net: fix aliasing in checksum computation

[ upstream commit 24f1955 ]

That means a superfluous cast is removed and aliasing through a uint8_t
pointer is eliminated. NB: The C standard specifies that a unsigned char
pointer may alias while the C standard doesn't include such requirement
for uint8_t pointers.

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.

Fixes: 6006818 ("net: new checksum functions")
Fixes: e079655 ("net: fix build with gcc 4.4.7 and strict aliasing")

Signed-off-by: Georg Sauthoff <mail@gms.tf>
Reviewed-by: Morten Brørup <mb@smartsharesystems.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>

lib/librte_net/rte_ip.h

@@ -119,29 +119,18 @@ struct rte_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 (unlikely(len % 2)) {
 		uint16_t left = 0;
-		*(uint8_t *)&left = *(const uint8_t *)u16_buf;
+		*(unsigned char *)&left = *(const unsigned char *)end;
 		sum += left;
 	}