This patch enables the use of the optimized memset(), memmove() & memcpy() versions recently added on ARM64.
Signed-off-by: Stefan Roese sr@denx.de
---
Changes in v5: - memmove is now auto-selected (or deselected) with the memcpy Kconfig selection as it's entry is the same as memcpy for ARM64
Changes in v3: - Add memmove as well
arch/arm/Kconfig | 37 +++++++++++++++++++++++++++++------ arch/arm/include/asm/string.h | 4 ++++ 2 files changed, 35 insertions(+), 6 deletions(-)
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 55a9c3acef8d..0cf29c702dde 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -457,7 +457,6 @@ config ARM_CORTEX_CPU_IS_UP config USE_ARCH_MEMCPY bool "Use an assembly optimized implementation of memcpy" default y - depends on !ARM64 help Enable the generation of an optimized version of memcpy. Such an implementation may be faster under some conditions @@ -466,7 +465,7 @@ config USE_ARCH_MEMCPY config SPL_USE_ARCH_MEMCPY bool "Use an assembly optimized implementation of memcpy for SPL" default y if USE_ARCH_MEMCPY - depends on !ARM64 && SPL + depends on SPL help Enable the generation of an optimized version of memcpy. Such an implementation may be faster under some conditions @@ -475,16 +474,42 @@ config SPL_USE_ARCH_MEMCPY config TPL_USE_ARCH_MEMCPY bool "Use an assembly optimized implementation of memcpy for TPL" default y if USE_ARCH_MEMCPY - depends on !ARM64 && TPL + depends on TPL help Enable the generation of an optimized version of memcpy. Such an implementation may be faster under some conditions but may increase the binary size.
+config USE_ARCH_MEMMOVE + bool "Use an assembly optimized implementation of memmove" if !ARM64 + default USE_ARCH_MEMCPY if ARM64 + depends on ARM64 + help + Enable the generation of an optimized version of memmove. + Such an implementation may be faster under some conditions + but may increase the binary size. + +config SPL_USE_ARCH_MEMMOVE + bool "Use an assembly optimized implementation of memmove for SPL" if !ARM64 + default SPL_USE_ARCH_MEMCPY if ARM64 + depends on SPL && ARM64 + help + Enable the generation of an optimized version of memmove. + Such an implementation may be faster under some conditions + but may increase the binary size. + +config TPL_USE_ARCH_MEMMOVE + bool "Use an assembly optimized implementation of memmove for TPL" if !ARM64 + default TPL_USE_ARCH_MEMCPY if ARM64 + depends on TPL && ARM64 + help + Enable the generation of an optimized version of memmove. + Such an implementation may be faster under some conditions + but may increase the binary size. + config USE_ARCH_MEMSET bool "Use an assembly optimized implementation of memset" default y - depends on !ARM64 help Enable the generation of an optimized version of memset. Such an implementation may be faster under some conditions @@ -493,7 +518,7 @@ config USE_ARCH_MEMSET config SPL_USE_ARCH_MEMSET bool "Use an assembly optimized implementation of memset for SPL" default y if USE_ARCH_MEMSET - depends on !ARM64 && SPL + depends on SPL help Enable the generation of an optimized version of memset. Such an implementation may be faster under some conditions @@ -502,7 +527,7 @@ config SPL_USE_ARCH_MEMSET config TPL_USE_ARCH_MEMSET bool "Use an assembly optimized implementation of memset for TPL" default y if USE_ARCH_MEMSET - depends on !ARM64 && TPL + depends on TPL help Enable the generation of an optimized version of memset. Such an implementation may be faster under some conditions diff --git a/arch/arm/include/asm/string.h b/arch/arm/include/asm/string.h index 11eaa34fab8c..ead3f2c35643 100644 --- a/arch/arm/include/asm/string.h +++ b/arch/arm/include/asm/string.h @@ -19,7 +19,11 @@ extern char * strchr(const char * s, int c); #endif extern void * memcpy(void *, const void *, __kernel_size_t);
+#if CONFIG_IS_ENABLED(USE_ARCH_MEMMOVE) +#define __HAVE_ARCH_MEMMOVE +#else #undef __HAVE_ARCH_MEMMOVE +#endif extern void * memmove(void *, const void *, __kernel_size_t);
#undef __HAVE_ARCH_MEMCHR