1 /*
2  * Cryptographic API.
3  *
4  * SHA-256, as specified in
5  * http://csrc.nist.gov/cryptval/shs/sha256-384-512.pdf
6  *
7  * SHA-256 code by Jean-Luc Cooke <jlcooke@certainkey.com>.
8  *
9  * Copyright (c) Jean-Luc Cooke <jlcooke@certainkey.com>
10  * Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk>
11  * Copyright (c) 2002 James Morris <jmorris@intercode.com.au>
12  *
13  * This program is free software; you can redistribute it and/or modify it
14  * under the terms of the GNU General Public License as published by the Free
15  * Software Foundation; either version 2 of the License, or (at your option)
16  * any later version.
17  *
18  */
19 #include <string.h>
20 
21 #include "../lib/bswap.h"
22 #include "sha256.h"
23 
24 #define SHA256_DIGEST_SIZE	32
25 #define SHA256_HMAC_BLOCK_SIZE	64
26 
Ch(uint32_t x,uint32_t y,uint32_t z)27 static inline uint32_t Ch(uint32_t x, uint32_t y, uint32_t z)
28 {
29 	return z ^ (x & (y ^ z));
30 }
31 
Maj(uint32_t x,uint32_t y,uint32_t z)32 static inline uint32_t Maj(uint32_t x, uint32_t y, uint32_t z)
33 {
34 	return (x & y) | (z & (x | y));
35 }
36 
37 #define e0(x)       (ror32(x, 2) ^ ror32(x,13) ^ ror32(x,22))
38 #define e1(x)       (ror32(x, 6) ^ ror32(x,11) ^ ror32(x,25))
39 #define s0(x)       (ror32(x, 7) ^ ror32(x,18) ^ (x >> 3))
40 #define s1(x)       (ror32(x,17) ^ ror32(x,19) ^ (x >> 10))
41 
42 #define H0         0x6a09e667
43 #define H1         0xbb67ae85
44 #define H2         0x3c6ef372
45 #define H3         0xa54ff53a
46 #define H4         0x510e527f
47 #define H5         0x9b05688c
48 #define H6         0x1f83d9ab
49 #define H7         0x5be0cd19
50 
ror32(uint32_t word,unsigned int shift)51 static inline uint32_t ror32(uint32_t word, unsigned int shift)
52 {
53 	 return (word >> shift) | (word << (32 - shift));
54 }
55 
LOAD_OP(int I,uint32_t * W,const uint8_t * input)56 static inline void LOAD_OP(int I, uint32_t *W, const uint8_t *input)
57 {
58 	W[I] = __be32_to_cpu(((uint32_t *)(input))[I]);
59 }
60 
BLEND_OP(int I,uint32_t * W)61 static inline void BLEND_OP(int I, uint32_t *W)
62 {
63 	W[I] = s1(W[I-2]) + W[I-7] + s0(W[I-15]) + W[I-16];
64 }
65 
sha256_transform(uint32_t * state,const uint8_t * input)66 static void sha256_transform(uint32_t *state, const uint8_t *input)
67 {
68 	uint32_t a, b, c, d, e, f, g, h, t1, t2;
69 	uint32_t W[64];
70 	int i;
71 
72 	/* load the input */
73 	for (i = 0; i < 16; i++)
74 		LOAD_OP(i, W, input);
75 
76 	/* now blend */
77 	for (i = 16; i < 64; i++)
78 		BLEND_OP(i, W);
79 
80 	/* load the state into our registers */
81 	a=state[0];  b=state[1];  c=state[2];  d=state[3];
82 	e=state[4];  f=state[5];  g=state[6];  h=state[7];
83 
84 	/* now iterate */
85 	t1 = h + e1(e) + Ch(e,f,g) + 0x428a2f98 + W[ 0];
86 	t2 = e0(a) + Maj(a,b,c);    d+=t1;    h=t1+t2;
87 	t1 = g + e1(d) + Ch(d,e,f) + 0x71374491 + W[ 1];
88 	t2 = e0(h) + Maj(h,a,b);    c+=t1;    g=t1+t2;
89 	t1 = f + e1(c) + Ch(c,d,e) + 0xb5c0fbcf + W[ 2];
90 	t2 = e0(g) + Maj(g,h,a);    b+=t1;    f=t1+t2;
91 	t1 = e + e1(b) + Ch(b,c,d) + 0xe9b5dba5 + W[ 3];
92 	t2 = e0(f) + Maj(f,g,h);    a+=t1;    e=t1+t2;
93 	t1 = d + e1(a) + Ch(a,b,c) + 0x3956c25b + W[ 4];
94 	t2 = e0(e) + Maj(e,f,g);    h+=t1;    d=t1+t2;
95 	t1 = c + e1(h) + Ch(h,a,b) + 0x59f111f1 + W[ 5];
96 	t2 = e0(d) + Maj(d,e,f);    g+=t1;    c=t1+t2;
97 	t1 = b + e1(g) + Ch(g,h,a) + 0x923f82a4 + W[ 6];
98 	t2 = e0(c) + Maj(c,d,e);    f+=t1;    b=t1+t2;
99 	t1 = a + e1(f) + Ch(f,g,h) + 0xab1c5ed5 + W[ 7];
100 	t2 = e0(b) + Maj(b,c,d);    e+=t1;    a=t1+t2;
101 
102 	t1 = h + e1(e) + Ch(e,f,g) + 0xd807aa98 + W[ 8];
103 	t2 = e0(a) + Maj(a,b,c);    d+=t1;    h=t1+t2;
104 	t1 = g + e1(d) + Ch(d,e,f) + 0x12835b01 + W[ 9];
105 	t2 = e0(h) + Maj(h,a,b);    c+=t1;    g=t1+t2;
106 	t1 = f + e1(c) + Ch(c,d,e) + 0x243185be + W[10];
107 	t2 = e0(g) + Maj(g,h,a);    b+=t1;    f=t1+t2;
108 	t1 = e + e1(b) + Ch(b,c,d) + 0x550c7dc3 + W[11];
109 	t2 = e0(f) + Maj(f,g,h);    a+=t1;    e=t1+t2;
110 	t1 = d + e1(a) + Ch(a,b,c) + 0x72be5d74 + W[12];
111 	t2 = e0(e) + Maj(e,f,g);    h+=t1;    d=t1+t2;
112 	t1 = c + e1(h) + Ch(h,a,b) + 0x80deb1fe + W[13];
113 	t2 = e0(d) + Maj(d,e,f);    g+=t1;    c=t1+t2;
114 	t1 = b + e1(g) + Ch(g,h,a) + 0x9bdc06a7 + W[14];
115 	t2 = e0(c) + Maj(c,d,e);    f+=t1;    b=t1+t2;
116 	t1 = a + e1(f) + Ch(f,g,h) + 0xc19bf174 + W[15];
117 	t2 = e0(b) + Maj(b,c,d);    e+=t1;    a=t1+t2;
118 
119 	t1 = h + e1(e) + Ch(e,f,g) + 0xe49b69c1 + W[16];
120 	t2 = e0(a) + Maj(a,b,c);    d+=t1;    h=t1+t2;
121 	t1 = g + e1(d) + Ch(d,e,f) + 0xefbe4786 + W[17];
122 	t2 = e0(h) + Maj(h,a,b);    c+=t1;    g=t1+t2;
123 	t1 = f + e1(c) + Ch(c,d,e) + 0x0fc19dc6 + W[18];
124 	t2 = e0(g) + Maj(g,h,a);    b+=t1;    f=t1+t2;
125 	t1 = e + e1(b) + Ch(b,c,d) + 0x240ca1cc + W[19];
126 	t2 = e0(f) + Maj(f,g,h);    a+=t1;    e=t1+t2;
127 	t1 = d + e1(a) + Ch(a,b,c) + 0x2de92c6f + W[20];
128 	t2 = e0(e) + Maj(e,f,g);    h+=t1;    d=t1+t2;
129 	t1 = c + e1(h) + Ch(h,a,b) + 0x4a7484aa + W[21];
130 	t2 = e0(d) + Maj(d,e,f);    g+=t1;    c=t1+t2;
131 	t1 = b + e1(g) + Ch(g,h,a) + 0x5cb0a9dc + W[22];
132 	t2 = e0(c) + Maj(c,d,e);    f+=t1;    b=t1+t2;
133 	t1 = a + e1(f) + Ch(f,g,h) + 0x76f988da + W[23];
134 	t2 = e0(b) + Maj(b,c,d);    e+=t1;    a=t1+t2;
135 
136 	t1 = h + e1(e) + Ch(e,f,g) + 0x983e5152 + W[24];
137 	t2 = e0(a) + Maj(a,b,c);    d+=t1;    h=t1+t2;
138 	t1 = g + e1(d) + Ch(d,e,f) + 0xa831c66d + W[25];
139 	t2 = e0(h) + Maj(h,a,b);    c+=t1;    g=t1+t2;
140 	t1 = f + e1(c) + Ch(c,d,e) + 0xb00327c8 + W[26];
141 	t2 = e0(g) + Maj(g,h,a);    b+=t1;    f=t1+t2;
142 	t1 = e + e1(b) + Ch(b,c,d) + 0xbf597fc7 + W[27];
143 	t2 = e0(f) + Maj(f,g,h);    a+=t1;    e=t1+t2;
144 	t1 = d + e1(a) + Ch(a,b,c) + 0xc6e00bf3 + W[28];
145 	t2 = e0(e) + Maj(e,f,g);    h+=t1;    d=t1+t2;
146 	t1 = c + e1(h) + Ch(h,a,b) + 0xd5a79147 + W[29];
147 	t2 = e0(d) + Maj(d,e,f);    g+=t1;    c=t1+t2;
148 	t1 = b + e1(g) + Ch(g,h,a) + 0x06ca6351 + W[30];
149 	t2 = e0(c) + Maj(c,d,e);    f+=t1;    b=t1+t2;
150 	t1 = a + e1(f) + Ch(f,g,h) + 0x14292967 + W[31];
151 	t2 = e0(b) + Maj(b,c,d);    e+=t1;    a=t1+t2;
152 
153 	t1 = h + e1(e) + Ch(e,f,g) + 0x27b70a85 + W[32];
154 	t2 = e0(a) + Maj(a,b,c);    d+=t1;    h=t1+t2;
155 	t1 = g + e1(d) + Ch(d,e,f) + 0x2e1b2138 + W[33];
156 	t2 = e0(h) + Maj(h,a,b);    c+=t1;    g=t1+t2;
157 	t1 = f + e1(c) + Ch(c,d,e) + 0x4d2c6dfc + W[34];
158 	t2 = e0(g) + Maj(g,h,a);    b+=t1;    f=t1+t2;
159 	t1 = e + e1(b) + Ch(b,c,d) + 0x53380d13 + W[35];
160 	t2 = e0(f) + Maj(f,g,h);    a+=t1;    e=t1+t2;
161 	t1 = d + e1(a) + Ch(a,b,c) + 0x650a7354 + W[36];
162 	t2 = e0(e) + Maj(e,f,g);    h+=t1;    d=t1+t2;
163 	t1 = c + e1(h) + Ch(h,a,b) + 0x766a0abb + W[37];
164 	t2 = e0(d) + Maj(d,e,f);    g+=t1;    c=t1+t2;
165 	t1 = b + e1(g) + Ch(g,h,a) + 0x81c2c92e + W[38];
166 	t2 = e0(c) + Maj(c,d,e);    f+=t1;    b=t1+t2;
167 	t1 = a + e1(f) + Ch(f,g,h) + 0x92722c85 + W[39];
168 	t2 = e0(b) + Maj(b,c,d);    e+=t1;    a=t1+t2;
169 
170 	t1 = h + e1(e) + Ch(e,f,g) + 0xa2bfe8a1 + W[40];
171 	t2 = e0(a) + Maj(a,b,c);    d+=t1;    h=t1+t2;
172 	t1 = g + e1(d) + Ch(d,e,f) + 0xa81a664b + W[41];
173 	t2 = e0(h) + Maj(h,a,b);    c+=t1;    g=t1+t2;
174 	t1 = f + e1(c) + Ch(c,d,e) + 0xc24b8b70 + W[42];
175 	t2 = e0(g) + Maj(g,h,a);    b+=t1;    f=t1+t2;
176 	t1 = e + e1(b) + Ch(b,c,d) + 0xc76c51a3 + W[43];
177 	t2 = e0(f) + Maj(f,g,h);    a+=t1;    e=t1+t2;
178 	t1 = d + e1(a) + Ch(a,b,c) + 0xd192e819 + W[44];
179 	t2 = e0(e) + Maj(e,f,g);    h+=t1;    d=t1+t2;
180 	t1 = c + e1(h) + Ch(h,a,b) + 0xd6990624 + W[45];
181 	t2 = e0(d) + Maj(d,e,f);    g+=t1;    c=t1+t2;
182 	t1 = b + e1(g) + Ch(g,h,a) + 0xf40e3585 + W[46];
183 	t2 = e0(c) + Maj(c,d,e);    f+=t1;    b=t1+t2;
184 	t1 = a + e1(f) + Ch(f,g,h) + 0x106aa070 + W[47];
185 	t2 = e0(b) + Maj(b,c,d);    e+=t1;    a=t1+t2;
186 
187 	t1 = h + e1(e) + Ch(e,f,g) + 0x19a4c116 + W[48];
188 	t2 = e0(a) + Maj(a,b,c);    d+=t1;    h=t1+t2;
189 	t1 = g + e1(d) + Ch(d,e,f) + 0x1e376c08 + W[49];
190 	t2 = e0(h) + Maj(h,a,b);    c+=t1;    g=t1+t2;
191 	t1 = f + e1(c) + Ch(c,d,e) + 0x2748774c + W[50];
192 	t2 = e0(g) + Maj(g,h,a);    b+=t1;    f=t1+t2;
193 	t1 = e + e1(b) + Ch(b,c,d) + 0x34b0bcb5 + W[51];
194 	t2 = e0(f) + Maj(f,g,h);    a+=t1;    e=t1+t2;
195 	t1 = d + e1(a) + Ch(a,b,c) + 0x391c0cb3 + W[52];
196 	t2 = e0(e) + Maj(e,f,g);    h+=t1;    d=t1+t2;
197 	t1 = c + e1(h) + Ch(h,a,b) + 0x4ed8aa4a + W[53];
198 	t2 = e0(d) + Maj(d,e,f);    g+=t1;    c=t1+t2;
199 	t1 = b + e1(g) + Ch(g,h,a) + 0x5b9cca4f + W[54];
200 	t2 = e0(c) + Maj(c,d,e);    f+=t1;    b=t1+t2;
201 	t1 = a + e1(f) + Ch(f,g,h) + 0x682e6ff3 + W[55];
202 	t2 = e0(b) + Maj(b,c,d);    e+=t1;    a=t1+t2;
203 
204 	t1 = h + e1(e) + Ch(e,f,g) + 0x748f82ee + W[56];
205 	t2 = e0(a) + Maj(a,b,c);    d+=t1;    h=t1+t2;
206 	t1 = g + e1(d) + Ch(d,e,f) + 0x78a5636f + W[57];
207 	t2 = e0(h) + Maj(h,a,b);    c+=t1;    g=t1+t2;
208 	t1 = f + e1(c) + Ch(c,d,e) + 0x84c87814 + W[58];
209 	t2 = e0(g) + Maj(g,h,a);    b+=t1;    f=t1+t2;
210 	t1 = e + e1(b) + Ch(b,c,d) + 0x8cc70208 + W[59];
211 	t2 = e0(f) + Maj(f,g,h);    a+=t1;    e=t1+t2;
212 	t1 = d + e1(a) + Ch(a,b,c) + 0x90befffa + W[60];
213 	t2 = e0(e) + Maj(e,f,g);    h+=t1;    d=t1+t2;
214 	t1 = c + e1(h) + Ch(h,a,b) + 0xa4506ceb + W[61];
215 	t2 = e0(d) + Maj(d,e,f);    g+=t1;    c=t1+t2;
216 	t1 = b + e1(g) + Ch(g,h,a) + 0xbef9a3f7 + W[62];
217 	t2 = e0(c) + Maj(c,d,e);    f+=t1;    b=t1+t2;
218 	t1 = a + e1(f) + Ch(f,g,h) + 0xc67178f2 + W[63];
219 	t2 = e0(b) + Maj(b,c,d);    e+=t1;    a=t1+t2;
220 
221 	state[0] += a; state[1] += b; state[2] += c; state[3] += d;
222 	state[4] += e; state[5] += f; state[6] += g; state[7] += h;
223 
224 	/* clear any sensitive info... */
225 	a = b = c = d = e = f = g = h = t1 = t2 = 0;
226 	memset(W, 0, 64 * sizeof(uint32_t));
227 }
228 
fio_sha256_init(struct fio_sha256_ctx * sctx)229 void fio_sha256_init(struct fio_sha256_ctx *sctx)
230 {
231 	sctx->state[0] = H0;
232 	sctx->state[1] = H1;
233 	sctx->state[2] = H2;
234 	sctx->state[3] = H3;
235 	sctx->state[4] = H4;
236 	sctx->state[5] = H5;
237 	sctx->state[6] = H6;
238 	sctx->state[7] = H7;
239 	sctx->count = 0;
240 }
241 
fio_sha256_update(struct fio_sha256_ctx * sctx,const uint8_t * data,unsigned int len)242 void fio_sha256_update(struct fio_sha256_ctx *sctx, const uint8_t *data,
243 		       unsigned int len)
244 {
245 	unsigned int partial, done;
246 	const uint8_t *src;
247 
248 	partial = sctx->count & 0x3f;
249 	sctx->count += len;
250 	done = 0;
251 	src = data;
252 
253 	if ((partial + len) > 63) {
254 		if (partial) {
255 			done = -partial;
256 			memcpy(sctx->buf + partial, data, done + 64);
257 			src = sctx->buf;
258 		}
259 
260 		do {
261 			sha256_transform(sctx->state, src);
262 			done += 64;
263 			src = data + done;
264 		} while (done + 63 < len);
265 
266 		partial = 0;
267 	}
268 	memcpy(sctx->buf + partial, src, len - done);
269 }
270 
fio_sha256_final(struct fio_sha256_ctx * sctx)271 void fio_sha256_final(struct fio_sha256_ctx *sctx)
272 {
273 	uint64_t bits;
274 	unsigned int index, pad_len;
275 	int i;
276 	static const uint8_t padding[64] = { 0x80, };
277 
278 	/* Save number of bits */
279 	bits = (uint64_t) sctx->count << 3;
280 
281 	/* Pad out to 56 mod 64. */
282 	index = sctx->count & 0x3f;
283 	pad_len = (index < 56) ? (56 - index) : ((64+56) - index);
284 	fio_sha256_update(sctx, padding, pad_len);
285 
286 	/* Append length (before padding) */
287 	fio_sha256_update(sctx, (const uint8_t *)&bits, sizeof(bits));
288 
289 	/* Store state in digest */
290 	for (i = 0; i < 8; i++)
291 		sctx->buf[i] = sctx->state[i];
292 }
293