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
|
/*
* Copyright 2012 Advanced Micro Devices, Inc.
* All Rights Reserved.
*
* 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
* on the rights to use, copy, modify, merge, publish, distribute, sub
* license, 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 NON-INFRINGEMENT. IN NO EVENT SHALL
* THE AUTHOR(S) AND/OR THEIR SUPPLIERS 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 "si_pipe.h"
#include "sid.h"
#include "util/u_memory.h"
void si_pm4_cmd_begin(struct si_pm4_state *state, unsigned opcode)
{
state->last_opcode = opcode;
state->last_pm4 = state->ndw++;
}
void si_pm4_cmd_add(struct si_pm4_state *state, uint32_t dw)
{
state->pm4[state->ndw++] = dw;
}
void si_pm4_cmd_end(struct si_pm4_state *state, bool predicate)
{
unsigned count;
count = state->ndw - state->last_pm4 - 2;
state->pm4[state->last_pm4] = PKT3(state->last_opcode, count, predicate);
assert(state->ndw <= SI_PM4_MAX_DW);
}
void si_pm4_set_reg(struct si_pm4_state *state, unsigned reg, uint32_t val)
{
unsigned opcode;
if (reg >= SI_CONFIG_REG_OFFSET && reg < SI_CONFIG_REG_END) {
opcode = PKT3_SET_CONFIG_REG;
reg -= SI_CONFIG_REG_OFFSET;
} else if (reg >= SI_SH_REG_OFFSET && reg < SI_SH_REG_END) {
opcode = PKT3_SET_SH_REG;
reg -= SI_SH_REG_OFFSET;
} else if (reg >= SI_CONTEXT_REG_OFFSET && reg < SI_CONTEXT_REG_END) {
opcode = PKT3_SET_CONTEXT_REG;
reg -= SI_CONTEXT_REG_OFFSET;
} else if (reg >= CIK_UCONFIG_REG_OFFSET && reg < CIK_UCONFIG_REG_END) {
opcode = PKT3_SET_UCONFIG_REG;
reg -= CIK_UCONFIG_REG_OFFSET;
} else {
PRINT_ERR("Invalid register offset %08x!\n", reg);
return;
}
reg >>= 2;
if (opcode != state->last_opcode || reg != (state->last_reg + 1)) {
si_pm4_cmd_begin(state, opcode);
si_pm4_cmd_add(state, reg);
}
state->last_reg = reg;
si_pm4_cmd_add(state, val);
si_pm4_cmd_end(state, false);
}
void si_pm4_clear_state(struct si_pm4_state *state)
{
state->ndw = 0;
}
void si_pm4_free_state(struct si_context *sctx, struct si_pm4_state *state, unsigned idx)
{
if (!state)
return;
if (idx != ~0 && sctx->emitted.array[idx] == state) {
sctx->emitted.array[idx] = NULL;
}
si_pm4_clear_state(state);
FREE(state);
}
void si_pm4_emit(struct si_context *sctx, struct si_pm4_state *state)
{
struct radeon_cmdbuf *cs = sctx->gfx_cs;
if (state->shader) {
radeon_add_to_buffer_list(sctx, sctx->gfx_cs, state->shader->bo,
RADEON_USAGE_READ, RADEON_PRIO_SHADER_BINARY);
}
radeon_emit_array(cs, state->pm4, state->ndw);
if (state->atom.emit)
state->atom.emit(sctx);
}
void si_pm4_reset_emitted(struct si_context *sctx)
{
memset(&sctx->emitted, 0, sizeof(sctx->emitted));
sctx->dirty_states |= u_bit_consecutive(0, SI_NUM_STATES);
}
|
