[Intel-gfx] [igt-dev] [PATCH i-g-t 04/11] tests/i915/i915_hangman: Explicitly test per engine reset vs full GPU reset

[Dandamudi, Priyanka]

Does this test series cover to prove that it can survive killing one without killing all the others except RCS+CCS combination(killing one affects other and shows with the help of reset stats)?


-----Original Message-----
From: igt-dev <igt-dev-bounces at lists.freedesktop.org> On Behalf Of John.C.Harrison at Intel.com
Sent: 14 December 2021 04:59 AM
To: IGT-Dev at Lists.FreeDesktop.Org
Cc: Intel-GFX at Lists.FreeDesktop.Org
Subject: [igt-dev] [PATCH i-g-t 04/11] tests/i915/i915_hangman: Explicitly test per engine reset vs full GPU reset

From: John Harrison <John.C.Harrison at Intel.com>

Although the hangman test was ensuring that *some* reset functionality was enabled, it did not differentiate what kind. The infrastructure required to choose between per engine reset or full GT reset was recently added. So update this test to use it as well.

Signed-off-by: John Harrison <John.C.Harrison at Intel.com>
---
 tests/i915/i915_hangman.c | 77 +++++++++++++++++++++++++--------------
 1 file changed, 50 insertions(+), 27 deletions(-)

diff --git a/tests/i915/i915_hangman.c b/tests/i915/i915_hangman.c index bd787d7b4..f8a48337c 100644
--- a/tests/i915/i915_hangman.c
+++ b/tests/i915/i915_hangman.c
@@ -323,40 +323,26 @@ static void hangcheck_unterminated(const intel_ctx_t *ctx)
 	}
 }
 
-igt_main
+static void do_tests(const char *name, const char *prefix,
+		     const intel_ctx_t *ctx)
 {
 	const struct intel_execution_engine2 *e;
-	const intel_ctx_t *ctx;
-	igt_hang_t hang = {};
-
-	igt_fixture {
-		device = drm_open_driver(DRIVER_INTEL);
-		igt_require_gem(device);
-
-		ctx = intel_ctx_create_all_physical(device);
-
-		hang = igt_allow_hang(device, ctx->id, HANG_ALLOW_CAPTURE);
-
-		sysfs = igt_sysfs_open(device);
-		igt_assert(sysfs != -1);
+	char buff[256];
 
-		igt_require(has_error_state(sysfs));
-	}
-
-	igt_describe("Basic error capture");
-	igt_subtest("error-state-basic")
-		test_error_state_basic();
-
-	igt_describe("Per engine error capture");
-	igt_subtest_with_dynamic("error-state-capture") {
+	snprintf(buff, sizeof(buff), "Per engine error capture (%s reset)", name);
+	igt_describe(buff);
+	snprintf(buff, sizeof(buff), "%s-error-state-capture", prefix);
+	igt_subtest_with_dynamic(buff) {
 		for_each_ctx_engine(device, ctx, e) {
 			igt_dynamic_f("%s", e->name)
 				test_error_state_capture(ctx, e);
 		}
 	}
 
-	igt_describe("Per engine hang recovery (spin)");
-	igt_subtest_with_dynamic("engine-hang") {
+	snprintf(buff, sizeof(buff), "Per engine hang recovery (spin, %s reset)", name);
+	igt_describe(buff);
+	snprintf(buff, sizeof(buff), "%s-engine-hang", prefix);
+	igt_subtest_with_dynamic(buff) {
                 int has_gpu_reset = 0;
 		struct drm_i915_getparam gp = {
 			.param = I915_PARAM_HAS_GPU_RESET,
@@ -374,8 +360,10 @@ igt_main
 		}
 	}
 
-	igt_describe("Per engine hang recovery (invalid CS)");
-	igt_subtest_with_dynamic("engine-error") {
+	snprintf(buff, sizeof(buff), "Per engine hang recovery (invalid CS, %s reset)", name);
+	igt_describe(buff);
+	snprintf(buff, sizeof(buff), "%s-engine-error", prefix);
+	igt_subtest_with_dynamic(buff) {
 		int has_gpu_reset = 0;
 		struct drm_i915_getparam gp = {
 			.param = I915_PARAM_HAS_GPU_RESET,
@@ -391,11 +379,46 @@ igt_main
 				test_engine_hang(ctx, e, IGT_SPIN_INVALID_CS);
 		}
 	}
+}
+
+igt_main
+{
+	const intel_ctx_t *ctx;
+	igt_hang_t hang = {};
+
+	igt_fixture {
+		device = drm_open_driver(DRIVER_INTEL);
+		igt_require_gem(device);
+
+		ctx = intel_ctx_create_all_physical(device);
+
+		hang = igt_allow_hang(device, ctx->id, HANG_ALLOW_CAPTURE);
+
+		sysfs = igt_sysfs_open(device);
+		igt_assert(sysfs != -1);
+
+		igt_require(has_error_state(sysfs));
+	}
+
+	igt_describe("Basic error capture");
+	igt_subtest("error-state-basic")
+		test_error_state_basic();
+
 
 	igt_describe("Check that executing unintialised memory causes a hang");
 	igt_subtest("hangcheck-unterminated")
 		hangcheck_unterminated(ctx);
 
+	do_tests("GT", "gt", ctx);
+
+	igt_fixture {
+		igt_disallow_hang(device, hang);
+
+		hang = igt_allow_hang(device, ctx->id, HANG_ALLOW_CAPTURE | HANG_WANT_ENGINE_RESET);
+	}
+
+	do_tests("engine", "engine", ctx);
+
 	igt_fixture {
 		igt_disallow_hang(device, hang);
 		intel_ctx_destroy(device, ctx);
--
2.25.1