summaryrefslogtreecommitdiff
path: root/src/intel/vulkan/gen8_cmd_buffer.c
blob: 58e41f29315a8884084b8eeebfb19f4f079e367f (plain)
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
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
/*
 * 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 "genxml/gen_macros.h"
#include "genxml/genX_pack.h"
#include "common/gen_guardband.h"

#if GEN_GEN == 8
void
gen8_cmd_buffer_emit_viewport(struct anv_cmd_buffer *cmd_buffer)
{
   struct anv_framebuffer *fb = cmd_buffer->state.framebuffer;
   uint32_t count = cmd_buffer->state.gfx.dynamic.viewport.count;
   const VkViewport *viewports =
      cmd_buffer->state.gfx.dynamic.viewport.viewports;
   struct anv_state sf_clip_state =
      anv_cmd_buffer_alloc_dynamic_state(cmd_buffer, count * 64, 64);

   for (uint32_t i = 0; i < count; i++) {
      const VkViewport *vp = &viewports[i];

      /* The gen7 state struct has just the matrix and guardband fields, the
       * gen8 struct adds the min/max viewport fields. */
      struct GENX(SF_CLIP_VIEWPORT) sfv = {
         .ViewportMatrixElementm00 = vp->width / 2,
         .ViewportMatrixElementm11 = vp->height / 2,
         .ViewportMatrixElementm22 = vp->maxDepth - vp->minDepth,
         .ViewportMatrixElementm30 = vp->x + vp->width / 2,
         .ViewportMatrixElementm31 = vp->y + vp->height / 2,
         .ViewportMatrixElementm32 = vp->minDepth,
         .XMinClipGuardband = -1.0f,
         .XMaxClipGuardband = 1.0f,
         .YMinClipGuardband = -1.0f,
         .YMaxClipGuardband = 1.0f,
         .XMinViewPort = vp->x,
         .XMaxViewPort = vp->x + vp->width - 1,
         .YMinViewPort = MIN2(vp->y, vp->y + vp->height),
         .YMaxViewPort = MAX2(vp->y, vp->y + vp->height) - 1,
      };

      if (fb) {
         /* We can only calculate a "real" guardband clip if we know the
          * framebuffer at the time we emit the packet.  Otherwise, we have
          * fall back to a worst-case guardband of [-1, 1].
          */
         gen_calculate_guardband_size(fb->width, fb->height,
                                      sfv.ViewportMatrixElementm00,
                                      sfv.ViewportMatrixElementm11,
                                      sfv.ViewportMatrixElementm30,
                                      sfv.ViewportMatrixElementm31,
                                      &sfv.XMinClipGuardband,
                                      &sfv.XMaxClipGuardband,
                                      &sfv.YMinClipGuardband,
                                      &sfv.YMaxClipGuardband);
      }

      GENX(SF_CLIP_VIEWPORT_pack)(NULL, sf_clip_state.map + i * 64, &sfv);
   }

   anv_batch_emit(&cmd_buffer->batch,
                  GENX(3DSTATE_VIEWPORT_STATE_POINTERS_SF_CLIP), clip) {
      clip.SFClipViewportPointer = sf_clip_state.offset;
   }
}

void
gen8_cmd_buffer_emit_depth_viewport(struct anv_cmd_buffer *cmd_buffer,
                                    bool depth_clamp_enable)
{
   uint32_t count = cmd_buffer->state.gfx.dynamic.viewport.count;
   const VkViewport *viewports =
      cmd_buffer->state.gfx.dynamic.viewport.viewports;
   struct anv_state cc_state =
      anv_cmd_buffer_alloc_dynamic_state(cmd_buffer, count * 8, 32);

   for (uint32_t i = 0; i < count; i++) {
      const VkViewport *vp = &viewports[i];

      struct GENX(CC_VIEWPORT) cc_viewport = {
         .MinimumDepth = depth_clamp_enable ? vp->minDepth : 0.0f,
         .MaximumDepth = depth_clamp_enable ? vp->maxDepth : 1.0f,
      };

      GENX(CC_VIEWPORT_pack)(NULL, cc_state.map + i * 8, &cc_viewport);
   }

   anv_batch_emit(&cmd_buffer->batch,
                  GENX(3DSTATE_VIEWPORT_STATE_POINTERS_CC), cc) {
      cc.CCViewportPointer = cc_state.offset;
   }
}
#endif

void
genX(cmd_buffer_enable_pma_fix)(struct anv_cmd_buffer *cmd_buffer, bool enable)
{
   if (cmd_buffer->state.pma_fix_enabled == enable)
      return;

   cmd_buffer->state.pma_fix_enabled = enable;

   /* According to the Broadwell PIPE_CONTROL documentation, software should
    * emit a PIPE_CONTROL with the CS Stall and Depth Cache Flush bits set
    * prior to the LRI.  If stencil buffer writes are enabled, then a Render
    * Cache Flush is also necessary.
    *
    * The Skylake docs say to use a depth stall rather than a command
    * streamer stall.  However, the hardware seems to violently disagree.
    * A full command streamer stall seems to be needed in both cases.
    */
   anv_batch_emit(&cmd_buffer->batch, GENX(PIPE_CONTROL), pc) {
      pc.DepthCacheFlushEnable = true;
      pc.CommandStreamerStallEnable = true;
      pc.RenderTargetCacheFlushEnable = true;
   }

#if GEN_GEN == 9

   uint32_t cache_mode;
   anv_pack_struct(&cache_mode, GENX(CACHE_MODE_0),
                   .STCPMAOptimizationEnable = enable,
                   .STCPMAOptimizationEnableMask = true);
   anv_batch_emit(&cmd_buffer->batch, GENX(MI_LOAD_REGISTER_IMM), lri) {
      lri.RegisterOffset   = GENX(CACHE_MODE_0_num);
      lri.DataDWord        = cache_mode;
   }

#elif GEN_GEN == 8

   uint32_t cache_mode;
   anv_pack_struct(&cache_mode, GENX(CACHE_MODE_1),
                   .NPPMAFixEnable = enable,
                   .NPEarlyZFailsDisable = enable,
                   .NPPMAFixEnableMask = true,
                   .NPEarlyZFailsDisableMask = true);
   anv_batch_emit(&cmd_buffer->batch, GENX(MI_LOAD_REGISTER_IMM), lri) {
      lri.RegisterOffset   = GENX(CACHE_MODE_1_num);
      lri.DataDWord        = cache_mode;
   }

#endif /* GEN_GEN == 8 */

   /* After the LRI, a PIPE_CONTROL with both the Depth Stall and Depth Cache
    * Flush bits is often necessary.  We do it regardless because it's easier.
    * The render cache flush is also necessary if stencil writes are enabled.
    *
    * Again, the Skylake docs give a different set of flushes but the BDW
    * flushes seem to work just as well.
    */
   anv_batch_emit(&cmd_buffer->batch, GENX(PIPE_CONTROL), pc) {
      pc.DepthStallEnable = true;
      pc.DepthCacheFlushEnable = true;
      pc.RenderTargetCacheFlushEnable = true;
   }
}

UNUSED static bool
want_depth_pma_fix(struct anv_cmd_buffer *cmd_buffer)
{
   assert(GEN_GEN == 8);

   /* From the Broadwell PRM Vol. 2c CACHE_MODE_1::NP_PMA_FIX_ENABLE:
    *
    *    SW must set this bit in order to enable this fix when following
    *    expression is TRUE.
    *
    *    3DSTATE_WM::ForceThreadDispatch != 1 &&
    *    !(3DSTATE_RASTER::ForceSampleCount != NUMRASTSAMPLES_0) &&
    *    (3DSTATE_DEPTH_BUFFER::SURFACE_TYPE != NULL) &&
    *    (3DSTATE_DEPTH_BUFFER::HIZ Enable) &&
    *    !(3DSTATE_WM::EDSC_Mode == EDSC_PREPS) &&
    *    (3DSTATE_PS_EXTRA::PixelShaderValid) &&
    *    !(3DSTATE_WM_HZ_OP::DepthBufferClear ||
    *      3DSTATE_WM_HZ_OP::DepthBufferResolve ||
    *      3DSTATE_WM_HZ_OP::Hierarchical Depth Buffer Resolve Enable ||
    *      3DSTATE_WM_HZ_OP::StencilBufferClear) &&
    *    (3DSTATE_WM_DEPTH_STENCIL::DepthTestEnable) &&
    *    (((3DSTATE_PS_EXTRA::PixelShaderKillsPixels ||
    *       3DSTATE_PS_EXTRA::oMask Present to RenderTarget ||
    *       3DSTATE_PS_BLEND::AlphaToCoverageEnable ||
    *       3DSTATE_PS_BLEND::AlphaTestEnable ||
    *       3DSTATE_WM_CHROMAKEY::ChromaKeyKillEnable) &&
    *      3DSTATE_WM::ForceKillPix != ForceOff &&
    *      ((3DSTATE_WM_DEPTH_STENCIL::DepthWriteEnable &&
    *        3DSTATE_DEPTH_BUFFER::DEPTH_WRITE_ENABLE) ||
    *       (3DSTATE_WM_DEPTH_STENCIL::Stencil Buffer Write Enable &&
    *        3DSTATE_DEPTH_BUFFER::STENCIL_WRITE_ENABLE &&
    *        3DSTATE_STENCIL_BUFFER::STENCIL_BUFFER_ENABLE))) ||
    *     (3DSTATE_PS_EXTRA:: Pixel Shader Computed Depth mode != PSCDEPTH_OFF))
    */

   /* These are always true:
    *    3DSTATE_WM::ForceThreadDispatch != 1 &&
    *    !(3DSTATE_RASTER::ForceSampleCount != NUMRASTSAMPLES_0)
    */

   /* We only enable the PMA fix if we know for certain that HiZ is enabled.
    * If we don't know whether HiZ is enabled or not, we disable the PMA fix
    * and there is no harm.
    *
    * (3DSTATE_DEPTH_BUFFER::SURFACE_TYPE != NULL) &&
    * 3DSTATE_DEPTH_BUFFER::HIZ Enable
    */
   if (!cmd_buffer->state.hiz_enabled)
      return false;

   /* 3DSTATE_PS_EXTRA::PixelShaderValid */
   struct anv_pipeline *pipeline = cmd_buffer->state.gfx.base.pipeline;
   if (!anv_pipeline_has_stage(pipeline, MESA_SHADER_FRAGMENT))
      return false;

   /* !(3DSTATE_WM::EDSC_Mode == EDSC_PREPS) */
   const struct brw_wm_prog_data *wm_prog_data = get_wm_prog_data(pipeline);
   if (wm_prog_data->early_fragment_tests)
      return false;

   /* We never use anv_pipeline for HiZ ops so this is trivially true:
    *    !(3DSTATE_WM_HZ_OP::DepthBufferClear ||
    *      3DSTATE_WM_HZ_OP::DepthBufferResolve ||
    *      3DSTATE_WM_HZ_OP::Hierarchical Depth Buffer Resolve Enable ||
    *      3DSTATE_WM_HZ_OP::StencilBufferClear)
    */

   /* 3DSTATE_WM_DEPTH_STENCIL::DepthTestEnable */
   if (!pipeline->depth_test_enable)
      return false;

   /* (((3DSTATE_PS_EXTRA::PixelShaderKillsPixels ||
    *    3DSTATE_PS_EXTRA::oMask Present to RenderTarget ||
    *    3DSTATE_PS_BLEND::AlphaToCoverageEnable ||
    *    3DSTATE_PS_BLEND::AlphaTestEnable ||
    *    3DSTATE_WM_CHROMAKEY::ChromaKeyKillEnable) &&
    *   3DSTATE_WM::ForceKillPix != ForceOff &&
    *   ((3DSTATE_WM_DEPTH_STENCIL::DepthWriteEnable &&
    *     3DSTATE_DEPTH_BUFFER::DEPTH_WRITE_ENABLE) ||
    *    (3DSTATE_WM_DEPTH_STENCIL::Stencil Buffer Write Enable &&
    *     3DSTATE_DEPTH_BUFFER::STENCIL_WRITE_ENABLE &&
    *     3DSTATE_STENCIL_BUFFER::STENCIL_BUFFER_ENABLE))) ||
    *  (3DSTATE_PS_EXTRA:: Pixel Shader Computed Depth mode != PSCDEPTH_OFF))
    */
   return (pipeline->kill_pixel && (pipeline->writes_depth ||
                                    pipeline->writes_stencil)) ||
          wm_prog_data->computed_depth_mode != PSCDEPTH_OFF;
}

UNUSED static bool
want_stencil_pma_fix(struct anv_cmd_buffer *cmd_buffer)
{
   if (GEN_GEN > 9)
      return false;
   assert(GEN_GEN == 9);

   /* From the Skylake PRM Vol. 2c CACHE_MODE_1::STC PMA Optimization Enable:
    *
    *    Clearing this bit will force the STC cache to wait for pending
    *    retirement of pixels at the HZ-read stage and do the STC-test for
    *    Non-promoted, R-computed and Computed depth modes instead of
    *    postponing the STC-test to RCPFE.
    *
    *    STC_TEST_EN = 3DSTATE_STENCIL_BUFFER::STENCIL_BUFFER_ENABLE &&
    *                  3DSTATE_WM_DEPTH_STENCIL::StencilTestEnable
    *
    *    STC_WRITE_EN = 3DSTATE_STENCIL_BUFFER::STENCIL_BUFFER_ENABLE &&
    *                   (3DSTATE_WM_DEPTH_STENCIL::Stencil Buffer Write Enable &&
    *                    3DSTATE_DEPTH_BUFFER::STENCIL_WRITE_ENABLE)
    *
    *    COMP_STC_EN = STC_TEST_EN &&
    *                  3DSTATE_PS_EXTRA::PixelShaderComputesStencil
    *
    *    SW parses the pipeline states to generate the following logical
    *    signal indicating if PMA FIX can be enabled.
    *
    *    STC_PMA_OPT =
    *       3DSTATE_WM::ForceThreadDispatch != 1 &&
    *       !(3DSTATE_RASTER::ForceSampleCount != NUMRASTSAMPLES_0) &&
    *       3DSTATE_DEPTH_BUFFER::SURFACE_TYPE != NULL &&
    *       3DSTATE_DEPTH_BUFFER::HIZ Enable &&
    *       !(3DSTATE_WM::EDSC_Mode == 2) &&
    *       3DSTATE_PS_EXTRA::PixelShaderValid &&
    *       !(3DSTATE_WM_HZ_OP::DepthBufferClear ||
    *         3DSTATE_WM_HZ_OP::DepthBufferResolve ||
    *         3DSTATE_WM_HZ_OP::Hierarchical Depth Buffer Resolve Enable ||
    *         3DSTATE_WM_HZ_OP::StencilBufferClear) &&
    *       (COMP_STC_EN || STC_WRITE_EN) &&
    *       ((3DSTATE_PS_EXTRA::PixelShaderKillsPixels ||
    *         3DSTATE_WM::ForceKillPix == ON ||
    *         3DSTATE_PS_EXTRA::oMask Present to RenderTarget ||
    *         3DSTATE_PS_BLEND::AlphaToCoverageEnable ||
    *         3DSTATE_PS_BLEND::AlphaTestEnable ||
    *         3DSTATE_WM_CHROMAKEY::ChromaKeyKillEnable) ||
    *        (3DSTATE_PS_EXTRA::Pixel Shader Computed Depth mode != PSCDEPTH_OFF))
    */

   /* These are always true:
    *    3DSTATE_WM::ForceThreadDispatch != 1 &&
    *    !(3DSTATE_RASTER::ForceSampleCount != NUMRASTSAMPLES_0)
    */

   /* We only enable the PMA fix if we know for certain that HiZ is enabled.
    * If we don't know whether HiZ is enabled or not, we disable the PMA fix
    * and there is no harm.
    *
    * (3DSTATE_DEPTH_BUFFER::SURFACE_TYPE != NULL) &&
    * 3DSTATE_DEPTH_BUFFER::HIZ Enable
    */
   if (!cmd_buffer->state.hiz_enabled)
      return false;

   /* We can't possibly know if HiZ is enabled without the framebuffer */
   assert(cmd_buffer->state.framebuffer);

   /* HiZ is enabled so we had better have a depth buffer with HiZ */
   const struct anv_image_view *ds_iview =
      anv_cmd_buffer_get_depth_stencil_view(cmd_buffer);
   assert(ds_iview && ds_iview->image->planes[0].aux_usage == ISL_AUX_USAGE_HIZ);

   /* 3DSTATE_PS_EXTRA::PixelShaderValid */
   struct anv_pipeline *pipeline = cmd_buffer->state.gfx.base.pipeline;
   if (!anv_pipeline_has_stage(pipeline, MESA_SHADER_FRAGMENT))
      return false;

   /* !(3DSTATE_WM::EDSC_Mode == 2) */
   const struct brw_wm_prog_data *wm_prog_data = get_wm_prog_data(pipeline);
   if (wm_prog_data->early_fragment_tests)
      return false;

   /* We never use anv_pipeline for HiZ ops so this is trivially true:
   *    !(3DSTATE_WM_HZ_OP::DepthBufferClear ||
    *      3DSTATE_WM_HZ_OP::DepthBufferResolve ||
    *      3DSTATE_WM_HZ_OP::Hierarchical Depth Buffer Resolve Enable ||
    *      3DSTATE_WM_HZ_OP::StencilBufferClear)
    */

   /* 3DSTATE_STENCIL_BUFFER::STENCIL_BUFFER_ENABLE &&
    * 3DSTATE_WM_DEPTH_STENCIL::StencilTestEnable
    */
   const bool stc_test_en =
      (ds_iview->image->aspects & VK_IMAGE_ASPECT_STENCIL_BIT) &&
      pipeline->stencil_test_enable;

   /* 3DSTATE_STENCIL_BUFFER::STENCIL_BUFFER_ENABLE &&
    * (3DSTATE_WM_DEPTH_STENCIL::Stencil Buffer Write Enable &&
    *  3DSTATE_DEPTH_BUFFER::STENCIL_WRITE_ENABLE)
    */
   const bool stc_write_en =
      (ds_iview->image->aspects & VK_IMAGE_ASPECT_STENCIL_BIT) &&
      (cmd_buffer->state.gfx.dynamic.stencil_write_mask.front ||
       cmd_buffer->state.gfx.dynamic.stencil_write_mask.back) &&
      pipeline->writes_stencil;

   /* STC_TEST_EN && 3DSTATE_PS_EXTRA::PixelShaderComputesStencil */
   const bool comp_stc_en = stc_test_en && wm_prog_data->computed_stencil;

   /* COMP_STC_EN || STC_WRITE_EN */
   if (!(comp_stc_en || stc_write_en))
      return false;

   /* (3DSTATE_PS_EXTRA::PixelShaderKillsPixels ||
    *  3DSTATE_WM::ForceKillPix == ON ||
    *  3DSTATE_PS_EXTRA::oMask Present to RenderTarget ||
    *  3DSTATE_PS_BLEND::AlphaToCoverageEnable ||
    *  3DSTATE_PS_BLEND::AlphaTestEnable ||
    *  3DSTATE_WM_CHROMAKEY::ChromaKeyKillEnable) ||
    * (3DSTATE_PS_EXTRA::Pixel Shader Computed Depth mode != PSCDEPTH_OFF)
    */
   return pipeline->kill_pixel ||
          wm_prog_data->computed_depth_mode != PSCDEPTH_OFF;
}

void
genX(cmd_buffer_flush_dynamic_state)(struct anv_cmd_buffer *cmd_buffer)
{
   struct anv_pipeline *pipeline = cmd_buffer->state.gfx.base.pipeline;
   struct anv_dynamic_state *d = &cmd_buffer->state.gfx.dynamic;

   if (cmd_buffer->state.gfx.dirty & (ANV_CMD_DIRTY_PIPELINE |
                                      ANV_CMD_DIRTY_DYNAMIC_LINE_WIDTH)) {
      uint32_t sf_dw[GENX(3DSTATE_SF_length)];
      struct GENX(3DSTATE_SF) sf = {
         GENX(3DSTATE_SF_header),
      };
#if GEN_GEN == 8
      if (cmd_buffer->device->info.is_cherryview) {
         sf.CHVLineWidth = d->line_width;
      } else {
         sf.LineWidth = d->line_width;
      }
#else
      sf.LineWidth = d->line_width,
#endif
      GENX(3DSTATE_SF_pack)(NULL, sf_dw, &sf);
      anv_batch_emit_merge(&cmd_buffer->batch, sf_dw, pipeline->gen8.sf);
   }

   if (cmd_buffer->state.gfx.dirty & (ANV_CMD_DIRTY_PIPELINE |
                                      ANV_CMD_DIRTY_DYNAMIC_DEPTH_BIAS)){
      uint32_t raster_dw[GENX(3DSTATE_RASTER_length)];
      struct GENX(3DSTATE_RASTER) raster = {
         GENX(3DSTATE_RASTER_header),
         .GlobalDepthOffsetConstant = d->depth_bias.bias,
         .GlobalDepthOffsetScale = d->depth_bias.slope,
         .GlobalDepthOffsetClamp = d->depth_bias.clamp
      };
      GENX(3DSTATE_RASTER_pack)(NULL, raster_dw, &raster);
      anv_batch_emit_merge(&cmd_buffer->batch, raster_dw,
                           pipeline->gen8.raster);
   }

   /* Stencil reference values moved from COLOR_CALC_STATE in gen8 to
    * 3DSTATE_WM_DEPTH_STENCIL in gen9. That means the dirty bits gets split
    * across different state packets for gen8 and gen9. We handle that by
    * using a big old #if switch here.
    */
#if GEN_GEN == 8
   if (cmd_buffer->state.gfx.dirty & (ANV_CMD_DIRTY_DYNAMIC_BLEND_CONSTANTS |
                                      ANV_CMD_DIRTY_DYNAMIC_STENCIL_REFERENCE)) {
      struct anv_state cc_state =
         anv_cmd_buffer_alloc_dynamic_state(cmd_buffer,
                                            GENX(COLOR_CALC_STATE_length) * 4,
                                            64);
      struct GENX(COLOR_CALC_STATE) cc = {
         .BlendConstantColorRed = d->blend_constants[0],
         .BlendConstantColorGreen = d->blend_constants[1],
         .BlendConstantColorBlue = d->blend_constants[2],
         .BlendConstantColorAlpha = d->blend_constants[3],
         .StencilReferenceValue = d->stencil_reference.front & 0xff,
         .BackfaceStencilReferenceValue = d->stencil_reference.back & 0xff,
      };
      GENX(COLOR_CALC_STATE_pack)(NULL, cc_state.map, &cc);

      anv_batch_emit(&cmd_buffer->batch, GENX(3DSTATE_CC_STATE_POINTERS), ccp) {
         ccp.ColorCalcStatePointer        = cc_state.offset;
         ccp.ColorCalcStatePointerValid   = true;
      }
   }

   if (cmd_buffer->state.gfx.dirty & (ANV_CMD_DIRTY_PIPELINE |
                                      ANV_CMD_DIRTY_RENDER_TARGETS |
                                      ANV_CMD_DIRTY_DYNAMIC_STENCIL_COMPARE_MASK |
                                      ANV_CMD_DIRTY_DYNAMIC_STENCIL_WRITE_MASK)) {
      uint32_t wm_depth_stencil_dw[GENX(3DSTATE_WM_DEPTH_STENCIL_length)];

      struct GENX(3DSTATE_WM_DEPTH_STENCIL wm_depth_stencil) = {
         GENX(3DSTATE_WM_DEPTH_STENCIL_header),

         .StencilTestMask = d->stencil_compare_mask.front & 0xff,
         .StencilWriteMask = d->stencil_write_mask.front & 0xff,

         .BackfaceStencilTestMask = d->stencil_compare_mask.back & 0xff,
         .BackfaceStencilWriteMask = d->stencil_write_mask.back & 0xff,

         .StencilBufferWriteEnable =
            (d->stencil_write_mask.front || d->stencil_write_mask.back) &&
            pipeline->writes_stencil,
      };
      GENX(3DSTATE_WM_DEPTH_STENCIL_pack)(NULL, wm_depth_stencil_dw,
                                          &wm_depth_stencil);

      anv_batch_emit_merge(&cmd_buffer->batch, wm_depth_stencil_dw,
                           pipeline->gen8.wm_depth_stencil);

      genX(cmd_buffer_enable_pma_fix)(cmd_buffer,
                                      want_depth_pma_fix(cmd_buffer));
   }
#else
   if (cmd_buffer->state.gfx.dirty & ANV_CMD_DIRTY_DYNAMIC_BLEND_CONSTANTS) {
      struct anv_state cc_state =
         anv_cmd_buffer_alloc_dynamic_state(cmd_buffer,
                                            GENX(COLOR_CALC_STATE_length) * 4,
                                            64);
      struct GENX(COLOR_CALC_STATE) cc = {
         .BlendConstantColorRed = d->blend_constants[0],
         .BlendConstantColorGreen = d->blend_constants[1],
         .BlendConstantColorBlue = d->blend_constants[2],
         .BlendConstantColorAlpha = d->blend_constants[3],
      };
      GENX(COLOR_CALC_STATE_pack)(NULL, cc_state.map, &cc);

      anv_batch_emit(&cmd_buffer->batch, GENX(3DSTATE_CC_STATE_POINTERS), ccp) {
         ccp.ColorCalcStatePointer = cc_state.offset;
         ccp.ColorCalcStatePointerValid = true;
      }
   }

   if (cmd_buffer->state.gfx.dirty & (ANV_CMD_DIRTY_PIPELINE |
                                      ANV_CMD_DIRTY_RENDER_TARGETS |
                                      ANV_CMD_DIRTY_DYNAMIC_STENCIL_COMPARE_MASK |
                                      ANV_CMD_DIRTY_DYNAMIC_STENCIL_WRITE_MASK |
                                      ANV_CMD_DIRTY_DYNAMIC_STENCIL_REFERENCE)) {
      uint32_t dwords[GENX(3DSTATE_WM_DEPTH_STENCIL_length)];
      struct GENX(3DSTATE_WM_DEPTH_STENCIL) wm_depth_stencil = {
         GENX(3DSTATE_WM_DEPTH_STENCIL_header),

         .StencilTestMask = d->stencil_compare_mask.front & 0xff,
         .StencilWriteMask = d->stencil_write_mask.front & 0xff,

         .BackfaceStencilTestMask = d->stencil_compare_mask.back & 0xff,
         .BackfaceStencilWriteMask = d->stencil_write_mask.back & 0xff,

         .StencilReferenceValue = d->stencil_reference.front & 0xff,
         .BackfaceStencilReferenceValue = d->stencil_reference.back & 0xff,

         .StencilBufferWriteEnable =
            (d->stencil_write_mask.front || d->stencil_write_mask.back) &&
            pipeline->writes_stencil,
      };
      GENX(3DSTATE_WM_DEPTH_STENCIL_pack)(NULL, dwords, &wm_depth_stencil);

      anv_batch_emit_merge(&cmd_buffer->batch, dwords,
                           pipeline->gen9.wm_depth_stencil);

      genX(cmd_buffer_enable_pma_fix)(cmd_buffer,
                                      want_stencil_pma_fix(cmd_buffer));
   }
#endif

#if GEN_GEN >= 12
   if(cmd_buffer->state.gfx.dirty & (ANV_CMD_DIRTY_PIPELINE |
                                     ANV_CMD_DIRTY_DYNAMIC_DEPTH_BOUNDS)) {
      anv_batch_emit(&cmd_buffer->batch, GENX(3DSTATE_DEPTH_BOUNDS), db) {
         db.DepthBoundsTestValueModifyDisable = false;
         db.DepthBoundsTestEnableModifyDisable = false;
         db.DepthBoundsTestEnable = pipeline->depth_bounds_test_enable;
         db.DepthBoundsTestMinValue = d->depth_bounds.min;
         db.DepthBoundsTestMaxValue = d->depth_bounds.max;
      }
   }
#endif

   if (cmd_buffer->state.gfx.dirty & ANV_CMD_DIRTY_DYNAMIC_LINE_STIPPLE) {
      anv_batch_emit(&cmd_buffer->batch, GENX(3DSTATE_LINE_STIPPLE), ls) {
         ls.LineStipplePattern = d->line_stipple.pattern;
         ls.LineStippleInverseRepeatCount =
            1.0f / MAX2(1, d->line_stipple.factor);
         ls.LineStippleRepeatCount = d->line_stipple.factor;
      }
   }

   if (cmd_buffer->state.gfx.dirty & (ANV_CMD_DIRTY_PIPELINE |
                                      ANV_CMD_DIRTY_INDEX_BUFFER)) {
      anv_batch_emit(&cmd_buffer->batch, GENX(3DSTATE_VF), vf) {
         vf.IndexedDrawCutIndexEnable  = pipeline->primitive_restart;
         vf.CutIndex                   = cmd_buffer->state.restart_index;
      }
   }

   cmd_buffer->state.gfx.dirty = 0;
}

static uint32_t vk_to_gen_index_type(VkIndexType type)
{
   switch (type) {
   case VK_INDEX_TYPE_UINT8_EXT:
      return INDEX_BYTE;
   case VK_INDEX_TYPE_UINT16:
      return INDEX_WORD;
   case VK_INDEX_TYPE_UINT32:
      return INDEX_DWORD;
   default:
      unreachable("invalid index type");
   }
}

static uint32_t restart_index_for_type(VkIndexType type)
{
   switch (type) {
   case VK_INDEX_TYPE_UINT8_EXT:
      return UINT8_MAX;
   case VK_INDEX_TYPE_UINT16:
      return UINT16_MAX;
   case VK_INDEX_TYPE_UINT32:
      return UINT32_MAX;
   default:
      unreachable("invalid index type");
   }
}

void genX(CmdBindIndexBuffer)(
    VkCommandBuffer                             commandBuffer,
    VkBuffer                                    _buffer,
    VkDeviceSize                                offset,
    VkIndexType                                 indexType)
{
   ANV_FROM_HANDLE(anv_cmd_buffer, cmd_buffer, commandBuffer);
   ANV_FROM_HANDLE(anv_buffer, buffer, _buffer);

   cmd_buffer->state.restart_index = restart_index_for_type(indexType);

   anv_batch_emit(&cmd_buffer->batch, GENX(3DSTATE_INDEX_BUFFER), ib) {
      ib.IndexFormat                = vk_to_gen_index_type(indexType);
      ib.MOCS                       = anv_mocs_for_bo(cmd_buffer->device,
                                                      buffer->address.bo);
      ib.BufferStartingAddress      = anv_address_add(buffer->address, offset);
      ib.BufferSize                 = buffer->size - offset;
   }

   cmd_buffer->state.gfx.dirty |= ANV_CMD_DIRTY_INDEX_BUFFER;
}