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
|
/* i80586 rshift
* Copyright (C) 1998 Free Software Foundation, Inc.
* Copyright (C) 1992, 1994 Free Software Foundation, Inc.
*
* This file is part of GNUPG.
*
* GNUPG 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.
*
* GNUPG is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
*
* Note: This code is heavily based on the GNU MP Library.
* Actually it's the same code with only minor changes in the
* way the data is stored; this is to support the abstraction
* of an optional secure memory allocation which may be used
* to avoid revealing of sensitive data due to paging etc.
* The GNU MP Library itself is published under the LGPL;
* however I decided to publish this code under the plain GPL.
*/
#include "sysdep.h"
#include "asm-syntax.h"
/*******************
* mpi_limb_t
* mpihelp_rshift( mpi_ptr_t wp, (sp + 4)
* mpi_ptr_t up, (sp + 8)
* mpi_size_t usize, (sp + 12)
* unsigned cnt) (sp + 16)
*/
.text
ALIGN (3)
.globl C_SYMBOL_NAME(mpihelp_rshift)
C_SYMBOL_NAME(mpihelp_rshift:)
pushl %edi
pushl %esi
pushl %ebx
pushl %ebp
movl 20(%esp),%edi /* res_ptr */
movl 24(%esp),%esi /* s_ptr */
movl 28(%esp),%ebp /* size */
movl 32(%esp),%ecx /* cnt */
/* We can use faster code for shift-by-1 under certain conditions. */
cmp $1,%ecx
jne Rnormal
leal 4(%edi),%eax
cmpl %esi,%eax
jnc Rspecial /* jump if res_ptr + 1 >= s_ptr */
leal (%edi,%ebp,4),%eax
cmpl %eax,%esi
jnc Rspecial /* jump if s_ptr >= res_ptr + size */
Rnormal:
movl (%esi),%edx
addl $4,%esi
xorl %eax,%eax
shrdl %cl,%edx,%eax /* compute carry limb */
pushl %eax /* push carry limb onto stack */
decl %ebp
pushl %ebp
shrl $3,%ebp
jz Rend
movl (%edi),%eax /* fetch destination cache line */
ALIGN (2)
Roop: movl 28(%edi),%eax /* fetch destination cache line */
movl %edx,%ebx
movl (%esi),%eax
movl 4(%esi),%edx
shrdl %cl,%eax,%ebx
shrdl %cl,%edx,%eax
movl %ebx,(%edi)
movl %eax,4(%edi)
movl 8(%esi),%ebx
movl 12(%esi),%eax
shrdl %cl,%ebx,%edx
shrdl %cl,%eax,%ebx
movl %edx,8(%edi)
movl %ebx,12(%edi)
movl 16(%esi),%edx
movl 20(%esi),%ebx
shrdl %cl,%edx,%eax
shrdl %cl,%ebx,%edx
movl %eax,16(%edi)
movl %edx,20(%edi)
movl 24(%esi),%eax
movl 28(%esi),%edx
shrdl %cl,%eax,%ebx
shrdl %cl,%edx,%eax
movl %ebx,24(%edi)
movl %eax,28(%edi)
addl $32,%esi
addl $32,%edi
decl %ebp
jnz Roop
Rend: popl %ebp
andl $7,%ebp
jz Rend2
Roop2: movl (%esi),%eax
shrdl %cl,%eax,%edx /* compute result limb */
movl %edx,(%edi)
movl %eax,%edx
addl $4,%esi
addl $4,%edi
decl %ebp
jnz Roop2
Rend2: shrl %cl,%edx /* compute most significant limb */
movl %edx,(%edi) /* store it */
popl %eax /* pop carry limb */
popl %ebp
popl %ebx
popl %esi
popl %edi
ret
/* We loop from least significant end of the arrays, which is only
permissable if the source and destination don't overlap, since the
function is documented to work for overlapping source and destination.
*/
Rspecial:
leal -4(%edi,%ebp,4),%edi
leal -4(%esi,%ebp,4),%esi
movl (%esi),%edx
subl $4,%esi
decl %ebp
pushl %ebp
shrl $3,%ebp
shrl $1,%edx
incl %ebp
decl %ebp
jz RLend
movl (%edi),%eax /* fetch destination cache line */
ALIGN (2)
RLoop: movl -28(%edi),%eax /* fetch destination cache line */
movl %edx,%ebx
movl (%esi),%eax
movl -4(%esi),%edx
rcrl $1,%eax
movl %ebx,(%edi)
rcrl $1,%edx
movl %eax,-4(%edi)
movl -8(%esi),%ebx
movl -12(%esi),%eax
rcrl $1,%ebx
movl %edx,-8(%edi)
rcrl $1,%eax
movl %ebx,-12(%edi)
movl -16(%esi),%edx
movl -20(%esi),%ebx
rcrl $1,%edx
movl %eax,-16(%edi)
rcrl $1,%ebx
movl %edx,-20(%edi)
movl -24(%esi),%eax
movl -28(%esi),%edx
rcrl $1,%eax
movl %ebx,-24(%edi)
rcrl $1,%edx
movl %eax,-28(%edi)
leal -32(%esi),%esi /* use leal not to clobber carry */
leal -32(%edi),%edi
decl %ebp
jnz RLoop
RLend: popl %ebp
sbbl %eax,%eax /* save carry in %eax */
andl $7,%ebp
jz RLend2
addl %eax,%eax /* restore carry from eax */
RLoop2: movl %edx,%ebx
movl (%esi),%edx
rcrl $1,%edx
movl %ebx,(%edi)
leal -4(%esi),%esi /* use leal not to clobber carry */
leal -4(%edi),%edi
decl %ebp
jnz RLoop2
jmp RL1
RLend2: addl %eax,%eax /* restore carry from eax */
RL1: movl %edx,(%edi) /* store last limb */
movl $0,%eax
rcrl $1,%eax
popl %ebp
popl %ebx
popl %esi
popl %edi
ret
|
