From eb1e5037294652ddf1437f62292c0727183f11ae Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Mon, 25 Mar 2024 19:10:37 +0800 Subject: [PATCH 1/2] riscv: select ARCH_USE_CMPXCHG_LOCKREF Select ARCH_USE_CMPXCHG_LOCKREF to enable the cmpxchg-based lockless lockref implementation for riscv. Using Linus' test case[1] on TH1520 platform, I see a 11.2% improvement. On JH7110 platform, I see 12.0% improvement. Link: http://marc.info/?l=linux-fsdevel&m=137782380714721&w=4 [1] Signed-off-by: Jisheng Zhang Reviewed-by: Andrea Parri Link: https://lore.kernel.org/r/20240325111038.1700-2-jszhang@kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index bffbd869a068..b8b96baad058 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -50,6 +50,7 @@ config RISCV select ARCH_SUPPORTS_PAGE_TABLE_CHECK if MMU select ARCH_SUPPORTS_PER_VMA_LOCK if MMU select ARCH_SUPPORTS_SHADOW_CALL_STACK if HAVE_SHADOW_CALL_STACK + select ARCH_USE_CMPXCHG_LOCKREF if 64BIT select ARCH_USE_MEMTEST select ARCH_USE_QUEUED_RWLOCKS select ARCH_USES_CFI_TRAPS if CFI_CLANG From 79d6e4eae9662b9103fecf94d52b44deca56743c Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Mon, 25 Mar 2024 19:10:38 +0800 Subject: [PATCH 2/2] 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 Reviewed-by: Andrea Parri Link: https://lore.kernel.org/r/20240325111038.1700-3-jszhang@kernel.org Signed-off-by: Palmer Dabbelt --- 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 2f4726d3cfcc..6318187f426f 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 */