summaryrefslogtreecommitdiff
path: root/src/mesa/drivers/dri/nouveau/nv10_swtcl.c
blob: 22144b6611773953d2e6a55651c6ce16d126247d (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
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
/*
 * Copyright 1998-2003 VIA Technologies, Inc. All Rights Reserved.
 * Copyright 2001-2003 S3 Graphics, Inc. All Rights Reserved.
 * Copyright 2006 Stephane Marchesin. 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, sub license,
 * 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 NON-INFRINGEMENT. IN NO EVENT SHALL
 * VIA, S3 GRAPHICS, AND/OR ITS SUPPLIERS 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.
 */

/* Software TCL for NV10, NV20, NV30, NV40, NV50 */

#include <stdio.h>
#include <math.h>

#include "glheader.h"
#include "context.h"
#include "mtypes.h"
#include "macros.h"
#include "colormac.h"
#include "enums.h"

#include "swrast/swrast.h"
#include "swrast_setup/swrast_setup.h"
#include "tnl/t_context.h"
#include "tnl/t_pipeline.h"

#include "nouveau_swtcl.h"
#include "nv10_swtcl.h"
#include "nouveau_context.h"
#include "nouveau_span.h"
#include "nouveau_reg.h"
#include "nouveau_tex.h"
#include "nouveau_fifo.h"
#include "nouveau_msg.h"
#include "nouveau_object.h"

static void nv10RasterPrimitive( GLcontext *ctx, GLenum rprim, GLuint hwprim );
static void nv10RenderPrimitive( GLcontext *ctx, GLenum prim );
static void nv10ResetLineStipple( GLcontext *ctx );

static const int default_attr_size[8]={3,3,3,4,3,1,4,4};

/* Mesa requires us to put pos attribute as the first attribute of the
 * vertex, but on NV10 it is the last attribute.
 * To fix that we put the pos attribute first, and we swap the pos
 * attribute before sending it to the card.
 * Speed cost of the swap seems negligeable
 */
#if 0
/* old stuff where pos attribute isn't put first for mesa.
 * Usefull for speed comparaison
 */
#define INV_VERT(i) i
#define OUT_RING_VERTp(nmesa, ptr,sz, vertex_size) OUT_RINGp(ptr,sz)
#define OUT_RING_VERT(nmesa, ptr, vertex_size) OUT_RINGp(ptr,vertex_size)
#else

#define INV_VERT(i) (i==0?7:i-1)

#define OUT_RING_VERT_RAW(ptr,vertex_size) do{						\
	/* if the vertex size is not null, we have at least pos attribute */ \
	OUT_RINGp((ptr) + default_attr_size[_TNL_ATTRIB_POS], (vertex_size) - default_attr_size[_TNL_ATTRIB_POS]); \
	OUT_RINGp((ptr), default_attr_size[_TNL_ATTRIB_POS]); \
}while(0)

#define OUT_RING_VERT(nmesa,ptr,vertex_size) do{ \
	if (nmesa->screen->card->type>=NV_20) \
		OUT_RINGp(ptr, vertex_size); \
	else \
		OUT_RING_VERT_RAW(ptr, vertex_size); \
}while(0)


#define OUT_RING_VERTp(nmesa, ptr,sz, vertex_size) do{						\
	int nb_vert; \
	if (nmesa->screen->card->type>=NV_20) \
		OUT_RINGp(ptr, sz); \
	else \
		for (nb_vert = 0; nb_vert < (sz)/(vertex_size); nb_vert++) { \
			OUT_RING_VERT_RAW((uint32_t*)(ptr)+nb_vert*(vertex_size), vertex_size); \
		} \
}while(0)

#endif


static inline void nv10StartPrimitive(struct nouveau_context* nmesa,uint32_t primitive,uint32_t size)
{
	if ((nmesa->screen->card->type>=NV_10) && (nmesa->screen->card->type<=NV_17))
		BEGIN_RING_SIZE(NvSub3D,NV10_TCL_PRIMITIVE_3D_BEGIN_END,1);
	else if (nmesa->screen->card->type==NV_20)
		BEGIN_RING_SIZE(NvSub3D,NV20_TCL_PRIMITIVE_3D_BEGIN_END,1);
	else
		BEGIN_RING_SIZE(NvSub3D,NV30_TCL_PRIMITIVE_3D_BEGIN_END,1);
	OUT_RING(primitive);

	if ((nmesa->screen->card->type>=NV_10) && (nmesa->screen->card->type<=NV_17))
		BEGIN_RING_SIZE(NvSub3D,NV10_TCL_PRIMITIVE_3D_VERTEX_ARRAY_DATA|NONINC_METHOD,size);
	else if (nmesa->screen->card->type==NV_20)
		BEGIN_RING_SIZE(NvSub3D,NV20_TCL_PRIMITIVE_3D_VERTEX_DATA|NONINC_METHOD,size);
	else
		BEGIN_RING_SIZE(NvSub3D,NV30_TCL_PRIMITIVE_3D_VERTEX_DATA|NONINC_METHOD,size);
}

void nv10FinishPrimitive(struct nouveau_context *nmesa)
{
	if ((nmesa->screen->card->type>=NV_10) && (nmesa->screen->card->type<=NV_17))
		BEGIN_RING_SIZE(NvSub3D,NV10_TCL_PRIMITIVE_3D_BEGIN_END,1);
	else if (nmesa->screen->card->type==NV_20)
		BEGIN_RING_SIZE(NvSub3D,NV20_TCL_PRIMITIVE_3D_BEGIN_END,1);
	else
		BEGIN_RING_SIZE(NvSub3D,NV30_TCL_PRIMITIVE_3D_BEGIN_END,1);
	OUT_RING(0x0);
	FIRE_RING();
}


static inline void nv10ExtendPrimitive(struct nouveau_context* nmesa, int size)
{
	/* make sure there's enough room. if not, wait */
	if (RING_AVAILABLE()<size)
	{
		WAIT_RING(nmesa,size);
	}
}

/**********************************************************************/
/*               Render unclipped begin/end objects                   */
/**********************************************************************/

static inline void nv10_render_generic_primitive_verts(GLcontext *ctx,GLuint start,GLuint count,GLuint flags,GLuint prim)
{
	struct nouveau_context *nmesa = NOUVEAU_CONTEXT(ctx);
	GLubyte *vertptr = (GLubyte *)nmesa->verts;
	GLuint vertsize = nmesa->vertex_size;
	GLuint size_dword = vertsize*(count-start)/4;

	nv10ExtendPrimitive(nmesa, size_dword);
	nv10StartPrimitive(nmesa,prim+1,size_dword);
	OUT_RING_VERTp(nmesa, (nouveauVertex*)(vertptr+(start*vertsize)),size_dword, (vertsize/4));
	nv10FinishPrimitive(nmesa);
}

static void nv10_render_points_verts(GLcontext *ctx,GLuint start,GLuint count,GLuint flags)
{
	nv10_render_generic_primitive_verts(ctx,start,count,flags,GL_POINTS);
}

static void nv10_render_lines_verts(GLcontext *ctx,GLuint start,GLuint count,GLuint flags)
{
	nv10_render_generic_primitive_verts(ctx,start,count,flags,GL_LINES);
}

static void nv10_render_line_strip_verts(GLcontext *ctx,GLuint start,GLuint count,GLuint flags)
{
	nv10_render_generic_primitive_verts(ctx,start,count,flags,GL_LINE_STRIP);
}

static void nv10_render_line_loop_verts(GLcontext *ctx,GLuint start,GLuint count,GLuint flags)
{
	nv10_render_generic_primitive_verts(ctx,start,count,flags,GL_LINE_LOOP);
}

static void nv10_render_triangles_verts(GLcontext *ctx,GLuint start,GLuint count,GLuint flags)
{
	nv10_render_generic_primitive_verts(ctx,start,count,flags,GL_TRIANGLES);
}

static void nv10_render_tri_strip_verts(GLcontext *ctx,GLuint start,GLuint count,GLuint flags)
{
	nv10_render_generic_primitive_verts(ctx,start,count,flags,GL_TRIANGLE_STRIP);
}

static void nv10_render_tri_fan_verts(GLcontext *ctx,GLuint start,GLuint count,GLuint flags)
{
	nv10_render_generic_primitive_verts(ctx,start,count,flags,GL_TRIANGLE_FAN);
}

static void nv10_render_quads_verts(GLcontext *ctx,GLuint start,GLuint count,GLuint flags)
{
	nv10_render_generic_primitive_verts(ctx,start,count,flags,GL_QUADS);
}

static void nv10_render_quad_strip_verts(GLcontext *ctx,GLuint start,GLuint count,GLuint flags)
{
	nv10_render_generic_primitive_verts(ctx,start,count,flags,GL_QUAD_STRIP);
}

static void nv10_render_poly_verts(GLcontext *ctx,GLuint start,GLuint count,GLuint flags)
{
	nv10_render_generic_primitive_verts(ctx,start,count,flags,GL_POLYGON);
}

static void nv10_render_noop_verts(GLcontext *ctx,GLuint start,GLuint count,GLuint flags)
{
}

static void (*nv10_render_tab_verts[GL_POLYGON+2])(GLcontext *,
							   GLuint,
							   GLuint,
							   GLuint) =
{
   nv10_render_points_verts,
   nv10_render_lines_verts,
   nv10_render_line_loop_verts,
   nv10_render_line_strip_verts,
   nv10_render_triangles_verts,
   nv10_render_tri_strip_verts,
   nv10_render_tri_fan_verts,
   nv10_render_quads_verts,
   nv10_render_quad_strip_verts,
   nv10_render_poly_verts,
   nv10_render_noop_verts,
};


static inline void nv10_render_generic_primitive_elts(GLcontext *ctx,GLuint start,GLuint count,GLuint flags,GLuint prim)
{
	struct nouveau_context *nmesa = NOUVEAU_CONTEXT(ctx);
	GLubyte *vertptr = (GLubyte *)nmesa->verts;
	GLuint vertsize = nmesa->vertex_size;
	GLuint size_dword = vertsize*(count-start)/4;
	const GLuint * const elt = TNL_CONTEXT(ctx)->vb.Elts;
	GLuint j;

	nv10ExtendPrimitive(nmesa, size_dword);
	nv10StartPrimitive(nmesa,prim+1,size_dword);
	for (j=start; j<count; j++ ) {
		OUT_RING_VERT(nmesa, (nouveauVertex*)(vertptr+(elt[j]*vertsize)),vertsize/4);
	}
	nv10FinishPrimitive(nmesa);
}

static void nv10_render_points_elts(GLcontext *ctx,GLuint start,GLuint count,GLuint flags)
{
	nv10_render_generic_primitive_elts(ctx,start,count,flags,GL_POINTS);
}

static void nv10_render_lines_elts(GLcontext *ctx,GLuint start,GLuint count,GLuint flags)
{
	nv10_render_generic_primitive_elts(ctx,start,count,flags,GL_LINES);
}

static void nv10_render_line_strip_elts(GLcontext *ctx,GLuint start,GLuint count,GLuint flags)
{
	nv10_render_generic_primitive_elts(ctx,start,count,flags,GL_LINE_STRIP);
}

static void nv10_render_line_loop_elts(GLcontext *ctx,GLuint start,GLuint count,GLuint flags)
{
	nv10_render_generic_primitive_elts(ctx,start,count,flags,GL_LINE_LOOP);
}

static void nv10_render_triangles_elts(GLcontext *ctx,GLuint start,GLuint count,GLuint flags)
{
	nv10_render_generic_primitive_elts(ctx,start,count,flags,GL_TRIANGLES);
}

static void nv10_render_tri_strip_elts(GLcontext *ctx,GLuint start,GLuint count,GLuint flags)
{
	nv10_render_generic_primitive_elts(ctx,start,count,flags,GL_TRIANGLE_STRIP);
}

static void nv10_render_tri_fan_elts(GLcontext *ctx,GLuint start,GLuint count,GLuint flags)
{
	nv10_render_generic_primitive_elts(ctx,start,count,flags,GL_TRIANGLE_FAN);
}

static void nv10_render_quads_elts(GLcontext *ctx,GLuint start,GLuint count,GLuint flags)
{
	nv10_render_generic_primitive_elts(ctx,start,count,flags,GL_QUADS);
}

static void nv10_render_quad_strip_elts(GLcontext *ctx,GLuint start,GLuint count,GLuint flags)
{
	nv10_render_generic_primitive_elts(ctx,start,count,flags,GL_QUAD_STRIP);
}

static void nv10_render_poly_elts(GLcontext *ctx,GLuint start,GLuint count,GLuint flags)
{
	nv10_render_generic_primitive_elts(ctx,start,count,flags,GL_POLYGON);
}

static void nv10_render_noop_elts(GLcontext *ctx,GLuint start,GLuint count,GLuint flags)
{
}

static void (*nv10_render_tab_elts[GL_POLYGON+2])(GLcontext *,
							   GLuint,
							   GLuint,
							   GLuint) =
{
   nv10_render_points_elts,
   nv10_render_lines_elts,
   nv10_render_line_loop_elts,
   nv10_render_line_strip_elts,
   nv10_render_triangles_elts,
   nv10_render_tri_strip_elts,
   nv10_render_tri_fan_elts,
   nv10_render_quads_elts,
   nv10_render_quad_strip_elts,
   nv10_render_poly_elts,
   nv10_render_noop_elts,
};


/**********************************************************************/
/*                    Choose render functions                         */
/**********************************************************************/


#define EMIT_ATTR( ATTR, STYLE )					\
do {									\
   nmesa->vertex_attrs[nmesa->vertex_attr_count].attrib = (ATTR);	\
   nmesa->vertex_attrs[nmesa->vertex_attr_count].format = (STYLE);	\
   nmesa->vertex_attr_count++;						\
} while (0)

static void nv10_render_clipped_line(GLcontext *ctx,GLuint ii,GLuint jj)
{
	/* FIXME do something here */
	WARN_ONCE("Unimplemented %s\n", __func__);
}

static void nv10_render_clipped_poly(GLcontext *ctx,const GLuint *elts,GLuint n)
{
	TNLcontext *tnl = TNL_CONTEXT(ctx);
	struct vertex_buffer *VB = &tnl->vb;
	GLuint *tmp = VB->Elts;
	VB->Elts = (GLuint *)elts;
	nv10_render_generic_primitive_elts( ctx, 0, n, PRIM_BEGIN|PRIM_END,GL_POLYGON );
	VB->Elts = tmp;
}

static inline void nv10_render_points(GLcontext *ctx,GLuint first,GLuint last)
{
	WARN_ONCE("Unimplemented\n");
}

static inline void nv10_render_line(GLcontext *ctx,GLuint v1,GLuint v2)
{
	struct nouveau_context *nmesa = NOUVEAU_CONTEXT(ctx);
	GLubyte *vertptr = (GLubyte *)nmesa->verts;
	GLuint vertsize = nmesa->vertex_size;
	GLuint size_dword = vertsize*(2)/4;

	/* OUT_RINGp wants size in DWORDS */
	vertsize >>= 2;

	nv10ExtendPrimitive(nmesa, size_dword);
	nv10StartPrimitive(nmesa,GL_LINES+1,size_dword);
	OUT_RING_VERT(nmesa, (nouveauVertex*)(vertptr+(v1*vertsize)),vertsize);
	OUT_RING_VERT(nmesa, (nouveauVertex*)(vertptr+(v2*vertsize)),vertsize);
	nv10FinishPrimitive(nmesa);
}

static inline void nv10_render_triangle(GLcontext *ctx,GLuint v1,GLuint v2,GLuint v3)
{
	struct nouveau_context *nmesa = NOUVEAU_CONTEXT(ctx);
	GLubyte *vertptr = (GLubyte *)nmesa->verts;
	GLuint vertsize = nmesa->vertex_size;
	GLuint size_dword = vertsize*(3)/4;

	/* OUT_RINGp wants size in DWORDS */
	vertsize >>= 2;

	nv10ExtendPrimitive(nmesa, size_dword);
	nv10StartPrimitive(nmesa,GL_TRIANGLES+1,size_dword);
	OUT_RING_VERT(nmesa, (nouveauVertex*)(vertptr+(v1*vertsize)),vertsize);
	OUT_RING_VERT(nmesa, (nouveauVertex*)(vertptr+(v2*vertsize)),vertsize);
	OUT_RING_VERT(nmesa, (nouveauVertex*)(vertptr+(v3*vertsize)),vertsize);
	nv10FinishPrimitive(nmesa);
}

static inline void nv10_render_quad(GLcontext *ctx,GLuint v1,GLuint v2,GLuint v3,GLuint v4)
{
	struct nouveau_context *nmesa = NOUVEAU_CONTEXT(ctx);
	GLubyte *vertptr = (GLubyte *)nmesa->verts;
	GLuint vertsize = nmesa->vertex_size;
	GLuint size_dword = vertsize*(4)/4;

	/* OUT_RINGp wants size in DWORDS */
	vertsize >>= 2;

	nv10ExtendPrimitive(nmesa, size_dword);
	nv10StartPrimitive(nmesa,GL_QUADS+1,size_dword);
	OUT_RING_VERT(nmesa, (nouveauVertex*)(vertptr+(v1*vertsize)),vertsize);
	OUT_RING_VERT(nmesa, (nouveauVertex*)(vertptr+(v2*vertsize)),vertsize);
	OUT_RING_VERT(nmesa, (nouveauVertex*)(vertptr+(v3*vertsize)),vertsize);
	OUT_RING_VERT(nmesa, (nouveauVertex*)(vertptr+(v4*vertsize)),vertsize);
	nv10FinishPrimitive(nmesa);
}



static void nv10ChooseRenderState(GLcontext *ctx)
{
	TNLcontext *tnl = TNL_CONTEXT(ctx);
	struct nouveau_context *nmesa = NOUVEAU_CONTEXT(ctx);

	tnl->Driver.Render.PrimTabVerts = nv10_render_tab_verts;
	tnl->Driver.Render.PrimTabElts = nv10_render_tab_elts;
	tnl->Driver.Render.ClippedLine = nv10_render_clipped_line;
	tnl->Driver.Render.ClippedPolygon = nv10_render_clipped_poly;
	tnl->Driver.Render.Points = nv10_render_points;
	tnl->Driver.Render.Line = nv10_render_line;
	tnl->Driver.Render.Triangle = nv10_render_triangle;
	tnl->Driver.Render.Quad = nv10_render_quad;
}



static inline void nv10OutputVertexFormat(struct nouveau_context* nmesa)
{
	GLcontext* ctx=nmesa->glCtx;
	TNLcontext *tnl = TNL_CONTEXT(ctx);
	DECLARE_RENDERINPUTS(index);
	struct vertex_buffer *VB = &tnl->vb;
	int attr_size[16];
	const int nv10_vtx_attribs[8]={
		_TNL_ATTRIB_FOG, _TNL_ATTRIB_WEIGHT,
		_TNL_ATTRIB_NORMAL, _TNL_ATTRIB_TEX1,
		_TNL_ATTRIB_TEX0, _TNL_ATTRIB_COLOR1,
		_TNL_ATTRIB_COLOR0, _TNL_ATTRIB_POS
	};
	int i;
	int slots=0;
	int total_size=0;

	nmesa->vertex_attr_count = 0;
	RENDERINPUTS_COPY(index, nmesa->render_inputs_bitset);

	/*
	 * Determine attribute sizes
	 */
	for(i=0;i<8;i++)
	{
		if (RENDERINPUTS_TEST(index, i))
			attr_size[i]=default_attr_size[i];
		else
			attr_size[i]=0;
	}
	for(i=8;i<16;i++)
	{
		if (RENDERINPUTS_TEST(index, i))
			attr_size[i]=VB->TexCoordPtr[i-8]->size;
		else
			attr_size[i]=0;
	}

	/*
	 * Tell t_vertex about the vertex format
	 */
	if ((nmesa->screen->card->type>=NV_10) && (nmesa->screen->card->type<=NV_17)) {
		for(i=0;i<8;i++) {
			int j = nv10_vtx_attribs[INV_VERT(i)];
			if (RENDERINPUTS_TEST(index, j)) {
				switch(attr_size[j])
				{
					case 1:
						EMIT_ATTR(j,EMIT_1F);
						break;
					case 2:
						EMIT_ATTR(j,EMIT_2F);
						break;
					case 3:
						EMIT_ATTR(j,EMIT_3F);
						break;
					case 4:
						EMIT_ATTR(j,EMIT_4F);
						break;
				}
				total_size+=attr_size[j];
			}
		}
	} else {
		for(i=0;i<16;i++)
		{
			if (RENDERINPUTS_TEST(index, i))
			{
				slots=i+1;
				switch(attr_size[i])
				{
					case 1:
						EMIT_ATTR(i,EMIT_1F);
						break;
					case 2:
						EMIT_ATTR(i,EMIT_2F);
						break;
					case 3:
						EMIT_ATTR(i,EMIT_3F);
						break;
					case 4:
						EMIT_ATTR(i,EMIT_4F);
						break;
				}
				if (i==_TNL_ATTRIB_COLOR0)
					nmesa->color_offset=total_size;
				if (i==_TNL_ATTRIB_COLOR1)
					nmesa->specular_offset=total_size;
				total_size+=attr_size[i];
			}
		}
	}

	nmesa->vertex_size=_tnl_install_attrs( ctx,
			nmesa->vertex_attrs, 
			nmesa->vertex_attr_count,
			NULL, 0 );
	assert(nmesa->vertex_size==total_size*4);

	/* 
	 * Tell the hardware about the vertex format
	 */
	if ((nmesa->screen->card->type>=NV_10) && (nmesa->screen->card->type<=NV_17)) {
		int total_stride = 0;

#define NV_VERTEX_ATTRIBUTE_TYPE_FLOAT 2

		for(i=0;i<8;i++) {
			int j = nv10_vtx_attribs[i];
			int size;
			int stride = attr_size[j] << 2;
			if (j==_TNL_ATTRIB_POS) {
				stride += total_stride;
			}
			size = attr_size[j] << 4;
			size |= stride << 8;
			size |= NV_VERTEX_ATTRIBUTE_TYPE_FLOAT;
			BEGIN_RING_CACHE(NvSub3D, NV10_TCL_PRIMITIVE_3D_VERTEX_ATTR((7-i)),1);
			OUT_RING_CACHE(size);
			total_stride += stride;
		}

		BEGIN_RING_CACHE(NvSub3D, NV10_TCL_PRIMITIVE_3D_VERTEX_ARRAY_VALIDATE,1);
		OUT_RING_CACHE(0);
	} else if (nmesa->screen->card->type==NV_20) {
		for(i=0;i<16;i++)
		{
			int size=attr_size[i];
			BEGIN_RING_CACHE(NvSub3D,NV20_TCL_PRIMITIVE_3D_VERTEX_ATTR(i),1);
			OUT_RING_CACHE(NV_VERTEX_ATTRIBUTE_TYPE_FLOAT|(size*0x10));
		}
	} else {
		BEGIN_RING_SIZE(NvSub3D, NV30_TCL_PRIMITIVE_3D_DO_VERTICES, 1);
		OUT_RING(0);
		BEGIN_RING_CACHE(NvSub3D,NV20_TCL_PRIMITIVE_3D_VB_POINTER_ATTR8_TX0,slots);
		for(i=0;i<slots;i++)
		{
			int size=attr_size[i];
			OUT_RING_CACHE(NV_VERTEX_ATTRIBUTE_TYPE_FLOAT|(size*0x10));
		}
		// FIXME this is probably not needed
		BEGIN_RING_SIZE(NvSub3D,NV30_TCL_PRIMITIVE_3D_VERTEX_UNK_0,1);
		OUT_RING(0);
		BEGIN_RING_SIZE(NvSub3D,NV30_TCL_PRIMITIVE_3D_VERTEX_UNK_0,1);
		OUT_RING(0);
		BEGIN_RING_SIZE(NvSub3D,NV30_TCL_PRIMITIVE_3D_VERTEX_UNK_0,1);
		OUT_RING(0);
	}
}


static void nv10ChooseVertexState( GLcontext *ctx )
{
	struct nouveau_context *nmesa = NOUVEAU_CONTEXT(ctx);
	TNLcontext *tnl = TNL_CONTEXT(ctx);
	DECLARE_RENDERINPUTS(index);
	
	RENDERINPUTS_COPY(index, tnl->render_inputs_bitset);
	if (!RENDERINPUTS_EQUAL(index, nmesa->render_inputs_bitset))
	{
		RENDERINPUTS_COPY(nmesa->render_inputs_bitset, index);
		nv10OutputVertexFormat(nmesa);
	}

	if (nmesa->screen->card->type == NV_30) {
		nouveauShader *fp;
		
		if (ctx->FragmentProgram.Enabled) {
			fp = (nouveauShader *) ctx->FragmentProgram.Current;
			nvsUpdateShader(ctx, fp);
		} else
			nvsUpdateShader(ctx, nmesa->passthrough_fp);
	}

	if (nmesa->screen->card->type >= NV_40) {
		/* Ensure passthrough shader is being used, and mvp matrix
		 * is up to date
		 */
		nvsUpdateShader(ctx, nmesa->passthrough_vp);

		/* Update texenv shader / user fragprog */
		nvsUpdateShader(ctx, (nouveauShader*)ctx->FragmentProgram._Current);
	}
}


/**********************************************************************/
/*                 High level hooks for t_vb_render.c                 */
/**********************************************************************/


static void nv10RenderStart(GLcontext *ctx)
{
	TNLcontext *tnl = TNL_CONTEXT(ctx);
	struct nouveau_context *nmesa = NOUVEAU_CONTEXT(ctx);

	if (nmesa->new_state) {
		nmesa->new_render_state |= nmesa->new_state;
	}

	if (nmesa->new_render_state) {
		nv10ChooseVertexState(ctx);
		nv10ChooseRenderState(ctx);
		nmesa->new_render_state = 0;
	}
}

static void nv10RenderFinish(GLcontext *ctx)
{
}


/* System to flush dma and emit state changes based on the rasterized
 * primitive.
 */
void nv10RasterPrimitive(GLcontext *ctx,
		GLenum glprim,
		GLuint hwprim)
{
	struct nouveau_context *nmesa = NOUVEAU_CONTEXT(ctx);

	assert (!nmesa->new_state);

	if (hwprim != nmesa->current_primitive)
	{
		nmesa->current_primitive=hwprim;
		
	}
}

static const GLuint hw_prim[GL_POLYGON+1] = {
	GL_POINTS+1,
	GL_LINES+1,
	GL_LINE_STRIP+1,
	GL_LINE_LOOP+1,
	GL_TRIANGLES+1,
	GL_TRIANGLE_STRIP+1,
	GL_TRIANGLE_FAN+1,
	GL_QUADS+1,
	GL_QUAD_STRIP+1,
	GL_POLYGON+1
};

/* Callback for mesa:
 */
static void nv10RenderPrimitive( GLcontext *ctx, GLuint prim )
{
	nv10RasterPrimitive( ctx, prim, hw_prim[prim] );
}

static void nv10ResetLineStipple( GLcontext *ctx )
{
	/* FIXME do something here */
	WARN_ONCE("Unimplemented nv10ResetLineStipple\n");
}


/**********************************************************************/
/*                            Initialization.                         */
/**********************************************************************/

void nv10TriInitFunctions(GLcontext *ctx)
{
	struct nouveau_context *nmesa = NOUVEAU_CONTEXT(ctx);
	TNLcontext *tnl = TNL_CONTEXT(ctx);

	tnl->Driver.RunPipeline = nouveauRunPipeline;
	tnl->Driver.Render.Start = nv10RenderStart;
	tnl->Driver.Render.Finish = nv10RenderFinish;
	tnl->Driver.Render.PrimitiveNotify = nv10RenderPrimitive;
	tnl->Driver.Render.ResetLineStipple = nv10ResetLineStipple;
	tnl->Driver.Render.BuildVertices = _tnl_build_vertices;
	tnl->Driver.Render.CopyPV = _tnl_copy_pv;
	tnl->Driver.Render.Interp = _tnl_interp;

	_tnl_init_vertices( ctx, ctx->Const.MaxArrayLockSize + 12, 
			64 * sizeof(GLfloat) );

	nmesa->verts = (GLubyte *)tnl->clipspace.vertex_buf;
}