Merge branch 'ipv4-ipv6-csums'

Alexander Duyck says:

====================
Fix differences between IPv4 and IPv6 TCP/UDP checksum calculation

This patch series is meant to address the differences that exist between
IPv4 and IPv6 in terms of checksum calculation.  Specifically the IPv6
function csum_ipv6_magic treated length as a value that could be greater
than 64K, while csum_tcpudp_magic was truncating the length at 16 bits.
After looking over the code and giving it some thought I decided it would
be best to update the IPv4 function so that it worked the same way the IPv6
one did.  This allows us to get the same results given the same inputs for
both functions.  As a result we can use the same processes to reverse the
calculation in the event we need to do something like remove the length of
the pseudo-header checksum.

I also took the opportunity to standardize things so that the parameters
for these functions all use the correct types.  IPv4 addresses are __be32,
length should always be __u32, and protocol is a __u8.

With this change in place it corrects an issue with UDP tunnels in which we
were getting a checksum that was off by 1 when performing fragmentation on
inner UDP packets.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

40 files changed, 137 insertions, 184 deletions

diff --git a/arch/alpha/include/asm/checksum.h b/arch/alpha/include/asm/checksum.h
index d3854bbf0a9e..f2bbdd2ace51 100644
--- a/arch/alpha/include/asm/checksum.h
+++ b/arch/alpha/include/asm/checksum.h
@@ -13,14 +13,11 @@ extern __sum16 ip_fast_csum(const void *iph, unsigned int ihl);
  * computes the checksum of the TCP/UDP pseudo-header
  * returns a 16-bit checksum, already complemented
  */
-extern __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
-					   unsigned short len,
-					   unsigned short proto,
-					   __wsum sum);
+__sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
+			  __u32 len, __u8 proto, __wsum sum);
 
 __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
-				unsigned short len, unsigned short proto,
-				__wsum sum);
+			  __u32 len, __u8 proto, __wsum sum);
 
 /*
  * computes the checksum of a memory block at buff, length len,
@@ -70,6 +67,5 @@ static inline __sum16 csum_fold(__wsum csum)
 #define _HAVE_ARCH_IPV6_CSUM
 extern __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 			       const struct in6_addr *daddr,
-			       __u32 len, unsigned short proto,
-			       __wsum sum);
+			       __u32 len, __u8 proto, __wsum sum);
 #endif
diff --git a/arch/alpha/lib/checksum.c b/arch/alpha/lib/checksum.c
index 199f6efa83fa..377f9e34eb97 100644
--- a/arch/alpha/lib/checksum.c
+++ b/arch/alpha/lib/checksum.c
@@ -42,9 +42,7 @@ static inline unsigned short from64to16(unsigned long x)
  * returns a 16-bit checksum, already complemented.
  */
 __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
-				   unsigned short len,
-				   unsigned short proto,
-				   __wsum sum)
+			  __u32 len, __u8 proto, __wsum sum)
 {
 	return (__force __sum16)~from64to16(
 		(__force u64)saddr + (__force u64)daddr +
@@ -52,9 +50,7 @@ __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
 }
 
 __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
-				   unsigned short len,
-				   unsigned short proto,
-				   __wsum sum)
+			  __u32 len, __u8 proto, __wsum sum)
 {
 	unsigned long result;
 
diff --git a/arch/arc/include/asm/checksum.h b/arch/arc/include/asm/checksum.h
index 10957298b7a3..913eb4aab05b 100644
--- a/arch/arc/include/asm/checksum.h
+++ b/arch/arc/include/asm/checksum.h
@@ -70,8 +70,8 @@ ip_fast_csum(const void *iph, unsigned int ihl)
  * SA [4], DA [4], zeroes [1], Proto[1], TCP Seg(hdr+data) Len [2]
  */
 static inline __wsum
-csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
-		   unsigned short proto, __wsum sum)
+csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len,
+		   __u8 proto, __wsum sum)
 {
 	__asm__ __volatile__(
 	"	add.f %0, %0, %1	\n"
diff --git a/arch/arm/include/asm/checksum.h b/arch/arm/include/asm/checksum.h
index 523315115478..524692f4acab 100644
--- a/arch/arm/include/asm/checksum.h
+++ b/arch/arm/include/asm/checksum.h
@@ -84,10 +84,10 @@ ip_fast_csum(const void *iph, unsigned int ihl)
 }
 
 static inline __wsum
-csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
-		   unsigned short proto, __wsum sum)
+csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len,
+		   __u8 proto, __wsum sum)
 {
-	u32 lenprot = len | proto << 16;
+	u32 lenprot = len + proto;
 	if (__builtin_constant_p(sum) && sum == 0) {
 		__asm__(
 		"adds	%0, %1, %2	@ csum_tcpudp_nofold0	\n\t"
@@ -121,8 +121,8 @@ csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
  * returns a 16-bit checksum, already complemented
  */
 static inline __sum16
-csum_tcpudp_magic(__be32 saddr, __be32 daddr, unsigned short len,
-		  unsigned short proto, __wsum sum)
+csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len,
+		  __u8 proto, __wsum sum)
 {
 	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
 }
@@ -144,8 +144,8 @@ __csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, __
 		__be32 proto, __wsum sum);
 
 static inline __sum16
-csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, __u32 len,
-		unsigned short proto, __wsum sum)
+csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr,
+		__u32 len, __u8 proto, __wsum sum)
 {
 	return csum_fold(__csum_ipv6_magic(saddr, daddr, htonl(len),
 					   htonl(proto), sum));
diff --git a/arch/avr32/include/asm/checksum.h b/arch/avr32/include/asm/checksum.h
index 4ddbfd2486af..4ab7d5bdaf53 100644
--- a/arch/avr32/include/asm/checksum.h
+++ b/arch/avr32/include/asm/checksum.h
@@ -111,9 +111,8 @@ static inline __sum16 csum_fold(__wsum sum)
 }
 
 static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
-					       unsigned short len,
-					       unsigned short proto,
-					       __wsum sum)
+					__u32 len, __u8 proto,
+					__wsum sum)
 {
 	asm("	add	%0, %1\n"
 	    "	adc	%0, %0, %2\n"
@@ -132,9 +131,8 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
  * returns a 16-bit checksum, already complemented
  */
 static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
-						   unsigned short len,
-						   unsigned short proto,
-						   __wsum sum)
+					__u32 len, __u8 proto,
+					__wsum sum)
 {
 	return csum_fold(csum_tcpudp_nofold(saddr,daddr,len,proto,sum));
 }
diff --git a/arch/blackfin/include/asm/checksum.h b/arch/blackfin/include/asm/checksum.h
index 623cc7fb00bc..e7134bf94e3c 100644
--- a/arch/blackfin/include/asm/checksum.h
+++ b/arch/blackfin/include/asm/checksum.h
@@ -14,8 +14,8 @@
  */
 
 static inline __wsum
-__csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
-		   unsigned short proto, __wsum sum)
+__csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len,
+		     __u8 proto, __wsum sum)
 {
 	unsigned int carry;
 
diff --git a/arch/c6x/include/asm/checksum.h b/arch/c6x/include/asm/checksum.h
index 7246816d6e4d..249b0e421ddc 100644
--- a/arch/c6x/include/asm/checksum.h
+++ b/arch/c6x/include/asm/checksum.h
@@ -10,8 +10,8 @@
 #define _ASM_C6X_CHECKSUM_H
 
 static inline __wsum
-csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
-		   unsigned short proto, __wsum sum)
+csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len,
+		   __u8 proto, __wsum sum)
 {
 	unsigned long long tmp;
 
diff --git a/arch/cris/include/arch-v10/arch/checksum.h b/arch/cris/include/arch-v10/arch/checksum.h
index b8000c5d7fe1..d1d1bd9e1090 100644
--- a/arch/cris/include/arch-v10/arch/checksum.h
+++ b/arch/cris/include/arch-v10/arch/checksum.h
@@ -9,8 +9,8 @@
  */
 
 static inline __wsum
-csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
-		   unsigned short proto, __wsum sum)
+csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len,
+		   __u8 proto, __wsum sum)
 {
 	__wsum res;
 	__asm__ ("add.d %2, %0\n\t"
diff --git a/arch/cris/include/arch-v32/arch/checksum.h b/arch/cris/include/arch-v32/arch/checksum.h
index e5dcfce6e0dc..65cf205b1329 100644
--- a/arch/cris/include/arch-v32/arch/checksum.h
+++ b/arch/cris/include/arch-v32/arch/checksum.h
@@ -11,7 +11,7 @@
  */
 static inline __wsum
 csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
-		   unsigned short len, unsigned short proto, __wsum sum)
+		   __u32 len, __u8 proto, __wsum sum)
 {
 	__wsum res;
 
diff --git a/arch/cris/include/asm/checksum.h b/arch/cris/include/asm/checksum.h
index 75dcb77d6cb0..ea949c60b190 100644
--- a/arch/cris/include/asm/checksum.h
+++ b/arch/cris/include/asm/checksum.h
@@ -63,9 +63,8 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
  */
 
 static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
-						   unsigned short len,
-						   unsigned short proto,
-						   __wsum sum)
+					__u32 len, __u8 proto,
+					__wsum sum)
 {
 	return csum_fold(csum_tcpudp_nofold(saddr,daddr,len,proto,sum));
 }
diff --git a/arch/frv/include/asm/checksum.h b/arch/frv/include/asm/checksum.h
index 269da09ff637..b77388c5901d 100644
--- a/arch/frv/include/asm/checksum.h
+++ b/arch/frv/include/asm/checksum.h
@@ -105,8 +105,8 @@ static inline __sum16 csum_fold(__wsum sum)
  * returns a 16-bit checksum, already complemented
  */
 static inline __wsum
-csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
-		  unsigned short proto, __wsum sum)
+csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len,
+		   __u8 proto, __wsum sum)
 {
 	asm("	addcc		%1,%0,%0,icc0	\n"
 	    "	addxcc		%2,%0,%0,icc0	\n"
@@ -120,8 +120,8 @@ csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
 }
 
 static inline __sum16
-csum_tcpudp_magic(__be32 saddr, __be32 daddr, unsigned short len,
-		  unsigned short proto, __wsum sum)
+csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len,
+		  __u8 proto, __wsum sum)
 {
 	return csum_fold(csum_tcpudp_nofold(saddr,daddr,len,proto,sum));
 }
@@ -135,7 +135,7 @@ extern __sum16 ip_compute_csum(const void *buff, int len);
 #define _HAVE_ARCH_IPV6_CSUM
 static inline __sum16
 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr,
-		__u32 len, unsigned short proto, __wsum sum)
+		__u32 len, __u8 proto, __wsum sum)
 {
 	unsigned long tmp, tmp2;
 
diff --git a/arch/hexagon/include/asm/checksum.h b/arch/hexagon/include/asm/checksum.h
index 46ec8a7fd65f..d9f58d696238 100644
--- a/arch/hexagon/include/asm/checksum.h
+++ b/arch/hexagon/include/asm/checksum.h
@@ -38,12 +38,12 @@ __wsum csum_partial_copy_nocheck(const void *src, void *dst,
  * returns a 16-bit checksum, already complemented
  */
 #define csum_tcpudp_nofold csum_tcpudp_nofold
-__wsum csum_tcpudp_nofold(unsigned long saddr, unsigned long daddr,
-	unsigned short len, unsigned short proto, __wsum sum);
+__wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
+			  __u32 len, __u8 proto, __wsum sum);
 
 #define csum_tcpudp_magic csum_tcpudp_magic
-__sum16 csum_tcpudp_magic(unsigned long saddr, unsigned long daddr,
-	unsigned short len, unsigned short proto, __wsum sum);
+__sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
+			  __u32 len, __u8 proto, __wsum sum);
 
 #include <asm-generic/checksum.h>
 
diff --git a/arch/hexagon/lib/checksum.c b/arch/hexagon/lib/checksum.c
index 8169f78a46a7..617506d1a559 100644
--- a/arch/hexagon/lib/checksum.c
+++ b/arch/hexagon/lib/checksum.c
@@ -60,18 +60,16 @@ static inline unsigned short from64to16(u64 x)
  * computes the checksum of the TCP/UDP pseudo-header
  * returns a 16-bit checksum, already complemented.
  */
-__sum16 csum_tcpudp_magic(unsigned long saddr, unsigned long daddr,
-			  unsigned short len, unsigned short proto,
-			  __wsum sum)
+__sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
+			  __u32 len, __u8 proto, __wsum sum)
 {
 	return (__force __sum16)~from64to16(
 		(__force u64)saddr + (__force u64)daddr +
 		(__force u64)sum + ((len + proto) << 8));
 }
 
-__wsum csum_tcpudp_nofold(unsigned long saddr, unsigned long daddr,
-			  unsigned short len, unsigned short proto,
-			  __wsum sum)
+__wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
+			  __u32 len, __u8 proto, __wsum sum)
 {
 	u64 result;
 
diff --git a/arch/ia64/include/asm/checksum.h b/arch/ia64/include/asm/checksum.h
index 97af155057e4..7accf54162b2 100644
--- a/arch/ia64/include/asm/checksum.h
+++ b/arch/ia64/include/asm/checksum.h
@@ -16,15 +16,11 @@ extern __sum16 ip_fast_csum(const void *iph, unsigned int ihl);
  * Computes the checksum of the TCP/UDP pseudo-header returns a 16-bit
  * checksum, already complemented
  */
-extern __sum16 csum_tcpudp_magic (__be32 saddr, __be32 daddr,
-					     unsigned short len,
-					     unsigned short proto,
-					     __wsum sum);
+extern __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
+				 __u32 len, __u8 proto, __wsum sum);
 
-extern __wsum csum_tcpudp_nofold (__be32 saddr, __be32 daddr,
-					unsigned short len,
-					unsigned short proto,
-					__wsum sum);
+extern __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
+				 __u32 len, __u8 proto, __wsum sum);
 
 /*
  * Computes the checksum of a memory block at buff, length len,
@@ -73,7 +69,7 @@ static inline __sum16 csum_fold(__wsum csum)
 #define _HAVE_ARCH_IPV6_CSUM	1
 struct in6_addr;
 extern __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
-	const struct in6_addr *daddr, __u32 len, unsigned short proto,
-	__wsum csum);
+			       const struct in6_addr *daddr,
+			       __u32 len, __u8 proto, __wsum csum);
 
 #endif /* _ASM_IA64_CHECKSUM_H */
diff --git a/arch/ia64/lib/checksum.c b/arch/ia64/lib/checksum.c
index 9fc955026f86..2cb23cb0c2e1 100644
--- a/arch/ia64/lib/checksum.c
+++ b/arch/ia64/lib/checksum.c
@@ -34,8 +34,8 @@ from64to16 (unsigned long x)
  * returns a 16-bit checksum, already complemented.
  */
 __sum16
-csum_tcpudp_magic (__be32 saddr, __be32 daddr, unsigned short len,
-		   unsigned short proto, __wsum sum)
+csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len,
+		  __u8 proto, __wsum sum)
 {
 	return (__force __sum16)~from64to16(
 		(__force u64)saddr + (__force u64)daddr +
@@ -45,8 +45,8 @@ csum_tcpudp_magic (__be32 saddr, __be32 daddr, unsigned short len,
 EXPORT_SYMBOL(csum_tcpudp_magic);
 
 __wsum
-csum_tcpudp_nofold (__be32 saddr, __be32 daddr, unsigned short len,
-		    unsigned short proto, __wsum sum)
+csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len,
+		   __u8 proto, __wsum sum)
 {
 	unsigned long result;
 
diff --git a/arch/m32r/include/asm/checksum.h b/arch/m32r/include/asm/checksum.h
index a7a7c4f44abe..d68e93c9bd62 100644
--- a/arch/m32r/include/asm/checksum.h
+++ b/arch/m32r/include/asm/checksum.h
@@ -114,9 +114,8 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
 }
 
 static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
-					       unsigned short len,
-					       unsigned short proto,
-					       __wsum sum)
+					__u32 len, __u8 proto,
+					__wsum sum)
 {
 #if defined(__LITTLE_ENDIAN)
 	unsigned long len_proto = (proto + len) << 8;
@@ -145,9 +144,8 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
  * returns a 16-bit checksum, already complemented
  */
 static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
-						   unsigned short len,
-						   unsigned short proto,
-						   __wsum sum)
+					__u32 len, __u8 proto,
+					__wsum sum)
 {
 	return csum_fold(csum_tcpudp_nofold(saddr,daddr,len,proto,sum));
 }
diff --git a/arch/m68k/include/asm/checksum.h b/arch/m68k/include/asm/checksum.h
index 2f88d867c711..75e91f03b178 100644
--- a/arch/m68k/include/asm/checksum.h
+++ b/arch/m68k/include/asm/checksum.h
@@ -117,7 +117,7 @@ static inline __sum16 ip_compute_csum(const void *buff, int len)
 #define _HAVE_ARCH_IPV6_CSUM
 static __inline__ __sum16
 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr,
-		__u32 len, unsigned short proto, __wsum sum)
+		__u32 len, __u8 proto, __wsum sum)
 {
 	register unsigned long tmp;
 	__asm__("addl %2@,%0\n\t"
diff --git a/arch/metag/include/asm/checksum.h b/arch/metag/include/asm/checksum.h
index 08dd1cc65799..f65fe83b1730 100644
--- a/arch/metag/include/asm/checksum.h
+++ b/arch/metag/include/asm/checksum.h
@@ -59,8 +59,7 @@ extern __sum16 ip_fast_csum(const void *iph, unsigned int ihl);
  * returns a 16-bit checksum, already complemented
  */
 static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
-					unsigned short len,
-					unsigned short proto,
+					__u32 len, __u8 proto,
 					__wsum sum)
 {
 	unsigned long len_proto = (proto + len) << 8;
@@ -78,8 +77,8 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
 }
 
 static inline __sum16
-csum_tcpudp_magic(__be32 saddr, __be32 daddr, unsigned short len,
-		  unsigned short proto, __wsum sum)
+csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len,
+		  __u8 proto, __wsum sum)
 {
 	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
 }
diff --git a/arch/microblaze/include/asm/checksum.h b/arch/microblaze/include/asm/checksum.h
index 0185cbefdda4..adeecebbb0d1 100644
--- a/arch/microblaze/include/asm/checksum.h
+++ b/arch/microblaze/include/asm/checksum.h
@@ -16,8 +16,8 @@
  */
 #define csum_tcpudp_nofold	csum_tcpudp_nofold
 static inline __wsum
-csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
-		   unsigned short proto, __wsum sum)
+csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len,
+		   __u8 proto, __wsum sum)
 {
 	__asm__("add %0, %0, %1\n\t"
 		"addc %0, %0, %2\n\t"
diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h
index 3ceacde5eb6e..bce1ce53149a 100644
--- a/arch/mips/include/asm/checksum.h
+++ b/arch/mips/include/asm/checksum.h
@@ -160,9 +160,9 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
 }
 #define ip_fast_csum ip_fast_csum
 
-static inline __wsum csum_tcpudp_nofold(__be32 saddr,
-	__be32 daddr, unsigned short len, unsigned short proto,
-	__wsum sum)
+static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
+					__u32 len, __u8 proto,
+					__wsum sum)
 {
 	__asm__(
 	"	.set	push		# csum_tcpudp_nofold\n"
@@ -215,7 +215,7 @@ static inline __sum16 ip_compute_csum(const void *buff, int len)
 #define _HAVE_ARCH_IPV6_CSUM
 static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 					  const struct in6_addr *daddr,
-					  __u32 len, unsigned short proto,
+					  __u32 len, __u8 proto,
 					  __wsum sum)
 {
 	__wsum tmp;
diff --git a/arch/mn10300/include/asm/checksum.h b/arch/mn10300/include/asm/checksum.h
index 9fb2a8d8826a..c80df5b504ac 100644
--- a/arch/mn10300/include/asm/checksum.h
+++ b/arch/mn10300/include/asm/checksum.h
@@ -37,16 +37,11 @@ static inline __sum16 csum_fold(__wsum sum)
 	return (~sum) >> 16;
 }
 
-static inline __wsum csum_tcpudp_nofold(unsigned long saddr,
-					unsigned long daddr,
-					unsigned short len,
-					unsigned short proto,
+static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
+					__u32 len, __u8 proto,
 					__wsum sum)
 {
-	__wsum tmp;
-
-	tmp = (__wsum) ntohs(len) << 16;
-	tmp += (__wsum) proto << 8;
+	__wsum tmp = (__wsum)((len + proto) << 8);
 
 	asm(
 		"	add	%1,%0		\n"
@@ -64,10 +59,8 @@ static inline __wsum csum_tcpudp_nofold(unsigned long saddr,
  * computes the checksum of the TCP/UDP pseudo-header
  * returns a 16-bit checksum, already complemented
  */
-static inline __sum16 csum_tcpudp_magic(unsigned long saddr,
-					unsigned long daddr,
-					unsigned short len,
-					unsigned short proto,
+static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
+					__u32 len, __u8 proto,
 					__wsum sum)
 {
 	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
diff --git a/arch/nios2/include/asm/checksum.h b/arch/nios2/include/asm/checksum.h
index 6bc1f0d5df7b..703c5ee63421 100644
--- a/arch/nios2/include/asm/checksum.h
+++ b/arch/nios2/include/asm/checksum.h
@@ -45,8 +45,7 @@ static inline __sum16 csum_fold(__wsum sum)
  */
 #define csum_tcpudp_nofold csum_tcpudp_nofold
 static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
-					unsigned short len,
-					unsigned short proto,
+					__u32 len, __u8 proto,
 					__wsum sum)
 {
 	__asm__ __volatile__(
@@ -60,7 +59,7 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
 		"cmpltu	r8, %0, %3\n"
 		"add	%0, %0, r8\n"	/* add carry */
 		: "=r" (sum), "=r" (saddr)
-		: "r" (daddr), "r" ((ntohs(len) << 16) + (proto * 256)),
+		: "r" (daddr), "r" ((len + proto) << 8),
 		  "0" (sum),
 		  "1" (saddr)
 		: "r8");
@@ -69,8 +68,8 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
 }
 
 static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
-					unsigned short len,
-					unsigned short proto, __wsum sum)
+					__u32 len, __u8 proto,
+					__wsum sum)
 {
 	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
 }
diff --git a/arch/parisc/include/asm/checksum.h b/arch/parisc/include/asm/checksum.h
index c84b2fcb18a9..60c2c42619c9 100644
--- a/arch/parisc/include/asm/checksum.h
+++ b/arch/parisc/include/asm/checksum.h
@@ -85,9 +85,8 @@ static inline __sum16 csum_fold(__wsum csum)
 }
  
 static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
-					       unsigned short len,
-					       unsigned short proto,
-					       __wsum sum)
+					__u32 len, __u8 proto,
+					__wsum sum)
 {
 	__asm__(
 	"	add  %1, %0, %0\n"
@@ -104,9 +103,8 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
  * returns a 16-bit checksum, already complemented
  */
 static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
-						   unsigned short len,
-						   unsigned short proto,
-						   __wsum sum)
+					__u32 len, __u8 proto,
+					__wsum sum)
 {
 	return csum_fold(csum_tcpudp_nofold(saddr,daddr,len,proto,sum));
 }
@@ -124,7 +122,7 @@ static inline __sum16 ip_compute_csum(const void *buf, int len)
 #define _HAVE_ARCH_IPV6_CSUM
 static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 					  const struct in6_addr *daddr,
-					  __u32 len, unsigned short proto,
+					  __u32 len, __u8 proto,
 					  __wsum sum)
 {
 	__asm__ __volatile__ (
diff --git a/arch/s390/include/asm/checksum.h b/arch/s390/include/asm/checksum.h
index 740364856355..d7f100c53f07 100644
--- a/arch/s390/include/asm/checksum.h
+++ b/arch/s390/include/asm/checksum.h
@@ -91,8 +91,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
  * returns a 32-bit checksum
  */
 static inline __wsum
-csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
-                   unsigned short len, unsigned short proto,
+csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, __u8 proto,
                    __wsum sum)
 {
 	__u32 csum = (__force __u32)sum;
@@ -118,8 +117,7 @@ csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
  */
 
 static inline __sum16
-csum_tcpudp_magic(__be32 saddr, __be32 daddr,
-                  unsigned short len, unsigned short proto,
+csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len, __u8 proto,
                   __wsum sum)
 {
 	return csum_fold(csum_tcpudp_nofold(saddr,daddr,len,proto,sum));
diff --git a/arch/score/include/asm/checksum.h b/arch/score/include/asm/checksum.h
index 961bd64015a8..539d9fd45d21 100644
--- a/arch/score/include/asm/checksum.h
+++ b/arch/score/include/asm/checksum.h
@@ -127,10 +127,10 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
 }
 
 static inline __wsum
-csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
-		unsigned short proto, __wsum sum)
+csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len,
+		   __u8 proto, __wsum sum)
 {
-	unsigned long tmp = (ntohs(len) << 16) + proto * 256;
+	unsigned long tmp = (len + proto) << 8;
 	__asm__ __volatile__(
 		".set volatile\n\t"
 		"add\t%0, %0, %2\n\t"
@@ -161,8 +161,8 @@ csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
  * returns a 16-bit checksum, already complemented
  */
 static inline __sum16
-csum_tcpudp_magic(__be32 saddr, __be32 daddr, unsigned short len,
-		unsigned short proto, __wsum sum)
+csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len,
+		  __u8 proto, __wsum sum)
 {
 	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
 }
@@ -179,9 +179,8 @@ static inline unsigned short ip_compute_csum(const void *buff, int len)
 
 #define _HAVE_ARCH_IPV6_CSUM
 static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
-				const struct in6_addr *daddr,
-				__u32 len, unsigned short proto,
-				__wsum sum)
+				      const struct in6_addr *daddr,
+				      __u32 len, __u8 proto, __wsum sum)
 {
 	__asm__ __volatile__(
 		".set\tvolatile\t\t\t# csum_ipv6_magic\n\t"
diff --git a/arch/sh/include/asm/checksum_32.h b/arch/sh/include/asm/checksum_32.h
index 14b7ac2f0a07..9c84386d35cb 100644
--- a/arch/sh/include/asm/checksum_32.h
+++ b/arch/sh/include/asm/checksum_32.h
@@ -115,8 +115,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
 }
 
 static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
-					unsigned short len,
-					unsigned short proto,
+					__u32 len, __u8 proto,
 					__wsum sum)
 {
 #ifdef __LITTLE_ENDIAN__
@@ -142,8 +141,7 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
  * returns a 16-bit checksum, already complemented
  */
 static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
-					unsigned short len,
-					unsigned short proto,
+					__u32 len, __u8 proto,
 					__wsum sum)
 {
 	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
@@ -161,8 +159,7 @@ static inline __sum16 ip_compute_csum(const void *buff, int len)
 #define _HAVE_ARCH_IPV6_CSUM
 static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 				      const struct in6_addr *daddr,
-				      __u32 len, unsigned short proto,
-				      __wsum sum)
+				      __u32 len, __u8 proto, __wsum sum)
 {
 	unsigned int __dummy;
 	__asm__("clrt\n\t"
diff --git a/arch/sparc/include/asm/checksum_32.h b/arch/sparc/include/asm/checksum_32.h
index 426b2389a1c2..eff748c871ec 100644
--- a/arch/sparc/include/asm/checksum_32.h
+++ b/arch/sparc/include/asm/checksum_32.h
@@ -170,9 +170,8 @@ static inline __sum16 csum_fold(__wsum sum)
 }
 
 static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
-					       unsigned short len,
-					       unsigned short proto,
-					       __wsum sum)
+					__u32 len, __u8 proto,
+					__wsum sum)
 {
 	__asm__ __volatile__("addcc\t%1, %0, %0\n\t"
 			     "addxcc\t%2, %0, %0\n\t"
@@ -190,9 +189,8 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
  * returns a 16-bit checksum, already complemented
  */
 static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
-						   unsigned short len,
-						   unsigned short proto,
-						   __wsum sum)
+					__u32 len, __u8 proto,
+					__wsum sum)
 {
 	return csum_fold(csum_tcpudp_nofold(saddr,daddr,len,proto,sum));
 }
@@ -201,8 +199,7 @@ static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
 
 static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 				      const struct in6_addr *daddr,
-				      __u32 len, unsigned short proto,
-				      __wsum sum)
+				      __u32 len, __u8 proto, __wsum sum)
 {
 	__asm__ __volatile__ (
 		"addcc	%3, %4, %%g4\n\t"
diff --git a/arch/sparc/include/asm/checksum_64.h b/arch/sparc/include/asm/checksum_64.h
index b8779a6a5911..0395d75322e9 100644
--- a/arch/sparc/include/asm/checksum_64.h
+++ b/arch/sparc/include/asm/checksum_64.h
@@ -96,8 +96,7 @@ static inline __sum16 csum_fold(__wsum sum)
 }
 
 static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
-					unsigned int len,
-					unsigned short proto,
+					__u32 len, __u8 proto,
 					__wsum sum)
 {
 	__asm__ __volatile__(
@@ -116,8 +115,7 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
  * returns a 16-bit checksum, already complemented
  */
 static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
-					unsigned short len,
-					unsigned short proto,
+					__u32 len, __u8 proto,
 					__wsum sum)
 {
 	return csum_fold(csum_tcpudp_nofold(saddr,daddr,len,proto,sum));
@@ -127,8 +125,7 @@ static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
 
 static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 				      const struct in6_addr *daddr,
-				      __u32 len, unsigned short proto,
-				      __wsum sum)
+				      __u32 len, __u8 proto, __wsum sum)
 {
 	__asm__ __volatile__ (
 "	addcc		%3, %4, %%g7\n"
diff --git a/arch/unicore32/include/asm/checksum.h b/arch/unicore32/include/asm/checksum.h
index f55c3f937c3e..23ceb9e3a89b 100644
--- a/arch/unicore32/include/asm/checksum.h
+++ b/arch/unicore32/include/asm/checksum.h
@@ -20,8 +20,8 @@
  */
 
 static inline __wsum
-csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
-		   unsigned short proto, __wsum sum)
+csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len,
+		   __u8 proto, __wsum sum)
 {
 	__asm__(
 	"add.a	%0, %1, %2\n"
diff --git a/arch/x86/include/asm/checksum_32.h b/arch/x86/include/asm/checksum_32.h
index f50de6951738..532f85e6651f 100644
--- a/arch/x86/include/asm/checksum_32.h
+++ b/arch/x86/include/asm/checksum_32.h
@@ -112,8 +112,7 @@ static inline __sum16 csum_fold(__wsum sum)
 }
 
 static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
-					unsigned short len,
-					unsigned short proto,
+					__u32 len, __u8 proto,
 					__wsum sum)
 {
 	asm("addl %1, %0	;\n"
@@ -131,8 +130,7 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
  * returns a 16-bit checksum, already complemented
  */
 static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
-					unsigned short len,
-					unsigned short proto,
+					__u32 len, __u8 proto,
 					__wsum sum)
 {
 	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
@@ -151,8 +149,7 @@ static inline __sum16 ip_compute_csum(const void *buff, int len)
 #define _HAVE_ARCH_IPV6_CSUM
 static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 				      const struct in6_addr *daddr,
-				      __u32 len, unsigned short proto,
-				      __wsum sum)
+				      __u32 len, __u8 proto, __wsum sum)
 {
 	asm("addl 0(%1), %0	;\n"
 	    "adcl 4(%1), %0	;\n"
diff --git a/arch/x86/include/asm/checksum_64.h b/arch/x86/include/asm/checksum_64.h
index cd00e1774491..c020ee75dce7 100644
--- a/arch/x86/include/asm/checksum_64.h
+++ b/arch/x86/include/asm/checksum_64.h
@@ -84,8 +84,8 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
  * 32bit unfolded.
  */
 static inline __wsum
-csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
-		   unsigned short proto, __wsum sum)
+csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len,
+		   __u8 proto, __wsum sum)
 {
 	asm("  addl %1, %0\n"
 	    "  adcl %2, %0\n"
@@ -110,8 +110,8 @@ csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
  * complemented and ready to be filled in.
  */
 static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
-					unsigned short len,
-					unsigned short proto, __wsum sum)
+					__u32 len, __u8 proto,
+					__wsum sum)
 {
 	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
 }
@@ -177,7 +177,7 @@ struct in6_addr;
 #define _HAVE_ARCH_IPV6_CSUM 1
 extern __sum16
 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr,
-		__u32 len, unsigned short proto, __wsum sum);
+		__u32 len, __u8 proto, __wsum sum);
 
 static inline unsigned add32_with_carry(unsigned a, unsigned b)
 {
diff --git a/arch/x86/lib/csum-wrappers_64.c b/arch/x86/lib/csum-wrappers_64.c
index 1318f75d56e4..28a6654f0d08 100644
--- a/arch/x86/lib/csum-wrappers_64.c
+++ b/arch/x86/lib/csum-wrappers_64.c
@@ -135,7 +135,7 @@ EXPORT_SYMBOL(csum_partial_copy_nocheck);
 
 __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 			const struct in6_addr *daddr,
-			__u32 len, unsigned short proto, __wsum sum)
+			__u32 len, __u8 proto, __wsum sum)
 {
 	__u64 rest, sum64;
 
diff --git a/arch/x86/um/asm/checksum.h b/arch/x86/um/asm/checksum.h
index ee940185e89f..54d96f1e3594 100644
--- a/arch/x86/um/asm/checksum.h
+++ b/arch/x86/um/asm/checksum.h
@@ -87,8 +87,8 @@ static inline __sum16 csum_fold(__wsum sum)
  * 32bit unfolded.
  */
 static inline __wsum
-csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
-		   unsigned short proto, __wsum sum)
+csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len,
+		  __u8 proto, __wsum sum)
 {
 	asm("  addl %1, %0\n"
 	    "  adcl %2, %0\n"
@@ -104,9 +104,8 @@ csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
  * returns a 16-bit checksum, already complemented
  */
 static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
-					   unsigned short len,
-					   unsigned short proto,
-					   __wsum sum)
+					__u32 len, __u8 proto,
+					__wsum sum)
 {
 	return csum_fold(csum_tcpudp_nofold(saddr,daddr,len,proto,sum));
 }
diff --git a/arch/x86/um/asm/checksum_32.h b/arch/x86/um/asm/checksum_32.h
index ab77b6f9a4bf..83a75f8a1233 100644
--- a/arch/x86/um/asm/checksum_32.h
+++ b/arch/x86/um/asm/checksum_32.h
@@ -13,7 +13,7 @@ static inline __sum16 ip_compute_csum(const void *buff, int len)
 #define _HAVE_ARCH_IPV6_CSUM
 static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 					  const struct in6_addr *daddr,
-					  __u32 len, unsigned short proto,
+					  __u32 len, __u8 proto,
 					  __wsum sum)
 {
 	__asm__(
diff --git a/arch/xtensa/include/asm/checksum.h b/arch/xtensa/include/asm/checksum.h
index 0593de689b56..ec35074fcb03 100644
--- a/arch/xtensa/include/asm/checksum.h
+++ b/arch/xtensa/include/asm/checksum.h
@@ -123,9 +123,8 @@ static __inline__ __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
 }
 
 static __inline__ __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
-						   unsigned short len,
-						   unsigned short proto,
-						   __wsum sum)
+					    __u32 len, __u8 proto,
+					    __wsum sum)
 {
 
 #ifdef __XTENSA_EL__
@@ -157,9 +156,8 @@ static __inline__ __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
  * returns a 16-bit checksum, already complemented
  */
 static __inline__ __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
-						       unsigned short len,
-						       unsigned short proto,
-						       __wsum sum)
+					    __u32 len, __u8 proto,
+					    __wsum sum)
 {
 	return csum_fold(csum_tcpudp_nofold(saddr,daddr,len,proto,sum));
 }
@@ -177,7 +175,7 @@ static __inline__ __sum16 ip_compute_csum(const void *buff, int len)
 #define _HAVE_ARCH_IPV6_CSUM
 static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 					  const struct in6_addr *daddr,
-					  __u32 len, unsigned short proto,
+					  __u32 len, __u8 proto,
 					  __wsum sum)
 {
 	unsigned int __dummy;
diff --git a/include/asm-generic/checksum.h b/include/asm-generic/checksum.h
index 59811df58c5b..3150cbd8eb21 100644
--- a/include/asm-generic/checksum.h
+++ b/include/asm-generic/checksum.h
@@ -65,14 +65,14 @@ static inline __sum16 csum_fold(__wsum csum)
  * returns a 16-bit checksum, already complemented
  */
 extern __wsum
-csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
-		unsigned short proto, __wsum sum);
+csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len,
+		   __u8 proto, __wsum sum);
 #endif
 
 #ifndef csum_tcpudp_magic
 static inline __sum16
-csum_tcpudp_magic(__be32 saddr, __be32 daddr, unsigned short len,
-		  unsigned short proto, __wsum sum)
+csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len,
+		  __u8 proto, __wsum sum)
 {
 	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
 }
diff --git a/include/net/ip6_checksum.h b/include/net/ip6_checksum.h
index 1a49b73f7f6e..cca840584c88 100644
--- a/include/net/ip6_checksum.h
+++ b/include/net/ip6_checksum.h
@@ -37,8 +37,7 @@
 #ifndef _HAVE_ARCH_IPV6_CSUM
 __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 			const struct in6_addr *daddr,
-			__u32 len, unsigned short proto,
-			__wsum csum);
+			__u32 len, __u8 proto, __wsum csum);
 #endif
 
 static inline __wsum ip6_compute_pseudo(struct sk_buff *skb, int proto)
diff --git a/lib/checksum.c b/lib/checksum.c
index 8b39e86dbab5..d3ec93f9e5f3 100644
--- a/lib/checksum.c
+++ b/lib/checksum.c
@@ -191,9 +191,7 @@ static inline u32 from64to32(u64 x)
 }
 
 __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
-			unsigned short len,
-			unsigned short proto,
-			__wsum sum)
+			  __u32 len, __u8 proto, __wsum sum)
 {
 	unsigned long long s = (__force u32)sum;
 
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index f5abb1ae1358..8a3405a80260 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -40,13 +40,19 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 	__be16 protocol = skb->protocol;
 	u16 mac_len = skb->mac_len;
 	int udp_offset, outer_hlen;
-	u32 partial;
+	__wsum partial;
 
 	if (unlikely(!pskb_may_pull(skb, tnl_hlen)))
 		goto out;
 
-	/* adjust partial header checksum to negate old length */
-	partial = (__force u32)uh->check + (__force u16)~uh->len;
+	/* Adjust partial header checksum to negate old length.
+	 * We cannot rely on the value contained in uh->len as it is
+	 * possible that the actual value exceeds the boundaries of the
+	 * 16 bit length field due to the header being added outside of an
+	 * IP or IPv6 frame that was already limited to 64K - 1.
+	 */
+	partial = csum_sub(csum_unfold(uh->check),
+			   (__force __wsum)htonl(skb->len));
 
 	/* setup inner skb. */
 	skb->encapsulation = 0;
@@ -119,8 +125,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 		if (!need_csum)
 			continue;
 
-		uh->check = ~csum_fold((__force __wsum)
-				       ((__force u32)len + partial));
+		uh->check = ~csum_fold(csum_add(partial, (__force __wsum)len));
 
 		if (skb->encapsulation || !offload_csum) {
 			uh->check = gso_make_checksum(skb, ~uh->check);
diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c
index 8f920580976f..b2025bf3da4a 100644
--- a/net/ipv6/ip6_checksum.c
+++ b/net/ipv6/ip6_checksum.c
@@ -6,8 +6,7 @@
 #ifndef _HAVE_ARCH_IPV6_CSUM
 __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 			const struct in6_addr *daddr,
-			__u32 len, unsigned short proto,
-			__wsum csum)
+			__u32 len, __u8 proto, __wsum csum)
 {
 
 	int carry;