Fixes for i915_hangman and gem_exec_capture

index 4c18c22db..b9c4d9983 100644
@@ -46,6 +46,8 @@
 static int device = -1;
 static int sysfs = -1;
 
+IGT_TEST_DESCRIPTION("Tests for hang detection and recovery");
+
 static bool has_error_state(int dir)
 {
 	bool result;

@@ -315,9 +317,9 @@ static void hangcheck_unterminated(void)
 
 	gem_execbuf(device, &execbuf);
 	if (gem_wait(device, handle, &timeout_ns) != 0) {
-		/* need to manually trigger an hang to clean before failing */
+		/* need to manually trigger a hang to clean before failing */
 		igt_force_gpu_reset(device);
-		igt_assert_f(0, "unterminated batch did not trigger an hang!");
+		igt_assert_f(0, "unterminated batch did not trigger a hang!\n");
 	}
 }
 

@@ -341,9 +343,11 @@ igt_main
 		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") {
 		for_each_ctx_engine(device, ctx, e) {
 			igt_dynamic_f("%s", e->name)

@@ -351,6 +355,7 @@ igt_main
 		}
 	}
 
+	igt_describe("Per engine hang recovery (spin)");
 	igt_subtest_with_dynamic("engine-hang") {
                 int has_gpu_reset = 0;
 		struct drm_i915_getparam gp = {

@@ -369,6 +374,7 @@ igt_main
 		}
 	}
 
+	igt_describe("Per engine hang recovery (invalid CS)");
 	igt_subtest_with_dynamic("engine-error") {
 		int has_gpu_reset = 0;
 		struct drm_i915_getparam gp = {

@@ -386,6 +392,7 @@ igt_main
 		}
 	}
 
+	igt_describe("Check that executing unintialised memory causes a hang");
 	igt_subtest("hangcheck-unterminated")
 		hangcheck_unterminated();
 

index 7c7df95ee..50da512f2 100644
@@ -122,12 +122,12 @@ static void eat_error_state(int dev)
  * to be done under hang injection.
  * Default: false
  */
-void igt_require_hang_ring(int fd, int ring)
+void igt_require_hang_ring(int fd, uint32_t ctx, int ring)
 {
 	if (!igt_check_boolean_env_var("IGT_HANG", true))
 		igt_skip("hang injection disabled by user [IGT_HANG=0]\n");
 
-	gem_require_ring(fd, ring);
+        igt_require(gem_context_has_engine(fd, ctx, ring));
 	gem_context_require_bannable(fd);
 	if (!igt_check_boolean_env_var("IGT_HANG_WITHOUT_RESET", false))
 		igt_require(has_gpu_reset(fd));

@@ -290,7 +290,7 @@ static igt_hang_t __igt_hang_ctx(int fd, uint64_t ahnd, uint32_t ctx, int ring,
 	igt_spin_t *spin;
 	unsigned ban;
 
-	igt_require_hang_ring(fd, ring);
+	igt_require_hang_ring(fd, ctx, ring);
 
 	/* check if non-default ctx submission is allowed */
 	igt_require(ctx == 0 || has_ctx_exec(fd, ring, ctx));

index c5059817b..3d10349e4 100644
@@ -31,7 +31,7 @@
 #include "i915/i915_drm_local.h"
 #include "i915_drm.h"
 
-void igt_require_hang_ring(int fd, int ring);
+void igt_require_hang_ring(int fd, uint32_t ctx, int ring);
 
 typedef struct igt_hang {
 	igt_spin_t *spin;

index b9c4d9983..f64b8819d 100644
@@ -295,7 +295,7 @@ test_engine_hang(const intel_ctx_t *ctx,
  * case and it takes a lot more time to wrap, so the acthd can potentially keep
  * increasing for a long time
  */
-static void hangcheck_unterminated(void)
+static void hangcheck_unterminated(const intel_ctx_t *ctx)
 {
 	/* timeout needs to be greater than ~5*hangcheck */
 	int64_t timeout_ns = 100ull * NSEC_PER_SEC; /* 100 seconds */

@@ -304,7 +304,7 @@ static void hangcheck_unterminated(void)
 	uint32_t handle;
 
 	igt_require(gem_uses_full_ppgtt(device));
-	igt_require_hang_ring(device, 0);
+	igt_require_hang_ring(device, ctx->id, 0);
 
 	handle = gem_create(device, 4096);
 

@@ -394,7 +394,7 @@ igt_main
 
 	igt_describe("Check that executing unintialised memory causes a hang");
 	igt_subtest("hangcheck-unterminated")
-		hangcheck_unterminated();
+		hangcheck_unterminated(ctx);
 
 	igt_fixture {
 		igt_disallow_hang(device, hang);

index f64b8819d..280eac197 100644
@@ -207,8 +207,8 @@ static void check_error_state(const char *expected_ring_name,
 	igt_assert(found);
 }
 
-static void test_error_state_capture(const intel_ctx_t *ctx, unsigned ring_id,
-				     const char *ring_name)
+static void test_error_state_capture(const intel_ctx_t *ctx,
+				     const struct intel_execution_engine2 *e)
 {
 	uint32_t *batch;
 	igt_hang_t hang;

@@ -217,7 +217,7 @@ static void test_error_state_capture(const intel_ctx_t *ctx, unsigned ring_id,
 
 	clear_error_state();
 
-	hang = igt_hang_ctx_with_ahnd(device, ahnd, ctx->id, ring_id,
+	hang = igt_hang_ctx_with_ahnd(device, ahnd, ctx->id, e->flags,
 				      HANG_ALLOW_CAPTURE);
 	offset = hang.spin->obj[IGT_SPIN_BATCH].offset;
 

@@ -226,7 +226,7 @@ static void test_error_state_capture(const intel_ctx_t *ctx, unsigned ring_id,
 
 	igt_post_hang_ring(device, hang);
 
-	check_error_state(ring_name, offset, batch);
+	check_error_state(e->name, offset, batch);
 	munmap(batch, 4096);
 	put_ahnd(ahnd);
 }

@@ -351,7 +351,7 @@ igt_main
 	igt_subtest_with_dynamic("error-state-capture") {
 		for_each_ctx_engine(device, ctx, e) {
 			igt_dynamic_f("%s", e->name)
-				test_error_state_capture(ctx, e->flags, e->name);
+				test_error_state_capture(ctx, e);
 		}
 	}
 

index 280eac197..7b8390a6c 100644
@@ -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);
-
-		igt_require(has_error_state(sysfs));
-	}
+	char buff[256];
 
-	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 +379,45 @@ 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);

index c247a1aa4..03cc38c93 100644
@@ -523,6 +523,13 @@ void igt_fork_hang_detector(int fd)
 
 void igt_stop_hang_detector(void)
 {
+	/*
+	 * Give the uevent time to arrive. No sleep at all misses about 20% of
+	 * hangs (at least, in the i915_hangman/detector test). A sleep of 1ms
+	 * seems to miss about 2%, 10ms loses <1%, so 100ms should be safe.
+	 */
+	usleep(100 * 1000);
+
 	igt_stop_helper(&hang_detector);
 }
 

61 lines not on this page · raw message

index 354769f39..6656b3fcd 100644
@@ -347,6 +347,7 @@ static void hangcheck_unterminated(const intel_ctx_t *ctx)
 	memset(&execbuf, 0, sizeof(execbuf));
 	execbuf.buffers_ptr = (uintptr_t)&gem_exec;
 	execbuf.buffer_count = 1;
+	execbuf.rsvd1 = ctx->id;
 
 	gem_execbuf(device, &execbuf);
 	if (gem_wait(device, handle, &timeout_ns) != 0) {

new file mode 100644
index 000000000..42c888b55
@@ -0,0 +1,96 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#include "i915/gem_create.h"
+#include "igt_core.h"
+#include "drmtest.h"
+#include "igt_store.h"
+#include "intel_chipset.h"
+#include "intel_reg.h"
+#include "ioctl_wrappers.h"
+#include "lib/intel_allocator.h"
+
+/**
+ * SECTION:igt_store_word
+ * @short_description: Library for writing a value to memory
+ * @title: StoreWord
+ * @include: igt.h
+ *
+ * A lot of igt testcases need some mechanism for writing a value to memory
+ * as a test that a batch buffer has executed.
+ *
+ * NB: Requires master for STORE_DWORD on gen4/5.
+ */
+void igt_store_word(int fd, uint64_t ahnd, const intel_ctx_t *ctx,
+		    const struct intel_execution_engine2 *e,
+		    int fence, uint32_t target_handle,
+		    uint64_t target_gpu_addr,
+		    uint64_t store_offset, uint32_t store_value)
+{
+	const int SCRATCH = 0;
+	const int BATCH = 1;
+	const unsigned int gen = intel_gen(intel_get_drm_devid(fd));
+	struct drm_i915_gem_exec_object2 obj[2];
+	struct drm_i915_gem_relocation_entry reloc;
+	struct drm_i915_gem_execbuffer2 execbuf;
+	uint32_t batch[16], delta;
+	uint64_t bb_offset;
+	int i;
+
+	memset(&execbuf, 0, sizeof(execbuf));
+	execbuf.buffers_ptr = to_user_pointer(obj);
+	execbuf.buffer_count = ARRAY_SIZE(obj);
+	execbuf.flags = e->flags;
+	execbuf.rsvd1 = ctx->id;
+	if (fence != -1) {
+		execbuf.flags |= I915_EXEC_FENCE_IN;
+		execbuf.rsvd2 = fence;
+	}
+	if (gen < 6)
+		execbuf.flags |= I915_EXEC_SECURE;
+
+	memset(obj, 0, sizeof(obj));
+	obj[SCRATCH].handle = target_handle;
+
+	obj[BATCH].handle = gem_create(fd, 4096);
+	obj[BATCH].relocs_ptr = to_user_pointer(&reloc);
+	obj[BATCH].relocation_count = !ahnd ? 1 : 0;
+	bb_offset = get_offset(ahnd, obj[BATCH].handle, 4096, 0);
+	memset(&reloc, 0, sizeof(reloc));
+
+	i = 0;
+	delta = sizeof(uint32_t) * store_offset;
+	if (!ahnd) {
+		reloc.target_handle = obj[SCRATCH].handle;
+		reloc.presumed_offset = -1;
+		reloc.offset = sizeof(uint32_t) * (i + 1);
+		reloc.delta = delta;
+		reloc.read_domains = I915_GEM_DOMAIN_INSTRUCTION;
+		reloc.write_domain = I915_GEM_DOMAIN_INSTRUCTION;
+	} else {
+		obj[SCRATCH].offset = target_gpu_addr;
+		obj[SCRATCH].flags |= EXEC_OBJECT_PINNED | EXEC_OBJECT_WRITE;
+		obj[BATCH].offset = bb_offset;
+		obj[BATCH].flags |= EXEC_OBJECT_PINNED;
+	}
+	batch[i] = MI_STORE_DWORD_IMM | (gen < 6 ? 1 << 22 : 0);
+	if (gen >= 8) {
+		batch[++i] = target_gpu_addr + delta;
+		batch[++i] = (target_gpu_addr + delta) >> 32;
+	} else if (gen >= 4) {
+		batch[++i] = 0;
+		batch[++i] = delta;
+		reloc.offset += sizeof(uint32_t);
+	} else {
+		batch[i]--;
+		batch[++i] = delta;
+	}
+	batch[++i] = store_value;
+	batch[++i] = MI_BATCH_BUFFER_END;
+	gem_write(fd, obj[BATCH].handle, 0, batch, sizeof(batch));
+	gem_execbuf(fd, &execbuf);
+	gem_close(fd, obj[BATCH].handle);
+	put_offset(ahnd, obj[BATCH].handle);
+}

new file mode 100644
index 000000000..5c6c8263c
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#include "igt_gt.h"
+
+void igt_store_word(int fd, uint64_t ahnd, const intel_ctx_t *ctx,
+		    const struct intel_execution_engine2 *e,
+		    int fence, uint32_t target_handle,
+		    uint64_t target_gpu_addr,
+		    uint64_t store_offset, uint32_t store_value);

98 lines not on this page · raw message

index 6656b3fcd..5a0c9497c 100644
@@ -36,6 +36,7 @@
 #include "i915/gem.h"
 #include "i915/gem_create.h"
 #include "igt.h"
+#include "igt_store.h"
 #include "igt_sysfs.h"
 #include "igt_debugfs.h"
 #include "sw_sync.h"

index 5a0c9497c..918418760 100644
@@ -48,8 +48,57 @@
 static int device = -1;
 static int sysfs = -1;
 
+#define OFFSET_ALIVE	10
+
 IGT_TEST_DESCRIPTION("Tests for hang detection and recovery");
 
+static void check_alive(void)
+{
+	const struct intel_execution_engine2 *engine;
+	const intel_ctx_t *ctx;
+	uint32_t scratch, *out;
+	int fd, i = 0;
+	uint64_t ahnd, scratch_addr;
+
+	fd = drm_open_driver(DRIVER_INTEL);
+	igt_require(gem_class_can_store_dword(fd, 0));
+
+	ctx = intel_ctx_create_all_physical(fd);
+	ahnd = get_reloc_ahnd(fd, ctx->id);
+	scratch = gem_create(fd, 4096);
+	scratch_addr = get_offset(ahnd, scratch, 4096, 0);
+	out = gem_mmap__wc(fd, scratch, 0, 4096, PROT_WRITE);
+	gem_set_domain(fd, scratch,
+			I915_GEM_DOMAIN_GTT, I915_GEM_DOMAIN_GTT);
+
+	for_each_physical_engine(fd, engine) {
+		igt_assert_eq_u32(out[i + OFFSET_ALIVE], 0);
+		i++;
+	}
+
+	i = 0;
+	for_each_ctx_engine(fd, ctx, engine) {
+		if (!gem_class_can_store_dword(fd, engine->class))
+			continue;
+
+		/* +OFFSET_ALIVE to ensure engine zero doesn't get a false negative */
+		igt_store_word(fd, ahnd, ctx, engine, -1, scratch, scratch_addr,
+			       i + OFFSET_ALIVE, i + OFFSET_ALIVE);
+		i++;
+	}
+
+	gem_set_domain(fd, scratch, I915_GEM_DOMAIN_GTT, 0);
+
+	while (i--)
+		igt_assert_eq_u32(out[i + OFFSET_ALIVE], i + OFFSET_ALIVE);
+
+	munmap(out, 4096);
+	gem_close(fd, scratch);
+	put_ahnd(ahnd);
+	intel_ctx_destroy(fd, ctx);
+	close(fd);
+}
+
 static bool has_error_state(int dir)
 {
 	bool result;

@@ -231,6 +280,8 @@ static void test_error_state_capture(const intel_ctx_t *ctx,
 	check_error_state(e->name, offset, batch);
 	munmap(batch, 4096);
 	put_ahnd(ahnd);
+
+	check_alive();
 }
 
 static void

@@ -289,6 +340,8 @@ test_engine_hang(const intel_ctx_t *ctx,
 		put_ahnd(ahndN);
 	}
 	put_ahnd(ahnd);
+
+	check_alive();
 }
 
 static int hang_count;

@@ -321,6 +374,8 @@ static void test_hang_detector(const intel_ctx_t *ctx,
 
 	/* Did it work? */
 	igt_assert(hang_count == 1);
+
+	check_alive();
 }
 
 /* This test covers the case where we end up in an uninitialised area of the

@@ -356,6 +411,8 @@ static void hangcheck_unterminated(const intel_ctx_t *ctx)
 		igt_force_gpu_reset(device);
 		igt_assert_f(0, "unterminated batch did not trigger a hang!\n");
 	}
+
+	check_alive();
 }
 
 static void do_tests(const char *name, const char *prefix,

@@ -433,6 +490,8 @@ igt_main
 		igt_assert(sysfs != -1);
 
 		igt_require(has_error_state(sysfs));
+
+		gem_require_mmap_wc(device);
 	}
 
 	igt_describe("Basic error capture");

index 918418760..6601db5f6 100644
@@ -289,27 +289,29 @@ test_engine_hang(const intel_ctx_t *ctx,
 		 const struct intel_execution_engine2 *e, unsigned int flags)
 {
 	const struct intel_execution_engine2 *other;
-	const intel_ctx_t *tmp_ctx;
+	const intel_ctx_t *local_ctx[GEM_MAX_ENGINES];
 	igt_spin_t *spin, *next;
 	IGT_LIST_HEAD(list);
 	uint64_t ahnd = get_reloc_ahnd(device, ctx->id), ahndN;
+	int num_ctx;
 
 	igt_skip_on(flags & IGT_SPIN_INVALID_CS &&
 		    gem_engine_has_cmdparser(device, &ctx->cfg, e->flags));
 
 	/* Fill all the other engines with background load */
+	num_ctx = 0;
 	for_each_ctx_engine(device, ctx, other) {
 		if (other->flags == e->flags)
 			continue;
 
-		tmp_ctx = intel_ctx_create(device, &ctx->cfg);
-		ahndN = get_reloc_ahnd(device, tmp_ctx->id);
+		local_ctx[num_ctx] = intel_ctx_create(device, &ctx->cfg);
+		ahndN = get_reloc_ahnd(device, local_ctx[num_ctx]->id);
 		spin = __igt_spin_new(device,
 				      .ahnd = ahndN,
-				      .ctx = tmp_ctx,
+				      .ctx = local_ctx[num_ctx],
 				      .engine = other->flags,
 				      .flags = IGT_SPIN_FENCE_OUT);
-		intel_ctx_destroy(device, tmp_ctx);
+		num_ctx++;
 
 		igt_list_move(&spin->link, &list);
 	}

@@ -339,7 +341,10 @@ test_engine_hang(const intel_ctx_t *ctx,
 		igt_spin_free(device, spin);
 		put_ahnd(ahndN);
 	}
+
 	put_ahnd(ahnd);
+	while (num_ctx)
+		intel_ctx_destroy(device, local_ctx[--num_ctx]);
 
 	check_alive();
 }

index 6601db5f6..9f7f8062c 100644
@@ -298,12 +298,14 @@ test_engine_hang(const intel_ctx_t *ctx,
 	igt_skip_on(flags & IGT_SPIN_INVALID_CS &&
 		    gem_engine_has_cmdparser(device, &ctx->cfg, e->flags));
 
-	/* Fill all the other engines with background load */
+	/*
+	 * Fill all engines with background load.
+	 * This verifies that independent engines are unaffected and gives
+	 * the target engine something to switch between so it notices the
+	 * hang.
+	 */
 	num_ctx = 0;
 	for_each_ctx_engine(device, ctx, other) {
-		if (other->flags == e->flags)
-			continue;
-
 		local_ctx[num_ctx] = intel_ctx_create(device, &ctx->cfg);
 		ahndN = get_reloc_ahnd(device, local_ctx[num_ctx]->id);
 		spin = __igt_spin_new(device,

index 9f7f8062c..567eb71ee 100644
@@ -284,6 +284,21 @@ static void test_error_state_capture(const intel_ctx_t *ctx,
 	check_alive();
 }
 
+static void context_unban(int fd, unsigned ctx)
+{
+	struct drm_i915_gem_context_param param = {
+		.ctx_id = ctx,
+		.param = I915_CONTEXT_PARAM_BANNABLE,
+		.value = 0,
+	};
+
+	if(__gem_context_set_param(fd, &param) == -EINVAL) {
+		igt_assert_eq(param.value, 0);
+		param.param = I915_CONTEXT_PARAM_BAN_PERIOD;
+		gem_context_set_param(fd, &param);
+	}
+}
+
 static void
 test_engine_hang(const intel_ctx_t *ctx,
 		 const struct intel_execution_engine2 *e, unsigned int flags)

@@ -307,6 +322,7 @@ test_engine_hang(const intel_ctx_t *ctx,
 	num_ctx = 0;
 	for_each_ctx_engine(device, ctx, other) {
 		local_ctx[num_ctx] = intel_ctx_create(device, &ctx->cfg);
+		context_unban(device, local_ctx[num_ctx]->id);
 		ahndN = get_reloc_ahnd(device, local_ctx[num_ctx]->id);
 		spin = __igt_spin_new(device,
 				      .ahnd = ahndN,

index 196236b27..5e45d0518 100644
@@ -3139,7 +3139,7 @@ igt_main
 			igt_hang_t hang;
 
 			igt_fixture {
-				hang = igt_allow_hang(i915, 0, 0);
+				hang = igt_allow_hang(i915, ctx->id, 0);
 				intel_allocator_multiprocess_start();
 			}
 

index 729f42b0a..3f6a861d3 100644
@@ -488,6 +488,45 @@ int gem_engine_property_printf(int i915, const char *engine, const char *attr,
 	return ret;
 }
 
+/* Ensure fast hang detection */
+void gem_engine_properties_configure(int fd, struct gem_engine_properties *params)
+{
+	int ret;
+	struct gem_engine_properties write = *params;
+
+	ret = gem_engine_property_scanf(fd, write.engine->name,
+					"preempt_timeout_ms",
+					"%d", &params->preempt_timeout);
+	igt_assert_eq(ret, 1);
+	ret = gem_engine_property_scanf(fd, write.engine->name,
+					"heartbeat_interval_ms",
+					"%d", &params->heartbeat_interval);
+	igt_assert_eq(ret, 1);
+
+	ret = gem_engine_property_printf(fd, write.engine->name,
+					 "preempt_timeout_ms", "%d",
+					 write.preempt_timeout);
+	igt_assert_lt(0, ret);
+	ret = gem_engine_property_printf(fd, write.engine->name,
+					 "heartbeat_interval_ms", "%d",
+					 write.heartbeat_interval);
+	igt_assert_lt(0, ret);
+}
+
+void gem_engine_properties_restore(int fd, const struct gem_engine_properties *saved)
+{
+	int ret;
+
+	ret = gem_engine_property_printf(fd, saved->engine->name,
+					 "preempt_timeout_ms", "%d",
+					 saved->preempt_timeout);
+	igt_assert_lt(0, ret);
+	ret = gem_engine_property_printf(fd, saved->engine->name,
+					 "heartbeat_interval_ms", "%d",
+					 saved->heartbeat_interval);
+	igt_assert_lt(0, ret);
+}
+
 uint32_t gem_engine_mmio_base(int i915, const char *engine)
 {
 	unsigned int mmio = 0;

index 4cfab560b..b413aa8ab 100644
@@ -115,6 +115,15 @@ struct intel_execution_engine2 gem_eb_flags_to_engine(unsigned int flags);
 	     ((e__) = intel_get_current_physical_engine(&i__##e__)); \
 	     intel_next_engine(&i__##e__))
 
+struct gem_engine_properties {
+	const struct intel_execution_engine2 *engine;
+	int preempt_timeout;
+	int heartbeat_interval;
+};
+
+void gem_engine_properties_configure(int fd, struct gem_engine_properties *params);
+void gem_engine_properties_restore(int fd, const struct gem_engine_properties *saved);
+
 __attribute__((format(scanf, 4, 5)))
 int gem_engine_property_scanf(int i915, const char *engine, const char *attr,
 			      const char *fmt, ...);

index 567eb71ee..1a2b2cf7a 100644
@@ -500,8 +500,12 @@ igt_main
 {
 	const intel_ctx_t *ctx;
 	igt_hang_t hang = {};
+	struct gem_engine_properties saved_params[GEM_MAX_ENGINES];
+	int num_engines = 0;
 
 	igt_fixture {
+		const struct intel_execution_engine2 *e;
+
 		device = drm_open_driver(DRIVER_INTEL);
 		igt_require_gem(device);
 

@@ -515,6 +519,13 @@ igt_main
 		igt_require(has_error_state(sysfs));
 
 		gem_require_mmap_wc(device);
+
+		for_each_physical_engine(device, e) {
+			saved_params[num_engines].engine = e;
+			saved_params[num_engines].preempt_timeout = 500;
+			saved_params[num_engines].heartbeat_interval = 1000;
+			gem_engine_properties_configure(device, saved_params + num_engines++);
+		}
 	}
 
 	igt_describe("Basic error capture");

@@ -546,6 +557,11 @@ igt_main
 	do_tests("engine", "engine", ctx);
 
 	igt_fixture {
+		int i;
+
+		for (i = 0; i < num_engines; i++)
+			gem_engine_properties_restore(device, saved_params + i);
+
 		igt_disallow_hang(device, hang);
 		intel_ctx_destroy(device, ctx);
 		close(device);

index 9beb36fc7..51db07c41 100644
@@ -209,14 +209,21 @@ static int check_error_state(int dir, struct offset *obj_offsets, int obj_count,
 	return blobs;
 }
 
-static void configure_hangs(int fd, const struct intel_execution_engine2 *e, int ctxt_id)
+static struct gem_engine_properties
+configure_hangs(int fd, const struct intel_execution_engine2 *e, int ctxt_id)
 {
+	struct gem_engine_properties props;
+
 	/* Ensure fast hang detection */
-	gem_engine_property_printf(fd, e->name, "preempt_timeout_ms", "%d", 250);
-	gem_engine_property_printf(fd, e->name, "heartbeat_interval_ms", "%d", 500);
+	props.engine = e;
+	props.preempt_timeout = 250;
+	props.heartbeat_interval = 500;
+	gem_engine_properties_configure(fd, &props);
 
 	/* Allow engine based resets and disable banning */
 	igt_allow_hang(fd, ctxt_id, HANG_ALLOW_CAPTURE | HANG_WANT_ENGINE_RESET);
+
+	return props;
 }
 
 static bool fence_busy(int fence)

@@ -256,8 +263,9 @@ static void __capture1(int fd, int dir, uint64_t ahnd, const intel_ctx_t *ctx,
 	uint32_t *batch, *seqno;
 	struct offset offset;
 	int i, fence_out;
+	struct gem_engine_properties saved_engine;
 
-	configure_hangs(fd, e, ctx->id);
+	saved_engine = configure_hangs(fd, e, ctx->id);
 
 	memset(obj, 0, sizeof(obj));
 	obj[SCRATCH].handle = gem_create_in_memory_regions(fd, 4096, region);

@@ -371,6 +379,8 @@ static void __capture1(int fd, int dir, uint64_t ahnd, const intel_ctx_t *ctx,
 	gem_close(fd, obj[BATCH].handle);
 	gem_close(fd, obj[NOCAPTURE].handle);
 	gem_close(fd, obj[SCRATCH].handle);
+
+	gem_engine_properties_restore(fd, &saved_engine);
 }
 
 static void capture(int fd, int dir, const intel_ctx_t *ctx,

@@ -417,8 +427,9 @@ __captureN(int fd, int dir, uint64_t ahnd, const intel_ctx_t *ctx,
 	uint32_t *batch, *seqno;
 	struct offset *offsets;
 	int i, fence_out;
+	struct gem_engine_properties saved_engine;
 
-	configure_hangs(fd, e, ctx->id);
+	saved_engine = configure_hangs(fd, e, ctx->id);
 
 	offsets = calloc(count, sizeof(*offsets));
 	igt_assert(offsets);

@@ -559,10 +570,12 @@ __captureN(int fd, int dir, uint64_t ahnd, const intel_ctx_t *ctx,
 
 	qsort(offsets, count, sizeof(*offsets), cmp);
 	igt_assert(offsets[0].addr <= offsets[count-1].addr);
+
+	gem_engine_properties_restore(fd, &saved_engine);
 	return offsets;
 }
 
-#define find_first_available_engine(fd, ctx, e) \
+#define find_first_available_engine(fd, ctx, e, saved) \
 	do { \
 		ctx = intel_ctx_create_all_physical(fd); \
 		igt_assert(ctx); \

@@ -570,7 +583,7 @@ __captureN(int fd, int dir, uint64_t ahnd, const intel_ctx_t *ctx,
 			for_each_if(gem_class_can_store_dword(fd, e->class)) \
 				break; \
 		igt_assert(e); \
-		configure_hangs(fd, e, ctx->id); \
+		saved = configure_hangs(fd, e, ctx->id); \
 	} while(0)
 
 static void many(int fd, int dir, uint64_t size, unsigned int flags)

@@ -580,8 +593,9 @@ static void many(int fd, int dir, uint64_t size, unsigned int flags)
 	uint64_t ram, gtt, ahnd;
 	unsigned long count, blobs;
 	struct offset *offsets;
+	struct gem_engine_properties saved_engine;
 
-	find_first_available_engine(fd, ctx, e);
+	find_first_available_engine(fd, ctx, e, saved_engine);
 
 	gtt = gem_aperture_size(fd) / size;
 	ram = (intel_get_avail_ram_mb() << 20) / size;

@@ -602,6 +616,8 @@ static void many(int fd, int dir, uint64_t size, unsigned int flags)
 
 	free(offsets);
 	put_ahnd(ahnd);
+
+	gem_engine_properties_restore(fd, &saved_engine);
 }
 
 static void prioinv(int fd, int dir, const intel_ctx_t *ctx,

@@ -697,8 +713,9 @@ static void userptr(int fd, int dir)
 	void *ptr;
 	int obj_size = 4096;
 	uint32_t system_region = INTEL_MEMORY_REGION_ID(I915_SYSTEM_MEMORY, 0);
+	struct gem_engine_properties saved_engine;
 
-	find_first_available_engine(fd, ctx, e);
+	find_first_available_engine(fd, ctx, e, saved_engine);
 
 	igt_assert(posix_memalign(&ptr, obj_size, obj_size) == 0);
 	memset(ptr, 0, obj_size);

@@ -710,6 +727,8 @@ static void userptr(int fd, int dir)
 	gem_close(fd, handle);
 	put_ahnd(ahnd);
 	free(ptr);
+
+	gem_engine_properties_restore(fd, &saved_engine);
 }
 
 static bool has_capture(int fd)