4 files changed, 65 insertions, 6 deletions

diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86
index adbd1de1cea5..35f71825b7f3 100644
--- a/drivers/cpufreq/Kconfig.x86
+++ b/drivers/cpufreq/Kconfig.x86
@@ -6,6 +6,7 @@ config X86_INTEL_PSTATE
        bool "Intel P state control"
        depends on X86
        select ACPI_PROCESSOR if ACPI
+       select ACPI_CPPC_LIB if X86_64 && ACPI && SCHED_MC_PRIO
        help
           This driver provides a P state for Intel core processors.
 	  The driver implements an internal governor and will become
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index 5c07ae05d69a..269013311e79 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -28,6 +28,7 @@
 #include "cpufreq-dt.h"
 
 struct private_data {
+	struct opp_table *opp_table;
 	struct device *cpu_dev;
 	struct thermal_cooling_device *cdev;
 	const char *reg_name;
@@ -143,6 +144,7 @@ static int resources_available(void)
 static int cpufreq_init(struct cpufreq_policy *policy)
 {
 	struct cpufreq_frequency_table *freq_table;
+	struct opp_table *opp_table = NULL;
 	struct private_data *priv;
 	struct device *cpu_dev;
 	struct clk *cpu_clk;
@@ -186,8 +188,9 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	 */
 	name = find_supply_name(cpu_dev);
 	if (name) {
-		ret = dev_pm_opp_set_regulator(cpu_dev, name);
-		if (ret) {
+		opp_table = dev_pm_opp_set_regulators(cpu_dev, &name, 1);
+		if (IS_ERR(opp_table)) {
+			ret = PTR_ERR(opp_table);
 			dev_err(cpu_dev, "Failed to set regulator for cpu%d: %d\n",
 				policy->cpu, ret);
 			goto out_put_clk;
@@ -237,6 +240,7 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	}
 
 	priv->reg_name = name;
+	priv->opp_table = opp_table;
 
 	ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table);
 	if (ret) {
@@ -285,7 +289,7 @@ out_free_priv:
 out_free_opp:
 	dev_pm_opp_of_cpumask_remove_table(policy->cpus);
 	if (name)
-		dev_pm_opp_put_regulator(cpu_dev);
+		dev_pm_opp_put_regulators(opp_table);
 out_put_clk:
 	clk_put(cpu_clk);
 
@@ -300,7 +304,7 @@ static int cpufreq_exit(struct cpufreq_policy *policy)
 	dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table);
 	dev_pm_opp_of_cpumask_remove_table(policy->related_cpus);
 	if (priv->reg_name)
-		dev_pm_opp_put_regulator(priv->cpu_dev);
+		dev_pm_opp_put_regulators(priv->opp_table);
 
 	clk_put(policy->clk);
 	kfree(priv);
diff --git a/drivers/cpufreq/ia64-acpi-cpufreq.c b/drivers/cpufreq/ia64-acpi-cpufreq.c
index 759612da4fdc..e28a31a40829 100644
--- a/drivers/cpufreq/ia64-acpi-cpufreq.c
+++ b/drivers/cpufreq/ia64-acpi-cpufreq.c
@@ -18,7 +18,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pal.h>
 
 #include <linux/acpi.h>
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index ed215c5592f6..a54d65aa776d 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -46,6 +46,7 @@
 
 #ifdef CONFIG_ACPI
 #include <acpi/processor.h>
+#include <acpi/cppc_acpi.h>
 #endif
 
 #define FRAC_BITS 8
@@ -406,14 +407,67 @@ static bool intel_pstate_get_ppc_enable_status(void)
 	return acpi_ppc;
 }
 
+#ifdef CONFIG_ACPI_CPPC_LIB
+
+/* The work item is needed to avoid CPU hotplug locking issues */
+static void intel_pstste_sched_itmt_work_fn(struct work_struct *work)
+{
+	sched_set_itmt_support();
+}
+
+static DECLARE_WORK(sched_itmt_work, intel_pstste_sched_itmt_work_fn);
+
+static void intel_pstate_set_itmt_prio(int cpu)
+{
+	struct cppc_perf_caps cppc_perf;
+	static u32 max_highest_perf = 0, min_highest_perf = U32_MAX;
+	int ret;
+
+	ret = cppc_get_perf_caps(cpu, &cppc_perf);
+	if (ret)
+		return;
+
+	/*
+	 * 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(cppc_perf.highest_perf, cpu);
+
+	if (max_highest_perf <= min_highest_perf) {
+		if (cppc_perf.highest_perf > max_highest_perf)
+			max_highest_perf = cppc_perf.highest_perf;
+
+		if (cppc_perf.highest_perf < min_highest_perf)
+			min_highest_perf = cppc_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_itmt_work);
+		}
+	}
+}
+#else
+static void intel_pstate_set_itmt_prio(int cpu)
+{
+}
+#endif
+
 static void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy)
 {
 	struct cpudata *cpu;
 	int ret;
 	int i;
 
-	if (hwp_active)
+	if (hwp_active) {
+		intel_pstate_set_itmt_prio(policy->cpu);
 		return;
+	}
 
 	if (!intel_pstate_get_ppc_enable_status())
 		return;