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
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
|
#ifndef _ASM_SCORE_CHECKSUM_H
#define _ASM_SCORE_CHECKSUM_H
#include <linux/in6.h>
#include <asm/uaccess.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
*/
unsigned int csum_partial(const void *buff, int len, __wsum sum);
unsigned int csum_partial_copy_from_user(const char *src, char *dst, int len,
unsigned int sum, int *csum_err);
unsigned int csum_partial_copy(const char *src, char *dst,
int len, unsigned int sum);
/*
* this is a new version of the above that records errors it finds in *errp,
* but continues and zeros the rest of the buffer.
*/
/*
* Copy and checksum to user
*/
#define HAVE_CSUM_COPY_USER
static inline
__wsum csum_and_copy_to_user(const void *src, void __user *dst, int len,
__wsum sum, int *err_ptr)
{
sum = csum_partial(src, len, sum);
if (copy_to_user(dst, src, len)) {
*err_ptr = -EFAULT;
return (__force __wsum) -1; /* invalid checksum */
}
return sum;
}
#define csum_partial_copy_nocheck csum_partial_copy
/*
* Fold a partial checksum without adding pseudo headers
*/
static inline __sum16 csum_fold(__wsum sum)
{
/* the while loop is unnecessary really, it's always enough with two
iterations */
__asm__ __volatile__(
".set volatile\n\t"
".set\tr1\n\t"
"slli\tr1,%0, 16\n\t"
"add\t%0,%0, r1\n\t"
"cmp.c\tr1, %0\n\t"
"srli\t%0, %0, 16\n\t"
"bleu\t1f\n\t"
"addi\t%0, 0x1\n\t"
"1:ldi\tr30, 0xffff\n\t"
"xor\t%0, %0, r30\n\t"
"slli\t%0, %0, 16\n\t"
"srli\t%0, %0, 16\n\t"
".set\tnor1\n\t"
".set optimize\n\t"
: "=r" (sum)
: "0" (sum));
return sum;
}
/*
* This is a version of ip_compute_csum() optimized for IP headers,
* which always checksum on 4 octet boundaries.
*
* By Jorge Cwik <jorge@laser.satlink.net>, adapted for linux by
* Arnt Gulbrandsen.
*/
static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
{
unsigned int sum;
unsigned long dummy;
__asm__ __volatile__(
".set volatile\n\t"
".set\tnor1\n\t"
"lw\t%0, [%1]\n\t"
"subri\t%2, %2, 4\n\t"
"slli\t%2, %2, 2\n\t"
"lw\t%3, [%1, 4]\n\t"
"add\t%2, %2, %1\n\t"
"add\t%0, %0, %3\n\t"
"cmp.c\t%3, %0\n\t"
"lw\t%3, [%1, 8]\n\t"
"bleu\t1f\n\t"
"addi\t%0, 0x1\n\t"
"1:\n\t"
"add\t%0, %0, %3\n\t"
"cmp.c\t%3, %0\n\t"
"lw\t%3, [%1, 12]\n\t"
"bleu\t1f\n\t"
"addi\t%0, 0x1\n\t"
"1:add\t%0, %0, %3\n\t"
"cmp.c\t%3, %0\n\t"
"bleu\t1f\n\t"
"addi\t%0, 0x1\n"
"1:\tlw\t%3, [%1, 16]\n\t"
"addi\t%1, 4\n\t"
"add\t%0, %0, %3\n\t"
"cmp.c\t%3, %0\n\t"
"bleu\t2f\n\t"
"addi\t%0, 0x1\n"
"2:cmp.c\t%2, %1\n\t"
"bne\t1b\n\t"
".set\tr1\n\t"
".set optimize\n\t"
: "=&r" (sum), "=&r" (iph), "=&r" (ihl), "=&r" (dummy)
: "1" (iph), "2" (ihl));
return csum_fold(sum);
}
static inline __wsum
csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
unsigned short proto, __wsum sum)
{
unsigned long tmp = (ntohs(len) << 16) + proto * 256;
__asm__ __volatile__(
".set volatile\n\t"
"add\t%0, %0, %2\n\t"
"cmp.c\t%2, %0\n\t"
"bleu\t1f\n\t"
"addi\t%0, 0x1\n\t"
"1:\n\t"
"add\t%0, %0, %3\n\t"
"cmp.c\t%3, %0\n\t"
"bleu\t1f\n\t"
"addi\t%0, 0x1\n\t"
"1:\n\t"
"add\t%0, %0, %4\n\t"
"cmp.c\t%4, %0\n\t"
"bleu\t1f\n\t"
"addi\t%0, 0x1\n\t"
"1:\n\t"
".set optimize\n\t"
: "=r" (sum)
: "0" (daddr), "r"(saddr),
"r" (tmp),
"r" (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, unsigned short len,
unsigned short 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 unsigned short ip_compute_csum(const void *buff, int len)
{
return csum_fold(csum_partial(buff, 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, unsigned short proto,
__wsum sum)
{
__asm__ __volatile__(
".set\tnoreorder\t\t\t# csum_ipv6_magic\n\t"
".set\tnoat\n\t"
"addu\t%0, %5\t\t\t# proto (long in network byte order)\n\t"
"sltu\t$1, %0, %5\n\t"
"addu\t%0, $1\n\t"
"addu\t%0, %6\t\t\t# csum\n\t"
"sltu\t$1, %0, %6\n\t"
"lw\t%1, 0(%2)\t\t\t# four words source address\n\t"
"addu\t%0, $1\n\t"
"addu\t%0, %1\n\t"
"sltu\t$1, %0, %1\n\t"
"lw\t%1, 4(%2)\n\t"
"addu\t%0, $1\n\t"
"addu\t%0, %1\n\t"
"sltu\t$1, %0, %1\n\t"
"lw\t%1, 8(%2)\n\t"
"addu\t%0, $1\n\t"
"addu\t%0, %1\n\t"
"sltu\t$1, %0, %1\n\t"
"lw\t%1, 12(%2)\n\t"
"addu\t%0, $1\n\t"
"addu\t%0, %1\n\t"
"sltu\t$1, %0, %1\n\t"
"lw\t%1, 0(%3)\n\t"
"addu\t%0, $1\n\t"
"addu\t%0, %1\n\t"
"sltu\t$1, %0, %1\n\t"
"lw\t%1, 4(%3)\n\t"
"addu\t%0, $1\n\t"
"addu\t%0, %1\n\t"
"sltu\t$1, %0, %1\n\t"
"lw\t%1, 8(%3)\n\t"
"addu\t%0, $1\n\t"
"addu\t%0, %1\n\t"
"sltu\t$1, %0, %1\n\t"
"lw\t%1, 12(%3)\n\t"
"addu\t%0, $1\n\t"
"addu\t%0, %1\n\t"
"sltu\t$1, %0, %1\n\t"
"addu\t%0, $1\t\t\t# Add final carry\n\t"
".set\tnoat\n\t"
".set\tnoreorder"
: "=r" (sum), "=r" (proto)
: "r" (saddr), "r" (daddr),
"0" (htonl(len)), "1" (htonl(proto)), "r" (sum));
return csum_fold(sum);
}
#endif /* _ASM_SCORE_CHECKSUM_H */
|
