Re: [PATCH i-g-t 2/2] tests/xe_pmu: Add frequency test

[Riana Tauro]

Hi Vinay

On 4/8/2025 5:14 AM, Vinay Belgaumkar wrote:
Add a basic test that uses PMU to read GT actual and requested
frequencies while running a workload.
v2: Rebase and comments (Riana)

Cc: Lucas De Marchi <lucas.demar...@intel.com>
Cc: Rodrigo Vivi <rodrigo.v...@intel.com>
Cc: Riana Tauro <riana.ta...@intel.com>
Signed-off-by: Vinay Belgaumkar <vinay.belgaum...@intel.com>
---
  tests/intel/xe_pmu.c | 128 ++++++++++++++++++++++++++++++++++++++++++-
  1 file changed, 127 insertions(+), 1 deletion(-)

diff --git a/tests/intel/xe_pmu.c b/tests/intel/xe_pmu.c
index 175bbf374..fbac9c798 100644
--- a/tests/intel/xe_pmu.c
+++ b/tests/intel/xe_pmu.c
@@ -376,6 +376,94 @@ static void test_gt_c6_idle(int xe, unsigned int gt)
        close(pmu_fd);
  }
  
+/**
+ * SUBTEST: gt-frequency
+ * Description: Validate we can collect accurate frequency PMU stats
+ *             while running a workload.
+ */
+static void test_gt_frequency(int fd, struct drm_xe_engine_class_instance *eci)
+{
+       struct xe_cork *cork = NULL;
+       uint64_t end[2], start[2];
+       unsigned long config_rq_freq, config_act_freq;
+       double min[2], max[2];
+       uint32_t gt = eci->gt_id;
+       uint32_t orig_min = xe_gt_get_freq(fd, eci->gt_id, "min");
+       uint32_t orig_max = xe_gt_get_freq(fd, eci->gt_id, "max");
+       uint32_t vm;
+       int pmu_fd[2];
+
+       config_rq_freq = get_event_config(gt, NULL, "gt-requested-frequency");
+       pmu_fd[0] = open_group(fd, config_rq_freq, -1);
+
+       config_act_freq = get_event_config(gt, NULL, "gt-actual-frequency");
+       pmu_fd[1] = open_group(fd, config_act_freq, 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);
+
+       /*
+        * Set GPU to min frequency and read PMU counters.
+        */
+       igt_assert(xe_gt_set_freq(fd, gt, "max", orig_min) > 0);
+       igt_assert(xe_gt_get_freq(fd, gt, "max") == orig_min);
+
+       pmu_read_multi(pmu_fd[0], 2, start);
+       usleep(SLEEP_DURATION * USEC_PER_SEC);
+       pmu_read_multi(pmu_fd[0], 2, end);
+
+       min[0] = (end[0] - start[0]);
+       min[1] = (end[1] - start[1]);
+
+       /*
+        * Set GPU to max frequency and read PMU counters.
+        */
+       igt_assert(xe_gt_set_freq(fd, gt, "max", orig_max) > 0);
+       igt_assert(xe_gt_get_freq(fd, gt, "max") == orig_max);
+       igt_assert(xe_gt_set_freq(fd, gt, "min", orig_max) > 0);
+       igt_assert(xe_gt_get_freq(fd, gt, "min") == orig_max);
+
+       pmu_read_multi(pmu_fd[0], 2, start);
+       usleep(SLEEP_DURATION * USEC_PER_SEC);
+       pmu_read_multi(pmu_fd[0], 2, end);
+
+       max[0] = (end[0] - start[0]);
+       max[1] = (end[1] - start[1]);
+
+       xe_cork_sync_end(fd, cork);
+
+       /*
+        * Restore min/max.
+        */
+       igt_assert(xe_gt_set_freq(fd, gt, "min", orig_min) > 0);
+       igt_assert(xe_gt_get_freq(fd, gt, "min") == orig_min);
+
+       igt_info("Minimum frequency: requested %.1f, actual %.1f\n",
+                min[0], min[1]);
+       igt_info("Maximum frequency: requested %.1f, actual %.1f\n",
+                max[0], max[1]);
+
+       close(pmu_fd[0]);
+       close(pmu_fd[1]);
+
+       if (cork)
+               xe_cork_destroy(fd, cork);
+
+       xe_vm_destroy(fd, vm);
+
+       close(pmu_fd[0]);
+       close(pmu_fd[1]);
+
+       assert_within_epsilon(min[0], orig_min, tolerance);
+       /*
+        * On thermally throttled devices we cannot be sure maximum frequency
+        * can be reached so use larger tolerance downwards.
+        */
+       assert_within_epsilon_up_down(max[0], orig_max, tolerance, 0.15f);
+}
+
  static unsigned int enable_and_provision_vfs(int fd)
  {
        unsigned int gt, num_vfs;
@@ -429,8 +517,9 @@ static void disable_vfs(int fd)
  
  igt_main
  {
-       int fd, gt;
+       int fd, gt, num_gts;
        struct drm_xe_engine_class_instance *eci;
+       uint32_t *stash_min, *stash_max;
  
  	igt_fixture {
                fd = drm_open_driver(DRIVER_XE);
@@ -482,6 +571,43 @@ igt_main
                        disable_vfs(fd);
        }
  
+	igt_subtest_group {
+               igt_fixture {
+                       igt_require(xe_sysfs_gt_has_node(fd, 0, "freq0"));
+                       num_gts = xe_number_gt(fd);
+
+                       stash_min = (uint32_t *) malloc(sizeof(uint32_t) * 
num_gts);
+                       stash_max = (uint32_t *) malloc(sizeof(uint32_t) * 
num_gts);
+
+                       xe_for_each_gt(fd, gt) {
+                               stash_min[gt] = xe_gt_get_freq(fd, gt, "min");
+                               stash_max[gt] = xe_gt_get_freq(fd, gt, "max");
This can be moved inside the igt_subtest with local variables since it's 
only one test. The subtest group is executed for all the other tests too

Thanks
Riana> +                     }
+               }
+
+               igt_describe("Validate PMU GT freq measured is within the 
tolerance");
+               igt_subtest_with_dynamic("gt-frequency") {
+                       xe_for_each_gt(fd, gt) {
+                               igt_dynamic_f("gt%u", gt)
+                               xe_for_each_engine(fd, eci) {
+                                       if (gt == eci->gt_id) {
+                                               test_gt_frequency(fd, eci);
+                                               break;
+                                       }
+                               }
+                       }
+               }
+
+               igt_fixture {
+                       xe_for_each_gt(fd, gt) {
+                               xe_gt_set_freq(fd, gt, "max", stash_max[gt]);
+                               xe_gt_set_freq(fd, gt, "min", stash_min[gt]);
+                       }
+                       free(stash_min);
+                       free(stash_max);
+               }
+       }
+
        igt_fixture {
                close(fd);
        }