mesa: Replace ctx->Shader.Current{Vertex,Fragment,Geometry}Program with an array.
[mesa.git] / src / mesa / drivers / dri / i965 / gen7_vs_state.c
1 /*
2 * Copyright © 2011 Intel Corporation
3 *
4 * Permission is hereby granted, free of charge, to any person obtaining a
5 * copy of this software and associated documentation files (the "Software"),
6 * to deal in the Software without restriction, including without limitation
7 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
8 * and/or sell copies of the Software, and to permit persons to whom the
9 * Software is furnished to do so, subject to the following conditions:
10 *
11 * The above copyright notice and this permission notice (including the next
12 * paragraph) shall be included in all copies or substantial portions of the
13 * Software.
14 *
15 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
18 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
20 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
21 * IN THE SOFTWARE.
22 */
23
24 #include "brw_context.h"
25 #include "brw_state.h"
26 #include "brw_defines.h"
27 #include "brw_util.h"
28 #include "program/prog_parameter.h"
29 #include "program/prog_statevars.h"
30 #include "intel_batchbuffer.h"
31
32
33 void
34 gen7_upload_constant_state(struct brw_context *brw,
35 const struct brw_stage_state *stage_state,
36 bool active, unsigned opcode)
37 {
38 if (!active || stage_state->push_const_size == 0) {
39 /* Disable the push constant buffers. */
40 BEGIN_BATCH(7);
41 OUT_BATCH(opcode << 16 | (7 - 2));
42 OUT_BATCH(0);
43 OUT_BATCH(0);
44 OUT_BATCH(0);
45 OUT_BATCH(0);
46 OUT_BATCH(0);
47 OUT_BATCH(0);
48 ADVANCE_BATCH();
49 } else {
50 BEGIN_BATCH(7);
51 OUT_BATCH(opcode << 16 | (7 - 2));
52 OUT_BATCH(stage_state->push_const_size);
53 OUT_BATCH(0);
54 /* Pointer to the constant buffer. Covered by the set of state flags
55 * from gen6_prepare_wm_contants
56 */
57 OUT_BATCH(stage_state->push_const_offset | GEN7_MOCS_L3);
58 OUT_BATCH(0);
59 OUT_BATCH(0);
60 OUT_BATCH(0);
61 ADVANCE_BATCH();
62 }
63 }
64
65
66 static void
67 upload_vs_state(struct brw_context *brw)
68 {
69 struct gl_context *ctx = &brw->ctx;
70 const struct brw_stage_state *stage_state = &brw->vs.base;
71 uint32_t floating_point_mode = 0;
72 const int max_threads_shift = brw->is_haswell ?
73 HSW_VS_MAX_THREADS_SHIFT : GEN6_VS_MAX_THREADS_SHIFT;
74
75 gen7_emit_vs_workaround_flush(brw);
76
77 /* BRW_NEW_VS_BINDING_TABLE */
78 BEGIN_BATCH(2);
79 OUT_BATCH(_3DSTATE_BINDING_TABLE_POINTERS_VS << 16 | (2 - 2));
80 OUT_BATCH(stage_state->bind_bo_offset);
81 ADVANCE_BATCH();
82
83 /* CACHE_NEW_SAMPLER */
84 BEGIN_BATCH(2);
85 OUT_BATCH(_3DSTATE_SAMPLER_STATE_POINTERS_VS << 16 | (2 - 2));
86 OUT_BATCH(stage_state->sampler_offset);
87 ADVANCE_BATCH();
88
89 gen7_upload_constant_state(brw, stage_state, true /* active */,
90 _3DSTATE_CONSTANT_VS);
91
92 /* Use ALT floating point mode for ARB vertex programs, because they
93 * require 0^0 == 1.
94 */
95 if (ctx->Shader.CurrentProgram[MESA_SHADER_VERTEX] == NULL)
96 floating_point_mode = GEN6_VS_FLOATING_POINT_MODE_ALT;
97
98 BEGIN_BATCH(6);
99 OUT_BATCH(_3DSTATE_VS << 16 | (6 - 2));
100 OUT_BATCH(stage_state->prog_offset);
101 OUT_BATCH(floating_point_mode |
102 ((ALIGN(stage_state->sampler_count, 4)/4) <<
103 GEN6_VS_SAMPLER_COUNT_SHIFT) |
104 ((brw->vs.prog_data->base.base.binding_table.size_bytes / 4) <<
105 GEN6_VS_BINDING_TABLE_ENTRY_COUNT_SHIFT));
106
107 if (brw->vs.prog_data->base.total_scratch) {
108 OUT_RELOC(stage_state->scratch_bo,
109 I915_GEM_DOMAIN_RENDER, I915_GEM_DOMAIN_RENDER,
110 ffs(brw->vs.prog_data->base.total_scratch) - 11);
111 } else {
112 OUT_BATCH(0);
113 }
114
115 OUT_BATCH((brw->vs.prog_data->base.dispatch_grf_start_reg <<
116 GEN6_VS_DISPATCH_START_GRF_SHIFT) |
117 (brw->vs.prog_data->base.urb_read_length << GEN6_VS_URB_READ_LENGTH_SHIFT) |
118 (0 << GEN6_VS_URB_ENTRY_READ_OFFSET_SHIFT));
119
120 OUT_BATCH(((brw->max_vs_threads - 1) << max_threads_shift) |
121 GEN6_VS_STATISTICS_ENABLE |
122 GEN6_VS_ENABLE);
123 ADVANCE_BATCH();
124 }
125
126 const struct brw_tracked_state gen7_vs_state = {
127 .dirty = {
128 .mesa = _NEW_TRANSFORM | _NEW_PROGRAM_CONSTANTS,
129 .brw = (BRW_NEW_CONTEXT |
130 BRW_NEW_VERTEX_PROGRAM |
131 BRW_NEW_VS_BINDING_TABLE |
132 BRW_NEW_BATCH |
133 BRW_NEW_PUSH_CONSTANT_ALLOCATION),
134 .cache = CACHE_NEW_VS_PROG | CACHE_NEW_SAMPLER
135 },
136 .emit = upload_vs_state,
137 };