[RESEND PATCH V9 3/7] cpufreq: amd-pstate: Enable amd-pstate preferred core supporting.

[Meng Li]

amd-pstate driver utilizes the functions and data structures
provided by the ITMT architecture to enable the scheduler to
favor scheduling on cores which can be get a higher frequency
with lower voltage. We call it amd-pstate preferrred core.

Here sched_set_itmt_core_prio() is called to set priorities and
sched_set_itmt_support() is called to enable ITMT feature.
amd-pstate driver uses the highest performance value to indicate
the priority of CPU. The higher value has a higher priority.

The initial core rankings are set up by amd-pstate when the
system boots.

Add a variable hw_prefcore in cpudata structure. It will check
if the processor and power firmware support preferred core
feature.

Add one new early parameter `disable` to allow user to disable
the preferred core.

Only when hardware supports preferred core and user set `enabled`
in early parameter, amd pstate driver supports preferred core featue.

Tested-by: Oleksandr Natalenko <oleksandr@xxxxxxxxxxxxxx>
Reviewed-by: Huang Rui <ray.huang@xxxxxxx>
Reviewed-by: Wyes Karny <wyes.karny@xxxxxxx>
Reviewed-by: Mario Limonciello <mario.limonciello@xxxxxxx>
Co-developed-by: Perry Yuan <Perry.Yuan@xxxxxxx>
Signed-off-by: Perry Yuan <Perry.Yuan@xxxxxxx>
Signed-off-by: Meng Li <li.meng@xxxxxxx>
---
 drivers/cpufreq/amd-pstate.c | 155 +++++++++++++++++++++++++++++++----
 include/linux/amd-pstate.h   |   4 +
 2 files changed, 143 insertions(+), 16 deletions(-)

diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 9a1e194d5cf8..6aae383990f1 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -37,6 +37,7 @@
 #include <linux/uaccess.h>
 #include <linux/static_call.h>
 #include <linux/amd-pstate.h>
+#include <linux/topology.h>
 
 #include <acpi/processor.h>
 #include <acpi/cppc_acpi.h>
@@ -49,6 +50,8 @@
 
 #define AMD_PSTATE_TRANSITION_LATENCY	20000
 #define AMD_PSTATE_TRANSITION_DELAY	1000
+#define AMD_PSTATE_PREFCORE_THRESHOLD	166
+#define AMD_PSTATE_MAX_CPPC_PERF	255
 
 /*
  * TODO: We need more time to fine tune processors with shared memory solution
@@ -64,6 +67,7 @@ static struct cpufreq_driver amd_pstate_driver;
 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;
 
 /*
  * AMD Energy Preference Performance (EPP)
@@ -290,23 +294,21 @@ 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);
 	if (ret)
 		return ret;
 
-	/*
-	 * TODO: Introduce AMD specific power feature.
-	 *
-	 * CPPC entry doesn't indicate the highest performance in some ASICs.
+	/* 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 AMD_CPPC_HIGHEST_PERF(cap1) value as
+	 * the default max 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);
+	if (cpudata->hw_prefcore)
+		WRITE_ONCE(cpudata->highest_perf, AMD_PSTATE_PREFCORE_THRESHOLD);
+	else
+		WRITE_ONCE(cpudata->highest_perf, AMD_CPPC_HIGHEST_PERF(cap1));
 
 	WRITE_ONCE(cpudata->nominal_perf, AMD_CPPC_NOMINAL_PERF(cap1));
 	WRITE_ONCE(cpudata->lowest_nonlinear_perf, AMD_CPPC_LOWNONLIN_PERF(cap1));
@@ -318,17 +320,15 @@ 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;
 
-	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);
+	if (cpudata->hw_prefcore)
+		WRITE_ONCE(cpudata->highest_perf, AMD_PSTATE_PREFCORE_THRESHOLD);
+	else
+		WRITE_ONCE(cpudata->highest_perf, cppc_perf.highest_perf);
 
 	WRITE_ONCE(cpudata->nominal_perf, cppc_perf.nominal_perf);
 	WRITE_ONCE(cpudata->lowest_nonlinear_perf,
@@ -676,6 +676,93 @@ static void amd_perf_ctl_reset(unsigned int cpu)
 	wrmsrl_on_cpu(cpu, MSR_AMD_PERF_CTL, 0);
 }
 
+/*
+ * Set amd-pstate preferred core enable can't be done directly from cpufreq callbacks
+ * due to locking, so queue the work for later.
+ */
+static void amd_pstste_sched_prefcore_workfn(struct work_struct *work)
+{
+	sched_set_itmt_support();
+}
+static DECLARE_WORK(sched_prefcore_work, amd_pstste_sched_prefcore_workfn);
+
+/*
+ * Get the highest performance register value.
+ * @cpu: CPU from which to get highest performance.
+ * @highest_perf: Return address.
+ *
+ * Return: 0 for success, -EIO otherwise.
+ */
+static int amd_pstate_get_highest_perf(int cpu, u32 *highest_perf)
+{
+	int ret;
+
+	if (boot_cpu_has(X86_FEATURE_CPPC)) {
+		u64 cap1;
+
+		ret = rdmsrl_safe_on_cpu(cpu, MSR_AMD_CPPC_CAP1, &cap1);
+		if (ret)
+			return ret;
+		WRITE_ONCE(*highest_perf, AMD_CPPC_HIGHEST_PERF(cap1));
+	} else {
+		u64 cppc_highest_perf;
+
+		ret = cppc_get_highest_perf(cpu, &cppc_highest_perf);
+		WRITE_ONCE(*highest_perf, cppc_highest_perf);
+	}
+
+	return (ret);
+}
+
+static void amd_pstate_init_prefcore(struct amd_cpudata *cpudata)
+{
+	int ret, prio;
+	u32 highest_perf;
+	static u32 max_highest_perf = 0, min_highest_perf = U32_MAX;
+
+	ret = amd_pstate_get_highest_perf(cpudata->cpu, &highest_perf);
+	if (ret)
+		return;
+
+	cpudata->hw_prefcore = true;
+	/* check if CPPC preferred core feature is enabled*/
+	if (highest_perf == AMD_PSTATE_MAX_CPPC_PERF) {
+		pr_debug("AMD CPPC preferred core is unsupported!\n");
+		cpudata->hw_prefcore = false;
+		return;
+	}
+
+	if (!amd_pstate_prefcore)
+		return;
+
+	/* The maximum value of highest perf is 255 */
+	prio = (int)(highest_perf & 0xff);
+	/*
+	 * The priorities can be set regardless of whether or not
+	 * sched_set_itmt_support(true) has been called and it is valid to
+	 * update them at any time after it has been called.
+	 */
+	sched_set_itmt_core_prio(prio, cpudata->cpu);
+
+	if (max_highest_perf <= min_highest_perf) {
+		if (highest_perf > max_highest_perf)
+			max_highest_perf = highest_perf;
+
+		if (highest_perf < min_highest_perf)
+			min_highest_perf = highest_perf;
+
+		if (max_highest_perf > min_highest_perf) {
+			/*
+			 * This code can be run during CPU online under the
+			 * CPU hotplug locks, so sched_set_itmt_support()
+			 * cannot be called from here.  Queue up a work item
+			 * to invoke it.
+			 */
+			schedule_work(&sched_prefcore_work);
+		}
+	}
+}
+
 static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
 {
 	int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret;
@@ -697,6 +784,8 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
 
 	cpudata->cpu = policy->cpu;
 
+	amd_pstate_init_prefcore(cpudata);
+
 	ret = amd_pstate_init_perf(cpudata);
 	if (ret)
 		goto free_cpudata1;
@@ -845,6 +934,17 @@ static ssize_t show_amd_pstate_highest_perf(struct cpufreq_policy *policy,
 	return sysfs_emit(buf, "%u\n", perf);
 }
 
+static ssize_t show_amd_pstate_hw_prefcore(struct cpufreq_policy *policy,
+					   char *buf)
+{
+	bool hw_prefcore;
+	struct amd_cpudata *cpudata = policy->driver_data;
+
+	hw_prefcore = READ_ONCE(cpudata->hw_prefcore);
+
+	return sysfs_emit(buf, "%s\n", hw_prefcore ? "supported" : "unsupported");
+}
+
 static ssize_t show_energy_performance_available_preferences(
 				struct cpufreq_policy *policy, char *buf)
 {
@@ -1037,18 +1137,27 @@ static ssize_t status_store(struct device *a, struct device_attribute *b,
 	return ret < 0 ? ret : count;
 }
 
+static ssize_t prefcore_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%s\n", amd_pstate_prefcore ? "enabled" : "disabled");
+}
+
 cpufreq_freq_attr_ro(amd_pstate_max_freq);
 cpufreq_freq_attr_ro(amd_pstate_lowest_nonlinear_freq);
 
 cpufreq_freq_attr_ro(amd_pstate_highest_perf);
+cpufreq_freq_attr_ro(amd_pstate_hw_prefcore);
 cpufreq_freq_attr_rw(energy_performance_preference);
 cpufreq_freq_attr_ro(energy_performance_available_preferences);
 static DEVICE_ATTR_RW(status);
+static DEVICE_ATTR_RO(prefcore);
 
 static struct freq_attr *amd_pstate_attr[] = {
 	&amd_pstate_max_freq,
 	&amd_pstate_lowest_nonlinear_freq,
 	&amd_pstate_highest_perf,
+	&amd_pstate_hw_prefcore,
 	NULL,
 };
 
@@ -1056,6 +1165,7 @@ static struct freq_attr *amd_pstate_epp_attr[] = {
 	&amd_pstate_max_freq,
 	&amd_pstate_lowest_nonlinear_freq,
 	&amd_pstate_highest_perf,
+	&amd_pstate_hw_prefcore,
 	&energy_performance_preference,
 	&energy_performance_available_preferences,
 	NULL,
@@ -1063,6 +1173,7 @@ static struct freq_attr *amd_pstate_epp_attr[] = {
 
 static struct attribute *pstate_global_attributes[] = {
 	&dev_attr_status.attr,
+	&dev_attr_prefcore.attr,
 	NULL
 };
 
@@ -1114,6 +1225,8 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 	cpudata->cpu = policy->cpu;
 	cpudata->epp_policy = 0;
 
+	amd_pstate_init_prefcore(cpudata);
+
 	ret = amd_pstate_init_perf(cpudata);
 	if (ret)
 		goto free_cpudata1;
@@ -1527,7 +1640,17 @@ static int __init amd_pstate_param(char *str)
 
 	return amd_pstate_set_driver(mode_idx);
 }
+
+static int __init amd_prefcore_param(char *str)
+{
+	if (!strcmp(str, "disable"))
+		amd_pstate_prefcore = false;
+
+	return 0;
+}
+
 early_param("amd_pstate", amd_pstate_param);
+early_param("amd_prefcore", amd_prefcore_param);
 
 MODULE_AUTHOR("Huang Rui <ray.huang@xxxxxxx>");
 MODULE_DESCRIPTION("AMD Processor P-state Frequency Driver");
diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h
index 446394f84606..87e140e9e6db 100644
--- a/include/linux/amd-pstate.h
+++ b/include/linux/amd-pstate.h
@@ -52,6 +52,9 @@ struct amd_aperf_mperf {
  * @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
@@ -81,6 +84,7 @@ struct amd_cpudata {
 
 	u64	freq;
 	bool	boost_supported;
+	bool	hw_prefcore;
 
 	/* EPP feature related attributes*/
 	s16	epp_policy;
-- 
2.34.1