[PATCH v2 11/22] thermal: intel: hfi: Store per-CPU IPCC scores

[Ricardo Neri]

The scheduler reads the IPCC scores when balancing load. These reads can
be quite frequent. Hardware can also update the HFI table frequently.
Concurrent access may cause a lot of contention. It gets worse as the
number of CPUs increases.

Instead, create separate per-CPU IPCC scores that the scheduler can read
without the HFI table lock.

Cc: Ben Segall <bsegall@xxxxxxxxxx>
Cc: Daniel Bristot de Oliveira <bristot@xxxxxxxxxx>
Cc: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>
Cc: Joel Fernandes (Google) <joel@xxxxxxxxxxxxxxxxx>
Cc: Len Brown <len.brown@xxxxxxxxx>
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
Suggested-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Signed-off-by: Ricardo Neri <ricardo.neri-calderon@xxxxxxxxxxxxxxx>
---
Changes since v1:
 * Added this patch.
---
 drivers/thermal/intel/intel_hfi.c | 38 +++++++++++++++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/drivers/thermal/intel/intel_hfi.c b/drivers/thermal/intel/intel_hfi.c
index df4dc50e19fb..56dba967849c 100644
--- a/drivers/thermal/intel/intel_hfi.c
+++ b/drivers/thermal/intel/intel_hfi.c
@@ -29,6 +29,7 @@
 #include <linux/kernel.h>
 #include <linux/math.h>
 #include <linux/mutex.h>
+#include <linux/percpu.h>
 #include <linux/percpu-defs.h>
 #include <linux/printk.h>
 #include <linux/processor.h>
@@ -172,6 +173,35 @@ static struct workqueue_struct *hfi_updates_wq;
 #define HFI_UPDATE_INTERVAL		HZ
 #define HFI_MAX_THERM_NOTIFY_COUNT	16
 
+#ifdef CONFIG_IPC_CLASSES
+static int __percpu *hfi_ipcc_scores;
+
+static int alloc_hfi_ipcc_scores(void)
+{
+	hfi_ipcc_scores = __alloc_percpu(sizeof(*hfi_ipcc_scores) *
+					 hfi_features.nr_classes,
+					 sizeof(*hfi_ipcc_scores));
+
+	return !hfi_ipcc_scores;
+}
+
+static void set_hfi_ipcc_score(void *caps, int cpu)
+{
+	int i, *hfi_class = per_cpu_ptr(hfi_ipcc_scores, cpu);
+
+	for (i = 0;  i < hfi_features.nr_classes; i++) {
+		struct hfi_cpu_data *class_caps;
+
+		class_caps = caps + i * hfi_features.class_stride;
+		WRITE_ONCE(hfi_class[i], class_caps->perf_cap);
+	}
+}
+
+#else
+static int alloc_hfi_ipcc_scores(void) { return 0; }
+static void set_hfi_ipcc_score(void *caps, int cpu) { }
+#endif /* CONFIG_IPC_CLASSES */
+
 static void get_hfi_caps(struct hfi_instance *hfi_instance,
 			 struct thermal_genl_cpu_caps *cpu_caps)
 {
@@ -194,6 +224,8 @@ static void get_hfi_caps(struct hfi_instance *hfi_instance,
 		cpu_caps[i].efficiency = caps->ee_cap << 2;
 
 		++i;
+
+		set_hfi_ipcc_score(caps, cpu);
 	}
 	raw_spin_unlock_irq(&hfi_instance->table_lock);
 }
@@ -572,8 +604,14 @@ void __init intel_hfi_init(void)
 	if (!hfi_updates_wq)
 		goto err_nomem;
 
+	if (alloc_hfi_ipcc_scores())
+		goto err_ipcc;
+
 	return;
 
+err_ipcc:
+	destroy_workqueue(hfi_updates_wq);
+
 err_nomem:
 	for (j = 0; j < i; ++j) {
 		hfi_instance = &hfi_instances[j];
-- 
2.25.1