summaryrefslogtreecommitdiff
path: root/src/mesa/drivers/dri/i965/gen8_draw_upload.c
blob: 2bac5ffb0586b1d0ec23814823288c79603652a7 (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
/*
 * Copyright © 2012 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 "main/glheader.h"
#include "main/bufferobj.h"
#include "main/context.h"
#include "main/enums.h"
#include "main/macros.h"

#include "brw_draw.h"
#include "brw_defines.h"
#include "brw_context.h"
#include "brw_state.h"

#include "intel_batchbuffer.h"
#include "intel_buffer_objects.h"

static void
gen8_emit_vertices(struct brw_context *brw)
{
   struct gl_context *ctx = &brw->ctx;
   uint32_t mocs_wb = brw->gen >= 9 ? SKL_MOCS_WB : BDW_MOCS_WB;
   bool uses_edge_flag;

   brw_prepare_vertices(brw);
   brw_prepare_shader_draw_parameters(brw);

   uses_edge_flag = (ctx->Polygon.FrontMode != GL_FILL ||
                     ctx->Polygon.BackMode != GL_FILL);

   if (brw->vs.prog_data->uses_vertexid || brw->vs.prog_data->uses_instanceid) {
      unsigned vue = brw->vb.nr_enabled;

      /* The element for the edge flags must always be last, so we have to
       * insert the SGVS before it in that case.
       */
      if (uses_edge_flag) {
         assert(vue > 0);
         vue--;
      }

      WARN_ONCE(vue >= 33,
                "Trying to insert VID/IID past 33rd vertex element, "
                "need to reorder the vertex attrbutes.");

      unsigned dw1 = 0;
      if (brw->vs.prog_data->uses_vertexid) {
         dw1 |= GEN8_SGVS_ENABLE_VERTEX_ID |
                (2 << GEN8_SGVS_VERTEX_ID_COMPONENT_SHIFT) |  /* .z channel */
                (vue << GEN8_SGVS_VERTEX_ID_ELEMENT_OFFSET_SHIFT);
      }

      if (brw->vs.prog_data->uses_instanceid) {
         dw1 |= GEN8_SGVS_ENABLE_INSTANCE_ID |
                (3 << GEN8_SGVS_INSTANCE_ID_COMPONENT_SHIFT) | /* .w channel */
                (vue << GEN8_SGVS_INSTANCE_ID_ELEMENT_OFFSET_SHIFT);
      }

      BEGIN_BATCH(2);
      OUT_BATCH(_3DSTATE_VF_SGVS << 16 | (2 - 2));
      OUT_BATCH(dw1);
      ADVANCE_BATCH();

      BEGIN_BATCH(3);
      OUT_BATCH(_3DSTATE_VF_INSTANCING << 16 | (3 - 2));
      OUT_BATCH(vue | GEN8_VF_INSTANCING_ENABLE);
      OUT_BATCH(0);
      ADVANCE_BATCH();
   } else {
      BEGIN_BATCH(2);
      OUT_BATCH(_3DSTATE_VF_SGVS << 16 | (2 - 2));
      OUT_BATCH(0);
      ADVANCE_BATCH();
   }

   /* If the VS doesn't read any inputs (calculating vertex position from
    * a state variable for some reason, for example), emit a single pad
    * VERTEX_ELEMENT struct and bail.
    *
    * The stale VB state stays in place, but they don't do anything unless
    * a VE loads from them.
    */
   if (brw->vb.nr_enabled == 0) {
      BEGIN_BATCH(3);
      OUT_BATCH((_3DSTATE_VERTEX_ELEMENTS << 16) | (3 - 2));
      OUT_BATCH((0 << GEN6_VE0_INDEX_SHIFT) |
                GEN6_VE0_VALID |
                (BRW_SURFACEFORMAT_R32G32B32A32_FLOAT << BRW_VE0_FORMAT_SHIFT) |
                (0 << BRW_VE0_SRC_OFFSET_SHIFT));
      OUT_BATCH((BRW_VE1_COMPONENT_STORE_0 << BRW_VE1_COMPONENT_0_SHIFT) |
                (BRW_VE1_COMPONENT_STORE_0 << BRW_VE1_COMPONENT_1_SHIFT) |
                (BRW_VE1_COMPONENT_STORE_0 << BRW_VE1_COMPONENT_2_SHIFT) |
                (BRW_VE1_COMPONENT_STORE_1_FLT << BRW_VE1_COMPONENT_3_SHIFT));
      ADVANCE_BATCH();
      return;
   }

   /* Now emit 3DSTATE_VERTEX_BUFFERS and 3DSTATE_VERTEX_ELEMENTS packets. */
   unsigned nr_buffers = brw->vb.nr_buffers + brw->vs.prog_data->uses_vertexid;
   if (nr_buffers) {
      assert(nr_buffers <= 33);

      BEGIN_BATCH(1 + 4 * nr_buffers);
      OUT_BATCH((_3DSTATE_VERTEX_BUFFERS << 16) | (4 * nr_buffers - 1));
      for (unsigned i = 0; i < brw->vb.nr_buffers; i++) {
         struct brw_vertex_buffer *buffer = &brw->vb.buffers[i];
         uint32_t dw0 = 0;

         dw0 |= i << GEN6_VB0_INDEX_SHIFT;
         dw0 |= GEN7_VB0_ADDRESS_MODIFYENABLE;
         dw0 |= buffer->stride << BRW_VB0_PITCH_SHIFT;
         dw0 |= mocs_wb << 16;

         OUT_BATCH(dw0);
         OUT_RELOC64(buffer->bo, I915_GEM_DOMAIN_VERTEX, 0, buffer->offset);
         OUT_BATCH(buffer->bo->size);
      }

      if (brw->vs.prog_data->uses_vertexid) {
         OUT_BATCH(brw->vb.nr_buffers << GEN6_VB0_INDEX_SHIFT |
                   GEN7_VB0_ADDRESS_MODIFYENABLE |
                   mocs_wb << 16);
         OUT_RELOC64(brw->draw.draw_params_bo, I915_GEM_DOMAIN_VERTEX, 0,
                     brw->draw.draw_params_offset);
         OUT_BATCH(brw->draw.draw_params_bo->size);
      }
      ADVANCE_BATCH();
   }

   /* Normally we don't need an element for the SGVS attribute because the
    * 3DSTATE_VF_SGVS instruction lets you store the generated attribute in an
    * element that is past the list in 3DSTATE_VERTEX_ELEMENTS. However if the
    * vertex ID is used then it needs an element for the base vertex buffer.
    * Additionally if there is an edge flag element then the SGVS can't be
    * inserted past that so we need a dummy element to ensure that the edge
    * flag is the last one.
    */
   bool needs_sgvs_element = (brw->vs.prog_data->uses_vertexid ||
                              (brw->vs.prog_data->uses_instanceid &&
                               uses_edge_flag));
   unsigned nr_elements = brw->vb.nr_enabled + needs_sgvs_element;

   /* The hardware allows one more VERTEX_ELEMENTS than VERTEX_BUFFERS,
    * presumably for VertexID/InstanceID.
    */
   assert(nr_elements <= 34);

   struct brw_vertex_element *gen6_edgeflag_input = NULL;

   BEGIN_BATCH(1 + nr_elements * 2);
   OUT_BATCH((_3DSTATE_VERTEX_ELEMENTS << 16) | (2 * nr_elements - 1));
   for (unsigned i = 0; i < brw->vb.nr_enabled; i++) {
      struct brw_vertex_element *input = brw->vb.enabled[i];
      uint32_t format = brw_get_vertex_surface_type(brw, input->glarray);
      uint32_t comp0 = BRW_VE1_COMPONENT_STORE_SRC;
      uint32_t comp1 = BRW_VE1_COMPONENT_STORE_SRC;
      uint32_t comp2 = BRW_VE1_COMPONENT_STORE_SRC;
      uint32_t comp3 = BRW_VE1_COMPONENT_STORE_SRC;

      /* The gen4 driver expects edgeflag to come in as a float, and passes
       * that float on to the tests in the clipper.  Mesa's current vertex
       * attribute value for EdgeFlag is stored as a float, which works out.
       * glEdgeFlagPointer, on the other hand, gives us an unnormalized
       * integer ubyte.  Just rewrite that to convert to a float.
       */
      if (input == &brw->vb.inputs[VERT_ATTRIB_EDGEFLAG]) {
         /* Gen6+ passes edgeflag as sideband along with the vertex, instead
          * of in the VUE.  We have to upload it sideband as the last vertex
          * element according to the B-Spec.
          */
         gen6_edgeflag_input = input;
         continue;
      }

      switch (input->glarray->Size) {
      case 0: comp0 = BRW_VE1_COMPONENT_STORE_0;
      case 1: comp1 = BRW_VE1_COMPONENT_STORE_0;
      case 2: comp2 = BRW_VE1_COMPONENT_STORE_0;
      case 3: comp3 = input->glarray->Integer ? BRW_VE1_COMPONENT_STORE_1_INT
                                              : BRW_VE1_COMPONENT_STORE_1_FLT;
         break;
      }

      OUT_BATCH((input->buffer << GEN6_VE0_INDEX_SHIFT) |
                GEN6_VE0_VALID |
                (format << BRW_VE0_FORMAT_SHIFT) |
                (input->offset << BRW_VE0_SRC_OFFSET_SHIFT));

      OUT_BATCH((comp0 << BRW_VE1_COMPONENT_0_SHIFT) |
                (comp1 << BRW_VE1_COMPONENT_1_SHIFT) |
                (comp2 << BRW_VE1_COMPONENT_2_SHIFT) |
                (comp3 << BRW_VE1_COMPONENT_3_SHIFT));
   }

   if (needs_sgvs_element) {
      if (brw->vs.prog_data->uses_vertexid) {
         OUT_BATCH(GEN6_VE0_VALID |
                   brw->vb.nr_buffers << GEN6_VE0_INDEX_SHIFT |
                   BRW_SURFACEFORMAT_R32_UINT << BRW_VE0_FORMAT_SHIFT);
         OUT_BATCH((BRW_VE1_COMPONENT_STORE_SRC << BRW_VE1_COMPONENT_0_SHIFT) |
                   (BRW_VE1_COMPONENT_STORE_0 << BRW_VE1_COMPONENT_1_SHIFT) |
                   (BRW_VE1_COMPONENT_STORE_0 << BRW_VE1_COMPONENT_2_SHIFT) |
                   (BRW_VE1_COMPONENT_STORE_0 << BRW_VE1_COMPONENT_3_SHIFT));
      } else {
         OUT_BATCH(GEN6_VE0_VALID);
         OUT_BATCH((BRW_VE1_COMPONENT_STORE_0 << BRW_VE1_COMPONENT_0_SHIFT) |
                   (BRW_VE1_COMPONENT_STORE_0 << BRW_VE1_COMPONENT_1_SHIFT) |
                   (BRW_VE1_COMPONENT_STORE_0 << BRW_VE1_COMPONENT_2_SHIFT) |
                   (BRW_VE1_COMPONENT_STORE_0 << BRW_VE1_COMPONENT_3_SHIFT));
      }
   }

   if (gen6_edgeflag_input) {
      uint32_t format =
         brw_get_vertex_surface_type(brw, gen6_edgeflag_input->glarray);

      OUT_BATCH((gen6_edgeflag_input->buffer << GEN6_VE0_INDEX_SHIFT) |
                GEN6_VE0_VALID |
                GEN6_VE0_EDGE_FLAG_ENABLE |
                (format << BRW_VE0_FORMAT_SHIFT) |
                (gen6_edgeflag_input->offset << BRW_VE0_SRC_OFFSET_SHIFT));
      OUT_BATCH((BRW_VE1_COMPONENT_STORE_SRC << BRW_VE1_COMPONENT_0_SHIFT) |
                (BRW_VE1_COMPONENT_STORE_0 << BRW_VE1_COMPONENT_1_SHIFT) |
                (BRW_VE1_COMPONENT_STORE_0 << BRW_VE1_COMPONENT_2_SHIFT) |
                (BRW_VE1_COMPONENT_STORE_0 << BRW_VE1_COMPONENT_3_SHIFT));
   }
   ADVANCE_BATCH();

   for (unsigned i = 0; i < brw->vb.nr_enabled; i++) {
      const struct brw_vertex_element *input = brw->vb.enabled[i];
      const struct brw_vertex_buffer *buffer = &brw->vb.buffers[input->buffer];

      BEGIN_BATCH(3);
      OUT_BATCH(_3DSTATE_VF_INSTANCING << 16 | (3 - 2));
      OUT_BATCH(i | (buffer->step_rate ? GEN8_VF_INSTANCING_ENABLE : 0));
      OUT_BATCH(buffer->step_rate);
      ADVANCE_BATCH();
   }
}

const struct brw_tracked_state gen8_vertices = {
   .dirty = {
      .mesa = _NEW_POLYGON,
      .brw = BRW_NEW_BATCH |
             BRW_NEW_VERTICES |
             BRW_NEW_VS_PROG_DATA,
   },
   .emit = gen8_emit_vertices,
};

static void
gen8_emit_index_buffer(struct brw_context *brw)
{
   const struct _mesa_index_buffer *index_buffer = brw->ib.ib;
   uint32_t mocs_wb = brw->gen >= 9 ? SKL_MOCS_WB : BDW_MOCS_WB;

   if (index_buffer == NULL)
      return;

   BEGIN_BATCH(5);
   OUT_BATCH(CMD_INDEX_BUFFER << 16 | (5 - 2));
   OUT_BATCH(brw_get_index_type(index_buffer->type) | mocs_wb);
   OUT_RELOC64(brw->ib.bo, I915_GEM_DOMAIN_VERTEX, 0, 0);
   OUT_BATCH(brw->ib.bo->size);
   ADVANCE_BATCH();
}

const struct brw_tracked_state gen8_index_buffer = {
   .dirty = {
      .mesa = 0,
      .brw = BRW_NEW_BATCH |
             BRW_NEW_INDEX_BUFFER,
   },
   .emit = gen8_emit_index_buffer,
};

static void
gen8_emit_vf_topology(struct brw_context *brw)
{
   BEGIN_BATCH(2);
   OUT_BATCH(_3DSTATE_VF_TOPOLOGY << 16 | (2 - 2));
   OUT_BATCH(brw->primitive);
   ADVANCE_BATCH();
}

const struct brw_tracked_state gen8_vf_topology = {
   .dirty = {
      .mesa = 0,
      .brw = BRW_NEW_PRIMITIVE,
   },
   .emit = gen8_emit_vf_topology,
};