lib/checksum.c: fix carry in csum_tcpudp_nofold

commit 150ae0e9 upstream.

The carry from the 64->32bits folding was dropped, e.g with:
saddr=0xFFFFFFFF daddr=0xFF0000FF len=0xFFFF proto=0 sum=1,
csum_tcpudp_nofold returned 0 instead of 1.
Signed-off-by: Karl Beldan <karl.beldan@rivierawaves.com>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Mike Frysinger <vapier@gentoo.org>
Cc: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Zefan Li <lizefan@huawei.com>

lib/checksum.c

@@ -47,6 +47,15 @@ static inline unsigned short from32to16(unsigned int x)
 	return x;
 }
 
+static inline u32 from64to32(u64 x)
+{
+	/* add up 32-bit and 32-bit for 32+c bit */
+	x = (x & 0xffffffff) + (x >> 32);
+	/* add up carry.. */
+	x = (x & 0xffffffff) + (x >> 32);
+	return (u32)x;
+}
+
 static unsigned int do_csum(const unsigned char *buff, int len)
 {
 	int odd;
@@ -193,8 +202,7 @@ __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
 #else
 	s += (proto + len) << 8;
 #endif
-	s += (s >> 32);
-	return (__force __wsum)s;
+	return (__force __wsum)from64to32(s);
 }
 EXPORT_SYMBOL(csum_tcpudp_nofold);
 #endif