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
|
/*
* 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.
*/
/** \file gen6_sol.c
*
* Code to initialize the binding table entries used by transform feedback.
*/
#include "main/bufferobj.h"
#include "main/macros.h"
#include "brw_context.h"
#include "intel_batchbuffer.h"
#include "brw_defines.h"
#include "brw_state.h"
#include "main/transformfeedback.h"
static void
gen6_update_sol_surfaces(struct brw_context *brw)
{
struct gl_context *ctx = &brw->ctx;
/* BRW_NEW_TRANSFORM_FEEDBACK */
struct gl_transform_feedback_object *xfb_obj =
ctx->TransformFeedback.CurrentObject;
/* BRW_NEW_VERTEX_PROGRAM */
const struct gl_shader_program *shaderprog =
ctx->_Shader->CurrentProgram[MESA_SHADER_VERTEX];
const struct gl_transform_feedback_info *linked_xfb_info =
&shaderprog->LinkedTransformFeedback;
int i;
for (i = 0; i < BRW_MAX_SOL_BINDINGS; ++i) {
const int surf_index = SURF_INDEX_GEN6_SOL_BINDING(i);
if (_mesa_is_xfb_active_and_unpaused(ctx) &&
i < linked_xfb_info->NumOutputs) {
unsigned buffer = linked_xfb_info->Outputs[i].OutputBuffer;
unsigned buffer_offset =
xfb_obj->Offset[buffer] / 4 +
linked_xfb_info->Outputs[i].DstOffset;
brw_update_sol_surface(
brw, xfb_obj->Buffers[buffer], &brw->ff_gs.surf_offset[surf_index],
linked_xfb_info->Outputs[i].NumComponents,
linked_xfb_info->BufferStride[buffer], buffer_offset);
} else {
brw->ff_gs.surf_offset[surf_index] = 0;
}
}
brw->state.dirty.brw |= BRW_NEW_SURFACES;
}
const struct brw_tracked_state gen6_sol_surface = {
.dirty = {
.mesa = 0,
.brw = (BRW_NEW_BATCH |
BRW_NEW_VERTEX_PROGRAM |
BRW_NEW_TRANSFORM_FEEDBACK),
.cache = 0
},
.emit = gen6_update_sol_surfaces,
};
/**
* Constructs the binding table for the WM surface state, which maps unit
* numbers to surface state objects.
*/
static void
brw_gs_upload_binding_table(struct brw_context *brw)
{
struct gl_context *ctx = &brw->ctx;
/* BRW_NEW_VERTEX_PROGRAM */
const struct gl_shader_program *shaderprog =
ctx->_Shader->CurrentProgram[MESA_SHADER_VERTEX];
bool has_surfaces = false;
uint32_t *bind;
if (shaderprog) {
const struct gl_transform_feedback_info *linked_xfb_info =
&shaderprog->LinkedTransformFeedback;
/* Currently we only ever upload surfaces for SOL. */
has_surfaces = linked_xfb_info->NumOutputs != 0;
}
/* Skip making a binding table if we don't have anything to put in it. */
if (!has_surfaces) {
if (brw->ff_gs.bind_bo_offset != 0) {
brw->state.dirty.brw |= BRW_NEW_GS_BINDING_TABLE;
brw->ff_gs.bind_bo_offset = 0;
}
return;
}
/* Might want to calculate nr_surfaces first, to avoid taking up so much
* space for the binding table.
*/
bind = brw_state_batch(brw, AUB_TRACE_BINDING_TABLE,
sizeof(uint32_t) * BRW_MAX_GEN6_GS_SURFACES,
32, &brw->ff_gs.bind_bo_offset);
/* BRW_NEW_SURFACES */
memcpy(bind, brw->ff_gs.surf_offset, BRW_MAX_GEN6_GS_SURFACES * sizeof(uint32_t));
brw->state.dirty.brw |= BRW_NEW_GS_BINDING_TABLE;
}
const struct brw_tracked_state gen6_gs_binding_table = {
.dirty = {
.mesa = 0,
.brw = (BRW_NEW_BATCH |
BRW_NEW_VERTEX_PROGRAM |
BRW_NEW_SURFACES),
.cache = 0
},
.emit = brw_gs_upload_binding_table,
};
struct gl_transform_feedback_object *
brw_new_transform_feedback(struct gl_context *ctx, GLuint name)
{
struct brw_context *brw = brw_context(ctx);
struct brw_transform_feedback_object *brw_obj =
CALLOC_STRUCT(brw_transform_feedback_object);
if (!brw_obj)
return NULL;
_mesa_init_transform_feedback_object(&brw_obj->base, name);
brw_obj->offset_bo =
drm_intel_bo_alloc(brw->bufmgr, "transform feedback offsets", 16, 64);
brw_obj->prim_count_bo =
drm_intel_bo_alloc(brw->bufmgr, "xfb primitive counts", 4096, 64);
return &brw_obj->base;
}
void
brw_delete_transform_feedback(struct gl_context *ctx,
struct gl_transform_feedback_object *obj)
{
struct brw_transform_feedback_object *brw_obj =
(struct brw_transform_feedback_object *) obj;
for (unsigned i = 0; i < Elements(obj->Buffers); i++) {
_mesa_reference_buffer_object(ctx, &obj->Buffers[i], NULL);
}
drm_intel_bo_unreference(brw_obj->offset_bo);
drm_intel_bo_unreference(brw_obj->prim_count_bo);
free(brw_obj);
}
void
brw_begin_transform_feedback(struct gl_context *ctx, GLenum mode,
struct gl_transform_feedback_object *obj)
{
struct brw_context *brw = brw_context(ctx);
const struct gl_shader_program *vs_prog =
ctx->_Shader->CurrentProgram[MESA_SHADER_VERTEX];
const struct gl_transform_feedback_info *linked_xfb_info =
&vs_prog->LinkedTransformFeedback;
struct gl_transform_feedback_object *xfb_obj =
ctx->TransformFeedback.CurrentObject;
assert(brw->gen == 6);
/* Compute the maximum number of vertices that we can write without
* overflowing any of the buffers currently being used for feedback.
*/
unsigned max_index
= _mesa_compute_max_transform_feedback_vertices(xfb_obj,
linked_xfb_info);
/* 3DSTATE_GS_SVB_INDEX is non-pipelined. */
intel_emit_post_sync_nonzero_flush(brw);
/* Initialize the SVBI 0 register to zero and set the maximum index. */
BEGIN_BATCH(4);
OUT_BATCH(_3DSTATE_GS_SVB_INDEX << 16 | (4 - 2));
OUT_BATCH(0); /* SVBI 0 */
OUT_BATCH(0); /* starting index */
OUT_BATCH(max_index);
ADVANCE_BATCH();
/* Initialize the rest of the unused streams to sane values. Otherwise,
* they may indicate that there is no room to write data and prevent
* anything from happening at all.
*/
for (int i = 1; i < 4; i++) {
BEGIN_BATCH(4);
OUT_BATCH(_3DSTATE_GS_SVB_INDEX << 16 | (4 - 2));
OUT_BATCH(i << SVB_INDEX_SHIFT);
OUT_BATCH(0); /* starting index */
OUT_BATCH(0xffffffff);
ADVANCE_BATCH();
}
}
void
brw_end_transform_feedback(struct gl_context *ctx,
struct gl_transform_feedback_object *obj)
{
/* After EndTransformFeedback, it's likely that the client program will try
* to draw using the contents of the transform feedback buffer as vertex
* input. In order for this to work, we need to flush the data through at
* least the GS stage of the pipeline, and flush out the render cache. For
* simplicity, just do a full flush.
*/
struct brw_context *brw = brw_context(ctx);
intel_batchbuffer_emit_mi_flush(brw);
}
|
