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
|
/*
* Copyright © 2011 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 "brw_context.h"
#include "brw_state.h"
#include "brw_defines.h"
#include "brw_util.h"
#include "program/prog_parameter.h"
#include "program/prog_statevars.h"
#include "intel_batchbuffer.h"
void
gen7_upload_constant_state(struct brw_context *brw,
const struct brw_stage_state *stage_state,
bool active, unsigned opcode)
{
uint32_t mocs = brw->gen < 8 ? GEN7_MOCS_L3 : 0;
/* Disable if the shader stage is inactive or there are no push constants. */
active = active && stage_state->push_const_size != 0;
int dwords = brw->gen >= 8 ? 11 : 7;
BEGIN_BATCH(dwords);
OUT_BATCH(opcode << 16 | (dwords - 2));
/* Workaround for SKL+ (we use option #2 until we have a need for more
* constant buffers). This comes from the documentation for 3DSTATE_CONSTANT_*
*
* The driver must ensure The following case does not occur without a flush
* to the 3D engine: 3DSTATE_CONSTANT_* with buffer 3 read length equal to
* zero committed followed by a 3DSTATE_CONSTANT_* with buffer 0 read length
* not equal to zero committed. Possible ways to avoid this condition
* include:
* 1. always force buffer 3 to have a non zero read length
* 2. always force buffer 0 to a zero read length
*/
if (brw->gen >= 9 && active) {
OUT_BATCH(0);
OUT_BATCH(stage_state->push_const_size);
} else {
OUT_BATCH(active ? stage_state->push_const_size : 0);
OUT_BATCH(0);
}
/* Pointer to the constant buffer. Covered by the set of state flags
* from gen6_prepare_wm_contants
*/
if (brw->gen >= 9 && active) {
OUT_BATCH(0);
OUT_BATCH(0);
OUT_BATCH(0);
OUT_BATCH(0);
/* XXX: When using buffers other than 0, you need to specify the
* graphics virtual address regardless of INSPM/debug bits
*/
OUT_RELOC64(brw->batch.bo, I915_GEM_DOMAIN_RENDER, 0,
stage_state->push_const_offset);
OUT_BATCH(0);
OUT_BATCH(0);
} else if (brw->gen>= 8) {
OUT_BATCH(active ? (stage_state->push_const_offset | mocs) : 0);
OUT_BATCH(0);
OUT_BATCH(0);
OUT_BATCH(0);
OUT_BATCH(0);
OUT_BATCH(0);
OUT_BATCH(0);
OUT_BATCH(0);
} else {
OUT_BATCH(active ? (stage_state->push_const_offset | mocs) : 0);
OUT_BATCH(0);
OUT_BATCH(0);
OUT_BATCH(0);
}
ADVANCE_BATCH();
/* On SKL+ the new constants don't take effect until the next corresponding
* 3DSTATE_BINDING_TABLE_POINTER_* command is parsed so we need to ensure
* that is sent
*/
if (brw->gen >= 9)
brw->ctx.NewDriverState |= BRW_NEW_SURFACES;
}
static void
upload_vs_state(struct brw_context *brw)
{
const struct brw_stage_state *stage_state = &brw->vs.base;
uint32_t floating_point_mode = 0;
const int max_threads_shift = brw->is_haswell ?
HSW_VS_MAX_THREADS_SHIFT : GEN6_VS_MAX_THREADS_SHIFT;
const struct brw_vue_prog_data *prog_data = &brw->vs.prog_data->base;
if (!brw->is_haswell && !brw->is_baytrail)
gen7_emit_vs_workaround_flush(brw);
if (brw->vs.prog_data->base.base.use_alt_mode)
floating_point_mode = GEN6_VS_FLOATING_POINT_MODE_ALT;
BEGIN_BATCH(6);
OUT_BATCH(_3DSTATE_VS << 16 | (6 - 2));
OUT_BATCH(stage_state->prog_offset);
OUT_BATCH(floating_point_mode |
((ALIGN(stage_state->sampler_count, 4)/4) <<
GEN6_VS_SAMPLER_COUNT_SHIFT) |
((brw->vs.prog_data->base.base.binding_table.size_bytes / 4) <<
GEN6_VS_BINDING_TABLE_ENTRY_COUNT_SHIFT) |
(brw->is_haswell && prog_data->base.nr_image_params ?
HSW_VS_UAV_ACCESS_ENABLE : 0));
if (prog_data->base.total_scratch) {
OUT_RELOC(stage_state->scratch_bo,
I915_GEM_DOMAIN_RENDER, I915_GEM_DOMAIN_RENDER,
ffs(prog_data->base.total_scratch) - 11);
} else {
OUT_BATCH(0);
}
OUT_BATCH((prog_data->base.dispatch_grf_start_reg <<
GEN6_VS_DISPATCH_START_GRF_SHIFT) |
(prog_data->urb_read_length << GEN6_VS_URB_READ_LENGTH_SHIFT) |
(0 << GEN6_VS_URB_ENTRY_READ_OFFSET_SHIFT));
OUT_BATCH(((brw->max_vs_threads - 1) << max_threads_shift) |
GEN6_VS_STATISTICS_ENABLE |
GEN6_VS_ENABLE);
ADVANCE_BATCH();
}
const struct brw_tracked_state gen7_vs_state = {
.dirty = {
.mesa = _NEW_TRANSFORM,
.brw = BRW_NEW_BATCH |
BRW_NEW_CONTEXT |
BRW_NEW_VS_PROG_DATA,
},
.emit = upload_vs_state,
};
|
