1 files changed, 174 insertions, 106 deletions

diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 2015c9fcc3c9..6a342b0c0140 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -50,7 +50,8 @@
 
 #define AMD_PSTATE_TRANSITION_LATENCY	20000
 #define AMD_PSTATE_TRANSITION_DELAY	1000
-#define AMD_PSTATE_PREFCORE_THRESHOLD	166
+#define CPPC_HIGHEST_PERF_PERFORMANCE	196
+#define CPPC_HIGHEST_PERF_DEFAULT	166
 
 /*
  * TODO: We need more time to fine tune processors with shared memory solution
@@ -67,6 +68,7 @@ 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)
@@ -111,6 +113,41 @@ 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;
@@ -290,6 +327,21 @@ static inline int amd_pstate_enable(bool enable)
 	return static_call(amd_pstate_enable)(enable);
 }
 
+static u32 amd_pstate_highest_perf_set(struct amd_cpudata *cpudata)
+{
+	struct cpuinfo_x86 *c = &cpu_data(0);
+
+	/*
+	 * For AMD CPUs with Family ID 19H and Model ID range 0x70 to 0x7f,
+	 * the highest performance level is set to 196.
+	 * https://bugzilla.kernel.org/show_bug.cgi?id=218759
+	 */
+	if (c->x86 == 0x19 && (c->x86_model >= 0x70 && c->x86_model <= 0x7f))
+		return CPPC_HIGHEST_PERF_PERFORMANCE;
+
+	return CPPC_HIGHEST_PERF_DEFAULT;
+}
+
 static int pstate_init_perf(struct amd_cpudata *cpudata)
 {
 	u64 cap1;
@@ -306,7 +358,7 @@ static int pstate_init_perf(struct amd_cpudata *cpudata)
 	 * the default max perf.
 	 */
 	if (cpudata->hw_prefcore)
-		highest_perf = AMD_PSTATE_PREFCORE_THRESHOLD;
+		highest_perf = amd_pstate_highest_perf_set(cpudata);
 	else
 		highest_perf = AMD_CPPC_HIGHEST_PERF(cap1);
 
@@ -330,7 +382,7 @@ static int cppc_init_perf(struct amd_cpudata *cpudata)
 		return ret;
 
 	if (cpudata->hw_prefcore)
-		highest_perf = AMD_PSTATE_PREFCORE_THRESHOLD;
+		highest_perf = amd_pstate_highest_perf_set(cpudata);
 	else
 		highest_perf = cppc_perf.highest_perf;
 
@@ -604,78 +656,6 @@ static void amd_pstate_adjust_perf(unsigned int cpu,
 	cpufreq_cpu_put(policy);
 }
 
-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;
-}
-
-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;
-}
-
-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;
-}
-
-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;
-}
-
 static int amd_pstate_set_boost(struct cpufreq_policy *policy, int state)
 {
 	struct amd_cpudata *cpudata = policy->driver_data;
@@ -828,9 +808,93 @@ free_cpufreq_put:
 	mutex_unlock(&amd_pstate_driver_lock);
 }
 
+/*
+ * Get pstate transition delay time from ACPI tables that firmware set
+ * instead of using hardcode value directly.
+ */
+static u32 amd_pstate_get_transition_delay_us(unsigned int cpu)
+{
+	u32 transition_delay_ns;
+
+	transition_delay_ns = cppc_get_transition_latency(cpu);
+	if (transition_delay_ns == CPUFREQ_ETERNAL)
+		return AMD_PSTATE_TRANSITION_DELAY;
+
+	return transition_delay_ns / NSEC_PER_USEC;
+}
+
+/*
+ * Get pstate transition latency value from ACPI tables that firmware
+ * set instead of using hardcode value directly.
+ */
+static u32 amd_pstate_get_transition_latency(unsigned int cpu)
+{
+	u32 transition_latency;
+
+	transition_latency = cppc_get_transition_latency(cpu);
+	if (transition_latency  == CPUFREQ_ETERNAL)
+		return AMD_PSTATE_TRANSITION_LATENCY;
+
+	return transition_latency;
+}
+
+/*
+ * 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;
+	int min_freq, max_freq, nominal_freq, ret;
 	struct device *dev;
 	struct amd_cpudata *cpudata;
 
@@ -855,20 +919,25 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
 	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);
-	lowest_nonlinear_freq = amd_get_lowest_nonlinear_freq(cpudata);
+	ret = amd_pstate_init_freq(cpudata);
+	if (ret)
+		goto free_cpudata1;
+
+	min_freq = READ_ONCE(cpudata->min_freq);
+	max_freq = READ_ONCE(cpudata->max_freq);
+	nominal_freq = READ_ONCE(cpudata->nominal_freq);
 
-	if (min_freq < 0 || max_freq < 0 || min_freq > max_freq) {
-		dev_err(dev, "min_freq(%d) or max_freq(%d) value is incorrect\n",
-			min_freq, max_freq);
+	if (min_freq <= 0 || max_freq <= 0 ||
+	    nominal_freq <= 0 || min_freq > max_freq) {
+		dev_err(dev,
+			"min_freq(%d) or max_freq(%d) or nominal_freq (%d) value is incorrect, check _CPC in ACPI tables\n",
+			min_freq, max_freq, nominal_freq);
 		ret = -EINVAL;
 		goto free_cpudata1;
 	}
 
-	policy->cpuinfo.transition_latency = AMD_PSTATE_TRANSITION_LATENCY;
-	policy->transition_delay_us = AMD_PSTATE_TRANSITION_DELAY;
+	policy->cpuinfo.transition_latency = amd_pstate_get_transition_latency(policy->cpu);
+	policy->transition_delay_us = amd_pstate_get_transition_delay_us(policy->cpu);
 
 	policy->min = min_freq;
 	policy->max = max_freq;
@@ -896,13 +965,8 @@ 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;
 
@@ -966,7 +1030,7 @@ static ssize_t show_amd_pstate_max_freq(struct cpufreq_policy *policy,
 	int max_freq;
 	struct amd_cpudata *cpudata = policy->driver_data;
 
-	max_freq = amd_get_max_freq(cpudata);
+	max_freq = READ_ONCE(cpudata->max_freq);
 	if (max_freq < 0)
 		return max_freq;
 
@@ -979,7 +1043,7 @@ static ssize_t show_amd_pstate_lowest_nonlinear_freq(struct cpufreq_policy *poli
 	int freq;
 	struct amd_cpudata *cpudata = policy->driver_data;
 
-	freq = amd_get_lowest_nonlinear_freq(cpudata);
+	freq = READ_ONCE(cpudata->lowest_nonlinear_freq);
 	if (freq < 0)
 		return freq;
 
@@ -1290,7 +1354,7 @@ static bool amd_pstate_acpi_pm_profile_undefined(void)
 
 static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 {
-	int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret;
+	int min_freq, max_freq, nominal_freq, ret;
 	struct amd_cpudata *cpudata;
 	struct device *dev;
 	u64 value;
@@ -1317,13 +1381,18 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 	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);
-	lowest_nonlinear_freq = amd_get_lowest_nonlinear_freq(cpudata);
-	if (min_freq < 0 || max_freq < 0 || min_freq > max_freq) {
-		dev_err(dev, "min_freq(%d) or max_freq(%d) value is incorrect\n",
-				min_freq, max_freq);
+	ret = amd_pstate_init_freq(cpudata);
+	if (ret)
+		goto free_cpudata1;
+
+	min_freq = READ_ONCE(cpudata->min_freq);
+	max_freq = READ_ONCE(cpudata->max_freq);
+	nominal_freq = READ_ONCE(cpudata->nominal_freq);
+	if (min_freq <= 0 || max_freq <= 0 ||
+	    nominal_freq <= 0 || min_freq > max_freq) {
+		dev_err(dev,
+			"min_freq(%d) or max_freq(%d) or nominal_freq(%d) value is incorrect, check _CPC in ACPI tables\n",
+			min_freq, max_freq, nominal_freq);
 		ret = -EINVAL;
 		goto free_cpudata1;
 	}
@@ -1333,12 +1402,6 @@ 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);
@@ -1656,6 +1719,11 @@ 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: