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
231
232
233
234
235
236
237
238
239
240
241
242
243
244
|
// Copyright 2013 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// +build race
#include "zasm_GOOS_GOARCH.h"
#include "funcdata.h"
#include "../../cmd/ld/textflag.h"
// The following thunks allow calling the gcc-compiled race runtime directly
// from Go code without going all the way through cgo.
// First, it's much faster (up to 50% speedup for real Go programs).
// Second, it eliminates race-related special cases from cgocall and scheduler.
// Third, in long-term it will allow to remove cyclic runtime/race dependency on cmd/go.
// A brief recap of the amd64 calling convention.
// Arguments are passed in DI, SI, DX, CX, R8, R9, the rest is on stack.
// Callee-saved registers are: BX, BP, R12-R15.
// SP must be 16-byte aligned.
// On Windows:
// Arguments are passed in CX, DX, R8, R9, the rest is on stack.
// Callee-saved registers are: BX, BP, DI, SI, R12-R15.
// SP must be 16-byte aligned. Windows also requires "stack-backing" for the 4 register arguments:
// http://msdn.microsoft.com/en-us/library/ms235286.aspx
// We do not do this, because it seems to be intended for vararg/unprototyped functions.
// Gcc-compiled race runtime does not try to use that space.
#ifdef GOOS_windows
#define RARG0 CX
#define RARG1 DX
#define RARG2 R8
#define RARG3 R9
#else
#define RARG0 DI
#define RARG1 SI
#define RARG2 DX
#define RARG3 CX
#endif
// func runtime·raceread(addr uintptr)
// Called from instrumented code.
TEXT runtime·raceread(SB), NOSPLIT, $0-8
MOVQ addr+0(FP), RARG1
MOVQ (SP), RARG2
// void __tsan_read(ThreadState *thr, void *addr, void *pc);
MOVQ $__tsan_read(SB), AX
JMP racecalladdr<>(SB)
// func runtime·RaceRead(addr uintptr)
TEXT runtime·RaceRead(SB), NOSPLIT, $0-8
// This needs to be a tail call, because raceread reads caller pc.
JMP runtime·raceread(SB)
// void runtime·racereadpc(void *addr, void *callpc, void *pc)
TEXT runtime·racereadpc(SB), NOSPLIT, $0-24
MOVQ addr+0(FP), RARG1
MOVQ callpc+8(FP), RARG2
MOVQ pc+16(FP), RARG3
// void __tsan_read_pc(ThreadState *thr, void *addr, void *callpc, void *pc);
MOVQ $__tsan_read_pc(SB), AX
JMP racecalladdr<>(SB)
// func runtime·racewrite(addr uintptr)
// Called from instrumented code.
TEXT runtime·racewrite(SB), NOSPLIT, $0-8
MOVQ addr+0(FP), RARG1
MOVQ (SP), RARG2
// void __tsan_write(ThreadState *thr, void *addr, void *pc);
MOVQ $__tsan_write(SB), AX
JMP racecalladdr<>(SB)
// func runtime·RaceWrite(addr uintptr)
TEXT runtime·RaceWrite(SB), NOSPLIT, $0-8
// This needs to be a tail call, because racewrite reads caller pc.
JMP runtime·racewrite(SB)
// void runtime·racewritepc(void *addr, void *callpc, void *pc)
TEXT runtime·racewritepc(SB), NOSPLIT, $0-24
MOVQ addr+0(FP), RARG1
MOVQ callpc+8(FP), RARG2
MOVQ cp+16(FP), RARG3
// void __tsan_write_pc(ThreadState *thr, void *addr, void *callpc, void *pc);
MOVQ $__tsan_write_pc(SB), AX
JMP racecalladdr<>(SB)
// func runtime·racereadrange(addr, size uintptr)
// Called from instrumented code.
TEXT runtime·racereadrange(SB), NOSPLIT, $0-16
MOVQ addr+0(FP), RARG1
MOVQ size+8(FP), RARG2
MOVQ (SP), RARG3
// void __tsan_read_range(ThreadState *thr, void *addr, uintptr size, void *pc);
MOVQ $__tsan_read_range(SB), AX
JMP racecalladdr<>(SB)
// func runtime·RaceReadRange(addr, size uintptr)
TEXT runtime·RaceReadRange(SB), NOSPLIT, $0-16
// This needs to be a tail call, because racereadrange reads caller pc.
JMP runtime·racereadrange(SB)
// void runtime·racereadrangepc1(void *addr, uintptr sz, void *pc)
TEXT runtime·racereadrangepc1(SB), NOSPLIT, $0-24
MOVQ addr+0(FP), RARG1
MOVQ size+8(FP), RARG2
MOVQ pc+16(FP), RARG3
// void __tsan_read_range(ThreadState *thr, void *addr, uintptr size, void *pc);
MOVQ $__tsan_read_range(SB), AX
JMP racecalladdr<>(SB)
// func runtime·racewriterange(addr, size uintptr)
// Called from instrumented code.
TEXT runtime·racewriterange(SB), NOSPLIT, $0-16
MOVQ addr+0(FP), RARG1
MOVQ size+8(FP), RARG2
MOVQ (SP), RARG3
// void __tsan_write_range(ThreadState *thr, void *addr, uintptr size, void *pc);
MOVQ $__tsan_write_range(SB), AX
JMP racecalladdr<>(SB)
// func runtime·RaceWriteRange(addr, size uintptr)
TEXT runtime·RaceWriteRange(SB), NOSPLIT, $0-16
// This needs to be a tail call, because racewriterange reads caller pc.
JMP runtime·racewriterange(SB)
// void runtime·racewriterangepc1(void *addr, uintptr sz, void *pc)
TEXT runtime·racewriterangepc1(SB), NOSPLIT, $0-24
MOVQ addr+0(FP), RARG1
MOVQ size+8(FP), RARG2
MOVQ pc+16(FP), RARG3
// void __tsan_write_range(ThreadState *thr, void *addr, uintptr size, void *pc);
MOVQ $__tsan_write_range(SB), AX
JMP racecalladdr<>(SB)
// If addr (RARG1) is out of range, do nothing.
// Otherwise, setup goroutine context and invoke racecall. Other arguments already set.
TEXT racecalladdr<>(SB), NOSPLIT, $0-0
get_tls(R12)
MOVQ g(R12), R14
MOVQ g_racectx(R14), RARG0 // goroutine context
// Check that addr is within [arenastart, arenaend) or within [noptrdata, enoptrbss).
CMPQ RARG1, runtime·racearenastart(SB)
JB racecalladdr_data
CMPQ RARG1, runtime·racearenaend(SB)
JB racecalladdr_call
racecalladdr_data:
CMPQ RARG1, $noptrdata(SB)
JB racecalladdr_ret
CMPQ RARG1, $enoptrbss(SB)
JAE racecalladdr_ret
racecalladdr_call:
MOVQ AX, AX // w/o this 6a miscompiles this function
JMP racecall<>(SB)
racecalladdr_ret:
RET
// func runtime·racefuncenter(pc uintptr)
// Called from instrumented code.
TEXT runtime·racefuncenter(SB), NOSPLIT, $0-8
MOVQ DX, R15 // save function entry context (for closures)
get_tls(R12)
MOVQ g(R12), R14
MOVQ g_racectx(R14), RARG0 // goroutine context
MOVQ callpc+0(FP), RARG1
// void __tsan_func_enter(ThreadState *thr, void *pc);
MOVQ $__tsan_func_enter(SB), AX
CALL racecall<>(SB)
MOVQ R15, DX // restore function entry context
RET
// func runtime·racefuncexit()
// Called from instrumented code.
TEXT runtime·racefuncexit(SB), NOSPLIT, $0-0
get_tls(R12)
MOVQ g(R12), R14
MOVQ g_racectx(R14), RARG0 // goroutine context
// void __tsan_func_exit(ThreadState *thr);
MOVQ $__tsan_func_exit(SB), AX
JMP racecall<>(SB)
// void runtime·racecall(void(*f)(...), ...)
// Calls C function f from race runtime and passes up to 4 arguments to it.
// The arguments are never heap-object-preserving pointers, so we pretend there are no arguments.
TEXT runtime·racecall(SB), NOSPLIT, $0-0
MOVQ fn+0(FP), AX
MOVQ arg0+8(FP), RARG0
MOVQ arg1+16(FP), RARG1
MOVQ arg2+24(FP), RARG2
MOVQ arg3+32(FP), RARG3
JMP racecall<>(SB)
// Switches SP to g0 stack and calls (AX). Arguments already set.
TEXT racecall<>(SB), NOSPLIT, $0-0
get_tls(R12)
MOVQ m(R12), R13
MOVQ g(R12), R14
// Switch to g0 stack.
MOVQ SP, R12 // callee-saved, preserved across the CALL
MOVQ m_g0(R13), R10
CMPQ R10, R14
JE racecall_cont // already on g0
MOVQ (g_sched+gobuf_sp)(R10), SP
racecall_cont:
ANDQ $~15, SP // alignment for gcc ABI
CALL AX
MOVQ R12, SP
RET
// C->Go callback thunk that allows to call runtime·racesymbolize from C code.
// Direct Go->C race call has only switched SP, finish g->g0 switch by setting correct g.
// The overall effect of Go->C->Go call chain is similar to that of mcall.
TEXT runtime·racesymbolizethunk(SB), NOSPLIT, $56-8
// Save callee-saved registers (Go code won't respect that).
// This is superset of darwin/linux/windows registers.
PUSHQ BX
PUSHQ BP
PUSHQ DI
PUSHQ SI
PUSHQ R12
PUSHQ R13
PUSHQ R14
PUSHQ R15
// Set g = g0.
get_tls(R12)
MOVQ m(R12), R13
MOVQ m_g0(R13), R14
MOVQ R14, g(R12) // g = m->g0
MOVQ RARG0, 0(SP) // func arg
CALL runtime·racesymbolize(SB)
// All registers are smashed after Go code, reload.
get_tls(R12)
MOVQ m(R12), R13
MOVQ m_curg(R13), R14
MOVQ R14, g(R12) // g = m->curg
// Restore callee-saved registers.
POPQ R15
POPQ R14
POPQ R13
POPQ R12
POPQ SI
POPQ DI
POPQ BP
POPQ BX
RET
|