1 files changed, 87 insertions, 7 deletions

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index f535f8123258..e8dc42fc0915 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -44,6 +44,7 @@
 
 #ifdef CONFIG_ACPI
 #include <acpi/processor.h>
+#include <acpi/cppc_acpi.h>
 #endif
 
 #define FRAC_BITS 8
@@ -179,6 +180,7 @@ struct _pid {
 /**
  * struct cpudata -	Per CPU instance data storage
  * @cpu:		CPU number for this instance data
+ * @policy:		CPUFreq policy value
  * @update_util:	CPUFreq utility callback information
  * @update_util_set:	CPUFreq utility callback is set
  * @iowait_boost:	iowait-related boost fraction
@@ -201,6 +203,7 @@ struct _pid {
 struct cpudata {
 	int cpu;
 
+	unsigned int policy;
 	struct update_util_data update_util;
 	bool   update_util_set;
 
@@ -377,14 +380,67 @@ 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;
@@ -1142,10 +1198,8 @@ static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
 	*min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf);
 }
 
-static void intel_pstate_set_min_pstate(struct cpudata *cpu)
+static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
 {
-	int pstate = cpu->pstate.min_pstate;
-
 	trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
 	cpu->pstate.current_pstate = pstate;
 	/*
@@ -1157,6 +1211,20 @@ static void intel_pstate_set_min_pstate(struct cpudata *cpu)
 		      pstate_funcs.get_val(cpu, pstate));
 }
 
+static void intel_pstate_set_min_pstate(struct cpudata *cpu)
+{
+	intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate);
+}
+
+static void intel_pstate_max_within_limits(struct cpudata *cpu)
+{
+	int min_pstate, max_pstate;
+
+	update_turbo_state();
+	intel_pstate_get_min_max(cpu, &min_pstate, &max_pstate);
+	intel_pstate_set_pstate(cpu, max_pstate);
+}
+
 static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
 {
 	cpu->pstate.min_pstate = pstate_funcs.get_min();
@@ -1325,7 +1393,8 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
 
 	from = cpu->pstate.current_pstate;
 
-	target_pstate = pstate_funcs.get_target_pstate(cpu);
+	target_pstate = cpu->policy == CPUFREQ_POLICY_PERFORMANCE ?
+		cpu->pstate.turbo_pstate : pstate_funcs.get_target_pstate(cpu);
 
 	intel_pstate_update_pstate(cpu, target_pstate);
 
@@ -1491,7 +1560,9 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 	pr_debug("set_policy cpuinfo.max %u policy->max %u\n",
 		 policy->cpuinfo.max_freq, policy->max);
 
-	cpu = all_cpu_data[0];
+	cpu = all_cpu_data[policy->cpu];
+	cpu->policy = policy->policy;
+
 	if (cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate &&
 	    policy->max < policy->cpuinfo.max_freq &&
 	    policy->max > cpu->pstate.max_pstate * cpu->pstate.scaling) {
@@ -1499,7 +1570,7 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 		policy->max = policy->cpuinfo.max_freq;
 	}
 
-	if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) {
+	if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) {
 		limits = &performance_limits;
 		if (policy->max >= policy->cpuinfo.max_freq) {
 			pr_debug("set performance\n");
@@ -1535,6 +1606,15 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 	limits->max_perf = round_up(limits->max_perf, FRAC_BITS);
 
  out:
+	if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) {
+		/*
+		 * NOHZ_FULL CPUs need this as the governor callback may not
+		 * be invoked on them.
+		 */
+		intel_pstate_clear_update_util_hook(policy->cpu);
+		intel_pstate_max_within_limits(cpu);
+	}
+
 	intel_pstate_set_update_util_hook(policy->cpu);
 
 	intel_pstate_hwp_set_policy(policy);