1/*
2 * Copyright 2017 Advanced Micro Devices, Inc.
3 *
4 * Permission is hereby granted, free of charge, to any person obtaining a
5 * copy of this software and associated documentation files (the "Software"),
6 * to deal in the Software without restriction, including without limitation
7 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
8 * and/or sell copies of the Software, and to permit persons to whom the
9 * Software is furnished to do so, subject to the following conditions:
10 *
11 * The above copyright notice and this permission notice shall be included in
12 * all copies or substantial portions of the Software.
13 *
14 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
15 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
16 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
17 * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
18 * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
19 * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
20 * OTHER DEALINGS IN THE SOFTWARE.
21 *
22*/
23
24#include "CUnit/Basic.h"
25#include "xf86drm.h"
26
27#include "amdgpu_test.h"
28#include "amdgpu_drm.h"
29#include "amdgpu_internal.h"
30#include <pthread.h>
31
32static  amdgpu_device_handle device_handle;
33static  uint32_t  major_version;
34static  uint32_t  minor_version;
35
36static  uint32_t  family_id;
37static  uint32_t  chip_id;
38static  uint32_t  chip_rev;
39
40static void amdgpu_syncobj_timeline_test(void);
41
42CU_BOOL suite_syncobj_timeline_tests_enable(void)
43{
44	int r;
45	uint64_t cap = 0;
46
47	r = drmGetCap(drm_amdgpu[0], DRM_CAP_SYNCOBJ_TIMELINE, &cap);
48	if (r || cap == 0)
49		return CU_FALSE;
50
51	return CU_TRUE;
52}
53
54int suite_syncobj_timeline_tests_init(void)
55{
56	int r;
57
58	r = amdgpu_device_initialize(drm_amdgpu[0], &major_version,
59				   &minor_version, &device_handle);
60
61	if (r) {
62		if ((r == -EACCES) && (errno == EACCES))
63			printf("\n\nError:%s. "
64				"Hint:Try to run this test program as root.",
65				strerror(errno));
66		return CUE_SINIT_FAILED;
67	}
68
69	return CUE_SUCCESS;
70}
71
72int suite_syncobj_timeline_tests_clean(void)
73{
74	int r = amdgpu_device_deinitialize(device_handle);
75
76	if (r == 0)
77		return CUE_SUCCESS;
78	else
79		return CUE_SCLEAN_FAILED;
80}
81
82
83CU_TestInfo syncobj_timeline_tests[] = {
84	{ "syncobj timeline test",  amdgpu_syncobj_timeline_test },
85	CU_TEST_INFO_NULL,
86};
87
88#define GFX_COMPUTE_NOP  0xffff1000
89#define SDMA_NOP  0x0
90static int syncobj_command_submission_helper(uint32_t syncobj_handle, bool
91					     wait_or_signal, uint64_t point)
92{
93	amdgpu_context_handle context_handle;
94	amdgpu_bo_handle ib_result_handle;
95	void *ib_result_cpu;
96	uint64_t ib_result_mc_address;
97	struct drm_amdgpu_cs_chunk chunks[2];
98	struct drm_amdgpu_cs_chunk_data chunk_data;
99	struct drm_amdgpu_cs_chunk_syncobj syncobj_data;
100	struct amdgpu_cs_fence fence_status;
101	amdgpu_bo_list_handle bo_list;
102	amdgpu_va_handle va_handle;
103	uint32_t expired;
104	int i, r;
105	uint64_t seq_no;
106	static uint32_t *ptr;
107	struct amdgpu_gpu_info gpu_info = {0};
108	unsigned gc_ip_type;
109
110	r = amdgpu_query_gpu_info(device_handle, &gpu_info);
111	CU_ASSERT_EQUAL(r, 0);
112
113	family_id = device_handle->info.family_id;
114	chip_id = device_handle->info.chip_external_rev;
115	chip_rev = device_handle->info.chip_rev;
116
117	gc_ip_type = (asic_is_gfx_pipe_removed(family_id, chip_id, chip_rev)) ?
118			AMDGPU_HW_IP_COMPUTE : AMDGPU_HW_IP_GFX;
119
120	r = amdgpu_cs_ctx_create(device_handle, &context_handle);
121	CU_ASSERT_EQUAL(r, 0);
122
123	r = amdgpu_bo_alloc_and_map(device_handle, 4096, 4096,
124				    AMDGPU_GEM_DOMAIN_GTT, 0,
125				    &ib_result_handle, &ib_result_cpu,
126				    &ib_result_mc_address, &va_handle);
127	CU_ASSERT_EQUAL(r, 0);
128
129	r = amdgpu_get_bo_list(device_handle, ib_result_handle, NULL,
130			       &bo_list);
131	CU_ASSERT_EQUAL(r, 0);
132
133	ptr = ib_result_cpu;
134
135	for (i = 0; i < 16; ++i)
136		ptr[i] = wait_or_signal ? GFX_COMPUTE_NOP: SDMA_NOP;
137
138	chunks[0].chunk_id = AMDGPU_CHUNK_ID_IB;
139	chunks[0].length_dw = sizeof(struct drm_amdgpu_cs_chunk_ib) / 4;
140	chunks[0].chunk_data = (uint64_t)(uintptr_t)&chunk_data;
141	chunk_data.ib_data._pad = 0;
142	chunk_data.ib_data.va_start = ib_result_mc_address;
143	chunk_data.ib_data.ib_bytes = 16 * 4;
144	chunk_data.ib_data.ip_type = wait_or_signal ? gc_ip_type :
145		AMDGPU_HW_IP_DMA;
146	chunk_data.ib_data.ip_instance = 0;
147	chunk_data.ib_data.ring = 0;
148	chunk_data.ib_data.flags = AMDGPU_IB_FLAG_EMIT_MEM_SYNC;
149
150	chunks[1].chunk_id = wait_or_signal ?
151		AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_WAIT :
152		AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_SIGNAL;
153	chunks[1].length_dw = sizeof(struct drm_amdgpu_cs_chunk_syncobj) / 4;
154	chunks[1].chunk_data = (uint64_t)(uintptr_t)&syncobj_data;
155	syncobj_data.handle = syncobj_handle;
156	syncobj_data.point = point;
157	syncobj_data.flags = DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT;
158
159	r = amdgpu_cs_submit_raw(device_handle,
160				 context_handle,
161				 bo_list,
162				 2,
163				 chunks,
164				 &seq_no);
165	CU_ASSERT_EQUAL(r, 0);
166
167
168	memset(&fence_status, 0, sizeof(struct amdgpu_cs_fence));
169	fence_status.context = context_handle;
170	fence_status.ip_type = wait_or_signal ? gc_ip_type :
171		AMDGPU_HW_IP_DMA;
172	fence_status.ip_instance = 0;
173	fence_status.ring = 0;
174	fence_status.fence = seq_no;
175
176	r = amdgpu_cs_query_fence_status(&fence_status,
177			AMDGPU_TIMEOUT_INFINITE,0, &expired);
178	CU_ASSERT_EQUAL(r, 0);
179
180	r = amdgpu_bo_list_destroy(bo_list);
181	CU_ASSERT_EQUAL(r, 0);
182
183	r = amdgpu_bo_unmap_and_free(ib_result_handle, va_handle,
184				     ib_result_mc_address, 4096);
185	CU_ASSERT_EQUAL(r, 0);
186
187	r = amdgpu_cs_ctx_free(context_handle);
188	CU_ASSERT_EQUAL(r, 0);
189
190	return r;
191}
192
193struct syncobj_point {
194	uint32_t syncobj_handle;
195	uint64_t point;
196};
197
198static void *syncobj_wait(void *data)
199{
200	struct syncobj_point *sp = (struct syncobj_point *)data;
201	int r;
202
203	r = syncobj_command_submission_helper(sp->syncobj_handle, true,
204					      sp->point);
205	CU_ASSERT_EQUAL(r, 0);
206
207	return (void *)(long)r;
208}
209
210static void *syncobj_signal(void *data)
211{
212	struct syncobj_point *sp = (struct syncobj_point *)data;
213	int r;
214
215	r = syncobj_command_submission_helper(sp->syncobj_handle, false,
216					      sp->point);
217	CU_ASSERT_EQUAL(r, 0);
218
219	return (void *)(long)r;
220}
221
222static void amdgpu_syncobj_timeline_test(void)
223{
224	static pthread_t wait_thread;
225	static pthread_t signal_thread;
226	static pthread_t c_thread;
227	struct syncobj_point sp1, sp2, sp3;
228	uint32_t syncobj_handle;
229	uint64_t payload;
230	uint64_t wait_point, signal_point;
231	uint64_t timeout;
232	struct timespec tp;
233	int r, sync_fd;
234	void *tmp;
235
236	r =  amdgpu_cs_create_syncobj2(device_handle, 0, &syncobj_handle);
237	CU_ASSERT_EQUAL(r, 0);
238
239	// wait on point 5
240	sp1.syncobj_handle = syncobj_handle;
241	sp1.point = 5;
242	r = pthread_create(&wait_thread, NULL, syncobj_wait, &sp1);
243	CU_ASSERT_EQUAL(r, 0);
244
245	// signal on point 10
246	sp2.syncobj_handle = syncobj_handle;
247	sp2.point = 10;
248	r = pthread_create(&signal_thread, NULL, syncobj_signal, &sp2);
249	CU_ASSERT_EQUAL(r, 0);
250
251	r = pthread_join(wait_thread, &tmp);
252	CU_ASSERT_EQUAL(r, 0);
253	CU_ASSERT_EQUAL(tmp, 0);
254
255	r = pthread_join(signal_thread, &tmp);
256	CU_ASSERT_EQUAL(r, 0);
257	CU_ASSERT_EQUAL(tmp, 0);
258
259	//query timeline payload
260	r = amdgpu_cs_syncobj_query(device_handle, &syncobj_handle,
261				    &payload, 1);
262	CU_ASSERT_EQUAL(r, 0);
263	CU_ASSERT_EQUAL(payload, 10);
264
265	//signal on point 16
266	sp3.syncobj_handle = syncobj_handle;
267	sp3.point = 16;
268	r = pthread_create(&c_thread, NULL, syncobj_signal, &sp3);
269	CU_ASSERT_EQUAL(r, 0);
270	//CPU wait on point 16
271	wait_point = 16;
272	timeout = 0;
273	clock_gettime(CLOCK_MONOTONIC, &tp);
274	timeout = tp.tv_sec * 1000000000ULL + tp.tv_nsec;
275	timeout += 0x10000000000; //10s
276	r = amdgpu_cs_syncobj_timeline_wait(device_handle, &syncobj_handle,
277					    &wait_point, 1, timeout,
278					    DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL |
279					    DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT,
280					    NULL);
281
282	CU_ASSERT_EQUAL(r, 0);
283	r = pthread_join(c_thread, &tmp);
284	CU_ASSERT_EQUAL(r, 0);
285	CU_ASSERT_EQUAL(tmp, 0);
286
287	// export point 16 and import to point 18
288	r = amdgpu_cs_syncobj_export_sync_file2(device_handle, syncobj_handle,
289						16,
290						DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT,
291						&sync_fd);
292	CU_ASSERT_EQUAL(r, 0);
293	r = amdgpu_cs_syncobj_import_sync_file2(device_handle, syncobj_handle,
294						18, sync_fd);
295	CU_ASSERT_EQUAL(r, 0);
296	r = amdgpu_cs_syncobj_query(device_handle, &syncobj_handle,
297				    &payload, 1);
298	CU_ASSERT_EQUAL(r, 0);
299	CU_ASSERT_EQUAL(payload, 18);
300
301	// CPU signal on point 20
302	signal_point = 20;
303	r = amdgpu_cs_syncobj_timeline_signal(device_handle, &syncobj_handle,
304					      &signal_point, 1);
305	CU_ASSERT_EQUAL(r, 0);
306	r = amdgpu_cs_syncobj_query(device_handle, &syncobj_handle,
307				    &payload, 1);
308	CU_ASSERT_EQUAL(r, 0);
309	CU_ASSERT_EQUAL(payload, 20);
310
311	r = amdgpu_cs_destroy_syncobj(device_handle, syncobj_handle);
312	CU_ASSERT_EQUAL(r, 0);
313
314}
315