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
305
306
307
308
309
310
311
312
313
314
315
316
317
318
|
From 52204a252c3a02e779a4107e21aeb5389de5e14f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>
Date: Wed, 26 Sep 2018 19:56:41 +0200
Subject: [PATCH 0667/2940] drm/amdgpu: fix sdma v4 startup under SRIOV
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Under SRIOV we were enabling the ring buffer before it was initialized.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 234 ++++++++++++-------------
1 file changed, 116 insertions(+), 118 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 7a8c9172d30a..fde27d8bfeb2 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -675,13 +675,14 @@ static void sdma_v4_0_enable(struct amdgpu_device *adev, bool enable)
* sdma_v4_0_gfx_resume - setup and start the async dma engines
*
* @adev: amdgpu_device pointer
+ * @i: instance to resume
*
* Set up the gfx DMA ring buffers and enable them (VEGA10).
* Returns 0 for success, error for failure.
*/
-static int sdma_v4_0_gfx_resume(struct amdgpu_device *adev)
+static void sdma_v4_0_gfx_resume(struct amdgpu_device *adev, unsigned int i)
{
- struct amdgpu_ring *ring;
+ struct amdgpu_ring *ring = &adev->sdma.instance[i].ring;
u32 rb_cntl, ib_cntl, wptr_poll_cntl;
u32 rb_bufsz;
u32 wb_offset;
@@ -689,129 +690,108 @@ static int sdma_v4_0_gfx_resume(struct amdgpu_device *adev)
u32 doorbell_offset;
u32 temp;
u64 wptr_gpu_addr;
- int i, r;
- for (i = 0; i < adev->sdma.num_instances; i++) {
- ring = &adev->sdma.instance[i].ring;
- wb_offset = (ring->rptr_offs * 4);
+ wb_offset = (ring->rptr_offs * 4);
- WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_SEM_WAIT_FAIL_TIMER_CNTL), 0);
+ WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_SEM_WAIT_FAIL_TIMER_CNTL), 0);
- /* Set ring buffer size in dwords */
- rb_bufsz = order_base_2(ring->ring_size / 4);
- rb_cntl = RREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL));
- rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_SIZE, rb_bufsz);
+ /* Set ring buffer size in dwords */
+ rb_bufsz = order_base_2(ring->ring_size / 4);
+ rb_cntl = RREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL));
+ rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_SIZE, rb_bufsz);
#ifdef __BIG_ENDIAN
- rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_SWAP_ENABLE, 1);
- rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL,
- RPTR_WRITEBACK_SWAP_ENABLE, 1);
+ rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_SWAP_ENABLE, 1);
+ rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL,
+ RPTR_WRITEBACK_SWAP_ENABLE, 1);
#endif
- WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL), rb_cntl);
+ WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL), rb_cntl);
- /* Initialize the ring buffer's read and write pointers */
- WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_RPTR), 0);
- WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_RPTR_HI), 0);
- WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR), 0);
- WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_HI), 0);
+ /* Initialize the ring buffer's read and write pointers */
+ WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_RPTR), 0);
+ WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_RPTR_HI), 0);
+ WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR), 0);
+ WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_HI), 0);
- /* set the wb address whether it's enabled or not */
- WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_RPTR_ADDR_HI),
- upper_32_bits(adev->wb.gpu_addr + wb_offset) & 0xFFFFFFFF);
- WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_RPTR_ADDR_LO),
- lower_32_bits(adev->wb.gpu_addr + wb_offset) & 0xFFFFFFFC);
+ /* set the wb address whether it's enabled or not */
+ WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_RPTR_ADDR_HI),
+ upper_32_bits(adev->wb.gpu_addr + wb_offset) & 0xFFFFFFFF);
+ WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_RPTR_ADDR_LO),
+ lower_32_bits(adev->wb.gpu_addr + wb_offset) & 0xFFFFFFFC);
- rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RPTR_WRITEBACK_ENABLE, 1);
+ rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RPTR_WRITEBACK_ENABLE, 1);
- WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_BASE), ring->gpu_addr >> 8);
- WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_BASE_HI), ring->gpu_addr >> 40);
+ WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_BASE), ring->gpu_addr >> 8);
+ WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_BASE_HI), ring->gpu_addr >> 40);
- ring->wptr = 0;
+ ring->wptr = 0;
- /* before programing wptr to a less value, need set minor_ptr_update first */
- WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_MINOR_PTR_UPDATE), 1);
+ /* before programing wptr to a less value, need set minor_ptr_update first */
+ WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_MINOR_PTR_UPDATE), 1);
- if (!amdgpu_sriov_vf(adev)) { /* only bare-metal use register write for wptr */
- WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR), lower_32_bits(ring->wptr) << 2);
- WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_HI), upper_32_bits(ring->wptr) << 2);
- }
+ if (!amdgpu_sriov_vf(adev)) { /* only bare-metal use register write for wptr */
+ WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR), lower_32_bits(ring->wptr) << 2);
+ WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_HI), upper_32_bits(ring->wptr) << 2);
+ }
- doorbell = RREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_DOORBELL));
- doorbell_offset = RREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_DOORBELL_OFFSET));
+ doorbell = RREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_DOORBELL));
+ doorbell_offset = RREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_DOORBELL_OFFSET));
- if (ring->use_doorbell) {
- doorbell = REG_SET_FIELD(doorbell, SDMA0_GFX_DOORBELL, ENABLE, 1);
- doorbell_offset = REG_SET_FIELD(doorbell_offset, SDMA0_GFX_DOORBELL_OFFSET,
- OFFSET, ring->doorbell_index);
- } else {
- doorbell = REG_SET_FIELD(doorbell, SDMA0_GFX_DOORBELL, ENABLE, 0);
- }
- WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_DOORBELL), doorbell);
- WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_DOORBELL_OFFSET), doorbell_offset);
- adev->nbio_funcs->sdma_doorbell_range(adev, i, ring->use_doorbell,
- ring->doorbell_index);
-
- if (amdgpu_sriov_vf(adev))
- sdma_v4_0_ring_set_wptr(ring);
-
- /* set minor_ptr_update to 0 after wptr programed */
- WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_MINOR_PTR_UPDATE), 0);
-
- /* set utc l1 enable flag always to 1 */
- temp = RREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_CNTL));
- temp = REG_SET_FIELD(temp, SDMA0_CNTL, UTC_L1_ENABLE, 1);
- WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_CNTL), temp);
-
- if (!amdgpu_sriov_vf(adev)) {
- /* unhalt engine */
- temp = RREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_F32_CNTL));
- temp = REG_SET_FIELD(temp, SDMA0_F32_CNTL, HALT, 0);
- WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_F32_CNTL), temp);
- }
+ if (ring->use_doorbell) {
+ doorbell = REG_SET_FIELD(doorbell, SDMA0_GFX_DOORBELL, ENABLE, 1);
+ doorbell_offset = REG_SET_FIELD(doorbell_offset, SDMA0_GFX_DOORBELL_OFFSET,
+ OFFSET, ring->doorbell_index);
+ } else {
+ doorbell = REG_SET_FIELD(doorbell, SDMA0_GFX_DOORBELL, ENABLE, 0);
+ }
+ WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_DOORBELL), doorbell);
+ WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_DOORBELL_OFFSET), doorbell_offset);
+ adev->nbio_funcs->sdma_doorbell_range(adev, i, ring->use_doorbell,
+ ring->doorbell_index);
- /* setup the wptr shadow polling */
- wptr_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
- WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_POLL_ADDR_LO),
- lower_32_bits(wptr_gpu_addr));
- WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_POLL_ADDR_HI),
- upper_32_bits(wptr_gpu_addr));
- wptr_poll_cntl = RREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_POLL_CNTL));
- if (amdgpu_sriov_vf(adev))
- wptr_poll_cntl = REG_SET_FIELD(wptr_poll_cntl, SDMA0_GFX_RB_WPTR_POLL_CNTL, F32_POLL_ENABLE, 1);
- else
- wptr_poll_cntl = REG_SET_FIELD(wptr_poll_cntl, SDMA0_GFX_RB_WPTR_POLL_CNTL, F32_POLL_ENABLE, 0);
- WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_POLL_CNTL), wptr_poll_cntl);
+ if (amdgpu_sriov_vf(adev))
+ sdma_v4_0_ring_set_wptr(ring);
- /* enable DMA RB */
- rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_ENABLE, 1);
- WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL), rb_cntl);
+ /* set minor_ptr_update to 0 after wptr programed */
+ WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_MINOR_PTR_UPDATE), 0);
- ib_cntl = RREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_IB_CNTL));
- ib_cntl = REG_SET_FIELD(ib_cntl, SDMA0_GFX_IB_CNTL, IB_ENABLE, 1);
-#ifdef __BIG_ENDIAN
- ib_cntl = REG_SET_FIELD(ib_cntl, SDMA0_GFX_IB_CNTL, IB_SWAP_ENABLE, 1);
-#endif
- /* enable DMA IBs */
- WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_IB_CNTL), ib_cntl);
+ /* set utc l1 enable flag always to 1 */
+ temp = RREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_CNTL));
+ temp = REG_SET_FIELD(temp, SDMA0_CNTL, UTC_L1_ENABLE, 1);
+ WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_CNTL), temp);
- ring->ready = true;
+ if (!amdgpu_sriov_vf(adev)) {
+ /* unhalt engine */
+ temp = RREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_F32_CNTL));
+ temp = REG_SET_FIELD(temp, SDMA0_F32_CNTL, HALT, 0);
+ WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_F32_CNTL), temp);
+ }
- if (amdgpu_sriov_vf(adev)) { /* bare-metal sequence doesn't need below to lines */
- sdma_v4_0_ctx_switch_enable(adev, true);
- sdma_v4_0_enable(adev, true);
- }
+ /* setup the wptr shadow polling */
+ wptr_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
+ WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_POLL_ADDR_LO),
+ lower_32_bits(wptr_gpu_addr));
+ WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_POLL_ADDR_HI),
+ upper_32_bits(wptr_gpu_addr));
+ wptr_poll_cntl = RREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_POLL_CNTL));
+ if (amdgpu_sriov_vf(adev))
+ wptr_poll_cntl = REG_SET_FIELD(wptr_poll_cntl, SDMA0_GFX_RB_WPTR_POLL_CNTL, F32_POLL_ENABLE, 1);
+ else
+ wptr_poll_cntl = REG_SET_FIELD(wptr_poll_cntl, SDMA0_GFX_RB_WPTR_POLL_CNTL, F32_POLL_ENABLE, 0);
+ WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_POLL_CNTL), wptr_poll_cntl);
- r = amdgpu_ring_test_ring(ring);
- if (r) {
- ring->ready = false;
- return r;
- }
+ /* enable DMA RB */
+ rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_ENABLE, 1);
+ WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL), rb_cntl);
- if (adev->mman.buffer_funcs_ring == ring)
- amdgpu_ttm_set_buffer_funcs_status(adev, true);
-
- }
+ ib_cntl = RREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_IB_CNTL));
+ ib_cntl = REG_SET_FIELD(ib_cntl, SDMA0_GFX_IB_CNTL, IB_ENABLE, 1);
+#ifdef __BIG_ENDIAN
+ ib_cntl = REG_SET_FIELD(ib_cntl, SDMA0_GFX_IB_CNTL, IB_SWAP_ENABLE, 1);
+#endif
+ /* enable DMA IBs */
+ WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_IB_CNTL), ib_cntl);
- return 0;
+ ring->ready = true;
}
static void
@@ -943,33 +923,51 @@ static int sdma_v4_0_load_microcode(struct amdgpu_device *adev)
*/
static int sdma_v4_0_start(struct amdgpu_device *adev)
{
- int r = 0;
+ struct amdgpu_ring *ring;
+ int i, r;
if (amdgpu_sriov_vf(adev)) {
sdma_v4_0_ctx_switch_enable(adev, false);
sdma_v4_0_enable(adev, false);
+ } else {
- /* set RB registers */
- r = sdma_v4_0_gfx_resume(adev);
- return r;
+ if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP) {
+ r = sdma_v4_0_load_microcode(adev);
+ if (r)
+ return r;
+ }
+
+ /* unhalt the MEs */
+ sdma_v4_0_enable(adev, true);
+ /* enable sdma ring preemption */
+ sdma_v4_0_ctx_switch_enable(adev, true);
}
- if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP) {
- r = sdma_v4_0_load_microcode(adev);
+ /* start the gfx rings and rlc compute queues */
+ for (i = 0; i < adev->sdma.num_instances; i++)
+ sdma_v4_0_gfx_resume(adev, i);
+
+ if (amdgpu_sriov_vf(adev)) {
+ sdma_v4_0_ctx_switch_enable(adev, true);
+ sdma_v4_0_enable(adev, true);
+ } else {
+ r = sdma_v4_0_rlc_resume(adev);
if (r)
return r;
}
- /* unhalt the MEs */
- sdma_v4_0_enable(adev, true);
- /* enable sdma ring preemption */
- sdma_v4_0_ctx_switch_enable(adev, true);
+ for (i = 0; i < adev->sdma.num_instances; i++) {
+ ring = &adev->sdma.instance[i].ring;
- /* start the gfx rings and rlc compute queues */
- r = sdma_v4_0_gfx_resume(adev);
- if (r)
- return r;
- r = sdma_v4_0_rlc_resume(adev);
+ r = amdgpu_ring_test_ring(ring);
+ if (r) {
+ ring->ready = false;
+ return r;
+ }
+
+ if (adev->mman.buffer_funcs_ring == ring)
+ amdgpu_ttm_set_buffer_funcs_status(adev, true);
+ }
return r;
}
--
2.17.1
|
