From: Robin Murphy Date: Wed, 15 Jan 2020 16:42:39 +0000 Subject: [PATCH] arm64: Implement optimised checksum routine Apparently there exist certain workloads which rely heavily on software checksumming, for which the generic do_csum() implementation becomes a significant bottleneck. Therefore let's give arm64 its own optimised version - for ease of maintenance this foregoes assembly or intrisics, and is thus not actually arm64-specific, but does rely heavily on C idioms that translate well to the A64 ISA and the typical load/store capabilities of most ARMv8 CPU cores. The resulting increase in checksum throughput scales nicely with buffer size, tending towards 4x for a small in-order core (Cortex-A53), and up to 6x or more for an aggressive big core (Ampere eMAG). Reported-by: Lingyan Huang Tested-by: Lingyan Huang Signed-off-by: Robin Murphy Signed-off-by: Will Deacon --- create mode 100644 arch/arm64/lib/csum.c --- a/arch/arm64/include/asm/checksum.h +++ b/arch/arm64/include/asm/checksum.h @@ -36,6 +36,9 @@ static inline __sum16 ip_fast_csum(const } #define ip_fast_csum ip_fast_csum +extern unsigned int do_csum(const unsigned char *buff, int len); +#define do_csum do_csum + #include #endif /* __ASM_CHECKSUM_H */ --- a/arch/arm64/lib/Makefile +++ b/arch/arm64/lib/Makefile @@ -1,9 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 lib-y := clear_user.o delay.o copy_from_user.o \ copy_to_user.o copy_in_user.o copy_page.o \ - clear_page.o memchr.o memcpy.o memmove.o memset.o \ - memcmp.o strcmp.o strncmp.o strlen.o strnlen.o \ - strchr.o strrchr.o tishift.o + clear_page.o csum.o memchr.o memcpy.o memmove.o \ + memset.o memcmp.o strcmp.o strncmp.o strlen.o \ + strnlen.o strchr.o strrchr.o tishift.o ifeq ($(CONFIG_KERNEL_MODE_NEON), y) obj-$(CONFIG_XOR_BLOCKS) += xor-neon.o --- /dev/null +++ b/arch/arm64/lib/csum.c @@ -0,0 +1,123 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (C) 2019-2020 Arm Ltd. + +#include +#include +#include + +#include + +/* Looks dumb, but generates nice-ish code */ +static u64 accumulate(u64 sum, u64 data) +{ + __uint128_t tmp = (__uint128_t)sum + data; + return tmp + (tmp >> 64); +} + +unsigned int do_csum(const unsigned char *buff, int len) +{ + unsigned int offset, shift, sum; + const u64 *ptr; + u64 data, sum64 = 0; + + offset = (unsigned long)buff & 7; + /* + * This is to all intents and purposes safe, since rounding down cannot + * result in a different page or cache line being accessed, and @buff + * should absolutely not be pointing to anything read-sensitive. We do, + * however, have to be careful not to piss off KASAN, which means using + * unchecked reads to accommodate the head and tail, for which we'll + * compensate with an explicit check up-front. + */ + kasan_check_read(buff, len); + ptr = (u64 *)(buff - offset); + len = len + offset - 8; + + /* + * Head: zero out any excess leading bytes. Shifting back by the same + * amount should be at least as fast as any other way of handling the + * odd/even alignment, and means we can ignore it until the very end. + */ + shift = offset * 8; + data = READ_ONCE_NOCHECK(*ptr++); +#ifdef __LITTLE_ENDIAN + data = (data >> shift) << shift; +#else + data = (data << shift) >> shift; +#endif + + /* + * Body: straightforward aligned loads from here on (the paired loads + * underlying the quadword type still only need dword alignment). The + * main loop strictly excludes the tail, so the second loop will always + * run at least once. + */ + while (unlikely(len > 64)) { + __uint128_t tmp1, tmp2, tmp3, tmp4; + + tmp1 = READ_ONCE_NOCHECK(*(__uint128_t *)ptr); + tmp2 = READ_ONCE_NOCHECK(*(__uint128_t *)(ptr + 2)); + tmp3 = READ_ONCE_NOCHECK(*(__uint128_t *)(ptr + 4)); + tmp4 = READ_ONCE_NOCHECK(*(__uint128_t *)(ptr + 6)); + + len -= 64; + ptr += 8; + + /* This is the "don't dump the carry flag into a GPR" idiom */ + tmp1 += (tmp1 >> 64) | (tmp1 << 64); + tmp2 += (tmp2 >> 64) | (tmp2 << 64); + tmp3 += (tmp3 >> 64) | (tmp3 << 64); + tmp4 += (tmp4 >> 64) | (tmp4 << 64); + tmp1 = ((tmp1 >> 64) << 64) | (tmp2 >> 64); + tmp1 += (tmp1 >> 64) | (tmp1 << 64); + tmp3 = ((tmp3 >> 64) << 64) | (tmp4 >> 64); + tmp3 += (tmp3 >> 64) | (tmp3 << 64); + tmp1 = ((tmp1 >> 64) << 64) | (tmp3 >> 64); + tmp1 += (tmp1 >> 64) | (tmp1 << 64); + tmp1 = ((tmp1 >> 64) << 64) | sum64; + tmp1 += (tmp1 >> 64) | (tmp1 << 64); + sum64 = tmp1 >> 64; + } + while (len > 8) { + __uint128_t tmp; + + sum64 = accumulate(sum64, data); + tmp = READ_ONCE_NOCHECK(*(__uint128_t *)ptr); + + len -= 16; + ptr += 2; + +#ifdef __LITTLE_ENDIAN + data = tmp >> 64; + sum64 = accumulate(sum64, tmp); +#else + data = tmp; + sum64 = accumulate(sum64, tmp >> 64); +#endif + } + if (len > 0) { + sum64 = accumulate(sum64, data); + data = READ_ONCE_NOCHECK(*ptr); + len -= 8; + } + /* + * Tail: zero any over-read bytes similarly to the head, again + * preserving odd/even alignment. + */ + shift = len * -8; +#ifdef __LITTLE_ENDIAN + data = (data << shift) >> shift; +#else + data = (data >> shift) << shift; +#endif + sum64 = accumulate(sum64, data); + + /* Finally, folding */ + sum64 += (sum64 >> 32) | (sum64 << 32); + sum = sum64 >> 32; + sum += (sum >> 16) | (sum << 16); + if (offset & 1) + return (u16)swab32(sum); + + return sum >> 16; +}