From 442302820356977237e32a76a211e7942255003a Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 8 Sep 2014 08:20:43 +0200 Subject: s390/spinlock: optimize spin_unlock code Use a memory barrier + store sequence instead of a load + compare and swap sequence to unlock a spinlock and an rw lock. For the spinlock case this saves us two memory reads and a not needed cpu serialization after the compare and swap instruction stored the new value. The kernel size (performance_defconfig) gets reduced by ~14k. Average execution time of a tight inlined spin_unlock loop drops from 5.8ns to 0.7ns on a zEC12 machine. An artificial stress test case where several counters are protected with a single spinlock and which are only incremented while holding the spinlock shows ~30% improvement on a 4 cpu machine. Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/include/asm/barrier.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'arch/s390/include/asm/barrier.h') diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h index 19ff956b752b..b5dce6544d76 100644 --- a/arch/s390/include/asm/barrier.h +++ b/arch/s390/include/asm/barrier.h @@ -15,11 +15,13 @@ #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES /* Fast-BCR without checkpoint synchronization */ -#define mb() do { asm volatile("bcr 14,0" : : : "memory"); } while (0) +#define __ASM_BARRIER "bcr 14,0\n" #else -#define mb() do { asm volatile("bcr 15,0" : : : "memory"); } while (0) +#define __ASM_BARRIER "bcr 15,0\n" #endif +#define mb() do { asm volatile(__ASM_BARRIER : : : "memory"); } while (0) + #define rmb() mb() #define wmb() mb() #define read_barrier_depends() do { } while(0) -- cgit v1.2.3