From: Ralf Baechle <ralf@linux-mips.org>
Date: Tue, 29 Sep 2015 10:19:48 +0000 (+0200)
Subject: MIPS: Use ARCH_USE_BUILTIN_BSWAP.
X-Git-Tag: v4.4-rc1~6^2~107
X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=1ee3630a3e57f38f688a6f0a5f9edbd8a0d7201f;p=platform%2Fkernel%2Flinux-exynos.git

MIPS: Use ARCH_USE_BUILTIN_BSWAP.

ARCH_USE_BUILTIN_BSWAP will use __builtin_bswap16(), __builtin_bswap32()
and __builtin_bswap64() where available.  This allows better instruction
scheduling.  On pre-R2 processors it will result in 32 bit and 64 bit
swapping being performed in a call to a __bswapsi2() rsp. __bswapdi2()
functions, so we add these, too.

For a 4.2 kernel with GCC 4.9 this yields the following kernel sizes:

   text    data     bss     dec     hex filename
3996071  155804   88992 4240867  40b5e3 vmlinux         ip22 baseline
3985687  159900   88992 4234579  409d53 vmlinux         ip22 + bswap patch
6913157  378552  251024 7542733  7317cd vmlinux         ip27 baseline
6878581  378552  251024 7508157  7290bd vmlinux         ip27 + bswap patch
5773777  268752  187424 6229953  5f0fc1 vmlinux         malta baseline
5773401  268752  187424 6229577  5f0e49 vmlinux         malta + bswap patch

Presumably the code size improvments yield better cache hit rate thus
better performance compensating for the extra function call but this
will still need to be benchmarked.

Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index e3aa5b0..c08e701 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -5,6 +5,7 @@ config MIPS
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select ARCH_USE_CMPXCHG_LOCKREF if 64BIT
+	select ARCH_USE_BUILTIN_BSWAP
 	select HAVE_CONTEXT_TRACKING
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_IDE
diff --git a/arch/mips/lib/Makefile b/arch/mips/lib/Makefile
index 1e9e900..0344e57 100644
--- a/arch/mips/lib/Makefile
+++ b/arch/mips/lib/Makefile
@@ -15,4 +15,4 @@ obj-$(CONFIG_CPU_R3000)		+= r3k_dump_tlb.o
 obj-$(CONFIG_CPU_TX39XX)	+= r3k_dump_tlb.o
 
 # libgcc-style stuff needed in the kernel
-obj-y += ashldi3.o ashrdi3.o cmpdi2.o lshrdi3.o ucmpdi2.o
+obj-y += ashldi3.o ashrdi3.o bswapsi.o bswapdi.o cmpdi2.o lshrdi3.o ucmpdi2.o
diff --git a/arch/mips/lib/bswapdi.c b/arch/mips/lib/bswapdi.c
new file mode 100644
index 0000000..77e5f9c1
--- /dev/null
+++ b/arch/mips/lib/bswapdi.c
@@ -0,0 +1,15 @@
+#include <linux/module.h>
+
+unsigned long long __bswapdi2(unsigned long long u)
+{
+	return (((u) & 0xff00000000000000ull) >> 56) |
+	       (((u) & 0x00ff000000000000ull) >> 40) |
+	       (((u) & 0x0000ff0000000000ull) >> 24) |
+	       (((u) & 0x000000ff00000000ull) >>  8) |
+	       (((u) & 0x00000000ff000000ull) <<  8) |
+	       (((u) & 0x0000000000ff0000ull) << 24) |
+	       (((u) & 0x000000000000ff00ull) << 40) |
+	       (((u) & 0x00000000000000ffull) << 56);
+}
+
+EXPORT_SYMBOL(__bswapdi2);
diff --git a/arch/mips/lib/bswapsi.c b/arch/mips/lib/bswapsi.c
new file mode 100644
index 0000000..2b302ff
--- /dev/null
+++ b/arch/mips/lib/bswapsi.c
@@ -0,0 +1,11 @@
+#include <linux/module.h>
+
+unsigned int __bswapsi2(unsigned int u)
+{
+	return (((u) & 0xff000000) >> 24) |
+	       (((u) & 0x00ff0000) >>  8) |
+	       (((u) & 0x0000ff00) <<  8) |
+	       (((u) & 0x000000ff) << 24);
+}
+
+EXPORT_SYMBOL(__bswapsi2);