diff mbox series

x86/asm: Implement local_xchg using CMPXCHG without lock prefix

Message ID 20240124105816.612670-1-ubizjak@gmail.com
State New
Headers
Series x86/asm: Implement local_xchg using CMPXCHG without lock prefix |

Commit Message

Uros Bizjak Jan. 24, 2024, 10:58 a.m. UTC 
  Implement local_xchg using CMPXCHG instruction without lock prefix.
XCHG is expensive due to the implied lock prefix.  The processor
cannot prefetch cachelines if XCHG is used.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
---
 arch/x86/include/asm/local.h | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)
diff mbox series

Patch

diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index 73dba8b94443..f9af6908aa2f 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 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