diff options
| author | David Woodhouse <David.Woodhouse@intel.com> | 2012-12-03 17:25:40 +0100 |
|---|---|---|
| committer | David Woodhouse <David.Woodhouse@intel.com> | 2012-12-06 02:22:31 +0100 |
| commit | cf66bb93e0f75e0a4ba1ec070692618fa028e994 (patch) | |
| tree | 0ae48658adb29f50bdd85a94cbb84670a234f441 /include | |
| parent | vfs: clear to the end of the buffer on partial buffer reads (diff) | |
| download | linux-cf66bb93e0f75e0a4ba1ec070692618fa028e994.tar.xz linux-cf66bb93e0f75e0a4ba1ec070692618fa028e994.zip | |
byteorder: allow arch to opt to use GCC intrinsics for byteswapping
Since GCC 4.4, there have been __builtin_bswap32() and __builtin_bswap16()
intrinsics. A __builtin_bswap16() came a little later (4.6 for PowerPC,
48 for other platforms).
By using these instead of the inline assembler that most architectures
have in their __arch_swabXX() macros, we let the compiler see what's
actually happening. The resulting code should be at least as good, and
much *better* in the cases where it can be combined with a nearby load
or store, using a load-and-byteswap or store-and-byteswap instruction
(e.g. lwbrx/stwbrx on PowerPC, movbe on Atom).
When GCC is sufficiently recent *and* the architecture opts in to using
the intrinsics by setting CONFIG_ARCH_USE_BUILTIN_BSWAP, they will be
used in preference to the __arch_swabXX() macros. An architecture which
does not set ARCH_USE_BUILTIN_BSWAP will continue to use its own
hand-crafted macros.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Acked-by: H. Peter Anvin <hpa@linux.intel.com>
Diffstat (limited to 'include')
| -rw-r--r-- | include/linux/compiler-gcc4.h | 10 | ||||
| -rw-r--r-- | include/linux/compiler-intel.h | 7 | ||||
| -rw-r--r-- | include/uapi/linux/swab.h | 12 |
3 files changed, 26 insertions, 3 deletions
diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h index 412bc6c2b023..dc16a858e77c 100644 --- a/include/linux/compiler-gcc4.h +++ b/include/linux/compiler-gcc4.h @@ -63,3 +63,13 @@ #define __compiletime_warning(message) __attribute__((warning(message))) #define __compiletime_error(message) __attribute__((error(message))) #endif + +#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP +#if __GNUC_MINOR__ >= 4 +#define __HAVE_BUILTIN_BSWAP32__ +#define __HAVE_BUILTIN_BSWAP64__ +#endif +#if __GNUC_MINOR__ >= 8 || (defined(__powerpc__) && __GNUC_MINOR__ >= 6) +#define __HAVE_BUILTIN_BSWAP16__ +#endif +#endif diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h index d8e636e5607d..973ce10c40b6 100644 --- a/include/linux/compiler-intel.h +++ b/include/linux/compiler-intel.h @@ -29,3 +29,10 @@ #endif #define uninitialized_var(x) x + +#ifndef __HAVE_BUILTIN_BSWAP16__ +/* icc has this, but it's called _bswap16 */ +#define __HAVE_BUILTIN_BSWAP16__ +#define __builtin_bswap16 _bswap16 +#endif + diff --git a/include/uapi/linux/swab.h b/include/uapi/linux/swab.h index e811474724c2..0e011eb91b5d 100644 --- a/include/uapi/linux/swab.h +++ b/include/uapi/linux/swab.h @@ -45,7 +45,9 @@ static inline __attribute_const__ __u16 __fswab16(__u16 val) { -#ifdef __arch_swab16 +#ifdef __HAVE_BUILTIN_BSWAP16__ + return __builtin_bswap16(val); +#elif defined (__arch_swab16) return __arch_swab16(val); #else return ___constant_swab16(val); @@ -54,7 +56,9 @@ static inline __attribute_const__ __u16 __fswab16(__u16 val) static inline __attribute_const__ __u32 __fswab32(__u32 val) { -#ifdef __arch_swab32 +#ifdef __HAVE_BUILTIN_BSWAP32__ + return __builtin_bswap32(val); +#elif defined(__arch_swab32) return __arch_swab32(val); #else return ___constant_swab32(val); @@ -63,7 +67,9 @@ static inline __attribute_const__ __u32 __fswab32(__u32 val) static inline __attribute_const__ __u64 __fswab64(__u64 val) { -#ifdef __arch_swab64 +#ifdef __HAVE_BUILTIN_BSWAP64__ + return __builtin_bswap64(val); +#elif defined (__arch_swab64) return __arch_swab64(val); #elif defined(__SWAB_64_THRU_32__) __u32 h = val >> 32; |