summaryrefslogtreecommitdiffstats
path: root/src/gallium/drivers/swr/swr_draw.cpp
blob: 03c82a7e510577c5764705b261a0a756a21e5f1b (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
/****************************************************************************
 * Copyright (C) 2015 Intel Corporation.   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, 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 "swr_screen.h"
#include "swr_context.h"
#include "swr_resource.h"
#include "swr_fence.h"
#include "swr_query.h"
#include "jit_api.h"

#include "util/u_draw.h"
#include "util/u_prim.h"

/*
 * Draw vertex arrays, with optional indexing, optional instancing.
 */
static void
swr_draw_vbo(struct pipe_context *pipe, const struct pipe_draw_info *info)
{
   struct swr_context *ctx = swr_context(pipe);

   if (!info->count_from_stream_output && !info->indirect &&
       !info->primitive_restart &&
       !u_trim_pipe_prim(info->mode, (unsigned*)&info->count))
      return;

   if (!swr_check_render_cond(pipe))
      return;

   if (info->indirect) {
      util_draw_indirect(pipe, info);
      return;
   }

   /* Update derived state, pass draw info to update function */
   swr_update_derived(pipe, info);

   swr_update_draw_context(ctx);

   if (ctx->vs->pipe.stream_output.num_outputs) {
      if (!ctx->vs->soFunc[info->mode]) {
         STREAMOUT_COMPILE_STATE state = {0};
         struct pipe_stream_output_info *so = &ctx->vs->pipe.stream_output;

         state.numVertsPerPrim = u_vertices_per_prim(info->mode);

         uint32_t offsets[MAX_SO_STREAMS] = {0};
         uint32_t num = 0;

         for (uint32_t i = 0; i < so->num_outputs; i++) {
            assert(so->output[i].stream == 0); // @todo
            uint32_t output_buffer = so->output[i].output_buffer;
            if (so->output[i].dst_offset != offsets[output_buffer]) {
               // hole - need to fill
               state.stream.decl[num].bufferIndex = output_buffer;
               state.stream.decl[num].hole = true;
               state.stream.decl[num].componentMask =
                  (1 << (so->output[i].dst_offset - offsets[output_buffer]))
                  - 1;
               num++;
               offsets[output_buffer] = so->output[i].dst_offset;
            }

            state.stream.decl[num].bufferIndex = output_buffer;
            state.stream.decl[num].attribSlot = so->output[i].register_index - 1;
            state.stream.decl[num].componentMask =
               ((1 << so->output[i].num_components) - 1)
               << so->output[i].start_component;
            state.stream.decl[num].hole = false;
            num++;

            offsets[output_buffer] += so->output[i].num_components;
         }

         state.stream.numDecls = num;

         HANDLE hJitMgr = swr_screen(pipe->screen)->hJitMgr;
         ctx->vs->soFunc[info->mode] = JitCompileStreamout(hJitMgr, state);
         debug_printf("so shader    %p\n", ctx->vs->soFunc[info->mode]);
         assert(ctx->vs->soFunc[info->mode] && "Error: SoShader = NULL");
      }

      SwrSetSoFunc(ctx->swrContext, ctx->vs->soFunc[info->mode], 0);
   }

   struct swr_vertex_element_state *velems = ctx->velems;
   velems->fsState.cutIndex = info->restart_index;
   velems->fsState.bEnableCutIndex = info->primitive_restart;
   velems->fsState.bPartialVertexBuffer = (info->min_index > 0);

   swr_jit_fetch_key key;
   swr_generate_fetch_key(key, velems);
   auto search = velems->map.find(key);
   if (search != velems->map.end()) {
      velems->fsFunc = search->second;
   } else {
      HANDLE hJitMgr = swr_screen(ctx->pipe.screen)->hJitMgr;
      velems->fsFunc = JitCompileFetch(hJitMgr, velems->fsState);

      debug_printf("fetch shader %p\n", velems->fsFunc);
      assert(velems->fsFunc && "Error: FetchShader = NULL");

      velems->map.insert(std::make_pair(key, velems->fsFunc));
   }

   SwrSetFetchFunc(ctx->swrContext, velems->fsFunc);

   /* Set up frontend state
    * XXX setup provokingVertex & topologyProvokingVertex */
   SWR_FRONTEND_STATE feState = {0};
   if (ctx->rasterizer->flatshade_first) {
      feState.provokingVertex = {1, 0, 0};
   } else {
      feState.provokingVertex = {2, 1, 2};
   }

   enum pipe_prim_type topology;
   if (ctx->gs)
      topology = (pipe_prim_type)ctx->gs->info.base.properties[TGSI_PROPERTY_GS_OUTPUT_PRIM];
   else
      topology = info->mode;

   switch (topology) {
   case PIPE_PRIM_TRIANGLE_FAN:
      feState.topologyProvokingVertex = feState.provokingVertex.triFan;
      break;
   case PIPE_PRIM_TRIANGLE_STRIP:
   case PIPE_PRIM_TRIANGLES:
      feState.topologyProvokingVertex = feState.provokingVertex.triStripList;
      break;
   case PIPE_PRIM_QUAD_STRIP:
   case PIPE_PRIM_QUADS:
      if (ctx->rasterizer->flatshade_first)
         feState.topologyProvokingVertex = 0;
      else
         feState.topologyProvokingVertex = 3;
      break;
   case PIPE_PRIM_LINES:
   case PIPE_PRIM_LINE_LOOP:
   case PIPE_PRIM_LINE_STRIP:
      feState.topologyProvokingVertex = feState.provokingVertex.lineStripList;
      break;
   default:
      feState.topologyProvokingVertex = 0;
   }

   feState.bEnableCutIndex = info->primitive_restart;
   SwrSetFrontendState(ctx->swrContext, &feState);

   if (info->index_size)
      SwrDrawIndexedInstanced(ctx->swrContext,
                              swr_convert_prim_topology(info->mode),
                              info->count,
                              info->instance_count,
                              info->start,
                              info->index_bias,
                              info->start_instance);
   else
      SwrDrawInstanced(ctx->swrContext,
                       swr_convert_prim_topology(info->mode),
                       info->count,
                       info->instance_count,
                       info->start,
                       info->start_instance);
}


static void
swr_flush(struct pipe_context *pipe,
          struct pipe_fence_handle **fence,
          unsigned flags)
{
   struct swr_context *ctx = swr_context(pipe);
   struct swr_screen *screen = swr_screen(pipe->screen);
   struct pipe_surface *cb = ctx->framebuffer.cbufs[0];

   /* If the current renderTarget is the display surface, store tiles back to
    * the surface, in preparation for present (swr_flush_frontbuffer).
    * Other renderTargets get stored back when attachment changes or
    * swr_surface_destroy */
   if (cb && swr_resource(cb->texture)->display_target)
      swr_store_dirty_resource(pipe, cb->texture, SWR_TILE_RESOLVED);

   if (fence)
      swr_fence_reference(pipe->screen, fence, screen->flush_fence);
}

void
swr_finish(struct pipe_context *pipe)
{
   struct pipe_fence_handle *fence = nullptr;

   swr_flush(pipe, &fence, 0);
   swr_fence_finish(pipe->screen, NULL, fence, 0);
   swr_fence_reference(pipe->screen, &fence, NULL);
}


/*
 * Store SWR HotTiles back to renderTarget surface.
 */
void
swr_store_render_target(struct pipe_context *pipe,
                        uint32_t attachment,
                        enum SWR_TILE_STATE post_tile_state)
{
   struct swr_context *ctx = swr_context(pipe);
   struct swr_draw_context *pDC = &ctx->swrDC;
   struct SWR_SURFACE_STATE *renderTarget = &pDC->renderTargets[attachment];

   /* Only proceed if there's a valid surface to store to */
   if (renderTarget->pBaseAddress) {
      swr_update_draw_context(ctx);
      SWR_RECT full_rect =
         {0, 0,
          (int32_t)u_minify(renderTarget->width, renderTarget->lod),
          (int32_t)u_minify(renderTarget->height, renderTarget->lod)};
      SwrStoreTiles(ctx->swrContext,
                    1 << attachment,
                    post_tile_state,
                    full_rect);
   }
}

void
swr_store_dirty_resource(struct pipe_context *pipe,
                         struct pipe_resource *resource,
                         enum SWR_TILE_STATE post_tile_state)
{
   /* Only store resource if it has been written to */
   if (swr_resource(resource)->status & SWR_RESOURCE_WRITE) {
      struct swr_context *ctx = swr_context(pipe);
      struct swr_screen *screen = swr_screen(pipe->screen);
      struct swr_resource *spr = swr_resource(resource);

      swr_draw_context *pDC = &ctx->swrDC;
      SWR_SURFACE_STATE *renderTargets = pDC->renderTargets;
      for (uint32_t i = 0; i < SWR_NUM_ATTACHMENTS; i++)
         if (renderTargets[i].pBaseAddress == spr->swr.pBaseAddress ||
             (spr->secondary.pBaseAddress &&
              renderTargets[i].pBaseAddress == spr->secondary.pBaseAddress)) {
            swr_store_render_target(pipe, i, post_tile_state);

            /* Mesa thinks depth/stencil are fused, so we'll never get an
             * explicit resource for stencil.  So, if checking depth, then
             * also check for stencil. */
            if (spr->has_stencil && (i == SWR_ATTACHMENT_DEPTH)) {
               swr_store_render_target(
                  pipe, SWR_ATTACHMENT_STENCIL, post_tile_state);
            }

            /* This fence signals StoreTiles completion */
            swr_fence_submit(ctx, screen->flush_fence);

            break;
         }
   }
}

void
swr_draw_init(struct pipe_context *pipe)
{
   pipe->draw_vbo = swr_draw_vbo;
   pipe->flush = swr_flush;
}