1 /* { dg-do compile } */
2 /* { dg-options "-Os -Wstack-usage=2500" } */
3 
4 #define SHA_LONG64 unsigned long long
5 #define U64(C)     C##ULL
6 
7 #define SHA_LBLOCK      16
8 #define SHA512_CBLOCK   (SHA_LBLOCK*8)
9 
10 typedef struct SHA512state_st {
11     SHA_LONG64 h[8];
12     SHA_LONG64 Nl, Nh;
13     union {
14         SHA_LONG64 d[SHA_LBLOCK];
15         unsigned char p[SHA512_CBLOCK];
16     } u;
17     unsigned int num, md_len;
18 } SHA512_CTX;
19 
20 static const SHA_LONG64 K512[80] = {
21     U64(0x428a2f98d728ae22), U64(0x7137449123ef65cd),
22     U64(0xb5c0fbcfec4d3b2f), U64(0xe9b5dba58189dbbc),
23     U64(0x3956c25bf348b538), U64(0x59f111f1b605d019),
24     U64(0x923f82a4af194f9b), U64(0xab1c5ed5da6d8118),
25     U64(0xd807aa98a3030242), U64(0x12835b0145706fbe),
26     U64(0x243185be4ee4b28c), U64(0x550c7dc3d5ffb4e2),
27     U64(0x72be5d74f27b896f), U64(0x80deb1fe3b1696b1),
28     U64(0x9bdc06a725c71235), U64(0xc19bf174cf692694),
29     U64(0xe49b69c19ef14ad2), U64(0xefbe4786384f25e3),
30     U64(0x0fc19dc68b8cd5b5), U64(0x240ca1cc77ac9c65),
31     U64(0x2de92c6f592b0275), U64(0x4a7484aa6ea6e483),
32     U64(0x5cb0a9dcbd41fbd4), U64(0x76f988da831153b5),
33     U64(0x983e5152ee66dfab), U64(0xa831c66d2db43210),
34     U64(0xb00327c898fb213f), U64(0xbf597fc7beef0ee4),
35     U64(0xc6e00bf33da88fc2), U64(0xd5a79147930aa725),
36     U64(0x06ca6351e003826f), U64(0x142929670a0e6e70),
37     U64(0x27b70a8546d22ffc), U64(0x2e1b21385c26c926),
38     U64(0x4d2c6dfc5ac42aed), U64(0x53380d139d95b3df),
39     U64(0x650a73548baf63de), U64(0x766a0abb3c77b2a8),
40     U64(0x81c2c92e47edaee6), U64(0x92722c851482353b),
41     U64(0xa2bfe8a14cf10364), U64(0xa81a664bbc423001),
42     U64(0xc24b8b70d0f89791), U64(0xc76c51a30654be30),
43     U64(0xd192e819d6ef5218), U64(0xd69906245565a910),
44     U64(0xf40e35855771202a), U64(0x106aa07032bbd1b8),
45     U64(0x19a4c116b8d2d0c8), U64(0x1e376c085141ab53),
46     U64(0x2748774cdf8eeb99), U64(0x34b0bcb5e19b48a8),
47     U64(0x391c0cb3c5c95a63), U64(0x4ed8aa4ae3418acb),
48     U64(0x5b9cca4f7763e373), U64(0x682e6ff3d6b2b8a3),
49     U64(0x748f82ee5defb2fc), U64(0x78a5636f43172f60),
50     U64(0x84c87814a1f0ab72), U64(0x8cc702081a6439ec),
51     U64(0x90befffa23631e28), U64(0xa4506cebde82bde9),
52     U64(0xbef9a3f7b2c67915), U64(0xc67178f2e372532b),
53     U64(0xca273eceea26619c), U64(0xd186b8c721c0c207),
54     U64(0xeada7dd6cde0eb1e), U64(0xf57d4f7fee6ed178),
55     U64(0x06f067aa72176fba), U64(0x0a637dc5a2c898a6),
56     U64(0x113f9804bef90dae), U64(0x1b710b35131c471b),
57     U64(0x28db77f523047d84), U64(0x32caab7b40c72493),
58     U64(0x3c9ebe0a15c9bebc), U64(0x431d67c49c100d4c),
59     U64(0x4cc5d4becb3e42b6), U64(0x597f299cfc657e2a),
60     U64(0x5fcb6fab3ad6faec), U64(0x6c44198c4a475817)
61 };
62 
63 #define B(x,j)    (((SHA_LONG64)(*(((const unsigned char *)(&x))+j)))<<((7-j)*8))
64 #define PULL64(x) (B(x,0)|B(x,1)|B(x,2)|B(x,3)|B(x,4)|B(x,5)|B(x,6)|B(x,7))
65 #define ROTR(x,s)       (((x)>>s) | (x)<<(64-s))
66 #define Sigma0(x)       (ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39))
67 #define Sigma1(x)       (ROTR((x),14) ^ ROTR((x),18) ^ ROTR((x),41))
68 #define sigma0(x)       (ROTR((x),1)  ^ ROTR((x),8)  ^ ((x)>>7))
69 #define sigma1(x)       (ROTR((x),19) ^ ROTR((x),61) ^ ((x)>>6))
70 #define Ch(x,y,z)       (((x) & (y)) ^ ((~(x)) & (z)))
71 #define Maj(x,y,z)      (((x) & (y)) ^ ((x) & (z)) ^ ((y) & (z)))
72 
73 #define ROUND_00_15(i,a,b,c,d,e,f,g,h)          do {    \
74         T1 += h + Sigma1(e) + Ch(e,f,g) + K512[i];      \
75         h = Sigma0(a) + Maj(a,b,c);                     \
76         d += T1;        h += T1;                } while (0)
77 #define ROUND_16_80(i,j,a,b,c,d,e,f,g,h,X)      do {    \
78         s0 = X[(j+1)&0x0f];     s0 = sigma0(s0);        \
79         s1 = X[(j+14)&0x0f];    s1 = sigma1(s1);        \
80         T1 = X[(j)&0x0f] += s0 + s1 + X[(j+9)&0x0f];    \
81         ROUND_00_15(i+j,a,b,c,d,e,f,g,h);               } while (0)
sha512_block_data_order(SHA512_CTX * ctx,const void * in,unsigned int num)82 void sha512_block_data_order(SHA512_CTX *ctx, const void *in,
83                                     unsigned int num)
84 {
85     const SHA_LONG64 *W = in;
86     SHA_LONG64 a, b, c, d, e, f, g, h, s0, s1, T1;
87     SHA_LONG64 X[16];
88     int i;
89 
90     while (num--) {
91 
92         a = ctx->h[0];
93         b = ctx->h[1];
94         c = ctx->h[2];
95         d = ctx->h[3];
96         e = ctx->h[4];
97         f = ctx->h[5];
98         g = ctx->h[6];
99         h = ctx->h[7];
100 
101         T1 = X[0] = PULL64(W[0]);
102         ROUND_00_15(0, a, b, c, d, e, f, g, h);
103         T1 = X[1] = PULL64(W[1]);
104         ROUND_00_15(1, h, a, b, c, d, e, f, g);
105         T1 = X[2] = PULL64(W[2]);
106         ROUND_00_15(2, g, h, a, b, c, d, e, f);
107         T1 = X[3] = PULL64(W[3]);
108         ROUND_00_15(3, f, g, h, a, b, c, d, e);
109         T1 = X[4] = PULL64(W[4]);
110         ROUND_00_15(4, e, f, g, h, a, b, c, d);
111         T1 = X[5] = PULL64(W[5]);
112         ROUND_00_15(5, d, e, f, g, h, a, b, c);
113         T1 = X[6] = PULL64(W[6]);
114         ROUND_00_15(6, c, d, e, f, g, h, a, b);
115         T1 = X[7] = PULL64(W[7]);
116         ROUND_00_15(7, b, c, d, e, f, g, h, a);
117         T1 = X[8] = PULL64(W[8]);
118         ROUND_00_15(8, a, b, c, d, e, f, g, h);
119         T1 = X[9] = PULL64(W[9]);
120         ROUND_00_15(9, h, a, b, c, d, e, f, g);
121         T1 = X[10] = PULL64(W[10]);
122         ROUND_00_15(10, g, h, a, b, c, d, e, f);
123         T1 = X[11] = PULL64(W[11]);
124         ROUND_00_15(11, f, g, h, a, b, c, d, e);
125         T1 = X[12] = PULL64(W[12]);
126         ROUND_00_15(12, e, f, g, h, a, b, c, d);
127         T1 = X[13] = PULL64(W[13]);
128         ROUND_00_15(13, d, e, f, g, h, a, b, c);
129         T1 = X[14] = PULL64(W[14]);
130         ROUND_00_15(14, c, d, e, f, g, h, a, b);
131         T1 = X[15] = PULL64(W[15]);
132         ROUND_00_15(15, b, c, d, e, f, g, h, a);
133 
134         for (i = 16; i < 80; i += 16) {
135             ROUND_16_80(i, 0, a, b, c, d, e, f, g, h, X);
136             ROUND_16_80(i, 1, h, a, b, c, d, e, f, g, X);
137             ROUND_16_80(i, 2, g, h, a, b, c, d, e, f, X);
138             ROUND_16_80(i, 3, f, g, h, a, b, c, d, e, X);
139             ROUND_16_80(i, 4, e, f, g, h, a, b, c, d, X);
140             ROUND_16_80(i, 5, d, e, f, g, h, a, b, c, X);
141             ROUND_16_80(i, 6, c, d, e, f, g, h, a, b, X);
142             ROUND_16_80(i, 7, b, c, d, e, f, g, h, a, X);
143             ROUND_16_80(i, 8, a, b, c, d, e, f, g, h, X);
144             ROUND_16_80(i, 9, h, a, b, c, d, e, f, g, X);
145             ROUND_16_80(i, 10, g, h, a, b, c, d, e, f, X);
146             ROUND_16_80(i, 11, f, g, h, a, b, c, d, e, X);
147             ROUND_16_80(i, 12, e, f, g, h, a, b, c, d, X);
148             ROUND_16_80(i, 13, d, e, f, g, h, a, b, c, X);
149             ROUND_16_80(i, 14, c, d, e, f, g, h, a, b, X);
150             ROUND_16_80(i, 15, b, c, d, e, f, g, h, a, X);
151         }
152 
153         ctx->h[0] += a;
154         ctx->h[1] += b;
155         ctx->h[2] += c;
156         ctx->h[3] += d;
157         ctx->h[4] += e;
158         ctx->h[5] += f;
159         ctx->h[6] += g;
160         ctx->h[7] += h;
161 
162         W += SHA_LBLOCK;
163     }
164 }
165