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.

David Woodhouse committed 13 years ago

Commit cf66bb91 parent 27d7c2a4 files · +45 −3Browse files

Showing the changes to include/uapi (1 of 4 files). Show all

Unified · Split

include/uapi/linux/swab.h+9−3

@@ -45,7 +45,9 @@ · 44 unmodified lines
45	45
46	46	static inline __attribute_const__ __u16 __fswab16(__u16 val)
47	47	{
48		−#ifdef __arch_swab16
	48	+#ifdef __HAVE_BUILTIN_BSWAP16__
	49	+ return __builtin_bswap16(val);
	50	+#elif defined (__arch_swab16)
49	51	return __arch_swab16(val);
50	52	#else
51	53	return ___constant_swab16(val);
@@ -54,7 +56,9 @@ static inline __attribute_const__ __u16 __fswab16(__u16 val) · 2 unmodified lines
54	56
55	57	static inline __attribute_const__ __u32 __fswab32(__u32 val)
56	58	{
57		−#ifdef __arch_swab32
	59	+#ifdef __HAVE_BUILTIN_BSWAP32__
	60	+ return __builtin_bswap32(val);
	61	+#elif defined(__arch_swab32)
58	62	return __arch_swab32(val);
59	63	#else
60	64	return ___constant_swab32(val);
@@ -63,7 +67,9 @@ static inline __attribute_const__ __u32 __fswab32(__u32 val) · 2 unmodified lines
63	67
64	68	static inline __attribute_const__ __u64 __fswab64(__u64 val)
65	69	{
66		−#ifdef __arch_swab64
	70	+#ifdef __HAVE_BUILTIN_BSWAP64__
	71	+ return __builtin_bswap64(val);
	72	+#elif defined (__arch_swab64)
67	73	return __arch_swab64(val);
68	74	#elif defined(__SWAB_64_THRU_32__)
69	75	__u32 h = val >> 32;