[PATCH i-g-t v2 2/3] tests/intel/xe_pmu: Add PMU test to validate engine activity stats

[Umesh Nerlige Ramappa]

On Mon, Feb 17, 2025 at 07:50:17PM +0530, Riana Tauro wrote:
>Add a test to validate engine activity by reading PMU counters
>(engine-active-ticks, engine-total-ticks) when running
>workload on every engine
>
>v2: rename busy to active
>    add assert to format events (Umesh)
>    add a helper macro
>
>Signed-off-by: Riana Tauro <riana.tauro at intel.com>
>---
> tests/intel/xe_pmu.c | 156 +++++++++++++++++++++++++++++++++++++++++++
> tests/meson.build    |   1 +
> 2 files changed, 157 insertions(+)
> create mode 100644 tests/intel/xe_pmu.c
>
>diff --git a/tests/intel/xe_pmu.c b/tests/intel/xe_pmu.c
>new file mode 100644
>index 000000000..aa7d53523
>--- /dev/null
>+++ b/tests/intel/xe_pmu.c
>@@ -0,0 +1,156 @@
>+// SPDX-License-Identifier: MIT
>+/*
>+ * Copyright © 2025 Intel Corporation
>+ */
>+
>+/**
>+ * TEST: Test Xe PMU(Performance Monitoring Unit) functionality
>+ * Category: Metrics
>+ * Functionality: Power/Perf
>+ * Mega feature: Performance Monitoring Unit
>+ * Sub-category: Telemetry
>+ * Test category: Functional tests
>+ *
>+ * SUBTEST: engine-activity-load
>+ * Description: Test to validate engine activity stats by running a workload and
>+ *              reading engine active ticks and engine total ticks PMU counters
>+ */
>+#include "igt.h"
>+#include "igt_perf.h"
>+
>+#include "xe/xe_ioctl.h"
>+#include "xe/xe_spin.h"
>+
>+#define SLEEP_DURATION 2 /* in seconds */
>+const double tolerance = 0.1;
>+
>+#define assert_within_epsilon(x, ref, tolerance) \
>+	igt_assert_f((double)(x) <= (1.0 + (tolerance)) * (double)(ref) && \
>+		     (double)(x) >= (1.0 - (tolerance)) * (double)(ref), \
>+		     "'%s' != '%s' (%f not within +%.1f%%/-%.1f%% tolerance of %f)\n",\
>+		     #x, #ref, (double)(x), \
>+		     (tolerance) * 100.0, (tolerance) * 100.0, \
>+		     (double)(ref))
>+
>+#define test_each_engine(test, fd, hwe) \
>+	igt_subtest_with_dynamic(test) \
>+		xe_for_each_engine(fd, hwe) \
>+			igt_dynamic_f("engine-%s%d", xe_engine_class_string(hwe->engine_class), \
>+				      hwe->engine_instance)
>+
>+static int open_group(int xe, uint64_t config, int group)
>+{
>+	int fd;
>+
>+	fd = igt_perf_open_group(xe_perf_type_id(xe), config, group);
>+	igt_skip_on(fd < 0 && errno == ENODEV);
>+	igt_assert(fd >= 0);
>+
>+	return fd;
>+}
>+
>+static uint64_t pmu_read_multi(int fd, unsigned int num, uint64_t *val)
>+{
>+	uint64_t buf[2 + num];
>+	unsigned int i;
>+
>+	igt_assert_eq(read(fd, buf, sizeof(buf)), sizeof(buf));
>+
>+	for (i = 0; i < num; i++)
>+		val[i] = buf[2 + i];
>+
>+	return buf[1];
>+}
>+
>+static uint64_t add_format_config(const char *xe_device, const char *format, uint64_t val)
>+{
>+	int ret;
>+	uint32_t shift;
>+	uint64_t config;
>+
>+	ret = perf_event_format(xe_device, format, &shift);
>+	igt_assert(ret >= 0);
>+	config = val << shift;
>+
>+	return config;
>+}
>+
>+static uint64_t get_event_config(int xe, unsigned int gt, struct drm_xe_engine_class_instance *eci,
>+				 const char *event)
>+{
>+	int ret;
>+	char xe_device[100];
>+	uint64_t pmu_config;

pmu_config should be initialized to 0 above in case eci is NULL.

With that, this is

Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa at intel.com>

Umesh

>+
>+	xe_perf_device(xe, xe_device, sizeof(xe_device));
>+	ret = perf_event_config(xe_device, event, &pmu_config);
>+	igt_assert(ret >= 0);
>+	pmu_config |= add_format_config(xe_device, "gt", gt);
>+
>+	if (eci) {
>+		pmu_config |= add_format_config(xe_device, "engine_class", eci->engine_class);
>+		pmu_config |= add_format_config(xe_device, "engine_instance", eci->engine_instance);
>+	}
>+
>+	return pmu_config;
>+}
>+
>+static void engine_activity(int fd, struct drm_xe_engine_class_instance *eci)
>+{
>+	uint64_t config, engine_active_ticks, engine_total_ticks, before[2], after[2];
>+	struct xe_cork *cork = NULL;
>+	uint32_t vm;
>+	int pmu_fd[2];
>+
>+	config = get_event_config(fd, eci->gt_id, eci, "engine-active-ticks");
>+	pmu_fd[0] = open_group(fd, config, -1);
>+
>+	config = get_event_config(fd, eci->gt_id, eci, "engine-total-ticks");
>+	pmu_fd[1] = open_group(fd, config, pmu_fd[0]);
>+
>+	vm = xe_vm_create(fd, 0, 0);
>+	cork = xe_cork_create_opts(fd, eci, vm, 1, 1);
>+	xe_cork_sync_start(fd, cork);
>+
>+	pmu_read_multi(pmu_fd[0], 2, before);
>+	usleep(SLEEP_DURATION * USEC_PER_SEC);
>+	pmu_read_multi(pmu_fd[0], 2, after);
>+
>+	xe_cork_sync_end(fd, cork);
>+
>+	engine_active_ticks = after[0] - before[0];
>+	engine_total_ticks = after[1] - before[1];
>+
>+	igt_debug("Engine active ticks:  after %ld, before %ld delta %ld\n", after[0], before[0],
>+		  engine_active_ticks);
>+	igt_debug("Engine total ticks: after %ld, before %ld delta %ld\n", after[1], before[1],
>+		  engine_total_ticks);
>+
>+	if (cork)
>+		xe_cork_destroy(fd, cork);
>+
>+	xe_vm_destroy(fd, vm);
>+
>+	close(pmu_fd[0]);
>+	close(pmu_fd[1]);
>+
>+	assert_within_epsilon(engine_active_ticks, engine_total_ticks, tolerance);
>+}
>+
>+igt_main
>+{
>+	int fd;
>+	struct drm_xe_engine_class_instance *eci;
>+
>+	igt_fixture {
>+		fd = drm_open_driver(DRIVER_XE);
>+	}
>+
>+	igt_describe("Validate engine activity with workload");
>+	test_each_engine("engine-activity-load", fd, eci)
>+		engine_activity(fd, eci);
>+
>+	igt_fixture {
>+		close(fd);
>+	}
>+}
>diff --git a/tests/meson.build b/tests/meson.build
>index 1a731fc73..a385e9cd4 100644
>--- a/tests/meson.build
>+++ b/tests/meson.build
>@@ -309,6 +309,7 @@ intel_xe_progs = [
> 	'xe_pat',
> 	'xe_peer2peer',
> 	'xe_pm',
>+	'xe_pmu',
> 	'xe_pm_residency',
> 	'xe_prime_self_import',
> 	'xe_query',
>-- 
>2.47.1
>