mm: fix exec activate_mm vs TLB shootdown and lazy tlb switching race
[linux/fpc-iii.git] / arch / x86 / purgatory / sha256.c
blob548ca675a14a131b78c8025b8c7185f23cd4a602
1 /*
2 * SHA-256, as specified in
3 * http://csrc.nist.gov/groups/STM/cavp/documents/shs/sha256-384-512.pdf
5 * SHA-256 code by Jean-Luc Cooke <jlcooke@certainkey.com>.
7 * Copyright (c) Jean-Luc Cooke <jlcooke@certainkey.com>
8 * Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk>
9 * Copyright (c) 2002 James Morris <jmorris@intercode.com.au>
10 * Copyright (c) 2014 Red Hat Inc.
12 * This program is free software; you can redistribute it and/or modify it
13 * under the terms of the GNU General Public License as published by the Free
14 * Software Foundation; either version 2 of the License, or (at your option)
15 * any later version.
18 #include <linux/bitops.h>
19 #include <asm/byteorder.h>
20 #include "sha256.h"
21 #include "../boot/string.h"
23 static inline u32 Ch(u32 x, u32 y, u32 z)
25 return z ^ (x & (y ^ z));
28 static inline u32 Maj(u32 x, u32 y, u32 z)
30 return (x & y) | (z & (x | y));
33 #define e0(x) (ror32(x, 2) ^ ror32(x, 13) ^ ror32(x, 22))
34 #define e1(x) (ror32(x, 6) ^ ror32(x, 11) ^ ror32(x, 25))
35 #define s0(x) (ror32(x, 7) ^ ror32(x, 18) ^ (x >> 3))
36 #define s1(x) (ror32(x, 17) ^ ror32(x, 19) ^ (x >> 10))
38 static inline void LOAD_OP(int I, u32 *W, const u8 *input)
40 W[I] = __be32_to_cpu(((__be32 *)(input))[I]);
43 static inline void BLEND_OP(int I, u32 *W)
45 W[I] = s1(W[I-2]) + W[I-7] + s0(W[I-15]) + W[I-16];
48 static void sha256_transform(u32 *state, const u8 *input)
50 u32 a, b, c, d, e, f, g, h, t1, t2;
51 u32 W[64];
52 int i;
54 /* load the input */
55 for (i = 0; i < 16; i++)
56 LOAD_OP(i, W, input);
58 /* now blend */
59 for (i = 16; i < 64; i++)
60 BLEND_OP(i, W);
62 /* load the state into our registers */
63 a = state[0]; b = state[1]; c = state[2]; d = state[3];
64 e = state[4]; f = state[5]; g = state[6]; h = state[7];
66 /* now iterate */
67 t1 = h + e1(e) + Ch(e, f, g) + 0x428a2f98 + W[0];
68 t2 = e0(a) + Maj(a, b, c); d += t1; h = t1 + t2;
69 t1 = g + e1(d) + Ch(d, e, f) + 0x71374491 + W[1];
70 t2 = e0(h) + Maj(h, a, b); c += t1; g = t1 + t2;
71 t1 = f + e1(c) + Ch(c, d, e) + 0xb5c0fbcf + W[2];
72 t2 = e0(g) + Maj(g, h, a); b += t1; f = t1 + t2;
73 t1 = e + e1(b) + Ch(b, c, d) + 0xe9b5dba5 + W[3];
74 t2 = e0(f) + Maj(f, g, h); a += t1; e = t1 + t2;
75 t1 = d + e1(a) + Ch(a, b, c) + 0x3956c25b + W[4];
76 t2 = e0(e) + Maj(e, f, g); h += t1; d = t1 + t2;
77 t1 = c + e1(h) + Ch(h, a, b) + 0x59f111f1 + W[5];
78 t2 = e0(d) + Maj(d, e, f); g += t1; c = t1 + t2;
79 t1 = b + e1(g) + Ch(g, h, a) + 0x923f82a4 + W[6];
80 t2 = e0(c) + Maj(c, d, e); f += t1; b = t1 + t2;
81 t1 = a + e1(f) + Ch(f, g, h) + 0xab1c5ed5 + W[7];
82 t2 = e0(b) + Maj(b, c, d); e += t1; a = t1 + t2;
84 t1 = h + e1(e) + Ch(e, f, g) + 0xd807aa98 + W[8];
85 t2 = e0(a) + Maj(a, b, c); d += t1; h = t1 + t2;
86 t1 = g + e1(d) + Ch(d, e, f) + 0x12835b01 + W[9];
87 t2 = e0(h) + Maj(h, a, b); c += t1; g = t1 + t2;
88 t1 = f + e1(c) + Ch(c, d, e) + 0x243185be + W[10];
89 t2 = e0(g) + Maj(g, h, a); b += t1; f = t1 + t2;
90 t1 = e + e1(b) + Ch(b, c, d) + 0x550c7dc3 + W[11];
91 t2 = e0(f) + Maj(f, g, h); a += t1; e = t1 + t2;
92 t1 = d + e1(a) + Ch(a, b, c) + 0x72be5d74 + W[12];
93 t2 = e0(e) + Maj(e, f, g); h += t1; d = t1 + t2;
94 t1 = c + e1(h) + Ch(h, a, b) + 0x80deb1fe + W[13];
95 t2 = e0(d) + Maj(d, e, f); g += t1; c = t1 + t2;
96 t1 = b + e1(g) + Ch(g, h, a) + 0x9bdc06a7 + W[14];
97 t2 = e0(c) + Maj(c, d, e); f += t1; b = t1 + t2;
98 t1 = a + e1(f) + Ch(f, g, h) + 0xc19bf174 + W[15];
99 t2 = e0(b) + Maj(b, c, d); e += t1; a = t1+t2;
101 t1 = h + e1(e) + Ch(e, f, g) + 0xe49b69c1 + W[16];
102 t2 = e0(a) + Maj(a, b, c); d += t1; h = t1+t2;
103 t1 = g + e1(d) + Ch(d, e, f) + 0xefbe4786 + W[17];
104 t2 = e0(h) + Maj(h, a, b); c += t1; g = t1+t2;
105 t1 = f + e1(c) + Ch(c, d, e) + 0x0fc19dc6 + W[18];
106 t2 = e0(g) + Maj(g, h, a); b += t1; f = t1+t2;
107 t1 = e + e1(b) + Ch(b, c, d) + 0x240ca1cc + W[19];
108 t2 = e0(f) + Maj(f, g, h); a += t1; e = t1+t2;
109 t1 = d + e1(a) + Ch(a, b, c) + 0x2de92c6f + W[20];
110 t2 = e0(e) + Maj(e, f, g); h += t1; d = t1+t2;
111 t1 = c + e1(h) + Ch(h, a, b) + 0x4a7484aa + W[21];
112 t2 = e0(d) + Maj(d, e, f); g += t1; c = t1+t2;
113 t1 = b + e1(g) + Ch(g, h, a) + 0x5cb0a9dc + W[22];
114 t2 = e0(c) + Maj(c, d, e); f += t1; b = t1+t2;
115 t1 = a + e1(f) + Ch(f, g, h) + 0x76f988da + W[23];
116 t2 = e0(b) + Maj(b, c, d); e += t1; a = t1+t2;
118 t1 = h + e1(e) + Ch(e, f, g) + 0x983e5152 + W[24];
119 t2 = e0(a) + Maj(a, b, c); d += t1; h = t1+t2;
120 t1 = g + e1(d) + Ch(d, e, f) + 0xa831c66d + W[25];
121 t2 = e0(h) + Maj(h, a, b); c += t1; g = t1+t2;
122 t1 = f + e1(c) + Ch(c, d, e) + 0xb00327c8 + W[26];
123 t2 = e0(g) + Maj(g, h, a); b += t1; f = t1+t2;
124 t1 = e + e1(b) + Ch(b, c, d) + 0xbf597fc7 + W[27];
125 t2 = e0(f) + Maj(f, g, h); a += t1; e = t1+t2;
126 t1 = d + e1(a) + Ch(a, b, c) + 0xc6e00bf3 + W[28];
127 t2 = e0(e) + Maj(e, f, g); h += t1; d = t1+t2;
128 t1 = c + e1(h) + Ch(h, a, b) + 0xd5a79147 + W[29];
129 t2 = e0(d) + Maj(d, e, f); g += t1; c = t1+t2;
130 t1 = b + e1(g) + Ch(g, h, a) + 0x06ca6351 + W[30];
131 t2 = e0(c) + Maj(c, d, e); f += t1; b = t1+t2;
132 t1 = a + e1(f) + Ch(f, g, h) + 0x14292967 + W[31];
133 t2 = e0(b) + Maj(b, c, d); e += t1; a = t1+t2;
135 t1 = h + e1(e) + Ch(e, f, g) + 0x27b70a85 + W[32];
136 t2 = e0(a) + Maj(a, b, c); d += t1; h = t1+t2;
137 t1 = g + e1(d) + Ch(d, e, f) + 0x2e1b2138 + W[33];
138 t2 = e0(h) + Maj(h, a, b); c += t1; g = t1+t2;
139 t1 = f + e1(c) + Ch(c, d, e) + 0x4d2c6dfc + W[34];
140 t2 = e0(g) + Maj(g, h, a); b += t1; f = t1+t2;
141 t1 = e + e1(b) + Ch(b, c, d) + 0x53380d13 + W[35];
142 t2 = e0(f) + Maj(f, g, h); a += t1; e = t1+t2;
143 t1 = d + e1(a) + Ch(a, b, c) + 0x650a7354 + W[36];
144 t2 = e0(e) + Maj(e, f, g); h += t1; d = t1+t2;
145 t1 = c + e1(h) + Ch(h, a, b) + 0x766a0abb + W[37];
146 t2 = e0(d) + Maj(d, e, f); g += t1; c = t1+t2;
147 t1 = b + e1(g) + Ch(g, h, a) + 0x81c2c92e + W[38];
148 t2 = e0(c) + Maj(c, d, e); f += t1; b = t1+t2;
149 t1 = a + e1(f) + Ch(f, g, h) + 0x92722c85 + W[39];
150 t2 = e0(b) + Maj(b, c, d); e += t1; a = t1+t2;
152 t1 = h + e1(e) + Ch(e, f, g) + 0xa2bfe8a1 + W[40];
153 t2 = e0(a) + Maj(a, b, c); d += t1; h = t1+t2;
154 t1 = g + e1(d) + Ch(d, e, f) + 0xa81a664b + W[41];
155 t2 = e0(h) + Maj(h, a, b); c += t1; g = t1+t2;
156 t1 = f + e1(c) + Ch(c, d, e) + 0xc24b8b70 + W[42];
157 t2 = e0(g) + Maj(g, h, a); b += t1; f = t1+t2;
158 t1 = e + e1(b) + Ch(b, c, d) + 0xc76c51a3 + W[43];
159 t2 = e0(f) + Maj(f, g, h); a += t1; e = t1+t2;
160 t1 = d + e1(a) + Ch(a, b, c) + 0xd192e819 + W[44];
161 t2 = e0(e) + Maj(e, f, g); h += t1; d = t1+t2;
162 t1 = c + e1(h) + Ch(h, a, b) + 0xd6990624 + W[45];
163 t2 = e0(d) + Maj(d, e, f); g += t1; c = t1+t2;
164 t1 = b + e1(g) + Ch(g, h, a) + 0xf40e3585 + W[46];
165 t2 = e0(c) + Maj(c, d, e); f += t1; b = t1+t2;
166 t1 = a + e1(f) + Ch(f, g, h) + 0x106aa070 + W[47];
167 t2 = e0(b) + Maj(b, c, d); e += t1; a = t1+t2;
169 t1 = h + e1(e) + Ch(e, f, g) + 0x19a4c116 + W[48];
170 t2 = e0(a) + Maj(a, b, c); d += t1; h = t1+t2;
171 t1 = g + e1(d) + Ch(d, e, f) + 0x1e376c08 + W[49];
172 t2 = e0(h) + Maj(h, a, b); c += t1; g = t1+t2;
173 t1 = f + e1(c) + Ch(c, d, e) + 0x2748774c + W[50];
174 t2 = e0(g) + Maj(g, h, a); b += t1; f = t1+t2;
175 t1 = e + e1(b) + Ch(b, c, d) + 0x34b0bcb5 + W[51];
176 t2 = e0(f) + Maj(f, g, h); a += t1; e = t1+t2;
177 t1 = d + e1(a) + Ch(a, b, c) + 0x391c0cb3 + W[52];
178 t2 = e0(e) + Maj(e, f, g); h += t1; d = t1+t2;
179 t1 = c + e1(h) + Ch(h, a, b) + 0x4ed8aa4a + W[53];
180 t2 = e0(d) + Maj(d, e, f); g += t1; c = t1+t2;
181 t1 = b + e1(g) + Ch(g, h, a) + 0x5b9cca4f + W[54];
182 t2 = e0(c) + Maj(c, d, e); f += t1; b = t1+t2;
183 t1 = a + e1(f) + Ch(f, g, h) + 0x682e6ff3 + W[55];
184 t2 = e0(b) + Maj(b, c, d); e += t1; a = t1+t2;
186 t1 = h + e1(e) + Ch(e, f, g) + 0x748f82ee + W[56];
187 t2 = e0(a) + Maj(a, b, c); d += t1; h = t1+t2;
188 t1 = g + e1(d) + Ch(d, e, f) + 0x78a5636f + W[57];
189 t2 = e0(h) + Maj(h, a, b); c += t1; g = t1+t2;
190 t1 = f + e1(c) + Ch(c, d, e) + 0x84c87814 + W[58];
191 t2 = e0(g) + Maj(g, h, a); b += t1; f = t1+t2;
192 t1 = e + e1(b) + Ch(b, c, d) + 0x8cc70208 + W[59];
193 t2 = e0(f) + Maj(f, g, h); a += t1; e = t1+t2;
194 t1 = d + e1(a) + Ch(a, b, c) + 0x90befffa + W[60];
195 t2 = e0(e) + Maj(e, f, g); h += t1; d = t1+t2;
196 t1 = c + e1(h) + Ch(h, a, b) + 0xa4506ceb + W[61];
197 t2 = e0(d) + Maj(d, e, f); g += t1; c = t1+t2;
198 t1 = b + e1(g) + Ch(g, h, a) + 0xbef9a3f7 + W[62];
199 t2 = e0(c) + Maj(c, d, e); f += t1; b = t1+t2;
200 t1 = a + e1(f) + Ch(f, g, h) + 0xc67178f2 + W[63];
201 t2 = e0(b) + Maj(b, c, d); e += t1; a = t1+t2;
203 state[0] += a; state[1] += b; state[2] += c; state[3] += d;
204 state[4] += e; state[5] += f; state[6] += g; state[7] += h;
206 /* clear any sensitive info... */
207 a = b = c = d = e = f = g = h = t1 = t2 = 0;
208 memset(W, 0, 64 * sizeof(u32));
211 int sha256_init(struct sha256_state *sctx)
213 sctx->state[0] = SHA256_H0;
214 sctx->state[1] = SHA256_H1;
215 sctx->state[2] = SHA256_H2;
216 sctx->state[3] = SHA256_H3;
217 sctx->state[4] = SHA256_H4;
218 sctx->state[5] = SHA256_H5;
219 sctx->state[6] = SHA256_H6;
220 sctx->state[7] = SHA256_H7;
221 sctx->count = 0;
223 return 0;
226 int sha256_update(struct sha256_state *sctx, const u8 *data, unsigned int len)
228 unsigned int partial, done;
229 const u8 *src;
231 partial = sctx->count & 0x3f;
232 sctx->count += len;
233 done = 0;
234 src = data;
236 if ((partial + len) > 63) {
237 if (partial) {
238 done = -partial;
239 memcpy(sctx->buf + partial, data, done + 64);
240 src = sctx->buf;
243 do {
244 sha256_transform(sctx->state, src);
245 done += 64;
246 src = data + done;
247 } while (done + 63 < len);
249 partial = 0;
251 memcpy(sctx->buf + partial, src, len - done);
253 return 0;
256 int sha256_final(struct sha256_state *sctx, u8 *out)
258 __be32 *dst = (__be32 *)out;
259 __be64 bits;
260 unsigned int index, pad_len;
261 int i;
262 static const u8 padding[64] = { 0x80, };
264 /* Save number of bits */
265 bits = cpu_to_be64(sctx->count << 3);
267 /* Pad out to 56 mod 64. */
268 index = sctx->count & 0x3f;
269 pad_len = (index < 56) ? (56 - index) : ((64+56) - index);
270 sha256_update(sctx, padding, pad_len);
272 /* Append length (before padding) */
273 sha256_update(sctx, (const u8 *)&bits, sizeof(bits));
275 /* Store state in digest */
276 for (i = 0; i < 8; i++)
277 dst[i] = cpu_to_be32(sctx->state[i]);
279 /* Zeroize sensitive information. */
280 memset(sctx, 0, sizeof(*sctx));
282 return 0;