if buffer is not aligned use sum_16b() only on the not aligned
part, and then use csum() on the remaining part
Signed-off-by: Laurent Vivier <lvivier(a)redhat.com>
---
checksum.c | 14 +++++++++++++-
1 file changed, 13 insertions(+), 1 deletion(-)
diff --git a/checksum.c b/checksum.c
index f21c9b7a14d1..c94980771c63 100644
--- a/checksum.c
+++ b/checksum.c
@@ -407,7 +407,19 @@ less_than_128_bytes:
__attribute__((optimize("-fno-strict-aliasing"))) /* See csum_16b() */
uint16_t csum(const void *buf, size_t len, uint32_t init)
{
- return (uint16_t)~csum_fold(csum_avx2(buf, len, init));
+ intptr_t align = ((intptr_t)buf + 0x1f) & ~(intptr_t)0x1f;
+ unsigned int pad = align - (intptr_t)buf;
+
+ if (len < pad)
+ pad = len;
+
+ if (pad)
+ init += sum_16b(buf, pad);
+
+ if (len > pad)
+ init = csum_avx2((void *)align, len - pad, init);
+
+ return (uint16_t)~csum_fold(init);
}
#else /* __AVX2__ */
--
2.42.0