[PATCH v3 21/24] thermal: intel: hfi: Implement model-specific checks for task classification

[Ricardo Neri]

In Alder Lake and Raptor Lake, the result of thread classification is more
accurate when only one SMT sibling is busy. Classification results for
class 2 and 3 are always reliable.

To avoid unnecessary migrations, only update the class of a task if it has
been the same during 4 consecutive user ticks.

Cc: Ben Segall <bsegall@xxxxxxxxxx>
Cc: Daniel Bristot de Oliveira <bristot@xxxxxxxxxx>
Cc: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>
Cc: Ionela Voinescu <ionela.voinescu@xxxxxxx>
Cc: Joel Fernandes (Google) <joel@xxxxxxxxxxxxxxxxx>
Cc: Len Brown <len.brown@xxxxxxxxx>
Cc: Lukasz Luba <lukasz.luba@xxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx>
Cc: Srinivas Pandruvada <srinivas.pandruvada@xxxxxxxxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Tim C. Chen <tim.c.chen@xxxxxxxxx>
Cc: Valentin Schneider <vschneid@xxxxxxxxxx>
Cc: x86@xxxxxxxxxx
Cc: linux-pm@xxxxxxxxxxxxxxx
Cc: linux-kernel@xxxxxxxxxxxxxxx
Signed-off-by: Ricardo Neri <ricardo.neri-calderon@xxxxxxxxxxxxxxx>
---
Changes since v2:
 * None

Changes since v1:
 * Adjusted the result the classification of Intel Thread Director to start
   at class 1. Class 0 for the scheduler means that the task is
   unclassified.
 * Used the new names of the IPC classes members in task_struct.
 * Reworked helper functions to use sched_smt_siblings_idle() to query
   the idle state of the SMT siblings of a CPU.
---
 drivers/thermal/intel/intel_hfi.c | 60 ++++++++++++++++++++++++++++++-
 1 file changed, 59 insertions(+), 1 deletion(-)

diff --git a/drivers/thermal/intel/intel_hfi.c b/drivers/thermal/intel/intel_hfi.c
index 35d947f47550..fdb53e4cabc1 100644
--- a/drivers/thermal/intel/intel_hfi.c
+++ b/drivers/thermal/intel/intel_hfi.c
@@ -40,6 +40,7 @@
 #include <linux/workqueue.h>
 
 #include <asm/msr.h>
+#include <asm/intel-family.h>
 
 #include "../thermal_core.h"
 #include "intel_hfi.h"
@@ -209,9 +210,64 @@ static int __percpu *hfi_ipcc_scores;
  */
 #define HFI_UNCLASSIFIED_DEFAULT 1
 
+#define CLASS_DEBOUNCER_SKIPS 4
+
+/**
+ * debounce_and_update_class() - Process and update a task's classification
+ *
+ * @p:		The task of which the classification will be updated
+ * @new_ipcc:	The new IPC classification
+ *
+ * Update the classification of @p with the new value that hardware provides.
+ * Only update the classification of @p if it has been the same during
+ * CLASS_DEBOUNCER_SKIPS consecutive ticks.
+ */
+static void debounce_and_update_class(struct task_struct *p, u8 new_ipcc)
+{
+	u16 debounce_skip;
+
+	/* The class of @p changed. Only restart the debounce counter. */
+	if (p->ipcc_tmp != new_ipcc) {
+		p->ipcc_cntr = 1;
+		goto out;
+	}
+
+	/*
+	 * The class of @p did not change. Update it if it has been the same
+	 * for CLASS_DEBOUNCER_SKIPS user ticks.
+	 */
+	debounce_skip = p->ipcc_cntr + 1;
+	if (debounce_skip < CLASS_DEBOUNCER_SKIPS)
+		p->ipcc_cntr++;
+	else
+		p->ipcc = new_ipcc;
+
+out:
+	p->ipcc_tmp = new_ipcc;
+}
+
+static bool classification_is_accurate(u8 hfi_class, bool smt_siblings_idle)
+{
+	switch (boot_cpu_data.x86_model) {
+	case INTEL_FAM6_ALDERLAKE:
+	case INTEL_FAM6_ALDERLAKE_L:
+	case INTEL_FAM6_RAPTORLAKE:
+	case INTEL_FAM6_RAPTORLAKE_P:
+	case INTEL_FAM6_RAPTORLAKE_S:
+		if (hfi_class == 3 || hfi_class == 2 || smt_siblings_idle)
+			return true;
+
+		return false;
+
+	default:
+		return true;
+	}
+}
+
 void intel_hfi_update_ipcc(struct task_struct *curr)
 {
 	union hfi_thread_feedback_char_msr msr;
+	bool idle;
 
 	/* We should not be here if ITD is not supported. */
 	if (!cpu_feature_enabled(X86_FEATURE_ITD)) {
@@ -227,7 +283,9 @@ void intel_hfi_update_ipcc(struct task_struct *curr)
 	 * 0 is a valid classification for Intel Thread Director. A scheduler
 	 * IPCC class of 0 means that the task is unclassified. Adjust.
 	 */
-	curr->ipcc = msr.split.classid + 1;
+	idle = sched_smt_siblings_idle(task_cpu(curr));
+	if (classification_is_accurate(msr.split.classid, idle))
+		debounce_and_update_class(curr, msr.split.classid + 1);
 }
 
 unsigned long intel_hfi_get_ipcc_score(unsigned short ipcc, int cpu)
-- 
2.25.1