From 37e08cad8f177f7bf6226a9b3724234ac3d3c81d Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 22 Sep 2015 16:34:25 +0200 Subject: powerpc: inline ip_fast_csum() In several architectures, ip_fast_csum() is inlined There are functions like ip_send_check() which do nothing much more than calling ip_fast_csum(). Inlining ip_fast_csum() allows the compiler to optimise better Suggested-by: Eric Dumazet Signed-off-by: Christophe Leroy [scottwood: whitespace and cast fixes] Signed-off-by: Scott Wood --- arch/powerpc/include/asm/checksum.h | 45 +++++++++++++++++++++++++++++++------ 1 file changed, 38 insertions(+), 7 deletions(-) (limited to 'arch/powerpc/include/asm/checksum.h') diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h index afa6722cb7d2..1778f75bf769 100644 --- a/arch/powerpc/include/asm/checksum.h +++ b/arch/powerpc/include/asm/checksum.h @@ -9,16 +9,9 @@ * 2 of the License, or (at your option) any later version. */ -/* - * This is a version of ip_compute_csum() optimized for IP headers, - * which always checksum on 4 octet boundaries. ihl is the number - * of 32-bit words and is always >= 5. - */ #ifdef CONFIG_GENERIC_CSUM #include #else -extern __sum16 ip_fast_csum(const void *iph, unsigned int ihl); - /* * computes the checksum of a memory block at buff, length len, * and adds in "sum" (32-bit) @@ -137,6 +130,44 @@ static inline __wsum csum_add(__wsum csum, __wsum addend) #endif } +/* + * This is a version of ip_compute_csum() optimized for IP headers, + * which always checksum on 4 octet boundaries. ihl is the number + * of 32-bit words and is always >= 5. + */ +static inline __wsum ip_fast_csum_nofold(const void *iph, unsigned int ihl) +{ + const u32 *ptr = (const u32 *)iph + 1; +#ifdef __powerpc64__ + unsigned int i; + u64 s = *(const u32 *)iph; + + for (i = 0; i < ihl - 1; i++, ptr++) + s += *ptr; + s += (s >> 32); + return (__force __wsum)s; +#else + __wsum sum, tmp; + + asm("mtctr %3;" + "addc %0,%4,%5;" + "1: lwzu %1, 4(%2);" + "adde %0,%0,%1;" + "bdnz 1b;" + "addze %0,%0;" + : "=r" (sum), "=r" (tmp), "+b" (ptr) + : "r" (ihl - 2), "r" (*(const u32 *)iph), "r" (*ptr) + : "ctr", "xer", "memory"); + + return sum; +#endif +} + +static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) +{ + return csum_fold(ip_fast_csum_nofold(iph, ihl)); +} + #endif #endif /* __KERNEL__ */ #endif -- cgit v1.2.1