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
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
|
/*
* 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.
*
* IP/TCP/UDP checksumming routines
*
* Authors: Jorge Cwik, <jorge@laser.satlink.net>
* Arnt Gulbrandsen, <agulbra@nvg.unit.no>
* Tom May, <ftom@netcom.com>
* Andreas Schwab, <schwab@issan.informatik.uni-dortmund.de>
* Lots of code moved from tcp.c and ip.c; see those files
* for more names.
*
* 03/02/96 Jes Sorensen, Andreas Schwab, Roman Hodek:
* Fixed some nasty bugs, causing some horrible crashes.
* A: At some points, the sum (%0) was used as
* length-counter instead of the length counter
* (%1). Thanks to Roman Hodek for pointing this out.
* B: GCC seems to mess up if one uses too many
* data-registers to hold input values and one tries to
* specify d0 and d1 as scratch registers. Letting gcc choose these
* registers itself solves the problem.
*
* 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>
/*
* 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 tmp1, tmp2;
/*
* Experiments with ethernet and slip connections show that buff
* is aligned on either a 2-byte or 4-byte boundary.
*/
__asm__("movel %2,%3\n\t"
"btst #1,%3\n\t" /* Check alignment */
"jeq 2f\n\t"
"subql #2,%1\n\t" /* buff%4==2: treat first word */
"jgt 1f\n\t"
"addql #2,%1\n\t" /* len was == 2, treat only rest */
"jra 4f\n"
"1:\t"
"addw %2@+,%0\n\t" /* add first word to sum */
"clrl %3\n\t"
"addxl %3,%0\n" /* add X bit */
"2:\t"
/* unrolled loop for the main part: do 8 longs at once */
"movel %1,%3\n\t" /* save len in tmp1 */
"lsrl #5,%1\n\t" /* len/32 */
"jeq 2f\n\t" /* not enough... */
"subql #1,%1\n"
"1:\t"
"movel %2@+,%4\n\t"
"addxl %4,%0\n\t"
"movel %2@+,%4\n\t"
"addxl %4,%0\n\t"
"movel %2@+,%4\n\t"
"addxl %4,%0\n\t"
"movel %2@+,%4\n\t"
"addxl %4,%0\n\t"
"movel %2@+,%4\n\t"
"addxl %4,%0\n\t"
"movel %2@+,%4\n\t"
"addxl %4,%0\n\t"
"movel %2@+,%4\n\t"
"addxl %4,%0\n\t"
"movel %2@+,%4\n\t"
"addxl %4,%0\n\t"
"dbra %1,1b\n\t"
"clrl %4\n\t"
"addxl %4,%0\n\t" /* add X bit */
"clrw %1\n\t"
"subql #1,%1\n\t"
"jcc 1b\n"
"2:\t"
"movel %3,%1\n\t" /* restore len from tmp1 */
"andw #0x1c,%3\n\t" /* number of rest longs */
"jeq 4f\n\t"
"lsrw #2,%3\n\t"
"subqw #1,%3\n"
"3:\t"
/* loop for rest longs */
"movel %2@+,%4\n\t"
"addxl %4,%0\n\t"
"dbra %3,3b\n\t"
"clrl %4\n\t"
"addxl %4,%0\n" /* add X bit */
"4:\t"
/* now check for rest bytes that do not fit into longs */
"andw #3,%1\n\t"
"jeq 7f\n\t"
"clrl %4\n\t" /* clear tmp2 for rest bytes */
"subqw #2,%1\n\t"
"jlt 5f\n\t"
"movew %2@+,%4\n\t" /* have rest >= 2: get word */
"swap %4\n\t" /* into bits 16..31 */
"tstw %1\n\t" /* another byte? */
"jeq 6f\n"
"5:\t"
"moveb %2@,%4\n\t" /* have odd rest: get byte */
"lslw #8,%4\n\t" /* into bits 8..15; 16..31 untouched */
"6:\t"
"addl %4,%0\n\t" /* now add rest long to sum */
"clrl %4\n\t"
"addxl %4,%0\n" /* add X bit */
"7:\t"
: "=d" (sum), "=d" (len), "=a" (buff),
"=&d" (tmp1), "=&d" (tmp2)
: "0" (sum), "1" (len), "2" (buff)
);
return(sum);
}
/*
* copy from fs while checksumming, otherwise like csum_partial
*/
unsigned int
csum_partial_copy_fromuser(const char *src, char *dst, int len, int sum)
{
unsigned long tmp1, tmp2;
__asm__("movel %2,%4\n\t"
"btst #1,%4\n\t" /* Check alignment */
"jeq 2f\n\t"
"subql #2,%1\n\t" /* buff%4==2: treat first word */
"jgt 1f\n\t"
"addql #2,%1\n\t" /* len was == 2, treat only rest */
"jra 4f\n"
"1:\t"
"movesw %2@+,%4\n\t" /* add first word to sum */
"addw %4,%0\n\t"
"movew %4,%3@+\n\t"
"clrl %4\n\t"
"addxl %4,%0\n" /* add X bit */
"2:\t"
/* unrolled loop for the main part: do 8 longs at once */
"movel %1,%4\n\t" /* save len in tmp1 */
"lsrl #5,%1\n\t" /* len/32 */
"jeq 2f\n\t" /* not enough... */
"subql #1,%1\n"
"1:\t"
"movesl %2@+,%5\n\t"
"addxl %5,%0\n\t"
"movel %5,%3@+\n\t"
"movesl %2@+,%5\n\t"
"addxl %5,%0\n\t"
"movel %5,%3@+\n\t"
"movesl %2@+,%5\n\t"
"addxl %5,%0\n\t"
"movel %5,%3@+\n\t"
"movesl %2@+,%5\n\t"
"addxl %5,%0\n\t"
"movel %5,%3@+\n\t"
"movesl %2@+,%5\n\t"
"addxl %5,%0\n\t"
"movel %5,%3@+\n\t"
"movesl %2@+,%5\n\t"
"addxl %5,%0\n\t"
"movel %5,%3@+\n\t"
"movesl %2@+,%5\n\t"
"addxl %5,%0\n\t"
"movel %5,%3@+\n\t"
"movesl %2@+,%5\n\t"
"addxl %5,%0\n\t"
"movel %5,%3@+\n\t"
"dbra %1,1b\n\t"
"clrl %5\n\t"
"addxl %5,%0\n\t" /* add X bit */
"clrw %1\n\t"
"subql #1,%1\n\t"
"jcc 1b\n"
"2:\t"
"movel %4,%1\n\t" /* restore len from tmp1 */
"andw #0x1c,%4\n\t" /* number of rest longs */
"jeq 4f\n\t"
"lsrw #2,%4\n\t"
"subqw #1,%4\n"
"3:\t"
/* loop for rest longs */
"movesl %2@+,%5\n\t"
"addxl %5,%0\n\t"
"movel %5,%3@+\n\t"
"dbra %4,3b\n\t"
"clrl %5\n\t"
"addxl %5,%0\n" /* add X bit */
"4:\t"
/* now check for rest bytes that do not fit into longs */
"andw #3,%1\n\t"
"jeq 7f\n\t"
"clrl %5\n\t" /* clear tmp2 for rest bytes */
"subqw #2,%1\n\t"
"jlt 5f\n\t"
"movesw %2@+,%5\n\t" /* have rest >= 2: get word */
"movew %5,%3@+\n\t"
"swap %5\n\t" /* into bits 16..31 */
"tstw %1\n\t" /* another byte? */
"jeq 6f\n"
"5:\t"
"movesb %2@,%5\n\t" /* have odd rest: get byte */
"moveb %5,%3@+\n\t"
"lslw #8,%5\n\t" /* into bits 8..15; 16..31 untouched */
"6:\t"
"addl %5,%0\n\t" /* now add rest long to sum */
"clrl %5\n\t"
"addxl %5,%0\n" /* add X bit */
"7:\t"
: "=d" (sum), "=d" (len), "=a" (src), "=a" (dst),
"=&d" (tmp1), "=&d" (tmp2)
: "0" (sum), "1" (len), "2" (src), "3" (dst)
);
return(sum);
}
/*
* copy from ds while checksumming, otherwise like csum_partial
*/
unsigned int
csum_partial_copy(const char *src, char *dst, int len, int sum)
{
unsigned long tmp1, tmp2;
__asm__("movel %2,%4\n\t"
"btst #1,%4\n\t" /* Check alignment */
"jeq 2f\n\t"
"subql #2,%1\n\t" /* buff%4==2: treat first word */
"jgt 1f\n\t"
"addql #2,%1\n\t" /* len was == 2, treat only rest */
"jra 4f\n"
"1:\t"
"movew %2@+,%4\n\t" /* add first word to sum */
"addw %4,%0\n\t"
"movew %4,%3@+\n\t"
"clrl %4\n\t"
"addxl %4,%0\n" /* add X bit */
"2:\t"
/* unrolled loop for the main part: do 8 longs at once */
"movel %1,%4\n\t" /* save len in tmp1 */
"lsrl #5,%1\n\t" /* len/32 */
"jeq 2f\n\t" /* not enough... */
"subql #1,%1\n"
"1:\t"
"movel %2@+,%5\n\t"
"addxl %5,%0\n\t"
"movel %5,%3@+\n\t"
"movel %2@+,%5\n\t"
"addxl %5,%0\n\t"
"movel %5,%3@+\n\t"
"movel %2@+,%5\n\t"
"addxl %5,%0\n\t"
"movel %5,%3@+\n\t"
"movel %2@+,%5\n\t"
"addxl %5,%0\n\t"
"movel %5,%3@+\n\t"
"movel %2@+,%5\n\t"
"addxl %5,%0\n\t"
"movel %5,%3@+\n\t"
"movel %2@+,%5\n\t"
"addxl %5,%0\n\t"
"movel %5,%3@+\n\t"
"movel %2@+,%5\n\t"
"addxl %5,%0\n\t"
"movel %5,%3@+\n\t"
"movel %2@+,%5\n\t"
"addxl %5,%0\n\t"
"movel %5,%3@+\n\t"
"dbra %1,1b\n\t"
"clrl %5\n\t"
"addxl %5,%0\n\t" /* add X bit */
"clrw %1\n\t"
"subql #1,%1\n\t"
"jcc 1b\n"
"2:\t"
"movel %4,%1\n\t" /* restore len from tmp1 */
"andw #0x1c,%4\n\t" /* number of rest longs */
"jeq 4f\n\t"
"lsrw #2,%4\n\t"
"subqw #1,%4\n"
"3:\t"
/* loop for rest longs */
"movel %2@+,%5\n\t"
"addxl %5,%0\n\t"
"movel %5,%3@+\n\t"
"dbra %4,3b\n\t"
"clrl %5\n\t"
"addxl %5,%0\n" /* add X bit */
"4:\t"
/* now check for rest bytes that do not fit into longs */
"andw #3,%1\n\t"
"jeq 7f\n\t"
"clrl %5\n\t" /* clear tmp2 for rest bytes */
"subqw #2,%1\n\t"
"jlt 5f\n\t"
"movew %2@+,%5\n\t" /* have rest >= 2: get word */
"movew %5,%3@+\n\t"
"swap %5\n\t" /* into bits 16..31 */
"tstw %1\n\t" /* another byte? */
"jeq 6f\n"
"5:\t"
"moveb %2@,%5\n\t" /* have odd rest: get byte */
"moveb %5,%3@+\n\t"
"lslw #8,%5\n" /* into bits 8..15; 16..31 untouched */
"6:\t"
"addl %5,%0\n\t" /* now add rest long to sum */
"clrl %5\n\t"
"addxl %5,%0\n" /* add X bit */
"7:\t"
: "=d" (sum), "=d" (len), "=a" (src), "=a" (dst),
"=&d" (tmp1), "=&d" (tmp2)
: "0" (sum), "1" (len), "2" (src), "3" (dst)
);
return(sum);
}
|
