The asm code in csum_tcpudp_nofold() is performance-critical, I am sorry
for the poorly considered implementation about the performance influence
with GCC in the commit 198688edbf77 ("MIPS: Fix inline asm input/output
type mismatch in checksum.h used with Clang").

With this patch, we can build successfully by both GCC and Clang,
at the same time, we can avoid the potential performance influence
with GCC.

Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
---
 arch/mips/include/asm/checksum.h | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h
index 1e6c135..80eddd4 100644
--- a/arch/mips/include/asm/checksum.h
+++ b/arch/mips/include/asm/checksum.h

@@ -128,9 +128,13 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)

 static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
 					__u32 len, __u8 proto,
-					__wsum sum)
+					__wsum sum_in)
 {
-	unsigned long tmp = (__force unsigned long)sum;
+#ifdef __clang__

+	unsigned long sum = (__force unsigned long)sum_in;
+#else
+	__wsum sum = sum_in;
+#endif

 	__asm__(
 	"	.set	push		# csum_tcpudp_nofold\n"

@@ -159,7 +163,7 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
 	"	addu	%0, $1		\n"
 #endif
 	"	.set	pop"
-	: "=r" (tmp)
+	: "=r" (sum)
 	: "0" ((__force unsigned long)daddr),
 	  "r" ((__force unsigned long)saddr),
 #ifdef __MIPSEL__

@@ -169,7 +173,7 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
 #endif
 	  "r" ((__force unsigned long)sum));

-	return (__force __wsum)tmp;
+	return (__force __wsum)sum;
 }
 #define csum_tcpudp_nofold csum_tcpudp_nofold

--

2.1.0