1 files changed, 284 insertions, 34 deletions

diff --git a/drivers/gpu/drm/i915/gt/selftest_slpc.c b/drivers/gpu/drm/i915/gt/selftest_slpc.c
index f8a1d27df272..e61bb0bad12c 100644
--- a/drivers/gpu/drm/i915/gt/selftest_slpc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_slpc.c
@@ -11,7 +11,16 @@
 enum test_type {
 	VARY_MIN,
 	VARY_MAX,
-	MAX_GRANTED
+	MAX_GRANTED,
+	SLPC_POWER,
+	TILE_INTERACTION,
+};
+
+struct slpc_thread {
+	struct kthread_worker *worker;
+	struct kthread_work work;
+	struct intel_gt *gt;
+	int result;
 };
 
 static int slpc_set_min_freq(struct intel_guc_slpc *slpc, u32 freq)
@@ -41,6 +50,79 @@ static int slpc_set_max_freq(struct intel_guc_slpc *slpc, u32 freq)
 	return ret;
 }
 
+static int slpc_set_freq(struct intel_gt *gt, u32 freq)
+{
+	int err;
+	struct intel_guc_slpc *slpc = &gt_to_guc(gt)->slpc;
+
+	err = slpc_set_max_freq(slpc, freq);
+	if (err) {
+		pr_err("Unable to update max freq");
+		return err;
+	}
+
+	err = slpc_set_min_freq(slpc, freq);
+	if (err) {
+		pr_err("Unable to update min freq");
+		return err;
+	}
+
+	return err;
+}
+
+static int slpc_restore_freq(struct intel_guc_slpc *slpc, u32 min, u32 max)
+{
+	int err;
+
+	err = slpc_set_max_freq(slpc, max);
+	if (err) {
+		pr_err("Unable to restore max freq");
+		return err;
+	}
+
+	err = slpc_set_min_freq(slpc, min);
+	if (err) {
+		pr_err("Unable to restore min freq");
+		return err;
+	}
+
+	err = intel_guc_slpc_set_ignore_eff_freq(slpc, false);
+	if (err) {
+		pr_err("Unable to restore efficient freq");
+		return err;
+	}
+
+	return 0;
+}
+
+static u64 slpc_measure_power(struct intel_rps *rps, int *freq)
+{
+	u64 x[5];
+	int i;
+
+	for (i = 0; i < 5; i++)
+		x[i] = __measure_power(5);
+
+	*freq = (*freq + intel_rps_read_actual_frequency(rps)) / 2;
+
+	/* A simple triangle filter for better result stability */
+	sort(x, 5, sizeof(*x), cmp_u64, NULL);
+	return div_u64(x[1] + 2 * x[2] + x[3], 4);
+}
+
+static u64 measure_power_at_freq(struct intel_gt *gt, int *freq, u64 *power)
+{
+	int err = 0;
+
+	err = slpc_set_freq(gt, *freq);
+	if (err)
+		return err;
+	*freq = intel_rps_read_actual_frequency(&gt->rps);
+	*power = slpc_measure_power(&gt->rps, freq);
+
+	return err;
+}
+
 static int vary_max_freq(struct intel_guc_slpc *slpc, struct intel_rps *rps,
 			 u32 *max_act_freq)
 {
@@ -113,6 +195,58 @@ static int vary_min_freq(struct intel_guc_slpc *slpc, struct intel_rps *rps,
 	return err;
 }
 
+static int slpc_power(struct intel_gt *gt, struct intel_engine_cs *engine)
+{
+	struct intel_guc_slpc *slpc = &gt_to_guc(gt)->slpc;
+	struct {
+		u64 power;
+		int freq;
+	} min, max;
+	int err = 0;
+
+	/*
+	 * Our fundamental assumption is that running at lower frequency
+	 * actually saves power. Let's see if our RAPL measurement supports
+	 * that theory.
+	 */
+	if (!librapl_supported(gt->i915))
+		return 0;
+
+	min.freq = slpc->min_freq;
+	err = measure_power_at_freq(gt, &min.freq, &min.power);
+
+	if (err)
+		return err;
+
+	max.freq = slpc->rp0_freq;
+	err = measure_power_at_freq(gt, &max.freq, &max.power);
+
+	if (err)
+		return err;
+
+	pr_info("%s: min:%llumW @ %uMHz, max:%llumW @ %uMHz\n",
+		engine->name,
+		min.power, min.freq,
+		max.power, max.freq);
+
+	if (10 * min.freq >= 9 * max.freq) {
+		pr_notice("Could not control frequency, ran at [%uMHz, %uMhz]\n",
+			  min.freq, max.freq);
+	}
+
+	if (11 * min.power > 10 * max.power) {
+		pr_err("%s: did not conserve power when setting lower frequency!\n",
+		       engine->name);
+		err = -EINVAL;
+	}
+
+	/* Restore min/max frequencies */
+	slpc_set_max_freq(slpc, slpc->rp0_freq);
+	slpc_set_min_freq(slpc, slpc->min_freq);
+
+	return err;
+}
+
 static int max_granted_freq(struct intel_guc_slpc *slpc, struct intel_rps *rps, u32 *max_act_freq)
 {
 	struct intel_gt *gt = rps_to_gt(rps);
@@ -126,7 +260,8 @@ static int max_granted_freq(struct intel_guc_slpc *slpc, struct intel_rps *rps,
 	*max_act_freq =  intel_rps_read_actual_frequency(rps);
 	if (*max_act_freq != slpc->rp0_freq) {
 		/* Check if there was some throttling by pcode */
-		perf_limit_reasons = intel_uncore_read(gt->uncore, GT0_PERF_LIMIT_REASONS);
+		perf_limit_reasons = intel_uncore_read(gt->uncore,
+						       intel_gt_perf_limit_reasons_reg(gt));
 
 		/* If not, this is an error */
 		if (!(perf_limit_reasons & GT0_PERF_LIMIT_REASONS_MASK)) {
@@ -142,10 +277,11 @@ static int max_granted_freq(struct intel_guc_slpc *slpc, struct intel_rps *rps,
 
 static int run_test(struct intel_gt *gt, int test_type)
 {
-	struct intel_guc_slpc *slpc = &gt->uc.guc.slpc;
+	struct intel_guc_slpc *slpc = &gt_to_guc(gt)->slpc;
 	struct intel_rps *rps = &gt->rps;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
+	intel_wakeref_t wakeref;
 	struct igt_spinner spin;
 	u32 slpc_min_freq, slpc_max_freq;
 	int err = 0;
@@ -153,6 +289,11 @@ static int run_test(struct intel_gt *gt, int test_type)
 	if (!intel_uc_uses_guc_slpc(&gt->uc))
 		return 0;
 
+	if (slpc->min_freq == slpc->rp0_freq) {
+		pr_err("Min/Max are fused to the same value\n");
+		return -EINVAL;
+	}
+
 	if (igt_spinner_init(&spin, gt))
 		return -ENOMEM;
 
@@ -167,21 +308,26 @@ static int run_test(struct intel_gt *gt, int test_type)
 	}
 
 	/*
-	 * FIXME: With efficient frequency enabled, GuC can request
-	 * frequencies higher than the SLPC max. While this is fixed
-	 * in GuC, we level set these tests with RPn as min.
+	 * Set min frequency to RPn so that we can test the whole
+	 * range of RPn-RP0.
 	 */
 	err = slpc_set_min_freq(slpc, slpc->min_freq);
-	if (err)
+	if (err) {
+		pr_err("Unable to update min freq!");
 		return err;
+	}
 
-	if (slpc->min_freq == slpc->rp0_freq) {
-		pr_err("Min/Max are fused to the same value\n");
-		return -EINVAL;
+	/*
+	 * Turn off efficient frequency so RPn/RP0 ranges are obeyed.
+	 */
+	err = intel_guc_slpc_set_ignore_eff_freq(slpc, true);
+	if (err) {
+		pr_err("Unable to turn off efficient freq!");
+		return err;
 	}
 
 	intel_gt_pm_wait_for_idle(gt);
-	intel_gt_pm_get(gt);
+	wakeref = intel_gt_pm_get(gt);
 	for_each_engine(engine, gt, id) {
 		struct i915_request *rq;
 		u32 max_act_freq;
@@ -222,9 +368,10 @@ static int run_test(struct intel_gt *gt, int test_type)
 			break;
 
 		case MAX_GRANTED:
+		case TILE_INTERACTION:
 			/* Media engines have a different RP0 */
-			if (engine->class == VIDEO_DECODE_CLASS ||
-			    engine->class == VIDEO_ENHANCEMENT_CLASS) {
+			if (gt->type != GT_MEDIA && (engine->class == VIDEO_DECODE_CLASS ||
+						     engine->class == VIDEO_ENHANCEMENT_CLASS)) {
 				igt_spinner_end(&spin);
 				st_engine_heartbeat_enable(engine);
 				err = 0;
@@ -233,17 +380,24 @@ static int run_test(struct intel_gt *gt, int test_type)
 
 			err = max_granted_freq(slpc, rps, &max_act_freq);
 			break;
-		}
 
-		pr_info("Max actual frequency for %s was %d\n",
-			engine->name, max_act_freq);
+		case SLPC_POWER:
+			err = slpc_power(gt, engine);
+			break;
+		}
 
-		/* Actual frequency should rise above min */
-		if (max_act_freq <= slpc_min_freq) {
-			pr_err("Actual freq did not rise above min\n");
-			pr_err("Perf Limit Reasons: 0x%x\n",
-			       intel_uncore_read(gt->uncore, GT0_PERF_LIMIT_REASONS));
-			err = -EINVAL;
+		if (test_type != SLPC_POWER) {
+			pr_info("Max actual frequency for %s was %d\n",
+				engine->name, max_act_freq);
+
+			/* Actual frequency should rise above min */
+			if (max_act_freq <= slpc->min_freq) {
+				pr_err("Actual freq did not rise above min\n");
+				pr_err("Perf Limit Reasons: 0x%x\n",
+				       intel_uncore_read(gt->uncore,
+							 intel_gt_perf_limit_reasons_reg(gt)));
+				err = -EINVAL;
+			}
 		}
 
 		igt_spinner_end(&spin);
@@ -253,14 +407,13 @@ static int run_test(struct intel_gt *gt, int test_type)
 			break;
 	}
 
-	/* Restore min/max frequencies */
-	slpc_set_max_freq(slpc, slpc_max_freq);
-	slpc_set_min_freq(slpc, slpc_min_freq);
+	/* Restore min/max/efficient frequencies */
+	err = slpc_restore_freq(slpc, slpc_min_freq, slpc_max_freq);
 
 	if (igt_flush_test(gt->i915))
 		err = -EIO;
 
-	intel_gt_pm_put(gt);
+	intel_gt_pm_put(gt, wakeref);
 	igt_spinner_fini(&spin);
 	intel_gt_pm_wait_for_idle(gt);
 
@@ -270,26 +423,116 @@ static int run_test(struct intel_gt *gt, int test_type)
 static int live_slpc_vary_min(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
-	struct intel_gt *gt = to_gt(i915);
+	struct intel_gt *gt;
+	unsigned int i;
+	int ret;
+
+	for_each_gt(gt, i915, i) {
+		ret = run_test(gt, VARY_MIN);
+		if (ret)
+			return ret;
+	}
 
-	return run_test(gt, VARY_MIN);
+	return ret;
 }
 
 static int live_slpc_vary_max(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
-	struct intel_gt *gt = to_gt(i915);
+	struct intel_gt *gt;
+	unsigned int i;
+	int ret;
+
+	for_each_gt(gt, i915, i) {
+		ret = run_test(gt, VARY_MAX);
+		if (ret)
+			return ret;
+	}
 
-	return run_test(gt, VARY_MAX);
+	return ret;
 }
 
 /* check if pcode can grant RP0 */
 static int live_slpc_max_granted(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
-	struct intel_gt *gt = to_gt(i915);
+	struct intel_gt *gt;
+	unsigned int i;
+	int ret;
+
+	for_each_gt(gt, i915, i) {
+		ret = run_test(gt, MAX_GRANTED);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
+}
+
+static int live_slpc_power(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt;
+	unsigned int i;
+	int ret;
+
+	for_each_gt(gt, i915, i) {
+		ret = run_test(gt, SLPC_POWER);
+		if (ret)
+			return ret;
+	}
 
-	return run_test(gt, MAX_GRANTED);
+	return ret;
+}
+
+static void slpc_spinner_thread(struct kthread_work *work)
+{
+	struct slpc_thread *thread = container_of(work, typeof(*thread), work);
+
+	thread->result = run_test(thread->gt, TILE_INTERACTION);
+}
+
+static int live_slpc_tile_interaction(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt;
+	struct slpc_thread *threads;
+	int i = 0, ret = 0;
+
+	threads = kcalloc(I915_MAX_GT, sizeof(*threads), GFP_KERNEL);
+	if (!threads)
+		return -ENOMEM;
+
+	for_each_gt(gt, i915, i) {
+		threads[i].worker = kthread_run_worker(0, "igt/slpc_parallel:%d", gt->info.id);
+
+		if (IS_ERR(threads[i].worker)) {
+			ret = PTR_ERR(threads[i].worker);
+			break;
+		}
+
+		threads[i].gt = gt;
+		kthread_init_work(&threads[i].work, slpc_spinner_thread);
+		kthread_queue_work(threads[i].worker, &threads[i].work);
+	}
+
+	for_each_gt(gt, i915, i) {
+		int status;
+
+		if (IS_ERR_OR_NULL(threads[i].worker))
+			continue;
+
+		kthread_flush_work(&threads[i].work);
+		status = READ_ONCE(threads[i].result);
+		if (status && !ret) {
+			pr_err("%s GT %d failed ", __func__, gt->info.id);
+			ret = status;
+		}
+		kthread_destroy_worker(threads[i].worker);
+	}
+
+	kfree(threads);
+	return ret;
 }
 
 int intel_slpc_live_selftests(struct drm_i915_private *i915)
@@ -298,10 +541,17 @@ int intel_slpc_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(live_slpc_vary_max),
 		SUBTEST(live_slpc_vary_min),
 		SUBTEST(live_slpc_max_granted),
+		SUBTEST(live_slpc_power),
+		SUBTEST(live_slpc_tile_interaction),
 	};
 
-	if (intel_gt_is_wedged(to_gt(i915)))
-		return 0;
+	struct intel_gt *gt;
+	unsigned int i;
+
+	for_each_gt(gt, i915, i) {
+		if (intel_gt_is_wedged(gt))
+			return 0;
+	}
 
 	return i915_live_subtests(tests, i915);
 }