crypto/sm3.c

   1 /* SPDX-License-Identifier: GPL-2.0-only */
   2 /*
   3  * SM3 secure hash, as specified by OSCCA GM/T 0004-2012 SM3 and described
   4  * at https://datatracker.ietf.org/doc/html/draft-sca-cfrg-sm3-02
   5  *
   6  * Copyright (C) 2017 ARM Limited or its affiliates.
   7  * Copyright (C) 2017 Gilad Ben-Yossef <gilad@benyossef.com>
   8  * Copyright (C) 2021 Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
   9  */
  10
  11 #include <linux/module.h>
  12 #include <linux/unaligned.h>
  13 #include <crypto/sm3.h>
  14
  15 static const u32 ____cacheline_aligned K[64] = {
  16         0x79cc4519, 0xf3988a32, 0xe7311465, 0xce6228cb,
  17         0x9cc45197, 0x3988a32f, 0x7311465e, 0xe6228cbc,
  18         0xcc451979, 0x988a32f3, 0x311465e7, 0x6228cbce,
  19         0xc451979c, 0x88a32f39, 0x11465e73, 0x228cbce6,
  20         0x9d8a7a87, 0x3b14f50f, 0x7629ea1e, 0xec53d43c,
  21         0xd8a7a879, 0xb14f50f3, 0x629ea1e7, 0xc53d43ce,
  22         0x8a7a879d, 0x14f50f3b, 0x29ea1e76, 0x53d43cec,
  23         0xa7a879d8, 0x4f50f3b1, 0x9ea1e762, 0x3d43cec5,
  24         0x7a879d8a, 0xf50f3b14, 0xea1e7629, 0xd43cec53,
  25         0xa879d8a7, 0x50f3b14f, 0xa1e7629e, 0x43cec53d,
  26         0x879d8a7a, 0x0f3b14f5, 0x1e7629ea, 0x3cec53d4,
  27         0x79d8a7a8, 0xf3b14f50, 0xe7629ea1, 0xcec53d43,
  28         0x9d8a7a87, 0x3b14f50f, 0x7629ea1e, 0xec53d43c,
  29         0xd8a7a879, 0xb14f50f3, 0x629ea1e7, 0xc53d43ce,
  30         0x8a7a879d, 0x14f50f3b, 0x29ea1e76, 0x53d43cec,
  31         0xa7a879d8, 0x4f50f3b1, 0x9ea1e762, 0x3d43cec5
  32 };
  33
  34 /*
  35  * Transform the message X which consists of 16 32-bit-words. See
  36  * GM/T 004-2012 for details.
  37  */
  38 #define R(i, a, b, c, d, e, f, g, h, t, w1, w2)                 \
  39         do {                                                    \
  40                 ss1 = rol32((rol32((a), 12) + (e) + (t)), 7);   \
  41                 ss2 = ss1 ^ rol32((a), 12);                     \
  42                 d += FF ## i(a, b, c) + ss2 + ((w1) ^ (w2));    \
  43                 h += GG ## i(e, f, g) + ss1 + (w1);             \
  44                 b = rol32((b), 9);                              \
  45                 f = rol32((f), 19);                             \
  46                 h = P0((h));                                    \
  47         } while (0)
  48
  49 #define R1(a, b, c, d, e, f, g, h, t, w1, w2) \
  50         R(1, a, b, c, d, e, f, g, h, t, w1, w2)
  51 #define R2(a, b, c, d, e, f, g, h, t, w1, w2) \
  52         R(2, a, b, c, d, e, f, g, h, t, w1, w2)
  53
  54 #define FF1(x, y, z)  (x ^ y ^ z)
  55 #define FF2(x, y, z)  ((x & y) | (x & z) | (y & z))
  56
  57 #define GG1(x, y, z)  FF1(x, y, z)
  58 #define GG2(x, y, z)  ((x & y) | (~x & z))
  59
  60 /* Message expansion */
  61 #define P0(x) ((x) ^ rol32((x), 9) ^ rol32((x), 17))
  62 #define P1(x) ((x) ^ rol32((x), 15) ^ rol32((x), 23))
  63 #define I(i)  (W[i] = get_unaligned_be32(data + i * 4))
  64 #define W1(i) (W[i & 0x0f])
  65 #define W2(i) (W[i & 0x0f] =                            \
  66                 P1(W[i & 0x0f]                          \
  67                         ^ W[(i-9) & 0x0f]               \
  68                         ^ rol32(W[(i-3) & 0x0f], 15))   \
  69                 ^ rol32(W[(i-13) & 0x0f], 7)            \
  70                 ^ W[(i-6) & 0x0f])
  71
  72 static void sm3_transform(struct sm3_state *sctx, u8 const *data, u32 W[16])
  73 {
  74         u32 a, b, c, d, e, f, g, h, ss1, ss2;
  75
  76         a = sctx->state[0];
  77         b = sctx->state[1];
  78         c = sctx->state[2];
  79         d = sctx->state[3];
  80         e = sctx->state[4];
  81         f = sctx->state[5];
  82         g = sctx->state[6];
  83         h = sctx->state[7];
  84
  85         R1(a, b, c, d, e, f, g, h, K[0], I(0), I(4));
  86         R1(d, a, b, c, h, e, f, g, K[1], I(1), I(5));
  87         R1(c, d, a, b, g, h, e, f, K[2], I(2), I(6));
  88         R1(b, c, d, a, f, g, h, e, K[3], I(3), I(7));
  89         R1(a, b, c, d, e, f, g, h, K[4], W1(4), I(8));
  90         R1(d, a, b, c, h, e, f, g, K[5], W1(5), I(9));
  91         R1(c, d, a, b, g, h, e, f, K[6], W1(6), I(10));
  92         R1(b, c, d, a, f, g, h, e, K[7], W1(7), I(11));
  93         R1(a, b, c, d, e, f, g, h, K[8], W1(8), I(12));
  94         R1(d, a, b, c, h, e, f, g, K[9], W1(9), I(13));
  95         R1(c, d, a, b, g, h, e, f, K[10], W1(10), I(14));
  96         R1(b, c, d, a, f, g, h, e, K[11], W1(11), I(15));
  97         R1(a, b, c, d, e, f, g, h, K[12], W1(12), W2(16));
  98         R1(d, a, b, c, h, e, f, g, K[13], W1(13), W2(17));
  99         R1(c, d, a, b, g, h, e, f, K[14], W1(14), W2(18));
 100         R1(b, c, d, a, f, g, h, e, K[15], W1(15), W2(19));
 101
 102         R2(a, b, c, d, e, f, g, h, K[16], W1(16), W2(20));
 103         R2(d, a, b, c, h, e, f, g, K[17], W1(17), W2(21));
 104         R2(c, d, a, b, g, h, e, f, K[18], W1(18), W2(22));
 105         R2(b, c, d, a, f, g, h, e, K[19], W1(19), W2(23));
 106         R2(a, b, c, d, e, f, g, h, K[20], W1(20), W2(24));
 107         R2(d, a, b, c, h, e, f, g, K[21], W1(21), W2(25));
 108         R2(c, d, a, b, g, h, e, f, K[22], W1(22), W2(26));
 109         R2(b, c, d, a, f, g, h, e, K[23], W1(23), W2(27));
 110         R2(a, b, c, d, e, f, g, h, K[24], W1(24), W2(28));
 111         R2(d, a, b, c, h, e, f, g, K[25], W1(25), W2(29));
 112         R2(c, d, a, b, g, h, e, f, K[26], W1(26), W2(30));
 113         R2(b, c, d, a, f, g, h, e, K[27], W1(27), W2(31));
 114         R2(a, b, c, d, e, f, g, h, K[28], W1(28), W2(32));
 115         R2(d, a, b, c, h, e, f, g, K[29], W1(29), W2(33));
 116         R2(c, d, a, b, g, h, e, f, K[30], W1(30), W2(34));
 117         R2(b, c, d, a, f, g, h, e, K[31], W1(31), W2(35));
 118
 119         R2(a, b, c, d, e, f, g, h, K[32], W1(32), W2(36));
 120         R2(d, a, b, c, h, e, f, g, K[33], W1(33), W2(37));
 121         R2(c, d, a, b, g, h, e, f, K[34], W1(34), W2(38));
 122         R2(b, c, d, a, f, g, h, e, K[35], W1(35), W2(39));
 123         R2(a, b, c, d, e, f, g, h, K[36], W1(36), W2(40));
 124         R2(d, a, b, c, h, e, f, g, K[37], W1(37), W2(41));
 125         R2(c, d, a, b, g, h, e, f, K[38], W1(38), W2(42));
 126         R2(b, c, d, a, f, g, h, e, K[39], W1(39), W2(43));
 127         R2(a, b, c, d, e, f, g, h, K[40], W1(40), W2(44));
 128         R2(d, a, b, c, h, e, f, g, K[41], W1(41), W2(45));
 129         R2(c, d, a, b, g, h, e, f, K[42], W1(42), W2(46));
 130         R2(b, c, d, a, f, g, h, e, K[43], W1(43), W2(47));
 131         R2(a, b, c, d, e, f, g, h, K[44], W1(44), W2(48));
 132         R2(d, a, b, c, h, e, f, g, K[45], W1(45), W2(49));
 133         R2(c, d, a, b, g, h, e, f, K[46], W1(46), W2(50));
 134         R2(b, c, d, a, f, g, h, e, K[47], W1(47), W2(51));
 135
 136         R2(a, b, c, d, e, f, g, h, K[48], W1(48), W2(52));
 137         R2(d, a, b, c, h, e, f, g, K[49], W1(49), W2(53));
 138         R2(c, d, a, b, g, h, e, f, K[50], W1(50), W2(54));
 139         R2(b, c, d, a, f, g, h, e, K[51], W1(51), W2(55));
 140         R2(a, b, c, d, e, f, g, h, K[52], W1(52), W2(56));
 141         R2(d, a, b, c, h, e, f, g, K[53], W1(53), W2(57));
 142         R2(c, d, a, b, g, h, e, f, K[54], W1(54), W2(58));
 143         R2(b, c, d, a, f, g, h, e, K[55], W1(55), W2(59));
 144         R2(a, b, c, d, e, f, g, h, K[56], W1(56), W2(60));
 145         R2(d, a, b, c, h, e, f, g, K[57], W1(57), W2(61));
 146         R2(c, d, a, b, g, h, e, f, K[58], W1(58), W2(62));
 147         R2(b, c, d, a, f, g, h, e, K[59], W1(59), W2(63));
 148         R2(a, b, c, d, e, f, g, h, K[60], W1(60), W2(64));
 149         R2(d, a, b, c, h, e, f, g, K[61], W1(61), W2(65));
 150         R2(c, d, a, b, g, h, e, f, K[62], W1(62), W2(66));
 151         R2(b, c, d, a, f, g, h, e, K[63], W1(63), W2(67));
 152
 153         sctx->state[0] ^= a;
 154         sctx->state[1] ^= b;
 155         sctx->state[2] ^= c;
 156         sctx->state[3] ^= d;
 157         sctx->state[4] ^= e;
 158         sctx->state[5] ^= f;
 159         sctx->state[6] ^= g;
 160         sctx->state[7] ^= h;
 161 }
 162 #undef R
 163 #undef R1
 164 #undef R2
 165 #undef I
 166 #undef W1
 167 #undef W2
 168
 169 static inline void sm3_block(struct sm3_state *sctx,
 170                 u8 const *data, int blocks, u32 W[16])
 171 {
 172         while (blocks--) {
 173                 sm3_transform(sctx, data, W);
 174                 data += SM3_BLOCK_SIZE;
 175         }
 176 }
 177
 178 void sm3_update(struct sm3_state *sctx, const u8 *data, unsigned int len)
 179 {
 180         unsigned int partial = sctx->count % SM3_BLOCK_SIZE;
 181         u32 W[16];
 182
 183         sctx->count += len;
 184
 185         if ((partial + len) >= SM3_BLOCK_SIZE) {
 186                 int blocks;
 187
 188                 if (partial) {
 189                         int p = SM3_BLOCK_SIZE - partial;
 190
 191                         memcpy(sctx->buffer + partial, data, p);
 192                         data += p;
 193                         len -= p;
 194
 195                         sm3_block(sctx, sctx->buffer, 1, W);
 196                 }
 197
 198                 blocks = len / SM3_BLOCK_SIZE;
 199                 len %= SM3_BLOCK_SIZE;
 200
 201                 if (blocks) {
 202                         sm3_block(sctx, data, blocks, W);
 203                         data += blocks * SM3_BLOCK_SIZE;
 204                 }
 205
 206                 memzero_explicit(W, sizeof(W));
 207
 208                 partial = 0;
 209         }
 210         if (len)
 211                 memcpy(sctx->buffer + partial, data, len);
 212 }
 213 EXPORT_SYMBOL_GPL(sm3_update);
 214
 215 void sm3_final(struct sm3_state *sctx, u8 *out)
 216 {
 217         const int bit_offset = SM3_BLOCK_SIZE - sizeof(u64);
 218         __be64 *bits = (__be64 *)(sctx->buffer + bit_offset);
 219         __be32 *digest = (__be32 *)out;
 220         unsigned int partial = sctx->count % SM3_BLOCK_SIZE;
 221         u32 W[16];
 222         int i;
 223
 224         sctx->buffer[partial++] = 0x80;
 225         if (partial > bit_offset) {
 226                 memset(sctx->buffer + partial, 0, SM3_BLOCK_SIZE - partial);
 227                 partial = 0;
 228
 229                 sm3_block(sctx, sctx->buffer, 1, W);
 230         }
 231
 232         memset(sctx->buffer + partial, 0, bit_offset - partial);
 233         *bits = cpu_to_be64(sctx->count << 3);
 234         sm3_block(sctx, sctx->buffer, 1, W);
 235
 236         for (i = 0; i < 8; i++)
 237                 put_unaligned_be32(sctx->state[i], digest++);
 238
 239         /* Zeroize sensitive information. */
 240         memzero_explicit(W, sizeof(W));
 241         memzero_explicit(sctx, sizeof(*sctx));
 242 }
 243 EXPORT_SYMBOL_GPL(sm3_final);
 244
 245 MODULE_DESCRIPTION("Generic SM3 library");
 246 MODULE_LICENSE("GPL v2");