[Intel-gfx] [PATCH 17/46] drm/i915: Simple selftest to exercise live requests

[Chris Wilson]

Just create several batches of requests and expect it to not fall over!

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
---
 drivers/gpu/drm/i915/selftests/i915_gem_request.c  | 147 +++++++++++++++++++++
 .../gpu/drm/i915/selftests/i915_live_selftests.h   |   1 +
 2 files changed, 148 insertions(+)

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_request.c b/drivers/gpu/drm/i915/selftests/i915_gem_request.c
index bc6f5618f22b..b5c7cd6633f0 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_request.c
@@ -22,6 +22,8 @@
  *
  */
 
+#include <linux/prime_numbers.h>
+
 #include "../i915_selftest.h"
 
 #include "mock_gem_device.h"
@@ -161,3 +163,148 @@ int i915_gem_request_mock_selftests(void)
 
 	return err;
 }
+
+struct live_test {
+	struct drm_i915_private *i915;
+	const char *func;
+	const char *name;
+
+	unsigned int reset_count;
+};
+
+static int begin_live_test(struct live_test *t,
+			   struct drm_i915_private *i915,
+			   const char *func,
+			   const char *name)
+{
+	int err;
+
+	t->i915 = i915;
+	t->func = func;
+	t->name = name;
+
+	err = i915_gem_wait_for_idle(i915, I915_WAIT_LOCKED);
+	if (err) {
+		pr_err("%s(%s): failed to idle before, with err=%d!",
+		       func, name, err);
+		return err;
+	}
+
+	i915_gem_retire_requests(i915);
+
+	i915->gpu_error.missed_irq_rings = 0;
+	t->reset_count = i915_reset_count(&i915->gpu_error);
+
+	return 0;
+}
+
+static int end_live_test(struct live_test *t)
+{
+	struct drm_i915_private *i915 = t->i915;
+
+	if (wait_for(intel_execlists_idle(i915), 1)) {
+		pr_err("%s(%s): GPU not idle\n", t->func, t->name);
+		return -EIO;
+	}
+
+	if (t->reset_count != i915_reset_count(&i915->gpu_error)) {
+		pr_err("%s(%s): GPU was reset %d times!\n",
+		       t->func, t->name,
+		       i915_reset_count(&i915->gpu_error) - t->reset_count);
+		return -EIO;
+	}
+
+	if (i915->gpu_error.missed_irq_rings) {
+		pr_err("%s(%s): Missed interrupts on engines %lx\n",
+		       t->func, t->name, i915->gpu_error.missed_irq_rings);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int live_nop_request(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct intel_engine_cs *engine;
+	struct live_test t;
+	unsigned int id;
+	int err;
+
+	/* Submit various sized batches of empty requests, to each engine
+	 * (individually), and wait for the batch to complete. We can check
+	 * the overhead of submitting requests to the hardware.
+	 */
+
+	mutex_lock(&i915->drm.struct_mutex);
+
+	for_each_engine(engine, i915, id) {
+		IGT_TIMEOUT(end_time);
+		struct drm_i915_gem_request *request;
+		unsigned long n, prime;
+		ktime_t times[2] = {};
+
+		err = begin_live_test(&t, i915, __func__, engine->name);
+		if (err)
+			goto out_unlock;
+
+		for_each_prime_number_from(prime, 1, 8192) {
+			times[1] = ktime_get_raw();
+
+			for (n = 0; n < prime; n++) {
+				request = i915_gem_request_alloc(engine,
+								 i915->kernel_context);
+				if (IS_ERR(request)) {
+					err = PTR_ERR(request);
+					goto out_unlock;
+				}
+
+				/* This space is left intentionally blank.
+				 *
+				 * We do not actually want to perform any
+				 * action with this request, we just want
+				 * to measure the latency in allocation
+				 * and submission of our breadcrumbs -
+				 * ensuring that the bare request is sufficient
+				 * for the system to work (i.e. proper HEAD
+				 * tracking of the rings, interrupt handling,
+				 * etc). It also gives us the lowest bounds
+				 * for latency.
+				 */
+
+				i915_add_request(request);
+			}
+			i915_wait_request(request,
+					  I915_WAIT_LOCKED,
+					  MAX_SCHEDULE_TIMEOUT);
+
+			times[1] = ktime_sub(ktime_get_raw(), times[1]);
+			if (prime == 1)
+				times[0] = times[1];
+
+			if (__igt_timeout(end_time, NULL))
+				break;
+		}
+
+		err = end_live_test(&t);
+		if (err)
+			goto out_unlock;
+
+		pr_info("Request latencies on %s: 1 = %lluns, %lu = %lluns\n",
+			engine->name,
+			ktime_to_ns(times[0]),
+			prime, div64_u64(ktime_to_ns(times[1]), prime));
+	}
+
+out_unlock:
+	mutex_unlock(&i915->drm.struct_mutex);
+	return err;
+}
+
+int i915_gem_request_live_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(live_nop_request),
+	};
+	return i915_subtests(tests, i915);
+}
diff --git a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
index f3e17cb10e05..09bf538826df 100644
--- a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
@@ -9,3 +9,4 @@
  * Tests are executed in order by igt/drv_selftest
  */
 selftest(sanitycheck, i915_live_sanitycheck) /* keep first (igt selfcheck) */
+selftest(requests, i915_gem_request_live_selftests)
-- 
2.11.0