Re: [U-Boot] [PATCH v3] arm: build arch memset/memcpy in Thumb2 mode
Hello Stefan, On Mon, 05 Jan 2015 23:21:41 +0100, Stefan Agner ste...@agner.ch wrote: Albert, I guess it is too late for that now. Thought it would make it into 2015.01, since your last comment in v2 suggested that you would treat it as bugfix... If Tom's OK, I or he can take it. Amicalement, -- Albert. ___ U-Boot mailing list U-Boot@lists.denx.de http://lists.denx.de/mailman/listinfo/u-boot
Re: [U-Boot] [PATCH v3] arm: build arch memset/memcpy in Thumb2 mode
Albert, I guess it is too late for that now. Thought it would make it into 2015.01, since your last comment in v2 suggested that you would treat it as bugfix... -- Stefan On 2014-12-18 18:10, Stefan Agner wrote: 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 s...@chromium.org Tested-by: Simon Glass s...@chromium.org Signed-off-by: Stefan Agner ste...@agner.ch --- arch/arm/config.mk | 4 +- arch/arm/include/asm/assembler.h | 33 ++-- arch/arm/lib/memcpy.S| 80 +++- arch/arm/lib/memset.S| 112 --- 4 files changed, 142 insertions(+), 87 deletions(-) diff --git a/arch/arm/config.mk b/arch/arm/config.mk index f0eafd6..9a4c270 100644 --- a/arch/arm/config.mk +++ b/arch/arm/config.mk @@ -26,7 +26,9 @@ PLATFORM_CPPFLAGS += -D__ARM__ # Choose between ARM/Thumb instruction sets ifeq ($(CONFIG_SYS_THUMB_BUILD),y) -PF_CPPFLAGS_ARM := $(call cc-option, -mthumb -mthumb-interwork,\ +AFLAGS_IMPLICIT_IT := $(call as-option,-Wa$(comma)-mimplicit-it=always) +PF_CPPFLAGS_ARM := $(AFLAGS_IMPLICIT_IT) \ + $(call cc-option, -mthumb -mthumb-interwork,\ $(call cc-option,-marm,)\ $(call cc-option,-mno-thumb-interwork,)\ ) diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index 5e4789b..11b80fb 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -14,12 +14,14 @@ * assembler source. */ +#include config.h + /* * Endian independent macros for shifting bytes within registers. */ #ifndef __ARMEB__ -#define pull lsr -#define push lsl +#define lspull lsr +#define lspush lsl #define get_byte_0 lsl #0 #define get_byte_1 lsr #8 #define get_byte_2 lsr #16 @@ -29,8 +31,8 @@ #define put_byte_2 lsl #16 #define put_byte_3 lsl #24 #else -#define pull lsl -#define push lsr +#define lspull lsl +#define lspush lsr #define get_byte_0 lsr #24 #define get_byte_1 lsr #16 #define get_byte_2 lsr #8 @@ -54,7 +56,28 @@ #define PLD(code...) #endif + .irpc,,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 + /* - * Cache alligned + * 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... */ +#ifdef CONFIG_SYS_THUMB_BUILD +#define CALGN(code...) +#else #define CALGN(code...) code +#endif diff --git a/arch/arm/lib/memcpy.S b/arch/arm/lib/memcpy.S index f655256..eeaf003 100644 --- a/arch/arm/lib/memcpy.S +++ b/arch/arm/lib/memcpy.S @@ -10,9 +10,14 @@ * published by the Free Software Foundation. */ +#include linux/linkage.h #include asm/assembler.h +#ifdef CONFIG_SYS_THUMB_BUILD +#define W(instr) instr.w +#else #define W(instr) instr +#endif #define LDR1W_SHIFT 0 #define STR1W_SHIFT 0 @@ -30,7 +35,7 @@ .endm .macro ldr1b ptr reg cond=al abort - ldr\cond\()b \reg, [\ptr], #1 + ldrb\cond\() \reg, [\ptr], #1 .endm .macro str1w ptr reg abort @@ -42,7 +47,7 @@ .endm .macro str1b ptr reg cond=al abort - str\cond\()b \reg, [\ptr], #1 + strb\cond\() \reg, [\ptr], #1 .endm .macro enter reg1 reg2 @@ -56,10 +61,12 @@ .text /* Prototype: void *memcpy(void *dest, const void *src, size_t n); */ - -.globl memcpy -memcpy: - + .syntax unified +#ifdef CONFIG_SYS_THUMB_BUILD + .thumb + .thumb_func +#endif +ENTRY(memcpy) cmp r0, r1 moveq pc, lr @@ -79,7 +86,7 @@ memcpy: CALGN( ands
[U-Boot] [PATCH v3] 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 s...@chromium.org Tested-by: Simon Glass s...@chromium.org Signed-off-by: Stefan Agner ste...@agner.ch --- arch/arm/config.mk | 4 +- arch/arm/include/asm/assembler.h | 33 ++-- arch/arm/lib/memcpy.S| 80 +++- arch/arm/lib/memset.S| 112 --- 4 files changed, 142 insertions(+), 87 deletions(-) diff --git a/arch/arm/config.mk b/arch/arm/config.mk index f0eafd6..9a4c270 100644 --- a/arch/arm/config.mk +++ b/arch/arm/config.mk @@ -26,7 +26,9 @@ PLATFORM_CPPFLAGS += -D__ARM__ # Choose between ARM/Thumb instruction sets ifeq ($(CONFIG_SYS_THUMB_BUILD),y) -PF_CPPFLAGS_ARM := $(call cc-option, -mthumb -mthumb-interwork,\ +AFLAGS_IMPLICIT_IT := $(call as-option,-Wa$(comma)-mimplicit-it=always) +PF_CPPFLAGS_ARM:= $(AFLAGS_IMPLICIT_IT) \ + $(call cc-option, -mthumb -mthumb-interwork,\ $(call cc-option,-marm,)\ $(call cc-option,-mno-thumb-interwork,)\ ) diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index 5e4789b..11b80fb 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -14,12 +14,14 @@ * assembler source. */ +#include config.h + /* * Endian independent macros for shifting bytes within registers. */ #ifndef __ARMEB__ -#define pull lsr -#define push lsl +#define lspull lsr +#define lspush lsl #define get_byte_0 lsl #0 #define get_byte_1 lsr #8 #define get_byte_2 lsr #16 @@ -29,8 +31,8 @@ #define put_byte_2 lsl #16 #define put_byte_3 lsl #24 #else -#define pull lsl -#define push lsr +#define lspull lsl +#define lspush lsr #define get_byte_0 lsr #24 #define get_byte_1 lsr #16 #define get_byte_2 lsr #8 @@ -54,7 +56,28 @@ #define PLD(code...) #endif + .irpc,,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 + /* - * Cache alligned + * 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... */ +#ifdef CONFIG_SYS_THUMB_BUILD +#define CALGN(code...) +#else #define CALGN(code...) code +#endif diff --git a/arch/arm/lib/memcpy.S b/arch/arm/lib/memcpy.S index f655256..eeaf003 100644 --- a/arch/arm/lib/memcpy.S +++ b/arch/arm/lib/memcpy.S @@ -10,9 +10,14 @@ * published by the Free Software Foundation. */ +#include linux/linkage.h #include asm/assembler.h +#ifdef CONFIG_SYS_THUMB_BUILD +#define W(instr) instr.w +#else #define W(instr) instr +#endif #define LDR1W_SHIFT0 #define STR1W_SHIFT0 @@ -30,7 +35,7 @@ .endm .macro ldr1b ptr reg cond=al abort - ldr\cond\()b \reg, [\ptr], #1 + ldrb\cond\() \reg, [\ptr], #1 .endm .macro str1w ptr reg abort @@ -42,7 +47,7 @@ .endm .macro str1b ptr reg cond=al abort - str\cond\()b \reg, [\ptr], #1 + strb\cond\() \reg, [\ptr], #1 .endm .macro enter reg1 reg2 @@ -56,10 +61,12 @@ .text /* Prototype: void *memcpy(void *dest, const void *src, size_t n); */ - -.globl memcpy -memcpy: - + .syntax unified +#ifdef CONFIG_SYS_THUMB_BUILD + .thumb + .thumb_func +#endif +ENTRY(memcpy) cmp r0, r1 moveq pc, lr @@ -79,7 +86,7 @@ memcpy: CALGN( andsip, r0, #31 ) CALGN( rsb r3, ip, #32 ) - CALGN( sbcnes r4, r3, r2 ) @ C is always set here + CALGN( sbcsne r4, r3, r2 ) @ C is always set here CALGN( bcs 2f ) CALGN( adr r4,