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#include <inttypes.h>
21
22#include "../lib/bswap.h"
23#include "sha256.h"
24
25#define SHA256_DIGEST_SIZE	32
26#define SHA256_HMAC_BLOCK_SIZE	64
27
28static inline uint32_t Ch(uint32_t x, uint32_t y, uint32_t z)
29{
30	return z ^ (x & (y ^ z));
31}
32
33static inline uint32_t Maj(uint32_t x, uint32_t y, uint32_t z)
34{
35	return (x & y) | (z & (x | y));
36}
37
38#define e0(x)       (ror32(x, 2) ^ ror32(x,13) ^ ror32(x,22))
39#define e1(x)       (ror32(x, 6) ^ ror32(x,11) ^ ror32(x,25))
40#define s0(x)       (ror32(x, 7) ^ ror32(x,18) ^ (x >> 3))
41#define s1(x)       (ror32(x,17) ^ ror32(x,19) ^ (x >> 10))
42
43#define H0         0x6a09e667
44#define H1         0xbb67ae85
45#define H2         0x3c6ef372
46#define H3         0xa54ff53a
47#define H4         0x510e527f
48#define H5         0x9b05688c
49#define H6         0x1f83d9ab
50#define H7         0x5be0cd19
51
52static inline uint32_t ror32(uint32_t word, unsigned int shift)
53{
54	 return (word >> shift) | (word << (32 - shift));
55}
56
57static inline void LOAD_OP(int I, uint32_t *W, const uint8_t *input)
58{
59	W[I] = __be32_to_cpu(((uint32_t *)(input))[I]);
60}
61
62static inline void BLEND_OP(int I, uint32_t *W)
63{
64	W[I] = s1(W[I-2]) + W[I-7] + s0(W[I-15]) + W[I-16];
65}
66
67static void sha256_transform(uint32_t *state, const uint8_t *input)
68{
69	uint32_t a, b, c, d, e, f, g, h, t1, t2;
70	uint32_t W[64];
71	int i;
72
73	/* load the input */
74	for (i = 0; i < 16; i++)
75		LOAD_OP(i, W, input);
76
77	/* now blend */
78	for (i = 16; i < 64; i++)
79		BLEND_OP(i, W);
80
81	/* load the state into our registers */
82	a=state[0];  b=state[1];  c=state[2];  d=state[3];
83	e=state[4];  f=state[5];  g=state[6];  h=state[7];
84
85	/* now iterate */
86	t1 = h + e1(e) + Ch(e,f,g) + 0x428a2f98 + W[ 0];
87	t2 = e0(a) + Maj(a,b,c);    d+=t1;    h=t1+t2;
88	t1 = g + e1(d) + Ch(d,e,f) + 0x71374491 + W[ 1];
89	t2 = e0(h) + Maj(h,a,b);    c+=t1;    g=t1+t2;
90	t1 = f + e1(c) + Ch(c,d,e) + 0xb5c0fbcf + W[ 2];
91	t2 = e0(g) + Maj(g,h,a);    b+=t1;    f=t1+t2;
92	t1 = e + e1(b) + Ch(b,c,d) + 0xe9b5dba5 + W[ 3];
93	t2 = e0(f) + Maj(f,g,h);    a+=t1;    e=t1+t2;
94	t1 = d + e1(a) + Ch(a,b,c) + 0x3956c25b + W[ 4];
95	t2 = e0(e) + Maj(e,f,g);    h+=t1;    d=t1+t2;
96	t1 = c + e1(h) + Ch(h,a,b) + 0x59f111f1 + W[ 5];
97	t2 = e0(d) + Maj(d,e,f);    g+=t1;    c=t1+t2;
98	t1 = b + e1(g) + Ch(g,h,a) + 0x923f82a4 + W[ 6];
99	t2 = e0(c) + Maj(c,d,e);    f+=t1;    b=t1+t2;
100	t1 = a + e1(f) + Ch(f,g,h) + 0xab1c5ed5 + W[ 7];
101	t2 = e0(b) + Maj(b,c,d);    e+=t1;    a=t1+t2;
102
103	t1 = h + e1(e) + Ch(e,f,g) + 0xd807aa98 + W[ 8];
104	t2 = e0(a) + Maj(a,b,c);    d+=t1;    h=t1+t2;
105	t1 = g + e1(d) + Ch(d,e,f) + 0x12835b01 + W[ 9];
106	t2 = e0(h) + Maj(h,a,b);    c+=t1;    g=t1+t2;
107	t1 = f + e1(c) + Ch(c,d,e) + 0x243185be + W[10];
108	t2 = e0(g) + Maj(g,h,a);    b+=t1;    f=t1+t2;
109	t1 = e + e1(b) + Ch(b,c,d) + 0x550c7dc3 + W[11];
110	t2 = e0(f) + Maj(f,g,h);    a+=t1;    e=t1+t2;
111	t1 = d + e1(a) + Ch(a,b,c) + 0x72be5d74 + W[12];
112	t2 = e0(e) + Maj(e,f,g);    h+=t1;    d=t1+t2;
113	t1 = c + e1(h) + Ch(h,a,b) + 0x80deb1fe + W[13];
114	t2 = e0(d) + Maj(d,e,f);    g+=t1;    c=t1+t2;
115	t1 = b + e1(g) + Ch(g,h,a) + 0x9bdc06a7 + W[14];
116	t2 = e0(c) + Maj(c,d,e);    f+=t1;    b=t1+t2;
117	t1 = a + e1(f) + Ch(f,g,h) + 0xc19bf174 + W[15];
118	t2 = e0(b) + Maj(b,c,d);    e+=t1;    a=t1+t2;
119
120	t1 = h + e1(e) + Ch(e,f,g) + 0xe49b69c1 + W[16];
121	t2 = e0(a) + Maj(a,b,c);    d+=t1;    h=t1+t2;
122	t1 = g + e1(d) + Ch(d,e,f) + 0xefbe4786 + W[17];
123	t2 = e0(h) + Maj(h,a,b);    c+=t1;    g=t1+t2;
124	t1 = f + e1(c) + Ch(c,d,e) + 0x0fc19dc6 + W[18];
125	t2 = e0(g) + Maj(g,h,a);    b+=t1;    f=t1+t2;
126	t1 = e + e1(b) + Ch(b,c,d) + 0x240ca1cc + W[19];
127	t2 = e0(f) + Maj(f,g,h);    a+=t1;    e=t1+t2;
128	t1 = d + e1(a) + Ch(a,b,c) + 0x2de92c6f + W[20];
129	t2 = e0(e) + Maj(e,f,g);    h+=t1;    d=t1+t2;
130	t1 = c + e1(h) + Ch(h,a,b) + 0x4a7484aa + W[21];
131	t2 = e0(d) + Maj(d,e,f);    g+=t1;    c=t1+t2;
132	t1 = b + e1(g) + Ch(g,h,a) + 0x5cb0a9dc + W[22];
133	t2 = e0(c) + Maj(c,d,e);    f+=t1;    b=t1+t2;
134	t1 = a + e1(f) + Ch(f,g,h) + 0x76f988da + W[23];
135	t2 = e0(b) + Maj(b,c,d);    e+=t1;    a=t1+t2;
136
137	t1 = h + e1(e) + Ch(e,f,g) + 0x983e5152 + W[24];
138	t2 = e0(a) + Maj(a,b,c);    d+=t1;    h=t1+t2;
139	t1 = g + e1(d) + Ch(d,e,f) + 0xa831c66d + W[25];
140	t2 = e0(h) + Maj(h,a,b);    c+=t1;    g=t1+t2;
141	t1 = f + e1(c) + Ch(c,d,e) + 0xb00327c8 + W[26];
142	t2 = e0(g) + Maj(g,h,a);    b+=t1;    f=t1+t2;
143	t1 = e + e1(b) + Ch(b,c,d) + 0xbf597fc7 + W[27];
144	t2 = e0(f) + Maj(f,g,h);    a+=t1;    e=t1+t2;
145	t1 = d + e1(a) + Ch(a,b,c) + 0xc6e00bf3 + W[28];
146	t2 = e0(e) + Maj(e,f,g);    h+=t1;    d=t1+t2;
147	t1 = c + e1(h) + Ch(h,a,b) + 0xd5a79147 + W[29];
148	t2 = e0(d) + Maj(d,e,f);    g+=t1;    c=t1+t2;
149	t1 = b + e1(g) + Ch(g,h,a) + 0x06ca6351 + W[30];
150	t2 = e0(c) + Maj(c,d,e);    f+=t1;    b=t1+t2;
151	t1 = a + e1(f) + Ch(f,g,h) + 0x14292967 + W[31];
152	t2 = e0(b) + Maj(b,c,d);    e+=t1;    a=t1+t2;
153
154	t1 = h + e1(e) + Ch(e,f,g) + 0x27b70a85 + W[32];
155	t2 = e0(a) + Maj(a,b,c);    d+=t1;    h=t1+t2;
156	t1 = g + e1(d) + Ch(d,e,f) + 0x2e1b2138 + W[33];
157	t2 = e0(h) + Maj(h,a,b);    c+=t1;    g=t1+t2;
158	t1 = f + e1(c) + Ch(c,d,e) + 0x4d2c6dfc + W[34];
159	t2 = e0(g) + Maj(g,h,a);    b+=t1;    f=t1+t2;
160	t1 = e + e1(b) + Ch(b,c,d) + 0x53380d13 + W[35];
161	t2 = e0(f) + Maj(f,g,h);    a+=t1;    e=t1+t2;
162	t1 = d + e1(a) + Ch(a,b,c) + 0x650a7354 + W[36];
163	t2 = e0(e) + Maj(e,f,g);    h+=t1;    d=t1+t2;
164	t1 = c + e1(h) + Ch(h,a,b) + 0x766a0abb + W[37];
165	t2 = e0(d) + Maj(d,e,f);    g+=t1;    c=t1+t2;
166	t1 = b + e1(g) + Ch(g,h,a) + 0x81c2c92e + W[38];
167	t2 = e0(c) + Maj(c,d,e);    f+=t1;    b=t1+t2;
168	t1 = a + e1(f) + Ch(f,g,h) + 0x92722c85 + W[39];
169	t2 = e0(b) + Maj(b,c,d);    e+=t1;    a=t1+t2;
170
171	t1 = h + e1(e) + Ch(e,f,g) + 0xa2bfe8a1 + W[40];
172	t2 = e0(a) + Maj(a,b,c);    d+=t1;    h=t1+t2;
173	t1 = g + e1(d) + Ch(d,e,f) + 0xa81a664b + W[41];
174	t2 = e0(h) + Maj(h,a,b);    c+=t1;    g=t1+t2;
175	t1 = f + e1(c) + Ch(c,d,e) + 0xc24b8b70 + W[42];
176	t2 = e0(g) + Maj(g,h,a);    b+=t1;    f=t1+t2;
177	t1 = e + e1(b) + Ch(b,c,d) + 0xc76c51a3 + W[43];
178	t2 = e0(f) + Maj(f,g,h);    a+=t1;    e=t1+t2;
179	t1 = d + e1(a) + Ch(a,b,c) + 0xd192e819 + W[44];
180	t2 = e0(e) + Maj(e,f,g);    h+=t1;    d=t1+t2;
181	t1 = c + e1(h) + Ch(h,a,b) + 0xd6990624 + W[45];
182	t2 = e0(d) + Maj(d,e,f);    g+=t1;    c=t1+t2;
183	t1 = b + e1(g) + Ch(g,h,a) + 0xf40e3585 + W[46];
184	t2 = e0(c) + Maj(c,d,e);    f+=t1;    b=t1+t2;
185	t1 = a + e1(f) + Ch(f,g,h) + 0x106aa070 + W[47];
186	t2 = e0(b) + Maj(b,c,d);    e+=t1;    a=t1+t2;
187
188	t1 = h + e1(e) + Ch(e,f,g) + 0x19a4c116 + W[48];
189	t2 = e0(a) + Maj(a,b,c);    d+=t1;    h=t1+t2;
190	t1 = g + e1(d) + Ch(d,e,f) + 0x1e376c08 + W[49];
191	t2 = e0(h) + Maj(h,a,b);    c+=t1;    g=t1+t2;
192	t1 = f + e1(c) + Ch(c,d,e) + 0x2748774c + W[50];
193	t2 = e0(g) + Maj(g,h,a);    b+=t1;    f=t1+t2;
194	t1 = e + e1(b) + Ch(b,c,d) + 0x34b0bcb5 + W[51];
195	t2 = e0(f) + Maj(f,g,h);    a+=t1;    e=t1+t2;
196	t1 = d + e1(a) + Ch(a,b,c) + 0x391c0cb3 + W[52];
197	t2 = e0(e) + Maj(e,f,g);    h+=t1;    d=t1+t2;
198	t1 = c + e1(h) + Ch(h,a,b) + 0x4ed8aa4a + W[53];
199	t2 = e0(d) + Maj(d,e,f);    g+=t1;    c=t1+t2;
200	t1 = b + e1(g) + Ch(g,h,a) + 0x5b9cca4f + W[54];
201	t2 = e0(c) + Maj(c,d,e);    f+=t1;    b=t1+t2;
202	t1 = a + e1(f) + Ch(f,g,h) + 0x682e6ff3 + W[55];
203	t2 = e0(b) + Maj(b,c,d);    e+=t1;    a=t1+t2;
204
205	t1 = h + e1(e) + Ch(e,f,g) + 0x748f82ee + W[56];
206	t2 = e0(a) + Maj(a,b,c);    d+=t1;    h=t1+t2;
207	t1 = g + e1(d) + Ch(d,e,f) + 0x78a5636f + W[57];
208	t2 = e0(h) + Maj(h,a,b);    c+=t1;    g=t1+t2;
209	t1 = f + e1(c) + Ch(c,d,e) + 0x84c87814 + W[58];
210	t2 = e0(g) + Maj(g,h,a);    b+=t1;    f=t1+t2;
211	t1 = e + e1(b) + Ch(b,c,d) + 0x8cc70208 + W[59];
212	t2 = e0(f) + Maj(f,g,h);    a+=t1;    e=t1+t2;
213	t1 = d + e1(a) + Ch(a,b,c) + 0x90befffa + W[60];
214	t2 = e0(e) + Maj(e,f,g);    h+=t1;    d=t1+t2;
215	t1 = c + e1(h) + Ch(h,a,b) + 0xa4506ceb + W[61];
216	t2 = e0(d) + Maj(d,e,f);    g+=t1;    c=t1+t2;
217	t1 = b + e1(g) + Ch(g,h,a) + 0xbef9a3f7 + W[62];
218	t2 = e0(c) + Maj(c,d,e);    f+=t1;    b=t1+t2;
219	t1 = a + e1(f) + Ch(f,g,h) + 0xc67178f2 + W[63];
220	t2 = e0(b) + Maj(b,c,d);    e+=t1;    a=t1+t2;
221
222	state[0] += a; state[1] += b; state[2] += c; state[3] += d;
223	state[4] += e; state[5] += f; state[6] += g; state[7] += h;
224
225	/* clear any sensitive info... */
226	a = b = c = d = e = f = g = h = t1 = t2 = 0;
227	memset(W, 0, 64 * sizeof(uint32_t));
228}
229
230void fio_sha256_init(struct fio_sha256_ctx *sctx)
231{
232	sctx->state[0] = H0;
233	sctx->state[1] = H1;
234	sctx->state[2] = H2;
235	sctx->state[3] = H3;
236	sctx->state[4] = H4;
237	sctx->state[5] = H5;
238	sctx->state[6] = H6;
239	sctx->state[7] = H7;
240	sctx->count[0] = sctx->count[1] = 0;
241}
242
243void fio_sha256_update(struct fio_sha256_ctx *sctx, const uint8_t *data,
244		       unsigned int len)
245{
246	unsigned int i, idx, part_len;
247
248	/* Compute number of bytes mod 128 */
249	idx = (unsigned int)((sctx->count[0] >> 3) & 0x3f);
250
251	/* Update number of bits */
252	if ((sctx->count[0] += (len << 3)) < (len << 3)) {
253		sctx->count[1]++;
254		sctx->count[1] += (len >> 29);
255	}
256
257	part_len = 64 - idx;
258
259	/* Transform as many times as possible. */
260	if (len >= part_len) {
261		memcpy(&sctx->buf[idx], data, part_len);
262		sha256_transform(sctx->state, sctx->buf);
263
264		for (i = part_len; i + 63 < len; i += 64)
265			sha256_transform(sctx->state, &data[i]);
266		idx = 0;
267	} else {
268		i = 0;
269	}
270
271	/* Buffer remaining input */
272	memcpy(&sctx->buf[idx], &data[i], len-i);
273}
274