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
|
//===-- tsd_shared.h --------------------------------------------*- C++ -*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
#ifndef SCUDO_TSD_SHARED_H_
#define SCUDO_TSD_SHARED_H_
#include "linux.h" // for getAndroidTlsPtr()
#include "tsd.h"
#include <pthread.h>
namespace scudo {
template <class Allocator, u32 MaxTSDCount> struct TSDRegistrySharedT {
void initLinkerInitialized(Allocator *Instance) {
Instance->initLinkerInitialized();
CHECK_EQ(pthread_key_create(&PThreadKey, nullptr), 0); // For non-TLS
NumberOfTSDs = Min(Max(1U, getNumberOfCPUs()), MaxTSDCount);
TSDs = reinterpret_cast<TSD<Allocator> *>(
map(nullptr, sizeof(TSD<Allocator>) * NumberOfTSDs, "scudo:tsd"));
for (u32 I = 0; I < NumberOfTSDs; I++)
TSDs[I].initLinkerInitialized(Instance);
// Compute all the coprimes of NumberOfTSDs. This will be used to walk the
// array of TSDs in a random order. For details, see:
// https://lemire.me/blog/2017/09/18/visiting-all-values-in-an-array-exactly-once-in-random-order/
for (u32 I = 0; I < NumberOfTSDs; I++) {
u32 A = I + 1;
u32 B = NumberOfTSDs;
// Find the GCD between I + 1 and NumberOfTSDs. If 1, they are coprimes.
while (B != 0) {
const u32 T = A;
A = B;
B = T % B;
}
if (A == 1)
CoPrimes[NumberOfCoPrimes++] = I + 1;
}
Initialized = true;
}
void init(Allocator *Instance) {
memset(this, 0, sizeof(*this));
initLinkerInitialized(Instance);
}
void unmapTestOnly() {
unmap(reinterpret_cast<void *>(TSDs),
sizeof(TSD<Allocator>) * NumberOfTSDs);
setCurrentTSD(nullptr);
pthread_key_delete(PThreadKey);
}
ALWAYS_INLINE void initThreadMaybe(Allocator *Instance,
UNUSED bool MinimalInit) {
if (LIKELY(getCurrentTSD()))
return;
initThread(Instance);
}
ALWAYS_INLINE TSD<Allocator> *getTSDAndLock(bool *UnlockRequired) {
TSD<Allocator> *TSD = getCurrentTSD();
DCHECK(TSD);
*UnlockRequired = true;
// Try to lock the currently associated context.
if (TSD->tryLock())
return TSD;
// If that fails, go down the slow path.
return getTSDAndLockSlow(TSD);
}
void disable() {
for (u32 I = 0; I < NumberOfTSDs; I++)
TSDs[I].lock();
}
void enable() {
for (u32 I = 0; I < NumberOfTSDs; I++)
TSDs[I].unlock();
}
private:
ALWAYS_INLINE void setCurrentTSD(TSD<Allocator> *CurrentTSD) {
#if _BIONIC
*getAndroidTlsPtr() = reinterpret_cast<uptr>(CurrentTSD);
#elif SCUDO_LINUX
ThreadTSD = CurrentTSD;
#else
CHECK_EQ(
pthread_setspecific(PThreadKey, reinterpret_cast<void *>(CurrentTSD)),
0);
#endif
}
ALWAYS_INLINE TSD<Allocator> *getCurrentTSD() {
#if _BIONIC
return reinterpret_cast<TSD<Allocator> *>(*getAndroidTlsPtr());
#elif SCUDO_LINUX
return ThreadTSD;
#else
return reinterpret_cast<TSD<Allocator> *>(pthread_getspecific(PThreadKey));
#endif
}
void initOnceMaybe(Allocator *Instance) {
ScopedLock L(Mutex);
if (LIKELY(Initialized))
return;
initLinkerInitialized(Instance); // Sets Initialized.
}
NOINLINE void initThread(Allocator *Instance) {
initOnceMaybe(Instance);
// Initial context assignment is done in a plain round-robin fashion.
const u32 Index = atomic_fetch_add(&CurrentIndex, 1U, memory_order_relaxed);
setCurrentTSD(&TSDs[Index % NumberOfTSDs]);
}
NOINLINE TSD<Allocator> *getTSDAndLockSlow(TSD<Allocator> *CurrentTSD) {
if (MaxTSDCount > 1U && NumberOfTSDs > 1U) {
// Use the Precedence of the current TSD as our random seed. Since we are
// in the slow path, it means that tryLock failed, and as a result it's
// very likely that said Precedence is non-zero.
const u32 R = static_cast<u32>(CurrentTSD->getPrecedence());
const u32 Inc = CoPrimes[R % NumberOfCoPrimes];
u32 Index = R % NumberOfTSDs;
uptr LowestPrecedence = UINTPTR_MAX;
TSD<Allocator> *CandidateTSD = nullptr;
// Go randomly through at most 4 contexts and find a candidate.
for (u32 I = 0; I < Min(4U, NumberOfTSDs); I++) {
if (TSDs[Index].tryLock()) {
setCurrentTSD(&TSDs[Index]);
return &TSDs[Index];
}
const uptr Precedence = TSDs[Index].getPrecedence();
// A 0 precedence here means another thread just locked this TSD.
if (Precedence && Precedence < LowestPrecedence) {
CandidateTSD = &TSDs[Index];
LowestPrecedence = Precedence;
}
Index += Inc;
if (Index >= NumberOfTSDs)
Index -= NumberOfTSDs;
}
if (CandidateTSD) {
CandidateTSD->lock();
setCurrentTSD(CandidateTSD);
return CandidateTSD;
}
}
// Last resort, stick with the current one.
CurrentTSD->lock();
return CurrentTSD;
}
pthread_key_t PThreadKey;
atomic_u32 CurrentIndex;
u32 NumberOfTSDs;
TSD<Allocator> *TSDs;
u32 NumberOfCoPrimes;
u32 CoPrimes[MaxTSDCount];
bool Initialized;
HybridMutex Mutex;
#if SCUDO_LINUX && !_BIONIC
static THREADLOCAL TSD<Allocator> *ThreadTSD;
#endif
};
#if SCUDO_LINUX && !_BIONIC
template <class Allocator, u32 MaxTSDCount>
THREADLOCAL TSD<Allocator>
*TSDRegistrySharedT<Allocator, MaxTSDCount>::ThreadTSD;
#endif
} // namespace scudo
#endif // SCUDO_TSD_SHARED_H_
|
