summaryrefslogtreecommitdiff
path: root/lib/rendercopy_gen6.c
blob: dafee88a511e4d22e36ae585baf657eaa4c75af9 (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
#include "rendercopy.h"
#include "gen6_render.h"

#include <assert.h>

#define ALIGN(x, y) (((x) + (y)-1) & ~((y)-1))
#define VERTEX_SIZE (3*4)

static const uint32_t ps_kernel_nomask_affine[][4] = {
	{ 0x0060005a, 0x204077be, 0x000000c0, 0x008d0040 },
	{ 0x0060005a, 0x206077be, 0x000000c0, 0x008d0080 },
	{ 0x0060005a, 0x208077be, 0x000000d0, 0x008d0040 },
	{ 0x0060005a, 0x20a077be, 0x000000d0, 0x008d0080 },
	{ 0x00000201, 0x20080061, 0x00000000, 0x00000000 },
	{ 0x00600001, 0x20200022, 0x008d0000, 0x00000000 },
	{ 0x02800031, 0x21c01cc9, 0x00000020, 0x0a8a0001 },
	{ 0x00600001, 0x204003be, 0x008d01c0, 0x00000000 },
	{ 0x00600001, 0x206003be, 0x008d01e0, 0x00000000 },
	{ 0x00600001, 0x208003be, 0x008d0200, 0x00000000 },
	{ 0x00600001, 0x20a003be, 0x008d0220, 0x00000000 },
	{ 0x00600001, 0x20c003be, 0x008d0240, 0x00000000 },
	{ 0x00600001, 0x20e003be, 0x008d0260, 0x00000000 },
	{ 0x00600001, 0x210003be, 0x008d0280, 0x00000000 },
	{ 0x00600001, 0x212003be, 0x008d02a0, 0x00000000 },
	{ 0x05800031, 0x24001cc8, 0x00000040, 0x90019000 },
	{ 0x0000007e, 0x00000000, 0x00000000, 0x00000000 },
	{ 0x0000007e, 0x00000000, 0x00000000, 0x00000000 },
	{ 0x0000007e, 0x00000000, 0x00000000, 0x00000000 },
	{ 0x0000007e, 0x00000000, 0x00000000, 0x00000000 },
	{ 0x0000007e, 0x00000000, 0x00000000, 0x00000000 },
	{ 0x0000007e, 0x00000000, 0x00000000, 0x00000000 },
	{ 0x0000007e, 0x00000000, 0x00000000, 0x00000000 },
	{ 0x0000007e, 0x00000000, 0x00000000, 0x00000000 },
};

static uint32_t
batch_used(struct intel_batchbuffer *batch)
{
	return batch->ptr - batch->buffer;
}

static uint32_t
batch_align(struct intel_batchbuffer *batch, uint32_t align)
{
	uint32_t offset = batch_used(batch);
	offset = ALIGN(offset, align);
	batch->ptr = batch->buffer + offset;
	return offset;
}

static uint32_t
batch_round_upto(struct intel_batchbuffer *batch, uint32_t divisor)
{
	uint32_t offset = batch_used(batch);
	offset = (offset + divisor-1) / divisor * divisor;
	batch->ptr = batch->buffer + offset;
	return offset;
}

static void *
batch_alloc(struct intel_batchbuffer *batch, uint32_t size, uint32_t align)
{
	uint32_t offset = batch_align(batch, align);
	batch->ptr += size;
	return memset(batch->buffer + offset, 0, size);
}

static uint32_t
batch_offset(struct intel_batchbuffer *batch, void *ptr)
{
	return (uint8_t *)ptr - batch->buffer;
}

static uint32_t
batch_copy(struct intel_batchbuffer *batch, const void *ptr, uint32_t size, uint32_t align)
{
	return batch_offset(batch, memcpy(batch_alloc(batch, size, align), ptr, size));
}

static void
gen6_render_flush(struct intel_batchbuffer *batch, uint32_t batch_end)
{
	int ret;

	ret = drm_intel_bo_subdata(batch->bo, 0, 4096, batch->buffer);
	if (ret == 0)
		ret = drm_intel_bo_mrb_exec(batch->bo, batch_end,
					    NULL, 0, 0, 0);
	assert(ret == 0);
}

static uint32_t
gen6_bind_buf(struct intel_batchbuffer *batch, struct scratch_buf *buf,
	      uint32_t format, int is_dst)
{
	struct gen6_surface_state *ss;
	uint32_t write_domain, read_domain;
	int ret;

	if (is_dst) {
		write_domain = read_domain = I915_GEM_DOMAIN_RENDER;
	} else {
		write_domain = 0;
		read_domain = I915_GEM_DOMAIN_SAMPLER;
	}

	ss = batch_alloc(batch, sizeof(*ss), 32);
	ss->ss0.surface_type = GEN6_SURFACE_2D;
	ss->ss0.surface_format = format;

	ss->ss0.data_return_format = GEN6_SURFACERETURNFORMAT_FLOAT32;
	ss->ss0.color_blend = 1;
	ss->ss1.base_addr = buf->bo->offset;

	ret = drm_intel_bo_emit_reloc(batch->bo,
				      batch_offset(batch, ss) + 4,
				      buf->bo, 0,
				      read_domain, write_domain);
	assert(ret == 0);

	ss->ss2.height = buf_height(buf) - 1;
	ss->ss2.width  = buf_width(buf) - 1;
	ss->ss3.pitch  = buf->stride - 1;
	ss->ss3.tiled_surface = buf->tiling != I915_TILING_NONE;
	ss->ss3.tile_walk     = buf->tiling == I915_TILING_Y;

	return batch_offset(batch, ss);
}

static uint32_t
gen6_bind_surfaces(struct intel_batchbuffer *batch,
		   struct scratch_buf *src,
		   struct scratch_buf *dst)
{
	uint32_t *binding_table;

	binding_table = batch_alloc(batch, 32, 32);

	binding_table[0] =
		gen6_bind_buf(batch, dst, GEN6_SURFACEFORMAT_B8G8R8A8_UNORM, 1);
	binding_table[1] =
		gen6_bind_buf(batch, src, GEN6_SURFACEFORMAT_B8G8R8A8_UNORM, 0);

	return batch_offset(batch, binding_table);
}

static void
gen6_emit_sip(struct intel_batchbuffer *batch)
{
	OUT_BATCH(GEN6_STATE_SIP | 0);
	OUT_BATCH(0);
}

static void
gen6_emit_urb(struct intel_batchbuffer *batch)
{
	OUT_BATCH(GEN6_3DSTATE_URB | (3 - 2));
	OUT_BATCH((1 - 1) << GEN6_3DSTATE_URB_VS_SIZE_SHIFT |
		  24 << GEN6_3DSTATE_URB_VS_ENTRIES_SHIFT); /* at least 24 on GEN6 */
	OUT_BATCH(0 << GEN6_3DSTATE_URB_GS_SIZE_SHIFT |
		  0 << GEN6_3DSTATE_URB_GS_ENTRIES_SHIFT); /* no GS thread */
}

static void
gen6_emit_state_base_address(struct intel_batchbuffer *batch)
{
	OUT_BATCH(GEN6_STATE_BASE_ADDRESS | (10 - 2));
	OUT_BATCH(0); /* general */
	OUT_RELOC(batch->bo, /* surface */
		  I915_GEM_DOMAIN_INSTRUCTION, 0,
		  BASE_ADDRESS_MODIFY);
	OUT_RELOC(batch->bo, /* instruction */
		  I915_GEM_DOMAIN_INSTRUCTION, 0,
		  BASE_ADDRESS_MODIFY);
	OUT_BATCH(0); /* indirect */
	OUT_RELOC(batch->bo, /* dynamic */
		  I915_GEM_DOMAIN_INSTRUCTION, 0,
		  BASE_ADDRESS_MODIFY);

	/* upper bounds, disable */
	OUT_BATCH(0);
	OUT_BATCH(BASE_ADDRESS_MODIFY);
	OUT_BATCH(0);
	OUT_BATCH(BASE_ADDRESS_MODIFY);
}

static void
gen6_emit_viewports(struct intel_batchbuffer *batch, uint32_t cc_vp)
{
	OUT_BATCH(GEN6_3DSTATE_VIEWPORT_STATE_POINTERS |
		  GEN6_3DSTATE_VIEWPORT_STATE_MODIFY_CC |
		  (4 - 2));
	OUT_BATCH(0);
	OUT_BATCH(0);
	OUT_BATCH(cc_vp);
}

static void
gen6_emit_vs(struct intel_batchbuffer *batch)
{
	/* disable VS constant buffer */
	OUT_BATCH(GEN6_3DSTATE_CONSTANT_VS | (5 - 2));
	OUT_BATCH(0);
	OUT_BATCH(0);
	OUT_BATCH(0);
	OUT_BATCH(0);

	OUT_BATCH(GEN6_3DSTATE_VS | (6 - 2));
	OUT_BATCH(0); /* no VS kernel */
	OUT_BATCH(0);
	OUT_BATCH(0);
	OUT_BATCH(0);
	OUT_BATCH(0); /* pass-through */
}

static void
gen6_emit_gs(struct intel_batchbuffer *batch)
{
	/* disable GS constant buffer */
	OUT_BATCH(GEN6_3DSTATE_CONSTANT_GS | (5 - 2));
	OUT_BATCH(0);
	OUT_BATCH(0);
	OUT_BATCH(0);
	OUT_BATCH(0);

	OUT_BATCH(GEN6_3DSTATE_GS | (7 - 2));
	OUT_BATCH(0); /* no GS kernel */
	OUT_BATCH(0);
	OUT_BATCH(0);
	OUT_BATCH(0);
	OUT_BATCH(0);
	OUT_BATCH(0); /* pass-through */
}

static void
gen6_emit_clip(struct intel_batchbuffer *batch)
{
	OUT_BATCH(GEN6_3DSTATE_CLIP | (4 - 2));
	OUT_BATCH(0);
	OUT_BATCH(0); /* pass-through */
	OUT_BATCH(0);
}

static void
gen6_emit_wm_constants(struct intel_batchbuffer *batch)
{
	/* disable WM constant buffer */
	OUT_BATCH(GEN6_3DSTATE_CONSTANT_PS | (5 - 2));
	OUT_BATCH(0);
	OUT_BATCH(0);
	OUT_BATCH(0);
	OUT_BATCH(0);
}

static void
gen6_emit_null_depth_buffer(struct intel_batchbuffer *batch)
{
	OUT_BATCH(GEN6_3DSTATE_DEPTH_BUFFER | (7 - 2));
	OUT_BATCH(GEN6_SURFACE_NULL << GEN6_3DSTATE_DEPTH_BUFFER_TYPE_SHIFT |
		  GEN6_DEPTHFORMAT_D32_FLOAT << GEN6_3DSTATE_DEPTH_BUFFER_FORMAT_SHIFT);
	OUT_BATCH(0);
	OUT_BATCH(0);
	OUT_BATCH(0);
	OUT_BATCH(0);
	OUT_BATCH(0);

	OUT_BATCH(GEN6_3DSTATE_CLEAR_PARAMS | (2 - 2));
	OUT_BATCH(0);
}

static void
gen6_emit_invariant(struct intel_batchbuffer *batch)
{
	OUT_BATCH(GEN6_PIPELINE_SELECT | PIPELINE_SELECT_3D);

	OUT_BATCH(GEN6_3DSTATE_MULTISAMPLE | (3 - 2));
	OUT_BATCH(GEN6_3DSTATE_MULTISAMPLE_PIXEL_LOCATION_CENTER |
		  GEN6_3DSTATE_MULTISAMPLE_NUMSAMPLES_1); /* 1 sample/pixel */
	OUT_BATCH(0);

	OUT_BATCH(GEN6_3DSTATE_SAMPLE_MASK | (2 - 2));
	OUT_BATCH(1);
}

static void
gen6_emit_cc(struct intel_batchbuffer *batch, uint32_t blend)
{
	OUT_BATCH(GEN6_3DSTATE_CC_STATE_POINTERS | (4 - 2));
	OUT_BATCH(blend | 1);
	OUT_BATCH(1024 | 1);
	OUT_BATCH(1024 | 1);
}

static void
gen6_emit_sampler(struct intel_batchbuffer *batch, uint32_t state)
{
	OUT_BATCH(GEN6_3DSTATE_SAMPLER_STATE_POINTERS |
		  GEN6_3DSTATE_SAMPLER_STATE_MODIFY_PS |
		  (4 - 2));
	OUT_BATCH(0); /* VS */
	OUT_BATCH(0); /* GS */
	OUT_BATCH(state);
}

static void
gen6_emit_sf(struct intel_batchbuffer *batch)
{
	OUT_BATCH(GEN6_3DSTATE_SF | (20 - 2));
	OUT_BATCH(1 << GEN6_3DSTATE_SF_NUM_OUTPUTS_SHIFT |
		  1 << GEN6_3DSTATE_SF_URB_ENTRY_READ_LENGTH_SHIFT |
		  1 << GEN6_3DSTATE_SF_URB_ENTRY_READ_OFFSET_SHIFT);
	OUT_BATCH(0);
	OUT_BATCH(GEN6_3DSTATE_SF_CULL_NONE);
	OUT_BATCH(2 << GEN6_3DSTATE_SF_TRIFAN_PROVOKE_SHIFT); /* DW4 */
	OUT_BATCH(0);
	OUT_BATCH(0);
	OUT_BATCH(0);
	OUT_BATCH(0);
	OUT_BATCH(0); /* DW9 */
	OUT_BATCH(0);
	OUT_BATCH(0);
	OUT_BATCH(0);
	OUT_BATCH(0);
	OUT_BATCH(0); /* DW14 */
	OUT_BATCH(0);
	OUT_BATCH(0);
	OUT_BATCH(0);
	OUT_BATCH(0);
	OUT_BATCH(0); /* DW19 */
}

static void
gen6_emit_wm(struct intel_batchbuffer *batch, int kernel)
{
	OUT_BATCH(GEN6_3DSTATE_WM | (9 - 2));
	OUT_BATCH(kernel);
	OUT_BATCH(1 << GEN6_3DSTATE_WM_SAMPLER_COUNT_SHIFT |
		  2 << GEN6_3DSTATE_WM_BINDING_TABLE_ENTRY_COUNT_SHIFT);
	OUT_BATCH(0);
	OUT_BATCH(6 << GEN6_3DSTATE_WM_DISPATCH_START_GRF_0_SHIFT); /* DW4 */
	OUT_BATCH((40 - 1) << GEN6_3DSTATE_WM_MAX_THREADS_SHIFT |
		  GEN6_3DSTATE_WM_DISPATCH_ENABLE |
		  GEN6_3DSTATE_WM_16_DISPATCH_ENABLE);
	OUT_BATCH(1 << GEN6_3DSTATE_WM_NUM_SF_OUTPUTS_SHIFT |
		  GEN6_3DSTATE_WM_PERSPECTIVE_PIXEL_BARYCENTRIC);
	OUT_BATCH(0);
	OUT_BATCH(0);
}

static void
gen6_emit_binding_table(struct intel_batchbuffer *batch, uint32_t wm_table)
{
	OUT_BATCH(GEN6_3DSTATE_BINDING_TABLE_POINTERS |
		  GEN6_3DSTATE_BINDING_TABLE_MODIFY_PS |
		  (4 - 2));
	OUT_BATCH(0);		/* vs */
	OUT_BATCH(0);		/* gs */
	OUT_BATCH(wm_table);
}

static void
gen6_emit_drawing_rectangle(struct intel_batchbuffer *batch, struct scratch_buf *dst)
{
	OUT_BATCH(GEN6_3DSTATE_DRAWING_RECTANGLE | (4 - 2));
	OUT_BATCH(0);
	OUT_BATCH((buf_height(dst) - 1) << 16 | (buf_width(dst) - 1));
	OUT_BATCH(0);
}

static void
gen6_emit_vertex_elements(struct intel_batchbuffer *batch)
{
	/* The VUE layout
	 *    dword 0-3: pad (0.0, 0.0, 0.0. 0.0)
	 *    dword 4-7: position (x, y, 1.0, 1.0),
	 *    dword 8-11: texture coordinate 0 (u0, v0, 0, 0)
	 *
	 * dword 4-11 are fetched from vertex buffer
	 */
	OUT_BATCH(GEN6_3DSTATE_VERTEX_ELEMENTS | (2 * 3 + 1 - 2));

	OUT_BATCH(0 << VE0_VERTEX_BUFFER_INDEX_SHIFT | VE0_VALID |
		  GEN6_SURFACEFORMAT_R32G32B32A32_FLOAT << VE0_FORMAT_SHIFT |
		  0 << VE0_OFFSET_SHIFT);
	OUT_BATCH(GEN6_VFCOMPONENT_STORE_0 << VE1_VFCOMPONENT_0_SHIFT |
		  GEN6_VFCOMPONENT_STORE_0 << VE1_VFCOMPONENT_1_SHIFT |
		  GEN6_VFCOMPONENT_STORE_0 << VE1_VFCOMPONENT_2_SHIFT |
		  GEN6_VFCOMPONENT_STORE_0 << VE1_VFCOMPONENT_3_SHIFT);

	/* x,y */
	OUT_BATCH(0 << VE0_VERTEX_BUFFER_INDEX_SHIFT | VE0_VALID |
		  GEN6_SURFACEFORMAT_R16G16_SSCALED << VE0_FORMAT_SHIFT |
		  0 << VE0_OFFSET_SHIFT); /* offsets vb in bytes */
	OUT_BATCH(GEN6_VFCOMPONENT_STORE_SRC << VE1_VFCOMPONENT_0_SHIFT |
		  GEN6_VFCOMPONENT_STORE_SRC << VE1_VFCOMPONENT_1_SHIFT |
		  GEN6_VFCOMPONENT_STORE_1_FLT << VE1_VFCOMPONENT_2_SHIFT |
		  GEN6_VFCOMPONENT_STORE_1_FLT << VE1_VFCOMPONENT_3_SHIFT);

	/* u0, v0 */
	OUT_BATCH(0 << VE0_VERTEX_BUFFER_INDEX_SHIFT | VE0_VALID |
		  GEN6_SURFACEFORMAT_R32G32_FLOAT << VE0_FORMAT_SHIFT |
		  4 << VE0_OFFSET_SHIFT);	/* offset vb in bytes */
	OUT_BATCH(GEN6_VFCOMPONENT_STORE_SRC << VE1_VFCOMPONENT_0_SHIFT |
		  GEN6_VFCOMPONENT_STORE_SRC << VE1_VFCOMPONENT_1_SHIFT |
		  GEN6_VFCOMPONENT_STORE_0 << VE1_VFCOMPONENT_2_SHIFT |
		  GEN6_VFCOMPONENT_STORE_0 << VE1_VFCOMPONENT_3_SHIFT);
}

static uint32_t
gen6_create_cc_viewport(struct intel_batchbuffer *batch)
{
	struct gen6_cc_viewport *vp;

	vp = batch_alloc(batch, sizeof(*vp), 32);

	vp->min_depth = -1.e35;
	vp->max_depth = 1.e35;

	return batch_offset(batch, vp);
}

static uint32_t
gen6_create_cc_blend(struct intel_batchbuffer *batch)
{
	struct gen6_blend_state *blend;

	blend = batch_alloc(batch, sizeof(*blend), 64);

	blend->blend0.dest_blend_factor = GEN6_BLENDFACTOR_ZERO;
	blend->blend0.source_blend_factor = GEN6_BLENDFACTOR_ONE;
	blend->blend0.blend_func = GEN6_BLENDFUNCTION_ADD;
	blend->blend0.blend_enable = 1;

	blend->blend1.post_blend_clamp_enable = 1;
	blend->blend1.pre_blend_clamp_enable = 1;

	return batch_offset(batch, blend);
}

static uint32_t
gen6_create_kernel(struct intel_batchbuffer *batch)
{
	return batch_copy(batch, ps_kernel_nomask_affine,
			  sizeof(ps_kernel_nomask_affine),
			  64);
}

static uint32_t
gen6_create_sampler(struct intel_batchbuffer *batch,
		    sampler_filter_t filter,
		   sampler_extend_t extend)
{
	struct gen6_sampler_state *ss;

	ss = batch_alloc(batch, sizeof(*ss), 32);
	ss->ss0.lod_preclamp = 1;	/* GL mode */

	/* We use the legacy mode to get the semantics specified by
	 * the Render extension. */
	ss->ss0.border_color_mode = GEN6_BORDER_COLOR_MODE_LEGACY;

	switch (filter) {
	default:
	case SAMPLER_FILTER_NEAREST:
		ss->ss0.min_filter = GEN6_MAPFILTER_NEAREST;
		ss->ss0.mag_filter = GEN6_MAPFILTER_NEAREST;
		break;
	case SAMPLER_FILTER_BILINEAR:
		ss->ss0.min_filter = GEN6_MAPFILTER_LINEAR;
		ss->ss0.mag_filter = GEN6_MAPFILTER_LINEAR;
		break;
	}

	switch (extend) {
	default:
	case SAMPLER_EXTEND_NONE:
		ss->ss1.r_wrap_mode = GEN6_TEXCOORDMODE_CLAMP_BORDER;
		ss->ss1.s_wrap_mode = GEN6_TEXCOORDMODE_CLAMP_BORDER;
		ss->ss1.t_wrap_mode = GEN6_TEXCOORDMODE_CLAMP_BORDER;
		break;
	case SAMPLER_EXTEND_REPEAT:
		ss->ss1.r_wrap_mode = GEN6_TEXCOORDMODE_WRAP;
		ss->ss1.s_wrap_mode = GEN6_TEXCOORDMODE_WRAP;
		ss->ss1.t_wrap_mode = GEN6_TEXCOORDMODE_WRAP;
		break;
	case SAMPLER_EXTEND_PAD:
		ss->ss1.r_wrap_mode = GEN6_TEXCOORDMODE_CLAMP;
		ss->ss1.s_wrap_mode = GEN6_TEXCOORDMODE_CLAMP;
		ss->ss1.t_wrap_mode = GEN6_TEXCOORDMODE_CLAMP;
		break;
	case SAMPLER_EXTEND_REFLECT:
		ss->ss1.r_wrap_mode = GEN6_TEXCOORDMODE_MIRROR;
		ss->ss1.s_wrap_mode = GEN6_TEXCOORDMODE_MIRROR;
		ss->ss1.t_wrap_mode = GEN6_TEXCOORDMODE_MIRROR;
		break;
	}

	return batch_offset(batch, ss);
}

static void gen6_emit_vertex_buffer(struct intel_batchbuffer *batch)
{
	OUT_BATCH(GEN6_3DSTATE_VERTEX_BUFFERS | 3);
	OUT_BATCH(VB0_VERTEXDATA |
		  0 << VB0_BUFFER_INDEX_SHIFT |
		  VERTEX_SIZE << VB0_BUFFER_PITCH_SHIFT);
	OUT_RELOC(batch->bo, I915_GEM_DOMAIN_VERTEX, 0, 0);
	OUT_RELOC(batch->bo, I915_GEM_DOMAIN_VERTEX, 0, batch->bo->size-1);
	OUT_BATCH(0);
}

static uint32_t gen6_emit_primitive(struct intel_batchbuffer *batch)
{
	uint32_t offset;

	OUT_BATCH(GEN6_3DPRIMITIVE |
		  GEN6_3DPRIMITIVE_VERTEX_SEQUENTIAL |
		  _3DPRIM_RECTLIST << GEN6_3DPRIMITIVE_TOPOLOGY_SHIFT |
		  0 << 9 |
		  4);
	OUT_BATCH(3);	/* vertex count */
	offset = batch_used(batch);
	OUT_BATCH(0);	/* vertex_index */
	OUT_BATCH(1);	/* single instance */
	OUT_BATCH(0);	/* start instance location */
	OUT_BATCH(0);	/* index buffer offset, ignored */

	return offset;
}

void gen6_render_copyfunc(struct intel_batchbuffer *batch,
			  struct scratch_buf *src, unsigned src_x, unsigned src_y,
			  unsigned width, unsigned height,
			  struct scratch_buf *dst, unsigned dst_x, unsigned dst_y)
{
	uint32_t wm_state, wm_kernel, wm_table;
	uint32_t cc_vp, cc_blend, offset;
	uint32_t batch_end;

	intel_batchbuffer_flush(batch);

	batch->ptr = batch->buffer + 1024;
	batch_alloc(batch, 64, 64);
	wm_table  = gen6_bind_surfaces(batch, src, dst);
	wm_kernel = gen6_create_kernel(batch);
	wm_state  = gen6_create_sampler(batch,
					SAMPLER_FILTER_NEAREST,
					SAMPLER_EXTEND_NONE);

	cc_vp = gen6_create_cc_viewport(batch);
	cc_blend = gen6_create_cc_blend(batch);

	batch->ptr = batch->buffer;

	gen6_emit_invariant(batch);
	gen6_emit_state_base_address(batch);

	gen6_emit_sip(batch);
	gen6_emit_urb(batch);

	gen6_emit_viewports(batch, cc_vp);
	gen6_emit_vs(batch);
	gen6_emit_gs(batch);
	gen6_emit_clip(batch);
	gen6_emit_wm_constants(batch);
	gen6_emit_null_depth_buffer(batch);

	gen6_emit_drawing_rectangle(batch, dst);
	gen6_emit_cc(batch, cc_blend);
	gen6_emit_sampler(batch, wm_state);
	gen6_emit_sf(batch);
	gen6_emit_wm(batch, wm_kernel);
	gen6_emit_vertex_elements(batch);
	gen6_emit_binding_table(batch, wm_table);

	gen6_emit_vertex_buffer(batch);
	offset = gen6_emit_primitive(batch);

	OUT_BATCH(MI_BATCH_BUFFER_END);
	batch_end = batch_align(batch, 8);

	*(uint32_t*)(batch->buffer + offset) =
		batch_round_upto(batch, VERTEX_SIZE)/VERTEX_SIZE;

	emit_vertex_2s(batch, dst_x + width, dst_y + height);
	emit_vertex_normalized(batch, src_x + width, buf_width(src));
	emit_vertex_normalized(batch, src_y + height, buf_height(src));

	emit_vertex_2s(batch, dst_x, dst_y + height);
	emit_vertex_normalized(batch, src_x, buf_width(src));
	emit_vertex_normalized(batch, src_y + height, buf_height(src));

	emit_vertex_2s(batch, dst_x, dst_y);
	emit_vertex_normalized(batch, src_x, buf_width(src));
	emit_vertex_normalized(batch, src_y, buf_height(src));

	gen6_render_flush(batch, batch_end);
	intel_batchbuffer_reset(batch);
}