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@xxxxxxxxxxx>
---
arch/mips/include/asm/checksum.h | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h
index 1e6c135..64d353e 100644
--- a/arch/mips/include/asm/checksum.h
+++ b/arch/mips/include/asm/checksum.h
@@ -130,7 +130,9 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
__u32 len, __u8 proto,
__wsum sum)
{
+#ifdef __clang__
unsigned long tmp = (__force unsigned long)sum;
+#endif
__asm__(
" .set push # csum_tcpudp_nofold\n"
@@ -159,7 +161,11 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
" addu %0, $1 \n"
#endif
" .set pop"
+#ifdef __clang__
: "=r" (tmp)
+#else
+ : "=r" (sum)
+#endif
: "0" ((__force unsigned long)daddr),
"r" ((__force unsigned long)saddr),
#ifdef __MIPSEL__
@@ -169,7 +175,11 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
#endif
"r" ((__force unsigned long)sum));
+#ifdef __clang__
return (__force __wsum)tmp;
+#else
+ return sum;
+#endif
}
#define csum_tcpudp_nofold csum_tcpudp_nofold
--
2.1.0
