Add helper support for the Octeon SNOW3G START and MORE selectors. This models the LFSR/FSM state, the hardware result window, and the shared HSH/SHA3/SNOW3G/ZUC register window used for state save and restore.
The helpers preserve the shared-window mode so DMFC2/DMTC2 accesses to the aliased window return the active engine view. Signed-off-by: James Hilliard <[email protected]> --- Changes v8 -> v9: - Split SNOW3G selector operations into their own COP2 helper patch. - Replace generic selector dispatch with per-operation SNOW3G helpers. - Add matching helper.h declarations with the helper implementation. --- target/mips/helper.h | 2 + target/mips/tcg/octeon_crypto.c | 233 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 235 insertions(+) diff --git a/target/mips/helper.h b/target/mips/helper.h index 3e6025b7de..056a9d3fc8 100644 --- a/target/mips/helper.h +++ b/target/mips/helper.h @@ -64,6 +64,8 @@ DEF_HELPER_2(octeon_cp2_mt_sha3_xordat17, void, env, i64) DEF_HELPER_2(octeon_cp2_mt_sha3_startop, void, env, i64) DEF_HELPER_2(octeon_cp2_mt_zuc_start, void, env, i64) DEF_HELPER_2(octeon_cp2_mt_zuc_more, void, env, i64) +DEF_HELPER_2(octeon_cp2_mt_snow3g_start, void, env, i64) +DEF_HELPER_2(octeon_cp2_mt_snow3g_more, void, env, i64) /* microMIPS functions */ DEF_HELPER_4(lwm, void, env, tl, tl, i32) diff --git a/target/mips/tcg/octeon_crypto.c b/target/mips/tcg/octeon_crypto.c index 673932ceba..ee4d33c24f 100644 --- a/target/mips/tcg/octeon_crypto.c +++ b/target/mips/tcg/octeon_crypto.c @@ -540,6 +540,229 @@ static bool octeon_zuc_is_shared_dmtc2_sel(uint32_t sel) return false; } } +static const uint8_t octeon_snow3g_sr[256] = { + 0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5, + 0x30, 0x01, 0x67, 0x2b, 0xfe, 0xd7, 0xab, 0x76, + 0xca, 0x82, 0xc9, 0x7d, 0xfa, 0x59, 0x47, 0xf0, + 0xad, 0xd4, 0xa2, 0xaf, 0x9c, 0xa4, 0x72, 0xc0, + 0xb7, 0xfd, 0x93, 0x26, 0x36, 0x3f, 0xf7, 0xcc, + 0x34, 0xa5, 0xe5, 0xf1, 0x71, 0xd8, 0x31, 0x15, + 0x04, 0xc7, 0x23, 0xc3, 0x18, 0x96, 0x05, 0x9a, + 0x07, 0x12, 0x80, 0xe2, 0xeb, 0x27, 0xb2, 0x75, + 0x09, 0x83, 0x2c, 0x1a, 0x1b, 0x6e, 0x5a, 0xa0, + 0x52, 0x3b, 0xd6, 0xb3, 0x29, 0xe3, 0x2f, 0x84, + 0x53, 0xd1, 0x00, 0xed, 0x20, 0xfc, 0xb1, 0x5b, + 0x6a, 0xcb, 0xbe, 0x39, 0x4a, 0x4c, 0x58, 0xcf, + 0xd0, 0xef, 0xaa, 0xfb, 0x43, 0x4d, 0x33, 0x85, + 0x45, 0xf9, 0x02, 0x7f, 0x50, 0x3c, 0x9f, 0xa8, + 0x51, 0xa3, 0x40, 0x8f, 0x92, 0x9d, 0x38, 0xf5, + 0xbc, 0xb6, 0xda, 0x21, 0x10, 0xff, 0xf3, 0xd2, + 0xcd, 0x0c, 0x13, 0xec, 0x5f, 0x97, 0x44, 0x17, + 0xc4, 0xa7, 0x7e, 0x3d, 0x64, 0x5d, 0x19, 0x73, + 0x60, 0x81, 0x4f, 0xdc, 0x22, 0x2a, 0x90, 0x88, + 0x46, 0xee, 0xb8, 0x14, 0xde, 0x5e, 0x0b, 0xdb, + 0xe0, 0x32, 0x3a, 0x0a, 0x49, 0x06, 0x24, 0x5c, + 0xc2, 0xd3, 0xac, 0x62, 0x91, 0x95, 0xe4, 0x79, + 0xe7, 0xc8, 0x37, 0x6d, 0x8d, 0xd5, 0x4e, 0xa9, + 0x6c, 0x56, 0xf4, 0xea, 0x65, 0x7a, 0xae, 0x08, + 0xba, 0x78, 0x25, 0x2e, 0x1c, 0xa6, 0xb4, 0xc6, + 0xe8, 0xdd, 0x74, 0x1f, 0x4b, 0xbd, 0x8b, 0x8a, + 0x70, 0x3e, 0xb5, 0x66, 0x48, 0x03, 0xf6, 0x0e, + 0x61, 0x35, 0x57, 0xb9, 0x86, 0xc1, 0x1d, 0x9e, + 0xe1, 0xf8, 0x98, 0x11, 0x69, 0xd9, 0x8e, 0x94, + 0x9b, 0x1e, 0x87, 0xe9, 0xce, 0x55, 0x28, 0xdf, + 0x8c, 0xa1, 0x89, 0x0d, 0xbf, 0xe6, 0x42, 0x68, + 0x41, 0x99, 0x2d, 0x0f, 0xb0, 0x54, 0xbb, 0x16, +}; + +static const uint8_t octeon_snow3g_sq[256] = { + 0x25, 0x24, 0x73, 0x67, 0xd7, 0xae, 0x5c, 0x30, + 0xa4, 0xee, 0x6e, 0xcb, 0x7d, 0xb5, 0x82, 0xdb, + 0xe4, 0x8e, 0x48, 0x49, 0x4f, 0x5d, 0x6a, 0x78, + 0x70, 0x88, 0xe8, 0x5f, 0x5e, 0x84, 0x65, 0xe2, + 0xd8, 0xe9, 0xcc, 0xed, 0x40, 0x2f, 0x11, 0x28, + 0x57, 0xd2, 0xac, 0xe3, 0x4a, 0x15, 0x1b, 0xb9, + 0xb2, 0x80, 0x85, 0xa6, 0x2e, 0x02, 0x47, 0x29, + 0x07, 0x4b, 0x0e, 0xc1, 0x51, 0xaa, 0x89, 0xd4, + 0xca, 0x01, 0x46, 0xb3, 0xef, 0xdd, 0x44, 0x7b, + 0xc2, 0x7f, 0xbe, 0xc3, 0x9f, 0x20, 0x4c, 0x64, + 0x83, 0xa2, 0x68, 0x42, 0x13, 0xb4, 0x41, 0xcd, + 0xba, 0xc6, 0xbb, 0x6d, 0x4d, 0x71, 0x21, 0xf4, + 0x8d, 0xb0, 0xe5, 0x93, 0xfe, 0x8f, 0xe6, 0xcf, + 0x43, 0x45, 0x31, 0x22, 0x37, 0x36, 0x96, 0xfa, + 0xbc, 0x0f, 0x08, 0x52, 0x1d, 0x55, 0x1a, 0xc5, + 0x4e, 0x23, 0x69, 0x7a, 0x92, 0xff, 0x5b, 0x5a, + 0xeb, 0x9a, 0x1c, 0xa9, 0xd1, 0x7e, 0x0d, 0xfc, + 0x50, 0x8a, 0xb6, 0x62, 0xf5, 0x0a, 0xf8, 0xdc, + 0x03, 0x3c, 0x0c, 0x39, 0xf1, 0xb8, 0xf3, 0x3d, + 0xf2, 0xd5, 0x97, 0x66, 0x81, 0x32, 0xa0, 0x00, + 0x06, 0xce, 0xf6, 0xea, 0xb7, 0x17, 0xf7, 0x8c, + 0x79, 0xd6, 0xa7, 0xbf, 0x8b, 0x3f, 0x1f, 0x53, + 0x63, 0x75, 0x35, 0x2c, 0x60, 0xfd, 0x27, 0xd3, + 0x94, 0xa5, 0x7c, 0xa1, 0x05, 0x58, 0x2d, 0xbd, + 0xd9, 0xc7, 0xaf, 0x6b, 0x54, 0x0b, 0xe0, 0x38, + 0x04, 0xc8, 0x9d, 0xe7, 0x14, 0xb1, 0x87, 0x9c, + 0xdf, 0x6f, 0xf9, 0xda, 0x2a, 0xc4, 0x59, 0x16, + 0x74, 0x91, 0xab, 0x26, 0x61, 0x76, 0x34, 0x2b, + 0xad, 0x99, 0xfb, 0x72, 0xec, 0x33, 0x12, 0xde, + 0x98, 0x3b, 0xc0, 0x9b, 0x3e, 0x18, 0x10, 0x3a, + 0x56, 0xe1, 0x77, 0xc9, 0x1e, 0x9e, 0x95, 0xa3, + 0x90, 0x19, 0xa8, 0x6c, 0x09, 0xd0, 0xf0, 0x86, +}; + +static inline uint8_t octeon_snow3g_mulx(uint8_t v, uint8_t c) +{ + return (v & 0x80) ? ((v << 1) ^ c) : (v << 1); +} + +static uint8_t octeon_snow3g_mulxpow(uint8_t v, unsigned int n, uint8_t c) +{ + while (n-- > 0) { + v = octeon_snow3g_mulx(v, c); + } + return v; +} + +static inline uint32_t octeon_snow3g_pack32(uint8_t b0, uint8_t b1, + uint8_t b2, uint8_t b3) +{ + return ((uint32_t)b0 << 24) | ((uint32_t)b1 << 16) | + ((uint32_t)b2 << 8) | b3; +} + +static uint32_t octeon_snow3g_mulalpha(uint8_t c) +{ + return octeon_snow3g_pack32(octeon_snow3g_mulxpow(c, 23, 0xa9), + octeon_snow3g_mulxpow(c, 245, 0xa9), + octeon_snow3g_mulxpow(c, 48, 0xa9), + octeon_snow3g_mulxpow(c, 239, 0xa9)); +} + +static uint32_t octeon_snow3g_divalpha(uint8_t c) +{ + return octeon_snow3g_pack32(octeon_snow3g_mulxpow(c, 16, 0xa9), + octeon_snow3g_mulxpow(c, 39, 0xa9), + octeon_snow3g_mulxpow(c, 6, 0xa9), + octeon_snow3g_mulxpow(c, 64, 0xa9)); +} + +static uint32_t octeon_snow3g_s1(uint32_t w) +{ + uint8_t x0 = octeon_snow3g_sr[w >> 24]; + uint8_t x1 = octeon_snow3g_sr[(uint8_t)(w >> 16)]; + uint8_t x2 = octeon_snow3g_sr[(uint8_t)(w >> 8)]; + uint8_t x3 = octeon_snow3g_sr[(uint8_t)w]; + uint8_t r0 = octeon_snow3g_mulx(x0, 0x1b) ^ x1 ^ x2 ^ + octeon_snow3g_mulx(x3, 0x1b) ^ x3; + uint8_t r1 = octeon_snow3g_mulx(x0, 0x1b) ^ x0 ^ + octeon_snow3g_mulx(x1, 0x1b) ^ x2 ^ x3; + uint8_t r2 = x0 ^ octeon_snow3g_mulx(x1, 0x1b) ^ x1 ^ + octeon_snow3g_mulx(x2, 0x1b) ^ x3; + uint8_t r3 = x0 ^ x1 ^ octeon_snow3g_mulx(x2, 0x1b) ^ x2 ^ + octeon_snow3g_mulx(x3, 0x1b); + + return octeon_snow3g_pack32(r0, r1, r2, r3); +} + +static uint32_t octeon_snow3g_s2(uint32_t w) +{ + uint8_t x0 = octeon_snow3g_sq[w >> 24]; + uint8_t x1 = octeon_snow3g_sq[(uint8_t)(w >> 16)]; + uint8_t x2 = octeon_snow3g_sq[(uint8_t)(w >> 8)]; + uint8_t x3 = octeon_snow3g_sq[(uint8_t)w]; + uint8_t r0 = octeon_snow3g_mulx(x0, 0x69) ^ x1 ^ x2 ^ + octeon_snow3g_mulx(x3, 0x69) ^ x3; + uint8_t r1 = octeon_snow3g_mulx(x0, 0x69) ^ x0 ^ + octeon_snow3g_mulx(x1, 0x69) ^ x2 ^ x3; + uint8_t r2 = x0 ^ octeon_snow3g_mulx(x1, 0x69) ^ x1 ^ + octeon_snow3g_mulx(x2, 0x69) ^ x3; + uint8_t r3 = x0 ^ x1 ^ octeon_snow3g_mulx(x2, 0x69) ^ x2 ^ + octeon_snow3g_mulx(x3, 0x69); + + return octeon_snow3g_pack32(r0, r1, r2, r3); +} + +static uint32_t octeon_snow3g_clock_fsm(MIPSOcteonCryptoState *crypto) +{ + uint32_t f = (uint32_t)(crypto->snow3g_lfsr[15] + crypto->snow3g_fsm[0]) ^ + crypto->snow3g_fsm[1]; + uint32_t r = (uint32_t)(crypto->snow3g_fsm[1] + + (crypto->snow3g_fsm[2] ^ crypto->snow3g_lfsr[5])); + + crypto->snow3g_fsm[2] = octeon_snow3g_s2(crypto->snow3g_fsm[1]); + crypto->snow3g_fsm[1] = octeon_snow3g_s1(crypto->snow3g_fsm[0]); + crypto->snow3g_fsm[0] = r; + return f; +} + +static void octeon_snow3g_clock_lfsr(MIPSOcteonCryptoState *crypto, + bool init_mode, uint32_t f) +{ + uint32_t s0 = crypto->snow3g_lfsr[0]; + uint32_t s11 = crypto->snow3g_lfsr[11]; + uint32_t v = (s0 << 8) ^ octeon_snow3g_mulalpha(s0 >> 24) ^ + crypto->snow3g_lfsr[2] ^ (s11 >> 8) ^ + octeon_snow3g_divalpha((uint8_t)s11); + int i; + + if (init_mode) { + v ^= f; + } + + for (i = 0; i < 15; i++) { + crypto->snow3g_lfsr[i] = crypto->snow3g_lfsr[i + 1]; + } + crypto->snow3g_lfsr[15] = v; +} + +static uint32_t octeon_snow3g_generate_word(MIPSOcteonCryptoState *crypto) +{ + uint32_t f = octeon_snow3g_clock_fsm(crypto); + uint32_t z = f ^ crypto->snow3g_lfsr[0]; + + octeon_snow3g_clock_lfsr(crypto, false, 0); + return z; +} + +static void octeon_snow3g_queue_result(MIPSOcteonCryptoState *crypto) +{ + uint32_t z0 = octeon_snow3g_generate_word(crypto); + uint32_t z1 = octeon_snow3g_generate_word(crypto); + + crypto->snow3g_result = ((uint64_t)z0 << 32) | z1; +} + +static void octeon_snow3g_start(MIPSOcteonCryptoState *crypto, uint64_t data) +{ + int i; + + octeon_set_shared_mode(crypto, OCTEON_SHARED_MODE_SNOW3G); + for (i = 0; i < 7; i++) { + uint64_t pair = crypto->hsh_datw[i]; + + crypto->snow3g_lfsr[i * 2] = pair >> 32; + crypto->snow3g_lfsr[i * 2 + 1] = pair; + } + crypto->snow3g_lfsr[14] = data >> 32; + crypto->snow3g_lfsr[15] = data; + memset(crypto->snow3g_fsm, 0, sizeof(crypto->snow3g_fsm)); + + for (i = 0; i < 32; i++) { + uint32_t f = octeon_snow3g_clock_fsm(crypto); + + octeon_snow3g_clock_lfsr(crypto, true, f); + } + + (void)octeon_snow3g_clock_fsm(crypto); + octeon_snow3g_clock_lfsr(crypto, false, 0); + octeon_snow3g_queue_result(crypto); +} + +static void octeon_snow3g_more(MIPSOcteonCryptoState *crypto) +{ + octeon_set_shared_mode(crypto, OCTEON_SHARED_MODE_SNOW3G); + octeon_snow3g_queue_result(crypto); +} static void octeon_gfm_mul(const uint64_t x[2], const uint64_t y[2], uint16_t poly, uint64_t out[2]) { @@ -719,6 +942,16 @@ void helper_octeon_cp2_mt_gfm_xormul1(CPUMIPSState *env, uint64_t value) } crypto->gfm_xor0 = 0; } +void helper_octeon_cp2_mt_snow3g_start(CPUMIPSState *env, uint64_t value) +{ + octeon_snow3g_start(&env->octeon_crypto, value); +} + +void helper_octeon_cp2_mt_snow3g_more(CPUMIPSState *env, uint64_t value) +{ + (void)value; + octeon_snow3g_more(&env->octeon_crypto); +} void helper_octeon_cp2_mt_zuc_start(CPUMIPSState *env, uint64_t value) { octeon_zuc_start(&env->octeon_crypto, value); -- 2.54.0
