[Intel-gfx] [RFC i-g-t] 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

Cc: Mika Kuoppala <mika.kuoppala at linux.intel.com>
Cc: Arun Siluvery <arun.siluvery at linux.intel.com>
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio at intel.com>
---
 tests/drv_hangman.c | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 52 insertions(+)

diff --git a/tests/drv_hangman.c b/tests/drv_hangman.c
index 8a465cf..353e7a8 100644
--- a/tests/drv_hangman.c
+++ b/tests/drv_hangman.c
@@ -288,6 +288,55 @@ 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 at an offset greater than the one where the last buffer is mapped. 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
+ */
+static void ppgtt_walking(void)
+{
+	int fd;
+	unsigned timeout = 100;
+	struct drm_i915_gem_execbuffer2 execbuf;
+	struct drm_i915_gem_exec_object2 gem_exec;
+	uint32_t handle;
+	uint32_t batch[4];
+
+	fd = drm_open_driver(DRIVER_INTEL);
+	igt_require(gem_gtt_type(fd) > 2);
+
+	/* the batch will be mapped to an offset < 4GB because the flag to allow
+	 * 48b offsets is not specified, so jump to address 0x00000001 00000000
+	 */
+	batch[0] = MI_BATCH_BUFFER_START | 1;
+	batch[1] = 0;
+	batch[2] = 1;
+	batch[3] = MI_BATCH_BUFFER_END;
+
+	handle = gem_create(fd, 4096);
+	gem_write(fd, handle, 0, batch, sizeof(batch));
+
+	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);
+
+	while (gem_bo_busy(fd, handle) && timeout > 0) {
+		igt_debug("decreasing timeout to %u\n", --timeout);
+		sleep(1);
+	}
+
+	gem_close(fd, handle);
+	close(fd);
+	igt_assert(timeout > 0);
+}
+
 igt_main
 {
 	const struct intel_execution_engine *e;
@@ -314,4 +363,7 @@ igt_main
 			test_error_state_capture(e->exec_id | e->flags,
 						 e->full_name);
 	}
+
+	igt_subtest("ppgtt-walking")
+		ppgtt_walking();
 }
-- 
1.9.1