diff options
Diffstat (limited to 'arch/x86/lib/csum-partial_64.c')
| -rw-r--r-- | arch/x86/lib/csum-partial_64.c | 183 |
1 files changed, 91 insertions, 92 deletions
diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c index e7925d668b68..1f8a8f895173 100644 --- a/arch/x86/lib/csum-partial_64.c +++ b/arch/x86/lib/csum-partial_64.c @@ -9,6 +9,7 @@ #include <linux/compiler.h> #include <linux/export.h> #include <asm/checksum.h> +#include <asm/word-at-a-time.h> static inline unsigned short from32to16(unsigned a) { @@ -21,120 +22,119 @@ static inline unsigned short from32to16(unsigned a) } /* - * Do a 64-bit checksum on an arbitrary memory area. + * Do a checksum on an arbitrary memory area. * Returns a 32bit checksum. * * This isn't as time critical as it used to be because many NICs * do hardware checksumming these days. - * - * Things tried and found to not make it faster: - * Manual Prefetching - * Unrolling to an 128 bytes inner loop. - * Using interleaving with more registers to break the carry chains. + * + * Still, with CHECKSUM_COMPLETE this is called to compute + * checksums on IPv6 headers (40 bytes) and other small parts. + * it's best to have buff aligned on a 64-bit boundary */ -static unsigned do_csum(const unsigned char *buff, unsigned len) +__wsum csum_partial(const void *buff, int len, __wsum sum) { - unsigned odd, count; - unsigned long result = 0; + u64 temp64 = (__force u64)sum; + unsigned odd, result; - if (unlikely(len == 0)) - return result; odd = 1 & (unsigned long) buff; if (unlikely(odd)) { - result = *buff << 8; + if (unlikely(len == 0)) + return sum; + temp64 = ror32((__force u32)sum, 8); + temp64 += (*(unsigned char *)buff << 8); len--; buff++; } - count = len >> 1; /* nr of 16-bit words.. */ - if (count) { - if (2 & (unsigned long) buff) { - result += *(unsigned short *)buff; - count--; - len -= 2; - buff += 2; - } - count >>= 1; /* nr of 32-bit words.. */ - if (count) { - unsigned long zero; - unsigned count64; - if (4 & (unsigned long) buff) { - result += *(unsigned int *) buff; - count--; - len -= 4; - buff += 4; - } - count >>= 1; /* nr of 64-bit words.. */ - /* main loop using 64byte blocks */ - zero = 0; - count64 = count >> 3; - while (count64) { - asm("addq 0*8(%[src]),%[res]\n\t" - "adcq 1*8(%[src]),%[res]\n\t" - "adcq 2*8(%[src]),%[res]\n\t" - "adcq 3*8(%[src]),%[res]\n\t" - "adcq 4*8(%[src]),%[res]\n\t" - "adcq 5*8(%[src]),%[res]\n\t" - "adcq 6*8(%[src]),%[res]\n\t" - "adcq 7*8(%[src]),%[res]\n\t" - "adcq %[zero],%[res]" - : [res] "=r" (result) - : [src] "r" (buff), [zero] "r" (zero), - "[res]" (result)); - buff += 64; - count64--; - } + while (unlikely(len >= 64)) { + asm("addq 0*8(%[src]),%[res]\n\t" + "adcq 1*8(%[src]),%[res]\n\t" + "adcq 2*8(%[src]),%[res]\n\t" + "adcq 3*8(%[src]),%[res]\n\t" + "adcq 4*8(%[src]),%[res]\n\t" + "adcq 5*8(%[src]),%[res]\n\t" + "adcq 6*8(%[src]),%[res]\n\t" + "adcq 7*8(%[src]),%[res]\n\t" + "adcq $0,%[res]" + : [res] "+r" (temp64) + : [src] "r" (buff) + : "memory"); + buff += 64; + len -= 64; + } + + if (len & 32) { + asm("addq 0*8(%[src]),%[res]\n\t" + "adcq 1*8(%[src]),%[res]\n\t" + "adcq 2*8(%[src]),%[res]\n\t" + "adcq 3*8(%[src]),%[res]\n\t" + "adcq $0,%[res]" + : [res] "+r" (temp64) + : [src] "r" (buff) + : "memory"); + buff += 32; + } + if (len & 16) { + asm("addq 0*8(%[src]),%[res]\n\t" + "adcq 1*8(%[src]),%[res]\n\t" + "adcq $0,%[res]" + : [res] "+r" (temp64) + : [src] "r" (buff) + : "memory"); + buff += 16; + } + if (len & 8) { + asm("addq 0*8(%[src]),%[res]\n\t" + "adcq $0,%[res]" + : [res] "+r" (temp64) + : [src] "r" (buff) + : "memory"); + buff += 8; + } + if (len & 7) { +#ifdef CONFIG_DCACHE_WORD_ACCESS + unsigned int shift = (8 - (len & 7)) * 8; + unsigned long trail; - /* last up to 7 8byte blocks */ - count %= 8; - while (count) { - asm("addq %1,%0\n\t" - "adcq %2,%0\n" - : "=r" (result) - : "m" (*(unsigned long *)buff), - "r" (zero), "0" (result)); - --count; - buff += 8; - } - result = add32_with_carry(result>>32, - result&0xffffffff); + trail = (load_unaligned_zeropad(buff) << shift) >> shift; - if (len & 4) { - result += *(unsigned int *) buff; - buff += 4; - } + asm("addq %[trail],%[res]\n\t" + "adcq $0,%[res]" + : [res] "+r" (temp64) + : [trail] "r" (trail)); +#else + if (len & 4) { + asm("addq %[val],%[res]\n\t" + "adcq $0,%[res]" + : [res] "+r" (temp64) + : [val] "r" ((u64)*(u32 *)buff) + : "memory"); + buff += 4; } if (len & 2) { - result += *(unsigned short *) buff; + asm("addq %[val],%[res]\n\t" + "adcq $0,%[res]" + : [res] "+r" (temp64) + : [val] "r" ((u64)*(u16 *)buff) + : "memory"); buff += 2; } + if (len & 1) { + asm("addq %[val],%[res]\n\t" + "adcq $0,%[res]" + : [res] "+r" (temp64) + : [val] "r" ((u64)*(u8 *)buff) + : "memory"); + } +#endif } - if (len & 1) - result += *buff; - result = add32_with_carry(result>>32, result & 0xffffffff); - if (unlikely(odd)) { + result = add32_with_carry(temp64 >> 32, temp64 & 0xffffffff); + if (unlikely(odd)) { result = from32to16(result); result = ((result >> 8) & 0xff) | ((result & 0xff) << 8); } - return result; -} - -/* - * computes the checksum of a memory block at buff, length len, - * and adds in "sum" (32-bit) - * - * returns a 32-bit number suitable for feeding into itself - * or csum_tcpudp_magic - * - * this function must be called with even lengths, except - * for the last fragment, which may be odd - * - * it's best to have buff aligned on a 64-bit boundary - */ -__wsum csum_partial(const void *buff, int len, __wsum sum) -{ - return (__force __wsum)add32_with_carry(do_csum(buff, len), - (__force u32)sum); + return (__force __wsum)result; } EXPORT_SYMBOL(csum_partial); @@ -147,4 +147,3 @@ __sum16 ip_compute_csum(const void *buff, int len) return csum_fold(csum_partial(buff,len,0)); } EXPORT_SYMBOL(ip_compute_csum); - |