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
|
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* MIPS specific IP/TCP/UDP checksumming routines
*
* Authors: Ralf Baechle, <ralf@waldorf-gmbh.de>
* Lots of code moved from tcp.c and ip.c; see those files
* for more names.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <net/checksum.h>
#include <asm/string.h>
/*
* computes a partial checksum, e.g. for TCP/UDP fragments
*/
unsigned int csum_partial(const unsigned char *buff, int len, unsigned int sum)
{
unsigned long scratch1;
unsigned long scratch2;
/*
* The GCC generated code for handling carry bits makes
* it strongly desirable to do this in assembler!
*/
__asm__("
.set noreorder
.set noat
andi $1,%5,2 # Check alignment
beqz $1,2f # Branch if ok
subu $1,%4,2 # delay slot, Alignment uses up two bytes
bgez $1,1f # Jump if we had at least two bytes
move %4,$1 # delay slot
j 4f
addiu %4,2 # delay slot; len was < 2. Deal with it
1: lw %2,(%5)
addiu %4,2
addu %0,%2
sltu $1,%0,%2
addu %0,$1
2: move %1,%4
srl %1,%1,5
beqz %1,2f
sll %1,%1,5 # delay slot
addu %1,%5
1: lw %2,0(%5)
addu %5,32
addu %0,%2
sltu $1,%0,%2
lw %2,-28(%5)
addu %0,$1
addu %0,%2
sltu $1,%0,%2
lw %2,-24(%5)
addu %0,$1
addu %0,%2
sltu $1,%0,%2
lw %2,-20(%5)
addu %0,$1
addu %0,%2
sltu $1,%0,%2
lw %2,-16(%5)
addu %0,$1
addu %0,%2
sltu $1,%0,%2
lw %2,-12(%5)
addu %0,$1
addu %0,%2
sltu $1,%0,%2
lw %2,-8(%5)
addu %0,$1
addu %0,%2
sltu $1,%0,%2
lw %2,-4(%5)
addu %0,$1
addu %0,%2
sltu $1,%0,%2
bne %5,%1,1b
addu %0,$1 # delay slot
2: andi %1,%4,0x1c
srl %1,%1,2
beqz %1,4f
addu %1,%5 # delay slot
3: lw %2,0(%5)
addu %5,4
addu %0,%2
sltu $1,%0,%2
bne %5,%1,3b
addu %0,$1 # delay slot
4: andi $1,%3,2
beqz $1,5f
move %2,$0 # delay slot
lhu %2,(%5)
addiu %5,2
5: andi $1,%3,1
beqz $1,6f
sll %1,16 # delay slot
lbu %1,(%5)
nop # NOP ALERT (spit, gasp)
6: or %2,%1
addu %0,%2
sltu $1,%0,%2
addu %0,$1
7: .set at
.set reorder"
: "=r"(sum), "=r" (scratch1), "=r" (scratch2)
: "0"(sum), "r"(len), "r"(buff)
: "$1");
return sum;
}
/*
* copy from fs while checksumming, otherwise like csum_partial
*/
unsigned int csum_partial_copy(const char *src, char *dst,
int len, int sum)
{
/*
* It's 2:30 am and I don't feel like doing it real ...
* This is lots slower than the real thing (tm)
*/
sum = csum_partial(src, len, sum);
memcpy(dst, src, len);
return sum;
}
|
