[PATCH 6/5] x86/percpu: Optimize raw_cpu_xchg()

[Peter Zijlstra]

And because it's one of _those_ days, I forgot to include one patch...

---
Subject: x86/percpu: Optimize raw_cpu_xchg()
From: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Date: Wed Feb 27 11:09:56 CET 2019

Since raw_cpu_xchg() doesn't need to be IRQ-safe, like
this_cpu_xchg(), we can use a simple load-store instead of the cmpxchg
loop.

Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
---
 arch/x86/include/asm/percpu.h |   18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -407,9 +407,21 @@ do {									\
 #define raw_cpu_or_1(pcp, val)		percpu_to_op(, "or", (pcp), val)
 #define raw_cpu_or_2(pcp, val)		percpu_to_op(, "or", (pcp), val)
 #define raw_cpu_or_4(pcp, val)		percpu_to_op(, "or", (pcp), val)
-#define raw_cpu_xchg_1(pcp, val)	percpu_xchg_op(, pcp, val)
-#define raw_cpu_xchg_2(pcp, val)	percpu_xchg_op(, pcp, val)
-#define raw_cpu_xchg_4(pcp, val)	percpu_xchg_op(, pcp, val)
+
+/*
+ * raw_cpu_xchg() can use a load-store since it is not required to be
+ * IRQ-safe.
+ */
+#define raw_percpu_xchg_op(var, nval)					\
+({									\
+	typeof(var) pxo_ret__ = raw_cpu_read(var);			\
+	raw_cpu_write(var, (nval));					\
+	pxo_ret__;							\
+})
+
+#define raw_cpu_xchg_1(pcp, val)	raw_percpu_xchg_op(pcp, val)
+#define raw_cpu_xchg_2(pcp, val)	raw_percpu_xchg_op(pcp, val)
+#define raw_cpu_xchg_4(pcp, val)	raw_percpu_xchg_op(pcp, val)
 
 #define this_cpu_read_1(pcp)		percpu_from_op(volatile, "mov", pcp)
 #define this_cpu_read_2(pcp)		percpu_from_op(volatile, "mov", pcp)