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
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
|
/*
* Copyright (C) 2013 Red Hat
* Author: Rob Clark <robdclark@gmail.com>
*
* Copyright (c) 2014 The Linux Foundation. All rights reserved.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published by
* the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*
* You should have received a copy of the GNU General Public License along with
* this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include "adreno_gpu.h"
#include "msm_gem.h"
#include "msm_mmu.h"
#define RB_SIZE SZ_32K
#define RB_BLKSIZE 32
int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value)
{
struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
switch (param) {
case MSM_PARAM_GPU_ID:
*value = adreno_gpu->info->revn;
return 0;
case MSM_PARAM_GMEM_SIZE:
*value = adreno_gpu->gmem;
return 0;
case MSM_PARAM_GMEM_BASE:
*value = 0x100000;
return 0;
case MSM_PARAM_CHIP_ID:
*value = adreno_gpu->rev.patchid |
(adreno_gpu->rev.minor << 8) |
(adreno_gpu->rev.major << 16) |
(adreno_gpu->rev.core << 24);
return 0;
case MSM_PARAM_MAX_FREQ:
*value = adreno_gpu->base.fast_rate;
return 0;
case MSM_PARAM_TIMESTAMP:
if (adreno_gpu->funcs->get_timestamp)
return adreno_gpu->funcs->get_timestamp(gpu, value);
return -EINVAL;
default:
DBG("%s: invalid param: %u", gpu->name, param);
return -EINVAL;
}
}
int adreno_hw_init(struct msm_gpu *gpu)
{
struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
int ret;
DBG("%s", gpu->name);
ret = msm_gem_get_iova(gpu->rb->bo, gpu->id, &gpu->rb_iova);
if (ret) {
gpu->rb_iova = 0;
dev_err(gpu->dev->dev, "could not map ringbuffer: %d\n", ret);
return ret;
}
/* reset ringbuffer: */
gpu->rb->cur = gpu->rb->start;
/* reset completed fence seqno: */
adreno_gpu->memptrs->fence = gpu->fctx->completed_fence;
adreno_gpu->memptrs->rptr = 0;
adreno_gpu->memptrs->wptr = 0;
/* Setup REG_CP_RB_CNTL: */
adreno_gpu_write(adreno_gpu, REG_ADRENO_CP_RB_CNTL,
/* size is log2(quad-words): */
AXXX_CP_RB_CNTL_BUFSZ(ilog2(gpu->rb->size / 8)) |
AXXX_CP_RB_CNTL_BLKSZ(ilog2(RB_BLKSIZE / 8)) |
(adreno_is_a430(adreno_gpu) ? AXXX_CP_RB_CNTL_NO_UPDATE : 0));
/* Setup ringbuffer address: */
adreno_gpu_write64(adreno_gpu, REG_ADRENO_CP_RB_BASE,
REG_ADRENO_CP_RB_BASE_HI, gpu->rb_iova);
if (!adreno_is_a430(adreno_gpu)) {
adreno_gpu_write64(adreno_gpu, REG_ADRENO_CP_RB_RPTR_ADDR,
REG_ADRENO_CP_RB_RPTR_ADDR_HI,
rbmemptr(adreno_gpu, rptr));
}
return 0;
}
static uint32_t get_wptr(struct msm_ringbuffer *ring)
{
return ring->cur - ring->start;
}
/* Use this helper to read rptr, since a430 doesn't update rptr in memory */
static uint32_t get_rptr(struct adreno_gpu *adreno_gpu)
{
if (adreno_is_a430(adreno_gpu))
return adreno_gpu->memptrs->rptr = adreno_gpu_read(
adreno_gpu, REG_ADRENO_CP_RB_RPTR);
else
return adreno_gpu->memptrs->rptr;
}
uint32_t adreno_last_fence(struct msm_gpu *gpu)
{
struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
return adreno_gpu->memptrs->fence;
}
void adreno_recover(struct msm_gpu *gpu)
{
struct drm_device *dev = gpu->dev;
int ret;
// XXX pm-runtime?? we *need* the device to be off after this
// so maybe continuing to call ->pm_suspend/resume() is better?
gpu->funcs->pm_suspend(gpu);
gpu->funcs->pm_resume(gpu);
ret = msm_gpu_hw_init(gpu);
if (ret) {
dev_err(dev->dev, "gpu hw init failed: %d\n", ret);
/* hmm, oh well? */
}
}
void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
struct msm_file_private *ctx)
{
struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
struct msm_drm_private *priv = gpu->dev->dev_private;
struct msm_ringbuffer *ring = gpu->rb;
unsigned i;
for (i = 0; i < submit->nr_cmds; i++) {
switch (submit->cmd[i].type) {
case MSM_SUBMIT_CMD_IB_TARGET_BUF:
/* ignore IB-targets */
break;
case MSM_SUBMIT_CMD_CTX_RESTORE_BUF:
/* ignore if there has not been a ctx switch: */
if (priv->lastctx == ctx)
break;
case MSM_SUBMIT_CMD_BUF:
OUT_PKT3(ring, adreno_is_a430(adreno_gpu) ?
CP_INDIRECT_BUFFER_PFE : CP_INDIRECT_BUFFER_PFD, 2);
OUT_RING(ring, submit->cmd[i].iova);
OUT_RING(ring, submit->cmd[i].size);
OUT_PKT2(ring);
break;
}
}
OUT_PKT0(ring, REG_AXXX_CP_SCRATCH_REG2, 1);
OUT_RING(ring, submit->fence->seqno);
if (adreno_is_a3xx(adreno_gpu) || adreno_is_a4xx(adreno_gpu)) {
/* Flush HLSQ lazy updates to make sure there is nothing
* pending for indirect loads after the timestamp has
* passed:
*/
OUT_PKT3(ring, CP_EVENT_WRITE, 1);
OUT_RING(ring, HLSQ_FLUSH);
OUT_PKT3(ring, CP_WAIT_FOR_IDLE, 1);
OUT_RING(ring, 0x00000000);
}
OUT_PKT3(ring, CP_EVENT_WRITE, 3);
OUT_RING(ring, CACHE_FLUSH_TS);
OUT_RING(ring, rbmemptr(adreno_gpu, fence));
OUT_RING(ring, submit->fence->seqno);
/* we could maybe be clever and only CP_COND_EXEC the interrupt: */
OUT_PKT3(ring, CP_INTERRUPT, 1);
OUT_RING(ring, 0x80000000);
/* Workaround for missing irq issue on 8x16/a306. Unsure if the
* root cause is a platform issue or some a306 quirk, but this
* keeps things humming along:
*/
if (adreno_is_a306(adreno_gpu)) {
OUT_PKT3(ring, CP_WAIT_FOR_IDLE, 1);
OUT_RING(ring, 0x00000000);
OUT_PKT3(ring, CP_INTERRUPT, 1);
OUT_RING(ring, 0x80000000);
}
#if 0
if (adreno_is_a3xx(adreno_gpu)) {
/* Dummy set-constant to trigger context rollover */
OUT_PKT3(ring, CP_SET_CONSTANT, 2);
OUT_RING(ring, CP_REG(REG_A3XX_HLSQ_CL_KERNEL_GROUP_X_REG));
OUT_RING(ring, 0x00000000);
}
#endif
gpu->funcs->flush(gpu);
}
void adreno_flush(struct msm_gpu *gpu)
{
struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
uint32_t wptr;
/*
* Mask wptr value that we calculate to fit in the HW range. This is
* to account for the possibility that the last command fit exactly into
* the ringbuffer and rb->next hasn't wrapped to zero yet
*/
wptr = get_wptr(gpu->rb) & ((gpu->rb->size / 4) - 1);
/* ensure writes to ringbuffer have hit system memory: */
mb();
adreno_gpu_write(adreno_gpu, REG_ADRENO_CP_RB_WPTR, wptr);
}
bool adreno_idle(struct msm_gpu *gpu)
{
struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
uint32_t wptr = get_wptr(gpu->rb);
/* wait for CP to drain ringbuffer: */
if (!spin_until(get_rptr(adreno_gpu) == wptr))
return true;
/* TODO maybe we need to reset GPU here to recover from hang? */
DRM_ERROR("%s: timeout waiting to drain ringbuffer!\n", gpu->name);
return false;
}
#ifdef CONFIG_DEBUG_FS
void adreno_show(struct msm_gpu *gpu, struct seq_file *m)
{
struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
int i;
seq_printf(m, "revision: %d (%d.%d.%d.%d)\n",
adreno_gpu->info->revn, adreno_gpu->rev.core,
adreno_gpu->rev.major, adreno_gpu->rev.minor,
adreno_gpu->rev.patchid);
seq_printf(m, "fence: %d/%d\n", adreno_gpu->memptrs->fence,
gpu->fctx->last_fence);
seq_printf(m, "rptr: %d\n", get_rptr(adreno_gpu));
seq_printf(m, "wptr: %d\n", adreno_gpu->memptrs->wptr);
seq_printf(m, "rb wptr: %d\n", get_wptr(gpu->rb));
/* dump these out in a form that can be parsed by demsm: */
seq_printf(m, "IO:region %s 00000000 00020000\n", gpu->name);
for (i = 0; adreno_gpu->registers[i] != ~0; i += 2) {
uint32_t start = adreno_gpu->registers[i];
uint32_t end = adreno_gpu->registers[i+1];
uint32_t addr;
for (addr = start; addr <= end; addr++) {
uint32_t val = gpu_read(gpu, addr);
seq_printf(m, "IO:R %08x %08x\n", addr<<2, val);
}
}
}
#endif
/* Dump common gpu status and scratch registers on any hang, to make
* the hangcheck logs more useful. The scratch registers seem always
* safe to read when GPU has hung (unlike some other regs, depending
* on how the GPU hung), and they are useful to match up to cmdstream
* dumps when debugging hangs:
*/
void adreno_dump_info(struct msm_gpu *gpu)
{
struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
printk("revision: %d (%d.%d.%d.%d)\n",
adreno_gpu->info->revn, adreno_gpu->rev.core,
adreno_gpu->rev.major, adreno_gpu->rev.minor,
adreno_gpu->rev.patchid);
printk("fence: %d/%d\n", adreno_gpu->memptrs->fence,
gpu->fctx->last_fence);
printk("rptr: %d\n", get_rptr(adreno_gpu));
printk("wptr: %d\n", adreno_gpu->memptrs->wptr);
printk("rb wptr: %d\n", get_wptr(gpu->rb));
}
/* would be nice to not have to duplicate the _show() stuff with printk(): */
void adreno_dump(struct msm_gpu *gpu)
{
struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
int i;
/* dump these out in a form that can be parsed by demsm: */
printk("IO:region %s 00000000 00020000\n", gpu->name);
for (i = 0; adreno_gpu->registers[i] != ~0; i += 2) {
uint32_t start = adreno_gpu->registers[i];
uint32_t end = adreno_gpu->registers[i+1];
uint32_t addr;
for (addr = start; addr <= end; addr++) {
uint32_t val = gpu_read(gpu, addr);
printk("IO:R %08x %08x\n", addr<<2, val);
}
}
}
static uint32_t ring_freewords(struct msm_gpu *gpu)
{
struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
uint32_t size = gpu->rb->size / 4;
uint32_t wptr = get_wptr(gpu->rb);
uint32_t rptr = get_rptr(adreno_gpu);
return (rptr + (size - 1) - wptr) % size;
}
void adreno_wait_ring(struct msm_gpu *gpu, uint32_t ndwords)
{
if (spin_until(ring_freewords(gpu) >= ndwords))
DRM_ERROR("%s: timeout waiting for ringbuffer space\n", gpu->name);
}
static const char *iommu_ports[] = {
"gfx3d_user", "gfx3d_priv",
"gfx3d1_user", "gfx3d1_priv",
};
int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
struct adreno_gpu *adreno_gpu, const struct adreno_gpu_funcs *funcs)
{
struct adreno_platform_config *config = pdev->dev.platform_data;
struct msm_gpu *gpu = &adreno_gpu->base;
int ret;
adreno_gpu->funcs = funcs;
adreno_gpu->info = adreno_info(config->rev);
adreno_gpu->gmem = adreno_gpu->info->gmem;
adreno_gpu->revn = adreno_gpu->info->revn;
adreno_gpu->rev = config->rev;
gpu->fast_rate = config->fast_rate;
gpu->bus_freq = config->bus_freq;
#ifdef DOWNSTREAM_CONFIG_MSM_BUS_SCALING
gpu->bus_scale_table = config->bus_scale_table;
#endif
DBG("fast_rate=%u, slow_rate=27000000, bus_freq=%u",
gpu->fast_rate, gpu->bus_freq);
ret = msm_gpu_init(drm, pdev, &adreno_gpu->base, &funcs->base,
adreno_gpu->info->name, "kgsl_3d0_reg_memory", "kgsl_3d0_irq",
RB_SIZE);
if (ret)
return ret;
pm_runtime_set_autosuspend_delay(&pdev->dev, DRM_MSM_INACTIVE_PERIOD);
pm_runtime_use_autosuspend(&pdev->dev);
pm_runtime_enable(&pdev->dev);
ret = request_firmware(&adreno_gpu->pm4, adreno_gpu->info->pm4fw, drm->dev);
if (ret) {
dev_err(drm->dev, "failed to load %s PM4 firmware: %d\n",
adreno_gpu->info->pm4fw, ret);
return ret;
}
ret = request_firmware(&adreno_gpu->pfp, adreno_gpu->info->pfpfw, drm->dev);
if (ret) {
dev_err(drm->dev, "failed to load %s PFP firmware: %d\n",
adreno_gpu->info->pfpfw, ret);
return ret;
}
if (gpu->aspace && gpu->aspace->mmu) {
struct msm_mmu *mmu = gpu->aspace->mmu;
ret = mmu->funcs->attach(mmu, iommu_ports,
ARRAY_SIZE(iommu_ports));
if (ret)
return ret;
}
mutex_lock(&drm->struct_mutex);
adreno_gpu->memptrs_bo = msm_gem_new(drm, sizeof(*adreno_gpu->memptrs),
MSM_BO_UNCACHED);
mutex_unlock(&drm->struct_mutex);
if (IS_ERR(adreno_gpu->memptrs_bo)) {
ret = PTR_ERR(adreno_gpu->memptrs_bo);
adreno_gpu->memptrs_bo = NULL;
dev_err(drm->dev, "could not allocate memptrs: %d\n", ret);
return ret;
}
adreno_gpu->memptrs = msm_gem_get_vaddr(adreno_gpu->memptrs_bo);
if (IS_ERR(adreno_gpu->memptrs)) {
dev_err(drm->dev, "could not vmap memptrs\n");
return -ENOMEM;
}
ret = msm_gem_get_iova(adreno_gpu->memptrs_bo, gpu->id,
&adreno_gpu->memptrs_iova);
if (ret) {
dev_err(drm->dev, "could not map memptrs: %d\n", ret);
return ret;
}
return 0;
}
void adreno_gpu_cleanup(struct adreno_gpu *adreno_gpu)
{
struct msm_gpu *gpu = &adreno_gpu->base;
if (adreno_gpu->memptrs_bo) {
if (adreno_gpu->memptrs)
msm_gem_put_vaddr(adreno_gpu->memptrs_bo);
if (adreno_gpu->memptrs_iova)
msm_gem_put_iova(adreno_gpu->memptrs_bo, gpu->id);
drm_gem_object_unreference_unlocked(adreno_gpu->memptrs_bo);
}
release_firmware(adreno_gpu->pm4);
release_firmware(adreno_gpu->pfp);
msm_gpu_cleanup(gpu);
if (gpu->aspace) {
gpu->aspace->mmu->funcs->detach(gpu->aspace->mmu,
iommu_ports, ARRAY_SIZE(iommu_ports));
msm_gem_address_space_put(gpu->aspace);
}
}
|