
 }
 
 static int amd_get_lowest_nonlinear_freq(struct amd_cpudata *cpudata)
 {
-	struct cppc_perf_caps cppc_perf;
-	u32 lowest_nonlinear_freq, lowest_nonlinear_perf,
-	    nominal_freq, nominal_perf;
-	u64 lowest_nonlinear_ratio;
-
-	int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf);
-	if (ret)
-		return ret;
-
-	nominal_freq = cppc_perf.nominal_freq;
-	nominal_perf = READ_ONCE(cpudata->nominal_perf);
-
-	lowest_nonlinear_perf = cppc_perf.lowest_nonlinear_perf;
-
-	lowest_nonlinear_ratio = div_u64(lowest_nonlinear_perf << SCHED_CAPACITY_SHIFT,
-					 nominal_perf);
-
-	lowest_nonlinear_freq = nominal_freq * lowest_nonlinear_ratio >> SCHED_CAPACITY_SHIFT;
-
-	/* Switch to khz */
-	return lowest_nonlinear_freq * 1000;
+	return READ_ONCE(cpudata->lowest_nonlinear_freq);
 }
 
 static int amd_pstate_set_boost(struct cpufreq_policy *policy, int state)
@@ -705,7 +721,7 @@ static int amd_pstate_set_boost(struct cpufreq_policy *policy, int state)
 	if (state)
 		policy->cpuinfo.max_freq = cpudata->max_freq;
 	else
-		policy->cpuinfo.max_freq = cpudata->nominal_freq;
+		policy->cpuinfo.max_freq = cpudata->nominal_freq * 1000;
 
 	policy->max = policy->cpuinfo.max_freq;
 
@@ -844,6 +860,61 @@ free_cpufreq_put:
 	mutex_unlock(&amd_pstate_driver_lock);
 }
 
+/**
+ * amd_pstate_init_freq: Initialize the max_freq, min_freq,
+ *                       nominal_freq and lowest_nonlinear_freq for
+ *                       the @cpudata object.
+ *
+ *  Requires: highest_perf, lowest_perf, nominal_perf and
+ *            lowest_nonlinear_perf members of @cpudata to be
+ *            initialized.
+ *
+ *  Returns 0 on success, non-zero value on failure.
+ */
+static int amd_pstate_init_freq(struct amd_cpudata *cpudata)
+{
+	int ret;
+	u32 min_freq;
+	u32 highest_perf, max_freq;
+	u32 nominal_perf, nominal_freq;
+	u32 lowest_nonlinear_perf, lowest_nonlinear_freq;
+	u32 boost_ratio, lowest_nonlinear_ratio;
+	struct cppc_perf_caps cppc_perf;
+
+
+	ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf);
+	if (ret)
+		return ret;
+
+	if (quirks && quirks->lowest_freq)
+		min_freq = quirks->lowest_freq * 1000;
+	else
+		min_freq = cppc_perf.lowest_freq * 1000;
+
+	if (quirks && quirks->nominal_freq)
+		nominal_freq = quirks->nominal_freq ;
+	else
+		nominal_freq = cppc_perf.nominal_freq;
+
+	nominal_perf = READ_ONCE(cpudata->nominal_perf);
+
+	highest_perf = READ_ONCE(cpudata->highest_perf);
+	boost_ratio = div_u64(highest_perf << SCHED_CAPACITY_SHIFT, nominal_perf);
+	max_freq = (nominal_freq * boost_ratio >> SCHED_CAPACITY_SHIFT) * 1000;
+
+	lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf);
+	lowest_nonlinear_ratio = div_u64(lowest_nonlinear_perf << SCHED_CAPACITY_SHIFT,
+					 nominal_perf);
+	lowest_nonlinear_freq = (nominal_freq * lowest_nonlinear_ratio >> SCHED_CAPACITY_SHIFT) * 1000;
+
+	WRITE_ONCE(cpudata->min_freq, min_freq);
+	WRITE_ONCE(cpudata->lowest_nonlinear_freq, lowest_nonlinear_freq);
+	WRITE_ONCE(cpudata->nominal_freq, nominal_freq);
+	WRITE_ONCE(cpudata->max_freq, max_freq);
+
+	return 0;
+}
+
 static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
 {
 	int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret;
@@ -871,6 +942,10 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
 	if (ret)
 		goto free_cpudata1;
 
+	ret = amd_pstate_init_freq(cpudata);
+	if (ret)
+		goto free_cpudata1;
+
 	min_freq = amd_get_min_freq(cpudata);
 	max_freq = amd_get_max_freq(cpudata);
 	nominal_freq = amd_get_nominal_freq(cpudata);
@@ -912,13 +987,8 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
 		goto free_cpudata2;
 	}
 
-	/* Initial processor data capability frequencies */
-	cpudata->max_freq = max_freq;
-	cpudata->min_freq = min_freq;
 	cpudata->max_limit_freq = max_freq;
 	cpudata->min_limit_freq = min_freq;
-	cpudata->nominal_freq = nominal_freq;
-	cpudata->lowest_nonlinear_freq = lowest_nonlinear_freq;
 
 	policy->driver_data = cpudata;
 
@@ -1333,6 +1403,10 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 	if (ret)
 		goto free_cpudata1;
 
+	ret = amd_pstate_init_freq(cpudata);
+	if (ret)
+		goto free_cpudata1;
+
 	min_freq = amd_get_min_freq(cpudata);
 	max_freq = amd_get_max_freq(cpudata);
 	nominal_freq = amd_get_nominal_freq(cpudata);
@@ -1349,12 +1423,6 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 	/* It will be updated by governor */
 	policy->cur = policy->cpuinfo.min_freq;
 
-	/* Initial processor data capability frequencies */
-	cpudata->max_freq = max_freq;
-	cpudata->min_freq = min_freq;
-	cpudata->nominal_freq = nominal_freq;
-	cpudata->lowest_nonlinear_freq = lowest_nonlinear_freq;
-
 	policy->driver_data = cpudata;
 
 	cpudata->epp_cached = amd_pstate_get_epp(cpudata, 0);
@@ -1394,6 +1462,13 @@ free_cpudata1:
 
 static int amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy)
 {
+	struct amd_cpudata *cpudata = policy->driver_data;
+
+	if (cpudata) {
+		kfree(cpudata);
+		policy->driver_data = NULL;
+	}
+
 	pr_debug("CPU %d exiting\n", policy->cpu);
 	return 0;
 }
@@ -1672,6 +1747,11 @@ static int __init amd_pstate_init(void)
 	if (cpufreq_get_current_driver())
 		return -EEXIST;
 
+	quirks = NULL;
+
+	/* check if this machine need CPPC quirks */
+	dmi_check_system(amd_pstate_quirks_table);
+
 	switch (cppc_state) {
 	case AMD_PSTATE_UNDEFINED:
 		/* Disable on the following configs by default:
diff --git a/drivers/cpufreq/amd-pstate.h b/drivers/cpufreq/amd-pstate.h
new file mode 100644
index 0000000000..bc341f3590
--- /dev/null
+++ b/drivers/cpufreq/amd-pstate.h
@@ -0,0 +1,100 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2022 Advanced Micro Devices, Inc.
+ *
+ * Author: Meng Li <li.meng@amd.com>
+ */
+
+#ifndef _LINUX_AMD_PSTATE_H
+#define _LINUX_AMD_PSTATE_H
+
+#include <linux/pm_qos.h>
+
+/*********************************************************************
+ *                        AMD P-state INTERFACE                       *
+ *********************************************************************/
+/**
+ * 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
+ *		  For platforms that do not support the preferred core feature, the
+ *		  highest_pef may be configured with 166 or 255, to avoid max frequency
+ *		  calculated wrongly. we take the fixed value as the highest_perf.
+ * @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
+ * @prefcore_ranking: the preferred core ranking, the higher value indicates a higher
+ * 		  priority.
+ * @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
+ * @hw_prefcore: check whether HW supports preferred core featue.
+ * 		  Only when hw_prefcore and early prefcore param are true,
+ * 		  AMD P-State driver supports preferred core featue.
+ * @epp_policy: Last saved policy used to set energy-performance preference
+ * @epp_cached: Cached CPPC energy-performance preference value
+ * @policy: Cpufreq policy value
+ * @cppc_cap1_cached Cached MSR_AMD_CPPC_CAP1 register value
+ *
+ * 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     prefcore_ranking;
+	u32     min_limit_perf;
+	u32     max_limit_perf;
+	u32     min_limit_freq;
+	u32     max_limit_freq;
+
+	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;
+	bool	hw_prefcore;
+
+	/* EPP feature related attributes*/
+	s16	epp_policy;
+	s16	epp_cached;
+	u32	policy;
+	u64	cppc_cap1_cached;
+	bool	suspended;
+};
+
+#endif /* _LINUX_AMD_PSTATE_H */
diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c
index 1a1857b0a6..ea8438550b 100644
--- a/drivers/cpufreq/brcmstb-avs-cpufreq.c
+++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c
@@ -481,9 +481,12 @@ static bool brcm_avs_is_firmware_loaded(struct private_data *priv)
 static unsigned int brcm_avs_cpufreq_get(unsigned int cpu)
 {
 	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+	struct private_data *priv;
+
 	if (!policy)
 		return 0;
-	struct private_data *priv = policy->driver_data;
+
+	priv = policy->driver_data;
 
 	cpufreq_cpu_put(policy);
 
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index 64420d9cfd..15f1d41920 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -741,10 +741,15 @@ static unsigned int cppc_cpufreq_get_rate(unsigned int cpu)
 {
 	struct cppc_perf_fb_ctrs fb_ctrs_t0 = {0}, fb_ctrs_t1 = {0};
 	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
-	struct cppc_cpudata *cpu_data = policy->driver_data;
+	struct cppc_cpudata *cpu_data;
 	u64 delivered_perf;
 	int ret;
 
+	if (!policy)
+		return -ENODEV;
+
+	cpu_data = policy->driver_data;
+
 	cpufreq_cpu_put(policy);
 
 	ret = cppc_get_perf_ctrs(cpu, &fb_ctrs_t0);
@@ -822,10 +827,15 @@ static struct cpufreq_driver cppc_cpufreq_driver = {
 static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpu)
 {
 	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
-	struct cppc_cpudata *cpu_data = policy->driver_data;
+	struct cppc_cpudata *cpu_data;
 	u64 desired_perf;
 	int ret;
 
+	if (!policy)
+		return -ENODEV;
+
+	cpu_data = policy->driver_data;
+
 	cpufreq_cpu_put(policy);
 
 	ret = cppc_get_desired_perf(cpu, &desired_perf);
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 66e10a19d7..fd9c3ed21f 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1679,10 +1679,13 @@ static void __cpufreq_offline(unsigned int cpu, struct cpufreq_policy *policy)
 	 */
 	if (cpufreq_driver->offline) {
 		cpufreq_driver->offline(policy);
-	} else if (cpufreq_driver->exit) {
-		cpufreq_driver->exit(policy);
-		policy->freq_table = NULL;
+		return;
 	}
+
+	if (cpufreq_driver->exit)
+		cpufreq_driver->exit(policy);
+
+	policy->freq_table = NULL;
 }
 
 static int cpufreq_offline(unsigned int cpu)
@@ -1740,7 +1743,7 @@ static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
 	}
 
 	/* We did light-weight exit earlier, do full tear down now */
-	if (cpufreq_driver->offline)
+	if (cpufreq_driver->offline && cpufreq_driver->exit)
 		cpufreq_driver->exit(policy);
 
 	up_write(&policy->rwsem);