diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2012-12-19 07:52:48 -0800 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-12-19 07:52:48 -0800 |
| commit | 7f2de8171ddf28fdb2ca7f9a683ee1207849f718 (patch) | |
| tree | d89da981ac762de3fd32e1c08ddc8041f3c37519 /include | |
| parent | 59771079c18c44e39106f0f30054025acafadb41 (diff) | |
| parent | cf66bb93e0f75e0a4ba1ec070692618fa028e994 (diff) | |
Merge tag 'byteswap-for-linus-20121219' of git://git.infradead.org/users/dwmw2/byteswap
Pull preparatory gcc intrisics bswap patch from David Woodhouse:
"This single patch is effectively a no-op for now. It enables
architectures to opt in to using GCC's __builtin_bswapXX() intrinsics
for byteswapping, and if we merge this now then the architecture
maintainers can enable it for their arch during the next cycle without
dependency issues.
It's worth making it a par-arch opt-in, because although in *theory*
the compiler should never do worse than hand-coded assembler (and of
course it also ought to do a lot better on platforms like Atom and
PowerPC which have load-and-swap or store-and-swap instructions), that
isn't always the case. See
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=46453
for example."
* tag 'byteswap-for-linus-20121219' of git://git.infradead.org/users/dwmw2/byteswap:
byteorder: allow arch to opt to use GCC intrinsics for byteswapping
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 412bc6c2b02..dc16a858e77 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 d8e636e5607..973ce10c40b 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 e811474724c..0e011eb91b5 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; |