1/**********************************************************
2 * Copyright 2008-2009 VMware, Inc.  All rights reserved.
3 *
4 * Permission is hereby granted, free of charge, to any person
5 * obtaining a copy of this software and associated documentation
6 * files (the "Software"), to deal in the Software without
7 * restriction, including without limitation the rights to use, copy,
8 * modify, merge, publish, distribute, sublicense, and/or sell copies
9 * of the Software, and to permit persons to whom the Software is
10 * furnished to do so, subject to the following conditions:
11 *
12 * The above copyright notice and this permission notice shall be
13 * included in all copies or substantial portions of the Software.
14 *
15 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
16 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
17 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
18 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
19 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
20 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
21 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
22 * SOFTWARE.
23 *
24 **********************************************************/
25
26#include "pipe/p_defines.h"
27#include "util/u_bitmask.h"
28#include "util/format/u_format.h"
29#include "util/u_inlines.h"
30#include "util/u_memory.h"
31#include "util/u_math.h"
32#include "util/u_memory.h"
33
34#include "svga_context.h"
35#include "svga_screen.h"
36#include "svga_state.h"
37#include "svga_cmd.h"
38#include "svga_format.h"
39#include "svga_shader.h"
40
41
42struct rs_queue {
43   unsigned rs_count;
44   SVGA3dRenderState rs[SVGA3D_RS_MAX];
45};
46
47
48#define EMIT_RS(svga, value, token)                       \
49do {                                                            \
50   STATIC_ASSERT(SVGA3D_RS_##token < ARRAY_SIZE(svga->state.hw_draw.rs)); \
51   if (svga->state.hw_draw.rs[SVGA3D_RS_##token] != value) {    \
52      svga_queue_rs(&queue, SVGA3D_RS_##token, value);          \
53      svga->state.hw_draw.rs[SVGA3D_RS_##token] = value;        \
54   }                                                            \
55} while (0)
56
57#define EMIT_RS_FLOAT(svga, fvalue, token)                \
58do {                                                            \
59   unsigned value = fui(fvalue);                                \
60   STATIC_ASSERT(SVGA3D_RS_##token < ARRAY_SIZE(svga->state.hw_draw.rs)); \
61   if (svga->state.hw_draw.rs[SVGA3D_RS_##token] != value) {    \
62      svga_queue_rs(&queue, SVGA3D_RS_##token, value);          \
63      svga->state.hw_draw.rs[SVGA3D_RS_##token] = value;        \
64   }                                                            \
65} while (0)
66
67
68static inline void
69svga_queue_rs(struct rs_queue *q, unsigned rss, unsigned value)
70{
71   assert(q->rs_count < ARRAY_SIZE(q->rs));
72   q->rs[q->rs_count].state = rss;
73   q->rs[q->rs_count].uintValue = value;
74   q->rs_count++;
75}
76
77
78static unsigned
79translate_fill_mode(unsigned fill)
80{
81   switch (fill) {
82   case PIPE_POLYGON_MODE_POINT:
83      return SVGA3D_FILLMODE_POINT;
84   case PIPE_POLYGON_MODE_LINE:
85      return SVGA3D_FILLMODE_LINE;
86   case PIPE_POLYGON_MODE_FILL:
87      return SVGA3D_FILLMODE_FILL;
88   default:
89      assert(!"Bad fill mode");
90      return SVGA3D_FILLMODE_FILL;
91   }
92}
93
94
95/* Compare old and new render states and emit differences between them
96 * to hardware.  Simplest implementation would be to emit the whole of
97 * the "to" state.
98 */
99static enum pipe_error
100emit_rss_vgpu9(struct svga_context *svga, uint64_t dirty)
101{
102   struct svga_screen *screen = svga_screen(svga->pipe.screen);
103   struct rs_queue queue;
104   float point_size_min;
105
106   queue.rs_count = 0;
107
108   if (dirty & (SVGA_NEW_BLEND | SVGA_NEW_BLEND_COLOR)) {
109      const struct svga_blend_state *curr = svga->curr.blend;
110
111      EMIT_RS(svga, curr->rt[0].writemask, COLORWRITEENABLE);
112      EMIT_RS(svga, curr->rt[0].blend_enable, BLENDENABLE);
113
114      if (curr->rt[0].blend_enable) {
115         EMIT_RS(svga, curr->rt[0].srcblend, SRCBLEND);
116         EMIT_RS(svga, curr->rt[0].dstblend, DSTBLEND);
117         EMIT_RS(svga, curr->rt[0].blendeq, BLENDEQUATION);
118
119         EMIT_RS(svga, curr->rt[0].separate_alpha_blend_enable,
120                  SEPARATEALPHABLENDENABLE);
121
122         if (curr->rt[0].separate_alpha_blend_enable) {
123            EMIT_RS(svga, curr->rt[0].srcblend_alpha, SRCBLENDALPHA);
124            EMIT_RS(svga, curr->rt[0].dstblend_alpha, DSTBLENDALPHA);
125            EMIT_RS(svga, curr->rt[0].blendeq_alpha, BLENDEQUATIONALPHA);
126         }
127      }
128   }
129
130   if (dirty & SVGA_NEW_BLEND_COLOR) {
131      uint32 color;
132      uint32 r = float_to_ubyte(svga->curr.blend_color.color[0]);
133      uint32 g = float_to_ubyte(svga->curr.blend_color.color[1]);
134      uint32 b = float_to_ubyte(svga->curr.blend_color.color[2]);
135      uint32 a = float_to_ubyte(svga->curr.blend_color.color[3]);
136
137      color = (a << 24) | (r << 16) | (g << 8) | b;
138
139      EMIT_RS(svga, color, BLENDCOLOR);
140   }
141
142   if (dirty & (SVGA_NEW_DEPTH_STENCIL_ALPHA | SVGA_NEW_RAST)) {
143      const struct svga_depth_stencil_state *curr = svga->curr.depth;
144      const struct svga_rasterizer_state *rast = svga->curr.rast;
145
146      if (!curr->stencil[0].enabled) {
147         /* Stencil disabled
148          */
149         EMIT_RS(svga, FALSE, STENCILENABLE);
150         EMIT_RS(svga, FALSE, STENCILENABLE2SIDED);
151      }
152      else if (curr->stencil[0].enabled && !curr->stencil[1].enabled) {
153         /* Regular stencil
154          */
155         EMIT_RS(svga, TRUE, STENCILENABLE);
156         EMIT_RS(svga, FALSE, STENCILENABLE2SIDED);
157
158         EMIT_RS(svga, curr->stencil[0].func,  STENCILFUNC);
159         EMIT_RS(svga, curr->stencil[0].fail,  STENCILFAIL);
160         EMIT_RS(svga, curr->stencil[0].zfail, STENCILZFAIL);
161         EMIT_RS(svga, curr->stencil[0].pass,  STENCILPASS);
162
163         EMIT_RS(svga, curr->stencil_mask, STENCILMASK);
164         EMIT_RS(svga, curr->stencil_writemask, STENCILWRITEMASK);
165      }
166      else {
167         int cw, ccw;
168
169         /* Hardware frontwinding is always CW, so if ours is also CW,
170          * then our definition of front face agrees with hardware.
171          * Otherwise need to flip.
172          */
173         if (rast->templ.front_ccw) {
174            ccw = 0;
175            cw = 1;
176         }
177         else {
178            ccw = 1;
179            cw = 0;
180         }
181
182         /* Twoside stencil
183          */
184         EMIT_RS(svga, TRUE, STENCILENABLE);
185         EMIT_RS(svga, TRUE, STENCILENABLE2SIDED);
186
187         EMIT_RS(svga, curr->stencil[cw].func,  STENCILFUNC);
188         EMIT_RS(svga, curr->stencil[cw].fail,  STENCILFAIL);
189         EMIT_RS(svga, curr->stencil[cw].zfail, STENCILZFAIL);
190         EMIT_RS(svga, curr->stencil[cw].pass,  STENCILPASS);
191
192         EMIT_RS(svga, curr->stencil[ccw].func,  CCWSTENCILFUNC);
193         EMIT_RS(svga, curr->stencil[ccw].fail,  CCWSTENCILFAIL);
194         EMIT_RS(svga, curr->stencil[ccw].zfail, CCWSTENCILZFAIL);
195         EMIT_RS(svga, curr->stencil[ccw].pass,  CCWSTENCILPASS);
196
197         EMIT_RS(svga, curr->stencil_mask, STENCILMASK);
198         EMIT_RS(svga, curr->stencil_writemask, STENCILWRITEMASK);
199      }
200
201      EMIT_RS(svga, curr->zenable, ZENABLE);
202      if (curr->zenable) {
203         EMIT_RS(svga, curr->zfunc, ZFUNC);
204         EMIT_RS(svga, curr->zwriteenable, ZWRITEENABLE);
205      }
206
207      EMIT_RS(svga, curr->alphatestenable, ALPHATESTENABLE);
208      if (curr->alphatestenable) {
209         EMIT_RS(svga, curr->alphafunc, ALPHAFUNC);
210         EMIT_RS_FLOAT(svga, curr->alpharef, ALPHAREF);
211      }
212   }
213
214   if (dirty & SVGA_NEW_STENCIL_REF) {
215      EMIT_RS(svga, svga->curr.stencil_ref.ref_value[0], STENCILREF);
216   }
217
218   if (dirty & (SVGA_NEW_RAST | SVGA_NEW_NEED_PIPELINE)) {
219      const struct svga_rasterizer_state *curr = svga->curr.rast;
220      unsigned cullmode = curr->cullmode;
221
222      /* Shademode: still need to rearrange index list to move
223       * flat-shading PV first vertex.
224       */
225      EMIT_RS(svga, curr->shademode, SHADEMODE);
226
227      EMIT_RS(svga, translate_fill_mode(curr->hw_fillmode), FILLMODE);
228
229      /* Don't do culling while the software pipeline is active.  It
230       * does it for us, and additionally introduces potentially
231       * back-facing triangles.
232       */
233      if (svga->state.sw.need_pipeline)
234         cullmode = SVGA3D_FACE_NONE;
235
236      point_size_min = util_get_min_point_size(&curr->templ);
237
238      EMIT_RS(svga, cullmode, CULLMODE);
239      EMIT_RS(svga, curr->scissortestenable, SCISSORTESTENABLE);
240      EMIT_RS(svga, curr->multisampleantialias, MULTISAMPLEANTIALIAS);
241      EMIT_RS(svga, curr->lastpixel, LASTPIXEL);
242      EMIT_RS_FLOAT(svga, curr->pointsize, POINTSIZE);
243      EMIT_RS_FLOAT(svga, point_size_min, POINTSIZEMIN);
244      EMIT_RS_FLOAT(svga, screen->maxPointSize, POINTSIZEMAX);
245      EMIT_RS(svga, curr->pointsprite, POINTSPRITEENABLE);
246
247      /* Emit line state, when the device understands it */
248      if (screen->haveLineStipple)
249         EMIT_RS(svga, curr->linepattern, LINEPATTERN);
250      if (screen->haveLineSmooth)
251         EMIT_RS(svga, curr->antialiasedlineenable, ANTIALIASEDLINEENABLE);
252      if (screen->maxLineWidth > 1.0F)
253         EMIT_RS_FLOAT(svga, curr->linewidth, LINEWIDTH);
254   }
255
256   if (dirty & (SVGA_NEW_RAST |
257                SVGA_NEW_FRAME_BUFFER |
258                SVGA_NEW_NEED_PIPELINE)) {
259      const struct svga_rasterizer_state *curr = svga->curr.rast;
260      float slope = 0.0;
261      float bias  = 0.0;
262
263      /* Need to modify depth bias according to bound depthbuffer
264       * format.  Don't do hardware depthbias while the software
265       * pipeline is active.
266       */
267      if (!svga->state.sw.need_pipeline &&
268          svga->curr.framebuffer.zsbuf)
269      {
270         slope = curr->slopescaledepthbias;
271         bias  = svga->curr.depthscale * curr->depthbias;
272      }
273
274      EMIT_RS_FLOAT(svga, slope, SLOPESCALEDEPTHBIAS);
275      EMIT_RS_FLOAT(svga, bias, DEPTHBIAS);
276   }
277
278   if (dirty & SVGA_NEW_FRAME_BUFFER) {
279      /* XXX: we only look at the first color buffer's sRGB state */
280      float gamma = 1.0f;
281      if (svga->curr.framebuffer.cbufs[0] &&
282          util_format_is_srgb(svga->curr.framebuffer.cbufs[0]->format)) {
283         gamma = 2.2f;
284      }
285      EMIT_RS_FLOAT(svga, gamma, OUTPUTGAMMA);
286   }
287
288   if (dirty & SVGA_NEW_RAST) {
289      /* bitmask of the enabled clip planes */
290      unsigned enabled = svga->curr.rast->templ.clip_plane_enable;
291      EMIT_RS(svga, enabled, CLIPPLANEENABLE);
292   }
293
294   if (queue.rs_count) {
295      SVGA3dRenderState *rs;
296
297      if (SVGA3D_BeginSetRenderState(svga->swc, &rs, queue.rs_count)
298          != PIPE_OK) {
299         /* XXX: need to poison cached hardware state on failure to ensure
300          * dirty state gets re-emitted.  Fix this by re-instating partial
301          * FIFOCommit command and only updating cached hw state once the
302          * initial allocation has succeeded.
303          */
304         memset(svga->state.hw_draw.rs, 0xcd, sizeof(svga->state.hw_draw.rs));
305
306         return PIPE_ERROR_OUT_OF_MEMORY;
307      }
308
309      memcpy(rs, queue.rs, queue.rs_count * sizeof queue.rs[0]);
310
311      SVGA_FIFOCommitAll(svga->swc);
312   }
313
314   return PIPE_OK;
315}
316
317
318/** Returns a non-culling rasterizer state object to be used with
319 *  point sprite.
320 */
321static struct svga_rasterizer_state *
322get_no_cull_rasterizer_state(struct svga_context *svga)
323{
324   struct svga_rasterizer_state *r = svga->curr.rast;
325
326   if (!r->no_cull_rasterizer) {
327      struct pipe_rasterizer_state rast;
328
329      memset(&rast, 0, sizeof(rast));
330      rast.flatshade = 1;
331      rast.front_ccw = 1;
332      rast.point_smooth = r->templ.point_smooth;
333
334      /* All rasterizer states have the same half_pixel_center,
335       * bottom_edge_rule and clip_halfz values since they are
336       * constant for a context. If we ever implement
337       * GL_ARB_clip_control, the clip_halfz field would have to be observed.
338       */
339      rast.half_pixel_center = r->templ.half_pixel_center;
340      rast.bottom_edge_rule = r->templ.bottom_edge_rule;
341      rast.clip_halfz = r->templ.clip_halfz;
342
343      r->no_cull_rasterizer =
344               svga->pipe.create_rasterizer_state(&svga->pipe, &rast);
345   }
346   return r->no_cull_rasterizer;
347}
348
349
350/** Returns a depth stencil state object with depth and stencil test disabled.
351 */
352static struct svga_depth_stencil_state *
353get_no_depth_stencil_test_state(struct svga_context *svga)
354{
355   if (!svga->depthstencil_disable) {
356      struct pipe_depth_stencil_alpha_state ds = {{{0}}};
357      svga->depthstencil_disable =
358         svga->pipe.create_depth_stencil_alpha_state(&svga->pipe, &ds);
359   }
360   return svga->depthstencil_disable;
361}
362
363
364/**
365 * A helper function to create an alternate svga rasterizer state object to use
366 * forcedSampleCount to support multisampled framebuffer without attachments.
367 */
368static SVGA3dRasterizerStateId
369get_alt_rasterizer_state_id(struct svga_context *svga,
370                            struct svga_rasterizer_state *rast,
371                            unsigned samples)
372{
373   assert(samples <= SVGA_MAX_FRAMEBUFFER_DEFAULT_SAMPLES);
374   assert(samples >= 0);
375
376   if (samples <= 1)
377      return rast->id;
378
379   if (rast->altRastIds[samples] == SVGA3D_INVALID_ID) {
380      rast->altRastIds[samples] = svga_define_rasterizer_object(svga, rast, samples);
381   }
382
383   return rast->altRastIds[samples];
384}
385
386
387static enum pipe_error
388emit_rss_vgpu10(struct svga_context *svga, uint64_t dirty)
389{
390   enum pipe_error ret = PIPE_OK;
391
392   svga_hwtnl_flush_retry(svga);
393
394   if (dirty & (SVGA_NEW_BLEND | SVGA_NEW_BLEND_COLOR)) {
395      const struct svga_blend_state *curr;
396      float blend_factor[4];
397
398      if (svga_has_any_integer_cbufs(svga)) {
399         /* Blending is not supported in integer-valued render targets. */
400         curr = svga->noop_blend;
401         blend_factor[0] =
402         blend_factor[1] =
403         blend_factor[2] =
404         blend_factor[3] = 0;
405      }
406      else {
407         curr = svga->curr.blend;
408
409         if (curr->blend_color_alpha) {
410            blend_factor[0] =
411            blend_factor[1] =
412            blend_factor[2] =
413            blend_factor[3] = svga->curr.blend_color.color[3];
414         }
415         else {
416            blend_factor[0] = svga->curr.blend_color.color[0];
417            blend_factor[1] = svga->curr.blend_color.color[1];
418            blend_factor[2] = svga->curr.blend_color.color[2];
419            blend_factor[3] = svga->curr.blend_color.color[3];
420         }
421      }
422
423      /* Set/bind the blend state object */
424      if (svga->state.hw_draw.blend_id != curr->id ||
425          svga->state.hw_draw.blend_factor[0] != blend_factor[0] ||
426          svga->state.hw_draw.blend_factor[1] != blend_factor[1] ||
427          svga->state.hw_draw.blend_factor[2] != blend_factor[2] ||
428          svga->state.hw_draw.blend_factor[3] != blend_factor[3] ||
429          svga->state.hw_draw.blend_sample_mask != svga->curr.sample_mask) {
430         ret = SVGA3D_vgpu10_SetBlendState(svga->swc, curr->id,
431                                           blend_factor,
432                                           svga->curr.sample_mask);
433         if (ret != PIPE_OK)
434            return ret;
435
436         svga->state.hw_draw.blend_id = curr->id;
437         svga->state.hw_draw.blend_factor[0] = blend_factor[0];
438         svga->state.hw_draw.blend_factor[1] = blend_factor[1];
439         svga->state.hw_draw.blend_factor[2] = blend_factor[2];
440         svga->state.hw_draw.blend_factor[3] = blend_factor[3];
441         svga->state.hw_draw.blend_sample_mask = svga->curr.sample_mask;
442      }
443   }
444
445   if (svga->disable_rasterizer) {
446      if (!svga->state.hw_draw.rasterizer_discard) {
447         struct svga_depth_stencil_state *ds;
448
449         /* If rasterization is to be disabled, disable depth and stencil
450          * testing as well.
451          */
452         ds = get_no_depth_stencil_test_state(svga);
453         if (ds->id != svga->state.hw_draw.depth_stencil_id) {
454            ret = SVGA3D_vgpu10_SetDepthStencilState(svga->swc, ds->id, 0);
455            if (ret != PIPE_OK)
456               return ret;
457
458            svga->state.hw_draw.depth_stencil_id = ds->id;
459            svga->state.hw_draw.stencil_ref = 0;
460         }
461         svga->state.hw_draw.rasterizer_discard = TRUE;
462      }
463   } else {
464      if ((dirty & (SVGA_NEW_DEPTH_STENCIL_ALPHA | SVGA_NEW_STENCIL_REF)) ||
465          svga->state.hw_draw.rasterizer_discard) {
466         const struct svga_depth_stencil_state *curr = svga->curr.depth;
467         unsigned curr_ref = svga->curr.stencil_ref.ref_value[0];
468
469         if (curr->id != svga->state.hw_draw.depth_stencil_id ||
470             curr_ref != svga->state.hw_draw.stencil_ref) {
471            /* Set/bind the depth/stencil state object */
472            ret = SVGA3D_vgpu10_SetDepthStencilState(svga->swc, curr->id,
473                                                     curr_ref);
474            if (ret != PIPE_OK)
475               return ret;
476
477            svga->state.hw_draw.depth_stencil_id = curr->id;
478            svga->state.hw_draw.stencil_ref = curr_ref;
479         }
480      }
481
482      if (dirty & (SVGA_NEW_REDUCED_PRIMITIVE | SVGA_NEW_RAST |
483                   SVGA_NEW_FRAME_BUFFER)) {
484         struct svga_rasterizer_state *rast = svga->curr.rast;
485
486         if (svga->curr.reduced_prim == PIPE_PRIM_POINTS &&
487             svga->curr.gs && svga->curr.gs->wide_point) {
488
489            /* If we are drawing a point sprite, we will need to
490             * bind a non-culling rasterizer state object
491             */
492            rast = get_no_cull_rasterizer_state(svga);
493         }
494
495         int rastId = rast->id;
496
497         /* In the case of no-attachment framebuffer, the sample count will be
498          * specified in forcedSampleCount in the RasterizerState_v2 object.
499          */
500         if ((svga->curr.framebuffer.nr_cbufs == 0) &&
501             (svga->curr.framebuffer.zsbuf == NULL)) {
502            rastId =
503               get_alt_rasterizer_state_id(svga, rast,
504                                           svga->curr.framebuffer.samples);
505
506            if (rastId == SVGA3D_INVALID_ID)
507               return PIPE_ERROR;
508         }
509
510         if (svga->state.hw_draw.rasterizer_id != rastId) {
511            /* Set/bind the rasterizer state object */
512            ret = SVGA3D_vgpu10_SetRasterizerState(svga->swc, rastId);
513            if (ret != PIPE_OK)
514               return ret;
515            svga->state.hw_draw.rasterizer_id = rastId;
516         }
517      }
518      svga->state.hw_draw.rasterizer_discard = FALSE;
519   }
520   return PIPE_OK;
521}
522
523
524static enum pipe_error
525emit_rss(struct svga_context *svga, uint64_t dirty)
526{
527   if (svga_have_vgpu10(svga)) {
528      return emit_rss_vgpu10(svga, dirty);
529   }
530   else {
531      return emit_rss_vgpu9(svga, dirty);
532   }
533}
534
535
536struct svga_tracked_state svga_hw_rss =
537{
538   "hw rss state",
539
540   (SVGA_NEW_BLEND |
541    SVGA_NEW_BLEND_COLOR |
542    SVGA_NEW_DEPTH_STENCIL_ALPHA |
543    SVGA_NEW_STENCIL_REF |
544    SVGA_NEW_RAST |
545    SVGA_NEW_FRAME_BUFFER |
546    SVGA_NEW_NEED_PIPELINE |
547    SVGA_NEW_FS |
548    SVGA_NEW_REDUCED_PRIMITIVE),
549
550   emit_rss
551};
552