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
|
/*
* 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.
*/
#ifndef _GLTHREAD_H
#define _GLTHREAD_H
/* The size of one batch and the maximum size of one call.
*
* This should be as low as possible, so that:
* - multiple synchronizations within a frame don't slow us down much
* - a smaller number of calls per frame can still get decent parallelism
* - the memory footprint of the queue is low, and with that comes a lower
* chance of experiencing CPU cache thrashing
* but it should be high enough so that u_queue overhead remains negligible.
*/
#define MARSHAL_MAX_CMD_SIZE (8 * 1024)
/* The number of batch slots in memory.
*
* One batch is being executed, one batch is being filled, the rest are
* waiting batches. There must be at least 1 slot for a waiting batch,
* so the minimum number of batches is 3.
*/
#define MARSHAL_MAX_BATCHES 8
#include <inttypes.h>
#include <stdbool.h>
#include "util/u_queue.h"
#include "GL/gl.h"
enum marshal_dispatch_cmd_id;
struct gl_context;
struct _mesa_HashTable;
struct glthread_vao {
GLuint Name;
bool HasUserPointer;
bool IndexBufferIsUserPointer;
};
/** A single batch of commands queued up for execution. */
struct glthread_batch
{
/** Batch fence for waiting for the execution to finish. */
struct util_queue_fence fence;
/** The worker thread will access the context with this. */
struct gl_context *ctx;
/** Amount of data used by batch commands, in bytes. */
int used;
/** Data contained in the command buffer. */
#ifdef _MSC_VER
__declspec(align(8))
#else
__attribute__((aligned(8)))
#endif
uint8_t buffer[MARSHAL_MAX_CMD_SIZE];
};
struct glthread_state
{
/** Multithreaded queue. */
struct util_queue queue;
/** This is sent to the driver for framebuffer overlay / HUD. */
struct util_queue_monitoring stats;
/** The ring of batches in memory. */
struct glthread_batch batches[MARSHAL_MAX_BATCHES];
/** Index of the last submitted batch. */
unsigned last;
/** Index of the batch being filled and about to be submitted. */
unsigned next;
/** Vertex Array objects tracked by glthread independently of Mesa. */
struct _mesa_HashTable *VAOs;
struct glthread_vao *CurrentVAO;
struct glthread_vao *LastLookedUpVAO;
struct glthread_vao DefaultVAO;
/**
* Tracks on the main thread side whether the current vertex array binding
* is in a VBO.
*/
bool vertex_array_is_vbo;
/**
* Tracks on the main thread side whether the current element array (index
* buffer) binding is in a VBO.
*/
bool draw_indirect_buffer_is_vbo;
};
void _mesa_glthread_init(struct gl_context *ctx);
void _mesa_glthread_destroy(struct gl_context *ctx);
void _mesa_glthread_restore_dispatch(struct gl_context *ctx, const char *func);
void _mesa_glthread_disable(struct gl_context *ctx, const char *func);
void _mesa_glthread_flush_batch(struct gl_context *ctx);
void _mesa_glthread_finish(struct gl_context *ctx);
void _mesa_glthread_finish_before(struct gl_context *ctx, const char *func);
void _mesa_glthread_BindVertexArray(struct gl_context *ctx, GLuint id);
void _mesa_glthread_DeleteVertexArrays(struct gl_context *ctx,
GLsizei n, const GLuint *ids);
void _mesa_glthread_GenVertexArrays(struct gl_context *ctx,
GLsizei n, GLuint *arrays);
void _mesa_glthread_AttribPointer(struct gl_context *ctx);
#endif /* _GLTHREAD_H*/
|
