[PATCH] arm: use built-in byte swap function

From: Kim Phillips
Date: Tue Feb 19 2013 - 18:16:11 EST

Next message: Paul Gortmaker: "Re: [patch 1/1] early_printk: Consolidate random copies of identical code"
Previous message: Rusty Russell: "[PULL] modules-next"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

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 tiny benefit on vmlinux size (Linaro gcc 4.7.3):

text data bss dec hex filename
2754100 121144 56520 2931764 2cbc34 vmlinux-lart #orig
2754050 121144 56520 2931714 2cbc02 vmlinux-lart #builtin-bswap
6282699 307852 5578076 12168627 b9adb3 vmlinux-mxs #orig
6282241 307832 5578076 12168149 b9abd5 vmlinux-mxs #builtin-bswap
7200193 364180 361748 7926121 78f169 vmlinux-imx_v6_v7 #orig
7199515 364188 361748 7925451 78eecb vmlinux-imx_v6_v7 #builtin-bswap

Signed-off-by: Kim Phillips <kim.phillips@xxxxxxxxxxxxx>
---
akin to: http://comments.gmane.org/gmane.linux.kernel.cross-arch/16016

based on linux-next-20130221.

changes from last diff:
- addressed Nicolas' comments
- updated commit text figures and reformatted as a patch

changes from diff before that:
- 1st asm version

changes from diff before that:
- enforce -O2 for bswapsdi2.o
- fix building out-of-source tree

changes from diff before that:
- implement custom __bswap[sd]i2 in arch/arm/lib/bswapsdi2.c

v5: re-work based on new gcc version test data:
- moved outside armv6 protection
- check for gcc 4.6+ demoted to gcc 4.5+ with:
!defined(CONFIG_CC_OPTIMIZE_FOR_SIZE)

v4:
- undo v2-2's addition of ARCH_DEFINES_BUILTIN_BSWAP per Boris
and David - object is to find arches that define _HAVE_BSWAP
and clean it up in the future: patch is much less intrusive. :)

v3:
- moved out of uapi swab.h into arch/arm/include/asm/swab.h
- moved ARCH_DEFINES_BUILTIN_BSWAP help text into commit message
- moved GCC_VERSION >= 40800 ifdef into GCC_VERSION >= 40600 block

v2:
- at91 and lpd270 builds fixed by limiting to ARMv6 and above
(i.e., ARM cores that have support for the 'rev' instruction).
Otherwise, the compiler emits calls to libgcc's __bswapsi2 on
these ARMv4/v5 builds (and arch ARM doesn't link with libgcc).
All ARM defconfigs now have the same build status as they did
without this patch (some are broken on linux-next).

- move ARM check from generic compiler.h to arch ARM's swab.h.
- pretty sure it should be limited to __KERNEL__ builds

- add new ARCH_DEFINES_BUILTIN_BSWAP (see Kconfig help).
- if set, generic compiler header does not set HAVE_BUILTIN_BSWAPxx
- not too sure about this having to be a new CONFIG_, but it's hard
to find a place for it given linux/compiler.h doesn't include any
arch-specific files.

- move new selects to end of CONFIG_ARM's Kconfig select list,
as is done in David Woodhouse's original patchseries for ppc/x86.

arch/arm/Kconfig | 1 +
arch/arm/boot/compressed/Makefile | 15 +++++++++++----
arch/arm/kernel/armksyms.c | 4 ++++
arch/arm/lib/Makefile | 2 +-
arch/arm/lib/bswapsdi2.S | 36 ++++++++++++++++++++++++++++++++++++
5 files changed, 53 insertions(+), 5 deletions(-)
create mode 100644 arch/arm/lib/bswapsdi2.S

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index dedf02b..e8a41d0 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -59,6 +59,7 @@ config ARM
select CLONE_BACKWARDS
select OLD_SIGSUSPEND3
select OLD_SIGACTION
+ select ARCH_USE_BUILTIN_BSWAP
help
The ARM series is a line of low-power-consumption RISC chip designs
licensed by ARM Ltd and targeted at embedded applications and
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index 5cad8a6..d9b5ee5 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/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 \
- lib1funcs.S ashldi3.S $(libfdt) $(libfdt_hdrs)
+ lib1funcs.S ashldi3.S bswapsdi2.S $(libfdt) $(libfdt_hdrs)

ifeq ($(CONFIG_FUNCTION_TRACER),y)
ORIG_CFLAGS := $(KBUILD_CFLAGS)
@@ -155,6 +155,12 @@ 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
@@ -176,7 +182,8 @@ 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)
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index 60d3b73..ba578f7 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/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);
diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index af72969..5383df7 100644
--- a/arch/arm/lib/Makefile
+++ b/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

diff --git a/arch/arm/lib/bswapsdi2.S b/arch/arm/lib/bswapsdi2.S
new file mode 100644
index 0000000..2ba43a0
--- /dev/null
+++ b/arch/arm/lib/bswapsdi2.S
@@ -0,0 +1,36 @@
+#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
--
1.8.1.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Next message: Paul Gortmaker: "Re: [patch 1/1] early_printk: Consolidate random copies of identical code"
Previous message: Rusty Russell: "[PULL] modules-next"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]