asm-generic: Improve csum_fold

This csum_fold implementation introduced into arch/arc by Vineet Gupta
is better than the default implementation on at least arc, x86, and
riscv. Using GCC trunk and compiling non-inlined version, this
implementation has 41.6667%, 25% fewer instructions on riscv64, x86-64
respectively with -O3 optimization. Most implmentations override this
default in asm, but this should be more performant than all of those
other implementations except for arm which has barrel shifting and
sparc32 which has a carry flag.

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
Reviewed-by: David Laight <david.laight@aculab.com>
Link: https://lore.kernel.org/r/20240108-optimize_checksum-v15-1-1c50de5f2167@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

diff --git a/include/asm-generic/checksum.h b/include/asm-generic/checksum.h
index 43e18db89c1439fc3aed1ed6a29a003fa66b899d..ad928cce268b40bcf09566c708e16a432f7c7c6d 100644 (file)
--- a/include/asm-generic/checksum.h
+++ b/include/asm-generic/checksum.h
@@ -2,6 +2,8 @@
 #ifndef __ASM_GENERIC_CHECKSUM_H
 #define __ASM_GENERIC_CHECKSUM_H
 
+#include <linux/bitops.h>
+
 /*
  * computes the checksum of a memory block at buff, length len,
  * and adds in "sum" (32-bit)
@@ -31,9 +33,7 @@ extern __sum16 ip_fast_csum(const void *iph, unsigned int ihl);
 static inline __sum16 csum_fold(__wsum csum)
 {
        u32 sum = (__force u32)csum;
-       sum = (sum & 0xffff) + (sum >> 16);
-       sum = (sum & 0xffff) + (sum >> 16);
-       return (__force __sum16)~sum;
+       return (__force __sum16)((~sum - ror32(sum, 16)) >> 16);
 }
 #endif