1/*
2 * Copyright 2019 Advanced Micro Devices, Inc.
3 * All Rights Reserved.
4 *
5 * Permission is hereby granted, free of charge, to any person obtaining a
6 * copy of this software and associated documentation files (the
7 * "Software"), to deal in the Software without restriction, including
8 * without limitation the rights to use, copy, modify, merge, publish,
9 * distribute, sub license, and/or sell copies of the Software, and to
10 * permit persons to whom the Software is furnished to do so, subject to
11 * the following conditions:
12 *
13 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
14 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
15 * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
16 * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
17 * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
18 * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
19 * USE OR OTHER DEALINGS IN THE SOFTWARE.
20 *
21 * The above copyright notice and this permission notice (including the
22 * next paragraph) shall be included in all copies or substantial portions
23 * of the Software.
24 *
25 */
26
27#include "amdgpu.h"
28#include "amdgpu_jpeg.h"
29#include "amdgpu_pm.h"
30#include "soc15d.h"
31#include "soc15_common.h"
32
33#define JPEG_IDLE_TIMEOUT	msecs_to_jiffies(1000)
34
35static void amdgpu_jpeg_idle_work_handler(struct work_struct *work);
36
37int amdgpu_jpeg_sw_init(struct amdgpu_device *adev)
38{
39	INIT_DELAYED_WORK(&adev->jpeg.idle_work, amdgpu_jpeg_idle_work_handler);
40	mutex_init(&adev->jpeg.jpeg_pg_lock);
41	atomic_set(&adev->jpeg.total_submission_cnt, 0);
42
43	return 0;
44}
45
46int amdgpu_jpeg_sw_fini(struct amdgpu_device *adev)
47{
48	int i, j;
49
50	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
51		if (adev->jpeg.harvest_config & (1 << i))
52			continue;
53
54		for (j = 0; j < adev->jpeg.num_jpeg_rings; ++j)
55			amdgpu_ring_fini(&adev->jpeg.inst[i].ring_dec[j]);
56	}
57
58	mutex_destroy(&adev->jpeg.jpeg_pg_lock);
59
60	return 0;
61}
62
63int amdgpu_jpeg_suspend(struct amdgpu_device *adev)
64{
65	cancel_delayed_work_sync(&adev->jpeg.idle_work);
66
67	return 0;
68}
69
70int amdgpu_jpeg_resume(struct amdgpu_device *adev)
71{
72	return 0;
73}
74
75static void amdgpu_jpeg_idle_work_handler(struct work_struct *work)
76{
77	struct amdgpu_device *adev =
78		container_of(work, struct amdgpu_device, jpeg.idle_work.work);
79	unsigned int fences = 0;
80	unsigned int i, j;
81
82	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
83		if (adev->jpeg.harvest_config & (1 << i))
84			continue;
85
86		for (j = 0; j < adev->jpeg.num_jpeg_rings; ++j)
87			fences += amdgpu_fence_count_emitted(&adev->jpeg.inst[i].ring_dec[j]);
88	}
89
90	if (!fences && !atomic_read(&adev->jpeg.total_submission_cnt))
91		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_JPEG,
92						       AMD_PG_STATE_GATE);
93	else
94		schedule_delayed_work(&adev->jpeg.idle_work, JPEG_IDLE_TIMEOUT);
95}
96
97void amdgpu_jpeg_ring_begin_use(struct amdgpu_ring *ring)
98{
99	struct amdgpu_device *adev = ring->adev;
100
101	atomic_inc(&adev->jpeg.total_submission_cnt);
102	cancel_delayed_work_sync(&adev->jpeg.idle_work);
103
104	mutex_lock(&adev->jpeg.jpeg_pg_lock);
105	amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_JPEG,
106						       AMD_PG_STATE_UNGATE);
107	mutex_unlock(&adev->jpeg.jpeg_pg_lock);
108}
109
110void amdgpu_jpeg_ring_end_use(struct amdgpu_ring *ring)
111{
112	atomic_dec(&ring->adev->jpeg.total_submission_cnt);
113	schedule_delayed_work(&ring->adev->jpeg.idle_work, JPEG_IDLE_TIMEOUT);
114}
115
116int amdgpu_jpeg_dec_ring_test_ring(struct amdgpu_ring *ring)
117{
118	struct amdgpu_device *adev = ring->adev;
119	uint32_t tmp = 0;
120	unsigned i;
121	int r;
122
123	/* JPEG in SRIOV does not support direct register read/write */
124	if (amdgpu_sriov_vf(adev))
125		return 0;
126
127	r = amdgpu_ring_alloc(ring, 3);
128	if (r)
129		return r;
130
131	WREG32(adev->jpeg.inst[ring->me].external.jpeg_pitch[ring->pipe], 0xCAFEDEAD);
132	/* Add a read register to make sure the write register is executed. */
133	RREG32(adev->jpeg.inst[ring->me].external.jpeg_pitch[ring->pipe]);
134
135	amdgpu_ring_write(ring, PACKET0(adev->jpeg.internal.jpeg_pitch[ring->pipe], 0));
136	amdgpu_ring_write(ring, 0xABADCAFE);
137	amdgpu_ring_commit(ring);
138
139	for (i = 0; i < adev->usec_timeout; i++) {
140		tmp = RREG32(adev->jpeg.inst[ring->me].external.jpeg_pitch[ring->pipe]);
141		if (tmp == 0xABADCAFE)
142			break;
143		udelay(1);
144	}
145
146	if (i >= adev->usec_timeout)
147		r = -ETIMEDOUT;
148
149	return r;
150}
151
152static int amdgpu_jpeg_dec_set_reg(struct amdgpu_ring *ring, uint32_t handle,
153		struct dma_fence **fence)
154{
155	struct amdgpu_device *adev = ring->adev;
156	struct amdgpu_job *job;
157	struct amdgpu_ib *ib;
158	struct dma_fence *f = NULL;
159	const unsigned ib_size_dw = 16;
160	int i, r;
161
162	r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, ib_size_dw * 4,
163				     AMDGPU_IB_POOL_DIRECT, &job);
164	if (r)
165		return r;
166
167	ib = &job->ibs[0];
168
169	ib->ptr[0] = PACKETJ(adev->jpeg.internal.jpeg_pitch[ring->pipe], 0, 0, PACKETJ_TYPE0);
170	ib->ptr[1] = 0xDEADBEEF;
171	for (i = 2; i < 16; i += 2) {
172		ib->ptr[i] = PACKETJ(0, 0, 0, PACKETJ_TYPE6);
173		ib->ptr[i+1] = 0;
174	}
175	ib->length_dw = 16;
176
177	r = amdgpu_job_submit_direct(job, ring, &f);
178	if (r)
179		goto err;
180
181	if (fence)
182		*fence = dma_fence_get(f);
183	dma_fence_put(f);
184
185	return 0;
186
187err:
188	amdgpu_job_free(job);
189	return r;
190}
191
192int amdgpu_jpeg_dec_ring_test_ib(struct amdgpu_ring *ring, long timeout)
193{
194	struct amdgpu_device *adev = ring->adev;
195	uint32_t tmp = 0;
196	unsigned i;
197	struct dma_fence *fence = NULL;
198	long r = 0;
199
200	r = amdgpu_jpeg_dec_set_reg(ring, 1, &fence);
201	if (r)
202		goto error;
203
204	r = dma_fence_wait_timeout(fence, false, timeout);
205	if (r == 0) {
206		r = -ETIMEDOUT;
207		goto error;
208	} else if (r < 0) {
209		goto error;
210	} else {
211		r = 0;
212	}
213	if (!amdgpu_sriov_vf(adev)) {
214		for (i = 0; i < adev->usec_timeout; i++) {
215			tmp = RREG32(adev->jpeg.inst[ring->me].external.jpeg_pitch[ring->pipe]);
216			if (tmp == 0xDEADBEEF)
217				break;
218			udelay(1);
219		}
220
221		if (i >= adev->usec_timeout)
222			r = -ETIMEDOUT;
223	}
224
225	dma_fence_put(fence);
226error:
227	return r;
228}
229
230int amdgpu_jpeg_process_poison_irq(struct amdgpu_device *adev,
231				struct amdgpu_irq_src *source,
232				struct amdgpu_iv_entry *entry)
233{
234	struct ras_common_if *ras_if = adev->jpeg.ras_if;
235	struct ras_dispatch_if ih_data = {
236		.entry = entry,
237	};
238
239	if (!ras_if)
240		return 0;
241
242	ih_data.head = *ras_if;
243	amdgpu_ras_interrupt_dispatch(adev, &ih_data);
244
245	return 0;
246}
247
248int amdgpu_jpeg_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *ras_block)
249{
250	int r, i;
251
252	r = amdgpu_ras_block_late_init(adev, ras_block);
253	if (r)
254		return r;
255
256	if (amdgpu_ras_is_supported(adev, ras_block->block)) {
257		for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
258			if (adev->jpeg.harvest_config & (1 << i) ||
259			    !adev->jpeg.inst[i].ras_poison_irq.funcs)
260				continue;
261
262			r = amdgpu_irq_get(adev, &adev->jpeg.inst[i].ras_poison_irq, 0);
263			if (r)
264				goto late_fini;
265		}
266	}
267	return 0;
268
269late_fini:
270	amdgpu_ras_block_late_fini(adev, ras_block);
271	return r;
272}
273
274int amdgpu_jpeg_ras_sw_init(struct amdgpu_device *adev)
275{
276	int err;
277	struct amdgpu_jpeg_ras *ras;
278
279	if (!adev->jpeg.ras)
280		return 0;
281
282	ras = adev->jpeg.ras;
283	err = amdgpu_ras_register_ras_block(adev, &ras->ras_block);
284	if (err) {
285		dev_err(adev->dev, "Failed to register jpeg ras block!\n");
286		return err;
287	}
288
289	strcpy(ras->ras_block.ras_comm.name, "jpeg");
290	ras->ras_block.ras_comm.block = AMDGPU_RAS_BLOCK__JPEG;
291	ras->ras_block.ras_comm.type = AMDGPU_RAS_ERROR__POISON;
292	adev->jpeg.ras_if = &ras->ras_block.ras_comm;
293
294	if (!ras->ras_block.ras_late_init)
295		ras->ras_block.ras_late_init = amdgpu_jpeg_ras_late_init;
296
297	return 0;
298}
299