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
|
/*
* Copyright © 2015 Intel Corporation
*
* 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 (including the next
* paragraph) 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.
*/
#include <assert.h>
#include <stdbool.h>
#include <string.h>
#include <unistd.h>
#include <fcntl.h>
#include "anv_private.h"
#include "common/gen_sample_positions.h"
#include "genxml/gen_macros.h"
#include "genxml/genX_pack.h"
#include "vk_util.h"
#if GEN_GEN == 10
/**
* From Gen10 Workarounds page in h/w specs:
* WaSampleOffsetIZ:
* "Prior to the 3DSTATE_SAMPLE_PATTERN driver must ensure there are no
* markers in the pipeline by programming a PIPE_CONTROL with stall."
*/
static void
gen10_emit_wa_cs_stall_flush(struct anv_batch *batch)
{
anv_batch_emit(batch, GENX(PIPE_CONTROL), pc) {
pc.CommandStreamerStallEnable = true;
pc.StallAtPixelScoreboard = true;
}
}
/**
* From Gen10 Workarounds page in h/w specs:
* WaSampleOffsetIZ:_cs_stall_flush
* "When 3DSTATE_SAMPLE_PATTERN is programmed, driver must then issue an
* MI_LOAD_REGISTER_IMM command to an offset between 0x7000 and 0x7FFF(SVL)
* after the command to ensure the state has been delivered prior to any
* command causing a marker in the pipeline."
*/
static void
gen10_emit_wa_lri_to_cache_mode_zero(struct anv_batch *batch)
{
/* Before changing the value of CACHE_MODE_0 register, GFX pipeline must
* be idle; i.e., full flush is required.
*/
anv_batch_emit(batch, GENX(PIPE_CONTROL), pc) {
pc.DepthCacheFlushEnable = true;
pc.DCFlushEnable = true;
pc.RenderTargetCacheFlushEnable = true;
pc.InstructionCacheInvalidateEnable = true;
pc.StateCacheInvalidationEnable = true;
pc.TextureCacheInvalidationEnable = true;
pc.VFCacheInvalidationEnable = true;
pc.ConstantCacheInvalidationEnable =true;
}
/* Write to CACHE_MODE_0 (0x7000) */
uint32_t cache_mode_0 = 0;
anv_pack_struct(&cache_mode_0, GENX(CACHE_MODE_0));
anv_batch_emit(batch, GENX(MI_LOAD_REGISTER_IMM), lri) {
lri.RegisterOffset = GENX(CACHE_MODE_0_num);
lri.DataDWord = cache_mode_0;
}
}
#endif
VkResult
genX(init_device_state)(struct anv_device *device)
{
GENX(MEMORY_OBJECT_CONTROL_STATE_pack)(NULL, &device->default_mocs,
&GENX(MOCS));
struct anv_batch batch;
uint32_t cmds[64];
batch.start = batch.next = cmds;
batch.end = (void *) cmds + sizeof(cmds);
anv_batch_emit(&batch, GENX(PIPELINE_SELECT), ps) {
#if GEN_GEN >= 9
ps.MaskBits = 3;
#endif
ps.PipelineSelection = _3D;
}
#if GEN_GEN == 9
uint32_t cache_mode_1;
anv_pack_struct(&cache_mode_1, GENX(CACHE_MODE_1),
.FloatBlendOptimizationEnable = true,
.FloatBlendOptimizationEnableMask = true,
.PartialResolveDisableInVC = true,
.PartialResolveDisableInVCMask = true);
anv_batch_emit(&batch, GENX(MI_LOAD_REGISTER_IMM), lri) {
lri.RegisterOffset = GENX(CACHE_MODE_1_num);
lri.DataDWord = cache_mode_1;
}
#endif
#if GEN_GEN == 10 || GEN_GEN == 11
uint32_t cache_mode_ss;
anv_pack_struct(&cache_mode_ss, GENX(CACHE_MODE_SS),
.FloatBlendOptimizationEnable = true,
.FloatBlendOptimizationEnableMask = true);
anv_batch_emit(&batch, GENX(MI_LOAD_REGISTER_IMM), lri) {
lri.RegisterOffset = GENX(CACHE_MODE_SS_num);
lri.DataDWord = cache_mode_ss;
}
#endif
anv_batch_emit(&batch, GENX(3DSTATE_AA_LINE_PARAMETERS), aa);
anv_batch_emit(&batch, GENX(3DSTATE_DRAWING_RECTANGLE), rect) {
rect.ClippedDrawingRectangleYMin = 0;
rect.ClippedDrawingRectangleXMin = 0;
rect.ClippedDrawingRectangleYMax = UINT16_MAX;
rect.ClippedDrawingRectangleXMax = UINT16_MAX;
rect.DrawingRectangleOriginY = 0;
rect.DrawingRectangleOriginX = 0;
}
#if GEN_GEN >= 8
anv_batch_emit(&batch, GENX(3DSTATE_WM_CHROMAKEY), ck);
#if GEN_GEN == 10
gen10_emit_wa_cs_stall_flush(&batch);
#endif
/* See the Vulkan 1.0 spec Table 24.1 "Standard sample locations" and
* VkPhysicalDeviceFeatures::standardSampleLocations.
*/
anv_batch_emit(&batch, GENX(3DSTATE_SAMPLE_PATTERN), sp) {
GEN_SAMPLE_POS_1X(sp._1xSample);
GEN_SAMPLE_POS_2X(sp._2xSample);
GEN_SAMPLE_POS_4X(sp._4xSample);
GEN_SAMPLE_POS_8X(sp._8xSample);
#if GEN_GEN >= 9
GEN_SAMPLE_POS_16X(sp._16xSample);
#endif
}
#endif
#if GEN_GEN == 10
gen10_emit_wa_lri_to_cache_mode_zero(&batch);
#endif
/* Set the "CONSTANT_BUFFER Address Offset Disable" bit, so
* 3DSTATE_CONSTANT_XS buffer 0 is an absolute address.
*
* This is only safe on kernels with context isolation support.
*/
if (GEN_GEN >= 8 &&
device->instance->physicalDevice.has_context_isolation) {
UNUSED uint32_t tmp_reg;
#if GEN_GEN >= 9
anv_pack_struct(&tmp_reg, GENX(CS_DEBUG_MODE2),
.CONSTANT_BUFFERAddressOffsetDisable = true,
.CONSTANT_BUFFERAddressOffsetDisableMask = true);
anv_batch_emit(&batch, GENX(MI_LOAD_REGISTER_IMM), lri) {
lri.RegisterOffset = GENX(CS_DEBUG_MODE2_num);
lri.DataDWord = tmp_reg;
}
#elif GEN_GEN == 8
anv_pack_struct(&tmp_reg, GENX(INSTPM),
.CONSTANT_BUFFERAddressOffsetDisable = true,
.CONSTANT_BUFFERAddressOffsetDisableMask = true);
anv_batch_emit(&batch, GENX(MI_LOAD_REGISTER_IMM), lri) {
lri.RegisterOffset = GENX(INSTPM_num);
lri.DataDWord = tmp_reg;
}
#endif
}
anv_batch_emit(&batch, GENX(MI_BATCH_BUFFER_END), bbe);
assert(batch.next <= batch.end);
return anv_device_submit_simple_batch(device, &batch);
}
static uint32_t
vk_to_gen_tex_filter(VkFilter filter, bool anisotropyEnable)
{
switch (filter) {
default:
assert(!"Invalid filter");
case VK_FILTER_NEAREST:
return anisotropyEnable ? MAPFILTER_ANISOTROPIC : MAPFILTER_NEAREST;
case VK_FILTER_LINEAR:
return anisotropyEnable ? MAPFILTER_ANISOTROPIC : MAPFILTER_LINEAR;
}
}
static uint32_t
vk_to_gen_max_anisotropy(float ratio)
{
return (anv_clamp_f(ratio, 2, 16) - 2) / 2;
}
static const uint32_t vk_to_gen_mipmap_mode[] = {
[VK_SAMPLER_MIPMAP_MODE_NEAREST] = MIPFILTER_NEAREST,
[VK_SAMPLER_MIPMAP_MODE_LINEAR] = MIPFILTER_LINEAR
};
static const uint32_t vk_to_gen_tex_address[] = {
[VK_SAMPLER_ADDRESS_MODE_REPEAT] = TCM_WRAP,
[VK_SAMPLER_ADDRESS_MODE_MIRRORED_REPEAT] = TCM_MIRROR,
[VK_SAMPLER_ADDRESS_MODE_CLAMP_TO_EDGE] = TCM_CLAMP,
[VK_SAMPLER_ADDRESS_MODE_MIRROR_CLAMP_TO_EDGE] = TCM_MIRROR_ONCE,
[VK_SAMPLER_ADDRESS_MODE_CLAMP_TO_BORDER] = TCM_CLAMP_BORDER,
};
/* Vulkan specifies the result of shadow comparisons as:
* 1 if ref <op> texel,
* 0 otherwise.
*
* The hardware does:
* 0 if texel <op> ref,
* 1 otherwise.
*
* So, these look a bit strange because there's both a negation
* and swapping of the arguments involved.
*/
static const uint32_t vk_to_gen_shadow_compare_op[] = {
[VK_COMPARE_OP_NEVER] = PREFILTEROPALWAYS,
[VK_COMPARE_OP_LESS] = PREFILTEROPLEQUAL,
[VK_COMPARE_OP_EQUAL] = PREFILTEROPNOTEQUAL,
[VK_COMPARE_OP_LESS_OR_EQUAL] = PREFILTEROPLESS,
[VK_COMPARE_OP_GREATER] = PREFILTEROPGEQUAL,
[VK_COMPARE_OP_NOT_EQUAL] = PREFILTEROPEQUAL,
[VK_COMPARE_OP_GREATER_OR_EQUAL] = PREFILTEROPGREATER,
[VK_COMPARE_OP_ALWAYS] = PREFILTEROPNEVER,
};
VkResult genX(CreateSampler)(
VkDevice _device,
const VkSamplerCreateInfo* pCreateInfo,
const VkAllocationCallbacks* pAllocator,
VkSampler* pSampler)
{
ANV_FROM_HANDLE(anv_device, device, _device);
struct anv_sampler *sampler;
assert(pCreateInfo->sType == VK_STRUCTURE_TYPE_SAMPLER_CREATE_INFO);
sampler = vk_zalloc2(&device->alloc, pAllocator, sizeof(*sampler), 8,
VK_SYSTEM_ALLOCATION_SCOPE_OBJECT);
if (!sampler)
return vk_error(VK_ERROR_OUT_OF_HOST_MEMORY);
sampler->n_planes = 1;
uint32_t border_color_offset = device->border_colors.offset +
pCreateInfo->borderColor * 64;
vk_foreach_struct(ext, pCreateInfo->pNext) {
switch (ext->sType) {
case VK_STRUCTURE_TYPE_SAMPLER_YCBCR_CONVERSION_INFO: {
VkSamplerYcbcrConversionInfo *pSamplerConversion =
(VkSamplerYcbcrConversionInfo *) ext;
ANV_FROM_HANDLE(anv_ycbcr_conversion, conversion,
pSamplerConversion->conversion);
if (conversion == NULL)
break;
sampler->n_planes = conversion->format->n_planes;
sampler->conversion = conversion;
break;
}
default:
anv_debug_ignored_stype(ext->sType);
break;
}
}
for (unsigned p = 0; p < sampler->n_planes; p++) {
const bool plane_has_chroma =
sampler->conversion && sampler->conversion->format->planes[p].has_chroma;
const VkFilter min_filter =
plane_has_chroma ? sampler->conversion->chroma_filter : pCreateInfo->minFilter;
const VkFilter mag_filter =
plane_has_chroma ? sampler->conversion->chroma_filter : pCreateInfo->magFilter;
const bool enable_min_filter_addr_rounding = min_filter != VK_FILTER_NEAREST;
const bool enable_mag_filter_addr_rounding = mag_filter != VK_FILTER_NEAREST;
/* From Broadwell PRM, SAMPLER_STATE:
* "Mip Mode Filter must be set to MIPFILTER_NONE for Planar YUV surfaces."
*/
const uint32_t mip_filter_mode =
(sampler->conversion &&
isl_format_is_yuv(sampler->conversion->format->planes[0].isl_format)) ?
MIPFILTER_NONE : vk_to_gen_mipmap_mode[pCreateInfo->mipmapMode];
struct GENX(SAMPLER_STATE) sampler_state = {
.SamplerDisable = false,
.TextureBorderColorMode = DX10OGL,
#if GEN_GEN >= 8
.LODPreClampMode = CLAMP_MODE_OGL,
#else
.LODPreClampEnable = CLAMP_ENABLE_OGL,
#endif
#if GEN_GEN == 8
.BaseMipLevel = 0.0,
#endif
.MipModeFilter = mip_filter_mode,
.MagModeFilter = vk_to_gen_tex_filter(mag_filter, pCreateInfo->anisotropyEnable),
.MinModeFilter = vk_to_gen_tex_filter(min_filter, pCreateInfo->anisotropyEnable),
.TextureLODBias = anv_clamp_f(pCreateInfo->mipLodBias, -16, 15.996),
.AnisotropicAlgorithm = EWAApproximation,
.MinLOD = anv_clamp_f(pCreateInfo->minLod, 0, 14),
.MaxLOD = anv_clamp_f(pCreateInfo->maxLod, 0, 14),
.ChromaKeyEnable = 0,
.ChromaKeyIndex = 0,
.ChromaKeyMode = 0,
.ShadowFunction = vk_to_gen_shadow_compare_op[pCreateInfo->compareOp],
.CubeSurfaceControlMode = OVERRIDE,
.BorderColorPointer = border_color_offset,
#if GEN_GEN >= 8
.LODClampMagnificationMode = MIPNONE,
#endif
.MaximumAnisotropy = vk_to_gen_max_anisotropy(pCreateInfo->maxAnisotropy),
.RAddressMinFilterRoundingEnable = enable_min_filter_addr_rounding,
.RAddressMagFilterRoundingEnable = enable_mag_filter_addr_rounding,
.VAddressMinFilterRoundingEnable = enable_min_filter_addr_rounding,
.VAddressMagFilterRoundingEnable = enable_mag_filter_addr_rounding,
.UAddressMinFilterRoundingEnable = enable_min_filter_addr_rounding,
.UAddressMagFilterRoundingEnable = enable_mag_filter_addr_rounding,
.TrilinearFilterQuality = 0,
.NonnormalizedCoordinateEnable = pCreateInfo->unnormalizedCoordinates,
.TCXAddressControlMode = vk_to_gen_tex_address[pCreateInfo->addressModeU],
.TCYAddressControlMode = vk_to_gen_tex_address[pCreateInfo->addressModeV],
.TCZAddressControlMode = vk_to_gen_tex_address[pCreateInfo->addressModeW],
};
GENX(SAMPLER_STATE_pack)(NULL, sampler->state[p], &sampler_state);
}
*pSampler = anv_sampler_to_handle(sampler);
return VK_SUCCESS;
}
|