2014-01-22 22:13:37 +08:00
|
|
|
//===-- sanitizer_atomic_clang_other.h --------------------------*- C++ -*-===//
|
|
|
|
//
|
2019-01-19 16:50:56 +08:00
|
|
|
// 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
|
2014-01-22 22:13:37 +08:00
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
//
|
|
|
|
// This file is a part of ThreadSanitizer/AddressSanitizer runtime.
|
|
|
|
// Not intended for direct inclusion. Include sanitizer_atomic.h.
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
|
|
|
#ifndef SANITIZER_ATOMIC_CLANG_OTHER_H
|
|
|
|
#define SANITIZER_ATOMIC_CLANG_OTHER_H
|
|
|
|
|
|
|
|
namespace __sanitizer {
|
|
|
|
|
2017-06-19 19:28:59 +08:00
|
|
|
|
2014-01-22 22:13:37 +08:00
|
|
|
INLINE void proc_yield(int cnt) {
|
|
|
|
__asm__ __volatile__("" ::: "memory");
|
|
|
|
}
|
|
|
|
|
|
|
|
template<typename T>
|
|
|
|
INLINE typename T::Type atomic_load(
|
|
|
|
const volatile T *a, memory_order mo) {
|
|
|
|
DCHECK(mo & (memory_order_relaxed | memory_order_consume
|
|
|
|
| memory_order_acquire | memory_order_seq_cst));
|
|
|
|
DCHECK(!((uptr)a % sizeof(*a)));
|
|
|
|
typename T::Type v;
|
|
|
|
|
|
|
|
if (sizeof(*a) < 8 || sizeof(void*) == 8) {
|
|
|
|
// Assume that aligned loads are atomic.
|
|
|
|
if (mo == memory_order_relaxed) {
|
|
|
|
v = a->val_dont_use;
|
|
|
|
} else if (mo == memory_order_consume) {
|
|
|
|
// Assume that processor respects data dependencies
|
|
|
|
// (and that compiler won't break them).
|
|
|
|
__asm__ __volatile__("" ::: "memory");
|
|
|
|
v = a->val_dont_use;
|
|
|
|
__asm__ __volatile__("" ::: "memory");
|
|
|
|
} else if (mo == memory_order_acquire) {
|
|
|
|
__asm__ __volatile__("" ::: "memory");
|
|
|
|
v = a->val_dont_use;
|
|
|
|
__sync_synchronize();
|
|
|
|
} else { // seq_cst
|
|
|
|
// E.g. on POWER we need a hw fence even before the store.
|
|
|
|
__sync_synchronize();
|
|
|
|
v = a->val_dont_use;
|
|
|
|
__sync_synchronize();
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
// 64-bit load on 32-bit platform.
|
|
|
|
// Gross, but simple and reliable.
|
|
|
|
// Assume that it is not in read-only memory.
|
2014-05-13 16:01:59 +08:00
|
|
|
v = __sync_fetch_and_add(
|
|
|
|
const_cast<typename T::Type volatile *>(&a->val_dont_use), 0);
|
2014-01-22 22:13:37 +08:00
|
|
|
}
|
|
|
|
return v;
|
|
|
|
}
|
|
|
|
|
|
|
|
template<typename T>
|
|
|
|
INLINE void atomic_store(volatile T *a, typename T::Type v, memory_order mo) {
|
|
|
|
DCHECK(mo & (memory_order_relaxed | memory_order_release
|
|
|
|
| memory_order_seq_cst));
|
|
|
|
DCHECK(!((uptr)a % sizeof(*a)));
|
|
|
|
|
|
|
|
if (sizeof(*a) < 8 || sizeof(void*) == 8) {
|
|
|
|
// Assume that aligned loads are atomic.
|
|
|
|
if (mo == memory_order_relaxed) {
|
|
|
|
a->val_dont_use = v;
|
|
|
|
} else if (mo == memory_order_release) {
|
|
|
|
__sync_synchronize();
|
|
|
|
a->val_dont_use = v;
|
|
|
|
__asm__ __volatile__("" ::: "memory");
|
|
|
|
} else { // seq_cst
|
|
|
|
__sync_synchronize();
|
|
|
|
a->val_dont_use = v;
|
|
|
|
__sync_synchronize();
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
// 64-bit store on 32-bit platform.
|
|
|
|
// Gross, but simple and reliable.
|
|
|
|
typename T::Type cmp = a->val_dont_use;
|
|
|
|
typename T::Type cur;
|
|
|
|
for (;;) {
|
|
|
|
cur = __sync_val_compare_and_swap(&a->val_dont_use, cmp, v);
|
[sanitizer] Correct 64-bit atomic_store on 32-bit "other" platforms
Summary:
I think there might be something to optimize in `atomic_store`.
Currently, if everything goes well (and we have a different new value), we
always iterate 3 times.
For example, `with a = 0`, `oldval = a`, `newval = 42`, we get:
```
oldval = 0, newval = 42, curval = 0
oldval = 0, newval = 42, curval = 42
oldval = 42, newval = 42, curval = 42
```
and then it breaks.
Unless I am not seeing something, I don't see a point to the third iteration.
If the current value is the one we want, we should just break.
This means that 2 iterations (with a different newval) should be sufficient to
achieve what we want.
Reviewers: dvyukov, alekseyshl
Reviewed By: dvyukov
Subscribers: kubamracek, delcypher, #sanitizers, llvm-commits
Differential Revision: https://reviews.llvm.org/D46597
llvm-svn: 331890
2018-05-10 00:20:52 +08:00
|
|
|
if (cur == cmp || cur == v)
|
2014-01-22 22:13:37 +08:00
|
|
|
break;
|
|
|
|
cmp = cur;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
} // namespace __sanitizer
|
|
|
|
|
|
|
|
#endif // #ifndef SANITIZER_ATOMIC_CLANG_OTHER_H
|