rvsim-core 2.0.0

A cycle-level RISC-V 64-bit system simulator.
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85

//! SM4 rounds and key expansion (Zvksed).

/// SM4 S-box.
pub(super) const SM4_SBOX: [u8; 256] = [
    0xd6, 0x90, 0xe9, 0xfe, 0xcc, 0xe1, 0x3d, 0xb7, 0x16, 0xb6, 0x14, 0xc2, 0x28, 0xfb, 0x2c, 0x05,
    0x2b, 0x67, 0x9a, 0x76, 0x2a, 0xbe, 0x04, 0xc3, 0xaa, 0x44, 0x13, 0x26, 0x49, 0x86, 0x06, 0x99,
    0x9c, 0x42, 0x50, 0xf4, 0x91, 0xef, 0x98, 0x7a, 0x33, 0x54, 0x0b, 0x43, 0xed, 0xcf, 0xac, 0x62,
    0xe4, 0xb3, 0x1c, 0xa9, 0xc9, 0x08, 0xe8, 0x95, 0x80, 0xdf, 0x94, 0xfa, 0x75, 0x8f, 0x3f, 0xa6,
    0x47, 0x07, 0xa7, 0xfc, 0xf3, 0x73, 0x17, 0xba, 0x83, 0x59, 0x3c, 0x19, 0xe6, 0x85, 0x4f, 0xa8,
    0x68, 0x6b, 0x81, 0xb2, 0x71, 0x64, 0xda, 0x8b, 0xf8, 0xeb, 0x0f, 0x4b, 0x70, 0x56, 0x9d, 0x35,
    0x1e, 0x24, 0x0e, 0x5e, 0x63, 0x58, 0xd1, 0xa2, 0x25, 0x22, 0x7c, 0x3b, 0x01, 0x21, 0x78, 0x87,
    0xd4, 0x00, 0x46, 0x57, 0x9f, 0xd3, 0x27, 0x52, 0x4c, 0x36, 0x02, 0xe7, 0xa0, 0xc4, 0xc8, 0x9e,
    0xea, 0xbf, 0x8a, 0xd2, 0x40, 0xc7, 0x38, 0xb5, 0xa3, 0xf7, 0xf2, 0xce, 0xf9, 0x61, 0x15, 0xa1,
    0xe0, 0xae, 0x5d, 0xa4, 0x9b, 0x34, 0x1a, 0x55, 0xad, 0x93, 0x32, 0x30, 0xf5, 0x8c, 0xb1, 0xe3,
    0x1d, 0xf6, 0xe2, 0x2e, 0x82, 0x66, 0xca, 0x60, 0xc0, 0x29, 0x23, 0xab, 0x0d, 0x53, 0x4e, 0x6f,
    0xd5, 0xdb, 0x37, 0x45, 0xde, 0xfd, 0x8e, 0x2f, 0x03, 0xff, 0x6a, 0x72, 0x6d, 0x6c, 0x5b, 0x51,
    0x8d, 0x1b, 0xaf, 0x92, 0xbb, 0xdd, 0xbc, 0x7f, 0x11, 0xd9, 0x5c, 0x41, 0x1f, 0x10, 0x5a, 0xd8,
    0x0a, 0xc1, 0x31, 0x88, 0xa5, 0xcd, 0x7b, 0xbd, 0x2d, 0x74, 0xd0, 0x12, 0xb8, 0xe5, 0xb4, 0xb0,
    0x89, 0x69, 0x97, 0x4a, 0x0c, 0x96, 0x77, 0x7e, 0x65, 0xb9, 0xf1, 0x09, 0xc5, 0x6e, 0xc6, 0x84,
    0x18, 0xf0, 0x7d, 0xec, 0x3a, 0xdc, 0x4d, 0x20, 0x79, 0xee, 0x5f, 0x3e, 0xd7, 0xcb, 0x39, 0x48,
];

/// SM4 round constants CK[0..32] (little-endian per byte).
pub(super) const SM4_CK: [u32; 32] = [
    0x00070E15, 0x1C232A31, 0x383F464D, 0x545B6269, 0x70777E85, 0x8C939AA1, 0xA8AFB6BD, 0xC4CBD2D9,
    0xE0E7EEF5, 0xFC030A11, 0x181F262D, 0x343B4249, 0x50575E65, 0x6C737A81, 0x888F969D, 0xA4ABB2B9,
    0xC0C7CED5, 0xDCE3EAF1, 0xF8FF060D, 0x141B2229, 0x30373E45, 0x4C535A61, 0x686F767D, 0x848B9299,
    0xA0A7AEB5, 0xBCC3CAD1, 0xD8DFE6ED, 0xF4FB0209, 0x10171E25, 0x2C333A41, 0x484F565D, 0x646B7279,
];

#[inline]
pub(super) const fn sm4_tau(a: u32) -> u32 {
    let bytes = a.to_le_bytes();
    u32::from_le_bytes([
        SM4_SBOX[bytes[0] as usize],
        SM4_SBOX[bytes[1] as usize],
        SM4_SBOX[bytes[2] as usize],
        SM4_SBOX[bytes[3] as usize],
    ])
}

/// SM4 linear transform L for round function.
#[inline]
pub(super) const fn sm4_l(b: u32) -> u32 {
    b ^ b.rotate_left(2) ^ b.rotate_left(10) ^ b.rotate_left(18) ^ b.rotate_left(24)
}

/// SM4 linear transform L' for key schedule.
#[inline]
pub(super) const fn sm4_l_prime(b: u32) -> u32 {
    b ^ b.rotate_left(13) ^ b.rotate_left(23)
}

/// vsm4r — SM4 round function applied to 4 elements.
///
/// vd = {X3, X2, X1, X0}, vs2 = {RK3, RK2, RK1, RK0}.
/// Output: {X7, X6, X5, X4} where Xi+4 = Xi ^ T(Xi+1 ^ Xi+2 ^ Xi+3 ^ `RKi`).
pub(super) fn sm4_r(vd: [u32; 4], vs2: [u32; 4]) -> [u32; 4] {
    let mut x = [vd[0], vd[1], vd[2], vd[3], 0, 0, 0, 0];
    for i in 0..4 {
        let t = x[i + 1] ^ x[i + 2] ^ x[i + 3] ^ vs2[i];
        x[i + 4] = x[i] ^ sm4_l(sm4_tau(t));
    }
    [x[4], x[5], x[6], x[7]]
}

/// vsm4k.vi — SM4 key expansion.
///
/// vd = current 4 round keys {RK3, RK2, RK1, RK0}, rnd selects which 4-round
/// chunk to produce. Output: next 4 round keys.
/// On the first call (rnd=0), vd should be MK ^ FK (caller responsibility?).
/// Actually per spec: vd contains the previous 4 K-values; output is next 4.
///
/// Per Zvksed: rnd comes from a 5-bit immediate but only bits [2:0] are used
/// (uimm[4:3] are reserved). Mask here so an out-of-spec encoding can't index
/// past `SM4_CK[32]`.
pub(super) fn sm4_k(vd: [u32; 4], rnd: u32) -> [u32; 4] {
    let mut k = [vd[0], vd[1], vd[2], vd[3], 0, 0, 0, 0];
    let base = ((rnd & 0x7) * 4) as usize;
    for i in 0..4 {
        let t = k[i + 1] ^ k[i + 2] ^ k[i + 3] ^ SM4_CK[base + i];
        k[i + 4] = k[i] ^ sm4_l_prime(sm4_tau(t));
    }
    [k[4], k[5], k[6], k[7]]
}