UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity
OpenCloudOS-Kernel/arch/arm64/lib/crc32.S

105 lines
2.0 KiB
ArmAsm
Raw Normal View History

arm64/lib: add accelerated crc32 routines Unlike crc32c(), which is wired up to the crypto API internally so the optimal driver is selected based on the platform's capabilities, crc32_le() is implemented as a library function using a slice-by-8 table based C implementation. Even though few of the call sites may be bottlenecks, calling a time variant implementation with a non-negligible D-cache footprint is a bit of a waste, given that ARMv8.1 and up mandates support for the CRC32 instructions that were optional in ARMv8.0, but are already widely available, even on the Cortex-A53 based Raspberry Pi. So implement routines that use these instructions if available, and fall back to the existing generic routines otherwise. The selection is based on alternatives patching. Note that this unconditionally selects CONFIG_CRC32 as a builtin. Since CRC32 is relied upon by core functionality such as CONFIG_OF_FLATTREE, this just codifies the status quo. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2018-08-27 19:02:44 +08:00
/*
* Accelerated CRC32(C) using AArch64 CRC instructions
*
* Copyright (C) 2016 - 2018 Linaro Ltd <ard.biesheuvel@linaro.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/linkage.h>
#include <asm/alternative.h>
#include <asm/assembler.h>
.cpu generic+crc
.macro __crc32, c
arm64/lib: improve CRC32 performance for deep pipelines Improve the performance of the crc32() asm routines by getting rid of most of the branches and small sized loads on the common path. Instead, use a branchless code path involving overlapping 16 byte loads to process the first (length % 32) bytes, and process the remainder using a loop that processes 32 bytes at a time. Tested using the following test program: #include <stdlib.h> extern void crc32_le(unsigned short, char const*, int); int main(void) { static const char buf[4096]; srand(20181126); for (int i = 0; i < 100 * 1000 * 1000; i++) crc32_le(0, buf, rand() % 1024); return 0; } On Cortex-A53 and Cortex-A57, the performance regresses but only very slightly. On Cortex-A72 however, the performance improves from $ time ./crc32 real 0m10.149s user 0m10.149s sys 0m0.000s to $ time ./crc32 real 0m7.915s user 0m7.915s sys 0m0.000s Cc: Rui Sun <sunrui26@huawei.com> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Will Deacon <will.deacon@arm.com>
2018-11-28 01:42:55 +08:00
cmp x2, #16
b.lt 8f // less than 16 bytes
and x7, x2, #0x1f
and x2, x2, #~0x1f
cbz x7, 32f // multiple of 32 bytes
and x8, x7, #0xf
ldp x3, x4, [x1]
add x8, x8, x1
add x1, x1, x7
ldp x5, x6, [x8]
arm64/lib: add accelerated crc32 routines Unlike crc32c(), which is wired up to the crypto API internally so the optimal driver is selected based on the platform's capabilities, crc32_le() is implemented as a library function using a slice-by-8 table based C implementation. Even though few of the call sites may be bottlenecks, calling a time variant implementation with a non-negligible D-cache footprint is a bit of a waste, given that ARMv8.1 and up mandates support for the CRC32 instructions that were optional in ARMv8.0, but are already widely available, even on the Cortex-A53 based Raspberry Pi. So implement routines that use these instructions if available, and fall back to the existing generic routines otherwise. The selection is based on alternatives patching. Note that this unconditionally selects CONFIG_CRC32 as a builtin. Since CRC32 is relied upon by core functionality such as CONFIG_OF_FLATTREE, this just codifies the status quo. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2018-08-27 19:02:44 +08:00
CPU_BE( rev x3, x3 )
CPU_BE( rev x4, x4 )
arm64/lib: improve CRC32 performance for deep pipelines Improve the performance of the crc32() asm routines by getting rid of most of the branches and small sized loads on the common path. Instead, use a branchless code path involving overlapping 16 byte loads to process the first (length % 32) bytes, and process the remainder using a loop that processes 32 bytes at a time. Tested using the following test program: #include <stdlib.h> extern void crc32_le(unsigned short, char const*, int); int main(void) { static const char buf[4096]; srand(20181126); for (int i = 0; i < 100 * 1000 * 1000; i++) crc32_le(0, buf, rand() % 1024); return 0; } On Cortex-A53 and Cortex-A57, the performance regresses but only very slightly. On Cortex-A72 however, the performance improves from $ time ./crc32 real 0m10.149s user 0m10.149s sys 0m0.000s to $ time ./crc32 real 0m7.915s user 0m7.915s sys 0m0.000s Cc: Rui Sun <sunrui26@huawei.com> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Will Deacon <will.deacon@arm.com>
2018-11-28 01:42:55 +08:00
CPU_BE( rev x5, x5 )
CPU_BE( rev x6, x6 )
tst x7, #8
crc32\c\()x w8, w0, x3
csel x3, x3, x4, eq
csel w0, w0, w8, eq
tst x7, #4
lsr x4, x3, #32
crc32\c\()w w8, w0, w3
csel x3, x3, x4, eq
csel w0, w0, w8, eq
tst x7, #2
lsr w4, w3, #16
crc32\c\()h w8, w0, w3
csel w3, w3, w4, eq
csel w0, w0, w8, eq
tst x7, #1
crc32\c\()b w8, w0, w3
csel w0, w0, w8, eq
tst x7, #16
crc32\c\()x w8, w0, x5
crc32\c\()x w8, w8, x6
csel w0, w0, w8, eq
cbz x2, 0f
32: ldp x3, x4, [x1], #32
sub x2, x2, #32
ldp x5, x6, [x1, #-16]
CPU_BE( rev x3, x3 )
CPU_BE( rev x4, x4 )
CPU_BE( rev x5, x5 )
CPU_BE( rev x6, x6 )
arm64/lib: add accelerated crc32 routines Unlike crc32c(), which is wired up to the crypto API internally so the optimal driver is selected based on the platform's capabilities, crc32_le() is implemented as a library function using a slice-by-8 table based C implementation. Even though few of the call sites may be bottlenecks, calling a time variant implementation with a non-negligible D-cache footprint is a bit of a waste, given that ARMv8.1 and up mandates support for the CRC32 instructions that were optional in ARMv8.0, but are already widely available, even on the Cortex-A53 based Raspberry Pi. So implement routines that use these instructions if available, and fall back to the existing generic routines otherwise. The selection is based on alternatives patching. Note that this unconditionally selects CONFIG_CRC32 as a builtin. Since CRC32 is relied upon by core functionality such as CONFIG_OF_FLATTREE, this just codifies the status quo. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2018-08-27 19:02:44 +08:00
crc32\c\()x w0, w0, x3
crc32\c\()x w0, w0, x4
arm64/lib: improve CRC32 performance for deep pipelines Improve the performance of the crc32() asm routines by getting rid of most of the branches and small sized loads on the common path. Instead, use a branchless code path involving overlapping 16 byte loads to process the first (length % 32) bytes, and process the remainder using a loop that processes 32 bytes at a time. Tested using the following test program: #include <stdlib.h> extern void crc32_le(unsigned short, char const*, int); int main(void) { static const char buf[4096]; srand(20181126); for (int i = 0; i < 100 * 1000 * 1000; i++) crc32_le(0, buf, rand() % 1024); return 0; } On Cortex-A53 and Cortex-A57, the performance regresses but only very slightly. On Cortex-A72 however, the performance improves from $ time ./crc32 real 0m10.149s user 0m10.149s sys 0m0.000s to $ time ./crc32 real 0m7.915s user 0m7.915s sys 0m0.000s Cc: Rui Sun <sunrui26@huawei.com> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Will Deacon <will.deacon@arm.com>
2018-11-28 01:42:55 +08:00
crc32\c\()x w0, w0, x5
crc32\c\()x w0, w0, x6
cbnz x2, 32b
0: ret
arm64/lib: add accelerated crc32 routines Unlike crc32c(), which is wired up to the crypto API internally so the optimal driver is selected based on the platform's capabilities, crc32_le() is implemented as a library function using a slice-by-8 table based C implementation. Even though few of the call sites may be bottlenecks, calling a time variant implementation with a non-negligible D-cache footprint is a bit of a waste, given that ARMv8.1 and up mandates support for the CRC32 instructions that were optional in ARMv8.0, but are already widely available, even on the Cortex-A53 based Raspberry Pi. So implement routines that use these instructions if available, and fall back to the existing generic routines otherwise. The selection is based on alternatives patching. Note that this unconditionally selects CONFIG_CRC32 as a builtin. Since CRC32 is relied upon by core functionality such as CONFIG_OF_FLATTREE, this just codifies the status quo. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2018-08-27 19:02:44 +08:00
8: tbz x2, #3, 4f
ldr x3, [x1], #8
CPU_BE( rev x3, x3 )
crc32\c\()x w0, w0, x3
4: tbz x2, #2, 2f
ldr w3, [x1], #4
CPU_BE( rev w3, w3 )
crc32\c\()w w0, w0, w3
2: tbz x2, #1, 1f
ldrh w3, [x1], #2
CPU_BE( rev16 w3, w3 )
crc32\c\()h w0, w0, w3
1: tbz x2, #0, 0f
ldrb w3, [x1]
crc32\c\()b w0, w0, w3
0: ret
.endm
.align 5
ENTRY(crc32_le)
alternative_if_not ARM64_HAS_CRC32
b crc32_le_base
alternative_else_nop_endif
__crc32
ENDPROC(crc32_le)
.align 5
ENTRY(__crc32c_le)
alternative_if_not ARM64_HAS_CRC32
b __crc32c_le_base
alternative_else_nop_endif
__crc32 c
ENDPROC(__crc32c_le)