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
|
/* umac-poly128.c
*/
/* nettle, low-level cryptographics library
*
* Copyright (C) 2013 Niels Möller
*
* The nettle library is free software; you can redistribute it and/or modify
* it under the terms of the GNU Lesser General Public License as published by
* the Free Software Foundation; either version 2.1 of the License, or (at your
* option) any later version.
*
* The nettle library 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 Lesser General Public
* License for more details.
*
* You should have received a copy of the GNU Lesser General Public License
* along with the nettle library; see the file COPYING.LIB. If not, write to
* the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
* MA 02111-1301, USA.
*/
#if HAVE_CONFIG_H
# include "config.h"
#endif
#include <assert.h>
#include "umac.h"
#define HI(x) (x >> 32)
#define LO(x) (x & 0xffffffffUL)
static void
poly128_mul (const uint32_t *k, uint64_t *y)
{
uint64_t y0,y1,y2,y3,p0,p1,p2,p3,m0,m1,m2;
y0 = LO (y[1]);
y1 = HI (y[1]);
y2 = LO (y[0]);
y3 = HI (y[0]);
p0 = y0 * k[3];
m0 = y0 * k[2] + y1 * k[3];
p1 = y0 * k[1] + y1 * k[2] + y2 * k[3];
m1 = y0 * k[0] + y1 * k[1] + y2 * k[2] + y3 * k[3];
p2 = y1 * k[0] + y2 * k[1] + y3 * k[2];
m2 = y2 * k[0] + y3 * k[1];
p3 = y3 * k[0];
/* Collaps to 4 64-bit words,
+---+---+---+---+
| p3| p2| p1| p0|
+-+-+-+-+-+-+-+-+
+ | m2| m1| m0|
-+-+-+-+-+-+-+-+-+
*/
/* But it's convenient to reduce (p3,p2,p1,p0) and (m2,m1,m0) mod p first.*/
m1 += UMAC_P128_OFFSET * HI(p3);
p1 += UMAC_P128_OFFSET * (LO(p3) + HI(m2));
m0 += UMAC_P128_OFFSET * (HI(p2) + LO(m2));
p0 += UMAC_P128_OFFSET * (LO(p2) + HI(m1));
/* Left to add
+---+---+
| p1| p0|
+-+-+-+-+
m1| m0|
+-+---+
*/
/* First add high parts, with no possibilities for carries */
p1 += m0 >> 32;
m0 <<= 32;
m1 <<= 32;
/* Remains:
+---+---+
| p1| p0|
+-+-+---+
+| m1| m0|
-+---+---+
*/
p0 += m0;
p1 += (p0 < m0);
p1 += m1;
if (p1 < m1)
{
p0 += UMAC_P128_OFFSET;
p1 += (p0 < UMAC_P128_OFFSET);
}
y[0] = p1;
y[1] = p0;
}
void
_umac_poly128 (const uint32_t *k, uint64_t *y, uint64_t mh, uint64_t ml)
{
uint64_t yh, yl, cy;
if ( (mh >> 32) == 0xffffffff)
{
poly128_mul (k, y);
if (y[1] > 0)
y[1]--;
else if (y[0] > 0)
{
y[0]--;
y[1] = UMAC_P128_HI;
}
else
{
y[0] = UMAC_P128_HI;
y[1] = UMAC_P128_LO-1;
}
mh -= (ml < UMAC_P128_OFFSET);
ml -= UMAC_P128_OFFSET;
}
assert (mh < UMAC_P128_HI || ml < UMAC_P128_LO);
poly128_mul (k, y);
yl = y[1] + ml;
cy = (yl < ml);
yh = y[0] + cy;
cy = (yh < cy);
yh += mh;
cy += (yh < mh);
assert (cy <= 1);
if (cy)
{
yl += UMAC_P128_OFFSET;
yh += yl < UMAC_P128_OFFSET;
}
y[0] = yh;
y[1] = yl;
}
|
