aboutsummaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
authorLinus Torvalds2024-03-11 18:33:03 -0700
committerLinus Torvalds2024-03-11 18:33:03 -0700
commita5b1a017cb76e4898dd62fcb97e8aee6a63b33b5 (patch)
treeaf38e275caeceed23ec5dea73cf71aa7818da75b /arch/x86
parentb0402403e54ae9eb94ce1cbb53c7def776e97426 (diff)
parentce3576ebd62d99f79c1dc98824e2ef6d6ab68434 (diff)
Merge tag 'locking-core-2024-03-11' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull locking updates from Ingo Molnar: - Micro-optimize local_xchg() and the rtmutex code on x86 - Fix percpu-rwsem contention tracepoints - Simplify debugging Kconfig dependencies - Update/clarify the documentation of atomic primitives - Misc cleanups * tag 'locking-core-2024-03-11' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: locking/rtmutex: Use try_cmpxchg_relaxed() in mark_rt_mutex_waiters() locking/x86: Implement local_xchg() using CMPXCHG without the LOCK prefix locking/percpu-rwsem: Trigger contention tracepoints only if contended locking/rwsem: Make DEBUG_RWSEMS and PREEMPT_RT mutually exclusive locking/rwsem: Clarify that RWSEM_READER_OWNED is just a hint locking/mutex: Simplify <linux/mutex.h> locking/qspinlock: Fix 'wait_early' set but not used warning locking/atomic: scripts: Clarify ordering of conditional atomics
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/include/asm/local.h16
1 files changed, 14 insertions, 2 deletions
diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index 73dba8b94443..59aa966dc212 100644
--- a/arch/x86/include/asm/local.h
+++ b/arch/x86/include/asm/local.h
@@ -131,8 +131,20 @@ static inline bool local_try_cmpxchg(local_t *l, long *old, long new)
(typeof(l->a.counter) *) old, new);
}
-/* Always has a lock prefix */
-#define local_xchg(l, n) (xchg(&((l)->a.counter), (n)))
+/*
+ * Implement local_xchg using CMPXCHG instruction without the LOCK prefix.
+ * XCHG is expensive due to the implied LOCK prefix. The processor
+ * cannot prefetch cachelines if XCHG is used.
+ */
+static __always_inline long
+local_xchg(local_t *l, long n)
+{
+ long c = local_read(l);
+
+ do { } while (!local_try_cmpxchg(l, &c, n));
+
+ return c;
+}
/**
* local_add_unless - add unless the number is already a given value