powerpc: Reduce csum_add() complexity for PPC64

PPC64 does everything in C, gcc is able to skip calculation
when one of the operands in zero.

Move the constant folding in PPC32 part.

This helps GCC and reduces ppc64_defconfig by 170 bytes.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/a4ca63dd4c4b09e1906d08fb814af5a41d0f3fcb.1644651363.git.christophe.leroy@csgroup.eu
This commit is contained in:
Christophe Leroy 2022-02-12 08:36:17 +01:00 committed by Michael Ellerman
parent a553476c44
commit f206fdd9d4
1 changed files with 4 additions and 5 deletions

View File

@ -95,16 +95,15 @@ static __always_inline __wsum csum_add(__wsum csum, __wsum addend)
{
#ifdef __powerpc64__
u64 res = (__force u64)csum;
#endif
res += (__force u64)addend;
return (__force __wsum)((u32)res + (res >> 32));
#else
if (__builtin_constant_p(csum) && csum == 0)
return addend;
if (__builtin_constant_p(addend) && addend == 0)
return csum;
#ifdef __powerpc64__
res += (__force u64)addend;
return (__force __wsum)((u32)res + (res >> 32));
#else
asm("addc %0,%0,%1;"
"addze %0,%0;"
: "+r" (csum) : "r" (addend) : "xer");