On 30 September 2018 at 10:58, Ard Biesheuvel <ard.biesheuvel@xxxxxxxxxx> wrote:
> Use the correct __le32 annotation and accessors to perform the
> single round of AES encryption performed inside the AEGIS transform.
> Otherwise, tcrypt reports:
>
> alg: aead: Test 1 failed on encryption for aegis128-generic
> 00000000: 6c 25 25 4a 3c 10 1d 27 2b c1 d4 84 9a ef 7f 6e
> alg: aead: Test 1 failed on encryption for aegis128l-generic
> 00000000: cd c6 e3 b8 a0 70 9d 8e c2 4f 6f fe 71 42 df 28
> alg: aead: Test 1 failed on encryption for aegis256-generic
> 00000000: aa ed 07 b1 96 1d e9 e6 f2 ed b5 8e 1c 5f dc 1c
>
> While at it, let's refer to the first precomputed table only, and
> derive the other ones by rotation. This reduces the D-cache footprint
> by 75%, and shouldn't be too costly or free on load/store architectures
> (and X86 has its own AES-NI based implementation)
>
> Fixes: f606a88e5823 ("crypto: aegis - Add generic AEGIS AEAD implementations")
> Cc: <stable@xxxxxxxxxxxxxxx> # v4.18+
> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@xxxxxxxxxx>
> ---
> crypto/aegis.h | 23 +++++++++-----------
> 1 file changed, 10 insertions(+), 13 deletions(-)
>
> diff --git a/crypto/aegis.h b/crypto/aegis.h
> index f1c6900ddb80..84d3e07a3c33 100644
> --- a/crypto/aegis.h
> +++ b/crypto/aegis.h
> @@ -21,7 +21,7 @@
>
> union aegis_block {
> __le64 words64[AEGIS_BLOCK_SIZE / sizeof(__le64)];
> - u32 words32[AEGIS_BLOCK_SIZE / sizeof(u32)];
> + __le32 words32[AEGIS_BLOCK_SIZE / sizeof(__le32)];
> u8 bytes[AEGIS_BLOCK_SIZE];
> };
>
> @@ -59,22 +59,19 @@ static void crypto_aegis_aesenc(union aegis_block *dst,
> {
> u32 *d = dst->words32;
> const u8 *s = src->bytes;
> - const u32 *k = key->words32;
> + const __le32 *k = key->words32;
> const u32 *t0 = crypto_ft_tab[0];
> - const u32 *t1 = crypto_ft_tab[1];
> - const u32 *t2 = crypto_ft_tab[2];
> - const u32 *t3 = crypto_ft_tab[3];
> u32 d0, d1, d2, d3;
>
> - d0 = t0[s[ 0]] ^ t1[s[ 5]] ^ t2[s[10]] ^ t3[s[15]] ^ k[0];
> - d1 = t0[s[ 4]] ^ t1[s[ 9]] ^ t2[s[14]] ^ t3[s[ 3]] ^ k[1];
> - d2 = t0[s[ 8]] ^ t1[s[13]] ^ t2[s[ 2]] ^ t3[s[ 7]] ^ k[2];
> - d3 = t0[s[12]] ^ t1[s[ 1]] ^ t2[s[ 6]] ^ t3[s[11]] ^ k[3];
> + d0 = t0[s[ 0]] ^ rol32(t0[s[ 5]], 8) ^ rol32(t0[s[10]], 16) ^ rol32(t0[s[15]], 24);
> + d1 = t0[s[ 4]] ^ rol32(t0[s[ 9]], 8) ^ rol32(t0[s[14]], 16) ^ rol32(t0[s[ 3]], 24);
> + d2 = t0[s[ 8]] ^ rol32(t0[s[13]], 8) ^ rol32(t0[s[ 2]], 16) ^ rol32(t0[s[ 7]], 24);
> + d3 = t0[s[12]] ^ rol32(t0[s[ 1]], 8) ^ rol32(t0[s[ 6]], 16) ^ rol32(t0[s[11]], 24);
>
> - d[0] = d0;
> - d[1] = d1;
> - d[2] = d2;
> - d[3] = d3;
> + d[0] = cpu_to_le32(d0 ^ le32_to_cpu(k[0]));
> + d[1] = cpu_to_le32(d1 ^ le32_to_cpu(k[1]));
> + d[2] = cpu_to_le32(d2 ^ le32_to_cpu(k[2]));
> + d[3] = cpu_to_le32(d3 ^ le32_to_cpu(k[3]));
I suppose this
> + d[0] = cpu_to_le32(d0) ^ k[0];
> + d[1] = cpu_to_le32(d1) ^ k[1];
> + d[2] = cpu_to_le32(d2) ^ k[2];
> + d[3] = cpu_to_le32(d3) ^ k[3];
should work fine as well
> }
>
> #endif /* _CRYPTO_AEGIS_H */
> --
> 2.19.0
>
