1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
|
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _PARISC_CHECKSUM_H
#define _PARISC_CHECKSUM_H
#include <linux/in6.h>
/*
* 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 32-bit boundary
*/
extern __wsum csum_partial(const void *, int, __wsum);
/*
* Optimized for IP headers, which always checksum on 4 octet boundaries.
*
* Written by Randolph Chung <tausq@debian.org>, and then mucked with by
* LaMont Jones <lamont@debian.org>
*/
static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
{
unsigned int sum;
unsigned long t0, t1, t2;
__asm__ __volatile__ (
" ldws,ma 4(%1), %0\n"
" addib,<= -4, %2, 2f\n"
"\n"
" ldws 4(%1), %4\n"
" ldws 8(%1), %5\n"
" add %0, %4, %0\n"
" ldws,ma 12(%1), %3\n"
" addc %0, %5, %0\n"
" addc %0, %3, %0\n"
"1: ldws,ma 4(%1), %3\n"
" addib,> -1, %2, 1b\n"
" addc %0, %3, %0\n"
"\n"
" extru %0, 31, 16, %4\n"
" extru %0, 15, 16, %5\n"
" addc %4, %5, %0\n"
" extru %0, 15, 16, %5\n"
" add %0, %5, %0\n"
" subi -1, %0, %0\n"
"2:\n"
: "=r" (sum), "=r" (iph), "=r" (ihl), "=r" (t0), "=r" (t1), "=r" (t2)
: "1" (iph), "2" (ihl)
: "memory");
return (__force __sum16)sum;
}
/*
* Fold a partial checksum
*/
static inline __sum16 csum_fold(__wsum csum)
{
u32 sum = (__force u32)csum;
/* add the swapped two 16-bit halves of sum,
a possible carry from adding the two 16-bit halves,
will carry from the lower half into the upper half,
giving us the correct sum in the upper half. */
sum += (sum << 16) + (sum >> 16);
return (__force __sum16)(~sum >> 16);
}
static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
__u32 len, __u8 proto,
__wsum sum)
{
__asm__(
" add %1, %0, %0\n"
" addc %2, %0, %0\n"
" addc %3, %0, %0\n"
" addc %%r0, %0, %0\n"
: "=r" (sum)
: "r" (daddr), "r"(saddr), "r"(proto+len), "0"(sum));
return sum;
}
/*
* computes the checksum of the TCP/UDP pseudo-header
* returns a 16-bit checksum, already complemented
*/
static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
__u32 len, __u8 proto,
__wsum sum)
{
return csum_fold(csum_tcpudp_nofold(saddr,daddr,len,proto,sum));
}
/*
* this routine is used for miscellaneous IP-like checksums, mainly
* in icmp.c
*/
static inline __sum16 ip_compute_csum(const void *buf, int len)
{
return csum_fold (csum_partial(buf, len, 0));
}
#define _HAVE_ARCH_IPV6_CSUM
static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
const struct in6_addr *daddr,
__u32 len, __u8 proto,
__wsum sum)
{
unsigned long t0, t1, t2, t3;
len += proto; /* add 16-bit proto + len */
__asm__ __volatile__ (
#if BITS_PER_LONG > 32
/*
** We can execute two loads and two adds per cycle on PA 8000.
** But add insn's get serialized waiting for the carry bit.
** Try to keep 4 registers with "live" values ahead of the ALU.
*/
" depdi 0, 31, 32, %0\n"/* clear upper half of incoming checksum */
" ldd,ma 8(%1), %4\n" /* get 1st saddr word */
" ldd,ma 8(%2), %5\n" /* get 1st daddr word */
" add %4, %0, %0\n"
" ldd,ma 8(%1), %6\n" /* 2nd saddr */
" ldd,ma 8(%2), %7\n" /* 2nd daddr */
" add,dc %5, %0, %0\n"
" add,dc %6, %0, %0\n"
" add,dc %7, %0, %0\n"
" add,dc %3, %0, %0\n" /* fold in proto+len | carry bit */
" extrd,u %0, 31, 32, %4\n"/* copy upper half down */
" depdi 0, 31, 32, %0\n"/* clear upper half */
" add,dc %4, %0, %0\n" /* fold into 32-bits, plus carry */
" addc 0, %0, %0\n" /* add final carry */
#else
/*
** For PA 1.x, the insn order doesn't matter as much.
** Insn stream is serialized on the carry bit here too.
** result from the previous operation (eg r0 + x)
*/
" ldw,ma 4(%1), %4\n" /* get 1st saddr word */
" ldw,ma 4(%2), %5\n" /* get 1st daddr word */
" add %4, %0, %0\n"
" ldw,ma 4(%1), %6\n" /* 2nd saddr */
" addc %5, %0, %0\n"
" ldw,ma 4(%2), %7\n" /* 2nd daddr */
" addc %6, %0, %0\n"
" ldw,ma 4(%1), %4\n" /* 3rd saddr */
" addc %7, %0, %0\n"
" ldw,ma 4(%2), %5\n" /* 3rd daddr */
" addc %4, %0, %0\n"
" ldw,ma 4(%1), %6\n" /* 4th saddr */
" addc %5, %0, %0\n"
" ldw,ma 4(%2), %7\n" /* 4th daddr */
" addc %6, %0, %0\n"
" addc %7, %0, %0\n"
" addc %3, %0, %0\n" /* fold in proto+len */
" addc 0, %0, %0\n" /* add carry */
#endif
: "=r" (sum), "=r" (saddr), "=r" (daddr), "=r" (len),
"=r" (t0), "=r" (t1), "=r" (t2), "=r" (t3)
: "0" (sum), "1" (saddr), "2" (daddr), "3" (len)
: "memory");
return csum_fold(sum);
}
#endif
|
