From 1a19ad7ee149a704999318492935f017137bbf24 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Wed, 12 Oct 2022 16:36:14 +0800 Subject: [PATCH] LoongArch: Add qspinlock support On NUMA system, the performance of qspinlock is better than generic spinlock. Below is the UnixBench test results on a 8 nodes (4 cores per node, 32 cores in total) machine. A. With generic spinlock: System Benchmarks Index Values BASELINE RESULT INDEX Dhrystone 2 using register variables 116700.0 449574022.5 38523.9 Double-Precision Whetstone 55.0 85190.4 15489.2 Execl Throughput 43.0 14696.2 3417.7 File Copy 1024 bufsize 2000 maxblocks 3960.0 143157.8 361.5 File Copy 256 bufsize 500 maxblocks 1655.0 37631.8 227.4 File Copy 4096 bufsize 8000 maxblocks 5800.0 444814.2 766.9 Pipe Throughput 12440.0 5047490.7 4057.5 Pipe-based Context Switching 4000.0 2021545.7 5053.9 Process Creation 126.0 23829.8 1891.3 Shell Scripts (1 concurrent) 42.4 33756.7 7961.5 Shell Scripts (8 concurrent) 6.0 4062.9 6771.5 System Call Overhead 15000.0 2479748.6 1653.2 ======== System Benchmarks Index Score 2955.6 B. With qspinlock: System Benchmarks Index Values BASELINE RESULT INDEX Dhrystone 2 using register variables 116700.0 449467876.9 38514.8 Double-Precision Whetstone 55.0 85174.6 15486.3 Execl Throughput 43.0 14769.1 3434.7 File Copy 1024 bufsize 2000 maxblocks 3960.0 146150.5 369.1 File Copy 256 bufsize 500 maxblocks 1655.0 37496.8 226.6 File Copy 4096 bufsize 8000 maxblocks 5800.0 447527.0 771.6 Pipe Throughput 12440.0 5175989.2 4160.8 Pipe-based Context Switching 4000.0 2207747.8 5519.4 Process Creation 126.0 25125.5 1994.1 Shell Scripts (1 concurrent) 42.4 33461.2 7891.8 Shell Scripts (8 concurrent) 6.0 4024.7 6707.8 System Call Overhead 15000.0 2917278.6 1944.9 ======== System Benchmarks Index Score 3040.1 Signed-off-by: Rui Wang Signed-off-by: Huacai Chen --- arch/loongarch/Kconfig | 1 + arch/loongarch/include/asm/Kbuild | 5 ++--- arch/loongarch/include/asm/spinlock.h | 12 ++++++++++++ arch/loongarch/include/asm/spinlock_types.h | 11 +++++++++++ 4 files changed, 26 insertions(+), 3 deletions(-) create mode 100644 arch/loongarch/include/asm/spinlock.h create mode 100644 arch/loongarch/include/asm/spinlock_types.h diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index d126c50b2310c..b36156a1896f7 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -51,6 +51,7 @@ config LOONGARCH select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF select ARCH_USE_QUEUED_RWLOCKS + select ARCH_USE_QUEUED_SPINLOCKS select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT select ARCH_WANT_LD_ORPHAN_WARN select ARCH_WANTS_NO_INSTR diff --git a/arch/loongarch/include/asm/Kbuild b/arch/loongarch/include/asm/Kbuild index 83bc0681e72b4..a0eed6076c79a 100644 --- a/arch/loongarch/include/asm/Kbuild +++ b/arch/loongarch/include/asm/Kbuild @@ -1,12 +1,11 @@ # SPDX-License-Identifier: GPL-2.0 generic-y += dma-contiguous.h generic-y += export.h +generic-y += mcs_spinlock.h generic-y += parport.h generic-y += early_ioremap.h generic-y += qrwlock.h -generic-y += qrwlock_types.h -generic-y += spinlock.h -generic-y += spinlock_types.h +generic-y += qspinlock.h generic-y += rwsem.h generic-y += segment.h generic-y += user.h diff --git a/arch/loongarch/include/asm/spinlock.h b/arch/loongarch/include/asm/spinlock.h new file mode 100644 index 0000000000000..7cb3476999bec --- /dev/null +++ b/arch/loongarch/include/asm/spinlock.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2020-2022 Loongson Technology Corporation Limited + */ +#ifndef _ASM_SPINLOCK_H +#define _ASM_SPINLOCK_H + +#include +#include +#include + +#endif /* _ASM_SPINLOCK_H */ diff --git a/arch/loongarch/include/asm/spinlock_types.h b/arch/loongarch/include/asm/spinlock_types.h new file mode 100644 index 0000000000000..7458d036c161d --- /dev/null +++ b/arch/loongarch/include/asm/spinlock_types.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2020-2022 Loongson Technology Corporation Limited + */ +#ifndef _ASM_SPINLOCK_TYPES_H +#define _ASM_SPINLOCK_TYPES_H + +#include +#include + +#endif -- 2.39.5