[Intel-gfx] [PATCH i-g-t v4 2/2] tests/drv_hangman: test for acthd increasing through invalid VM space

[daniele.ceraolospurio at intel.com]

From: Daniele Ceraolo Spurio <daniele.ceraolospurio at intel.com>

The hangcheck logic will not flag an hang if acthd keeps increasing.
However, if a malformed batch jumps to an invalid offset in the ppgtt it
can potentially continue executing through the whole address space
without triggering the hangcheck mechanism.

This patch adds a test to simulate the issue. I've kept the test running
for more than 10 minutes before killing it on a BDW and no hang occurred.
I've sampled i915_hangcheck_info a few times during the run and got the
following:

Hangcheck active, fires in 468ms
render ring:
	seqno = fffff55e [current fffff55e]
	ACTHD = 0x47df685ecc [current 0x4926b81d90]
	max ACTHD = 0x47df685ecc
	score = 0
	action = 2
	instdone read = 0xffd7ffff 0xffffffff 0xffffffff 0xffffffff
	instdone accu = 0x00000000 0x00000000 0x00000000 0x00000000

Hangcheck active, fires in 424ms
render ring:
	seqno = fffff55e [current fffff55e]
	ACTHD = 0x6c953d3a34 [current 0x6de5e76fa4]
	max ACTHD = 0x6c953d3a34
	score = 0
	action = 2
	instdone read = 0xffd7ffff 0xffffffff 0xffffffff 0xffffffff
	instdone accu = 0x00000000 0x00000000 0x00000000 0x00000000

Hangcheck active, fires in 1692ms
render ring:
	seqno = fffff55e [current fffff55e]
	ACTHD = 0x1f49b0366dc [current 0x1f4dcbd88ec]
	max ACTHD = 0x1f49b0366dc
	score = 0
	action = 2
	instdone read = 0xffd7ffff 0xffffffff 0xffffffff 0xffffffff
	instdone accu = 0x00000000 0x00000000 0x00000000 0x00000000

v2: use the new gem_wait() function (Chris)

v3: switch to unterminated batch and rename test, remove redundant
    check, update test requirements (Chris), update top comment

v4: force gpu reset if the hang detection fails (Mika)

Cc: Mika Kuoppala <mika.kuoppala at linux.intel.com>
Cc: Arun Siluvery <arun.siluvery at linux.intel.com>
Cc: Chris Wilson <chris at chris-wilson.co.uk>
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio at intel.com>
---
 tests/drv_hangman.c | 44 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/tests/drv_hangman.c b/tests/drv_hangman.c
index a4f187a..a1a3faa 100644
--- a/tests/drv_hangman.c
+++ b/tests/drv_hangman.c
@@ -284,6 +284,47 @@ static void test_error_state_capture(unsigned ring_id,
 	check_error_state(gen, cmd_parser, ring_name, offset);
 }
 
+
+/* This test covers the case where we end up in an uninitialised area of the
+ * ppgtt and keep executing through it. This is particularly relevant if 48b
+ * ppgtt is enabled because the ppgtt is massively bigger compared to the 32b
+ * case and it takes a lot more time to wrap, so the acthd can potentially keep
+ * increasing for a long time
+ */
+#define NSEC_PER_SEC	1000000000L
+static void hangcheck_unterminated(void)
+{
+	int fd;
+	/* timeout needs to be greater than ~5*hangcheck */
+	int64_t timeout_ns = 100 * NSEC_PER_SEC; /* 100 seconds */
+	struct drm_i915_gem_execbuffer2 execbuf;
+	struct drm_i915_gem_exec_object2 gem_exec;
+	uint32_t handle;
+
+	fd = drm_open_driver(DRIVER_INTEL);
+	igt_require(gem_uses_full_ppgtt(fd));
+	igt_require_hang_ring(fd, 0);
+
+	handle = gem_create(fd, 4096);
+
+	memset(&gem_exec, 0, sizeof(gem_exec));
+	gem_exec.handle = handle;
+
+	memset(&execbuf, 0, sizeof(execbuf));
+	execbuf.buffers_ptr = (uintptr_t)&gem_exec;
+	execbuf.buffer_count = 1;
+	execbuf.batch_len = 8;
+
+	gem_execbuf(fd, &execbuf);
+	if (gem_wait(fd, handle, &timeout_ns) != 0) {
+		/* need to manually trigger an hang to clean before failing */
+		igt_force_gpu_reset();
+		igt_assert_f(0, "unterminated batch did not trigger an hang!");
+	}
+
+	close(fd);
+}
+
 igt_main
 {
 	const struct intel_execution_engine *e;
@@ -310,4 +351,7 @@ igt_main
 			test_error_state_capture(e->exec_id | e->flags,
 						 e->full_name);
 	}
+
+	igt_subtest("hangcheck-unterminated")
+		hangcheck_unterminated();
 }
-- 
1.9.1