Messages in this thread Patch in this message | | | From | David Laight <> | Subject | [PATCH] x86/lib: Remove the special case for odd-aligned buffers in csum_partial.c | Date | Mon, 13 Dec 2021 14:43:48 +0000 |
| |
There is no need to special case the very unusual odd-aligned buffers. They are no worse than 4n+2 aligned buffers.
Signed-off-by: David Laight <david.laight@aculab.com> ---
On an i7-7700 misaligned buffers add 2 or 3 clocks (in 115) to a 512 byte checksum. That is just measuring the main loop with an lfence prior to rdpmc to read PERF_COUNT_HW_CPU_CYCLES.
arch/x86/lib/csum-partial_64.c | 16 +--------------- 1 file changed, 1 insertion(+), 15 deletions(-)
diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c index 40b527ba1da1..abf819dd8525 100644 --- a/arch/x86/lib/csum-partial_64.c +++ b/arch/x86/lib/csum-partial_64.c @@ -35,17 +35,7 @@ static inline unsigned short from32to16(unsigned a) __wsum csum_partial(const void *buff, int len, __wsum sum) { u64 temp64 = (__force u64)sum; - unsigned odd, result; - - odd = 1 & (unsigned long) buff; - if (unlikely(odd)) { - if (unlikely(len == 0)) - return sum; - temp64 = ror32((__force u32)sum, 8); - temp64 += (*(unsigned char *)buff << 8); - len--; - buff++; - } + unsigned result; while (unlikely(len >= 64)) { asm("addq 0*8(%[src]),%[res]\n\t" @@ -130,10 +120,6 @@ __wsum csum_partial(const void *buff, int len, __wsum sum) #endif } result = add32_with_carry(temp64 >> 32, temp64 & 0xffffffff); - if (unlikely(odd)) { - result = from32to16(result); - result = ((result >> 8) & 0xff) | ((result & 0xff) << 8); - } return (__force __wsum)result; } EXPORT_SYMBOL(csum_partial); -- 2.17.1 - Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK Registration No: 1397386 (Wales)
| |