1ee3630a3e
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>
15 lines
494 B
C
15 lines
494 B
C
#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);
|