linux/arch/arc/include/asm/checksum.h

99 lines
2.3 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
*
* Joern Rennecke <joern.rennecke@embecosm.com>: Jan 2012
* -Insn Scheduling improvements to csum core routines.
* = csum_fold( ) largely derived from ARM version.
* = ip_fast_cum( ) to have module scheduling
* -gcc 4.4.x broke networking. Alias analysis needed to be primed.
* worked around by adding memory clobber to ip_fast_csum( )
*
* vineetg: May 2010
* -Rewrote ip_fast_cscum( ) and csum_fold( ) with fast inline asm
*/
#ifndef _ASM_ARC_CHECKSUM_H
#define _ASM_ARC_CHECKSUM_H
/*
* Fold a partial checksum
*
* The 2 swords comprising the 32bit sum are added, any carry to 16th bit
* added back and final sword result inverted.
*/
static inline __sum16 csum_fold(__wsum s)
{
unsigned int r = s << 16 | s >> 16; /* ror */
s = ~s;
s -= r;
return s >> 16;
}
/*
* This is a version of ip_compute_csum() optimized for IP headers,
* which always checksum on 4 octet boundaries.
*/
static inline __sum16
ip_fast_csum(const void *iph, unsigned int ihl)
{
const void *ptr = iph;
unsigned int tmp, tmp2, sum;
__asm__(
" ld.ab %0, [%3, 4] \n"
" ld.ab %2, [%3, 4] \n"
" sub %1, %4, 2 \n"
" lsr.f lp_count, %1, 1 \n"
" bcc 0f \n"
" add.f %0, %0, %2 \n"
" ld.ab %2, [%3, 4] \n"
"0: lp 1f \n"
" ld.ab %1, [%3, 4] \n"
" adc.f %0, %0, %2 \n"
" ld.ab %2, [%3, 4] \n"
" adc.f %0, %0, %1 \n"
"1: adc.f %0, %0, %2 \n"
" add.cs %0,%0,1 \n"
: "=&r"(sum), "=r"(tmp), "=&r"(tmp2), "+&r" (ptr)
: "r"(ihl)
: "cc", "lp_count", "memory");
return csum_fold(sum);
}
/*
* TCP pseudo Header is 12 bytes:
* SA [4], DA [4], zeroes [1], Proto[1], TCP Seg(hdr+data) Len [2]
*/
static inline __wsum
ipv4: Update parameters for csum_tcpudp_magic to their original types This patch updates all instances of csum_tcpudp_magic and csum_tcpudp_nofold to reflect the types that are usually used as the source inputs. For example the protocol field is populated based on nexthdr which is actually an unsigned 8 bit value. The length is usually populated based on skb->len which is an unsigned integer. This addresses an issue in which the IPv6 function csum_ipv6_magic was generating a checksum using the full 32b of skb->len while csum_tcpudp_magic was only using the lower 16 bits. As a result we could run into issues when attempting to adjust the checksum as there was no protocol agnostic way to update it. With this change the value is still truncated as many architectures use "(len + proto) << 8", however this truncation only occurs for values greater than 16776960 in length and as such is unlikely to occur as we stop the inner headers at ~64K in size. I did have to make a few minor changes in the arm, mn10300, nios2, and score versions of the function in order to support these changes as they were either using things such as an OR to combine the protocol and length, or were using ntohs to convert the length which would have truncated the value. I also updated a few spots in terms of whitespace and type differences for the addresses. Most of this was just to make sure all of the definitions were in sync going forward. Signed-off-by: Alexander Duyck <aduyck@mirantis.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-03-12 06:05:34 +08:00
csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len,
__u8 proto, __wsum sum)
{
__asm__ __volatile__(
" add.f %0, %0, %1 \n"
" adc.f %0, %0, %2 \n"
" adc.f %0, %0, %3 \n"
" adc.f %0, %0, %4 \n"
" adc %0, %0, 0 \n"
: "+&r"(sum)
: "r"(saddr), "r"(daddr),
#ifdef CONFIG_CPU_BIG_ENDIAN
"r"(len),
#else
"r"(len << 8),
#endif
"r"(htons(proto))
: "cc");
return sum;
}
#define csum_fold csum_fold
#define ip_fast_csum ip_fast_csum
#define csum_tcpudp_nofold csum_tcpudp_nofold
#include <asm-generic/checksum.h>
#endif /* _ASM_ARC_CHECKSUM_H */