linux-next/crypto/aegis.h

80 lines
2.5 KiB
C
Raw Permalink Normal View History

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* AEGIS common definitions
*
* Copyright (c) 2018 Ondrej Mosnacek <omosnacek@gmail.com>
* Copyright (c) 2018 Red Hat, Inc. All rights reserved.
*/
#ifndef _CRYPTO_AEGIS_H
#define _CRYPTO_AEGIS_H
#include <crypto/aes.h>
#include <linux/bitops.h>
#include <linux/types.h>
#define AEGIS_BLOCK_SIZE 16
union aegis_block {
__le64 words64[AEGIS_BLOCK_SIZE / sizeof(__le64)];
__le32 words32[AEGIS_BLOCK_SIZE / sizeof(__le32)];
u8 bytes[AEGIS_BLOCK_SIZE];
};
struct aegis_state;
extern int aegis128_have_aes_insn;
#define AEGIS_BLOCK_ALIGN (__alignof__(union aegis_block))
#define AEGIS_ALIGNED(p) IS_ALIGNED((uintptr_t)p, AEGIS_BLOCK_ALIGN)
bool crypto_aegis128_have_simd(void);
void crypto_aegis128_update_simd(struct aegis_state *state, const void *msg);
void crypto_aegis128_init_simd(struct aegis_state *state,
const union aegis_block *key,
const u8 *iv);
void crypto_aegis128_encrypt_chunk_simd(struct aegis_state *state, u8 *dst,
const u8 *src, unsigned int size);
void crypto_aegis128_decrypt_chunk_simd(struct aegis_state *state, u8 *dst,
const u8 *src, unsigned int size);
int crypto_aegis128_final_simd(struct aegis_state *state,
union aegis_block *tag_xor,
unsigned int assoclen,
unsigned int cryptlen,
unsigned int authsize);
crypto: aegis - fix badly optimized clang output Clang sometimes makes very different inlining decisions from gcc. In case of the aegis crypto algorithms, it decides to turn the innermost primitives (and, xor, ...) into separate functions but inline most of the rest. This results in a huge amount of variables spilled on the stack, leading to rather slow execution as well as kernel stack usage beyond the 32-bit warning limit when CONFIG_KASAN is enabled: crypto/aegis256.c:123:13: warning: stack frame size of 648 bytes in function 'crypto_aegis256_encrypt_chunk' [-Wframe-larger-than=] crypto/aegis256.c:366:13: warning: stack frame size of 1264 bytes in function 'crypto_aegis256_crypt' [-Wframe-larger-than=] crypto/aegis256.c:187:13: warning: stack frame size of 656 bytes in function 'crypto_aegis256_decrypt_chunk' [-Wframe-larger-than=] crypto/aegis128l.c:135:13: warning: stack frame size of 832 bytes in function 'crypto_aegis128l_encrypt_chunk' [-Wframe-larger-than=] crypto/aegis128l.c:415:13: warning: stack frame size of 1480 bytes in function 'crypto_aegis128l_crypt' [-Wframe-larger-than=] crypto/aegis128l.c:218:13: warning: stack frame size of 848 bytes in function 'crypto_aegis128l_decrypt_chunk' [-Wframe-larger-than=] crypto/aegis128.c:116:13: warning: stack frame size of 584 bytes in function 'crypto_aegis128_encrypt_chunk' [-Wframe-larger-than=] crypto/aegis128.c:351:13: warning: stack frame size of 1064 bytes in function 'crypto_aegis128_crypt' [-Wframe-larger-than=] crypto/aegis128.c:177:13: warning: stack frame size of 592 bytes in function 'crypto_aegis128_decrypt_chunk' [-Wframe-larger-than=] Forcing the primitives to all get inlined avoids the issue and the resulting code is similar to what gcc produces. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Nick Desaulniers <ndesaulniers@google.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2019-07-18 13:50:04 +00:00
static __always_inline void crypto_aegis_block_xor(union aegis_block *dst,
const union aegis_block *src)
{
dst->words64[0] ^= src->words64[0];
dst->words64[1] ^= src->words64[1];
}
crypto: aegis - fix badly optimized clang output Clang sometimes makes very different inlining decisions from gcc. In case of the aegis crypto algorithms, it decides to turn the innermost primitives (and, xor, ...) into separate functions but inline most of the rest. This results in a huge amount of variables spilled on the stack, leading to rather slow execution as well as kernel stack usage beyond the 32-bit warning limit when CONFIG_KASAN is enabled: crypto/aegis256.c:123:13: warning: stack frame size of 648 bytes in function 'crypto_aegis256_encrypt_chunk' [-Wframe-larger-than=] crypto/aegis256.c:366:13: warning: stack frame size of 1264 bytes in function 'crypto_aegis256_crypt' [-Wframe-larger-than=] crypto/aegis256.c:187:13: warning: stack frame size of 656 bytes in function 'crypto_aegis256_decrypt_chunk' [-Wframe-larger-than=] crypto/aegis128l.c:135:13: warning: stack frame size of 832 bytes in function 'crypto_aegis128l_encrypt_chunk' [-Wframe-larger-than=] crypto/aegis128l.c:415:13: warning: stack frame size of 1480 bytes in function 'crypto_aegis128l_crypt' [-Wframe-larger-than=] crypto/aegis128l.c:218:13: warning: stack frame size of 848 bytes in function 'crypto_aegis128l_decrypt_chunk' [-Wframe-larger-than=] crypto/aegis128.c:116:13: warning: stack frame size of 584 bytes in function 'crypto_aegis128_encrypt_chunk' [-Wframe-larger-than=] crypto/aegis128.c:351:13: warning: stack frame size of 1064 bytes in function 'crypto_aegis128_crypt' [-Wframe-larger-than=] crypto/aegis128.c:177:13: warning: stack frame size of 592 bytes in function 'crypto_aegis128_decrypt_chunk' [-Wframe-larger-than=] Forcing the primitives to all get inlined avoids the issue and the resulting code is similar to what gcc produces. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Nick Desaulniers <ndesaulniers@google.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2019-07-18 13:50:04 +00:00
static __always_inline void crypto_aegis_block_and(union aegis_block *dst,
const union aegis_block *src)
{
dst->words64[0] &= src->words64[0];
dst->words64[1] &= src->words64[1];
}
crypto: aegis - fix badly optimized clang output Clang sometimes makes very different inlining decisions from gcc. In case of the aegis crypto algorithms, it decides to turn the innermost primitives (and, xor, ...) into separate functions but inline most of the rest. This results in a huge amount of variables spilled on the stack, leading to rather slow execution as well as kernel stack usage beyond the 32-bit warning limit when CONFIG_KASAN is enabled: crypto/aegis256.c:123:13: warning: stack frame size of 648 bytes in function 'crypto_aegis256_encrypt_chunk' [-Wframe-larger-than=] crypto/aegis256.c:366:13: warning: stack frame size of 1264 bytes in function 'crypto_aegis256_crypt' [-Wframe-larger-than=] crypto/aegis256.c:187:13: warning: stack frame size of 656 bytes in function 'crypto_aegis256_decrypt_chunk' [-Wframe-larger-than=] crypto/aegis128l.c:135:13: warning: stack frame size of 832 bytes in function 'crypto_aegis128l_encrypt_chunk' [-Wframe-larger-than=] crypto/aegis128l.c:415:13: warning: stack frame size of 1480 bytes in function 'crypto_aegis128l_crypt' [-Wframe-larger-than=] crypto/aegis128l.c:218:13: warning: stack frame size of 848 bytes in function 'crypto_aegis128l_decrypt_chunk' [-Wframe-larger-than=] crypto/aegis128.c:116:13: warning: stack frame size of 584 bytes in function 'crypto_aegis128_encrypt_chunk' [-Wframe-larger-than=] crypto/aegis128.c:351:13: warning: stack frame size of 1064 bytes in function 'crypto_aegis128_crypt' [-Wframe-larger-than=] crypto/aegis128.c:177:13: warning: stack frame size of 592 bytes in function 'crypto_aegis128_decrypt_chunk' [-Wframe-larger-than=] Forcing the primitives to all get inlined avoids the issue and the resulting code is similar to what gcc produces. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Nick Desaulniers <ndesaulniers@google.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2019-07-18 13:50:04 +00:00
static __always_inline void crypto_aegis_aesenc(union aegis_block *dst,
const union aegis_block *src,
const union aegis_block *key)
{
const u8 *s = src->bytes;
const u32 *t = crypto_ft_tab[0];
u32 d0, d1, d2, d3;
d0 = t[s[ 0]] ^ rol32(t[s[ 5]], 8) ^ rol32(t[s[10]], 16) ^ rol32(t[s[15]], 24);
d1 = t[s[ 4]] ^ rol32(t[s[ 9]], 8) ^ rol32(t[s[14]], 16) ^ rol32(t[s[ 3]], 24);
d2 = t[s[ 8]] ^ rol32(t[s[13]], 8) ^ rol32(t[s[ 2]], 16) ^ rol32(t[s[ 7]], 24);
d3 = t[s[12]] ^ rol32(t[s[ 1]], 8) ^ rol32(t[s[ 6]], 16) ^ rol32(t[s[11]], 24);
dst->words32[0] = cpu_to_le32(d0) ^ key->words32[0];
dst->words32[1] = cpu_to_le32(d1) ^ key->words32[1];
dst->words32[2] = cpu_to_le32(d2) ^ key->words32[2];
dst->words32[3] = cpu_to_le32(d3) ^ key->words32[3];
}
#endif /* _CRYPTO_AEGIS_H */