Mirrors/u-boot
2
0
Fork 0
mirror of https://github.com/AsahiLinux/u-boot synced 2024-11-18 18:59:44 +00:00
Code Issues Projects Releases Packages Wiki Activity
u-boot/arch/arm/include/asm/assembler.h

85 lines
2 KiB
C
Raw Normal View History

arm: Use optimized memcpy and memset from linux Using optimized versions of memset and memcpy from linux brings a quite noticeable speed (x2 or better) improvement for these two functions. Here are some numbers for test done with jadecpu | HEAD(1)| HEAD(1)| HEAD(2)| HEAD(2)| | | +patch | | +patch | ---------------------------+--------+--------+--------+--------+ Reset to prompt | 438ms | 330ms | 228ms | 120ms | | | | | | TFTP a 3MB img | 4782ms | 3428ms | 3245ms | 2820ms | | | | | | FATLOAD USB a 3MB img* | 8515ms | 8510ms | ------ | ------ | | | | | | BOOTM LZO img in RAM | 3473ms | 3168ms | 592ms | 592ms | where CRC is | 615ms | 615ms | 54ms | 54ms | uncompress | 2460ms | 2462ms | 450ms | 451ms | final boot_elf | 376ms | 68ms | 65ms | 65ms | | | | | | BOOTM LZO img in FLASH | 3207ms | 2902ms | 1050ms | 1050ms | where CRC is | 600ms | 600ms | 135ms | 135ms | uncompress | 2209ms | 2211ms | 828ms | 828ms | | | | | | Copy 1.4MB from NOR to RAM | 134ms | 72ms | 120ms | 70ms | (1) No dcache (2) dcache enabled in board_init *Does not work when dcache is on Size impact: C version: text data bss dec hex filename 202862 18912 266456 488230 77326 u-boot ASM version: text data bss dec hex filename 203798 18912 266288 488998 77626 u-boot 222712 u-boot.bin Signed-off-by: Matthias Weisser <weisserm@arcor.de>
2011-03-10 21:36:32 +00:00
/*
* arch/arm/include/asm/assembler.h
*
* Copyright (C) 1996-2000 Russell King
*
* 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.
*
* This file contains arm architecture specific defines
* for the different processors.
*
* Do not include any C declarations in this file - it is included by
* assembler source.
*/
arm: build arch memset/memcpy in Thumb2 mode Resynchronize memcpy/memset with kernel 3.17 and build them in Thumb2 mode (unified syntax). Those assembler files can be built and linked in ARM mode too, however when calling them from Thumb2 built code, the stack got corrupted and the copy did not succeed (the exact details have not been traced back). However, the Linux kernel builds those files in Thumb2 mode. Hence U-Boot should build them in Thumb2 mode too when CONFIG_SYS_THUMB_BUILD is set. To build the files without warning, some assembler instructions had to be replaced with their UAL compliant variant (thanks Jeroen for this input). To build the file in Thumb2 mode the implicit-it=always option need to be set to generate Thumb2 compliant IT instructions where needed. We add this option to the general AFLAGS when building for Thumb2. Reviewed-by: Simon Glass <sjg@chromium.org> Tested-by: Simon Glass <sjg@chromium.org> Signed-off-by: Stefan Agner <stefan@agner.ch>
2014-12-18 17:10:33 +00:00
#include <config.h>
arm: include: Import unified.h from Linux kernel Import unified.h from Linux kernel 4.4.6 , commit 0d1912303e54ed1b2a371be0bba51c384dd57326 . This header file contains macros used in libgcc functions in Linux kernel on ARM and will be needed for the libgcc sync. Since unified.h defines the W(instr) macro, we must drop this from the macro from memcpy.S , otherwise this triggers a warning about symbol redefinition. In order to keep the changes to unified.h to the minimum, tweak arch/arm/lib/Makefile such that it defines the CONFIG_ARM_ASM_UNIFIED macro, which places .syntax unified into all of the assembler files. This is mandatory. Moreover, for Thumb2 build, define CONFIG_THUMB2_KERNEL macro if and only if Thumb2 build is enabled. This macro is checked by unified.h and toggles between ARM and Thumb2 variant of the instructions in the assembler source files. Finally, this patch defines __LINUX_ARM_ARCH__=N macro based on the new CONFIG_SYS_ARM_ARCH Kconfig option. This macro selects between more optimal and more dense codepaths which work on armv5 and newer and less optimal codepaths which work on armv4 and possible armv3m. Tegra2 needs the same special handling as it does in arch/arm/Makefile to cater for the arm720t boot core. Signed-off-by: Marek Vasut <marex@denx.de> Cc: Albert Aribaud <albert.u.boot@aribaud.net> Cc: Masahiro Yamada <yamada.masahiro@socionext.com> Cc: Simon Glass <sjg@chromium.org> Cc: Tom Rini <trini@konsulko.com> Reviewed-by: Tom Rini <trini@konsulko.com>
2016-05-26 16:01:37 +00:00
#include <asm/unified.h>
arm: build arch memset/memcpy in Thumb2 mode Resynchronize memcpy/memset with kernel 3.17 and build them in Thumb2 mode (unified syntax). Those assembler files can be built and linked in ARM mode too, however when calling them from Thumb2 built code, the stack got corrupted and the copy did not succeed (the exact details have not been traced back). However, the Linux kernel builds those files in Thumb2 mode. Hence U-Boot should build them in Thumb2 mode too when CONFIG_SYS_THUMB_BUILD is set. To build the files without warning, some assembler instructions had to be replaced with their UAL compliant variant (thanks Jeroen for this input). To build the file in Thumb2 mode the implicit-it=always option need to be set to generate Thumb2 compliant IT instructions where needed. We add this option to the general AFLAGS when building for Thumb2. Reviewed-by: Simon Glass <sjg@chromium.org> Tested-by: Simon Glass <sjg@chromium.org> Signed-off-by: Stefan Agner <stefan@agner.ch>
2014-12-18 17:10:33 +00:00
arm: Use optimized memcpy and memset from linux Using optimized versions of memset and memcpy from linux brings a quite noticeable speed (x2 or better) improvement for these two functions. Here are some numbers for test done with jadecpu | HEAD(1)| HEAD(1)| HEAD(2)| HEAD(2)| | | +patch | | +patch | ---------------------------+--------+--------+--------+--------+ Reset to prompt | 438ms | 330ms | 228ms | 120ms | | | | | | TFTP a 3MB img | 4782ms | 3428ms | 3245ms | 2820ms | | | | | | FATLOAD USB a 3MB img* | 8515ms | 8510ms | ------ | ------ | | | | | | BOOTM LZO img in RAM | 3473ms | 3168ms | 592ms | 592ms | where CRC is | 615ms | 615ms | 54ms | 54ms | uncompress | 2460ms | 2462ms | 450ms | 451ms | final boot_elf | 376ms | 68ms | 65ms | 65ms | | | | | | BOOTM LZO img in FLASH | 3207ms | 2902ms | 1050ms | 1050ms | where CRC is | 600ms | 600ms | 135ms | 135ms | uncompress | 2209ms | 2211ms | 828ms | 828ms | | | | | | Copy 1.4MB from NOR to RAM | 134ms | 72ms | 120ms | 70ms | (1) No dcache (2) dcache enabled in board_init *Does not work when dcache is on Size impact: C version: text data bss dec hex filename 202862 18912 266456 488230 77326 u-boot ASM version: text data bss dec hex filename 203798 18912 266288 488998 77626 u-boot 222712 u-boot.bin Signed-off-by: Matthias Weisser <weisserm@arcor.de>
2011-03-10 21:36:32 +00:00
/*
* Endian independent macros for shifting bytes within registers.
*/
#ifndef __ARMEB__
arm: build arch memset/memcpy in Thumb2 mode Resynchronize memcpy/memset with kernel 3.17 and build them in Thumb2 mode (unified syntax). Those assembler files can be built and linked in ARM mode too, however when calling them from Thumb2 built code, the stack got corrupted and the copy did not succeed (the exact details have not been traced back). However, the Linux kernel builds those files in Thumb2 mode. Hence U-Boot should build them in Thumb2 mode too when CONFIG_SYS_THUMB_BUILD is set. To build the files without warning, some assembler instructions had to be replaced with their UAL compliant variant (thanks Jeroen for this input). To build the file in Thumb2 mode the implicit-it=always option need to be set to generate Thumb2 compliant IT instructions where needed. We add this option to the general AFLAGS when building for Thumb2. Reviewed-by: Simon Glass <sjg@chromium.org> Tested-by: Simon Glass <sjg@chromium.org> Signed-off-by: Stefan Agner <stefan@agner.ch>
2014-12-18 17:10:33 +00:00
#define lspull lsr
#define lspush lsl
arm: Use optimized memcpy and memset from linux Using optimized versions of memset and memcpy from linux brings a quite noticeable speed (x2 or better) improvement for these two functions. Here are some numbers for test done with jadecpu | HEAD(1)| HEAD(1)| HEAD(2)| HEAD(2)| | | +patch | | +patch | ---------------------------+--------+--------+--------+--------+ Reset to prompt | 438ms | 330ms | 228ms | 120ms | | | | | | TFTP a 3MB img | 4782ms | 3428ms | 3245ms | 2820ms | | | | | | FATLOAD USB a 3MB img* | 8515ms | 8510ms | ------ | ------ | | | | | | BOOTM LZO img in RAM | 3473ms | 3168ms | 592ms | 592ms | where CRC is | 615ms | 615ms | 54ms | 54ms | uncompress | 2460ms | 2462ms | 450ms | 451ms | final boot_elf | 376ms | 68ms | 65ms | 65ms | | | | | | BOOTM LZO img in FLASH | 3207ms | 2902ms | 1050ms | 1050ms | where CRC is | 600ms | 600ms | 135ms | 135ms | uncompress | 2209ms | 2211ms | 828ms | 828ms | | | | | | Copy 1.4MB from NOR to RAM | 134ms | 72ms | 120ms | 70ms | (1) No dcache (2) dcache enabled in board_init *Does not work when dcache is on Size impact: C version: text data bss dec hex filename 202862 18912 266456 488230 77326 u-boot ASM version: text data bss dec hex filename 203798 18912 266288 488998 77626 u-boot 222712 u-boot.bin Signed-off-by: Matthias Weisser <weisserm@arcor.de>
2011-03-10 21:36:32 +00:00
#define get_byte_0 lsl #0
#define get_byte_1 lsr #8
#define get_byte_2 lsr #16
#define get_byte_3 lsr #24
#define put_byte_0 lsl #0
#define put_byte_1 lsl #8
#define put_byte_2 lsl #16
#define put_byte_3 lsl #24
#else
arm: build arch memset/memcpy in Thumb2 mode Resynchronize memcpy/memset with kernel 3.17 and build them in Thumb2 mode (unified syntax). Those assembler files can be built and linked in ARM mode too, however when calling them from Thumb2 built code, the stack got corrupted and the copy did not succeed (the exact details have not been traced back). However, the Linux kernel builds those files in Thumb2 mode. Hence U-Boot should build them in Thumb2 mode too when CONFIG_SYS_THUMB_BUILD is set. To build the files without warning, some assembler instructions had to be replaced with their UAL compliant variant (thanks Jeroen for this input). To build the file in Thumb2 mode the implicit-it=always option need to be set to generate Thumb2 compliant IT instructions where needed. We add this option to the general AFLAGS when building for Thumb2. Reviewed-by: Simon Glass <sjg@chromium.org> Tested-by: Simon Glass <sjg@chromium.org> Signed-off-by: Stefan Agner <stefan@agner.ch>
2014-12-18 17:10:33 +00:00
#define lspull lsl
#define lspush lsr
arm: Use optimized memcpy and memset from linux Using optimized versions of memset and memcpy from linux brings a quite noticeable speed (x2 or better) improvement for these two functions. Here are some numbers for test done with jadecpu | HEAD(1)| HEAD(1)| HEAD(2)| HEAD(2)| | | +patch | | +patch | ---------------------------+--------+--------+--------+--------+ Reset to prompt | 438ms | 330ms | 228ms | 120ms | | | | | | TFTP a 3MB img | 4782ms | 3428ms | 3245ms | 2820ms | | | | | | FATLOAD USB a 3MB img* | 8515ms | 8510ms | ------ | ------ | | | | | | BOOTM LZO img in RAM | 3473ms | 3168ms | 592ms | 592ms | where CRC is | 615ms | 615ms | 54ms | 54ms | uncompress | 2460ms | 2462ms | 450ms | 451ms | final boot_elf | 376ms | 68ms | 65ms | 65ms | | | | | | BOOTM LZO img in FLASH | 3207ms | 2902ms | 1050ms | 1050ms | where CRC is | 600ms | 600ms | 135ms | 135ms | uncompress | 2209ms | 2211ms | 828ms | 828ms | | | | | | Copy 1.4MB from NOR to RAM | 134ms | 72ms | 120ms | 70ms | (1) No dcache (2) dcache enabled in board_init *Does not work when dcache is on Size impact: C version: text data bss dec hex filename 202862 18912 266456 488230 77326 u-boot ASM version: text data bss dec hex filename 203798 18912 266288 488998 77626 u-boot 222712 u-boot.bin Signed-off-by: Matthias Weisser <weisserm@arcor.de>
2011-03-10 21:36:32 +00:00
#define get_byte_0 lsr #24
#define get_byte_1 lsr #16
#define get_byte_2 lsr #8
#define get_byte_3 lsl #0
#define put_byte_0 lsl #24
#define put_byte_1 lsl #16
#define put_byte_2 lsl #8
#define put_byte_3 lsl #0
#endif
/*
* Data preload for architectures that support it
*/
#if defined(__ARM_ARCH_5E__) || defined(__ARM_ARCH_5TE__) || \
defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || \
defined(__ARM_ARCH_6T2__) || defined(__ARM_ARCH_6Z__) || \
defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_7A__) || \
defined(__ARM_ARCH_7R__)
#define PLD(code...) code
#else
#define PLD(code...)
#endif
arm: build arch memset/memcpy in Thumb2 mode Resynchronize memcpy/memset with kernel 3.17 and build them in Thumb2 mode (unified syntax). Those assembler files can be built and linked in ARM mode too, however when calling them from Thumb2 built code, the stack got corrupted and the copy did not succeed (the exact details have not been traced back). However, the Linux kernel builds those files in Thumb2 mode. Hence U-Boot should build them in Thumb2 mode too when CONFIG_SYS_THUMB_BUILD is set. To build the files without warning, some assembler instructions had to be replaced with their UAL compliant variant (thanks Jeroen for this input). To build the file in Thumb2 mode the implicit-it=always option need to be set to generate Thumb2 compliant IT instructions where needed. We add this option to the general AFLAGS when building for Thumb2. Reviewed-by: Simon Glass <sjg@chromium.org> Tested-by: Simon Glass <sjg@chromium.org> Signed-off-by: Stefan Agner <stefan@agner.ch>
2014-12-18 17:10:33 +00:00
.irp c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo
.macro ret\c, reg
#if defined(__ARM_ARCH_5E__) || defined(__ARM_ARCH_5TE__)
mov\c pc, \reg
#else
.ifeqs "\reg", "lr"
bx\c \reg
.else
mov\c pc, \reg
.endif
#endif
.endm
.endr
arm: Use optimized memcpy and memset from linux Using optimized versions of memset and memcpy from linux brings a quite noticeable speed (x2 or better) improvement for these two functions. Here are some numbers for test done with jadecpu | HEAD(1)| HEAD(1)| HEAD(2)| HEAD(2)| | | +patch | | +patch | ---------------------------+--------+--------+--------+--------+ Reset to prompt | 438ms | 330ms | 228ms | 120ms | | | | | | TFTP a 3MB img | 4782ms | 3428ms | 3245ms | 2820ms | | | | | | FATLOAD USB a 3MB img* | 8515ms | 8510ms | ------ | ------ | | | | | | BOOTM LZO img in RAM | 3473ms | 3168ms | 592ms | 592ms | where CRC is | 615ms | 615ms | 54ms | 54ms | uncompress | 2460ms | 2462ms | 450ms | 451ms | final boot_elf | 376ms | 68ms | 65ms | 65ms | | | | | | BOOTM LZO img in FLASH | 3207ms | 2902ms | 1050ms | 1050ms | where CRC is | 600ms | 600ms | 135ms | 135ms | uncompress | 2209ms | 2211ms | 828ms | 828ms | | | | | | Copy 1.4MB from NOR to RAM | 134ms | 72ms | 120ms | 70ms | (1) No dcache (2) dcache enabled in board_init *Does not work when dcache is on Size impact: C version: text data bss dec hex filename 202862 18912 266456 488230 77326 u-boot ASM version: text data bss dec hex filename 203798 18912 266288 488998 77626 u-boot 222712 u-boot.bin Signed-off-by: Matthias Weisser <weisserm@arcor.de>
2011-03-10 21:36:32 +00:00
/*
arm: build arch memset/memcpy in Thumb2 mode Resynchronize memcpy/memset with kernel 3.17 and build them in Thumb2 mode (unified syntax). Those assembler files can be built and linked in ARM mode too, however when calling them from Thumb2 built code, the stack got corrupted and the copy did not succeed (the exact details have not been traced back). However, the Linux kernel builds those files in Thumb2 mode. Hence U-Boot should build them in Thumb2 mode too when CONFIG_SYS_THUMB_BUILD is set. To build the files without warning, some assembler instructions had to be replaced with their UAL compliant variant (thanks Jeroen for this input). To build the file in Thumb2 mode the implicit-it=always option need to be set to generate Thumb2 compliant IT instructions where needed. We add this option to the general AFLAGS when building for Thumb2. Reviewed-by: Simon Glass <sjg@chromium.org> Tested-by: Simon Glass <sjg@chromium.org> Signed-off-by: Stefan Agner <stefan@agner.ch>
2014-12-18 17:10:33 +00:00
* Cache aligned, used for optimized memcpy/memset
* In the kernel this is only enabled for Feroceon CPU's...
* We disable it especially for Thumb builds since those instructions
* are not made in a Thumb ready way...
arm: Use optimized memcpy and memset from linux Using optimized versions of memset and memcpy from linux brings a quite noticeable speed (x2 or better) improvement for these two functions. Here are some numbers for test done with jadecpu | HEAD(1)| HEAD(1)| HEAD(2)| HEAD(2)| | | +patch | | +patch | ---------------------------+--------+--------+--------+--------+ Reset to prompt | 438ms | 330ms | 228ms | 120ms | | | | | | TFTP a 3MB img | 4782ms | 3428ms | 3245ms | 2820ms | | | | | | FATLOAD USB a 3MB img* | 8515ms | 8510ms | ------ | ------ | | | | | | BOOTM LZO img in RAM | 3473ms | 3168ms | 592ms | 592ms | where CRC is | 615ms | 615ms | 54ms | 54ms | uncompress | 2460ms | 2462ms | 450ms | 451ms | final boot_elf | 376ms | 68ms | 65ms | 65ms | | | | | | BOOTM LZO img in FLASH | 3207ms | 2902ms | 1050ms | 1050ms | where CRC is | 600ms | 600ms | 135ms | 135ms | uncompress | 2209ms | 2211ms | 828ms | 828ms | | | | | | Copy 1.4MB from NOR to RAM | 134ms | 72ms | 120ms | 70ms | (1) No dcache (2) dcache enabled in board_init *Does not work when dcache is on Size impact: C version: text data bss dec hex filename 202862 18912 266456 488230 77326 u-boot ASM version: text data bss dec hex filename 203798 18912 266288 488998 77626 u-boot 222712 u-boot.bin Signed-off-by: Matthias Weisser <weisserm@arcor.de>
2011-03-10 21:36:32 +00:00
*/
arm: build arch memset/memcpy in Thumb2 mode Resynchronize memcpy/memset with kernel 3.17 and build them in Thumb2 mode (unified syntax). Those assembler files can be built and linked in ARM mode too, however when calling them from Thumb2 built code, the stack got corrupted and the copy did not succeed (the exact details have not been traced back). However, the Linux kernel builds those files in Thumb2 mode. Hence U-Boot should build them in Thumb2 mode too when CONFIG_SYS_THUMB_BUILD is set. To build the files without warning, some assembler instructions had to be replaced with their UAL compliant variant (thanks Jeroen for this input). To build the file in Thumb2 mode the implicit-it=always option need to be set to generate Thumb2 compliant IT instructions where needed. We add this option to the general AFLAGS when building for Thumb2. Reviewed-by: Simon Glass <sjg@chromium.org> Tested-by: Simon Glass <sjg@chromium.org> Signed-off-by: Stefan Agner <stefan@agner.ch>
2014-12-18 17:10:33 +00:00
#ifdef CONFIG_SYS_THUMB_BUILD
#define CALGN(code...)
#else
arm: Use optimized memcpy and memset from linux Using optimized versions of memset and memcpy from linux brings a quite noticeable speed (x2 or better) improvement for these two functions. Here are some numbers for test done with jadecpu | HEAD(1)| HEAD(1)| HEAD(2)| HEAD(2)| | | +patch | | +patch | ---------------------------+--------+--------+--------+--------+ Reset to prompt | 438ms | 330ms | 228ms | 120ms | | | | | | TFTP a 3MB img | 4782ms | 3428ms | 3245ms | 2820ms | | | | | | FATLOAD USB a 3MB img* | 8515ms | 8510ms | ------ | ------ | | | | | | BOOTM LZO img in RAM | 3473ms | 3168ms | 592ms | 592ms | where CRC is | 615ms | 615ms | 54ms | 54ms | uncompress | 2460ms | 2462ms | 450ms | 451ms | final boot_elf | 376ms | 68ms | 65ms | 65ms | | | | | | BOOTM LZO img in FLASH | 3207ms | 2902ms | 1050ms | 1050ms | where CRC is | 600ms | 600ms | 135ms | 135ms | uncompress | 2209ms | 2211ms | 828ms | 828ms | | | | | | Copy 1.4MB from NOR to RAM | 134ms | 72ms | 120ms | 70ms | (1) No dcache (2) dcache enabled in board_init *Does not work when dcache is on Size impact: C version: text data bss dec hex filename 202862 18912 266456 488230 77326 u-boot ASM version: text data bss dec hex filename 203798 18912 266288 488998 77626 u-boot 222712 u-boot.bin Signed-off-by: Matthias Weisser <weisserm@arcor.de>
2011-03-10 21:36:32 +00:00
#define CALGN(code...) code
arm: build arch memset/memcpy in Thumb2 mode Resynchronize memcpy/memset with kernel 3.17 and build them in Thumb2 mode (unified syntax). Those assembler files can be built and linked in ARM mode too, however when calling them from Thumb2 built code, the stack got corrupted and the copy did not succeed (the exact details have not been traced back). However, the Linux kernel builds those files in Thumb2 mode. Hence U-Boot should build them in Thumb2 mode too when CONFIG_SYS_THUMB_BUILD is set. To build the files without warning, some assembler instructions had to be replaced with their UAL compliant variant (thanks Jeroen for this input). To build the file in Thumb2 mode the implicit-it=always option need to be set to generate Thumb2 compliant IT instructions where needed. We add this option to the general AFLAGS when building for Thumb2. Reviewed-by: Simon Glass <sjg@chromium.org> Tested-by: Simon Glass <sjg@chromium.org> Signed-off-by: Stefan Agner <stefan@agner.ch>
2014-12-18 17:10:33 +00:00
#endif
Reference in a new issue Copy permalink