ARM: 7877/1: use built-in byte swap function

Enable the compiler intrinsic for byte swapping on arch ARM. This
allows the compiler to detect and be able to optimize out byte
swappings, and has a very modest benefit on vmlinux size (Linaro gcc
4.8):

text data bss dec hex filename
2840310 123932 61960 3026202 2e2d1a vmlinux-lart #orig
2840152 123932 61960 3026044 2e2c7c vmlinux-lart #builtin-bswap

6473120 314840 5616016 12403976 bd4508 vmlinux-mxs #orig
6472586 314848 5616016 12403450 bd42fa vmlinux-mxs #builtin-bswap

7419872 318372 379556 8117800 7bde28 vmlinux-imx_v6_v7 #orig
7419170 318364 379556 8117090 7bdb62 vmlinux-imx_v6_v7 #builtin-bswap
Signed-off-by: Kim Phillips <kim.phillips@freescale.com>
Reviewed-by: Nicolas Pitre <nico@linaro.org>
Acked-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

arch/arm/Kconfig

@@ -6,6 +6,7 @@ config ARM
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAVE_CUSTOM_GPIO_H
 	select ARCH_MIGHT_HAVE_PC_PARPORT
+	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select BUILDTIME_EXTABLE_SORT if MMU

arch/arm/boot/compressed/Makefile

@@ -108,12 +108,12 @@ endif
 
 targets       := vmlinux vmlinux.lds \
 		 piggy.$(suffix_y) piggy.$(suffix_y).o \
-		 lib1funcs.o lib1funcs.S ashldi3.o ashldi3.S \
-		 font.o font.c head.o misc.o $(OBJS)
+		 lib1funcs.o lib1funcs.S ashldi3.o ashldi3.S bswapsdi2.o \
+		 bswapsdi2.S font.o font.c head.o misc.o $(OBJS)
 
 # Make sure files are removed during clean
 extra-y       += piggy.gzip piggy.lzo piggy.lzma piggy.xzkern piggy.lz4 \
-		 lib1funcs.S ashldi3.S $(libfdt) $(libfdt_hdrs) \
+		 lib1funcs.S ashldi3.S bswapsdi2.S $(libfdt) $(libfdt_hdrs) \
 		 hyp-stub.S
 
 ifeq ($(CONFIG_FUNCTION_TRACER),y)
@@ -156,6 +156,12 @@ ashldi3 = $(obj)/ashldi3.o
 $(obj)/ashldi3.S: $(srctree)/arch/$(SRCARCH)/lib/ashldi3.S
 	$(call cmd,shipped)
 
+# For __bswapsi2, __bswapdi2
+bswapsdi2 = $(obj)/bswapsdi2.o
+
+$(obj)/bswapsdi2.S: $(srctree)/arch/$(SRCARCH)/lib/bswapsdi2.S
+	$(call cmd,shipped)
+
 # We need to prevent any GOTOFF relocs being used with references
 # to symbols in the .bss section since we cannot relocate them
 # independently from the rest at run time.  This can be achieved by
@@ -177,7 +183,8 @@ if [ $(words $(ZRELADDR)) -gt 1 -a "$(CONFIG_AUTO_ZRELADDR)" = "" ]; then \
 fi
 
 $(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/$(HEAD) $(obj)/piggy.$(suffix_y).o \
-		$(addprefix $(obj)/, $(OBJS)) $(lib1funcs) $(ashldi3) FORCE
+		$(addprefix $(obj)/, $(OBJS)) $(lib1funcs) $(ashldi3) \
+		$(bswapsdi2) FORCE
 	@$(check_for_multiple_zreladdr)
 	$(call if_changed,ld)
 	@$(check_for_bad_syms)

arch/arm/kernel/armksyms.c

@@ -35,6 +35,8 @@ extern void __ucmpdi2(void);
 extern void __udivsi3(void);
 extern void __umodsi3(void);
 extern void __do_div64(void);
+extern void __bswapsi2(void);
+extern void __bswapdi2(void);
 
 extern void __aeabi_idiv(void);
 extern void __aeabi_idivmod(void);
@@ -114,6 +116,8 @@ EXPORT_SYMBOL(__ucmpdi2);
 EXPORT_SYMBOL(__udivsi3);
 EXPORT_SYMBOL(__umodsi3);
 EXPORT_SYMBOL(__do_div64);
+EXPORT_SYMBOL(__bswapsi2);
+EXPORT_SYMBOL(__bswapdi2);
 
 #ifdef CONFIG_AEABI
 EXPORT_SYMBOL(__aeabi_idiv);

arch/arm/lib/Makefile

@@ -13,7 +13,7 @@ lib-y		:= backtrace.o changebit.o csumipv6.o csumpartial.o   \
 		   ashldi3.o ashrdi3.o lshrdi3.o muldi3.o             \
 		   ucmpdi2.o lib1funcs.o div64.o                      \
 		   io-readsb.o io-writesb.o io-readsl.o io-writesl.o  \
-		   call_with_stack.o
+		   call_with_stack.o bswapsdi2.o
 
 mmu-y	:= clear_user.o copy_page.o getuser.o putuser.o
 

arch/arm/lib/bswapsdi2.S

+#include <linux/linkage.h>
+
+#if __LINUX_ARM_ARCH__ >= 6
+ENTRY(__bswapsi2)
+	rev r0, r0
+	bx lr
+ENDPROC(__bswapsi2)
+
+ENTRY(__bswapdi2)
+	rev r3, r0
+	rev r0, r1
+	mov r1, r3
+	bx lr
+ENDPROC(__bswapdi2)
+#else
+ENTRY(__bswapsi2)
+	eor r3, r0, r0, ror #16
+	mov r3, r3, lsr #8
+	bic r3, r3, #0xff00
+	eor r0, r3, r0, ror #8
+	mov pc, lr
+ENDPROC(__bswapsi2)
+
+ENTRY(__bswapdi2)
+	mov ip, r1
+	eor r3, ip, ip, ror #16
+	eor r1, r0, r0, ror #16
+	mov r1, r1, lsr #8
+	mov r3, r3, lsr #8
+	bic r3, r3, #0xff00
+	bic r1, r1, #0xff00
+	eor r1, r1, r0, ror #8
+	eor r0, r3, ip, ror #8
+	mov pc, lr
+ENDPROC(__bswapdi2)
+#endif