This way we can acquire the lock with xchg+test, instead of test+xchg+test.
Most spinlocks should be uncontended so this should result in a ne
performance gain.
Before:
4ad957: eb 09 jmp 4ad962 <qht_insert+0x32>
4ad959: 0f 1f 80 00 00 00 00 nopl 0x0(%rax)
4ad960: f3 90 pause
4ad962: 8b 03 mov (%rbx),%eax
4ad964: 85 c0 test %eax,%eax
4ad966: 75 f8 jne 4ad960 <qht_insert+0x30>
4ad968: 89 f8 mov %edi,%eax
4ad96a: 87 03 xchg %eax,(%rbx)
4ad96c: 85 c0 test %eax,%eax
4ad96e: 75 f2 jne 4ad962 <qht_insert+0x32>
After:
4ad980: 89 f8 mov %edi,%eax
4ad982: 87 03 xchg %eax,(%rbx)
4ad984: 85 c0 test %eax,%eax
4ad986: 74 12 je 4ad99a <qht_insert+0x4a>
4ad988: 0f 1f 84 00 00 00 00 nopl 0x0(%rax,%rax,1)
4ad98f: 00
4ad990: 8b 03 mov (%rbx),%eax
4ad992: 85 c0 test %eax,%eax
4ad994: 74 ea je 4ad980 <qht_insert+0x30>
4ad996: f3 90 pause
4ad998: eb f6 jmp 4ad990 <qht_insert+0x40>
Signed-off-by: Emilio G. Cota <c...@braap.org>
---
include/qemu/thread.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/include/qemu/thread.h b/include/qemu/thread.h
index 599965e..e2af57c 100644
--- a/include/qemu/thread.h
+++ b/include/qemu/thread.h
@@ -74,11 +74,11 @@ static inline void qemu_spin_init(QemuSpin *spin)
static inline void qemu_spin_lock(QemuSpin *spin)
{
- do {
+ while (atomic_xchg(&spin->value, true)) {
while (atomic_read(&spin->value)) {
cpu_relax();
}
- } while (atomic_xchg(&spin->value, true));
+ }
}
static inline int qemu_spin_trylock(QemuSpin *spin)
--
2.5.0
