From cf66bb93e0f75e0a4ba1ec070692618fa028e994 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Mon, 3 Dec 2012 16:25:40 +0000 Subject: 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 Acked-by: H. Peter Anvin --- arch/Kconfig | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'arch/Kconfig') diff --git a/arch/Kconfig b/arch/Kconfig index 366ec06a5185..c31416b10586 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -112,6 +112,25 @@ config HAVE_EFFICIENT_UNALIGNED_ACCESS See Documentation/unaligned-memory-access.txt for more information on the topic of unaligned memory accesses. +config ARCH_USE_BUILTIN_BSWAP + bool + help + Modern versions of GCC (since 4.4) have builtin functions + for handling byte-swapping. Using these, instead of the old + inline assembler that the architecture code provides in the + __arch_bswapXX() macros, allows the compiler to see what's + happening and offers more opportunity for optimisation. In + particular, the compiler will be able to combine the byteswap + with a nearby load or store and use load-and-swap or + store-and-swap instructions if the architecture has them. It + should almost *never* result in code which is worse than the + hand-coded assembler in . But just in case it + does, the use of the builtins is optional. + + Any architecture with load-and-swap or store-and-swap + instructions should set this. And it shouldn't hurt to set it + on architectures that don't have such instructions. + config HAVE_SYSCALL_WRAPPERS bool -- cgit v1.2.3