diff options
| author | Ard Biesheuvel <ard.biesheuvel@linaro.org> | 2019-10-14 18:16:45 +0200 |
|---|---|---|
| committer | Herbert Xu <herbert@gondor.apana.org.au> | 2019-10-26 02:06:05 +1100 |
| commit | 528282630ca961d6284f68f5f2f0057c86873bb6 (patch) | |
| tree | 307324123ac73bba9d91116fdcecd7a24161dffc /crypto/aegis128-neon-inner.c | |
| parent | 2698bce1f05f0a13e2df1db7364df2b50a47e08d (diff) | |
| download | linux-528282630ca961d6284f68f5f2f0057c86873bb6.tar.bz2 | |
crypto: aegis128 - duplicate init() and final() hooks in SIMD code
In order to speed up aegis128 processing even more, duplicate the init()
and final() routines as SIMD versions in their entirety. This results
in a 2x speedup on ARM Cortex-A57 for ~1500 byte packets (using AES
instructions).
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Diffstat (limited to 'crypto/aegis128-neon-inner.c')
| -rw-r--r-- | crypto/aegis128-neon-inner.c | 50 |
1 files changed, 50 insertions, 0 deletions
diff --git a/crypto/aegis128-neon-inner.c b/crypto/aegis128-neon-inner.c index f05310ca22aa..2a660ac1bc3a 100644 --- a/crypto/aegis128-neon-inner.c +++ b/crypto/aegis128-neon-inner.c @@ -132,6 +132,36 @@ void preload_sbox(void) :: "r"(crypto_aes_sbox)); } +void crypto_aegis128_init_neon(void *state, const void *key, const void *iv) +{ + static const uint8_t const0[] = { + 0x00, 0x01, 0x01, 0x02, 0x03, 0x05, 0x08, 0x0d, + 0x15, 0x22, 0x37, 0x59, 0x90, 0xe9, 0x79, 0x62, + }; + static const uint8_t const1[] = { + 0xdb, 0x3d, 0x18, 0x55, 0x6d, 0xc2, 0x2f, 0xf1, + 0x20, 0x11, 0x31, 0x42, 0x73, 0xb5, 0x28, 0xdd, + }; + uint8x16_t k = vld1q_u8(key); + uint8x16_t kiv = k ^ vld1q_u8(iv); + struct aegis128_state st = {{ + kiv, + vld1q_u8(const1), + vld1q_u8(const0), + k ^ vld1q_u8(const0), + k ^ vld1q_u8(const1), + }}; + int i; + + preload_sbox(); + + for (i = 0; i < 5; i++) { + st = aegis128_update_neon(st, k); + st = aegis128_update_neon(st, kiv); + } + aegis128_save_state_neon(st, state); +} + void crypto_aegis128_update_neon(void *state, const void *msg) { struct aegis128_state st = aegis128_load_state_neon(state); @@ -210,3 +240,23 @@ void crypto_aegis128_decrypt_chunk_neon(void *state, void *dst, const void *src, aegis128_save_state_neon(st, state); } + +void crypto_aegis128_final_neon(void *state, void *tag_xor, uint64_t assoclen, + uint64_t cryptlen) +{ + struct aegis128_state st = aegis128_load_state_neon(state); + uint8x16_t v; + int i; + + preload_sbox(); + + v = st.v[3] ^ (uint8x16_t)vcombine_u64(vmov_n_u64(8 * assoclen), + vmov_n_u64(8 * cryptlen)); + + for (i = 0; i < 7; i++) + st = aegis128_update_neon(st, v); + + v = vld1q_u8(tag_xor); + v ^= st.v[0] ^ st.v[1] ^ st.v[2] ^ st.v[3] ^ st.v[4]; + vst1q_u8(tag_xor, v); +} |