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
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
|
/*
* Copyright 2013 VMware, Inc. All rights reserved.
*
* Permission is hereby granted, free of charge, to any person
* obtaining a copy of this software and associated documentation
* files (the "Software"), to deal in the Software without
* restriction, including without limitation the rights to use, copy,
* modify, merge, publish, distribute, sublicense, and/or sell copies
* of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be
* included in all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
* BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
* ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
/**
* VGPU10 sampler and sampler view functions.
*/
#include "pipe/p_defines.h"
#include "util/u_bitmask.h"
#include "util/u_format.h"
#include "util/u_inlines.h"
#include "util/u_math.h"
#include "util/u_memory.h"
#include "svga_cmd.h"
#include "svga_context.h"
#include "svga_format.h"
#include "svga_resource_buffer.h"
#include "svga_resource_texture.h"
#include "svga_sampler_view.h"
#include "svga_shader.h"
#include "svga_state.h"
#include "svga_surface.h"
#include "svga3d_surfacedefs.h"
/** Get resource handle for a texture or buffer */
static inline struct svga_winsys_surface *
svga_resource_handle(struct pipe_resource *res)
{
if (res->target == PIPE_BUFFER) {
return svga_buffer(res)->handle;
}
else {
return svga_texture(res)->handle;
}
}
/**
* This helper function returns TRUE if the specified resource collides with
* any of the resources bound to any of the currently bound sampler views.
*/
boolean
svga_check_sampler_view_resource_collision(const struct svga_context *svga,
const struct svga_winsys_surface *res,
enum pipe_shader_type shader)
{
struct pipe_screen *screen = svga->pipe.screen;
unsigned i;
if (svga_screen(screen)->debug.no_surface_view) {
return FALSE;
}
for (i = 0; i < svga->curr.num_sampler_views[shader]; i++) {
struct svga_pipe_sampler_view *sv =
svga_pipe_sampler_view(svga->curr.sampler_views[shader][i]);
if (sv && res == svga_resource_handle(sv->base.texture)) {
return TRUE;
}
}
return FALSE;
}
/**
* Check if there are any resources that are both bound to a render target
* and bound as a shader resource for the given type of shader.
*/
boolean
svga_check_sampler_framebuffer_resource_collision(struct svga_context *svga,
enum pipe_shader_type shader)
{
struct svga_surface *surf;
unsigned i;
for (i = 0; i < svga->curr.framebuffer.nr_cbufs; i++) {
surf = svga_surface(svga->curr.framebuffer.cbufs[i]);
if (surf &&
svga_check_sampler_view_resource_collision(svga, surf->handle,
shader)) {
return TRUE;
}
}
surf = svga_surface(svga->curr.framebuffer.zsbuf);
if (surf &&
svga_check_sampler_view_resource_collision(svga, surf->handle, shader)) {
return TRUE;
}
return FALSE;
}
/**
* Create a DX ShaderResourceSamplerView for the given pipe_sampler_view,
* if needed.
*/
enum pipe_error
svga_validate_pipe_sampler_view(struct svga_context *svga,
struct svga_pipe_sampler_view *sv)
{
enum pipe_error ret = PIPE_OK;
if (sv->id == SVGA3D_INVALID_ID) {
struct svga_screen *ss = svga_screen(svga->pipe.screen);
struct pipe_resource *texture = sv->base.texture;
struct svga_winsys_surface *surface = svga_resource_handle(texture);
SVGA3dSurfaceFormat format;
SVGA3dResourceType resourceDim;
SVGA3dShaderResourceViewDesc viewDesc;
enum pipe_format viewFormat = sv->base.format;
/* vgpu10 cannot create a BGRX view for a BGRA resource, so force it to
* create a BGRA view (and vice versa).
*/
if (viewFormat == PIPE_FORMAT_B8G8R8X8_UNORM &&
svga_texture_device_format_has_alpha(texture)) {
viewFormat = PIPE_FORMAT_B8G8R8A8_UNORM;
}
else if (viewFormat == PIPE_FORMAT_B8G8R8A8_UNORM &&
!svga_texture_device_format_has_alpha(texture)) {
viewFormat = PIPE_FORMAT_B8G8R8X8_UNORM;
}
if (texture->target == PIPE_BUFFER) {
unsigned pf_flags;
svga_translate_texture_buffer_view_format(viewFormat,
&format,
&pf_flags);
}
else {
format = svga_translate_format(ss, viewFormat,
PIPE_BIND_SAMPLER_VIEW);
/* Convert the format to a sampler-friendly format, if needed */
format = svga_sampler_format(format);
}
assert(format != SVGA3D_FORMAT_INVALID);
if (texture->target == PIPE_BUFFER) {
unsigned elem_size = util_format_get_blocksize(sv->base.format);
viewDesc.buffer.firstElement = sv->base.u.buf.offset / elem_size;
viewDesc.buffer.numElements = sv->base.u.buf.size / elem_size;
}
else {
viewDesc.tex.mostDetailedMip = sv->base.u.tex.first_level;
viewDesc.tex.firstArraySlice = sv->base.u.tex.first_layer;
viewDesc.tex.mipLevels = (sv->base.u.tex.last_level -
sv->base.u.tex.first_level + 1);
}
/* arraySize in viewDesc specifies the number of array slices in a
* texture array. For 3D texture, last_layer in
* pipe_sampler_view specifies the last slice of the texture
* which is different from the last slice in a texture array,
* hence we need to set arraySize to 1 explicitly.
*/
viewDesc.tex.arraySize =
(texture->target == PIPE_TEXTURE_3D ||
texture->target == PIPE_BUFFER) ? 1 :
(sv->base.u.tex.last_layer - sv->base.u.tex.first_layer + 1);
switch (texture->target) {
case PIPE_BUFFER:
resourceDim = SVGA3D_RESOURCE_BUFFER;
break;
case PIPE_TEXTURE_1D:
case PIPE_TEXTURE_1D_ARRAY:
resourceDim = SVGA3D_RESOURCE_TEXTURE1D;
break;
case PIPE_TEXTURE_RECT:
case PIPE_TEXTURE_2D:
case PIPE_TEXTURE_2D_ARRAY:
resourceDim = SVGA3D_RESOURCE_TEXTURE2D;
break;
case PIPE_TEXTURE_3D:
resourceDim = SVGA3D_RESOURCE_TEXTURE3D;
break;
case PIPE_TEXTURE_CUBE:
case PIPE_TEXTURE_CUBE_ARRAY:
resourceDim = SVGA3D_RESOURCE_TEXTURECUBE;
break;
default:
assert(!"Unexpected texture type");
resourceDim = SVGA3D_RESOURCE_TEXTURE2D;
}
sv->id = util_bitmask_add(svga->sampler_view_id_bm);
ret = SVGA3D_vgpu10_DefineShaderResourceView(svga->swc,
sv->id,
surface,
format,
resourceDim,
&viewDesc);
if (ret != PIPE_OK) {
util_bitmask_clear(svga->sampler_view_id_bm, sv->id);
sv->id = SVGA3D_INVALID_ID;
}
}
return ret;
}
static enum pipe_error
update_sampler_resources(struct svga_context *svga, unsigned dirty)
{
enum pipe_error ret = PIPE_OK;
enum pipe_shader_type shader;
if (!svga_have_vgpu10(svga))
return PIPE_OK;
for (shader = PIPE_SHADER_VERTEX; shader <= PIPE_SHADER_GEOMETRY; shader++) {
SVGA3dShaderResourceViewId ids[PIPE_MAX_SAMPLERS];
struct svga_winsys_surface *surfaces[PIPE_MAX_SAMPLERS];
struct pipe_sampler_view *sampler_views[PIPE_MAX_SAMPLERS];
unsigned count;
unsigned nviews;
unsigned i;
count = svga->curr.num_sampler_views[shader];
for (i = 0; i < count; i++) {
struct svga_pipe_sampler_view *sv =
svga_pipe_sampler_view(svga->curr.sampler_views[shader][i]);
if (sv) {
surfaces[i] = svga_resource_handle(sv->base.texture);
ret = svga_validate_pipe_sampler_view(svga, sv);
if (ret != PIPE_OK)
return ret;
assert(sv->id != SVGA3D_INVALID_ID);
ids[i] = sv->id;
sampler_views[i] = &sv->base;
}
else {
surfaces[i] = NULL;
ids[i] = SVGA3D_INVALID_ID;
sampler_views[i] = NULL;
}
}
for (; i < svga->state.hw_draw.num_sampler_views[shader]; i++) {
ids[i] = SVGA3D_INVALID_ID;
surfaces[i] = NULL;
sampler_views[i] = NULL;
}
/* Number of ShaderResources that need to be modified. This includes
* the one that need to be unbound.
*/
nviews = MAX2(svga->state.hw_draw.num_sampler_views[shader], count);
if (nviews > 0) {
if (count != svga->state.hw_draw.num_sampler_views[shader] ||
memcmp(sampler_views, svga->state.hw_draw.sampler_views[shader],
count * sizeof(sampler_views[0])) != 0) {
SVGA3dShaderResourceViewId *pIds = ids;
struct svga_winsys_surface **pSurf = surfaces;
unsigned numSR = 0;
/* Loop through the sampler view list to only emit
* the sampler views that are not already in the
* corresponding entries in the device's
* shader resource list.
*/
for (i = 0; i < nviews; i++) {
boolean emit;
emit = sampler_views[i] ==
svga->state.hw_draw.sampler_views[shader][i];
if (!emit && i == nviews-1) {
/* Include the last sampler view in the next emit
* if it is different.
*/
emit = TRUE;
numSR++;
i++;
}
if (emit) {
/* numSR can only be 0 if the first entry of the list
* is the same as the one in the device list.
* In this case, * there is nothing to send yet.
*/
if (numSR) {
ret = SVGA3D_vgpu10_SetShaderResources(
svga->swc,
svga_shader_type(shader),
i - numSR, /* startView */
numSR,
pIds,
pSurf);
if (ret != PIPE_OK)
return ret;
}
pIds += (numSR + 1);
pSurf += (numSR + 1);
numSR = 0;
}
else
numSR++;
}
/* Save referenced sampler views in the hw draw state. */
svga->state.hw_draw.num_sampler_views[shader] = count;
for (i = 0; i < nviews; i++) {
pipe_sampler_view_reference(
&svga->state.hw_draw.sampler_views[shader][i],
sampler_views[i]);
}
}
}
}
/* Handle polygon stipple sampler view */
if (svga->curr.rast->templ.poly_stipple_enable) {
const unsigned unit = svga->state.hw_draw.fs->pstipple_sampler_unit;
struct svga_pipe_sampler_view *sv = svga->polygon_stipple.sampler_view;
struct svga_winsys_surface *surface;
assert(sv);
if (!sv) {
return PIPE_OK; /* probably out of memory */
}
ret = svga_validate_pipe_sampler_view(svga, sv);
if (ret != PIPE_OK)
return ret;
surface = svga_resource_handle(sv->base.texture);
ret = SVGA3D_vgpu10_SetShaderResources(
svga->swc,
svga_shader_type(PIPE_SHADER_FRAGMENT),
unit, /* startView */
1,
&sv->id,
&surface);
}
return ret;
}
struct svga_tracked_state svga_hw_sampler_bindings = {
"shader resources emit",
SVGA_NEW_STIPPLE |
SVGA_NEW_TEXTURE_BINDING,
update_sampler_resources
};
static enum pipe_error
update_samplers(struct svga_context *svga, unsigned dirty )
{
enum pipe_error ret = PIPE_OK;
enum pipe_shader_type shader;
if (!svga_have_vgpu10(svga))
return PIPE_OK;
for (shader = PIPE_SHADER_VERTEX; shader <= PIPE_SHADER_GEOMETRY; shader++) {
const unsigned count = svga->curr.num_samplers[shader];
SVGA3dSamplerId ids[PIPE_MAX_SAMPLERS];
unsigned i;
unsigned nsamplers;
for (i = 0; i < count; i++) {
bool fs_shadow = false;
/* _NEW_FS */
if (shader == PIPE_SHADER_FRAGMENT) {
struct svga_shader_variant *fs = svga->state.hw_draw.fs;
/* If the fragment shader is doing the shadow comparison
* for this texture unit, don't enable shadow compare in
* the texture sampler state.
*/
if (fs && (fs->fs_shadow_compare_units & (1 << i))) {
fs_shadow = true;
}
}
if (svga->curr.sampler[shader][i]) {
ids[i] = svga->curr.sampler[shader][i]->id[fs_shadow];
assert(ids[i] != SVGA3D_INVALID_ID);
}
else {
ids[i] = SVGA3D_INVALID_ID;
}
}
for (; i < svga->state.hw_draw.num_samplers[shader]; i++) {
ids[i] = SVGA3D_INVALID_ID;
}
nsamplers = MAX2(svga->state.hw_draw.num_samplers[shader], count);
if (nsamplers > 0) {
if (count != svga->state.hw_draw.num_samplers[shader] ||
memcmp(ids, svga->state.hw_draw.samplers[shader],
count * sizeof(ids[0])) != 0) {
/* HW state is really changing */
ret = SVGA3D_vgpu10_SetSamplers(svga->swc,
nsamplers,
0, /* start */
svga_shader_type(shader), /* type */
ids);
if (ret != PIPE_OK)
return ret;
memcpy(svga->state.hw_draw.samplers[shader], ids,
nsamplers * sizeof(ids[0]));
svga->state.hw_draw.num_samplers[shader] = count;
}
}
}
/* Handle polygon stipple sampler texture */
if (svga->curr.rast->templ.poly_stipple_enable) {
const unsigned unit = svga->state.hw_draw.fs->pstipple_sampler_unit;
struct svga_sampler_state *sampler = svga->polygon_stipple.sampler;
assert(sampler);
if (!sampler) {
return PIPE_OK; /* probably out of memory */
}
if (svga->state.hw_draw.samplers[PIPE_SHADER_FRAGMENT][unit]
!= sampler->id[0]) {
ret = SVGA3D_vgpu10_SetSamplers(svga->swc,
1, /* count */
unit, /* start */
SVGA3D_SHADERTYPE_PS,
&sampler->id[0]);
if (ret != PIPE_OK)
return ret;
/* save the polygon stipple sampler in the hw draw state */
svga->state.hw_draw.samplers[PIPE_SHADER_FRAGMENT][unit] =
sampler->id[0];
}
}
return ret;
}
struct svga_tracked_state svga_hw_sampler = {
"texture sampler emit",
(SVGA_NEW_FS |
SVGA_NEW_SAMPLER |
SVGA_NEW_STIPPLE),
update_samplers
};
|