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
|
/*
* 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>
* Pentium Pro/II routines:
* Alexander Kjeldaas <astor@guardian.no>
* Finn Arne Gangstad <finnag@guardian.no>
* Lots of code moved from tcp.c and ip.c; see those files
* for more names.
*
* Changes: Ingo Molnar, converted csum_partial_copy() to 2.1 exception
* handling.
* Andi Kleen, add zeroing on error
* converted to pure assembler
*
* 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 <asm/errno.h>
#include <asm/asm.h>
#include <asm/export.h>
/*
* computes a partial checksum, e.g. for TCP/UDP fragments
*/
/*
unsigned int csum_partial(const unsigned char * buff, int len, unsigned int sum)
*/
.text
.align 4
.globl csum_partial
#ifndef CONFIG_X86_USE_PPRO_CHECKSUM
/*
* Experiments with Ethernet and SLIP connections show that buff
* is aligned on either a 2-byte or 4-byte boundary. We get at
* least a twofold speedup on 486 and Pentium if it is 4-byte aligned.
* Fortunately, it is easy to convert 2-byte alignment to 4-byte
* alignment for the unrolled loop.
*/
csum_partial:
pushl %esi
pushl %ebx
movl 20(%esp),%eax # Function arg: unsigned int sum
movl 16(%esp),%ecx # Function arg: int len
movl 12(%esp),%esi # Function arg: unsigned char *buff
testl $2, %esi # Check alignment.
jz 2f # Jump if alignment is ok.
subl $2, %ecx # Alignment uses up two bytes.
jae 1f # Jump if we had at least two bytes.
addl $2, %ecx # ecx was < 2. Deal with it.
jmp 4f
1: movw (%esi), %bx
addl $2, %esi
addw %bx, %ax
adcl $0, %eax
2:
movl %ecx, %edx
shrl $5, %ecx
jz 2f
testl %esi, %esi
1: movl (%esi), %ebx
adcl %ebx, %eax
movl 4(%esi), %ebx
adcl %ebx, %eax
movl 8(%esi), %ebx
adcl %ebx, %eax
movl 12(%esi), %ebx
adcl %ebx, %eax
movl 16(%esi), %ebx
adcl %ebx, %eax
movl 20(%esi), %ebx
adcl %ebx, %eax
movl 24(%esi), %ebx
adcl %ebx, %eax
movl 28(%esi), %ebx
adcl %ebx, %eax
lea 32(%esi), %esi
dec %ecx
jne 1b
adcl $0, %eax
2: movl %edx, %ecx
andl $0x1c, %edx
je 4f
shrl $2, %edx # This clears CF
3: adcl (%esi), %eax
lea 4(%esi), %esi
dec %edx
jne 3b
adcl $0, %eax
4: andl $3, %ecx
jz 7f
cmpl $2, %ecx
jb 5f
movw (%esi),%cx
leal 2(%esi),%esi
je 6f
shll $16,%ecx
5: movb (%esi),%cl
6: addl %ecx,%eax
adcl $0, %eax
7:
popl %ebx
popl %esi
ret
#else
/* Version for PentiumII/PPro */
csum_partial:
pushl %esi
pushl %ebx
movl 20(%esp),%eax # Function arg: unsigned int sum
movl 16(%esp),%ecx # Function arg: int len
movl 12(%esp),%esi # Function arg: const unsigned char *buf
testl $2, %esi
jnz 30f
10:
movl %ecx, %edx
movl %ecx, %ebx
andl $0x7c, %ebx
shrl $7, %ecx
addl %ebx,%esi
shrl $2, %ebx
negl %ebx
lea 45f(%ebx,%ebx,2), %ebx
testl %esi, %esi
jmp *%ebx
# Handle 2-byte-aligned regions
20: addw (%esi), %ax
lea 2(%esi), %esi
adcl $0, %eax
jmp 10b
30: subl $2, %ecx
ja 20b
je 32f
movzbl (%esi),%ebx # csumming 1 byte, 2-aligned
addl %ebx, %eax
adcl $0, %eax
jmp 80f
32:
addw (%esi), %ax # csumming 2 bytes, 2-aligned
adcl $0, %eax
jmp 80f
40:
addl -128(%esi), %eax
adcl -124(%esi), %eax
adcl -120(%esi), %eax
adcl -116(%esi), %eax
adcl -112(%esi), %eax
adcl -108(%esi), %eax
adcl -104(%esi), %eax
adcl -100(%esi), %eax
adcl -96(%esi), %eax
adcl -92(%esi), %eax
adcl -88(%esi), %eax
adcl -84(%esi), %eax
adcl -80(%esi), %eax
adcl -76(%esi), %eax
adcl -72(%esi), %eax
adcl -68(%esi), %eax
adcl -64(%esi), %eax
adcl -60(%esi), %eax
adcl -56(%esi), %eax
adcl -52(%esi), %eax
adcl -48(%esi), %eax
adcl -44(%esi), %eax
adcl -40(%esi), %eax
adcl -36(%esi), %eax
adcl -32(%esi), %eax
adcl -28(%esi), %eax
adcl -24(%esi), %eax
adcl -20(%esi), %eax
adcl -16(%esi), %eax
adcl -12(%esi), %eax
adcl -8(%esi), %eax
adcl -4(%esi), %eax
45:
lea 128(%esi), %esi
adcl $0, %eax
dec %ecx
jge 40b
movl %edx, %ecx
50: andl $3, %ecx
jz 80f
# Handle the last 1-3 bytes without jumping
notl %ecx # 1->2, 2->1, 3->0, higher bits are masked
movl $0xffffff,%ebx # by the shll and shrl instructions
shll $3,%ecx
shrl %cl,%ebx
andl -128(%esi),%ebx # esi is 4-aligned so should be ok
addl %ebx,%eax
adcl $0,%eax
80:
popl %ebx
popl %esi
ret
#endif
EXPORT_SYMBOL(csum_partial)
|
