aboutsummaryrefslogtreecommitdiffstats
path: root/crypto/aes/aes_core.c
diff options
context:
space:
mode:
Diffstat (limited to 'crypto/aes/aes_core.c')
-rw-r--r--crypto/aes/aes_core.c805
1 files changed, 405 insertions, 400 deletions
diff --git a/crypto/aes/aes_core.c b/crypto/aes/aes_core.c
index 8f5210ac70a9..2ddb0860d78a 100644
--- a/crypto/aes/aes_core.c
+++ b/crypto/aes/aes_core.c
@@ -40,7 +40,7 @@
#include "aes_locl.h"
#ifndef AES_ASM
-/*
+/*-
Te0[x] = S [x].[02, 01, 01, 03];
Te1[x] = S [x].[03, 02, 01, 01];
Te2[x] = S [x].[01, 03, 02, 01];
@@ -617,161 +617,163 @@ static const u8 Td4[256] = {
0xe1U, 0x69U, 0x14U, 0x63U, 0x55U, 0x21U, 0x0cU, 0x7dU,
};
static const u32 rcon[] = {
- 0x01000000, 0x02000000, 0x04000000, 0x08000000,
- 0x10000000, 0x20000000, 0x40000000, 0x80000000,
- 0x1B000000, 0x36000000, /* for 128-bit blocks, Rijndael never uses more than 10 rcon values */
+ 0x01000000, 0x02000000, 0x04000000, 0x08000000,
+ 0x10000000, 0x20000000, 0x40000000, 0x80000000,
+ 0x1B000000, 0x36000000, /* for 128-bit blocks, Rijndael never uses more than 10 rcon values */
};
/**
* Expand the cipher key into the encryption key schedule.
*/
int private_AES_set_encrypt_key(const unsigned char *userKey, const int bits,
- AES_KEY *key) {
+ AES_KEY *key)
+{
- u32 *rk;
- int i = 0;
- u32 temp;
+ u32 *rk;
+ int i = 0;
+ u32 temp;
- if (!userKey || !key)
- return -1;
- if (bits != 128 && bits != 192 && bits != 256)
- return -2;
+ if (!userKey || !key)
+ return -1;
+ if (bits != 128 && bits != 192 && bits != 256)
+ return -2;
- rk = key->rd_key;
+ rk = key->rd_key;
- if (bits==128)
- key->rounds = 10;
- else if (bits==192)
- key->rounds = 12;
- else
- key->rounds = 14;
+ if (bits==128)
+ key->rounds = 10;
+ else if (bits==192)
+ key->rounds = 12;
+ else
+ key->rounds = 14;
- rk[0] = GETU32(userKey );
- rk[1] = GETU32(userKey + 4);
- rk[2] = GETU32(userKey + 8);
- rk[3] = GETU32(userKey + 12);
- if (bits == 128) {
- while (1) {
- temp = rk[3];
- rk[4] = rk[0] ^
- (Te2[(temp >> 16) & 0xff] & 0xff000000) ^
- (Te3[(temp >> 8) & 0xff] & 0x00ff0000) ^
- (Te0[(temp ) & 0xff] & 0x0000ff00) ^
- (Te1[(temp >> 24) ] & 0x000000ff) ^
- rcon[i];
- rk[5] = rk[1] ^ rk[4];
- rk[6] = rk[2] ^ rk[5];
- rk[7] = rk[3] ^ rk[6];
- if (++i == 10) {
- return 0;
- }
- rk += 4;
- }
- }
- rk[4] = GETU32(userKey + 16);
- rk[5] = GETU32(userKey + 20);
- if (bits == 192) {
- while (1) {
- temp = rk[ 5];
- rk[ 6] = rk[ 0] ^
- (Te2[(temp >> 16) & 0xff] & 0xff000000) ^
- (Te3[(temp >> 8) & 0xff] & 0x00ff0000) ^
- (Te0[(temp ) & 0xff] & 0x0000ff00) ^
- (Te1[(temp >> 24) ] & 0x000000ff) ^
- rcon[i];
- rk[ 7] = rk[ 1] ^ rk[ 6];
- rk[ 8] = rk[ 2] ^ rk[ 7];
- rk[ 9] = rk[ 3] ^ rk[ 8];
- if (++i == 8) {
- return 0;
- }
- rk[10] = rk[ 4] ^ rk[ 9];
- rk[11] = rk[ 5] ^ rk[10];
- rk += 6;
- }
- }
- rk[6] = GETU32(userKey + 24);
- rk[7] = GETU32(userKey + 28);
- if (bits == 256) {
- while (1) {
- temp = rk[ 7];
- rk[ 8] = rk[ 0] ^
- (Te2[(temp >> 16) & 0xff] & 0xff000000) ^
- (Te3[(temp >> 8) & 0xff] & 0x00ff0000) ^
- (Te0[(temp ) & 0xff] & 0x0000ff00) ^
- (Te1[(temp >> 24) ] & 0x000000ff) ^
- rcon[i];
- rk[ 9] = rk[ 1] ^ rk[ 8];
- rk[10] = rk[ 2] ^ rk[ 9];
- rk[11] = rk[ 3] ^ rk[10];
- if (++i == 7) {
- return 0;
- }
- temp = rk[11];
- rk[12] = rk[ 4] ^
- (Te2[(temp >> 24) ] & 0xff000000) ^
- (Te3[(temp >> 16) & 0xff] & 0x00ff0000) ^
- (Te0[(temp >> 8) & 0xff] & 0x0000ff00) ^
- (Te1[(temp ) & 0xff] & 0x000000ff);
- rk[13] = rk[ 5] ^ rk[12];
- rk[14] = rk[ 6] ^ rk[13];
- rk[15] = rk[ 7] ^ rk[14];
+ rk[0] = GETU32(userKey );
+ rk[1] = GETU32(userKey + 4);
+ rk[2] = GETU32(userKey + 8);
+ rk[3] = GETU32(userKey + 12);
+ if (bits == 128) {
+ while (1) {
+ temp = rk[3];
+ rk[4] = rk[0] ^
+ (Te2[(temp >> 16) & 0xff] & 0xff000000) ^
+ (Te3[(temp >> 8) & 0xff] & 0x00ff0000) ^
+ (Te0[(temp ) & 0xff] & 0x0000ff00) ^
+ (Te1[(temp >> 24) ] & 0x000000ff) ^
+ rcon[i];
+ rk[5] = rk[1] ^ rk[4];
+ rk[6] = rk[2] ^ rk[5];
+ rk[7] = rk[3] ^ rk[6];
+ if (++i == 10) {
+ return 0;
+ }
+ rk += 4;
+ }
+ }
+ rk[4] = GETU32(userKey + 16);
+ rk[5] = GETU32(userKey + 20);
+ if (bits == 192) {
+ while (1) {
+ temp = rk[ 5];
+ rk[ 6] = rk[ 0] ^
+ (Te2[(temp >> 16) & 0xff] & 0xff000000) ^
+ (Te3[(temp >> 8) & 0xff] & 0x00ff0000) ^
+ (Te0[(temp ) & 0xff] & 0x0000ff00) ^
+ (Te1[(temp >> 24) ] & 0x000000ff) ^
+ rcon[i];
+ rk[ 7] = rk[ 1] ^ rk[ 6];
+ rk[ 8] = rk[ 2] ^ rk[ 7];
+ rk[ 9] = rk[ 3] ^ rk[ 8];
+ if (++i == 8) {
+ return 0;
+ }
+ rk[10] = rk[ 4] ^ rk[ 9];
+ rk[11] = rk[ 5] ^ rk[10];
+ rk += 6;
+ }
+ }
+ rk[6] = GETU32(userKey + 24);
+ rk[7] = GETU32(userKey + 28);
+ if (bits == 256) {
+ while (1) {
+ temp = rk[ 7];
+ rk[ 8] = rk[ 0] ^
+ (Te2[(temp >> 16) & 0xff] & 0xff000000) ^
+ (Te3[(temp >> 8) & 0xff] & 0x00ff0000) ^
+ (Te0[(temp ) & 0xff] & 0x0000ff00) ^
+ (Te1[(temp >> 24) ] & 0x000000ff) ^
+ rcon[i];
+ rk[ 9] = rk[ 1] ^ rk[ 8];
+ rk[10] = rk[ 2] ^ rk[ 9];
+ rk[11] = rk[ 3] ^ rk[10];
+ if (++i == 7) {
+ return 0;
+ }
+ temp = rk[11];
+ rk[12] = rk[ 4] ^
+ (Te2[(temp >> 24) ] & 0xff000000) ^
+ (Te3[(temp >> 16) & 0xff] & 0x00ff0000) ^
+ (Te0[(temp >> 8) & 0xff] & 0x0000ff00) ^
+ (Te1[(temp ) & 0xff] & 0x000000ff);
+ rk[13] = rk[ 5] ^ rk[12];
+ rk[14] = rk[ 6] ^ rk[13];
+ rk[15] = rk[ 7] ^ rk[14];
- rk += 8;
- }
- }
- return 0;
+ rk += 8;
+ }
+ }
+ return 0;
}
/**
* Expand the cipher key into the decryption key schedule.
*/
int private_AES_set_decrypt_key(const unsigned char *userKey, const int bits,
- AES_KEY *key) {
+ AES_KEY *key)
+{
- u32 *rk;
- int i, j, status;
- u32 temp;
+ u32 *rk;
+ int i, j, status;
+ u32 temp;
- /* first, start with an encryption schedule */
- status = private_AES_set_encrypt_key(userKey, bits, key);
- if (status < 0)
- return status;
+ /* first, start with an encryption schedule */
+ status = private_AES_set_encrypt_key(userKey, bits, key);
+ if (status < 0)
+ return status;
- rk = key->rd_key;
+ rk = key->rd_key;
- /* invert the order of the round keys: */
- for (i = 0, j = 4*(key->rounds); i < j; i += 4, j -= 4) {
- temp = rk[i ]; rk[i ] = rk[j ]; rk[j ] = temp;
- temp = rk[i + 1]; rk[i + 1] = rk[j + 1]; rk[j + 1] = temp;
- temp = rk[i + 2]; rk[i + 2] = rk[j + 2]; rk[j + 2] = temp;
- temp = rk[i + 3]; rk[i + 3] = rk[j + 3]; rk[j + 3] = temp;
- }
- /* apply the inverse MixColumn transform to all round keys but the first and the last: */
- for (i = 1; i < (key->rounds); i++) {
- rk += 4;
- rk[0] =
- Td0[Te1[(rk[0] >> 24) ] & 0xff] ^
- Td1[Te1[(rk[0] >> 16) & 0xff] & 0xff] ^
- Td2[Te1[(rk[0] >> 8) & 0xff] & 0xff] ^
- Td3[Te1[(rk[0] ) & 0xff] & 0xff];
- rk[1] =
- Td0[Te1[(rk[1] >> 24) ] & 0xff] ^
- Td1[Te1[(rk[1] >> 16) & 0xff] & 0xff] ^
- Td2[Te1[(rk[1] >> 8) & 0xff] & 0xff] ^
- Td3[Te1[(rk[1] ) & 0xff] & 0xff];
- rk[2] =
- Td0[Te1[(rk[2] >> 24) ] & 0xff] ^
- Td1[Te1[(rk[2] >> 16) & 0xff] & 0xff] ^
- Td2[Te1[(rk[2] >> 8) & 0xff] & 0xff] ^
- Td3[Te1[(rk[2] ) & 0xff] & 0xff];
- rk[3] =
- Td0[Te1[(rk[3] >> 24) ] & 0xff] ^
- Td1[Te1[(rk[3] >> 16) & 0xff] & 0xff] ^
- Td2[Te1[(rk[3] >> 8) & 0xff] & 0xff] ^
- Td3[Te1[(rk[3] ) & 0xff] & 0xff];
- }
- return 0;
+ /* invert the order of the round keys: */
+ for (i = 0, j = 4*(key->rounds); i < j; i += 4, j -= 4) {
+ temp = rk[i ]; rk[i ] = rk[j ]; rk[j ] = temp;
+ temp = rk[i + 1]; rk[i + 1] = rk[j + 1]; rk[j + 1] = temp;
+ temp = rk[i + 2]; rk[i + 2] = rk[j + 2]; rk[j + 2] = temp;
+ temp = rk[i + 3]; rk[i + 3] = rk[j + 3]; rk[j + 3] = temp;
+ }
+ /* apply the inverse MixColumn transform to all round keys but the first and the last: */
+ for (i = 1; i < (key->rounds); i++) {
+ rk += 4;
+ rk[0] =
+ Td0[Te1[(rk[0] >> 24) ] & 0xff] ^
+ Td1[Te1[(rk[0] >> 16) & 0xff] & 0xff] ^
+ Td2[Te1[(rk[0] >> 8) & 0xff] & 0xff] ^
+ Td3[Te1[(rk[0] ) & 0xff] & 0xff];
+ rk[1] =
+ Td0[Te1[(rk[1] >> 24) ] & 0xff] ^
+ Td1[Te1[(rk[1] >> 16) & 0xff] & 0xff] ^
+ Td2[Te1[(rk[1] >> 8) & 0xff] & 0xff] ^
+ Td3[Te1[(rk[1] ) & 0xff] & 0xff];
+ rk[2] =
+ Td0[Te1[(rk[2] >> 24) ] & 0xff] ^
+ Td1[Te1[(rk[2] >> 16) & 0xff] & 0xff] ^
+ Td2[Te1[(rk[2] >> 8) & 0xff] & 0xff] ^
+ Td3[Te1[(rk[2] ) & 0xff] & 0xff];
+ rk[3] =
+ Td0[Te1[(rk[3] >> 24) ] & 0xff] ^
+ Td1[Te1[(rk[3] >> 16) & 0xff] & 0xff] ^
+ Td2[Te1[(rk[3] >> 8) & 0xff] & 0xff] ^
+ Td3[Te1[(rk[3] ) & 0xff] & 0xff];
+ }
+ return 0;
}
/*
@@ -779,71 +781,71 @@ int private_AES_set_decrypt_key(const unsigned char *userKey, const int bits,
* in and out can overlap
*/
void AES_encrypt(const unsigned char *in, unsigned char *out,
- const AES_KEY *key) {
+ const AES_KEY *key) {
- const u32 *rk;
- u32 s0, s1, s2, s3, t0, t1, t2, t3;
+ const u32 *rk;
+ u32 s0, s1, s2, s3, t0, t1, t2, t3;
#ifndef FULL_UNROLL
- int r;
+ int r;
#endif /* ?FULL_UNROLL */
- assert(in && out && key);
- rk = key->rd_key;
+ assert(in && out && key);
+ rk = key->rd_key;
- /*
- * map byte array block to cipher state
- * and add initial round key:
- */
- s0 = GETU32(in ) ^ rk[0];
- s1 = GETU32(in + 4) ^ rk[1];
- s2 = GETU32(in + 8) ^ rk[2];
- s3 = GETU32(in + 12) ^ rk[3];
+ /*
+ * map byte array block to cipher state
+ * and add initial round key:
+ */
+ s0 = GETU32(in ) ^ rk[0];
+ s1 = GETU32(in + 4) ^ rk[1];
+ s2 = GETU32(in + 8) ^ rk[2];
+ s3 = GETU32(in + 12) ^ rk[3];
#ifdef FULL_UNROLL
- /* round 1: */
- t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >> 8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[ 4];
- t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >> 8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[ 5];
- t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >> 8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[ 6];
- t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >> 8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[ 7];
- /* round 2: */
- s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >> 8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[ 8];
- s1 = Te0[t1 >> 24] ^ Te1[(t2 >> 16) & 0xff] ^ Te2[(t3 >> 8) & 0xff] ^ Te3[t0 & 0xff] ^ rk[ 9];
- s2 = Te0[t2 >> 24] ^ Te1[(t3 >> 16) & 0xff] ^ Te2[(t0 >> 8) & 0xff] ^ Te3[t1 & 0xff] ^ rk[10];
- s3 = Te0[t3 >> 24] ^ Te1[(t0 >> 16) & 0xff] ^ Te2[(t1 >> 8) & 0xff] ^ Te3[t2 & 0xff] ^ rk[11];
- /* round 3: */
- t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >> 8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[12];
- t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >> 8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[13];
- t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >> 8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[14];
- t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >> 8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[15];
- /* round 4: */
- s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >> 8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[16];
- s1 = Te0[t1 >> 24] ^ Te1[(t2 >> 16) & 0xff] ^ Te2[(t3 >> 8) & 0xff] ^ Te3[t0 & 0xff] ^ rk[17];
- s2 = Te0[t2 >> 24] ^ Te1[(t3 >> 16) & 0xff] ^ Te2[(t0 >> 8) & 0xff] ^ Te3[t1 & 0xff] ^ rk[18];
- s3 = Te0[t3 >> 24] ^ Te1[(t0 >> 16) & 0xff] ^ Te2[(t1 >> 8) & 0xff] ^ Te3[t2 & 0xff] ^ rk[19];
- /* round 5: */
- t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >> 8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[20];
- t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >> 8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[21];
- t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >> 8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[22];
- t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >> 8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[23];
- /* round 6: */
- s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >> 8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[24];
- s1 = Te0[t1 >> 24] ^ Te1[(t2 >> 16) & 0xff] ^ Te2[(t3 >> 8) & 0xff] ^ Te3[t0 & 0xff] ^ rk[25];
- s2 = Te0[t2 >> 24] ^ Te1[(t3 >> 16) & 0xff] ^ Te2[(t0 >> 8) & 0xff] ^ Te3[t1 & 0xff] ^ rk[26];
- s3 = Te0[t3 >> 24] ^ Te1[(t0 >> 16) & 0xff] ^ Te2[(t1 >> 8) & 0xff] ^ Te3[t2 & 0xff] ^ rk[27];
- /* round 7: */
- t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >> 8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[28];
- t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >> 8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[29];
- t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >> 8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[30];
- t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >> 8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[31];
- /* round 8: */
- s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >> 8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[32];
- s1 = Te0[t1 >> 24] ^ Te1[(t2 >> 16) & 0xff] ^ Te2[(t3 >> 8) & 0xff] ^ Te3[t0 & 0xff] ^ rk[33];
- s2 = Te0[t2 >> 24] ^ Te1[(t3 >> 16) & 0xff] ^ Te2[(t0 >> 8) & 0xff] ^ Te3[t1 & 0xff] ^ rk[34];
- s3 = Te0[t3 >> 24] ^ Te1[(t0 >> 16) & 0xff] ^ Te2[(t1 >> 8) & 0xff] ^ Te3[t2 & 0xff] ^ rk[35];
- /* round 9: */
- t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >> 8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[36];
- t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >> 8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[37];
- t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >> 8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[38];
- t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >> 8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[39];
+ /* round 1: */
+ t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >> 8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[ 4];
+ t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >> 8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[ 5];
+ t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >> 8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[ 6];
+ t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >> 8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[ 7];
+ /* round 2: */
+ s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >> 8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[ 8];
+ s1 = Te0[t1 >> 24] ^ Te1[(t2 >> 16) & 0xff] ^ Te2[(t3 >> 8) & 0xff] ^ Te3[t0 & 0xff] ^ rk[ 9];
+ s2 = Te0[t2 >> 24] ^ Te1[(t3 >> 16) & 0xff] ^ Te2[(t0 >> 8) & 0xff] ^ Te3[t1 & 0xff] ^ rk[10];
+ s3 = Te0[t3 >> 24] ^ Te1[(t0 >> 16) & 0xff] ^ Te2[(t1 >> 8) & 0xff] ^ Te3[t2 & 0xff] ^ rk[11];
+ /* round 3: */
+ t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >> 8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[12];
+ t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >> 8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[13];
+ t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >> 8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[14];
+ t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >> 8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[15];
+ /* round 4: */
+ s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >> 8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[16];
+ s1 = Te0[t1 >> 24] ^ Te1[(t2 >> 16) & 0xff] ^ Te2[(t3 >> 8) & 0xff] ^ Te3[t0 & 0xff] ^ rk[17];
+ s2 = Te0[t2 >> 24] ^ Te1[(t3 >> 16) & 0xff] ^ Te2[(t0 >> 8) & 0xff] ^ Te3[t1 & 0xff] ^ rk[18];
+ s3 = Te0[t3 >> 24] ^ Te1[(t0 >> 16) & 0xff] ^ Te2[(t1 >> 8) & 0xff] ^ Te3[t2 & 0xff] ^ rk[19];
+ /* round 5: */
+ t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >> 8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[20];
+ t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >> 8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[21];
+ t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >> 8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[22];
+ t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >> 8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[23];
+ /* round 6: */
+ s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >> 8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[24];
+ s1 = Te0[t1 >> 24] ^ Te1[(t2 >> 16) & 0xff] ^ Te2[(t3 >> 8) & 0xff] ^ Te3[t0 & 0xff] ^ rk[25];
+ s2 = Te0[t2 >> 24] ^ Te1[(t3 >> 16) & 0xff] ^ Te2[(t0 >> 8) & 0xff] ^ Te3[t1 & 0xff] ^ rk[26];
+ s3 = Te0[t3 >> 24] ^ Te1[(t0 >> 16) & 0xff] ^ Te2[(t1 >> 8) & 0xff] ^ Te3[t2 & 0xff] ^ rk[27];
+ /* round 7: */
+ t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >> 8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[28];
+ t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >> 8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[29];
+ t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >> 8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[30];
+ t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >> 8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[31];
+ /* round 8: */
+ s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >> 8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[32];
+ s1 = Te0[t1 >> 24] ^ Te1[(t2 >> 16) & 0xff] ^ Te2[(t3 >> 8) & 0xff] ^ Te3[t0 & 0xff] ^ rk[33];
+ s2 = Te0[t2 >> 24] ^ Te1[(t3 >> 16) & 0xff] ^ Te2[(t0 >> 8) & 0xff] ^ Te3[t1 & 0xff] ^ rk[34];
+ s3 = Te0[t3 >> 24] ^ Te1[(t0 >> 16) & 0xff] ^ Te2[(t1 >> 8) & 0xff] ^ Te3[t2 & 0xff] ^ rk[35];
+ /* round 9: */
+ t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >> 8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[36];
+ t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >> 8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[37];
+ t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >> 8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[38];
+ t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >> 8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[39];
if (key->rounds > 10) {
/* round 10: */
s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >> 8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[40];
@@ -932,37 +934,37 @@ void AES_encrypt(const unsigned char *in, unsigned char *out,
}
#endif /* ?FULL_UNROLL */
/*
- * apply last round and
- * map cipher state to byte array block:
- */
- s0 =
- (Te2[(t0 >> 24) ] & 0xff000000) ^
- (Te3[(t1 >> 16) & 0xff] & 0x00ff0000) ^
- (Te0[(t2 >> 8) & 0xff] & 0x0000ff00) ^
- (Te1[(t3 ) & 0xff] & 0x000000ff) ^
- rk[0];
- PUTU32(out , s0);
- s1 =
- (Te2[(t1 >> 24) ] & 0xff000000) ^
- (Te3[(t2 >> 16) & 0xff] & 0x00ff0000) ^
- (Te0[(t3 >> 8) & 0xff] & 0x0000ff00) ^
- (Te1[(t0 ) & 0xff] & 0x000000ff) ^
- rk[1];
- PUTU32(out + 4, s1);
- s2 =
- (Te2[(t2 >> 24) ] & 0xff000000) ^
- (Te3[(t3 >> 16) & 0xff] & 0x00ff0000) ^
- (Te0[(t0 >> 8) & 0xff] & 0x0000ff00) ^
- (Te1[(t1 ) & 0xff] & 0x000000ff) ^
- rk[2];
- PUTU32(out + 8, s2);
- s3 =
- (Te2[(t3 >> 24) ] & 0xff000000) ^
- (Te3[(t0 >> 16) & 0xff] & 0x00ff0000) ^
- (Te0[(t1 >> 8) & 0xff] & 0x0000ff00) ^
- (Te1[(t2 ) & 0xff] & 0x000000ff) ^
- rk[3];
- PUTU32(out + 12, s3);
+ * apply last round and
+ * map cipher state to byte array block:
+ */
+ s0 =
+ (Te2[(t0 >> 24) ] & 0xff000000) ^
+ (Te3[(t1 >> 16) & 0xff] & 0x00ff0000) ^
+ (Te0[(t2 >> 8) & 0xff] & 0x0000ff00) ^
+ (Te1[(t3 ) & 0xff] & 0x000000ff) ^
+ rk[0];
+ PUTU32(out , s0);
+ s1 =
+ (Te2[(t1 >> 24) ] & 0xff000000) ^
+ (Te3[(t2 >> 16) & 0xff] & 0x00ff0000) ^
+ (Te0[(t3 >> 8) & 0xff] & 0x0000ff00) ^
+ (Te1[(t0 ) & 0xff] & 0x000000ff) ^
+ rk[1];
+ PUTU32(out + 4, s1);
+ s2 =
+ (Te2[(t2 >> 24) ] & 0xff000000) ^
+ (Te3[(t3 >> 16) & 0xff] & 0x00ff0000) ^
+ (Te0[(t0 >> 8) & 0xff] & 0x0000ff00) ^
+ (Te1[(t1 ) & 0xff] & 0x000000ff) ^
+ rk[2];
+ PUTU32(out + 8, s2);
+ s3 =
+ (Te2[(t3 >> 24) ] & 0xff000000) ^
+ (Te3[(t0 >> 16) & 0xff] & 0x00ff0000) ^
+ (Te0[(t1 >> 8) & 0xff] & 0x0000ff00) ^
+ (Te1[(t2 ) & 0xff] & 0x000000ff) ^
+ rk[3];
+ PUTU32(out + 12, s3);
}
/*
@@ -970,21 +972,22 @@ void AES_encrypt(const unsigned char *in, unsigned char *out,
* in and out can overlap
*/
void AES_decrypt(const unsigned char *in, unsigned char *out,
- const AES_KEY *key) {
+ const AES_KEY *key)
+{
- const u32 *rk;
- u32 s0, s1, s2, s3, t0, t1, t2, t3;
+ const u32 *rk;
+ u32 s0, s1, s2, s3, t0, t1, t2, t3;
#ifndef FULL_UNROLL
- int r;
+ int r;
#endif /* ?FULL_UNROLL */
- assert(in && out && key);
- rk = key->rd_key;
+ assert(in && out && key);
+ rk = key->rd_key;
- /*
- * map byte array block to cipher state
- * and add initial round key:
- */
+ /*
+ * map byte array block to cipher state
+ * and add initial round key:
+ */
s0 = GETU32(in ) ^ rk[0];
s1 = GETU32(in + 4) ^ rk[1];
s2 = GETU32(in + 8) ^ rk[2];
@@ -1059,7 +1062,7 @@ void AES_decrypt(const unsigned char *in, unsigned char *out,
t3 = Td0[s3 >> 24] ^ Td1[(s2 >> 16) & 0xff] ^ Td2[(s1 >> 8) & 0xff] ^ Td3[s0 & 0xff] ^ rk[55];
}
}
- rk += key->rounds << 2;
+ rk += key->rounds << 2;
#else /* !FULL_UNROLL */
/*
* Nr - 1 full rounds:
@@ -1123,37 +1126,37 @@ void AES_decrypt(const unsigned char *in, unsigned char *out,
}
#endif /* ?FULL_UNROLL */
/*
- * apply last round and
- * map cipher state to byte array block:
- */
- s0 =
- (Td4[(t0 >> 24) ] << 24) ^
- (Td4[(t3 >> 16) & 0xff] << 16) ^
- (Td4[(t2 >> 8) & 0xff] << 8) ^
- (Td4[(t1 ) & 0xff]) ^
- rk[0];
- PUTU32(out , s0);
- s1 =
- (Td4[(t1 >> 24) ] << 24) ^
- (Td4[(t0 >> 16) & 0xff] << 16) ^
- (Td4[(t3 >> 8) & 0xff] << 8) ^
- (Td4[(t2 ) & 0xff]) ^
- rk[1];
- PUTU32(out + 4, s1);
- s2 =
- (Td4[(t2 >> 24) ] << 24) ^
- (Td4[(t1 >> 16) & 0xff] << 16) ^
- (Td4[(t0 >> 8) & 0xff] << 8) ^
- (Td4[(t3 ) & 0xff]) ^
- rk[2];
- PUTU32(out + 8, s2);
- s3 =
- (Td4[(t3 >> 24) ] << 24) ^
- (Td4[(t2 >> 16) & 0xff] << 16) ^
- (Td4[(t1 >> 8) & 0xff] << 8) ^
- (Td4[(t0 ) & 0xff]) ^
- rk[3];
- PUTU32(out + 12, s3);
+ * apply last round and
+ * map cipher state to byte array block:
+ */
+ s0 =
+ ((u32)Td4[(t0 >> 24) ] << 24) ^
+ ((u32)Td4[(t3 >> 16) & 0xff] << 16) ^
+ ((u32)Td4[(t2 >> 8) & 0xff] << 8) ^
+ ((u32)Td4[(t1 ) & 0xff]) ^
+ rk[0];
+ PUTU32(out , s0);
+ s1 =
+ ((u32)Td4[(t1 >> 24) ] << 24) ^
+ ((u32)Td4[(t0 >> 16) & 0xff] << 16) ^
+ ((u32)Td4[(t3 >> 8) & 0xff] << 8) ^
+ ((u32)Td4[(t2 ) & 0xff]) ^
+ rk[1];
+ PUTU32(out + 4, s1);
+ s2 =
+ ((u32)Td4[(t2 >> 24) ] << 24) ^
+ ((u32)Td4[(t1 >> 16) & 0xff] << 16) ^
+ ((u32)Td4[(t0 >> 8) & 0xff] << 8) ^
+ ((u32)Td4[(t3 ) & 0xff]) ^
+ rk[2];
+ PUTU32(out + 8, s2);
+ s3 =
+ ((u32)Td4[(t3 >> 24) ] << 24) ^
+ ((u32)Td4[(t2 >> 16) & 0xff] << 16) ^
+ ((u32)Td4[(t1 >> 8) & 0xff] << 8) ^
+ ((u32)Td4[(t0 ) & 0xff]) ^
+ rk[3];
+ PUTU32(out + 12, s3);
}
#else /* AES_ASM */
@@ -1193,166 +1196,168 @@ static const u8 Te4[256] = {
0x41U, 0x99U, 0x2dU, 0x0fU, 0xb0U, 0x54U, 0xbbU, 0x16U
};
static const u32 rcon[] = {
- 0x01000000, 0x02000000, 0x04000000, 0x08000000,
- 0x10000000, 0x20000000, 0x40000000, 0x80000000,
- 0x1B000000, 0x36000000, /* for 128-bit blocks, Rijndael never uses more than 10 rcon values */
+ 0x01000000, 0x02000000, 0x04000000, 0x08000000,
+ 0x10000000, 0x20000000, 0x40000000, 0x80000000,
+ 0x1B000000, 0x36000000, /* for 128-bit blocks, Rijndael never uses more than 10 rcon values */
};
/**
* Expand the cipher key into the encryption key schedule.
*/
int private_AES_set_encrypt_key(const unsigned char *userKey, const int bits,
- AES_KEY *key) {
- u32 *rk;
+ AES_KEY *key)
+{
+ u32 *rk;
int i = 0;
- u32 temp;
+ u32 temp;
- if (!userKey || !key)
- return -1;
- if (bits != 128 && bits != 192 && bits != 256)
- return -2;
+ if (!userKey || !key)
+ return -1;
+ if (bits != 128 && bits != 192 && bits != 256)
+ return -2;
- rk = key->rd_key;
+ rk = key->rd_key;
- if (bits==128)
- key->rounds = 10;
- else if (bits==192)
- key->rounds = 12;
- else
- key->rounds = 14;
+ if (bits==128)
+ key->rounds = 10;
+ else if (bits==192)
+ key->rounds = 12;
+ else
+ key->rounds = 14;
- rk[0] = GETU32(userKey );
- rk[1] = GETU32(userKey + 4);
- rk[2] = GETU32(userKey + 8);
- rk[3] = GETU32(userKey + 12);
- if (bits == 128) {
- while (1) {
- temp = rk[3];
- rk[4] = rk[0] ^
- (Te4[(temp >> 16) & 0xff] << 24) ^
- (Te4[(temp >> 8) & 0xff] << 16) ^
- (Te4[(temp ) & 0xff] << 8) ^
- (Te4[(temp >> 24) ]) ^
- rcon[i];
- rk[5] = rk[1] ^ rk[4];
- rk[6] = rk[2] ^ rk[5];
- rk[7] = rk[3] ^ rk[6];
- if (++i == 10) {
- return 0;
- }
- rk += 4;
- }
- }
- rk[4] = GETU32(userKey + 16);
- rk[5] = GETU32(userKey + 20);
- if (bits == 192) {
- while (1) {
- temp = rk[ 5];
- rk[ 6] = rk[ 0] ^
- (Te4[(temp >> 16) & 0xff] << 24) ^
- (Te4[(temp >> 8) & 0xff] << 16) ^
- (Te4[(temp ) & 0xff] << 8) ^
- (Te4[(temp >> 24) ]) ^
- rcon[i];
- rk[ 7] = rk[ 1] ^ rk[ 6];
- rk[ 8] = rk[ 2] ^ rk[ 7];
- rk[ 9] = rk[ 3] ^ rk[ 8];
- if (++i == 8) {
- return 0;
- }
- rk[10] = rk[ 4] ^ rk[ 9];
- rk[11] = rk[ 5] ^ rk[10];
- rk += 6;
- }
- }
- rk[6] = GETU32(userKey + 24);
- rk[7] = GETU32(userKey + 28);
- if (bits == 256) {
- while (1) {
- temp = rk[ 7];
- rk[ 8] = rk[ 0] ^
- (Te4[(temp >> 16) & 0xff] << 24) ^
- (Te4[(temp >> 8) & 0xff] << 16) ^
- (Te4[(temp ) & 0xff] << 8) ^
- (Te4[(temp >> 24) ]) ^
- rcon[i];
- rk[ 9] = rk[ 1] ^ rk[ 8];
- rk[10] = rk[ 2] ^ rk[ 9];
- rk[11] = rk[ 3] ^ rk[10];
- if (++i == 7) {
- return 0;
- }
- temp = rk[11];
- rk[12] = rk[ 4] ^
- (Te4[(temp >> 24) ] << 24) ^
- (Te4[(temp >> 16) & 0xff] << 16) ^
- (Te4[(temp >> 8) & 0xff] << 8) ^
- (Te4[(temp ) & 0xff]);
- rk[13] = rk[ 5] ^ rk[12];
- rk[14] = rk[ 6] ^ rk[13];
- rk[15] = rk[ 7] ^ rk[14];
+ rk[0] = GETU32(userKey );
+ rk[1] = GETU32(userKey + 4);
+ rk[2] = GETU32(userKey + 8);
+ rk[3] = GETU32(userKey + 12);
+ if (bits == 128) {
+ while (1) {
+ temp = rk[3];
+ rk[4] = rk[0] ^
+ ((u32)Te4[(temp >> 16) & 0xff] << 24) ^
+ ((u32)Te4[(temp >> 8) & 0xff] << 16) ^
+ ((u32)Te4[(temp ) & 0xff] << 8) ^
+ ((u32)Te4[(temp >> 24) ]) ^
+ rcon[i];
+ rk[5] = rk[1] ^ rk[4];
+ rk[6] = rk[2] ^ rk[5];
+ rk[7] = rk[3] ^ rk[6];
+ if (++i == 10) {
+ return 0;
+ }
+ rk += 4;
+ }
+ }
+ rk[4] = GETU32(userKey + 16);
+ rk[5] = GETU32(userKey + 20);
+ if (bits == 192) {
+ while (1) {
+ temp = rk[ 5];
+ rk[ 6] = rk[ 0] ^
+ ((u32)Te4[(temp >> 16) & 0xff] << 24) ^
+ ((u32)Te4[(temp >> 8) & 0xff] << 16) ^
+ ((u32)Te4[(temp ) & 0xff] << 8) ^
+ ((u32)Te4[(temp >> 24) ]) ^
+ rcon[i];
+ rk[ 7] = rk[ 1] ^ rk[ 6];
+ rk[ 8] = rk[ 2] ^ rk[ 7];
+ rk[ 9] = rk[ 3] ^ rk[ 8];
+ if (++i == 8) {
+ return 0;
+ }
+ rk[10] = rk[ 4] ^ rk[ 9];
+ rk[11] = rk[ 5] ^ rk[10];
+ rk += 6;
+ }
+ }
+ rk[6] = GETU32(userKey + 24);
+ rk[7] = GETU32(userKey + 28);
+ if (bits == 256) {
+ while (1) {
+ temp = rk[ 7];
+ rk[ 8] = rk[ 0] ^
+ ((u32)Te4[(temp >> 16) & 0xff] << 24) ^
+ ((u32)Te4[(temp >> 8) & 0xff] << 16) ^
+ ((u32)Te4[(temp ) & 0xff] << 8) ^
+ ((u32)Te4[(temp >> 24) ]) ^
+ rcon[i];
+ rk[ 9] = rk[ 1] ^ rk[ 8];
+ rk[10] = rk[ 2] ^ rk[ 9];
+ rk[11] = rk[ 3] ^ rk[10];
+ if (++i == 7) {
+ return 0;
+ }
+ temp = rk[11];
+ rk[12] = rk[ 4] ^
+ ((u32)Te4[(temp >> 24) ] << 24) ^
+ ((u32)Te4[(temp >> 16) & 0xff] << 16) ^
+ ((u32)Te4[(temp >> 8) & 0xff] << 8) ^
+ ((u32)Te4[(temp ) & 0xff]);
+ rk[13] = rk[ 5] ^ rk[12];
+ rk[14] = rk[ 6] ^ rk[13];
+ rk[15] = rk[ 7] ^ rk[14];
- rk += 8;
- }
- }
- return 0;
+ rk += 8;
+ }
+ }
+ return 0;
}
/**
* Expand the cipher key into the decryption key schedule.
*/
int private_AES_set_decrypt_key(const unsigned char *userKey, const int bits,
- AES_KEY *key) {
+ AES_KEY *key)
+{
- u32 *rk;
- int i, j, status;
- u32 temp;
+ u32 *rk;
+ int i, j, status;
+ u32 temp;
- /* first, start with an encryption schedule */
- status = private_AES_set_encrypt_key(userKey, bits, key);
- if (status < 0)
- return status;
+ /* first, start with an encryption schedule */
+ status = private_AES_set_encrypt_key(userKey, bits, key);
+ if (status < 0)
+ return status;
- rk = key->rd_key;
+ rk = key->rd_key;
- /* invert the order of the round keys: */
- for (i = 0, j = 4*(key->rounds); i < j; i += 4, j -= 4) {
- temp = rk[i ]; rk[i ] = rk[j ]; rk[j ] = temp;
- temp = rk[i + 1]; rk[i + 1] = rk[j + 1]; rk[j + 1] = temp;
- temp = rk[i + 2]; rk[i + 2] = rk[j + 2]; rk[j + 2] = temp;
- temp = rk[i + 3]; rk[i + 3] = rk[j + 3]; rk[j + 3] = temp;
- }
- /* apply the inverse MixColumn transform to all round keys but the first and the last: */
- for (i = 1; i < (key->rounds); i++) {
- rk += 4;
- for (j = 0; j < 4; j++) {
- u32 tp1, tp2, tp4, tp8, tp9, tpb, tpd, tpe, m;
+ /* invert the order of the round keys: */
+ for (i = 0, j = 4*(key->rounds); i < j; i += 4, j -= 4) {
+ temp = rk[i ]; rk[i ] = rk[j ]; rk[j ] = temp;
+ temp = rk[i + 1]; rk[i + 1] = rk[j + 1]; rk[j + 1] = temp;
+ temp = rk[i + 2]; rk[i + 2] = rk[j + 2]; rk[j + 2] = temp;
+ temp = rk[i + 3]; rk[i + 3] = rk[j + 3]; rk[j + 3] = temp;
+ }
+ /* apply the inverse MixColumn transform to all round keys but the first and the last: */
+ for (i = 1; i < (key->rounds); i++) {
+ rk += 4;
+ for (j = 0; j < 4; j++) {
+ u32 tp1, tp2, tp4, tp8, tp9, tpb, tpd, tpe, m;
- tp1 = rk[j];
- m = tp1 & 0x80808080;
- tp2 = ((tp1 & 0x7f7f7f7f) << 1) ^
- ((m - (m >> 7)) & 0x1b1b1b1b);
- m = tp2 & 0x80808080;
- tp4 = ((tp2 & 0x7f7f7f7f) << 1) ^
- ((m - (m >> 7)) & 0x1b1b1b1b);
- m = tp4 & 0x80808080;
- tp8 = ((tp4 & 0x7f7f7f7f) << 1) ^
- ((m - (m >> 7)) & 0x1b1b1b1b);
- tp9 = tp8 ^ tp1;
- tpb = tp9 ^ tp2;
- tpd = tp9 ^ tp4;
- tpe = tp8 ^ tp4 ^ tp2;
+ tp1 = rk[j];
+ m = tp1 & 0x80808080;
+ tp2 = ((tp1 & 0x7f7f7f7f) << 1) ^
+ ((m - (m >> 7)) & 0x1b1b1b1b);
+ m = tp2 & 0x80808080;
+ tp4 = ((tp2 & 0x7f7f7f7f) << 1) ^
+ ((m - (m >> 7)) & 0x1b1b1b1b);
+ m = tp4 & 0x80808080;
+ tp8 = ((tp4 & 0x7f7f7f7f) << 1) ^
+ ((m - (m >> 7)) & 0x1b1b1b1b);
+ tp9 = tp8 ^ tp1;
+ tpb = tp9 ^ tp2;
+ tpd = tp9 ^ tp4;
+ tpe = tp8 ^ tp4 ^ tp2;
#if defined(ROTATE)
- rk[j] = tpe ^ ROTATE(tpd,16) ^
- ROTATE(tp9,24) ^ ROTATE(tpb,8);
+ rk[j] = tpe ^ ROTATE(tpd,16) ^
+ ROTATE(tp9,24) ^ ROTATE(tpb,8);
#else
- rk[j] = tpe ^ (tpd >> 16) ^ (tpd << 16) ^
- (tp9 >> 8) ^ (tp9 << 24) ^
- (tpb >> 24) ^ (tpb << 8);
+ rk[j] = tpe ^ (tpd >> 16) ^ (tpd << 16) ^
+ (tp9 >> 8) ^ (tp9 << 24) ^
+ (tpb >> 24) ^ (tpb << 8);
#endif
- }
- }
- return 0;
+ }
+ }
+ return 0;
}
#endif /* AES_ASM */