mirror of
https://github.com/torvalds/linux.git
synced 2024-11-21 19:41:42 +00:00
0d75e0c420
Replace this pattern in osq_unlock():
atomic_cmpxchg(*ptr, old, new) == old
... with the simpler and faster:
atomic_try_cmpxchg(*ptr, &old, new)
The x86 CMPXCHG instruction returns success in the ZF flag,
so this change saves a compare after the CMPXCHG. The code
in the fast path of osq_unlock() improves from:
11b: 31 c9 xor %ecx,%ecx
11d: 8d 50 01 lea 0x1(%rax),%edx
120: 89 d0 mov %edx,%eax
122: f0 0f b1 0f lock cmpxchg %ecx,(%rdi)
126: 39 c2 cmp %eax,%edx
128: 75 05 jne 12f <...>
to:
12b: 31 d2 xor %edx,%edx
12d: 83 c0 01 add $0x1,%eax
130: f0 0f b1 17 lock cmpxchg %edx,(%rdi)
134: 75 05 jne 13b <...>
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Waiman Long <longman@redhat.com>
Link: https://lore.kernel.org/r/20241001114606.820277-1-ubizjak@gmail.com
|
||
|---|---|---|
| .. | ||
| irqflag-debug.c | ||
| lock_events_list.h | ||
| lock_events.c | ||
| lock_events.h | ||
| lockdep_internals.h | ||
| lockdep_proc.c | ||
| lockdep_states.h | ||
| lockdep.c | ||
| locktorture.c | ||
| Makefile | ||
| mcs_spinlock.h | ||
| mutex-debug.c | ||
| mutex.c | ||
| mutex.h | ||
| osq_lock.c | ||
| percpu-rwsem.c | ||
| qrwlock.c | ||
| qspinlock_paravirt.h | ||
| qspinlock_stat.h | ||
| qspinlock.c | ||
| rtmutex_api.c | ||
| rtmutex_common.h | ||
| rtmutex.c | ||
| rwbase_rt.c | ||
| rwsem.c | ||
| semaphore.c | ||
| spinlock_debug.c | ||
| spinlock_rt.c | ||
| spinlock.c | ||
| test-ww_mutex.c | ||
| ww_mutex.h | ||
| ww_rt_mutex.c | ||