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
|
/* aes256.h */
/* Hongjun Wu, January 2007*/
#include "ecrypt-sync.h"
#include "aes-table.h"
#include <stdio.h>
#ifdef NATIVE_LITTLE_ENDIAN
# define LEROT(X, S) ((uint8_t) ((uint32_t)(X) >> (S)))
# define SWP32(X) (X)
#elif defined(NATIVE_BIG_ENDIAN)
# define LEROT(X, S) ((uint8_t) ((uint32_t)(X) >> (24 - (S))))
# define SWP32(X) ((uint32_t)((((uint32_t)(X) & 0xff000000) >> 24) | \
(((uint32_t)(X) & 0x00ff0000) >> 8) | \
(((uint32_t)(X) & 0x0000ff00) << 8) | \
(((uint32_t)(X) & 0x000000ff) << 24)))
#else
# error Unsupported byte ordering
#endif
#define first_round(ctx,x0,y0) { \
u32 z0,t0,tem0; \
z0 = (x0) ^ ctx->round_key[0][0]; \
t0 = LEROT(z0, 0); \
tem0 = T0[t0]; \
(y0) = tem0 ^ ctx->first_round_output_x0; \
}
#define second_round(ctx,x0,y0,y1,y2,y3) { \
u32 t0,t7,t10,t13; \
u32 tem0,tem7,tem10,tem13; \
t0 = LEROT(x0, 0); \
tem0 = T0[t0]; \
(y0) = tem0 ^ ctx->second_round_output[0]; \
t7 = LEROT(x0, 24); \
tem7 = T3[t7]; \
(y1) = tem7 ^ ctx->second_round_output[1]; \
t10 = LEROT(x0, 16); \
tem10 = T2[t10]; \
(y2) = tem10 ^ ctx->second_round_output[2]; \
t13 = LEROT(x0, 8); \
tem13 = T1[t13];\
(y3) = tem13 ^ ctx->second_round_output[3]; \
}
#define round(ctx,x0,x1,x2,x3,y0,y1,y2,y3,r) { \
u32 t0,t1,t2,t3; \
u32 t4,t5,t6,t7; \
u32 t8,t9,t10,t11; \
u32 t12,t13,t14,t15;\
u32 tem0,tem1,tem2,tem3; \
u32 tem4,tem5,tem6,tem7; \
u32 tem8,tem9,tem10,tem11; \
u32 tem12,tem13,tem14,tem15;\
\
t0 = LEROT(x0, 0); \
tem0 = T0[t0]; \
t1 = LEROT(x1, 8); \
tem1 = tem0 ^ T1[t1]; \
t2 = LEROT(x2, 16); \
tem2 = tem1 ^ T2[t2]; \
t3 = LEROT(x3, 24); \
tem3 = tem2 ^ T3[t3]; \
(y0) = tem3 ^ ctx->round_key[r][0]; \
\
t4 = LEROT(x1, 0); \
tem4 = T0[t4]; \
t5 = LEROT(x2, 8); \
tem5 = tem4 ^ T1[t5]; \
t6 = LEROT(x3, 16); \
tem6 = tem5 ^ T2[t6]; \
t7 = LEROT(x0, 24); \
tem7 = tem6 ^ T3[t7]; \
(y1) = tem7 ^ ctx->round_key[r][1]; \
\
t8 = LEROT(x2, 0); \
tem8 = T0[t8]; \
t9 = LEROT(x3, 8); \
tem9 = tem8 ^ T1[t9]; \
t10 = LEROT(x0, 16); \
tem10 = tem9 ^ T2[t10]; \
t11 = LEROT(x1, 24); \
tem11 = tem10 ^ T3[t11];\
(y2) = tem11 ^ ctx->round_key[r][2]; \
\
t12 = LEROT(x3, 0); \
tem12 = T0[t12]; \
t13 = LEROT(x0, 8); \
tem13 = tem12 ^ T1[t13];\
t14 = LEROT(x1, 16); \
tem14 = tem13 ^ T2[t14];\
t15 = LEROT(x2, 24); \
tem15 = tem14 ^ T3[t15];\
(y3) = tem15 ^ ctx->round_key[r][3]; \
}
/* 22.14 cycles/byte*/
#define last_round(ctx,x0,x1,x2,x3,output,r) { \
u32 t0,t1,t2,t3; \
u32 t4,t5,t6,t7; \
u32 t8,t9,t10,t11; \
u32 t12,t13,t14,t15;\
\
t0 = LEROT(x0, 0); \
output[0] = Sbox[t0]; \
t7 = LEROT(x0, 24); \
output[7] = Sbox[t7]; \
t10 = LEROT(x0, 16); \
output[10] = Sbox[t10]; \
t13 = LEROT(x0, 8); \
output[13] = Sbox[t13]; \
\
t1 = LEROT(x1, 8); \
output[1] = Sbox[t1]; \
t4 = LEROT(x1, 0); \
output[4] = Sbox[t4]; \
t11 = LEROT(x1, 24); \
output[11] = Sbox[t11]; \
t14 = LEROT(x1, 16); \
output[14] = Sbox[t14]; \
\
t2 = LEROT(x2, 16); \
output[2] = Sbox[t2]; \
t5 = LEROT(x2, 8); \
output[5] = Sbox[t5]; \
t8 = LEROT(x2, 0); \
output[8] = Sbox[t8]; \
t15 = LEROT(x2, 24); \
output[15] = Sbox[t15]; \
\
t3 = LEROT(x3, 24); \
output[3] = Sbox[t3]; \
t6 = LEROT(x3, 16); \
output[6] = Sbox[t6]; \
t9 = LEROT(x3, 8); \
output[9] = Sbox[t9]; \
t12 = LEROT(x3, 0); \
output[12] = Sbox[t12]; \
}
#define aes256_enc_block(x,output,ctx) {\
u32 y0;\
u32 z0,z1,z2,z3;\
u32 a0,a1,a2,a3;\
u32 b0,b1,b2,b3;\
u32 c0,c1,c2,c3;\
u32 d0,d1,d2,d3;\
u32 e0,e1,e2,e3;\
u32 f0,f1,f2,f3;\
u32 g0,g1,g2,g3;\
u32 h0,h1,h2,h3;\
u32 i0,i1,i2,i3;\
u32 j0,j1,j2,j3;\
u32 k0,k1,k2,k3;\
first_round(ctx,x[0],y0);\
second_round(ctx,y0,z0,z1,z2,z3);\
round(ctx,z0,z1,z2,z3,a0,a1,a2,a3,3);\
round(ctx,a0,a1,a2,a3,b0,b1,b2,b3,4);\
round(ctx,b0,b1,b2,b3,c0,c1,c2,c3,5);\
round(ctx,c0,c1,c2,c3,d0,d1,d2,d3,6);\
round(ctx,d0,d1,d2,d3,e0,e1,e2,e3,7);\
round(ctx,e0,e1,e2,e3,f0,f1,f2,f3,8);\
round(ctx,f0,f1,f2,f3,g0,g1,g2,g3,9);\
round(ctx,g0,g1,g2,g3,h0,h1,h2,h3,10);\
round(ctx,h0,h1,h2,h3,i0,i1,i2,i3,11);\
round(ctx,i0,i1,i2,i3,j0,j1,j2,j3,12);\
round(ctx,j0,j1,j2,j3,k0,k1,k2,k3,13);\
last_round(ctx,k0,k1,k2,k3,(output),14);\
}
|
