1 files changed, 327 insertions, 149 deletions

diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
index 853246fad05f..4f252f704975 100644
--- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
@@ -6,7 +6,9 @@
 #include <linux/kthread.h>
 
 #include "gem/i915_gem_context.h"
+#include "gem/i915_gem_internal.h"
 
+#include "i915_gem_evict.h"
 #include "intel_gt.h"
 #include "intel_engine_heartbeat.h"
 #include "intel_engine_pm.h"
@@ -17,6 +19,8 @@
 #include "selftests/igt_flush_test.h"
 #include "selftests/igt_reset.h"
 #include "selftests/igt_atomic.h"
+#include "selftests/igt_spinner.h"
+#include "selftests/intel_scheduler_helpers.h"
 
 #include "selftests/mock_drm.h"
 
@@ -42,7 +46,7 @@ static int hang_init(struct hang *h, struct intel_gt *gt)
 	memset(h, 0, sizeof(*h));
 	h->gt = gt;
 
-	h->ctx = kernel_context(gt->i915);
+	h->ctx = kernel_context(gt->i915, NULL);
 	if (IS_ERR(h->ctx))
 		return PTR_ERR(h->ctx);
 
@@ -69,7 +73,7 @@ static int hang_init(struct hang *h, struct intel_gt *gt)
 	h->seqno = memset(vaddr, 0xff, PAGE_SIZE);
 
 	vaddr = i915_gem_object_pin_map_unlocked(h->obj,
-						 i915_coherent_map_type(gt->i915, h->obj, false));
+						 intel_gt_coherent_map_type(gt, h->obj, false));
 	if (IS_ERR(vaddr)) {
 		err = PTR_ERR(vaddr);
 		goto err_unpin_hws;
@@ -92,30 +96,15 @@ err_ctx:
 static u64 hws_address(const struct i915_vma *hws,
 		       const struct i915_request *rq)
 {
-	return hws->node.start + offset_in_page(sizeof(u32)*rq->fence.context);
-}
-
-static int move_to_active(struct i915_vma *vma,
-			  struct i915_request *rq,
-			  unsigned int flags)
-{
-	int err;
-
-	i915_vma_lock(vma);
-	err = i915_request_await_object(rq, vma->obj,
-					flags & EXEC_OBJECT_WRITE);
-	if (err == 0)
-		err = i915_vma_move_to_active(vma, rq, flags);
-	i915_vma_unlock(vma);
-
-	return err;
+	return i915_vma_offset(hws) +
+	       offset_in_page(sizeof(u32) * rq->fence.context);
 }
 
 static struct i915_request *
 hang_create_request(struct hang *h, struct intel_engine_cs *engine)
 {
 	struct intel_gt *gt = h->gt;
-	struct i915_address_space *vm = i915_gem_context_get_vm_rcu(h->ctx);
+	struct i915_address_space *vm = i915_gem_context_get_eb_vm(h->ctx);
 	struct drm_i915_gem_object *obj;
 	struct i915_request *rq = NULL;
 	struct i915_vma *hws, *vma;
@@ -130,7 +119,7 @@ hang_create_request(struct hang *h, struct intel_engine_cs *engine)
 		return ERR_CAST(obj);
 	}
 
-	vaddr = i915_gem_object_pin_map_unlocked(obj, i915_coherent_map_type(gt->i915, obj, false));
+	vaddr = i915_gem_object_pin_map_unlocked(obj, intel_gt_coherent_map_type(gt, obj, false));
 	if (IS_ERR(vaddr)) {
 		i915_gem_object_put(obj);
 		i915_vm_put(vm);
@@ -171,11 +160,11 @@ hang_create_request(struct hang *h, struct intel_engine_cs *engine)
 		goto unpin_hws;
 	}
 
-	err = move_to_active(vma, rq, 0);
+	err = igt_vma_move_to_active_unlocked(vma, rq, 0);
 	if (err)
 		goto cancel_rq;
 
-	err = move_to_active(hws, rq, 0);
+	err = igt_vma_move_to_active_unlocked(hws, rq, 0);
 	if (err)
 		goto cancel_rq;
 
@@ -192,8 +181,8 @@ hang_create_request(struct hang *h, struct intel_engine_cs *engine)
 
 		*batch++ = MI_NOOP;
 		*batch++ = MI_BATCH_BUFFER_START | 1 << 8 | 1;
-		*batch++ = lower_32_bits(vma->node.start);
-		*batch++ = upper_32_bits(vma->node.start);
+		*batch++ = lower_32_bits(i915_vma_offset(vma));
+		*batch++ = upper_32_bits(i915_vma_offset(vma));
 	} else if (GRAPHICS_VER(gt->i915) >= 6) {
 		*batch++ = MI_STORE_DWORD_IMM_GEN4;
 		*batch++ = 0;
@@ -206,7 +195,7 @@ hang_create_request(struct hang *h, struct intel_engine_cs *engine)
 
 		*batch++ = MI_NOOP;
 		*batch++ = MI_BATCH_BUFFER_START | 1 << 8;
-		*batch++ = lower_32_bits(vma->node.start);
+		*batch++ = lower_32_bits(i915_vma_offset(vma));
 	} else if (GRAPHICS_VER(gt->i915) >= 4) {
 		*batch++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
 		*batch++ = 0;
@@ -219,7 +208,7 @@ hang_create_request(struct hang *h, struct intel_engine_cs *engine)
 
 		*batch++ = MI_NOOP;
 		*batch++ = MI_BATCH_BUFFER_START | 2 << 6;
-		*batch++ = lower_32_bits(vma->node.start);
+		*batch++ = lower_32_bits(i915_vma_offset(vma));
 	} else {
 		*batch++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
 		*batch++ = lower_32_bits(hws_address(hws, rq));
@@ -231,7 +220,7 @@ hang_create_request(struct hang *h, struct intel_engine_cs *engine)
 
 		*batch++ = MI_NOOP;
 		*batch++ = MI_BATCH_BUFFER_START | 2 << 6;
-		*batch++ = lower_32_bits(vma->node.start);
+		*batch++ = lower_32_bits(i915_vma_offset(vma));
 	}
 	*batch++ = MI_BATCH_BUFFER_END; /* not reached */
 	intel_gt_chipset_flush(engine->gt);
@@ -246,7 +235,7 @@ hang_create_request(struct hang *h, struct intel_engine_cs *engine)
 	if (GRAPHICS_VER(gt->i915) <= 5)
 		flags |= I915_DISPATCH_SECURE;
 
-	err = rq->engine->emit_bb_start(rq, vma->node.start, PAGE_SIZE, flags);
+	err = rq->engine->emit_bb_start(rq, i915_vma_offset(vma), PAGE_SIZE, flags);
 
 cancel_rq:
 	if (err) {
@@ -330,7 +319,7 @@ static int igt_hang_sanitycheck(void *arg)
 		i915_request_add(rq);
 
 		timeout = 0;
-		intel_wedge_on_timeout(&w, gt, HZ / 10 /* 100ms */)
+		intel_wedge_on_timeout(&w, gt, HZ / 5 /* 200ms */)
 			timeout = i915_request_wait(rq, 0,
 						    MAX_SCHEDULE_TIMEOUT);
 		if (intel_gt_is_wedged(gt))
@@ -378,6 +367,7 @@ static int igt_reset_nop(void *arg)
 			ce = intel_context_create(engine);
 			if (IS_ERR(ce)) {
 				err = PTR_ERR(ce);
+				pr_err("[%s] Create context failed: %d!\n", engine->name, err);
 				break;
 			}
 
@@ -387,6 +377,8 @@ static int igt_reset_nop(void *arg)
 				rq = intel_context_create_request(ce);
 				if (IS_ERR(rq)) {
 					err = PTR_ERR(rq);
+					pr_err("[%s] Create request failed: %d!\n",
+					       engine->name, err);
 					break;
 				}
 
@@ -401,24 +393,31 @@ static int igt_reset_nop(void *arg)
 		igt_global_reset_unlock(gt);
 
 		if (intel_gt_is_wedged(gt)) {
+			pr_err("[%s] GT is wedged!\n", engine->name);
 			err = -EIO;
 			break;
 		}
 
 		if (i915_reset_count(global) != reset_count + ++count) {
-			pr_err("Full GPU reset not recorded!\n");
+			pr_err("[%s] Reset not recorded: %d vs %d + %d!\n",
+			       engine->name, i915_reset_count(global), reset_count, count);
 			err = -EINVAL;
 			break;
 		}
 
 		err = igt_flush_test(gt->i915);
-		if (err)
+		if (err) {
+			pr_err("[%s] Flush failed: %d!\n", engine->name, err);
 			break;
+		}
 	} while (time_before(jiffies, end_time));
 	pr_info("%s: %d resets\n", __func__, count);
 
-	if (igt_flush_test(gt->i915))
+	if (igt_flush_test(gt->i915)) {
+		pr_err("Post flush failed: %d!\n", err);
 		err = -EIO;
+	}
+
 	return err;
 }
 
@@ -440,16 +439,27 @@ static int igt_reset_nop_engine(void *arg)
 		IGT_TIMEOUT(end_time);
 		int err;
 
+		if (intel_engine_uses_guc(engine)) {
+			/* Engine level resets are triggered by GuC when a hang
+			 * is detected. They can't be triggered by the KMD any
+			 * more. Thus a nop batch cannot be used as a reset test
+			 */
+			continue;
+		}
+
 		ce = intel_context_create(engine);
-		if (IS_ERR(ce))
+		if (IS_ERR(ce)) {
+			pr_err("[%s] Create context failed: %pe!\n", engine->name, ce);
 			return PTR_ERR(ce);
+		}
 
 		reset_count = i915_reset_count(global);
 		reset_engine_count = i915_reset_engine_count(global, engine);
 		count = 0;
 
 		st_engine_heartbeat_disable(engine);
-		set_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
+		GEM_BUG_ON(test_and_set_bit(I915_RESET_ENGINE + id,
+					    &gt->reset.flags));
 		do {
 			int i;
 
@@ -506,7 +516,7 @@ static int igt_reset_nop_engine(void *arg)
 				break;
 			}
 		} while (time_before(jiffies, end_time));
-		clear_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
+		clear_and_wake_up_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 		st_engine_heartbeat_enable(engine);
 
 		pr_info("%s(%s): %d resets\n", __func__, engine->name, count);
@@ -538,7 +548,7 @@ static int igt_reset_fail_engine(void *arg)
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
-	/* Check that we can recover from engine-reset failues */
+	/* Check that we can recover from engine-reset failures */
 
 	if (!intel_has_reset_engine(gt))
 		return 0;
@@ -549,12 +559,19 @@ static int igt_reset_fail_engine(void *arg)
 		IGT_TIMEOUT(end_time);
 		int err;
 
+		/* Can't manually break the reset if i915 doesn't perform it */
+		if (intel_engine_uses_guc(engine))
+			continue;
+
 		ce = intel_context_create(engine);
-		if (IS_ERR(ce))
+		if (IS_ERR(ce)) {
+			pr_err("[%s] Create context failed: %pe!\n", engine->name, ce);
 			return PTR_ERR(ce);
+		}
 
 		st_engine_heartbeat_disable(engine);
-		set_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
+		GEM_BUG_ON(test_and_set_bit(I915_RESET_ENGINE + id,
+					    &gt->reset.flags));
 
 		force_reset_timeout(engine);
 		err = intel_engine_reset(engine, NULL);
@@ -651,7 +668,7 @@ static int igt_reset_fail_engine(void *arg)
 out:
 		pr_info("%s(%s): %d resets\n", __func__, engine->name, count);
 skip:
-		clear_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
+		clear_and_wake_up_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 		st_engine_heartbeat_enable(engine);
 		intel_context_put(ce);
 
@@ -686,8 +703,12 @@ static int __igt_reset_engine(struct intel_gt *gt, bool active)
 	for_each_engine(engine, gt, id) {
 		unsigned int reset_count, reset_engine_count;
 		unsigned long count;
+		bool using_guc = intel_engine_uses_guc(engine);
 		IGT_TIMEOUT(end_time);
 
+		if (using_guc && !active)
+			continue;
+
 		if (active && !intel_engine_can_store_dword(engine))
 			continue;
 
@@ -702,16 +723,28 @@ static int __igt_reset_engine(struct intel_gt *gt, bool active)
 		reset_engine_count = i915_reset_engine_count(global, engine);
 
 		st_engine_heartbeat_disable(engine);
-		set_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
+		GEM_BUG_ON(test_and_set_bit(I915_RESET_ENGINE + id,
+					    &gt->reset.flags));
 		count = 0;
 		do {
-			if (active) {
-				struct i915_request *rq;
+			struct i915_request *rq = NULL;
+			struct intel_selftest_saved_policy saved;
+			int err2;
+
+			err = intel_selftest_modify_policy(engine, &saved,
+							   SELFTEST_SCHEDULER_MODIFY_FAST_RESET);
+			if (err) {
+				pr_err("[%s] Modify policy failed: %d!\n", engine->name, err);
+				break;
+			}
 
+			if (active) {
 				rq = hang_create_request(&h, engine);
 				if (IS_ERR(rq)) {
 					err = PTR_ERR(rq);
-					break;
+					pr_err("[%s] Create hang request failed: %d!\n",
+					       engine->name, err);
+					goto restore;
 				}
 
 				i915_request_get(rq);
@@ -727,36 +760,61 @@ static int __igt_reset_engine(struct intel_gt *gt, bool active)
 
 					i915_request_put(rq);
 					err = -EIO;
-					break;
+					goto restore;
 				}
+			}
 
-				i915_request_put(rq);
+			if (!using_guc) {
+				err = intel_engine_reset(engine, NULL);
+				if (err) {
+					pr_err("intel_engine_reset(%s) failed, err:%d\n",
+					       engine->name, err);
+					goto skip;
+				}
 			}
 
-			err = intel_engine_reset(engine, NULL);
-			if (err) {
-				pr_err("intel_engine_reset(%s) failed, err:%d\n",
-				       engine->name, err);
-				break;
+			if (rq) {
+				/* Ensure the reset happens and kills the engine */
+				err = intel_selftest_wait_for_rq(rq);
+				if (err)
+					pr_err("[%s] Wait for request %lld:%lld [0x%04X] failed: %d!\n",
+					       engine->name, rq->fence.context,
+					       rq->fence.seqno, rq->context->guc_id.id, err);
 			}
 
+skip:
+			if (rq)
+				i915_request_put(rq);
+
 			if (i915_reset_count(global) != reset_count) {
 				pr_err("Full GPU reset recorded! (engine reset expected)\n");
 				err = -EINVAL;
-				break;
+				goto restore;
 			}
 
-			if (i915_reset_engine_count(global, engine) !=
-			    ++reset_engine_count) {
-				pr_err("%s engine reset not recorded!\n",
-				       engine->name);
-				err = -EINVAL;
-				break;
+			/* GuC based resets are not logged per engine */
+			if (!using_guc) {
+				if (i915_reset_engine_count(global, engine) !=
+				    ++reset_engine_count) {
+					pr_err("%s engine reset not recorded!\n",
+					       engine->name);
+					err = -EINVAL;
+					goto restore;
+				}
 			}
 
 			count++;
+
+restore:
+			err2 = intel_selftest_restore_policy(engine, &saved);
+			if (err2)
+				pr_err("[%s] Restore policy failed: %d!\n", engine->name, err);
+			if (err == 0)
+				err = err2;
+			if (err)
+				break;
 		} while (time_before(jiffies, end_time));
-		clear_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
+		clear_and_wake_up_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 		st_engine_heartbeat_enable(engine);
 		pr_info("%s: Completed %lu %s resets\n",
 			engine->name, count, active ? "active" : "idle");
@@ -765,12 +823,16 @@ static int __igt_reset_engine(struct intel_gt *gt, bool active)
 			break;
 
 		err = igt_flush_test(gt->i915);
-		if (err)
+		if (err) {
+			pr_err("[%s] Flush failed: %d!\n", engine->name, err);
 			break;
+		}
 	}
 
-	if (intel_gt_is_wedged(gt))
+	if (intel_gt_is_wedged(gt)) {
+		pr_err("GT is wedged!\n");
 		err = -EIO;
+	}
 
 	if (active)
 		hang_fini(&h);
@@ -789,10 +851,13 @@ static int igt_reset_active_engine(void *arg)
 }
 
 struct active_engine {
-	struct task_struct *task;
+	struct kthread_worker *worker;
+	struct kthread_work work;
 	struct intel_engine_cs *engine;
 	unsigned long resets;
 	unsigned int flags;
+	bool stop;
+	int result;
 };
 
 #define TEST_ACTIVE	BIT(0)
@@ -807,7 +872,7 @@ static int active_request_put(struct i915_request *rq)
 	if (!rq)
 		return 0;
 
-	if (i915_request_wait(rq, 0, 5 * HZ) < 0) {
+	if (i915_request_wait(rq, 0, 10 * HZ) < 0) {
 		GEM_TRACE("%s timed out waiting for completion of fence %llx:%lld\n",
 			  rq->engine->name,
 			  rq->fence.context,
@@ -823,10 +888,10 @@ static int active_request_put(struct i915_request *rq)
 	return err;
 }
 
-static int active_engine(void *data)
+static void active_engine(struct kthread_work *work)
 {
 	I915_RND_STATE(prng);
-	struct active_engine *arg = data;
+	struct active_engine *arg = container_of(work, typeof(*arg), work);
 	struct intel_engine_cs *engine = arg->engine;
 	struct i915_request *rq[8] = {};
 	struct intel_context *ce[ARRAY_SIZE(rq)];
@@ -836,15 +901,17 @@ static int active_engine(void *data)
 	for (count = 0; count < ARRAY_SIZE(ce); count++) {
 		ce[count] = intel_context_create(engine);
 		if (IS_ERR(ce[count])) {
-			err = PTR_ERR(ce[count]);
-			while (--count)
+			arg->result = PTR_ERR(ce[count]);
+			pr_err("[%s] Create context #%ld failed: %d!\n",
+			       engine->name, count, arg->result);
+			while (count--)
 				intel_context_put(ce[count]);
-			return err;
+			return;
 		}
 	}
 
 	count = 0;
-	while (!kthread_should_stop()) {
+	while (!READ_ONCE(arg->stop)) {
 		unsigned int idx = count++ & (ARRAY_SIZE(rq) - 1);
 		struct i915_request *old = rq[idx];
 		struct i915_request *new;
@@ -852,23 +919,26 @@ static int active_engine(void *data)
 		new = intel_context_create_request(ce[idx]);
 		if (IS_ERR(new)) {
 			err = PTR_ERR(new);
+			pr_err("[%s] Create request #%d failed: %d!\n", engine->name, idx, err);
 			break;
 		}
 
 		rq[idx] = i915_request_get(new);
 		i915_request_add(new);
 
-		if (engine->schedule && arg->flags & TEST_PRIORITY) {
+		if (engine->sched_engine->schedule && arg->flags & TEST_PRIORITY) {
 			struct i915_sched_attr attr = {
 				.priority =
 					i915_prandom_u32_max_state(512, &prng),
 			};
-			engine->schedule(rq[idx], &attr);
+			engine->sched_engine->schedule(rq[idx], &attr);
 		}
 
 		err = active_request_put(old);
-		if (err)
+		if (err) {
+			pr_err("[%s] Request put failed: %d!\n", engine->name, err);
 			break;
+		}
 
 		cond_resched();
 	}
@@ -876,6 +946,9 @@ static int active_engine(void *data)
 	for (count = 0; count < ARRAY_SIZE(rq); count++) {
 		int err__ = active_request_put(rq[count]);
 
+		if (err)
+			pr_err("[%s] Request put #%ld failed: %d!\n", engine->name, count, err);
+
 		/* Keep the first error */
 		if (!err)
 			err = err__;
@@ -883,7 +956,7 @@ static int active_engine(void *data)
 		intel_context_put(ce[count]);
 	}
 
-	return err;
+	arg->result = err;
 }
 
 static int __igt_reset_engines(struct intel_gt *gt,
@@ -892,6 +965,7 @@ static int __igt_reset_engines(struct intel_gt *gt,
 {
 	struct i915_gpu_error *global = &gt->i915->gpu_error;
 	struct intel_engine_cs *engine, *other;
+	struct active_engine *threads;
 	enum intel_engine_id id, tmp;
 	struct hang h;
 	int err = 0;
@@ -912,14 +986,20 @@ static int __igt_reset_engines(struct intel_gt *gt,
 			h.ctx->sched.priority = 1024;
 	}
 
+	threads = kmalloc_array(I915_NUM_ENGINES, sizeof(*threads), GFP_KERNEL);
+	if (!threads)
+		return -ENOMEM;
+
 	for_each_engine(engine, gt, id) {
-		struct active_engine threads[I915_NUM_ENGINES] = {};
 		unsigned long device = i915_reset_count(global);
 		unsigned long count = 0, reported;
+		bool using_guc = intel_engine_uses_guc(engine);
 		IGT_TIMEOUT(end_time);
 
-		if (flags & TEST_ACTIVE &&
-		    !intel_engine_can_store_dword(engine))
+		if (flags & TEST_ACTIVE) {
+			if (!intel_engine_can_store_dword(engine))
+				continue;
+		} else if (using_guc)
 			continue;
 
 		if (!wait_for_idle(engine)) {
@@ -929,9 +1009,9 @@ static int __igt_reset_engines(struct intel_gt *gt,
 			break;
 		}
 
-		memset(threads, 0, sizeof(threads));
+		memset(threads, 0, sizeof(*threads) * I915_NUM_ENGINES);
 		for_each_engine(other, gt, tmp) {
-			struct task_struct *tsk;
+			struct kthread_worker *worker;
 
 			threads[tmp].resets =
 				i915_reset_engine_count(global, other);
@@ -945,29 +1025,44 @@ static int __igt_reset_engines(struct intel_gt *gt,
 			threads[tmp].engine = other;
 			threads[tmp].flags = flags;
 
-			tsk = kthread_run(active_engine, &threads[tmp],
-					  "igt/%s", other->name);
-			if (IS_ERR(tsk)) {
-				err = PTR_ERR(tsk);
+			worker = kthread_run_worker(0, "igt/%s",
+						       other->name);
+			if (IS_ERR(worker)) {
+				err = PTR_ERR(worker);
+				pr_err("[%s] Worker create failed: %d!\n",
+				       engine->name, err);
 				goto unwind;
 			}
 
-			threads[tmp].task = tsk;
-			get_task_struct(tsk);
-		}
+			threads[tmp].worker = worker;
 
-		yield(); /* start all threads before we begin */
+			kthread_init_work(&threads[tmp].work, active_engine);
+			kthread_queue_work(threads[tmp].worker,
+					   &threads[tmp].work);
+		}
 
-		st_engine_heartbeat_disable(engine);
-		set_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
+		st_engine_heartbeat_disable_no_pm(engine);
+		GEM_BUG_ON(test_and_set_bit(I915_RESET_ENGINE + id,
+					    &gt->reset.flags));
 		do {
 			struct i915_request *rq = NULL;
+			struct intel_selftest_saved_policy saved;
+			int err2;
+
+			err = intel_selftest_modify_policy(engine, &saved,
+							   SELFTEST_SCHEDULER_MODIFY_FAST_RESET);
+			if (err) {
+				pr_err("[%s] Modify policy failed: %d!\n", engine->name, err);
+				break;
+			}
 
 			if (flags & TEST_ACTIVE) {
 				rq = hang_create_request(&h, engine);
 				if (IS_ERR(rq)) {
 					err = PTR_ERR(rq);
-					break;
+					pr_err("[%s] Create hang request failed: %d!\n",
+					       engine->name, err);
+					goto restore;
 				}
 
 				i915_request_get(rq);
@@ -983,32 +1078,44 @@ static int __igt_reset_engines(struct intel_gt *gt,
 
 					i915_request_put(rq);
 					err = -EIO;
-					break;
+					goto restore;
 				}
+			} else {
+				intel_engine_pm_get(engine);
 			}
 
-			err = intel_engine_reset(engine, NULL);
-			if (err) {
-				pr_err("i915_reset_engine(%s:%s): failed, err=%d\n",
-				       engine->name, test_name, err);
-				break;
+			if (!using_guc) {
+				err = intel_engine_reset(engine, NULL);
+				if (err) {
+					pr_err("i915_reset_engine(%s:%s): failed, err=%d\n",
+					       engine->name, test_name, err);
+					goto restore;
+				}
+			}
+
+			if (rq) {
+				/* Ensure the reset happens and kills the engine */
+				err = intel_selftest_wait_for_rq(rq);
+				if (err)
+					pr_err("[%s] Wait for request %lld:%lld [0x%04X] failed: %d!\n",
+					       engine->name, rq->fence.context,
+					       rq->fence.seqno, rq->context->guc_id.id, err);
 			}
 
 			count++;
 
 			if (rq) {
 				if (rq->fence.error != -EIO) {
-					pr_err("i915_reset_engine(%s:%s):"
-					       " failed to reset request %llx:%lld\n",
+					pr_err("i915_reset_engine(%s:%s): failed to reset request %lld:%lld [0x%04X]\n",
 					       engine->name, test_name,
 					       rq->fence.context,
-					       rq->fence.seqno);
+					       rq->fence.seqno, rq->context->guc_id.id);
 					i915_request_put(rq);
 
 					GEM_TRACE_DUMP();
 					intel_gt_set_wedged(gt);
 					err = -EIO;
-					break;
+					goto restore;
 				}
 
 				if (i915_request_wait(rq, 0, HZ / 5) < 0) {
@@ -1027,12 +1134,15 @@ static int __igt_reset_engines(struct intel_gt *gt,
 					GEM_TRACE_DUMP();
 					intel_gt_set_wedged(gt);
 					err = -EIO;
-					break;
+					goto restore;
 				}
 
 				i915_request_put(rq);
 			}
 
+			if (!(flags & TEST_ACTIVE))
+				intel_engine_pm_put(engine);
+
 			if (!(flags & TEST_SELF) && !wait_for_idle(engine)) {
 				struct drm_printer p =
 					drm_info_printer(gt->i915->drm.dev);
@@ -1044,49 +1154,67 @@ static int __igt_reset_engines(struct intel_gt *gt,
 						  "%s\n", engine->name);
 
 				err = -EIO;
-				break;
+				goto restore;
 			}
+
+restore:
+			err2 = intel_selftest_restore_policy(engine, &saved);
+			if (err2)
+				pr_err("[%s] Restore policy failed: %d!\n", engine->name, err2);
+			if (err == 0)
+				err = err2;
+			if (err)
+				break;
 		} while (time_before(jiffies, end_time));
-		clear_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
-		st_engine_heartbeat_enable(engine);
+		clear_and_wake_up_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
+		st_engine_heartbeat_enable_no_pm(engine);
 
 		pr_info("i915_reset_engine(%s:%s): %lu resets\n",
 			engine->name, test_name, count);
 
-		reported = i915_reset_engine_count(global, engine);
-		reported -= threads[engine->id].resets;
-		if (reported != count) {
-			pr_err("i915_reset_engine(%s:%s): reset %lu times, but reported %lu\n",
-			       engine->name, test_name, count, reported);
-			if (!err)
-				err = -EINVAL;
+		/* GuC based resets are not logged per engine */
+		if (!using_guc) {
+			reported = i915_reset_engine_count(global, engine);
+			reported -= threads[engine->id].resets;
+			if (reported != count) {
+				pr_err("i915_reset_engine(%s:%s): reset %lu times, but reported %lu\n",
+				       engine->name, test_name, count, reported);
+				if (!err)
+					err = -EINVAL;
+			}
 		}
 
 unwind:
 		for_each_engine(other, gt, tmp) {
 			int ret;
 
-			if (!threads[tmp].task)
+			if (!threads[tmp].worker)
 				continue;
 
-			ret = kthread_stop(threads[tmp].task);
+			WRITE_ONCE(threads[tmp].stop, true);
+			kthread_flush_work(&threads[tmp].work);
+			ret = READ_ONCE(threads[tmp].result);
 			if (ret) {
 				pr_err("kthread for other engine %s failed, err=%d\n",
 				       other->name, ret);
 				if (!err)
 					err = ret;
 			}
-			put_task_struct(threads[tmp].task);
-
-			if (other->uabi_class != engine->uabi_class &&
-			    threads[tmp].resets !=
-			    i915_reset_engine_count(global, other)) {
-				pr_err("Innocent engine %s was reset (count=%ld)\n",
-				       other->name,
-				       i915_reset_engine_count(global, other) -
-				       threads[tmp].resets);
-				if (!err)
-					err = -EINVAL;
+
+			kthread_destroy_worker(threads[tmp].worker);
+
+			/* GuC based resets are not logged per engine */
+			if (!using_guc) {
+				if (other->uabi_class != engine->uabi_class &&
+				    threads[tmp].resets !=
+				    i915_reset_engine_count(global, other)) {
+					pr_err("Innocent engine %s was reset (count=%ld)\n",
+					       other->name,
+					       i915_reset_engine_count(global, other) -
+					       threads[tmp].resets);
+					if (!err)
+						err = -EINVAL;
+				}
 			}
 		}
 
@@ -1101,9 +1229,12 @@ unwind:
 			break;
 
 		err = igt_flush_test(gt->i915);
-		if (err)
+		if (err) {
+			pr_err("[%s] Flush failed: %d!\n", engine->name, err);
 			break;
+		}
 	}
+	kfree(threads);
 
 	if (intel_gt_is_wedged(gt))
 		err = -EIO;
@@ -1165,13 +1296,15 @@ static int igt_reset_wait(void *arg)
 {
 	struct intel_gt *gt = arg;
 	struct i915_gpu_error *global = &gt->i915->gpu_error;
-	struct intel_engine_cs *engine = gt->engine[RCS0];
+	struct intel_engine_cs *engine;
 	struct i915_request *rq;
 	unsigned int reset_count;
 	struct hang h;
 	long timeout;
 	int err;
 
+	engine = intel_selftest_find_any_engine(gt);
+
 	if (!engine || !intel_engine_can_store_dword(engine))
 		return 0;
 
@@ -1180,12 +1313,15 @@ static int igt_reset_wait(void *arg)
 	igt_global_reset_lock(gt);
 
 	err = hang_init(&h, gt);
-	if (err)
+	if (err) {
+		pr_err("[%s] Hang init failed: %d!\n", engine->name, err);
 		goto unlock;
+	}
 
 	rq = hang_create_request(&h, engine);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
+		pr_err("[%s] Create hang request failed: %d!\n", engine->name, err);
 		goto fini;
 	}
 
@@ -1249,7 +1385,7 @@ static int evict_vma(void *data)
 	complete(&arg->completion);
 
 	mutex_lock(&vm->mutex);
-	err = i915_gem_evict_for_node(vm, &evict, 0);
+	err = i915_gem_evict_for_node(vm, NULL, &evict, 0);
 	mutex_unlock(&vm->mutex);
 
 	return err;
@@ -1292,7 +1428,7 @@ static int __igt_reset_evict_vma(struct intel_gt *gt,
 				 int (*fn)(void *),
 				 unsigned int flags)
 {
-	struct intel_engine_cs *engine = gt->engine[RCS0];
+	struct intel_engine_cs *engine;
 	struct drm_i915_gem_object *obj;
 	struct task_struct *tsk = NULL;
 	struct i915_request *rq;
@@ -1304,18 +1440,23 @@ static int __igt_reset_evict_vma(struct intel_gt *gt,
 	if (!gt->ggtt->num_fences && flags & EXEC_OBJECT_NEEDS_FENCE)
 		return 0;
 
+	engine = intel_selftest_find_any_engine(gt);
+
 	if (!engine || !intel_engine_can_store_dword(engine))
 		return 0;
 
 	/* Check that we can recover an unbind stuck on a hanging request */
 
 	err = hang_init(&h, gt);
-	if (err)
+	if (err) {
+		pr_err("[%s] Hang init failed: %d!\n", engine->name, err);
 		return err;
+	}
 
 	obj = i915_gem_object_create_internal(gt->i915, SZ_1M);
 	if (IS_ERR(obj)) {
 		err = PTR_ERR(obj);
+		pr_err("[%s] Create object failed: %d!\n", engine->name, err);
 		goto fini;
 	}
 
@@ -1330,12 +1471,14 @@ static int __igt_reset_evict_vma(struct intel_gt *gt,
 	arg.vma = i915_vma_instance(obj, vm, NULL);
 	if (IS_ERR(arg.vma)) {
 		err = PTR_ERR(arg.vma);
+		pr_err("[%s] VMA instance failed: %d!\n", engine->name, err);
 		goto out_obj;
 	}
 
 	rq = hang_create_request(&h, engine);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
+		pr_err("[%s] Create hang request failed: %d!\n", engine->name, err);
 		goto out_obj;
 	}
 
@@ -1347,6 +1490,7 @@ static int __igt_reset_evict_vma(struct intel_gt *gt,
 	err = i915_vma_pin(arg.vma, 0, 0, pin_flags);
 	if (err) {
 		i915_request_add(rq);
+		pr_err("[%s] VMA pin failed: %d!\n", engine->name, err);
 		goto out_obj;
 	}
 
@@ -1360,12 +1504,9 @@ static int __igt_reset_evict_vma(struct intel_gt *gt,
 		}
 	}
 
-	i915_vma_lock(arg.vma);
-	err = i915_request_await_object(rq, arg.vma->obj,
-					flags & EXEC_OBJECT_WRITE);
-	if (err == 0)
-		err = i915_vma_move_to_active(arg.vma, rq, flags);
-	i915_vma_unlock(arg.vma);
+	err = igt_vma_move_to_active_unlocked(arg.vma, rq, flags);
+	if (err)
+		pr_err("[%s] Move to active failed: %d!\n", engine->name, err);
 
 	if (flags & EXEC_OBJECT_NEEDS_FENCE)
 		i915_vma_unpin_fence(arg.vma);
@@ -1392,6 +1533,7 @@ static int __igt_reset_evict_vma(struct intel_gt *gt,
 	tsk = kthread_run(fn, &arg, "igt/evict_vma");
 	if (IS_ERR(tsk)) {
 		err = PTR_ERR(tsk);
+		pr_err("[%s] Thread spawn failed: %d!\n", engine->name, err);
 		tsk = NULL;
 		goto out_reset;
 	}
@@ -1454,7 +1596,7 @@ static int igt_reset_evict_ppgtt(void *arg)
 	if (INTEL_PPGTT(gt->i915) < INTEL_PPGTT_FULL)
 		return 0;
 
-	ppgtt = i915_ppgtt_create(gt);
+	ppgtt = i915_ppgtt_create(gt, 0);
 	if (IS_ERR(ppgtt))
 		return PTR_ERR(ppgtt);
 
@@ -1508,17 +1650,29 @@ static int igt_reset_queue(void *arg)
 		goto unlock;
 
 	for_each_engine(engine, gt, id) {
+		struct intel_selftest_saved_policy saved;
 		struct i915_request *prev;
 		IGT_TIMEOUT(end_time);
 		unsigned int count;
+		bool using_guc = intel_engine_uses_guc(engine);
 
 		if (!intel_engine_can_store_dword(engine))
 			continue;
 
+		if (using_guc) {
+			err = intel_selftest_modify_policy(engine, &saved,
+							   SELFTEST_SCHEDULER_MODIFY_NO_HANGCHECK);
+			if (err) {
+				pr_err("[%s] Modify policy failed: %d!\n", engine->name, err);
+				goto fini;
+			}
+		}
+
 		prev = hang_create_request(&h, engine);
 		if (IS_ERR(prev)) {
 			err = PTR_ERR(prev);
-			goto fini;
+			pr_err("[%s] Create 'prev' hang request failed: %d!\n", engine->name, err);
+			goto restore;
 		}
 
 		i915_request_get(prev);
@@ -1532,7 +1686,8 @@ static int igt_reset_queue(void *arg)
 			rq = hang_create_request(&h, engine);
 			if (IS_ERR(rq)) {
 				err = PTR_ERR(rq);
-				goto fini;
+				pr_err("[%s] Create hang request failed: %d!\n", engine->name, err);
+				goto restore;
 			}
 
 			i915_request_get(rq);
@@ -1557,7 +1712,7 @@ static int igt_reset_queue(void *arg)
 
 				GEM_TRACE_DUMP();
 				intel_gt_set_wedged(gt);
-				goto fini;
+				goto restore;
 			}
 
 			if (!wait_until_running(&h, prev)) {
@@ -1575,7 +1730,7 @@ static int igt_reset_queue(void *arg)
 				intel_gt_set_wedged(gt);
 
 				err = -EIO;
-				goto fini;
+				goto restore;
 			}
 
 			reset_count = fake_hangcheck(gt, BIT(id));
@@ -1586,7 +1741,7 @@ static int igt_reset_queue(void *arg)
 				i915_request_put(rq);
 				i915_request_put(prev);
 				err = -EINVAL;
-				goto fini;
+				goto restore;
 			}
 
 			if (rq->fence.error) {
@@ -1595,7 +1750,7 @@ static int igt_reset_queue(void *arg)
 				i915_request_put(rq);
 				i915_request_put(prev);
 				err = -EINVAL;
-				goto fini;
+				goto restore;
 			}
 
 			if (i915_reset_count(global) == reset_count) {
@@ -1603,7 +1758,7 @@ static int igt_reset_queue(void *arg)
 				i915_request_put(rq);
 				i915_request_put(prev);
 				err = -EINVAL;
-				goto fini;
+				goto restore;
 			}
 
 			i915_request_put(prev);
@@ -1618,9 +1773,24 @@ static int igt_reset_queue(void *arg)
 
 		i915_request_put(prev);
 
-		err = igt_flush_test(gt->i915);
+restore:
+		if (using_guc) {
+			int err2 = intel_selftest_restore_policy(engine, &saved);
+
+			if (err2)
+				pr_err("%s:%d> [%s] Restore policy failed: %d!\n",
+				       __func__, __LINE__, engine->name, err2);
+			if (err == 0)
+				err = err2;
+		}
 		if (err)
+			goto fini;
+
+		err = igt_flush_test(gt->i915);
+		if (err) {
+			pr_err("[%s] Flush failed: %d!\n", engine->name, err);
 			break;
+		}
 	}
 
 fini:
@@ -1638,12 +1808,14 @@ static int igt_handle_error(void *arg)
 {
 	struct intel_gt *gt = arg;
 	struct i915_gpu_error *global = &gt->i915->gpu_error;
-	struct intel_engine_cs *engine = gt->engine[RCS0];
+	struct intel_engine_cs *engine;
 	struct hang h;
 	struct i915_request *rq;
 	struct i915_gpu_coredump *error;
 	int err;
 
+	engine = intel_selftest_find_any_engine(gt);
+
 	/* Check that we can issue a global GPU and engine reset */
 
 	if (!intel_has_reset_engine(gt))
@@ -1653,12 +1825,15 @@ static int igt_handle_error(void *arg)
 		return 0;
 
 	err = hang_init(&h, gt);
-	if (err)
+	if (err) {
+		pr_err("[%s] Hang init failed: %d!\n", engine->name, err);
 		return err;
+	}
 
 	rq = hang_create_request(&h, engine);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
+		pr_err("[%s] Create hang request failed: %d!\n", engine->name, err);
 		goto err_fini;
 	}
 
@@ -1702,7 +1877,7 @@ static int __igt_atomic_reset_engine(struct intel_engine_cs *engine,
 				     const struct igt_atomic_section *p,
 				     const char *mode)
 {
-	struct tasklet_struct * const t = &engine->execlists.tasklet;
+	struct tasklet_struct * const t = &engine->sched_engine->tasklet;
 	int err;
 
 	GEM_TRACE("i915_reset_engine(%s:%s) under %s\n",
@@ -1743,12 +1918,15 @@ static int igt_atomic_reset_engine(struct intel_engine_cs *engine,
 		return err;
 
 	err = hang_init(&h, engine->gt);
-	if (err)
+	if (err) {
+		pr_err("[%s] Hang init failed: %d!\n", engine->name, err);
 		return err;
+	}
 
 	rq = hang_create_request(&h, engine);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
+		pr_err("[%s] Create hang request failed: %d!\n", engine->name, err);
 		goto out;
 	}
 
@@ -1838,7 +2016,7 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_reset_evict_fence),
 		SUBTEST(igt_handle_error),
 	};
-	struct intel_gt *gt = &i915->gt;
+	struct intel_gt *gt = to_gt(i915);
 	intel_wakeref_t wakeref;
 	int err;