ARM: Default to using optimized memset and memcpy routines

We have long had available optimized versions of the memset and memcpy
functions that are borrowed from the Linux kernel.  We should use these
in normal conditions as the speed wins in many workflows outweigh the
relatively minor size increase.  However, we have a number of places
where we're simply too close to size limits in SPL and must be able to
make the size vs performance trade-off in those cases.

Cc: Philippe Reynes <tremyfr@yahoo.fr>
Cc: Eric Jarrige <eric.jarrige@armadeus.org>
Cc: Heiko Schocher <hs@denx.de>
Cc: Magnus Lilja <lilja.magnus@gmail.com>
Cc: Lokesh Vutla <lokeshvutla@ti.com>
Cc: Chander Kashyap <k.chander@samsung.com>
Cc: Akshay Saraswat <akshay.s@samsung.com>
Cc: Simon Glass <sjg@chromium.org>
Cc: Stefan Roese <sr@denx.de>
Signed-off-by: Tom Rini <trini@konsulko.com>
Acked-by: Stefan Roese <sr@denx.de>
Reviewed-by: Simon Glass <sjg@chromium.org>

arch/arm/Kconfig

@@ -128,7 +128,16 @@ config ENABLE_ARM_SOC_BOOT0_HOOK
 
 config USE_ARCH_MEMCPY
 	bool "Use an assembly optimized implementation of memcpy"
-	default y if CPU_V7
+	default y
+	depends on !ARM64
+	help
+	  Enable the generation of an optimized version of memcpy.
+	  Such implementation may be faster under some conditions
+	  but may increase the binary size.
+
+config SPL_USE_ARCH_MEMCPY
+	bool "Use an assembly optimized implementation of memcpy"
+	default y if USE_ARCH_MEMCPY
 	depends on !ARM64
 	help
 	  Enable the generation of an optimized version of memcpy.
@@ -137,7 +146,16 @@ config USE_ARCH_MEMCPY
 
 config USE_ARCH_MEMSET
 	bool "Use an assembly optimized implementation of memset"
-	default y if CPU_V7
+	default y
+	depends on !ARM64
+	help
+	  Enable the generation of an optimized version of memset.
+	  Such implementation may be faster under some conditions
+	  but may increase the binary size.
+
+config SPL_USE_ARCH_MEMSET
+	bool "Use an assembly optimized implementation of memset"
+	default y if USE_ARCH_MEMSET
 	depends on !ARM64
 	help
 	  Enable the generation of an optimized version of memset.

arch/arm/lib/Makefile

@@ -30,12 +30,12 @@ obj-$(CONFIG_CMD_BOOTI) += bootm.o
 obj-$(CONFIG_CMD_BOOTM) += bootm.o
 obj-$(CONFIG_CMD_BOOTZ) += bootm.o zimage.o
 obj-$(CONFIG_SYS_L2_PL310) += cache-pl310.o
-obj-$(CONFIG_USE_ARCH_MEMSET) += memset.o
-obj-$(CONFIG_USE_ARCH_MEMCPY) += memcpy.o
 else
 obj-$(CONFIG_SPL_FRAMEWORK) += spl.o
 obj-$(CONFIG_SPL_FRAMEWORK) += zimage.o
 endif
+obj-$(CONFIG_$(SPL_)USE_ARCH_MEMSET) += memset.o
+obj-$(CONFIG_$(SPL_)USE_ARCH_MEMCPY) += memcpy.o
 obj-$(CONFIG_SEMIHOSTING) += semihosting.o
 
 obj-y	+= sections.o

common/init/board_init.c

@@ -17,7 +17,7 @@ DECLARE_GLOBAL_DATA_PTR;
  */
 #if !defined(CONFIG_SPL_BUILD) || \
 		(defined(CONFIG_SPL_LIBGENERIC_SUPPORT) && \
-		!defined(CONFIG_USE_ARCH_MEMSET))
+		!defined(CONFIG_SPL_USE_ARCH_MEMCPY))
 #define _USE_MEMCPY
 #endif
 

configs/apf27_defconfig

 CONFIG_ARM=y
+# CONFIG_SPL_USE_ARCH_MEMCPY is not set
 CONFIG_TARGET_APF27=y
 CONFIG_SPL_NAND_SUPPORT=y
 CONFIG_SPL_SERIAL_SUPPORT=y

configs/axm_defconfig

 CONFIG_ARM=y
+# CONFIG_SPL_USE_ARCH_MEMCPY is not set
+# CONFIG_SPL_USE_ARCH_MEMSET is not set
 CONFIG_ARCH_AT91=y
 CONFIG_TARGET_TAURUS=y
 CONFIG_SPL_GPIO_SUPPORT=y

configs/corvus_defconfig

 CONFIG_ARM=y
+# CONFIG_SPL_USE_ARCH_MEMCPY is not set
+# CONFIG_SPL_USE_ARCH_MEMSET is not set
 CONFIG_ARCH_AT91=y
 CONFIG_TARGET_CORVUS=y
 CONFIG_SPL_GPIO_SUPPORT=y

configs/mx31pdk_defconfig

 CONFIG_ARM=y
+# CONFIG_SPL_USE_ARCH_MEMCPY is not set
+# CONFIG_SPL_USE_ARCH_MEMSET is not set
 CONFIG_TARGET_MX31PDK=y
 CONFIG_SPL_LIBGENERIC_SUPPORT=y
 CONFIG_SPL_NAND_SUPPORT=y

configs/omap4_sdp4430_defconfig

 CONFIG_ARM=y
+# CONFIG_SPL_USE_ARCH_MEMCPY is not set
+# CONFIG_SPL_USE_ARCH_MEMSET is not set
 CONFIG_OMAP44XX=y
 # CONFIG_SPL_I2C_SUPPORT is not set
 # CONFIG_SPL_NAND_SUPPORT is not set

configs/smartweb_defconfig

 CONFIG_ARM=y
+# CONFIG_SPL_USE_ARCH_MEMCPY is not set
+# CONFIG_SPL_USE_ARCH_MEMSET is not set
 CONFIG_ARCH_AT91=y
 CONFIG_TARGET_SMARTWEB=y
 CONFIG_SPL_GPIO_SUPPORT=y

configs/smdk5250_defconfig

 CONFIG_ARM=y
+# CONFIG_SPL_USE_ARCH_MEMCPY is not set
+# CONFIG_SPL_USE_ARCH_MEMSET is not set
 CONFIG_ARCH_EXYNOS=y
 CONFIG_ARCH_EXYNOS5=y
 CONFIG_TARGET_SMDK5250=y

configs/snow_defconfig

 CONFIG_ARM=y
+# CONFIG_SPL_USE_ARCH_MEMCPY is not set
+# CONFIG_SPL_USE_ARCH_MEMSET is not set
 CONFIG_ARCH_EXYNOS=y
 CONFIG_ARCH_EXYNOS5=y
 CONFIG_TARGET_SNOW=y

configs/spring_defconfig

 CONFIG_ARM=y
+# CONFIG_SPL_USE_ARCH_MEMCPY is not set
+# CONFIG_SPL_USE_ARCH_MEMSET is not set
 CONFIG_ARCH_EXYNOS=y
 CONFIG_ARCH_EXYNOS5=y
 CONFIG_TARGET_SPRING=y

configs/taurus_defconfig

 CONFIG_ARM=y
+# CONFIG_SPL_USE_ARCH_MEMCPY is not set
+# CONFIG_SPL_USE_ARCH_MEMSET is not set
 CONFIG_ARCH_AT91=y
 CONFIG_TARGET_TAURUS=y
 CONFIG_SPL_GPIO_SUPPORT=y

configs/x600_defconfig

 CONFIG_ARM=y
+# CONFIG_SPL_USE_ARCH_MEMCPY is not set
+# CONFIG_SPL_USE_ARCH_MEMSET is not set
 CONFIG_TARGET_X600=y
 CONFIG_SPL_LIBCOMMON_SUPPORT=y
 CONFIG_SPL_LIBGENERIC_SUPPORT=y

examples/api/Makefile

@@ -35,6 +35,9 @@ EXT_COBJ-y += lib/string.o
 EXT_COBJ-y += lib/time.o
 EXT_COBJ-y += lib/vsprintf.o
 EXT_SOBJ-$(CONFIG_PPC) += arch/powerpc/lib/ppcstring.o
+ifeq ($(ARCH),arm)
+EXT_SOBJ-$(CONFIG_USE_ARCH_MEMSET) += arch/arm/lib/memset.o
+endif
 
 # Create a list of object files to be compiled
 OBJS := $(OBJ-y) $(notdir $(EXT_COBJ-y) $(EXT_SOBJ-y))
@@ -60,5 +63,5 @@ $(addprefix $(obj)/,$(notdir $(EXT_COBJ-y))): $(obj)/%.o: lib/%.c FORCE
 	$(call if_changed_rule,cc_o_c)
 
 # Rule to build architecture-specific library assembly files
-$(addprefix $(obj)/,$(notdir $(EXT_SOBJ-y))): $(obj)/%.o: arch/powerpc/lib/%.S FORCE
+$(addprefix $(obj)/,$(notdir $(EXT_SOBJ-y))): $(obj)/%.o: arch/$(ARCH)/lib/%.S FORCE
 	$(call if_changed_dep,as_o_S)