[CRYPTO] padlock-aes: Use generic setkey function
The Padlock AES setkey routine is the same as exported by the generic implementation. So we could use it. Signed-off-by: Sebastian Siewior <sebastian@breakpoint.cc> Cc: Michal Ludvig <michal@logix.cz> Tested-by: Stefan Hellermann <stefan@the2masters.de> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
This commit is contained in:
parent
5427663f49
commit
7dc748e4e7
|
@ -27,6 +27,7 @@ config CRYPTO_DEV_PADLOCK_AES
|
|||
tristate "PadLock driver for AES algorithm"
|
||||
depends on CRYPTO_DEV_PADLOCK
|
||||
select CRYPTO_BLKCIPHER
|
||||
select CRYPTO_AES
|
||||
help
|
||||
Use VIA PadLock for AES algorithm.
|
||||
|
||||
|
|
|
@ -5,42 +5,6 @@
|
|||
*
|
||||
* Copyright (c) 2004 Michal Ludvig <michal@logix.cz>
|
||||
*
|
||||
* Key expansion routine taken from crypto/aes_generic.c
|
||||
*
|
||||
* This program is free software; you can redistribute it and/or modify
|
||||
* it under the terms of the GNU General Public License as published by
|
||||
* the Free Software Foundation; either version 2 of the License, or
|
||||
* (at your option) any later version.
|
||||
*
|
||||
* ---------------------------------------------------------------------------
|
||||
* Copyright (c) 2002, Dr Brian Gladman <brg@gladman.me.uk>, Worcester, UK.
|
||||
* All rights reserved.
|
||||
*
|
||||
* LICENSE TERMS
|
||||
*
|
||||
* The free distribution and use of this software in both source and binary
|
||||
* form is allowed (with or without changes) provided that:
|
||||
*
|
||||
* 1. distributions of this source code include the above copyright
|
||||
* notice, this list of conditions and the following disclaimer;
|
||||
*
|
||||
* 2. distributions in binary form include the above copyright
|
||||
* notice, this list of conditions and the following disclaimer
|
||||
* in the documentation and/or other associated materials;
|
||||
*
|
||||
* 3. the copyright holder's name is not used to endorse products
|
||||
* built using this software without specific written permission.
|
||||
*
|
||||
* ALTERNATIVELY, provided that this notice is retained in full, this product
|
||||
* may be distributed under the terms of the GNU General Public License (GPL),
|
||||
* in which case the provisions of the GPL apply INSTEAD OF those given above.
|
||||
*
|
||||
* DISCLAIMER
|
||||
*
|
||||
* This software is provided 'as is' with no explicit or implied warranties
|
||||
* in respect of its properties, including, but not limited to, correctness
|
||||
* and/or fitness for purpose.
|
||||
* ---------------------------------------------------------------------------
|
||||
*/
|
||||
|
||||
#include <crypto/algapi.h>
|
||||
|
@ -54,9 +18,6 @@
|
|||
#include <asm/byteorder.h>
|
||||
#include "padlock.h"
|
||||
|
||||
#define AES_EXTENDED_KEY_SIZE 64 /* in uint32_t units */
|
||||
#define AES_EXTENDED_KEY_SIZE_B (AES_EXTENDED_KEY_SIZE * sizeof(uint32_t))
|
||||
|
||||
/* Control word. */
|
||||
struct cword {
|
||||
unsigned int __attribute__ ((__packed__))
|
||||
|
@ -70,218 +31,23 @@ struct cword {
|
|||
|
||||
/* Whenever making any changes to the following
|
||||
* structure *make sure* you keep E, d_data
|
||||
* and cword aligned on 16 Bytes boundaries!!! */
|
||||
* and cword aligned on 16 Bytes boundaries and
|
||||
* the Hardware can access 16 * 16 bytes of E and d_data
|
||||
* (only the first 15 * 16 bytes matter but the HW reads
|
||||
* more).
|
||||
*/
|
||||
struct aes_ctx {
|
||||
u32 E[AES_MAX_KEYLENGTH_U32]
|
||||
__attribute__ ((__aligned__(PADLOCK_ALIGNMENT)));
|
||||
u32 d_data[AES_MAX_KEYLENGTH_U32]
|
||||
__attribute__ ((__aligned__(PADLOCK_ALIGNMENT)));
|
||||
struct {
|
||||
struct cword encrypt;
|
||||
struct cword decrypt;
|
||||
} cword;
|
||||
u32 *D;
|
||||
int key_length;
|
||||
u32 E[AES_EXTENDED_KEY_SIZE]
|
||||
__attribute__ ((__aligned__(PADLOCK_ALIGNMENT)));
|
||||
u32 d_data[AES_EXTENDED_KEY_SIZE]
|
||||
__attribute__ ((__aligned__(PADLOCK_ALIGNMENT)));
|
||||
};
|
||||
|
||||
/* ====== Key management routines ====== */
|
||||
|
||||
static inline uint32_t
|
||||
generic_rotr32 (const uint32_t x, const unsigned bits)
|
||||
{
|
||||
const unsigned n = bits % 32;
|
||||
return (x >> n) | (x << (32 - n));
|
||||
}
|
||||
|
||||
static inline uint32_t
|
||||
generic_rotl32 (const uint32_t x, const unsigned bits)
|
||||
{
|
||||
const unsigned n = bits % 32;
|
||||
return (x << n) | (x >> (32 - n));
|
||||
}
|
||||
|
||||
#define rotl generic_rotl32
|
||||
#define rotr generic_rotr32
|
||||
|
||||
/*
|
||||
* #define byte(x, nr) ((unsigned char)((x) >> (nr*8)))
|
||||
*/
|
||||
static inline uint8_t
|
||||
byte(const uint32_t x, const unsigned n)
|
||||
{
|
||||
return x >> (n << 3);
|
||||
}
|
||||
|
||||
#define E_KEY ctx->E
|
||||
#define D_KEY ctx->D
|
||||
|
||||
static uint8_t pow_tab[256];
|
||||
static uint8_t log_tab[256];
|
||||
static uint8_t sbx_tab[256];
|
||||
static uint8_t isb_tab[256];
|
||||
static uint32_t rco_tab[10];
|
||||
static uint32_t ft_tab[4][256];
|
||||
static uint32_t it_tab[4][256];
|
||||
|
||||
static uint32_t fl_tab[4][256];
|
||||
static uint32_t il_tab[4][256];
|
||||
|
||||
static inline uint8_t
|
||||
f_mult (uint8_t a, uint8_t b)
|
||||
{
|
||||
uint8_t aa = log_tab[a], cc = aa + log_tab[b];
|
||||
|
||||
return pow_tab[cc + (cc < aa ? 1 : 0)];
|
||||
}
|
||||
|
||||
#define ff_mult(a,b) (a && b ? f_mult(a, b) : 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)
|
||||
|
||||
#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)
|
||||
|
||||
static void
|
||||
gen_tabs (void)
|
||||
{
|
||||
uint32_t i, t;
|
||||
uint8_t p, q;
|
||||
|
||||
/* log and power tables for GF(2**8) finite field with
|
||||
0x011b as modular polynomial - the simplest prmitive
|
||||
root is 0x03, used here to generate the tables */
|
||||
|
||||
for (i = 0, p = 1; i < 256; ++i) {
|
||||
pow_tab[i] = (uint8_t) p;
|
||||
log_tab[p] = (uint8_t) i;
|
||||
|
||||
p ^= (p << 1) ^ (p & 0x80 ? 0x01b : 0);
|
||||
}
|
||||
|
||||
log_tab[1] = 0;
|
||||
|
||||
for (i = 0, p = 1; i < 10; ++i) {
|
||||
rco_tab[i] = p;
|
||||
|
||||
p = (p << 1) ^ (p & 0x80 ? 0x01b : 0);
|
||||
}
|
||||
|
||||
for (i = 0; i < 256; ++i) {
|
||||
p = (i ? pow_tab[255 - log_tab[i]] : 0);
|
||||
q = ((p >> 7) | (p << 1)) ^ ((p >> 6) | (p << 2));
|
||||
p ^= 0x63 ^ q ^ ((q >> 6) | (q << 2));
|
||||
sbx_tab[i] = p;
|
||||
isb_tab[p] = (uint8_t) i;
|
||||
}
|
||||
|
||||
for (i = 0; i < 256; ++i) {
|
||||
p = sbx_tab[i];
|
||||
|
||||
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);
|
||||
|
||||
t = ((uint32_t) ff_mult (2, p)) |
|
||||
((uint32_t) p << 8) |
|
||||
((uint32_t) p << 16) | ((uint32_t) 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];
|
||||
|
||||
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);
|
||||
|
||||
t = ((uint32_t) ff_mult (14, p)) |
|
||||
((uint32_t) ff_mult (9, p) << 8) |
|
||||
((uint32_t) ff_mult (13, p) << 16) |
|
||||
((uint32_t) 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);
|
||||
}
|
||||
}
|
||||
|
||||
#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 = rotr(t, 8); t = ls_box(t) ^ 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 = rotr(t, 8); t = ls_box(t) ^ 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 = rotr(t, 8); ; t = ls_box(t) ^ 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; \
|
||||
}
|
||||
|
||||
/* Tells whether the ACE is capable to generate
|
||||
the extended key for a given key_len. */
|
||||
static inline int
|
||||
|
@ -321,17 +87,13 @@ static int aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
|
|||
struct aes_ctx *ctx = aes_ctx(tfm);
|
||||
const __le32 *key = (const __le32 *)in_key;
|
||||
u32 *flags = &tfm->crt_flags;
|
||||
uint32_t i, t, u, v, w;
|
||||
uint32_t P[AES_EXTENDED_KEY_SIZE];
|
||||
uint32_t rounds;
|
||||
struct crypto_aes_ctx gen_aes;
|
||||
|
||||
if (key_len % 8) {
|
||||
*flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
|
||||
return -EINVAL;
|
||||
}
|
||||
|
||||
ctx->key_length = key_len;
|
||||
|
||||
/*
|
||||
* If the hardware is capable of generating the extended key
|
||||
* itself we must supply the plain key for both encryption
|
||||
|
@ -339,10 +101,10 @@ static int aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
|
|||
*/
|
||||
ctx->D = ctx->E;
|
||||
|
||||
E_KEY[0] = le32_to_cpu(key[0]);
|
||||
E_KEY[1] = le32_to_cpu(key[1]);
|
||||
E_KEY[2] = le32_to_cpu(key[2]);
|
||||
E_KEY[3] = le32_to_cpu(key[3]);
|
||||
ctx->E[0] = le32_to_cpu(key[0]);
|
||||
ctx->E[1] = le32_to_cpu(key[1]);
|
||||
ctx->E[2] = le32_to_cpu(key[2]);
|
||||
ctx->E[3] = le32_to_cpu(key[3]);
|
||||
|
||||
/* Prepare control words. */
|
||||
memset(&ctx->cword, 0, sizeof(ctx->cword));
|
||||
|
@ -361,56 +123,13 @@ static int aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
|
|||
ctx->cword.encrypt.keygen = 1;
|
||||
ctx->cword.decrypt.keygen = 1;
|
||||
|
||||
switch (key_len) {
|
||||
case 16:
|
||||
t = E_KEY[3];
|
||||
for (i = 0; i < 10; ++i)
|
||||
loop4 (i);
|
||||
break;
|
||||
|
||||
case 24:
|
||||
E_KEY[4] = le32_to_cpu(key[4]);
|
||||
t = E_KEY[5] = le32_to_cpu(key[5]);
|
||||
for (i = 0; i < 8; ++i)
|
||||
loop6 (i);
|
||||
break;
|
||||
|
||||
case 32:
|
||||
E_KEY[4] = le32_to_cpu(key[4]);
|
||||
E_KEY[5] = le32_to_cpu(key[5]);
|
||||
E_KEY[6] = le32_to_cpu(key[6]);
|
||||
t = E_KEY[7] = le32_to_cpu(key[7]);
|
||||
for (i = 0; i < 7; ++i)
|
||||
loop8 (i);
|
||||
break;
|
||||
if (crypto_aes_expand_key(&gen_aes, in_key, key_len)) {
|
||||
*flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
|
||||
return -EINVAL;
|
||||
}
|
||||
|
||||
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 < key_len + 24; ++i) {
|
||||
imix_col (D_KEY[i], E_KEY[i]);
|
||||
}
|
||||
|
||||
/* PadLock needs a different format of the decryption key. */
|
||||
rounds = 10 + (key_len - 16) / 4;
|
||||
|
||||
for (i = 0; i < rounds; i++) {
|
||||
P[((i + 1) * 4) + 0] = D_KEY[((rounds - i - 1) * 4) + 0];
|
||||
P[((i + 1) * 4) + 1] = D_KEY[((rounds - i - 1) * 4) + 1];
|
||||
P[((i + 1) * 4) + 2] = D_KEY[((rounds - i - 1) * 4) + 2];
|
||||
P[((i + 1) * 4) + 3] = D_KEY[((rounds - i - 1) * 4) + 3];
|
||||
}
|
||||
|
||||
P[0] = E_KEY[(rounds * 4) + 0];
|
||||
P[1] = E_KEY[(rounds * 4) + 1];
|
||||
P[2] = E_KEY[(rounds * 4) + 2];
|
||||
P[3] = E_KEY[(rounds * 4) + 3];
|
||||
|
||||
memcpy(D_KEY, P, AES_EXTENDED_KEY_SIZE_B);
|
||||
|
||||
memcpy(ctx->E, gen_aes.key_enc, AES_MAX_KEYLENGTH);
|
||||
memcpy(ctx->D, gen_aes.key_dec, AES_MAX_KEYLENGTH);
|
||||
return 0;
|
||||
}
|
||||
|
||||
|
@ -675,7 +394,6 @@ static int __init padlock_init(void)
|
|||
return -ENODEV;
|
||||
}
|
||||
|
||||
gen_tabs();
|
||||
if ((ret = crypto_register_alg(&aes_alg)))
|
||||
goto aes_err;
|
||||
|
||||
|
|
Loading…
Reference in New Issue