1 // SPDX-License-Identifier: GPL-2.0+
2 /*
3 * FIPS-180-2 compliant SHA-512 and SHA-384 implementation
4 *
5 * SHA-512 code by Jean-Luc Cooke <jlcooke@certainkey.com>
6 *
7 * Copyright (c) Jean-Luc Cooke <jlcooke@certainkey.com>
8 * Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk>
9 * Copyright (c) 2003 Kyle McMartin <kyle@debian.org>
10 * Copyright (c) 2020 Reuben Dowle <reuben.dowle@4rf.com>
11 */
12
13 #ifndef USE_HOSTCC
14 #include <u-boot/schedule.h>
15 #endif /* USE_HOSTCC */
16 #include <compiler.h>
17 #include <u-boot/sha512.h>
18
19 const uint8_t sha384_der_prefix[SHA384_DER_LEN] = {
20 0x30, 0x41, 0x30, 0x0d, 0x06, 0x09, 0x60, 0x86,
21 0x48, 0x01, 0x65, 0x03, 0x04, 0x02, 0x02, 0x05,
22 0x00, 0x04, 0x30
23 };
24
25 const uint8_t sha512_der_prefix[SHA512_DER_LEN] = {
26 0x30, 0x51, 0x30, 0x0d, 0x06, 0x09, 0x60, 0x86,
27 0x48, 0x01, 0x65, 0x03, 0x04, 0x02, 0x03, 0x05,
28 0x00, 0x04, 0x40
29 };
30
31 #define SHA384_H0 0xcbbb9d5dc1059ed8ULL
32 #define SHA384_H1 0x629a292a367cd507ULL
33 #define SHA384_H2 0x9159015a3070dd17ULL
34 #define SHA384_H3 0x152fecd8f70e5939ULL
35 #define SHA384_H4 0x67332667ffc00b31ULL
36 #define SHA384_H5 0x8eb44a8768581511ULL
37 #define SHA384_H6 0xdb0c2e0d64f98fa7ULL
38 #define SHA384_H7 0x47b5481dbefa4fa4ULL
39
40 #define SHA512_H0 0x6a09e667f3bcc908ULL
41 #define SHA512_H1 0xbb67ae8584caa73bULL
42 #define SHA512_H2 0x3c6ef372fe94f82bULL
43 #define SHA512_H3 0xa54ff53a5f1d36f1ULL
44 #define SHA512_H4 0x510e527fade682d1ULL
45 #define SHA512_H5 0x9b05688c2b3e6c1fULL
46 #define SHA512_H6 0x1f83d9abfb41bd6bULL
47 #define SHA512_H7 0x5be0cd19137e2179ULL
48
Ch(uint64_t x,uint64_t y,uint64_t z)49 static inline uint64_t Ch(uint64_t x, uint64_t y, uint64_t z)
50 {
51 return z ^ (x & (y ^ z));
52 }
53
Maj(uint64_t x,uint64_t y,uint64_t z)54 static inline uint64_t Maj(uint64_t x, uint64_t y, uint64_t z)
55 {
56 return (x & y) | (z & (x | y));
57 }
58
59 static const uint64_t sha512_K[80] = {
60 0x428a2f98d728ae22ULL, 0x7137449123ef65cdULL, 0xb5c0fbcfec4d3b2fULL,
61 0xe9b5dba58189dbbcULL, 0x3956c25bf348b538ULL, 0x59f111f1b605d019ULL,
62 0x923f82a4af194f9bULL, 0xab1c5ed5da6d8118ULL, 0xd807aa98a3030242ULL,
63 0x12835b0145706fbeULL, 0x243185be4ee4b28cULL, 0x550c7dc3d5ffb4e2ULL,
64 0x72be5d74f27b896fULL, 0x80deb1fe3b1696b1ULL, 0x9bdc06a725c71235ULL,
65 0xc19bf174cf692694ULL, 0xe49b69c19ef14ad2ULL, 0xefbe4786384f25e3ULL,
66 0x0fc19dc68b8cd5b5ULL, 0x240ca1cc77ac9c65ULL, 0x2de92c6f592b0275ULL,
67 0x4a7484aa6ea6e483ULL, 0x5cb0a9dcbd41fbd4ULL, 0x76f988da831153b5ULL,
68 0x983e5152ee66dfabULL, 0xa831c66d2db43210ULL, 0xb00327c898fb213fULL,
69 0xbf597fc7beef0ee4ULL, 0xc6e00bf33da88fc2ULL, 0xd5a79147930aa725ULL,
70 0x06ca6351e003826fULL, 0x142929670a0e6e70ULL, 0x27b70a8546d22ffcULL,
71 0x2e1b21385c26c926ULL, 0x4d2c6dfc5ac42aedULL, 0x53380d139d95b3dfULL,
72 0x650a73548baf63deULL, 0x766a0abb3c77b2a8ULL, 0x81c2c92e47edaee6ULL,
73 0x92722c851482353bULL, 0xa2bfe8a14cf10364ULL, 0xa81a664bbc423001ULL,
74 0xc24b8b70d0f89791ULL, 0xc76c51a30654be30ULL, 0xd192e819d6ef5218ULL,
75 0xd69906245565a910ULL, 0xf40e35855771202aULL, 0x106aa07032bbd1b8ULL,
76 0x19a4c116b8d2d0c8ULL, 0x1e376c085141ab53ULL, 0x2748774cdf8eeb99ULL,
77 0x34b0bcb5e19b48a8ULL, 0x391c0cb3c5c95a63ULL, 0x4ed8aa4ae3418acbULL,
78 0x5b9cca4f7763e373ULL, 0x682e6ff3d6b2b8a3ULL, 0x748f82ee5defb2fcULL,
79 0x78a5636f43172f60ULL, 0x84c87814a1f0ab72ULL, 0x8cc702081a6439ecULL,
80 0x90befffa23631e28ULL, 0xa4506cebde82bde9ULL, 0xbef9a3f7b2c67915ULL,
81 0xc67178f2e372532bULL, 0xca273eceea26619cULL, 0xd186b8c721c0c207ULL,
82 0xeada7dd6cde0eb1eULL, 0xf57d4f7fee6ed178ULL, 0x06f067aa72176fbaULL,
83 0x0a637dc5a2c898a6ULL, 0x113f9804bef90daeULL, 0x1b710b35131c471bULL,
84 0x28db77f523047d84ULL, 0x32caab7b40c72493ULL, 0x3c9ebe0a15c9bebcULL,
85 0x431d67c49c100d4cULL, 0x4cc5d4becb3e42b6ULL, 0x597f299cfc657e2aULL,
86 0x5fcb6fab3ad6faecULL, 0x6c44198c4a475817ULL,
87 };
88
ror64(uint64_t word,unsigned int shift)89 static inline uint64_t ror64(uint64_t word, unsigned int shift)
90 {
91 return (word >> (shift & 63)) | (word << ((-shift) & 63));
92 }
93
94 #define e0(x) (ror64(x,28) ^ ror64(x,34) ^ ror64(x,39))
95 #define e1(x) (ror64(x,14) ^ ror64(x,18) ^ ror64(x,41))
96 #define s0(x) (ror64(x, 1) ^ ror64(x, 8) ^ (x >> 7))
97 #define s1(x) (ror64(x,19) ^ ror64(x,61) ^ (x >> 6))
98
99 /*
100 * 64-bit integer manipulation macros (big endian)
101 */
102 #ifndef GET_UINT64_BE
103 #define GET_UINT64_BE(n,b,i) { \
104 (n) = ( (unsigned long long) (b)[(i) ] << 56 ) \
105 | ( (unsigned long long) (b)[(i) + 1] << 48 ) \
106 | ( (unsigned long long) (b)[(i) + 2] << 40 ) \
107 | ( (unsigned long long) (b)[(i) + 3] << 32 ) \
108 | ( (unsigned long long) (b)[(i) + 4] << 24 ) \
109 | ( (unsigned long long) (b)[(i) + 5] << 16 ) \
110 | ( (unsigned long long) (b)[(i) + 6] << 8 ) \
111 | ( (unsigned long long) (b)[(i) + 7] ); \
112 }
113 #endif
114 #ifndef PUT_UINT64_BE
115 #define PUT_UINT64_BE(n,b,i) { \
116 (b)[(i) ] = (unsigned char) ( (n) >> 56 ); \
117 (b)[(i) + 1] = (unsigned char) ( (n) >> 48 ); \
118 (b)[(i) + 2] = (unsigned char) ( (n) >> 40 ); \
119 (b)[(i) + 3] = (unsigned char) ( (n) >> 32 ); \
120 (b)[(i) + 4] = (unsigned char) ( (n) >> 24 ); \
121 (b)[(i) + 5] = (unsigned char) ( (n) >> 16 ); \
122 (b)[(i) + 6] = (unsigned char) ( (n) >> 8 ); \
123 (b)[(i) + 7] = (unsigned char) ( (n) ); \
124 }
125 #endif
126
LOAD_OP(int I,uint64_t * W,const uint8_t * input)127 static inline void LOAD_OP(int I, uint64_t *W, const uint8_t *input)
128 {
129 GET_UINT64_BE(W[I], input, I*8);
130 }
131
BLEND_OP(int I,uint64_t * W)132 static inline void BLEND_OP(int I, uint64_t *W)
133 {
134 W[I & 15] += s1(W[(I-2) & 15]) + W[(I-7) & 15] + s0(W[(I-15) & 15]);
135 }
136
137 static void
sha512_transform(uint64_t * state,const uint8_t * input)138 sha512_transform(uint64_t *state, const uint8_t *input)
139 {
140 uint64_t a, b, c, d, e, f, g, h, t1, t2;
141
142 int i;
143 uint64_t W[16];
144
145 /* load the state into our registers */
146 a=state[0]; b=state[1]; c=state[2]; d=state[3];
147 e=state[4]; f=state[5]; g=state[6]; h=state[7];
148
149 /* now iterate */
150 for (i=0; i<80; i+=8) {
151 if (!(i & 8)) {
152 int j;
153
154 if (i < 16) {
155 /* load the input */
156 for (j = 0; j < 16; j++)
157 LOAD_OP(i + j, W, input);
158 } else {
159 for (j = 0; j < 16; j++) {
160 BLEND_OP(i + j, W);
161 }
162 }
163 }
164
165 t1 = h + e1(e) + Ch(e,f,g) + sha512_K[i ] + W[(i & 15)];
166 t2 = e0(a) + Maj(a,b,c); d+=t1; h=t1+t2;
167 t1 = g + e1(d) + Ch(d,e,f) + sha512_K[i+1] + W[(i & 15) + 1];
168 t2 = e0(h) + Maj(h,a,b); c+=t1; g=t1+t2;
169 t1 = f + e1(c) + Ch(c,d,e) + sha512_K[i+2] + W[(i & 15) + 2];
170 t2 = e0(g) + Maj(g,h,a); b+=t1; f=t1+t2;
171 t1 = e + e1(b) + Ch(b,c,d) + sha512_K[i+3] + W[(i & 15) + 3];
172 t2 = e0(f) + Maj(f,g,h); a+=t1; e=t1+t2;
173 t1 = d + e1(a) + Ch(a,b,c) + sha512_K[i+4] + W[(i & 15) + 4];
174 t2 = e0(e) + Maj(e,f,g); h+=t1; d=t1+t2;
175 t1 = c + e1(h) + Ch(h,a,b) + sha512_K[i+5] + W[(i & 15) + 5];
176 t2 = e0(d) + Maj(d,e,f); g+=t1; c=t1+t2;
177 t1 = b + e1(g) + Ch(g,h,a) + sha512_K[i+6] + W[(i & 15) + 6];
178 t2 = e0(c) + Maj(c,d,e); f+=t1; b=t1+t2;
179 t1 = a + e1(f) + Ch(f,g,h) + sha512_K[i+7] + W[(i & 15) + 7];
180 t2 = e0(b) + Maj(b,c,d); e+=t1; a=t1+t2;
181 }
182
183 state[0] += a; state[1] += b; state[2] += c; state[3] += d;
184 state[4] += e; state[5] += f; state[6] += g; state[7] += h;
185
186 /* erase our data */
187 a = b = c = d = e = f = g = h = t1 = t2 = 0;
188 }
189
sha512_block_fn(sha512_context * sst,const uint8_t * src,int blocks)190 static void sha512_block_fn(sha512_context *sst, const uint8_t *src,
191 int blocks)
192 {
193 while (blocks--) {
194 sha512_transform(sst->state, src);
195 src += SHA512_BLOCK_SIZE;
196 }
197 }
198
sha512_base_do_update(sha512_context * sctx,const uint8_t * data,unsigned int len)199 static void sha512_base_do_update(sha512_context *sctx,
200 const uint8_t *data,
201 unsigned int len)
202 {
203 unsigned int partial = sctx->count[0] % SHA512_BLOCK_SIZE;
204
205 sctx->count[0] += len;
206 if (sctx->count[0] < len)
207 sctx->count[1]++;
208
209 if (unlikely((partial + len) >= SHA512_BLOCK_SIZE)) {
210 int blocks;
211
212 if (partial) {
213 int p = SHA512_BLOCK_SIZE - partial;
214
215 memcpy(sctx->buf + partial, data, p);
216 data += p;
217 len -= p;
218
219 sha512_block_fn(sctx, sctx->buf, 1);
220 }
221
222 blocks = len / SHA512_BLOCK_SIZE;
223 len %= SHA512_BLOCK_SIZE;
224
225 if (blocks) {
226 sha512_block_fn(sctx, data, blocks);
227 data += blocks * SHA512_BLOCK_SIZE;
228 }
229 partial = 0;
230 }
231 if (len)
232 memcpy(sctx->buf + partial, data, len);
233 }
234
sha512_base_do_finalize(sha512_context * sctx)235 static void sha512_base_do_finalize(sha512_context *sctx)
236 {
237 const int bit_offset = SHA512_BLOCK_SIZE - sizeof(uint64_t[2]);
238 uint64_t *bits = (uint64_t *)(sctx->buf + bit_offset);
239 unsigned int partial = sctx->count[0] % SHA512_BLOCK_SIZE;
240
241 sctx->buf[partial++] = 0x80;
242 if (partial > bit_offset) {
243 memset(sctx->buf + partial, 0x0, SHA512_BLOCK_SIZE - partial);
244 partial = 0;
245
246 sha512_block_fn(sctx, sctx->buf, 1);
247 }
248
249 memset(sctx->buf + partial, 0x0, bit_offset - partial);
250 bits[0] = cpu_to_be64(sctx->count[1] << 3 | sctx->count[0] >> 61);
251 bits[1] = cpu_to_be64(sctx->count[0] << 3);
252 sha512_block_fn(sctx, sctx->buf, 1);
253 }
254
255 #if defined(CONFIG_SHA384)
sha384_starts(sha512_context * ctx)256 void sha384_starts(sha512_context * ctx)
257 {
258 ctx->state[0] = SHA384_H0;
259 ctx->state[1] = SHA384_H1;
260 ctx->state[2] = SHA384_H2;
261 ctx->state[3] = SHA384_H3;
262 ctx->state[4] = SHA384_H4;
263 ctx->state[5] = SHA384_H5;
264 ctx->state[6] = SHA384_H6;
265 ctx->state[7] = SHA384_H7;
266 ctx->count[0] = ctx->count[1] = 0;
267 }
268
sha384_update(sha512_context * ctx,const uint8_t * input,uint32_t length)269 void sha384_update(sha512_context *ctx, const uint8_t *input, uint32_t length)
270 {
271 sha512_base_do_update(ctx, input, length);
272 }
273
sha384_finish(sha512_context * ctx,uint8_t digest[SHA384_SUM_LEN])274 void sha384_finish(sha512_context * ctx, uint8_t digest[SHA384_SUM_LEN])
275 {
276 int i;
277
278 sha512_base_do_finalize(ctx);
279 for(i=0; i<SHA384_SUM_LEN / sizeof(uint64_t); i++)
280 PUT_UINT64_BE(ctx->state[i], digest, i * 8);
281 }
282
283 /*
284 * Output = SHA-512( input buffer ). Trigger the watchdog every 'chunk_sz'
285 * bytes of input processed.
286 */
sha384_csum_wd(const unsigned char * input,unsigned int ilen,unsigned char * output,unsigned int chunk_sz)287 void sha384_csum_wd(const unsigned char *input, unsigned int ilen,
288 unsigned char *output, unsigned int chunk_sz)
289 {
290 sha512_context ctx;
291 #if !defined(USE_HOSTCC) && \
292 (defined(CONFIG_HW_WATCHDOG) || defined(CONFIG_WATCHDOG))
293 const unsigned char *end;
294 unsigned char *curr;
295 int chunk;
296 #endif
297
298 sha384_starts(&ctx);
299
300 #if !defined(USE_HOSTCC) && \
301 (defined(CONFIG_HW_WATCHDOG) || defined(CONFIG_WATCHDOG))
302 curr = (unsigned char *)input;
303 end = input + ilen;
304 while (curr < end) {
305 chunk = end - curr;
306 if (chunk > chunk_sz)
307 chunk = chunk_sz;
308 sha384_update(&ctx, curr, chunk);
309 curr += chunk;
310 schedule();
311 }
312 #else
313 sha384_update(&ctx, input, ilen);
314 #endif
315
316 sha384_finish(&ctx, output);
317 }
318
319 #endif
320
sha512_starts(sha512_context * ctx)321 void sha512_starts(sha512_context * ctx)
322 {
323 ctx->state[0] = SHA512_H0;
324 ctx->state[1] = SHA512_H1;
325 ctx->state[2] = SHA512_H2;
326 ctx->state[3] = SHA512_H3;
327 ctx->state[4] = SHA512_H4;
328 ctx->state[5] = SHA512_H5;
329 ctx->state[6] = SHA512_H6;
330 ctx->state[7] = SHA512_H7;
331 ctx->count[0] = ctx->count[1] = 0;
332 }
333
sha512_update(sha512_context * ctx,const uint8_t * input,uint32_t length)334 void sha512_update(sha512_context *ctx, const uint8_t *input, uint32_t length)
335 {
336 sha512_base_do_update(ctx, input, length);
337 }
338
sha512_finish(sha512_context * ctx,uint8_t digest[SHA512_SUM_LEN])339 void sha512_finish(sha512_context * ctx, uint8_t digest[SHA512_SUM_LEN])
340 {
341 int i;
342
343 sha512_base_do_finalize(ctx);
344 for(i=0; i<SHA512_SUM_LEN / sizeof(uint64_t); i++)
345 PUT_UINT64_BE(ctx->state[i], digest, i * 8);
346 }
347
348 /*
349 * Output = SHA-512( input buffer ). Trigger the watchdog every 'chunk_sz'
350 * bytes of input processed.
351 */
sha512_csum_wd(const unsigned char * input,unsigned int ilen,unsigned char * output,unsigned int chunk_sz)352 void sha512_csum_wd(const unsigned char *input, unsigned int ilen,
353 unsigned char *output, unsigned int chunk_sz)
354 {
355 sha512_context ctx;
356 #if !defined(USE_HOSTCC) && \
357 (defined(CONFIG_HW_WATCHDOG) || defined(CONFIG_WATCHDOG))
358 const unsigned char *end;
359 unsigned char *curr;
360 int chunk;
361 #endif
362
363 sha512_starts(&ctx);
364
365 #if !defined(USE_HOSTCC) && \
366 (defined(CONFIG_HW_WATCHDOG) || defined(CONFIG_WATCHDOG))
367 curr = (unsigned char *)input;
368 end = input + ilen;
369 while (curr < end) {
370 chunk = end - curr;
371 if (chunk > chunk_sz)
372 chunk = chunk_sz;
373 sha512_update(&ctx, curr, chunk);
374 curr += chunk;
375 schedule();
376 }
377 #else
378 sha512_update(&ctx, input, ilen);
379 #endif
380
381 sha512_finish(&ctx, output);
382 }
383