Merge branch 'amd-pstate'

Merge AMD P-state driver changes from Perry Yuan for v6.10:

"- Enable CPPC v2 for certain processors in the family 17H, as requested
by TR40 processor users who expect improved performance and lower
system temperature.

- Change latency and delay values to be read from platform firmware
firstly for more accurate timing.

- A new quirk is introduced for supporting amd-pstate on legacy
processors which either lack CPPC capability, or only only have CPPC
v2 capability."

* amd-pstate:
MAINTAINERS: cpufreq: amd-pstate: Add co-maintainers and reviewer
cpufreq: amd-pstate: remove unused variable lowest_nonlinear_freq
cpufreq: amd-pstate: fix code format problems
cpufreq: amd-pstate: Add quirk for the pstate CPPC capabilities missing
cppc_acpi: print error message if CPPC is unsupported
cpufreq: amd-pstate: get transition delay and latency value from ACPI tables
cpufreq: amd-pstate: Bail out if min/max/nominal_freq is 0
cpufreq: amd-pstate: Remove amd_get_{min,max,nominal,lowest_nonlinear}_freq()
cpufreq: amd-pstate: Unify computation of {max,min,nominal,lowest_nonlinear}_freq
cpufreq: amd-pstate: Document the units for freq variables in amd_cpudata
cpufreq: amd-pstate: Document *_limit_* fields in struct amd_cpudata

MAINTAINERS

···
 
 AMD PSTATE DRIVER
 M:	Huang Rui <[e-mail]>
+M:	Gautham R. Shenoy <[e-mail]>
+M:	Mario Limonciello <[e-mail]>
+R:	Perry Yuan <[e-mail]>
 L:	[e-mail]
 S:	Supported
 F:	Documentation/admin-guide/pm/amd-pstate.rst

drivers/acpi/cppc_acpi.c

···
 
 	if (!osc_sb_cppc2_support_acked) {
 		pr_debug("CPPC v2 _OSC not acked\n");
-		if (!cpc_supported_by_cpu())
+		if (!cpc_supported_by_cpu()) {
+			pr_debug("CPPC is not supported by the CPU\n");
 			return -ENODEV;
+		}
 	}
 
 	/* Parse the ACPI _CPC table for this CPU. */

drivers/cpufreq/amd-pstate.c

···
 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)
···
  };
 
 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)
 {
···
 	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;
···
 	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;
 
···
 	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;
 
-	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);
+	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;
 	}
 
-	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;
···
 		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;
 
···
 	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;
 
···
 	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;
 
···
 
 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;
···
 	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;
 	}
···
 	policy->cpuinfo.max_freq = max_freq;
 	/* 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;
 
···
 	/* don't keep reloading if cpufreq_driver exists */
 	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:

include/linux/amd-pstate.h

···
  * @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
+ * @min_limit_perf: Cached value of the performance corresponding to policy->min
+ * @max_limit_perf: Cached value of the performance corresponding to policy->max
+ * @min_limit_freq: Cached value of policy->min (in khz)
+ * @max_limit_freq: Cached value of policy->max (in khz)
+ * @max_freq: the frequency (in khz) that mapped to highest_perf
+ * @min_freq: the frequency (in khz) that mapped to lowest_perf
+ * @nominal_freq: the frequency (in khz) that mapped to nominal_perf
+ * @lowest_nonlinear_freq: the frequency (in khz) 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
+ * @freq: current cpu frequency value (in khz)
  * @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_PSTATE_GUIDED]      = "guided",
 	NULL,
 };
+
+struct quirk_entry {
+	u32 nominal_freq;
+	u32 lowest_freq;
+};
+
 #endif /* _LINUX_AMD_PSTATE_H */