summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/i915/gt/uc/selftest_guc.c
blob: 1fd760539f77bc67835288c484eaf62412524056 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
// SPDX-License-Identifier: MIT
/*
 * Copyright �� 2021 Intel Corporation
 */

#include "gt/intel_gt_print.h"
#include "intel_guc_print.h"
#include "selftests/igt_spinner.h"
#include "selftests/intel_scheduler_helpers.h"

static int request_add_spin(struct i915_request *rq, struct igt_spinner *spin)
{
	int err = 0;

	i915_request_get(rq);
	i915_request_add(rq);
	if (spin && !igt_wait_for_spinner(spin, rq))
		err = -ETIMEDOUT;

	return err;
}

static struct i915_request *nop_user_request(struct intel_context *ce,
					     struct i915_request *from)
{
	struct i915_request *rq;
	int ret;

	rq = intel_context_create_request(ce);
	if (IS_ERR(rq))
		return rq;

	if (from) {
		ret = i915_sw_fence_await_dma_fence(&rq->submit,
						    &from->fence, 0,
						    I915_FENCE_GFP);
		if (ret < 0) {
			i915_request_put(rq);
			return ERR_PTR(ret);
		}
	}

	i915_request_get(rq);
	i915_request_add(rq);

	return rq;
}

static int intel_guc_scrub_ctbs(void *arg)
{
	struct intel_gt *gt = arg;
	int ret = 0;
	int i;
	struct i915_request *last[3] = {NULL, NULL, NULL}, *rq;
	intel_wakeref_t wakeref;
	struct intel_engine_cs *engine;
	struct intel_context *ce;

	if (!intel_has_gpu_reset(gt))
		return 0;

	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
	engine = intel_selftest_find_any_engine(gt);

	/* Submit requests and inject errors forcing G2H to be dropped */
	for (i = 0; i < 3; ++i) {
		ce = intel_context_create(engine);
		if (IS_ERR(ce)) {
			ret = PTR_ERR(ce);
			gt_err(gt, "Failed to create context %d: %pe\n", i, ce);
			goto err;
		}

		switch (i) {
		case 0:
			ce->drop_schedule_enable = true;
			break;
		case 1:
			ce->drop_schedule_disable = true;
			break;
		case 2:
			ce->drop_deregister = true;
			break;
		}

		rq = nop_user_request(ce, NULL);
		intel_context_put(ce);

		if (IS_ERR(rq)) {
			ret = PTR_ERR(rq);
			gt_err(gt, "Failed to create request %d: %pe\n", i, rq);
			goto err;
		}

		last[i] = rq;
	}

	for (i = 0; i < 3; ++i) {
		ret = i915_request_wait(last[i], 0, HZ);
		if (ret < 0) {
			gt_err(gt, "Last request failed to complete: %pe\n", ERR_PTR(ret));
			goto err;
		}
		i915_request_put(last[i]);
		last[i] = NULL;
	}

	/* Force all H2G / G2H to be submitted / processed */
	intel_gt_retire_requests(gt);
	msleep(500);

	/* Scrub missing G2H */
	intel_gt_handle_error(engine->gt, -1, 0, "selftest reset");

	/* GT will not idle if G2H are lost */
	ret = intel_gt_wait_for_idle(gt, HZ);
	if (ret < 0) {
		gt_err(gt, "GT failed to idle: %pe\n", ERR_PTR(ret));
		goto err;
	}

err:
	for (i = 0; i < 3; ++i)
		if (last[i])
			i915_request_put(last[i]);
	intel_runtime_pm_put(gt->uncore->rpm, wakeref);

	return ret;
}

/*
 * intel_guc_steal_guc_ids - Test to exhaust all guc_ids and then steal one
 *
 * This test creates a spinner which is used to block all subsequent submissions
 * until it completes. Next, a loop creates a context and a NOP request each
 * iteration until the guc_ids are exhausted (request creation returns -EAGAIN).
 * The spinner is ended, unblocking all requests created in the loop. At this
 * point all guc_ids are exhausted but are available to steal. Try to create
 * another request which should successfully steal a guc_id. Wait on last
 * request to complete, idle GPU, verify a guc_id was stolen via a counter, and
 * exit the test. Test also artificially reduces the number of guc_ids so the
 * test runs in a timely manner.
 */
static int intel_guc_steal_guc_ids(void *arg)
{
	struct intel_gt *gt = arg;
	struct intel_guc *guc = &gt->uc.guc;
	int ret, sv, context_index = 0;
	intel_wakeref_t wakeref;
	struct intel_engine_cs *engine;
	struct intel_context **ce;
	struct igt_spinner spin;
	struct i915_request *spin_rq = NULL, *rq, *last = NULL;
	int number_guc_id_stolen = guc->number_guc_id_stolen;

	ce = kcalloc(GUC_MAX_CONTEXT_ID, sizeof(*ce), GFP_KERNEL);
	if (!ce) {
		guc_err(guc, "Context array allocation failed\n");
		return -ENOMEM;
	}

	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
	engine = intel_selftest_find_any_engine(gt);
	sv = guc->submission_state.num_guc_ids;
	guc->submission_state.num_guc_ids = 512;

	/* Create spinner to block requests in below loop */
	ce[context_index] = intel_context_create(engine);
	if (IS_ERR(ce[context_index])) {
		ret = PTR_ERR(ce[context_index]);
		guc_err(guc, "Failed to create context: %pe\n", ce[context_index]);
		ce[context_index] = NULL;
		goto err_wakeref;
	}
	ret = igt_spinner_init(&spin, engine->gt);
	if (ret) {
		guc_err(guc, "Failed to create spinner: %pe\n", ERR_PTR(ret));
		goto err_contexts;
	}
	spin_rq = igt_spinner_create_request(&spin, ce[context_index],
					     MI_ARB_CHECK);
	if (IS_ERR(spin_rq)) {
		ret = PTR_ERR(spin_rq);
		guc_err(guc, "Failed to create spinner request: %pe\n", spin_rq);
		goto err_contexts;
	}
	ret = request_add_spin(spin_rq, &spin);
	if (ret) {
		guc_err(guc, "Failed to add Spinner request: %pe\n", ERR_PTR(ret));
		goto err_spin_rq;
	}

	/* Use all guc_ids */
	while (ret != -EAGAIN) {
		ce[++context_index] = intel_context_create(engine);
		if (IS_ERR(ce[context_index])) {
			ret = PTR_ERR(ce[context_index]);
			guc_err(guc, "Failed to create context: %pe\n", ce[context_index]);
			ce[context_index--] = NULL;
			goto err_spin_rq;
		}

		rq = nop_user_request(ce[context_index], spin_rq);
		if (IS_ERR(rq)) {
			ret = PTR_ERR(rq);
			rq = NULL;
			if (ret != -EAGAIN) {
				guc_err(guc, "Failed to create request %d: %pe\n",
					context_index, ERR_PTR(ret));
				goto err_spin_rq;
			}
		} else {
			if (last)
				i915_request_put(last);
			last = rq;
		}
	}

	/* Release blocked requests */
	igt_spinner_end(&spin);
	ret = intel_selftest_wait_for_rq(spin_rq);
	if (ret) {
		guc_err(guc, "Spin request failed to complete: %pe\n", ERR_PTR(ret));
		i915_request_put(last);
		goto err_spin_rq;
	}
	i915_request_put(spin_rq);
	igt_spinner_fini(&spin);
	spin_rq = NULL;

	/* Wait for last request */
	ret = i915_request_wait(last, 0, HZ * 30);
	i915_request_put(last);
	if (ret < 0) {
		guc_err(guc, "Last request failed to complete: %pe\n", ERR_PTR(ret));
		goto err_spin_rq;
	}

	/* Try to steal guc_id */
	rq = nop_user_request(ce[context_index], NULL);
	if (IS_ERR(rq)) {
		ret = PTR_ERR(rq);
		guc_err(guc, "Failed to steal guc_id %d: %pe\n", context_index, rq);
		goto err_spin_rq;
	}

	/* Wait for request with stolen guc_id */
	ret = i915_request_wait(rq, 0, HZ);
	i915_request_put(rq);
	if (ret < 0) {
		guc_err(guc, "Request with stolen guc_id failed to complete: %pe\n", ERR_PTR(ret));
		goto err_spin_rq;
	}

	/* Wait for idle */
	ret = intel_gt_wait_for_idle(gt, HZ * 30);
	if (ret < 0) {
		guc_err(guc, "GT failed to idle: %pe\n", ERR_PTR(ret));
		goto err_spin_rq;
	}

	/* Verify a guc_id was stolen */
	if (guc->number_guc_id_stolen == number_guc_id_stolen) {
		guc_err(guc, "No guc_id was stolen");
		ret = -EINVAL;
	} else {
		ret = 0;
	}

err_spin_rq:
	if (spin_rq) {
		igt_spinner_end(&spin);
		intel_selftest_wait_for_rq(spin_rq);
		i915_request_put(spin_rq);
		igt_spinner_fini(&spin);
		intel_gt_wait_for_idle(gt, HZ * 30);
	}
err_contexts:
	for (; context_index >= 0 && ce[context_index]; --context_index)
		intel_context_put(ce[context_index]);
err_wakeref:
	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
	kfree(ce);
	guc->submission_state.num_guc_ids = sv;

	return ret;
}

int intel_guc_live_selftests(struct drm_i915_private *i915)
{
	static const struct i915_subtest tests[] = {
		SUBTEST(intel_guc_scrub_ctbs),
		SUBTEST(intel_guc_steal_guc_ids),
	};
	struct intel_gt *gt = to_gt(i915);

	if (intel_gt_is_wedged(gt))
		return 0;

	if (!intel_uc_uses_guc_submission(&gt->uc))
		return 0;

	return intel_gt_live_subtests(tests, gt);
}