When building kernel with CONFIG_CC_OPTIMISE_FOR_SIZE, several
copies of csum_sub() are generated, with the following code:

	00000170 <csum_sub>:
	     170:	7c 84 20 f8 	not     r4,r4
	     174:	7c 63 20 14 	addc    r3,r3,r4
	     178:	7c 63 01 94 	addze   r3,r3
	     17c:	4e 80 00 20 	blr

Let's define a PPC32 version with subc/addme, and for it's inlining.

It will return 0 instead of 0xffffffff when subtracting 0x80000000 to itself,
this is not an issue as 0 and ~0 are equivalent, refer to RFC 1624.

Signed-off-by: Christophe Leroy <redacted>
---
 arch/powerpc/include/asm/checksum.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h
index 350de8f90250..3288a1bf5e8d 100644
--- a/arch/powerpc/include/asm/checksum.h
+++ b/arch/powerpc/include/asm/checksum.h

@@ -112,6 +112,22 @@ static __always_inline __wsum csum_add(__wsum csum, __wsum addend)
 #endif
 }
 
+#ifdef CONFIG_PPC32
+#define HAVE_ARCH_CSUM_SUB
+static __always_inline __wsum csum_sub(__wsum csum, __wsum addend)
+{
+	if (__builtin_constant_p(csum) && (csum == 0 || csum == ~0))
+		return ~addend;
+	if (__builtin_constant_p(addend) && (addend == 0 || addend == ~0))
+		return csum;
+
+	asm("subc %0,%0,%1;"
+	    "addme %0,%0;"
+	    : "+r" (csum) : "r" (addend) : "xer");
+	return csum;
+}
+#endif
+
 /*
  * This is a version of ip_compute_csum() optimized for IP headers,
  * which always checksum on 4 octet boundaries.  ihl is the number

-- 
2.34.1