On 9/18/2021 12:49 PM, Georg Sauthoff wrote:
That means a superfluous cast is removed and aliasing through a uint8_t
pointer is eliminated. Note that uint8_t doesn't have the same
strict-aliasing properties as unsigned char.
Also simplified the loop since a modern C compiler can speed up (i.e.
auto-vectorize) it in a similar way. For example, GCC auto-vectorizes it
for Haswell using AVX registers while halving the number of instructions
in the generated code.
Signed-off-by: Georg Sauthoff <m...@gms.tf>
+ Morten. (Because of past reviews on cksum code)
---
lib/net/rte_ip.h | 27 ++++++++-------------------
1 file changed, 8 insertions(+), 19 deletions(-)
diff --git a/lib/net/rte_ip.h b/lib/net/rte_ip.h
index 05948b69b7..386db94c85 100644
--- a/lib/net/rte_ip.h
+++ b/lib/net/rte_ip.h
@@ -141,29 +141,18 @@ rte_ipv4_hdr_len(const struct rte_ipv4_hdr *ipv4_hdr)
static inline uint32_t
__rte_raw_cksum(const void *buf, size_t len, uint32_t sum)
{
- /* workaround gcc strict-aliasing warning */
- uintptr_t ptr = (uintptr_t)buf;
+ /* extend strict-aliasing rules */
typedef uint16_t __attribute__((__may_alias__)) u16_p;
- const u16_p *u16_buf = (const u16_p *)ptr;
-
- while (len >= (sizeof(*u16_buf) * 4)) {
- sum += u16_buf[0];
- sum += u16_buf[1];
- sum += u16_buf[2];
- sum += u16_buf[3];
- len -= sizeof(*u16_buf) * 4;
- u16_buf += 4;
- }
- while (len >= sizeof(*u16_buf)) {
+ const u16_p *u16_buf = (const u16_p *)buf;
+ const u16_p *end = u16_buf + len / sizeof(*u16_buf);
+
+ for (; u16_buf != end; ++u16_buf)
sum += *u16_buf;
- len -= sizeof(*u16_buf);
- u16_buf += 1;
- }
- /* if length is in odd bytes */
- if (len == 1) {
+ /* if length is odd, keeping it byte order independent */
+ if (len % 2) {
uint16_t left = 0;
- *(uint8_t *)&left = *(const uint8_t *)u16_buf;
+ *(unsigned char*)&left = *(const unsigned char *)end;
sum += left;
}
