--- /dev/null
+/* Modified for SILC. -Pekka */
+/* The AES */
+
+/* This is an independent implementation of the encryption algorithm: */
+/* */
+/* RIJNDAEL by Joan Daemen and Vincent Rijmen */
+/* */
+/* which is a candidate algorithm in the Advanced Encryption Standard */
+/* programme of the US National Institute of Standards and Technology. */
+/* */
+/* Copyright in this implementation is held by Dr B R Gladman but I */
+/* hereby give permission for its free direct or derivative use subject */
+/* to acknowledgment of its origin and compliance with any conditions */
+/* that the originators of the algorithm place on its exploitation. */
+/* */
+/* Dr Brian Gladman (gladman@seven77.demon.co.uk) 14th January 1999 */
+
+/* Timing data for Rijndael (rijndael.c)
+
+Algorithm: rijndael (rijndael.c)
+
+128 bit key:
+Key Setup: 305/1389 cycles (encrypt/decrypt)
+Encrypt: 374 cycles = 68.4 mbits/sec
+Decrypt: 352 cycles = 72.7 mbits/sec
+Mean: 363 cycles = 70.5 mbits/sec
+
+192 bit key:
+Key Setup: 277/1595 cycles (encrypt/decrypt)
+Encrypt: 439 cycles = 58.3 mbits/sec
+Decrypt: 425 cycles = 60.2 mbits/sec
+Mean: 432 cycles = 59.3 mbits/sec
+
+256 bit key:
+Key Setup: 374/1960 cycles (encrypt/decrypt)
+Encrypt: 502 cycles = 51.0 mbits/sec
+Decrypt: 498 cycles = 51.4 mbits/sec
+Mean: 500 cycles = 51.2 mbits/sec
+
+*/
+
+#include "silcincludes.h"
+#include "aes.h"
+
+/*
+ * SILC Crypto API for Rijndael
+ */
+
+/* Sets the key for the cipher. */
+
+SILC_CIPHER_API_SET_KEY(aes)
+{
+ rijndael_set_key((RijndaelContext *)context, (unsigned int *)key, keylen);
+ return 1;
+}
+
+/* Sets the string as a new key for the cipher. The string is first
+ hashed and then used as a new key. */
+
+SILC_CIPHER_API_SET_KEY_WITH_STRING(aes)
+{
+ /* unsigned char key[md5_hash_len];
+ SilcMarsContext *ctx = (SilcMarsContext *)context;
+
+ make_md5_hash(string, &key);
+ memcpy(&ctx->key, mars_set_key(&key, keylen), keylen);
+ memset(&key, 'F', sizeoof(key));
+ */
+
+ return 1;
+}
+
+/* Returns the size of the cipher context. */
+
+SILC_CIPHER_API_CONTEXT_LEN(aes)
+{
+ return sizeof(RijndaelContext);
+}
+
+/* Encrypts with the cipher in CBC mode. Source and destination buffers
+ maybe one and same. */
+
+SILC_CIPHER_API_ENCRYPT_CBC(aes)
+{
+ unsigned int *in, *out, *tiv;
+ unsigned int tmp[4];
+ int i;
+
+ in = (unsigned int *)src;
+ out = (unsigned int *)dst;
+ tiv = (unsigned int *)iv;
+
+ tmp[0] = in[0] ^ tiv[0];
+ tmp[1] = in[1] ^ tiv[1];
+ tmp[2] = in[2] ^ tiv[2];
+ tmp[3] = in[3] ^ tiv[3];
+ rijndael_encrypt((RijndaelContext *)context, tmp, out);
+ in += 4;
+ out += 4;
+
+ for (i = 16; i < len; i += 16) {
+ tmp[0] = in[0] ^ out[0 - 4];
+ tmp[1] = in[1] ^ out[1 - 4];
+ tmp[2] = in[2] ^ out[2 - 4];
+ tmp[3] = in[3] ^ out[3 - 4];
+ rijndael_encrypt((RijndaelContext *)context, tmp, out);
+ in += 4;
+ out += 4;
+ }
+
+ tiv[0] = out[0 - 4];
+ tiv[1] = out[1 - 4];
+ tiv[2] = out[2 - 4];
+ tiv[3] = out[3 - 4];
+
+ return TRUE;
+}
+
+/* Decrypts with the cipher in CBC mode. Source and destination buffers
+ maybe one and same. */
+
+SILC_CIPHER_API_DECRYPT_CBC(aes)
+{
+ unsigned int *tiv, *in, *out;
+ unsigned int tmp[4], tmp2[4];
+ int i;
+
+ in = (unsigned int *)src;
+ out = (unsigned int *)dst;
+ tiv = (unsigned int *)iv;
+
+ tmp[0] = in[0];
+ tmp[1] = in[1];
+ tmp[2] = in[2];
+ tmp[3] = in[3];
+ rijndael_decrypt((RijndaelContext *)context, in, out);
+ out[0] ^= tiv[0];
+ out[1] ^= tiv[1];
+ out[2] ^= tiv[2];
+ out[3] ^= tiv[3];
+ in += 4;
+ out += 4;
+
+ for (i = 16; i < len; i += 16) {
+ tmp2[0] = tmp[0];
+ tmp2[1] = tmp[1];
+ tmp2[2] = tmp[2];
+ tmp2[3] = tmp[3];
+ tmp[0] = in[0];
+ tmp[1] = in[1];
+ tmp[2] = in[2];
+ tmp[3] = in[3];
+ rijndael_decrypt((RijndaelContext *)context, in, out);
+ out[0] ^= tmp2[0];
+ out[1] ^= tmp2[1];
+ out[2] ^= tmp2[2];
+ out[3] ^= tmp2[3];
+ in += 4;
+ out += 4;
+ }
+
+ tiv[0] = tmp[0];
+ tiv[1] = tmp[1];
+ tiv[2] = tmp[2];
+ tiv[3] = tmp[3];
+
+ return TRUE;
+}
+
+#define LARGE_TABLES
+
+u1byte pow_tab[256];
+u1byte log_tab[256];
+u1byte sbx_tab[256];
+u1byte isb_tab[256];
+u4byte rco_tab[ 10];
+u4byte ft_tab[4][256];
+u4byte it_tab[4][256];
+
+u4byte fl_tab[4][256];
+u4byte il_tab[4][256];
+
+u4byte tab_gen = 0;
+
+#define ff_mult(a,b) (a && b ? pow_tab[(log_tab[a] + log_tab[b]) % 255] : 0)
+
+#define f_rn(bo, bi, n, k) \
+ bo[n] = ft_tab[0][byte(bi[n],0)] ^ \
+ ft_tab[1][byte(bi[(n + 1) & 3],1)] ^ \
+ ft_tab[2][byte(bi[(n + 2) & 3],2)] ^ \
+ ft_tab[3][byte(bi[(n + 3) & 3],3)] ^ *(k + n)
+
+#define i_rn(bo, bi, n, k) \
+ bo[n] = it_tab[0][byte(bi[n],0)] ^ \
+ it_tab[1][byte(bi[(n + 3) & 3],1)] ^ \
+ it_tab[2][byte(bi[(n + 2) & 3],2)] ^ \
+ it_tab[3][byte(bi[(n + 1) & 3],3)] ^ *(k + n)
+
+#ifdef LARGE_TABLES
+
+#define ls_box(x) \
+ ( fl_tab[0][byte(x, 0)] ^ \
+ fl_tab[1][byte(x, 1)] ^ \
+ fl_tab[2][byte(x, 2)] ^ \
+ fl_tab[3][byte(x, 3)] )
+
+#define f_rl(bo, bi, n, k) \
+ bo[n] = fl_tab[0][byte(bi[n],0)] ^ \
+ fl_tab[1][byte(bi[(n + 1) & 3],1)] ^ \
+ fl_tab[2][byte(bi[(n + 2) & 3],2)] ^ \
+ fl_tab[3][byte(bi[(n + 3) & 3],3)] ^ *(k + n)
+
+#define i_rl(bo, bi, n, k) \
+ bo[n] = il_tab[0][byte(bi[n],0)] ^ \
+ il_tab[1][byte(bi[(n + 3) & 3],1)] ^ \
+ il_tab[2][byte(bi[(n + 2) & 3],2)] ^ \
+ il_tab[3][byte(bi[(n + 1) & 3],3)] ^ *(k + n)
+
+#else
+
+#define ls_box(x) \
+ ((u4byte)sbx_tab[byte(x, 0)] << 0) ^ \
+ ((u4byte)sbx_tab[byte(x, 1)] << 8) ^ \
+ ((u4byte)sbx_tab[byte(x, 2)] << 16) ^ \
+ ((u4byte)sbx_tab[byte(x, 3)] << 24)
+
+#define f_rl(bo, bi, n, k) \
+ bo[n] = (u4byte)sbx_tab[byte(bi[n],0)] ^ \
+ rotl(((u4byte)sbx_tab[byte(bi[(n + 1) & 3],1)]), 8) ^ \
+ rotl(((u4byte)sbx_tab[byte(bi[(n + 2) & 3],2)]), 16) ^ \
+ rotl(((u4byte)sbx_tab[byte(bi[(n + 3) & 3],3)]), 24) ^ *(k + n)
+
+#define i_rl(bo, bi, n, k) \
+ bo[n] = (u4byte)isb_tab[byte(bi[n],0)] ^ \
+ rotl(((u4byte)isb_tab[byte(bi[(n + 3) & 3],1)]), 8) ^ \
+ rotl(((u4byte)isb_tab[byte(bi[(n + 2) & 3],2)]), 16) ^ \
+ rotl(((u4byte)isb_tab[byte(bi[(n + 1) & 3],3)]), 24) ^ *(k + n)
+
+#endif
+
+void gen_tabs(void)
+{ u4byte i, t;
+ u1byte p, q;
+
+ /* log and power tables for GF(2**8) finite field with */
+ /* 0x11b as modular polynomial - the simplest prmitive */
+ /* root is 0x11, used here to generate the tables */
+
+ for(i = 0,p = 1; i < 256; ++i)
+ {
+ pow_tab[i] = (u1byte)p; log_tab[p] = (u1byte)i;
+
+ p = p ^ (p << 1) ^ (p & 0x80 ? 0x01b : 0);
+ }
+
+ log_tab[1] = 0; p = 1;
+
+ for(i = 0; i < 10; ++i)
+ {
+ rco_tab[i] = p;
+
+ p = (p << 1) ^ (p & 0x80 ? 0x1b : 0);
+ }
+
+ /* note that the affine byte transformation matrix in */
+ /* rijndael specification is in big endian format with */
+ /* bit 0 as the most significant bit. In the remainder */
+ /* of the specification the bits are numbered from the */
+ /* least significant end of a byte. */
+
+ for(i = 0; i < 256; ++i)
+ {
+ p = (i ? pow_tab[255 - log_tab[i]] : 0); q = p;
+ q = (q >> 7) | (q << 1); p ^= q;
+ q = (q >> 7) | (q << 1); p ^= q;
+ q = (q >> 7) | (q << 1); p ^= q;
+ q = (q >> 7) | (q << 1); p ^= q ^ 0x63;
+ sbx_tab[i] = (u1byte)p; isb_tab[p] = (u1byte)i;
+ }
+
+ for(i = 0; i < 256; ++i)
+ {
+ p = sbx_tab[i];
+
+#ifdef LARGE_TABLES
+
+ t = p; fl_tab[0][i] = t;
+ fl_tab[1][i] = rotl(t, 8);
+ fl_tab[2][i] = rotl(t, 16);
+ fl_tab[3][i] = rotl(t, 24);
+#endif
+ t = ((u4byte)ff_mult(2, p)) |
+ ((u4byte)p << 8) |
+ ((u4byte)p << 16) |
+ ((u4byte)ff_mult(3, p) << 24);
+
+ ft_tab[0][i] = t;
+ ft_tab[1][i] = rotl(t, 8);
+ ft_tab[2][i] = rotl(t, 16);
+ ft_tab[3][i] = rotl(t, 24);
+
+ p = isb_tab[i];
+
+#ifdef LARGE_TABLES
+
+ t = p; il_tab[0][i] = t;
+ il_tab[1][i] = rotl(t, 8);
+ il_tab[2][i] = rotl(t, 16);
+ il_tab[3][i] = rotl(t, 24);
+#endif
+ t = ((u4byte)ff_mult(14, p)) |
+ ((u4byte)ff_mult( 9, p) << 8) |
+ ((u4byte)ff_mult(13, p) << 16) |
+ ((u4byte)ff_mult(11, p) << 24);
+
+ it_tab[0][i] = t;
+ it_tab[1][i] = rotl(t, 8);
+ it_tab[2][i] = rotl(t, 16);
+ it_tab[3][i] = rotl(t, 24);
+ }
+
+ tab_gen = 1;
+};
+
+#define star_x(x) (((x) & 0x7f7f7f7f) << 1) ^ ((((x) & 0x80808080) >> 7) * 0x1b)
+
+#define imix_col(y,x) \
+ u = star_x(x); \
+ v = star_x(u); \
+ w = star_x(v); \
+ t = w ^ (x); \
+ (y) = u ^ v ^ w; \
+ (y) ^= rotr(u ^ t, 8) ^ \
+ rotr(v ^ t, 16) ^ \
+ rotr(t,24)
+
+/* initialise the key schedule from the user supplied key */
+
+#define loop4(i) \
+{ \
+ t = ls_box(rotr(t, 8)) ^ rco_tab[i]; \
+ t ^= e_key[4 * i]; e_key[4 * i + 4] = t; \
+ t ^= e_key[4 * i + 1]; e_key[4 * i + 5] = t; \
+ t ^= e_key[4 * i + 2]; e_key[4 * i + 6] = t; \
+ t ^= e_key[4 * i + 3]; e_key[4 * i + 7] = t; \
+}
+
+#define loop6(i) \
+{ t = ls_box(rotr(t, 8)) ^ rco_tab[i]; \
+ t ^= e_key[6 * i]; e_key[6 * i + 6] = t; \
+ t ^= e_key[6 * i + 1]; e_key[6 * i + 7] = t; \
+ t ^= e_key[6 * i + 2]; e_key[6 * i + 8] = t; \
+ t ^= e_key[6 * i + 3]; e_key[6 * i + 9] = t; \
+ t ^= e_key[6 * i + 4]; e_key[6 * i + 10] = t; \
+ t ^= e_key[6 * i + 5]; e_key[6 * i + 11] = t; \
+}
+
+#define loop8(i) \
+{ t = ls_box(rotr(t, 8)) ^ rco_tab[i]; \
+ t ^= e_key[8 * i]; e_key[8 * i + 8] = t; \
+ t ^= e_key[8 * i + 1]; e_key[8 * i + 9] = t; \
+ t ^= e_key[8 * i + 2]; e_key[8 * i + 10] = t; \
+ t ^= e_key[8 * i + 3]; e_key[8 * i + 11] = t; \
+ t = e_key[8 * i + 4] ^ ls_box(t); \
+ e_key[8 * i + 12] = t; \
+ t ^= e_key[8 * i + 5]; e_key[8 * i + 13] = t; \
+ t ^= e_key[8 * i + 6]; e_key[8 * i + 14] = t; \
+ t ^= e_key[8 * i + 7]; e_key[8 * i + 15] = t; \
+}
+
+u4byte *rijndael_set_key(RijndaelContext *ctx,
+ const u4byte in_key[], const u4byte key_len)
+{
+ u4byte i, t, u, v, w;
+ u4byte *e_key = ctx->e_key;
+ u4byte *d_key = ctx->d_key;
+ u4byte k_len;
+
+ if(!tab_gen)
+ gen_tabs();
+
+ k_len = ctx->k_len = (key_len + 31) / 32;
+
+ e_key[0] = in_key[0]; e_key[1] = in_key[1];
+ e_key[2] = in_key[2]; e_key[3] = in_key[3];
+
+ switch(k_len)
+ {
+ case 4: t = e_key[3];
+ for(i = 0; i < 10; ++i)
+ loop4(i);
+ break;
+
+ case 6: e_key[4] = in_key[4]; t = e_key[5] = in_key[5];
+ for(i = 0; i < 8; ++i)
+ loop6(i);
+ break;
+
+ case 8: e_key[4] = in_key[4]; e_key[5] = in_key[5];
+ e_key[6] = in_key[6]; t = e_key[7] = in_key[7];
+ for(i = 0; i < 7; ++i)
+ loop8(i);
+ break;
+ }
+
+ d_key[0] = e_key[0]; d_key[1] = e_key[1];
+ d_key[2] = e_key[2]; d_key[3] = e_key[3];
+
+ for(i = 4; i < 4 * k_len + 24; ++i)
+ {
+ imix_col(d_key[i], e_key[i]);
+ }
+
+ return e_key;
+};
+
+/* encrypt a block of text */
+
+#define f_nround(bo, bi, k) \
+ f_rn(bo, bi, 0, k); \
+ f_rn(bo, bi, 1, k); \
+ f_rn(bo, bi, 2, k); \
+ f_rn(bo, bi, 3, k); \
+ k += 4
+
+#define f_lround(bo, bi, k) \
+ f_rl(bo, bi, 0, k); \
+ f_rl(bo, bi, 1, k); \
+ f_rl(bo, bi, 2, k); \
+ f_rl(bo, bi, 3, k)
+
+void rijndael_encrypt(RijndaelContext *ctx,
+ const u4byte in_blk[4], u4byte out_blk[4])
+{
+ u4byte b0[4], b1[4], *kp;
+ u4byte *e_key = ctx->e_key;
+ u4byte k_len = ctx->k_len;
+
+ b0[0] = in_blk[0] ^ e_key[0]; b0[1] = in_blk[1] ^ e_key[1];
+ b0[2] = in_blk[2] ^ e_key[2]; b0[3] = in_blk[3] ^ e_key[3];
+
+ kp = e_key + 4;
+
+ if(k_len > 6)
+ {
+ f_nround(b1, b0, kp); f_nround(b0, b1, kp);
+ }
+
+ if(k_len > 4)
+ {
+ f_nround(b1, b0, kp); f_nround(b0, b1, kp);
+ }
+
+ f_nround(b1, b0, kp); f_nround(b0, b1, kp);
+ f_nround(b1, b0, kp); f_nround(b0, b1, kp);
+ f_nround(b1, b0, kp); f_nround(b0, b1, kp);
+ f_nround(b1, b0, kp); f_nround(b0, b1, kp);
+ f_nround(b1, b0, kp); f_lround(b0, b1, kp);
+
+ out_blk[0] = b0[0]; out_blk[1] = b0[1];
+ out_blk[2] = b0[2]; out_blk[3] = b0[3];
+};
+
+/* decrypt a block of text */
+
+#define i_nround(bo, bi, k) \
+ i_rn(bo, bi, 0, k); \
+ i_rn(bo, bi, 1, k); \
+ i_rn(bo, bi, 2, k); \
+ i_rn(bo, bi, 3, k); \
+ k -= 4
+
+#define i_lround(bo, bi, k) \
+ i_rl(bo, bi, 0, k); \
+ i_rl(bo, bi, 1, k); \
+ i_rl(bo, bi, 2, k); \
+ i_rl(bo, bi, 3, k)
+
+void rijndael_decrypt(RijndaelContext *ctx,
+ const u4byte in_blk[4], u4byte out_blk[4])
+{
+ u4byte b0[4], b1[4], *kp;
+ u4byte *e_key = ctx->e_key;
+ u4byte *d_key = ctx->d_key;
+ u4byte k_len = ctx->k_len;
+
+ b0[0] = in_blk[0] ^ e_key[4 * k_len + 24]; b0[1] = in_blk[1] ^ e_key[4 * k_len + 25];
+ b0[2] = in_blk[2] ^ e_key[4 * k_len + 26]; b0[3] = in_blk[3] ^ e_key[4 * k_len + 27];
+
+ kp = d_key + 4 * (k_len + 5);
+
+ if(k_len > 6)
+ {
+ i_nround(b1, b0, kp); i_nround(b0, b1, kp);
+ }
+
+ if(k_len > 4)
+ {
+ i_nround(b1, b0, kp); i_nround(b0, b1, kp);
+ }
+
+ i_nround(b1, b0, kp); i_nround(b0, b1, kp);
+ i_nround(b1, b0, kp); i_nround(b0, b1, kp);
+ i_nround(b1, b0, kp); i_nround(b0, b1, kp);
+ i_nround(b1, b0, kp); i_nround(b0, b1, kp);
+ i_nround(b1, b0, kp); i_lround(b0, b1, kp);
+
+ out_blk[0] = b0[0]; out_blk[1] = b0[1];
+ out_blk[2] = b0[2]; out_blk[3] = b0[3];
+};
projects / crypto.git / blobdiff