From 1f8f674f4a22c13a8104b8d5e795b201676c9e00 Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Sat, 25 Nov 2023 16:21:44 +0800 Subject: [PATCH] riscv: cmpxchg: implement arch_cmpxchg64_{relaxed|acquire|release} After selecting ARCH_USE_CMPXCHG_LOCKREF, one straight futher optimization is implementing the arch_cmpxchg64_relaxed() because the lockref code does not need the cmpxchg to have barrier semantics. At the same time, implement arch_cmpxchg64_acquire and arch_cmpxchg64_release as well. However, on both TH1520 and JH7110 platforms, I didn't see obvious performance improvement with Linus' test case [1]. IMHO, this may be related with the fence and lr.d/sc.d hw implementations. In theory, lr/sc without fence could give performance improvement over lr/sc plus fence, so add the code here to leave performance improvement room on newer HW platforms. Link: http://marc.info/?l=linux-fsdevel&m=137782380714721&w=4 [1] Signed-off-by: Jisheng Zhang --- arch/riscv/include/asm/cmpxchg.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h index 2f4726d3cfcc25..6318187f426f65 100644 --- a/arch/riscv/include/asm/cmpxchg.h +++ b/arch/riscv/include/asm/cmpxchg.h @@ -360,4 +360,22 @@ arch_cmpxchg_relaxed((ptr), (o), (n)); \ }) +#define arch_cmpxchg64_relaxed(ptr, o, n) \ +({ \ + BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ + arch_cmpxchg_relaxed((ptr), (o), (n)); \ +}) + +#define arch_cmpxchg64_acquire(ptr, o, n) \ +({ \ + BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ + arch_cmpxchg_acquire((ptr), (o), (n)); \ +}) + +#define arch_cmpxchg64_release(ptr, o, n) \ +({ \ + BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ + arch_cmpxchg_release((ptr), (o), (n)); \ +}) + #endif /* _ASM_RISCV_CMPXCHG_H */