diff options
Diffstat (limited to 'target/riscv')
| -rw-r--r-- | target/riscv/cpu.c | 83 | ||||
| -rw-r--r-- | target/riscv/cpu_bits.h | 8 | ||||
| -rw-r--r-- | target/riscv/cpu_cfg.h | 9 | ||||
| -rw-r--r-- | target/riscv/cpu_helper.c | 6 | ||||
| -rw-r--r-- | target/riscv/crypto_helper.c | 51 | ||||
| -rw-r--r-- | target/riscv/csr.c | 54 | ||||
| -rw-r--r-- | target/riscv/debug.c | 15 | ||||
| -rw-r--r-- | target/riscv/debug.h | 3 | ||||
| -rw-r--r-- | target/riscv/helper.h | 98 | ||||
| -rw-r--r-- | target/riscv/insn32.decode | 58 | ||||
| -rw-r--r-- | target/riscv/insn_trans/trans_rvv.c.inc | 171 | ||||
| -rw-r--r-- | target/riscv/insn_trans/trans_rvvk.c.inc | 606 | ||||
| -rw-r--r-- | target/riscv/insn_trans/trans_rvzfa.c.inc | 4 | ||||
| -rw-r--r-- | target/riscv/kvm.c | 201 | ||||
| -rw-r--r-- | target/riscv/kvm_riscv.h | 5 | ||||
| -rw-r--r-- | target/riscv/meson.build | 4 | ||||
| -rw-r--r-- | target/riscv/pmp.c | 4 | ||||
| -rw-r--r-- | target/riscv/translate.c | 1 | ||||
| -rw-r--r-- | target/riscv/vcrypto_helper.c | 970 | ||||
| -rw-r--r-- | target/riscv/vector_helper.c | 245 | ||||
| -rw-r--r-- | target/riscv/vector_internals.c | 81 | ||||
| -rw-r--r-- | target/riscv/vector_internals.h | 228 |
22 files changed, 2475 insertions, 430 deletions
diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c index 6b93b04453..f227c7664e 100644 --- a/target/riscv/cpu.c +++ b/target/riscv/cpu.c @@ -87,7 +87,9 @@ static const struct isa_ext_data isa_edata_arr[] = { ISA_EXT_DATA_ENTRY(zicond, PRIV_VERSION_1_12_0, ext_zicond), ISA_EXT_DATA_ENTRY(zicsr, PRIV_VERSION_1_10_0, ext_icsr), ISA_EXT_DATA_ENTRY(zifencei, PRIV_VERSION_1_10_0, ext_ifencei), + ISA_EXT_DATA_ENTRY(zihintntl, PRIV_VERSION_1_10_0, ext_zihintntl), ISA_EXT_DATA_ENTRY(zihintpause, PRIV_VERSION_1_10_0, ext_zihintpause), + ISA_EXT_DATA_ENTRY(zmmul, PRIV_VERSION_1_12_0, ext_zmmul), ISA_EXT_DATA_ENTRY(zawrs, PRIV_VERSION_1_12_0, ext_zawrs), ISA_EXT_DATA_ENTRY(zfa, PRIV_VERSION_1_12_0, ext_zfa), ISA_EXT_DATA_ENTRY(zfbfmin, PRIV_VERSION_1_12_0, ext_zfbfmin), @@ -119,6 +121,8 @@ static const struct isa_ext_data isa_edata_arr[] = { ISA_EXT_DATA_ENTRY(zksed, PRIV_VERSION_1_12_0, ext_zksed), ISA_EXT_DATA_ENTRY(zksh, PRIV_VERSION_1_12_0, ext_zksh), ISA_EXT_DATA_ENTRY(zkt, PRIV_VERSION_1_12_0, ext_zkt), + ISA_EXT_DATA_ENTRY(zvbb, PRIV_VERSION_1_12_0, ext_zvbb), + ISA_EXT_DATA_ENTRY(zvbc, PRIV_VERSION_1_12_0, ext_zvbc), ISA_EXT_DATA_ENTRY(zve32f, PRIV_VERSION_1_10_0, ext_zve32f), ISA_EXT_DATA_ENTRY(zve64f, PRIV_VERSION_1_10_0, ext_zve64f), ISA_EXT_DATA_ENTRY(zve64d, PRIV_VERSION_1_10_0, ext_zve64d), @@ -126,9 +130,16 @@ static const struct isa_ext_data isa_edata_arr[] = { ISA_EXT_DATA_ENTRY(zvfbfwma, PRIV_VERSION_1_12_0, ext_zvfbfwma), ISA_EXT_DATA_ENTRY(zvfh, PRIV_VERSION_1_12_0, ext_zvfh), ISA_EXT_DATA_ENTRY(zvfhmin, PRIV_VERSION_1_12_0, ext_zvfhmin), + ISA_EXT_DATA_ENTRY(zvkg, PRIV_VERSION_1_12_0, ext_zvkg), + ISA_EXT_DATA_ENTRY(zvkned, PRIV_VERSION_1_12_0, ext_zvkned), + ISA_EXT_DATA_ENTRY(zvknha, PRIV_VERSION_1_12_0, ext_zvknha), + ISA_EXT_DATA_ENTRY(zvknhb, PRIV_VERSION_1_12_0, ext_zvknhb), + ISA_EXT_DATA_ENTRY(zvksed, PRIV_VERSION_1_12_0, ext_zvksed), + ISA_EXT_DATA_ENTRY(zvksh, PRIV_VERSION_1_12_0, ext_zvksh), ISA_EXT_DATA_ENTRY(zhinx, PRIV_VERSION_1_12_0, ext_zhinx), ISA_EXT_DATA_ENTRY(zhinxmin, PRIV_VERSION_1_12_0, ext_zhinxmin), ISA_EXT_DATA_ENTRY(smaia, PRIV_VERSION_1_12_0, ext_smaia), + ISA_EXT_DATA_ENTRY(smepmp, PRIV_VERSION_1_12_0, epmp), ISA_EXT_DATA_ENTRY(smstateen, PRIV_VERSION_1_12_0, ext_smstateen), ISA_EXT_DATA_ENTRY(ssaia, PRIV_VERSION_1_12_0, ext_ssaia), ISA_EXT_DATA_ENTRY(sscofpmf, PRIV_VERSION_1_12_0, ext_sscofpmf), @@ -298,6 +309,17 @@ static uint8_t satp_mode_from_str(const char *satp_mode_str) uint8_t satp_mode_max_from_map(uint32_t map) { + /* + * 'map = 0' will make us return (31 - 32), which C will + * happily overflow to UINT_MAX. There's no good result to + * return if 'map = 0' (e.g. returning 0 will be ambiguous + * with the result for 'map = 1'). + * + * Assert out if map = 0. Callers will have to deal with + * it outside of this function. + */ + g_assert(map > 0); + /* map here has at least one bit set, so no problem with clz */ return 31 - __builtin_clz(map); } @@ -875,9 +897,9 @@ static void riscv_cpu_reset_hold(Object *obj) env->two_stage_lookup = false; env->menvcfg = (cpu->cfg.ext_svpbmt ? MENVCFG_PBMTE : 0) | - (cpu->cfg.ext_svadu ? MENVCFG_HADE : 0); + (cpu->cfg.ext_svadu ? MENVCFG_ADUE : 0); env->henvcfg = (cpu->cfg.ext_svpbmt ? HENVCFG_PBMTE : 0) | - (cpu->cfg.ext_svadu ? HENVCFG_HADE : 0); + (cpu->cfg.ext_svadu ? HENVCFG_ADUE : 0); /* Initialized default priorities of local interrupts. */ for (i = 0; i < ARRAY_SIZE(env->miprio); i++) { @@ -904,7 +926,7 @@ static void riscv_cpu_reset_hold(Object *obj) #ifndef CONFIG_USER_ONLY if (cpu->cfg.debug) { - riscv_trigger_init(env); + riscv_trigger_reset_hold(env); } if (kvm_enabled()) { @@ -1269,6 +1291,25 @@ void riscv_cpu_validate_set_extensions(RISCVCPU *cpu, Error **errp) return; } + /* + * In principle Zve*x would also suffice here, were they supported + * in qemu + */ + if ((cpu->cfg.ext_zvbb || cpu->cfg.ext_zvkg || cpu->cfg.ext_zvkned || + cpu->cfg.ext_zvknha || cpu->cfg.ext_zvksed || cpu->cfg.ext_zvksh) && + !cpu->cfg.ext_zve32f) { + error_setg(errp, + "Vector crypto extensions require V or Zve* extensions"); + return; + } + + if ((cpu->cfg.ext_zvbc || cpu->cfg.ext_zvknhb) && !cpu->cfg.ext_zve64f) { + error_setg( + errp, + "Zvbc and Zvknhb extensions require V or Zve64{f,d} extensions"); + return; + } + if (cpu->cfg.ext_zk) { cpu->cfg.ext_zkn = true; cpu->cfg.ext_zkr = true; @@ -1303,9 +1344,15 @@ void riscv_cpu_validate_set_extensions(RISCVCPU *cpu, Error **errp) static void riscv_cpu_satp_mode_finalize(RISCVCPU *cpu, Error **errp) { bool rv32 = riscv_cpu_mxl(&cpu->env) == MXL_RV32; - uint8_t satp_mode_map_max; - uint8_t satp_mode_supported_max = - satp_mode_max_from_map(cpu->cfg.satp_mode.supported); + uint8_t satp_mode_map_max, satp_mode_supported_max; + + /* The CPU wants the OS to decide which satp mode to use */ + if (cpu->cfg.satp_mode.supported == 0) { + return; + } + + satp_mode_supported_max = + satp_mode_max_from_map(cpu->cfg.satp_mode.supported); if (cpu->cfg.satp_mode.map == 0) { if (cpu->cfg.satp_mode.init == 0) { @@ -1395,6 +1442,11 @@ static void riscv_cpu_realize_tcg(DeviceState *dev, Error **errp) CPURISCVState *env = &cpu->env; Error *local_err = NULL; + if (object_dynamic_cast(OBJECT(dev), TYPE_RISCV_CPU_HOST)) { + error_setg(errp, "'host' CPU is not compatible with TCG acceleration"); + return; + } + riscv_cpu_validate_misa_mxl(cpu, &local_err); if (local_err != NULL) { error_propagate(errp, local_err); @@ -1473,6 +1525,12 @@ static void riscv_cpu_realize(DeviceState *dev, Error **errp) riscv_cpu_register_gdb_regs_for_features(cs); +#ifndef CONFIG_USER_ONLY + if (cpu->cfg.debug) { + riscv_trigger_realize(&cpu->env); + } +#endif + qemu_init_vcpu(cs); cpu_reset(cs); @@ -1756,6 +1814,7 @@ static Property riscv_cpu_extensions[] = { DEFINE_PROP_BOOL("sscofpmf", RISCVCPU, cfg.ext_sscofpmf, false), DEFINE_PROP_BOOL("Zifencei", RISCVCPU, cfg.ext_ifencei, true), DEFINE_PROP_BOOL("Zicsr", RISCVCPU, cfg.ext_icsr, true), + DEFINE_PROP_BOOL("Zihintntl", RISCVCPU, cfg.ext_zihintntl, true), DEFINE_PROP_BOOL("Zihintpause", RISCVCPU, cfg.ext_zihintpause, true), DEFINE_PROP_BOOL("Zawrs", RISCVCPU, cfg.ext_zawrs, true), DEFINE_PROP_BOOL("Zfa", RISCVCPU, cfg.ext_zfa, true), @@ -1816,6 +1875,7 @@ static Property riscv_cpu_extensions[] = { DEFINE_PROP_BOOL("zcf", RISCVCPU, cfg.ext_zcf, false), DEFINE_PROP_BOOL("zcmp", RISCVCPU, cfg.ext_zcmp, false), DEFINE_PROP_BOOL("zcmt", RISCVCPU, cfg.ext_zcmt, false), + DEFINE_PROP_BOOL("zicond", RISCVCPU, cfg.ext_zicond, false), /* Vendor-specific custom extensions */ DEFINE_PROP_BOOL("xtheadba", RISCVCPU, cfg.ext_xtheadba, false), @@ -1832,7 +1892,6 @@ static Property riscv_cpu_extensions[] = { DEFINE_PROP_BOOL("xventanacondops", RISCVCPU, cfg.ext_XVentanaCondOps, false), /* These are experimental so mark with 'x-' */ - DEFINE_PROP_BOOL("x-zicond", RISCVCPU, cfg.ext_zicond, false), /* ePMP 0.9.3 */ DEFINE_PROP_BOOL("x-epmp", RISCVCPU, cfg.epmp, false), @@ -1846,6 +1905,16 @@ static Property riscv_cpu_extensions[] = { DEFINE_PROP_BOOL("x-zvfbfmin", RISCVCPU, cfg.ext_zvfbfmin, false), DEFINE_PROP_BOOL("x-zvfbfwma", RISCVCPU, cfg.ext_zvfbfwma, false), + /* Vector cryptography extensions */ + DEFINE_PROP_BOOL("x-zvbb", RISCVCPU, cfg.ext_zvbb, false), + DEFINE_PROP_BOOL("x-zvbc", RISCVCPU, cfg.ext_zvbc, false), + DEFINE_PROP_BOOL("x-zvkg", RISCVCPU, cfg.ext_zvkg, false), + DEFINE_PROP_BOOL("x-zvkned", RISCVCPU, cfg.ext_zvkned, false), + DEFINE_PROP_BOOL("x-zvknha", RISCVCPU, cfg.ext_zvknha, false), + DEFINE_PROP_BOOL("x-zvknhb", RISCVCPU, cfg.ext_zvknhb, false), + DEFINE_PROP_BOOL("x-zvksed", RISCVCPU, cfg.ext_zvksed, false), + DEFINE_PROP_BOOL("x-zvksh", RISCVCPU, cfg.ext_zvksh, false), + DEFINE_PROP_END_OF_LIST(), }; diff --git a/target/riscv/cpu_bits.h b/target/riscv/cpu_bits.h index 31a8d80990..3d6ffaabc7 100644 --- a/target/riscv/cpu_bits.h +++ b/target/riscv/cpu_bits.h @@ -745,12 +745,12 @@ typedef enum RISCVException { #define MENVCFG_CBIE (3UL << 4) #define MENVCFG_CBCFE BIT(6) #define MENVCFG_CBZE BIT(7) -#define MENVCFG_HADE (1ULL << 61) +#define MENVCFG_ADUE (1ULL << 61) #define MENVCFG_PBMTE (1ULL << 62) #define MENVCFG_STCE (1ULL << 63) /* For RV32 */ -#define MENVCFGH_HADE BIT(29) +#define MENVCFGH_ADUE BIT(29) #define MENVCFGH_PBMTE BIT(30) #define MENVCFGH_STCE BIT(31) @@ -763,12 +763,12 @@ typedef enum RISCVException { #define HENVCFG_CBIE MENVCFG_CBIE #define HENVCFG_CBCFE MENVCFG_CBCFE #define HENVCFG_CBZE MENVCFG_CBZE -#define HENVCFG_HADE MENVCFG_HADE +#define HENVCFG_ADUE MENVCFG_ADUE #define HENVCFG_PBMTE MENVCFG_PBMTE #define HENVCFG_STCE MENVCFG_STCE /* For RV32 */ -#define HENVCFGH_HADE MENVCFGH_HADE +#define HENVCFGH_ADUE MENVCFGH_ADUE #define HENVCFGH_PBMTE MENVCFGH_PBMTE #define HENVCFGH_STCE MENVCFGH_STCE diff --git a/target/riscv/cpu_cfg.h b/target/riscv/cpu_cfg.h index 2bd9510ba3..0e6a0f245c 100644 --- a/target/riscv/cpu_cfg.h +++ b/target/riscv/cpu_cfg.h @@ -66,6 +66,7 @@ struct RISCVCPUConfig { bool ext_icbom; bool ext_icboz; bool ext_zicond; + bool ext_zihintntl; bool ext_zihintpause; bool ext_smstateen; bool ext_sstc; @@ -85,6 +86,14 @@ struct RISCVCPUConfig { bool ext_zve32f; bool ext_zve64f; bool ext_zve64d; + bool ext_zvbb; + bool ext_zvbc; + bool ext_zvkg; + bool ext_zvkned; + bool ext_zvknha; + bool ext_zvknhb; + bool ext_zvksed; + bool ext_zvksh; bool ext_zmmul; bool ext_zvfbfmin; bool ext_zvfbfwma; diff --git a/target/riscv/cpu_helper.c b/target/riscv/cpu_helper.c index 9f611d89bb..3a02079290 100644 --- a/target/riscv/cpu_helper.c +++ b/target/riscv/cpu_helper.c @@ -861,11 +861,11 @@ static int get_physical_address(CPURISCVState *env, hwaddr *physical, } bool pbmte = env->menvcfg & MENVCFG_PBMTE; - bool hade = env->menvcfg & MENVCFG_HADE; + bool adue = env->menvcfg & MENVCFG_ADUE; if (first_stage && two_stage && env->virt_enabled) { pbmte = pbmte && (env->henvcfg & HENVCFG_PBMTE); - hade = hade && (env->henvcfg & HENVCFG_HADE); + adue = adue && (env->henvcfg & HENVCFG_ADUE); } int ptshift = (levels - 1) * ptidxbits; @@ -1026,7 +1026,7 @@ restart: /* Page table updates need to be atomic with MTTCG enabled */ if (updated_pte != pte && !is_debug) { - if (!hade) { + if (!adue) { return TRANSLATE_FAIL; } diff --git a/target/riscv/crypto_helper.c b/target/riscv/crypto_helper.c index 99d85a6188..bb084e00ef 100644 --- a/target/riscv/crypto_helper.c +++ b/target/riscv/crypto_helper.c @@ -25,29 +25,6 @@ #include "crypto/aes-round.h" #include "crypto/sm4.h" -#define AES_XTIME(a) \ - ((a << 1) ^ ((a & 0x80) ? 0x1b : 0)) - -#define AES_GFMUL(a, b) (( \ - (((b) & 0x1) ? (a) : 0) ^ \ - (((b) & 0x2) ? AES_XTIME(a) : 0) ^ \ - (((b) & 0x4) ? AES_XTIME(AES_XTIME(a)) : 0) ^ \ - (((b) & 0x8) ? AES_XTIME(AES_XTIME(AES_XTIME(a))) : 0)) & 0xFF) - -static inline uint32_t aes_mixcolumn_byte(uint8_t x, bool fwd) -{ - uint32_t u; - - if (fwd) { - u = (AES_GFMUL(x, 3) << 24) | (x << 16) | (x << 8) | - (AES_GFMUL(x, 2) << 0); - } else { - u = (AES_GFMUL(x, 0xb) << 24) | (AES_GFMUL(x, 0xd) << 16) | - (AES_GFMUL(x, 0x9) << 8) | (AES_GFMUL(x, 0xe) << 0); - } - return u; -} - #define sext32_xlen(x) (target_ulong)(int32_t)(x) static inline target_ulong aes32_operation(target_ulong shamt, @@ -55,23 +32,20 @@ static inline target_ulong aes32_operation(target_ulong shamt, bool enc, bool mix) { uint8_t si = rs2 >> shamt; - uint8_t so; uint32_t mixed; target_ulong res; if (enc) { - so = AES_sbox[si]; if (mix) { - mixed = aes_mixcolumn_byte(so, true); + mixed = be32_to_cpu(AES_Te0[si]); } else { - mixed = so; + mixed = AES_sbox[si]; } } else { - so = AES_isbox[si]; if (mix) { - mixed = aes_mixcolumn_byte(so, false); + mixed = be32_to_cpu(AES_Td0[si]); } else { - mixed = so; + mixed = AES_isbox[si]; } } mixed = rol32(mixed, shamt); @@ -174,24 +148,17 @@ target_ulong HELPER(aes64ks1i)(target_ulong rs1, target_ulong rnum) uint8_t enc_rnum = rnum; uint32_t temp = (RS1 >> 32) & 0xFFFFFFFF; - uint8_t rcon_ = 0; - target_ulong result; + AESState t, rc = {}; if (enc_rnum != 0xA) { temp = ror32(temp, 8); /* Rotate right by 8 */ - rcon_ = round_consts[enc_rnum]; + rc.w[0] = rc.w[1] = round_consts[enc_rnum]; } - temp = ((uint32_t)AES_sbox[(temp >> 24) & 0xFF] << 24) | - ((uint32_t)AES_sbox[(temp >> 16) & 0xFF] << 16) | - ((uint32_t)AES_sbox[(temp >> 8) & 0xFF] << 8) | - ((uint32_t)AES_sbox[(temp >> 0) & 0xFF] << 0); - - temp ^= rcon_; + t.w[0] = t.w[1] = t.w[2] = t.w[3] = temp; + aesenc_SB_SR_AK(&t, &t, &rc, false); - result = ((uint64_t)temp << 32) | temp; - - return result; + return t.d[0]; } target_ulong HELPER(aes64im)(target_ulong rs1) diff --git a/target/riscv/csr.c b/target/riscv/csr.c index ca95ae1527..85a31dc420 100644 --- a/target/riscv/csr.c +++ b/target/riscv/csr.c @@ -1684,7 +1684,7 @@ static int rmw_iprio(target_ulong xlen, static int rmw_xireg(CPURISCVState *env, int csrno, target_ulong *val, target_ulong new_val, target_ulong wr_mask) { - bool virt; + bool virt, isel_reserved; uint8_t *iprio; int ret = -EINVAL; target_ulong priv, isel, vgein; @@ -1694,6 +1694,7 @@ static int rmw_xireg(CPURISCVState *env, int csrno, target_ulong *val, /* Decode register details from CSR number */ virt = false; + isel_reserved = false; switch (csrno) { case CSR_MIREG: iprio = env->miprio; @@ -1738,11 +1739,13 @@ static int rmw_xireg(CPURISCVState *env, int csrno, target_ulong *val, riscv_cpu_mxl_bits(env)), val, new_val, wr_mask); } + } else { + isel_reserved = true; } done: if (ret) { - return (env->virt_enabled && virt) ? + return (env->virt_enabled && virt && !isel_reserved) ? RISCV_EXCP_VIRT_INSTRUCTION_FAULT : RISCV_EXCP_ILLEGAL_INST; } return RISCV_EXCP_NONE; @@ -1833,8 +1836,11 @@ static RISCVException write_mcountinhibit(CPURISCVState *env, int csrno, { int cidx; PMUCTRState *counter; + RISCVCPU *cpu = env_archcpu(env); - env->mcountinhibit = val; + /* WARL register - disable unavailable counters; TM bit is always 0 */ + env->mcountinhibit = + val & (cpu->pmu_avail_ctrs | COUNTEREN_CY | COUNTEREN_IR); /* Check if any other counter is also monitoring cycles/instructions */ for (cidx = 0; cidx < RV_MAX_MHPMCOUNTERS; cidx++) { @@ -1857,7 +1863,11 @@ static RISCVException read_mcounteren(CPURISCVState *env, int csrno, static RISCVException write_mcounteren(CPURISCVState *env, int csrno, target_ulong val) { - env->mcounteren = val; + RISCVCPU *cpu = env_archcpu(env); + + /* WARL register - disable unavailable counters */ + env->mcounteren = val & (cpu->pmu_avail_ctrs | COUNTEREN_CY | COUNTEREN_TM | + COUNTEREN_IR); return RISCV_EXCP_NONE; } @@ -1950,7 +1960,7 @@ static RISCVException write_menvcfg(CPURISCVState *env, int csrno, if (riscv_cpu_mxl(env) == MXL_RV64) { mask |= (cfg->ext_svpbmt ? MENVCFG_PBMTE : 0) | (cfg->ext_sstc ? MENVCFG_STCE : 0) | - (cfg->ext_svadu ? MENVCFG_HADE : 0); + (cfg->ext_svadu ? MENVCFG_ADUE : 0); } env->menvcfg = (env->menvcfg & ~mask) | (val & mask); @@ -1970,7 +1980,7 @@ static RISCVException write_menvcfgh(CPURISCVState *env, int csrno, const RISCVCPUConfig *cfg = riscv_cpu_cfg(env); uint64_t mask = (cfg->ext_svpbmt ? MENVCFG_PBMTE : 0) | (cfg->ext_sstc ? MENVCFG_STCE : 0) | - (cfg->ext_svadu ? MENVCFG_HADE : 0); + (cfg->ext_svadu ? MENVCFG_ADUE : 0); uint64_t valh = (uint64_t)val << 32; env->menvcfg = (env->menvcfg & ~mask) | (valh & mask); @@ -2022,7 +2032,7 @@ static RISCVException read_henvcfg(CPURISCVState *env, int csrno, * henvcfg.stce is read_only 0 when menvcfg.stce = 0 * henvcfg.hade is read_only 0 when menvcfg.hade = 0 */ - *val = env->henvcfg & (~(HENVCFG_PBMTE | HENVCFG_STCE | HENVCFG_HADE) | + *val = env->henvcfg & (~(HENVCFG_PBMTE | HENVCFG_STCE | HENVCFG_ADUE) | env->menvcfg); return RISCV_EXCP_NONE; } @@ -2039,7 +2049,7 @@ static RISCVException write_henvcfg(CPURISCVState *env, int csrno, } if (riscv_cpu_mxl(env) == MXL_RV64) { - mask |= env->menvcfg & (HENVCFG_PBMTE | HENVCFG_STCE | HENVCFG_HADE); + mask |= env->menvcfg & (HENVCFG_PBMTE | HENVCFG_STCE | HENVCFG_ADUE); } env->henvcfg = (env->henvcfg & ~mask) | (val & mask); @@ -2057,7 +2067,7 @@ static RISCVException read_henvcfgh(CPURISCVState *env, int csrno, return ret; } - *val = (env->henvcfg & (~(HENVCFG_PBMTE | HENVCFG_STCE | HENVCFG_HADE) | + *val = (env->henvcfg & (~(HENVCFG_PBMTE | HENVCFG_STCE | HENVCFG_ADUE) | env->menvcfg)) >> 32; return RISCV_EXCP_NONE; } @@ -2066,7 +2076,7 @@ static RISCVException write_henvcfgh(CPURISCVState *env, int csrno, target_ulong val) { uint64_t mask = env->menvcfg & (HENVCFG_PBMTE | HENVCFG_STCE | - HENVCFG_HADE); + HENVCFG_ADUE); uint64_t valh = (uint64_t)val << 32; RISCVException ret; @@ -3907,21 +3917,27 @@ static RISCVException riscv_csrrw_do64(CPURISCVState *env, int csrno, target_ulong write_mask) { RISCVException ret; - target_ulong old_value; + target_ulong old_value = 0; /* execute combined read/write operation if it exists */ if (csr_ops[csrno].op) { return csr_ops[csrno].op(env, csrno, ret_value, new_value, write_mask); } - /* if no accessor exists then return failure */ - if (!csr_ops[csrno].read) { - return RISCV_EXCP_ILLEGAL_INST; - } - /* read old value */ - ret = csr_ops[csrno].read(env, csrno, &old_value); - if (ret != RISCV_EXCP_NONE) { - return ret; + /* + * ret_value == NULL means that rd=x0 and we're coming from helper_csrw() + * and we can't throw side effects caused by CSR reads. + */ + if (ret_value) { + /* if no accessor exists then return failure */ + if (!csr_ops[csrno].read) { + return RISCV_EXCP_ILLEGAL_INST; + } + /* read old value */ + ret = csr_ops[csrno].read(env, csrno, &old_value); + if (ret != RISCV_EXCP_NONE) { + return ret; + } } /* write value if writable and write mask set, otherwise drop writes */ diff --git a/target/riscv/debug.c b/target/riscv/debug.c index 211f5921b6..4945d1a1f2 100644 --- a/target/riscv/debug.c +++ b/target/riscv/debug.c @@ -903,7 +903,17 @@ bool riscv_cpu_debug_check_watchpoint(CPUState *cs, CPUWatchpoint *wp) return false; } -void riscv_trigger_init(CPURISCVState *env) +void riscv_trigger_realize(CPURISCVState *env) +{ + int i; + + for (i = 0; i < RV_MAX_TRIGGERS; i++) { + env->itrigger_timer[i] = timer_new_ns(QEMU_CLOCK_VIRTUAL, + riscv_itrigger_timer_cb, env); + } +} + +void riscv_trigger_reset_hold(CPURISCVState *env) { target_ulong tdata1 = build_tdata1(env, TRIGGER_TYPE_AD_MATCH, 0, 0); int i; @@ -928,7 +938,6 @@ void riscv_trigger_init(CPURISCVState *env) env->tdata3[i] = 0; env->cpu_breakpoint[i] = NULL; env->cpu_watchpoint[i] = NULL; - env->itrigger_timer[i] = timer_new_ns(QEMU_CLOCK_VIRTUAL, - riscv_itrigger_timer_cb, env); + timer_del(env->itrigger_timer[i]); } } diff --git a/target/riscv/debug.h b/target/riscv/debug.h index c471748d5a..5794aa6ee5 100644 --- a/target/riscv/debug.h +++ b/target/riscv/debug.h @@ -143,7 +143,8 @@ void riscv_cpu_debug_excp_handler(CPUState *cs); bool riscv_cpu_debug_check_breakpoint(CPUState *cs); bool riscv_cpu_debug_check_watchpoint(CPUState *cs, CPUWatchpoint *wp); -void riscv_trigger_init(CPURISCVState *env); +void riscv_trigger_realize(CPURISCVState *env); +void riscv_trigger_reset_hold(CPURISCVState *env); bool riscv_itrigger_enabled(CPURISCVState *env); void riscv_itrigger_update_priv(CPURISCVState *env); diff --git a/target/riscv/helper.h b/target/riscv/helper.h index c95adaf08a..8a63523851 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -1182,3 +1182,101 @@ DEF_HELPER_5(vfwcvtbf16_f_f_v, void, ptr, ptr, ptr, env, i32) DEF_HELPER_6(vfwmaccbf16_vv, void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_6(vfwmaccbf16_vf, void, ptr, ptr, i64, ptr, env, i32) + +/* Vector crypto functions */ +DEF_HELPER_6(vclmul_vv, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vclmul_vx, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vclmulh_vv, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vclmulh_vx, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vror_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vror_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vror_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vror_vv_d, void, ptr, ptr, ptr, ptr, env, i32) + +DEF_HELPER_6(vror_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vror_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vror_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vror_vx_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vrol_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vrol_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vrol_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vrol_vv_d, void, ptr, ptr, ptr, ptr, env, i32) + +DEF_HELPER_6(vrol_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vrol_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vrol_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vrol_vx_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_5(vrev8_v_b, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vrev8_v_h, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vrev8_v_w, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vrev8_v_d, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vbrev8_v_b, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vbrev8_v_h, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vbrev8_v_w, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vbrev8_v_d, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vbrev_v_b, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vbrev_v_h, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vbrev_v_w, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vbrev_v_d, void, ptr, ptr, ptr, env, i32) + +DEF_HELPER_5(vclz_v_b, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vclz_v_h, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vclz_v_w, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vclz_v_d, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vctz_v_b, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vctz_v_h, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vctz_v_w, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vctz_v_d, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vcpop_v_b, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vcpop_v_h, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vcpop_v_w, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vcpop_v_d, void, ptr, ptr, ptr, env, i32) + +DEF_HELPER_6(vwsll_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsll_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsll_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsll_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsll_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsll_vx_w, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vandn_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vandn_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vandn_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vandn_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vandn_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vandn_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vandn_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vandn_vx_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_2(egs_check, void, i32, env) + +DEF_HELPER_4(vaesef_vv, void, ptr, ptr, env, i32) +DEF_HELPER_4(vaesef_vs, void, ptr, ptr, env, i32) +DEF_HELPER_4(vaesdf_vv, void, ptr, ptr, env, i32) +DEF_HELPER_4(vaesdf_vs, void, ptr, ptr, env, i32) +DEF_HELPER_4(vaesem_vv, void, ptr, ptr, env, i32) +DEF_HELPER_4(vaesem_vs, void, ptr, ptr, env, i32) +DEF_HELPER_4(vaesdm_vv, void, ptr, ptr, env, i32) +DEF_HELPER_4(vaesdm_vs, void, ptr, ptr, env, i32) +DEF_HELPER_4(vaesz_vs, void, ptr, ptr, env, i32) +DEF_HELPER_5(vaeskf1_vi, void, ptr, ptr, i32, env, i32) +DEF_HELPER_5(vaeskf2_vi, void, ptr, ptr, i32, env, i32) + +DEF_HELPER_5(vsha2ms_vv, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vsha2ch32_vv, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vsha2ch64_vv, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vsha2cl32_vv, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vsha2cl64_vv, void, ptr, ptr, ptr, env, i32) + +DEF_HELPER_5(vsm3me_vv, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vsm3c_vi, void, ptr, ptr, i32, env, i32) + +DEF_HELPER_5(vghsh_vv, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_4(vgmul_vv, void, ptr, ptr, env, i32) + +DEF_HELPER_5(vsm4k_vi, void, ptr, ptr, i32, env, i32) +DEF_HELPER_4(vsm4r_vv, void, ptr, ptr, env, i32) +DEF_HELPER_4(vsm4r_vs, void, ptr, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index e341fa9213..33597fe2bb 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -37,6 +37,7 @@ %imm_u 12:s20 !function=ex_shift_12 %imm_bs 30:2 !function=ex_shift_3 %imm_rnum 20:4 +%imm_z6 26:1 15:5 # Argument sets: &empty @@ -74,6 +75,7 @@ @r_rm ....... ..... ..... ... ..... ....... %rs2 %rs1 %rm %rd @r2_rm ....... ..... ..... ... ..... ....... %rs1 %rm %rd @r2 ....... ..... ..... ... ..... ....... &r2 %rs1 %rd +@r2_vm_1 ...... . ..... ..... ... ..... ....... &rmr vm=1 %rs2 %rd @r2_nfvm ... ... vm:1 ..... ..... ... ..... ....... &r2nfvm %nf %rs1 %rd @r2_vm ...... vm:1 ..... ..... ... ..... ....... &rmr %rs2 %rd @r1_vm ...... vm:1 ..... ..... ... ..... ....... %rd @@ -82,6 +84,7 @@ @r_vm ...... vm:1 ..... ..... ... ..... ....... &rmrr %rs2 %rs1 %rd @r_vm_1 ...... . ..... ..... ... ..... ....... &rmrr vm=1 %rs2 %rs1 %rd @r_vm_0 ...... . ..... ..... ... ..... ....... &rmrr vm=0 %rs2 %rs1 %rd +@r2_zimm6 ..... . vm:1 ..... ..... ... ..... ....... &rmrr %rs2 rs1=%imm_z6 %rd @r2_zimm11 . zimm:11 ..... ... ..... ....... %rs1 %rd @r2_zimm10 .. zimm:10 ..... ... ..... ....... %rs1 %rd @r2_s ....... ..... ..... ... ..... ....... %rs2 %rs1 @@ -946,3 +949,58 @@ vfwcvtbf16_f_f_v 010010 . ..... 01101 001 ..... 1010111 @r2_vm # *** Zvfbfwma Standard Extension *** vfwmaccbf16_vv 111011 . ..... ..... 001 ..... 1010111 @r_vm vfwmaccbf16_vf 111011 . ..... ..... 101 ..... 1010111 @r_vm + +# *** Zvbc vector crypto extension *** +vclmul_vv 001100 . ..... ..... 010 ..... 1010111 @r_vm +vclmul_vx 001100 . ..... ..... 110 ..... 1010111 @r_vm +vclmulh_vv 001101 . ..... ..... 010 ..... 1010111 @r_vm +vclmulh_vx 001101 . ..... ..... 110 ..... 1010111 @r_vm + +# *** Zvbb vector crypto extension *** +vrol_vv 010101 . ..... ..... 000 ..... 1010111 @r_vm +vrol_vx 010101 . ..... ..... 100 ..... 1010111 @r_vm +vror_vv 010100 . ..... ..... 000 ..... 1010111 @r_vm +vror_vx 010100 . ..... ..... 100 ..... 1010111 @r_vm +vror_vi 01010. . ..... ..... 011 ..... 1010111 @r2_zimm6 +vbrev8_v 010010 . ..... 01000 010 ..... 1010111 @r2_vm +vrev8_v 010010 . ..... 01001 010 ..... 1010111 @r2_vm +vandn_vv 000001 . ..... ..... 000 ..... 1010111 @r_vm +vandn_vx 000001 . ..... ..... 100 ..... 1010111 @r_vm +vbrev_v 010010 . ..... 01010 010 ..... 1010111 @r2_vm +vclz_v 010010 . ..... 01100 010 ..... 1010111 @r2_vm +vctz_v 010010 . ..... 01101 010 ..... 1010111 @r2_vm +vcpop_v 010010 . ..... 01110 010 ..... 1010111 @r2_vm +vwsll_vv 110101 . ..... ..... 000 ..... 1010111 @r_vm +vwsll_vx 110101 . ..... ..... 100 ..... 1010111 @r_vm +vwsll_vi 110101 . ..... ..... 011 ..... 1010111 @r_vm + +# *** Zvkned vector crypto extension *** +vaesef_vv 101000 1 ..... 00011 010 ..... 1110111 @r2_vm_1 +vaesef_vs 101001 1 ..... 00011 010 ..... 1110111 @r2_vm_1 +vaesdf_vv 101000 1 ..... 00001 010 ..... 1110111 @r2_vm_1 +vaesdf_vs 101001 1 ..... 00001 010 ..... 1110111 @r2_vm_1 +vaesem_vv 101000 1 ..... 00010 010 ..... 1110111 @r2_vm_1 +vaesem_vs 101001 1 ..... 00010 010 ..... 1110111 @r2_vm_1 +vaesdm_vv 101000 1 ..... 00000 010 ..... 1110111 @r2_vm_1 +vaesdm_vs 101001 1 ..... 00000 010 ..... 1110111 @r2_vm_1 +vaesz_vs 101001 1 ..... 00111 010 ..... 1110111 @r2_vm_1 +vaeskf1_vi 100010 1 ..... ..... 010 ..... 1110111 @r_vm_1 +vaeskf2_vi 101010 1 ..... ..... 010 ..... 1110111 @r_vm_1 + +# *** Zvknh vector crypto extension *** +vsha2ms_vv 101101 1 ..... ..... 010 ..... 1110111 @r_vm_1 +vsha2ch_vv 101110 1 ..... ..... 010 ..... 1110111 @r_vm_1 +vsha2cl_vv 101111 1 ..... ..... 010 ..... 1110111 @r_vm_1 + +# *** Zvksh vector crypto extension *** +vsm3me_vv 100000 1 ..... ..... 010 ..... 1110111 @r_vm_1 +vsm3c_vi 101011 1 ..... ..... 010 ..... 1110111 @r_vm_1 + +# *** Zvkg vector crypto extension *** +vghsh_vv 101100 1 ..... ..... 010 ..... 1110111 @r_vm_1 +vgmul_vv 101000 1 ..... 10001 010 ..... 1110111 @r2_vm_1 + +# *** Zvksed vector crypto extension *** +vsm4k_vi 100001 1 ..... ..... 010 ..... 1110111 @r_vm_1 +vsm4r_vv 101000 1 ..... 10000 010 ..... 1110111 @r2_vm_1 +vsm4r_vs 101001 1 ..... 10000 010 ..... 1110111 @r2_vm_1 diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc index 6ab63f4442..63404f61fc 100644 --- a/target/riscv/insn_trans/trans_rvv.c.inc +++ b/target/riscv/insn_trans/trans_rvv.c.inc @@ -617,7 +617,6 @@ static bool ldst_us_trans(uint32_t vd, uint32_t rs1, uint32_t data, TCGv_i32 desc; TCGLabel *over = gen_new_label(); - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); dest = tcg_temp_new_ptr(); @@ -786,7 +785,6 @@ static bool ldst_stride_trans(uint32_t vd, uint32_t rs1, uint32_t rs2, TCGv_i32 desc; TCGLabel *over = gen_new_label(); - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); dest = tcg_temp_new_ptr(); @@ -893,7 +891,6 @@ static bool ldst_index_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, TCGv_i32 desc; TCGLabel *over = gen_new_label(); - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); dest = tcg_temp_new_ptr(); @@ -1034,7 +1031,6 @@ static bool ldff_trans(uint32_t vd, uint32_t rs1, uint32_t data, TCGv_i32 desc; TCGLabel *over = gen_new_label(); - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); dest = tcg_temp_new_ptr(); @@ -1187,11 +1183,7 @@ do_opivv_gvec(DisasContext *s, arg_rmrr *a, GVecGen3Fn *gvec_fn, gen_helper_gvec_4_ptr *fn) { TCGLabel *over = gen_new_label(); - if (!opivv_check(s, a)) { - return false; - } - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) { @@ -1223,6 +1215,9 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ gen_helper_##NAME##_b, gen_helper_##NAME##_h, \ gen_helper_##NAME##_w, gen_helper_##NAME##_d, \ }; \ + if (!opivv_check(s, a)) { \ + return false; \ + } \ return do_opivv_gvec(s, a, tcg_gen_gvec_##SUF, fns[s->sew]); \ } @@ -1241,7 +1236,6 @@ static bool opivx_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, uint32_t vm, uint32_t data = 0; TCGLabel *over = gen_new_label(); - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); dest = tcg_temp_new_ptr(); @@ -1282,10 +1276,6 @@ static inline bool do_opivx_gvec(DisasContext *s, arg_rmrr *a, GVecGen2sFn *gvec_fn, gen_helper_opivx *fn) { - if (!opivx_check(s, a)) { - return false; - } - if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) { TCGv_i64 src1 = tcg_temp_new_i64(); @@ -1307,6 +1297,9 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ gen_helper_##NAME##_b, gen_helper_##NAME##_h, \ gen_helper_##NAME##_w, gen_helper_##NAME##_d, \ }; \ + if (!opivx_check(s, a)) { \ + return false; \ + } \ return do_opivx_gvec(s, a, tcg_gen_gvec_##SUF, fns[s->sew]); \ } @@ -1405,7 +1398,6 @@ static bool opivi_trans(uint32_t vd, uint32_t imm, uint32_t vs2, uint32_t vm, uint32_t data = 0; TCGLabel *over = gen_new_label(); - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); dest = tcg_temp_new_ptr(); @@ -1439,10 +1431,6 @@ static inline bool do_opivi_gvec(DisasContext *s, arg_rmrr *a, GVecGen2iFn *gvec_fn, gen_helper_opivx *fn, imm_mode_t imm_mode) { - if (!opivx_check(s, a)) { - return false; - } - if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) { gvec_fn(s->sew, vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2), extract_imm(s, a->rs1, imm_mode), MAXSZ(s), MAXSZ(s)); @@ -1460,6 +1448,9 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ gen_helper_##OPIVX##_b, gen_helper_##OPIVX##_h, \ gen_helper_##OPIVX##_w, gen_helper_##OPIVX##_d, \ }; \ + if (!opivx_check(s, a)) { \ + return false; \ + } \ return do_opivi_gvec(s, a, tcg_gen_gvec_##SUF, \ fns[s->sew], IMM_MODE); \ } @@ -1492,7 +1483,6 @@ static bool do_opivv_widen(DisasContext *s, arg_rmrr *a, if (checkfn(s, a)) { uint32_t data = 0; TCGLabel *over = gen_new_label(); - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); data = FIELD_DP32(data, VDATA, VM, a->vm); @@ -1536,30 +1526,24 @@ static bool opivx_widen_check(DisasContext *s, arg_rmrr *a) vext_check_ds(s, a->rd, a->rs2, a->vm); } -static bool do_opivx_widen(DisasContext *s, arg_rmrr *a, - gen_helper_opivx *fn) -{ - if (opivx_widen_check(s, a)) { - return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fn, s); - } - return false; -} - -#define GEN_OPIVX_WIDEN_TRANS(NAME) \ -static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ -{ \ - static gen_helper_opivx * const fns[3] = { \ - gen_helper_##NAME##_b, \ - gen_helper_##NAME##_h, \ - gen_helper_##NAME##_w \ - }; \ - return do_opivx_widen(s, a, fns[s->sew]); \ +#define GEN_OPIVX_WIDEN_TRANS(NAME, CHECK) \ +static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ +{ \ + if (CHECK(s, a)) { \ + static gen_helper_opivx * const fns[3] = { \ + gen_helper_##NAME##_b, \ + gen_helper_##NAME##_h, \ + gen_helper_##NAME##_w \ + }; \ + return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fns[s->sew], s); \ + } \ + return false; \ } -GEN_OPIVX_WIDEN_TRANS(vwaddu_vx) -GEN_OPIVX_WIDEN_TRANS(vwadd_vx) -GEN_OPIVX_WIDEN_TRANS(vwsubu_vx) -GEN_OPIVX_WIDEN_TRANS(vwsub_vx) +GEN_OPIVX_WIDEN_TRANS(vwaddu_vx, opivx_widen_check) +GEN_OPIVX_WIDEN_TRANS(vwadd_vx, opivx_widen_check) +GEN_OPIVX_WIDEN_TRANS(vwsubu_vx, opivx_widen_check) +GEN_OPIVX_WIDEN_TRANS(vwsub_vx, opivx_widen_check) /* WIDEN OPIVV with WIDEN */ static bool opiwv_widen_check(DisasContext *s, arg_rmrr *a) @@ -1575,7 +1559,6 @@ static bool do_opiwv_widen(DisasContext *s, arg_rmrr *a, if (opiwv_widen_check(s, a)) { uint32_t data = 0; TCGLabel *over = gen_new_label(); - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); data = FIELD_DP32(data, VDATA, VM, a->vm); @@ -1643,38 +1626,39 @@ GEN_OPIWX_WIDEN_TRANS(vwadd_wx) GEN_OPIWX_WIDEN_TRANS(vwsubu_wx) GEN_OPIWX_WIDEN_TRANS(vwsub_wx) +static bool opivv_trans(uint32_t vd, uint32_t vs1, uint32_t vs2, uint32_t vm, + gen_helper_gvec_4_ptr *fn, DisasContext *s) +{ + uint32_t data = 0; + TCGLabel *over = gen_new_label(); + tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); + + data = FIELD_DP32(data, VDATA, VM, vm); + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); + data = FIELD_DP32(data, VDATA, VTA, s->vta); + data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s); + data = FIELD_DP32(data, VDATA, VMA, s->vma); + tcg_gen_gvec_4_ptr(vreg_ofs(s, vd), vreg_ofs(s, 0), vreg_ofs(s, vs1), + vreg_ofs(s, vs2), cpu_env, s->cfg_ptr->vlen / 8, + s->cfg_ptr->vlen / 8, data, fn); + mark_vs_dirty(s); + gen_set_label(over); + return true; +} + /* Vector Integer Add-with-Carry / Subtract-with-Borrow Instructions */ /* OPIVV without GVEC IR */ -#define GEN_OPIVV_TRANS(NAME, CHECK) \ -static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ -{ \ - if (CHECK(s, a)) { \ - uint32_t data = 0; \ - static gen_helper_gvec_4_ptr * const fns[4] = { \ - gen_helper_##NAME##_b, gen_helper_##NAME##_h, \ - gen_helper_##NAME##_w, gen_helper_##NAME##_d, \ - }; \ - TCGLabel *over = gen_new_label(); \ - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \ - \ - data = FIELD_DP32(data, VDATA, VM, a->vm); \ - data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ - data = FIELD_DP32(data, VDATA, VTA, s->vta); \ - data = \ - FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);\ - data = FIELD_DP32(data, VDATA, VMA, s->vma); \ - tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ - vreg_ofs(s, a->rs1), \ - vreg_ofs(s, a->rs2), cpu_env, \ - s->cfg_ptr->vlen / 8, \ - s->cfg_ptr->vlen / 8, data, \ - fns[s->sew]); \ - mark_vs_dirty(s); \ - gen_set_label(over); \ - return true; \ - } \ - return false; \ +#define GEN_OPIVV_TRANS(NAME, CHECK) \ +static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ +{ \ + if (CHECK(s, a)) { \ + static gen_helper_gvec_4_ptr * const fns[4] = { \ + gen_helper_##NAME##_b, gen_helper_##NAME##_h, \ + gen_helper_##NAME##_w, gen_helper_##NAME##_d, \ + }; \ + return opivv_trans(a->rd, a->rs1, a->rs2, a->vm, fns[s->sew], s);\ + } \ + return false; \ } /* @@ -1783,10 +1767,6 @@ static inline bool do_opivx_gvec_shift(DisasContext *s, arg_rmrr *a, GVecGen2sFn32 *gvec_fn, gen_helper_opivx *fn) { - if (!opivx_check(s, a)) { - return false; - } - if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) { TCGv_i32 src1 = tcg_temp_new_i32(); @@ -1808,7 +1788,9 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ gen_helper_##NAME##_b, gen_helper_##NAME##_h, \ gen_helper_##NAME##_w, gen_helper_##NAME##_d, \ }; \ - \ + if (!opivx_check(s, a)) { \ + return false; \ + } \ return do_opivx_gvec_shift(s, a, tcg_gen_gvec_##SUF, fns[s->sew]); \ } @@ -1840,7 +1822,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ gen_helper_##NAME##_w, \ }; \ TCGLabel *over = gen_new_label(); \ - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \ \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ @@ -2010,9 +1991,9 @@ GEN_OPIVX_TRANS(vrem_vx, opivx_check) GEN_OPIVV_WIDEN_TRANS(vwmul_vv, opivv_widen_check) GEN_OPIVV_WIDEN_TRANS(vwmulu_vv, opivv_widen_check) GEN_OPIVV_WIDEN_TRANS(vwmulsu_vv, opivv_widen_check) -GEN_OPIVX_WIDEN_TRANS(vwmul_vx) -GEN_OPIVX_WIDEN_TRANS(vwmulu_vx) -GEN_OPIVX_WIDEN_TRANS(vwmulsu_vx) +GEN_OPIVX_WIDEN_TRANS(vwmul_vx, opivx_widen_check) +GEN_OPIVX_WIDEN_TRANS(vwmulu_vx, opivx_widen_check) +GEN_OPIVX_WIDEN_TRANS(vwmulsu_vx, opivx_widen_check) /* Vector Single-Width Integer Multiply-Add Instructions */ GEN_OPIVV_TRANS(vmacc_vv, opivv_check) @@ -2028,10 +2009,10 @@ GEN_OPIVX_TRANS(vnmsub_vx, opivx_check) GEN_OPIVV_WIDEN_TRANS(vwmaccu_vv, opivv_widen_check) GEN_OPIVV_WIDEN_TRANS(vwmacc_vv, opivv_widen_check) GEN_OPIVV_WIDEN_TRANS(vwmaccsu_vv, opivv_widen_check) -GEN_OPIVX_WIDEN_TRANS(vwmaccu_vx) -GEN_OPIVX_WIDEN_TRANS(vwmacc_vx) -GEN_OPIVX_WIDEN_TRANS(vwmaccsu_vx) -GEN_OPIVX_WIDEN_TRANS(vwmaccus_vx) +GEN_OPIVX_WIDEN_TRANS(vwmaccu_vx, opivx_widen_check) +GEN_OPIVX_WIDEN_TRANS(vwmacc_vx, opivx_widen_check) +GEN_OPIVX_WIDEN_TRANS(vwmaccsu_vx, opivx_widen_check) +GEN_OPIVX_WIDEN_TRANS(vwmaccus_vx, opivx_widen_check) /* Vector Integer Merge and Move Instructions */ static bool trans_vmv_v_v(DisasContext *s, arg_vmv_v_v *a) @@ -2052,7 +2033,6 @@ static bool trans_vmv_v_v(DisasContext *s, arg_vmv_v_v *a) gen_helper_vmv_v_v_w, gen_helper_vmv_v_v_d, }; TCGLabel *over = gen_new_label(); - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); tcg_gen_gvec_2_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, a->rs1), @@ -2076,7 +2056,6 @@ static bool trans_vmv_v_x(DisasContext *s, arg_vmv_v_x *a) vext_check_ss(s, a->rd, 0, 1)) { TCGv s1; TCGLabel *over = gen_new_label(); - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); s1 = get_gpr(s, a->rs1, EXT_SIGN); @@ -2138,7 +2117,6 @@ static bool trans_vmv_v_i(DisasContext *s, arg_vmv_v_i *a) gen_helper_vmv_v_x_w, gen_helper_vmv_v_x_d, }; TCGLabel *over = gen_new_label(); - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); s1 = tcg_constant_i64(simm); @@ -2286,7 +2264,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ }; \ TCGLabel *over = gen_new_label(); \ gen_set_rm(s, RISCV_FRM_DYN); \ - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \ \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ @@ -2321,7 +2298,6 @@ static bool opfvf_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, TCGv_i64 t1; TCGLabel *over = gen_new_label(); - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); dest = tcg_temp_new_ptr(); @@ -2406,7 +2382,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ }; \ TCGLabel *over = gen_new_label(); \ gen_set_rm(s, RISCV_FRM_DYN); \ - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);\ \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ @@ -2481,7 +2456,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ }; \ TCGLabel *over = gen_new_label(); \ gen_set_rm(s, RISCV_FRM_DYN); \ - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \ \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ @@ -2599,7 +2573,6 @@ static bool do_opfv(DisasContext *s, arg_rmr *a, uint32_t data = 0; TCGLabel *over = gen_new_label(); gen_set_rm_chkfrm(s, rm); - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); data = FIELD_DP32(data, VDATA, VM, a->vm); @@ -2711,7 +2684,6 @@ static bool trans_vfmv_v_f(DisasContext *s, arg_vfmv_v_f *a) gen_helper_vmv_v_x_d, }; TCGLabel *over = gen_new_label(); - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); t1 = tcg_temp_new_i64(); @@ -2790,7 +2762,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \ }; \ TCGLabel *over = gen_new_label(); \ gen_set_rm_chkfrm(s, FRM); \ - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \ \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ @@ -2842,7 +2813,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \ }; \ TCGLabel *over = gen_new_label(); \ gen_set_rm(s, RISCV_FRM_DYN); \ - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \ \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ @@ -2910,7 +2880,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \ }; \ TCGLabel *over = gen_new_label(); \ gen_set_rm_chkfrm(s, FRM); \ - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \ \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ @@ -2960,7 +2929,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \ }; \ TCGLabel *over = gen_new_label(); \ gen_set_rm_chkfrm(s, FRM); \ - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \ \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ @@ -3051,7 +3019,6 @@ static bool trans_##NAME(DisasContext *s, arg_r *a) \ uint32_t data = 0; \ gen_helper_gvec_4_ptr *fn = gen_helper_##NAME; \ TCGLabel *over = gen_new_label(); \ - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \ \ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ @@ -3222,7 +3189,6 @@ static bool trans_vid_v(DisasContext *s, arg_vid_v *a) require_vm(a->vm, a->rd)) { uint32_t data = 0; TCGLabel *over = gen_new_label(); - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); data = FIELD_DP32(data, VDATA, VM, a->vm); @@ -3409,7 +3375,6 @@ static bool trans_vmv_s_x(DisasContext *s, arg_vmv_s_x *a) TCGv s1; TCGLabel *over = gen_new_label(); - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); t1 = tcg_temp_new_i64(); @@ -3466,8 +3431,7 @@ static bool trans_vfmv_s_f(DisasContext *s, arg_vfmv_s_f *a) TCGv_i64 t1; TCGLabel *over = gen_new_label(); - /* if vl == 0 or vstart >= vl, skip vector register write back */ - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); + /* if vstart >= vl, skip vector register write back */ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); /* NaN-box f[rs1] */ @@ -3718,7 +3682,6 @@ static bool int_ext_op(DisasContext *s, arg_rmr *a, uint8_t seq) uint32_t data = 0; gen_helper_gvec_3_ptr *fn; TCGLabel *over = gen_new_label(); - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); static gen_helper_gvec_3_ptr * const fns[6][4] = { diff --git a/target/riscv/insn_trans/trans_rvvk.c.inc b/target/riscv/insn_trans/trans_rvvk.c.inc new file mode 100644 index 0000000000..c00c70dfc6 --- /dev/null +++ b/target/riscv/insn_trans/trans_rvvk.c.inc @@ -0,0 +1,606 @@ +/* + * RISC-V translation routines for the vector crypto extension. + * + * Copyright (C) 2023 SiFive, Inc. + * Written by Codethink Ltd and SiFive. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2 or later, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * Zvbc + */ + +#define GEN_VV_MASKED_TRANS(NAME, CHECK) \ + static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ + { \ + if (CHECK(s, a)) { \ + return opivv_trans(a->rd, a->rs1, a->rs2, a->vm, \ + gen_helper_##NAME, s); \ + } \ + return false; \ + } + +static bool vclmul_vv_check(DisasContext *s, arg_rmrr *a) +{ + return opivv_check(s, a) && + s->cfg_ptr->ext_zvbc == true && + s->sew == MO_64; +} + +GEN_VV_MASKED_TRANS(vclmul_vv, vclmul_vv_check) +GEN_VV_MASKED_TRANS(vclmulh_vv, vclmul_vv_check) + +#define GEN_VX_MASKED_TRANS(NAME, CHECK) \ + static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ + { \ + if (CHECK(s, a)) { \ + return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, \ + gen_helper_##NAME, s); \ + } \ + return false; \ + } + +static bool vclmul_vx_check(DisasContext *s, arg_rmrr *a) +{ + return opivx_check(s, a) && + s->cfg_ptr->ext_zvbc == true && + s->sew == MO_64; +} + +GEN_VX_MASKED_TRANS(vclmul_vx, vclmul_vx_check) +GEN_VX_MASKED_TRANS(vclmulh_vx, vclmul_vx_check) + +/* + * Zvbb + */ + +#define GEN_OPIVI_GVEC_TRANS_CHECK(NAME, IMM_MODE, OPIVX, SUF, CHECK) \ + static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ + { \ + if (CHECK(s, a)) { \ + static gen_helper_opivx *const fns[4] = { \ + gen_helper_##OPIVX##_b, \ + gen_helper_##OPIVX##_h, \ + gen_helper_##OPIVX##_w, \ + gen_helper_##OPIVX##_d, \ + }; \ + return do_opivi_gvec(s, a, tcg_gen_gvec_##SUF, fns[s->sew], \ + IMM_MODE); \ + } \ + return false; \ + } + +#define GEN_OPIVV_GVEC_TRANS_CHECK(NAME, SUF, CHECK) \ + static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ + { \ + if (CHECK(s, a)) { \ + static gen_helper_gvec_4_ptr *const fns[4] = { \ + gen_helper_##NAME##_b, \ + gen_helper_##NAME##_h, \ + gen_helper_##NAME##_w, \ + gen_helper_##NAME##_d, \ + }; \ + return do_opivv_gvec(s, a, tcg_gen_gvec_##SUF, fns[s->sew]); \ + } \ + return false; \ + } + +#define GEN_OPIVX_GVEC_SHIFT_TRANS_CHECK(NAME, SUF, CHECK) \ + static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ + { \ + if (CHECK(s, a)) { \ + static gen_helper_opivx *const fns[4] = { \ + gen_helper_##NAME##_b, \ + gen_helper_##NAME##_h, \ + gen_helper_##NAME##_w, \ + gen_helper_##NAME##_d, \ + }; \ + return do_opivx_gvec_shift(s, a, tcg_gen_gvec_##SUF, \ + fns[s->sew]); \ + } \ + return false; \ + } + +static bool zvbb_vv_check(DisasContext *s, arg_rmrr *a) +{ + return opivv_check(s, a) && s->cfg_ptr->ext_zvbb == true; +} + +static bool zvbb_vx_check(DisasContext *s, arg_rmrr *a) +{ + return opivx_check(s, a) && s->cfg_ptr->ext_zvbb == true; +} + +/* vrol.v[vx] */ +GEN_OPIVV_GVEC_TRANS_CHECK(vrol_vv, rotlv, zvbb_vv_check) +GEN_OPIVX_GVEC_SHIFT_TRANS_CHECK(vrol_vx, rotls, zvbb_vx_check) + +/* vror.v[vxi] */ +GEN_OPIVV_GVEC_TRANS_CHECK(vror_vv, rotrv, zvbb_vv_check) +GEN_OPIVX_GVEC_SHIFT_TRANS_CHECK(vror_vx, rotrs, zvbb_vx_check) +GEN_OPIVI_GVEC_TRANS_CHECK(vror_vi, IMM_TRUNC_SEW, vror_vx, rotri, zvbb_vx_check) + +#define GEN_OPIVX_GVEC_TRANS_CHECK(NAME, SUF, CHECK) \ + static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ + { \ + if (CHECK(s, a)) { \ + static gen_helper_opivx *const fns[4] = { \ + gen_helper_##NAME##_b, \ + gen_helper_##NAME##_h, \ + gen_helper_##NAME##_w, \ + gen_helper_##NAME##_d, \ + }; \ + return do_opivx_gvec(s, a, tcg_gen_gvec_##SUF, fns[s->sew]); \ + } \ + return false; \ + } + +/* vandn.v[vx] */ +GEN_OPIVV_GVEC_TRANS_CHECK(vandn_vv, andc, zvbb_vv_check) +GEN_OPIVX_GVEC_TRANS_CHECK(vandn_vx, andcs, zvbb_vx_check) + +#define GEN_OPIV_TRANS(NAME, CHECK) \ + static bool trans_##NAME(DisasContext *s, arg_rmr *a) \ + { \ + if (CHECK(s, a)) { \ + uint32_t data = 0; \ + static gen_helper_gvec_3_ptr *const fns[4] = { \ + gen_helper_##NAME##_b, \ + gen_helper_##NAME##_h, \ + gen_helper_##NAME##_w, \ + gen_helper_##NAME##_d, \ + }; \ + TCGLabel *over = gen_new_label(); \ + tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \ + \ + data = FIELD_DP32(data, VDATA, VM, a->vm); \ + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ + data = FIELD_DP32(data, VDATA, VTA, s->vta); \ + data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s); \ + data = FIELD_DP32(data, VDATA, VMA, s->vma); \ + tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ + vreg_ofs(s, a->rs2), cpu_env, \ + s->cfg_ptr->vlen / 8, s->cfg_ptr->vlen / 8, \ + data, fns[s->sew]); \ + mark_vs_dirty(s); \ + gen_set_label(over); \ + return true; \ + } \ + return false; \ + } + +static bool zvbb_opiv_check(DisasContext *s, arg_rmr *a) +{ + return s->cfg_ptr->ext_zvbb == true && + require_rvv(s) && + vext_check_isa_ill(s) && + vext_check_ss(s, a->rd, a->rs2, a->vm); +} + +GEN_OPIV_TRANS(vbrev8_v, zvbb_opiv_check) +GEN_OPIV_TRANS(vrev8_v, zvbb_opiv_check) +GEN_OPIV_TRANS(vbrev_v, zvbb_opiv_check) +GEN_OPIV_TRANS(vclz_v, zvbb_opiv_check) +GEN_OPIV_TRANS(vctz_v, zvbb_opiv_check) +GEN_OPIV_TRANS(vcpop_v, zvbb_opiv_check) + +static bool vwsll_vv_check(DisasContext *s, arg_rmrr *a) +{ + return s->cfg_ptr->ext_zvbb && opivv_widen_check(s, a); +} + +static bool vwsll_vx_check(DisasContext *s, arg_rmrr *a) +{ + return s->cfg_ptr->ext_zvbb && opivx_widen_check(s, a); +} + +/* OPIVI without GVEC IR */ +#define GEN_OPIVI_WIDEN_TRANS(NAME, IMM_MODE, OPIVX, CHECK) \ + static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ + { \ + if (CHECK(s, a)) { \ + static gen_helper_opivx *const fns[3] = { \ + gen_helper_##OPIVX##_b, \ + gen_helper_##OPIVX##_h, \ + gen_helper_##OPIVX##_w, \ + }; \ + return opivi_trans(a->rd, a->rs1, a->rs2, a->vm, fns[s->sew], s, \ + IMM_MODE); \ + } \ + return false; \ + } + +GEN_OPIVV_WIDEN_TRANS(vwsll_vv, vwsll_vv_check) +GEN_OPIVX_WIDEN_TRANS(vwsll_vx, vwsll_vx_check) +GEN_OPIVI_WIDEN_TRANS(vwsll_vi, IMM_ZX, vwsll_vx, vwsll_vx_check) + +/* + * Zvkned + */ + +#define ZVKNED_EGS 4 + +#define GEN_V_UNMASKED_TRANS(NAME, CHECK, EGS) \ + static bool trans_##NAME(DisasContext *s, arg_##NAME *a) \ + { \ + if (CHECK(s, a)) { \ + TCGv_ptr rd_v, rs2_v; \ + TCGv_i32 desc, egs; \ + uint32_t data = 0; \ + TCGLabel *over = gen_new_label(); \ + \ + if (!s->vstart_eq_zero || !s->vl_eq_vlmax) { \ + /* save opcode for unwinding in case we throw an exception */ \ + decode_save_opc(s); \ + egs = tcg_constant_i32(EGS); \ + gen_helper_egs_check(egs, cpu_env); \ + tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \ + } \ + \ + data = FIELD_DP32(data, VDATA, VM, a->vm); \ + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ + data = FIELD_DP32(data, VDATA, VTA, s->vta); \ + data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s); \ + data = FIELD_DP32(data, VDATA, VMA, s->vma); \ + rd_v = tcg_temp_new_ptr(); \ + rs2_v = tcg_temp_new_ptr(); \ + desc = tcg_constant_i32( \ + simd_desc(s->cfg_ptr->vlen / 8, s->cfg_ptr->vlen / 8, data)); \ + tcg_gen_addi_ptr(rd_v, cpu_env, vreg_ofs(s, a->rd)); \ + tcg_gen_addi_ptr(rs2_v, cpu_env, vreg_ofs(s, a->rs2)); \ + gen_helper_##NAME(rd_v, rs2_v, cpu_env, desc); \ + mark_vs_dirty(s); \ + gen_set_label(over); \ + return true; \ + } \ + return false; \ + } + +static bool vaes_check_vv(DisasContext *s, arg_rmr *a) +{ + int egw_bytes = ZVKNED_EGS << s->sew; + return s->cfg_ptr->ext_zvkned == true && + require_rvv(s) && + vext_check_isa_ill(s) && + MAXSZ(s) >= egw_bytes && + require_align(a->rd, s->lmul) && + require_align(a->rs2, s->lmul) && + s->sew == MO_32; +} + +static bool vaes_check_overlap(DisasContext *s, int vd, int vs2) +{ + int8_t op_size = s->lmul <= 0 ? 1 : 1 << s->lmul; + return !is_overlapped(vd, op_size, vs2, 1); +} + +static bool vaes_check_vs(DisasContext *s, arg_rmr *a) +{ + int egw_bytes = ZVKNED_EGS << s->sew; + return vaes_check_overlap(s, a->rd, a->rs2) && + MAXSZ(s) >= egw_bytes && + s->cfg_ptr->ext_zvkned == true && + require_rvv(s) && + vext_check_isa_ill(s) && + require_align(a->rd, s->lmul) && + s->sew == MO_32; +} + +GEN_V_UNMASKED_TRANS(vaesef_vv, vaes_check_vv, ZVKNED_EGS) +GEN_V_UNMASKED_TRANS(vaesef_vs, vaes_check_vs, ZVKNED_EGS) +GEN_V_UNMASKED_TRANS(vaesdf_vv, vaes_check_vv, ZVKNED_EGS) +GEN_V_UNMASKED_TRANS(vaesdf_vs, vaes_check_vs, ZVKNED_EGS) +GEN_V_UNMASKED_TRANS(vaesdm_vv, vaes_check_vv, ZVKNED_EGS) +GEN_V_UNMASKED_TRANS(vaesdm_vs, vaes_check_vs, ZVKNED_EGS) +GEN_V_UNMASKED_TRANS(vaesz_vs, vaes_check_vs, ZVKNED_EGS) +GEN_V_UNMASKED_TRANS(vaesem_vv, vaes_check_vv, ZVKNED_EGS) +GEN_V_UNMASKED_TRANS(vaesem_vs, vaes_check_vs, ZVKNED_EGS) + +#define GEN_VI_UNMASKED_TRANS(NAME, CHECK, EGS) \ + static bool trans_##NAME(DisasContext *s, arg_##NAME *a) \ + { \ + if (CHECK(s, a)) { \ + TCGv_ptr rd_v, rs2_v; \ + TCGv_i32 uimm_v, desc, egs; \ + uint32_t data = 0; \ + TCGLabel *over = gen_new_label(); \ + \ + if (!s->vstart_eq_zero || !s->vl_eq_vlmax) { \ + /* save opcode for unwinding in case we throw an exception */ \ + decode_save_opc(s); \ + egs = tcg_constant_i32(EGS); \ + gen_helper_egs_check(egs, cpu_env); \ + tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \ + } \ + \ + data = FIELD_DP32(data, VDATA, VM, a->vm); \ + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ + data = FIELD_DP32(data, VDATA, VTA, s->vta); \ + data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s); \ + data = FIELD_DP32(data, VDATA, VMA, s->vma); \ + \ + rd_v = tcg_temp_new_ptr(); \ + rs2_v = tcg_temp_new_ptr(); \ + uimm_v = tcg_constant_i32(a->rs1); \ + desc = tcg_constant_i32( \ + simd_desc(s->cfg_ptr->vlen / 8, s->cfg_ptr->vlen / 8, data)); \ + tcg_gen_addi_ptr(rd_v, cpu_env, vreg_ofs(s, a->rd)); \ + tcg_gen_addi_ptr(rs2_v, cpu_env, vreg_ofs(s, a->rs2)); \ + gen_helper_##NAME(rd_v, rs2_v, uimm_v, cpu_env, desc); \ + mark_vs_dirty(s); \ + gen_set_label(over); \ + return true; \ + } \ + return false; \ + } + +static bool vaeskf1_check(DisasContext *s, arg_vaeskf1_vi *a) +{ + int egw_bytes = ZVKNED_EGS << s->sew; + return s->cfg_ptr->ext_zvkned == true && + require_rvv(s) && + vext_check_isa_ill(s) && + MAXSZ(s) >= egw_bytes && + s->sew == MO_32 && + require_align(a->rd, s->lmul) && + require_align(a->rs2, s->lmul); +} + +static bool vaeskf2_check(DisasContext *s, arg_vaeskf2_vi *a) +{ + int egw_bytes = ZVKNED_EGS << s->sew; + return s->cfg_ptr->ext_zvkned == true && + require_rvv(s) && + vext_check_isa_ill(s) && + MAXSZ(s) >= egw_bytes && + s->sew == MO_32 && + require_align(a->rd, s->lmul) && + require_align(a->rs2, s->lmul); +} + +GEN_VI_UNMASKED_TRANS(vaeskf1_vi, vaeskf1_check, ZVKNED_EGS) +GEN_VI_UNMASKED_TRANS(vaeskf2_vi, vaeskf2_check, ZVKNED_EGS) + +/* + * Zvknh + */ + +#define ZVKNH_EGS 4 + +#define GEN_VV_UNMASKED_TRANS(NAME, CHECK, EGS) \ + static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ + { \ + if (CHECK(s, a)) { \ + uint32_t data = 0; \ + TCGLabel *over = gen_new_label(); \ + TCGv_i32 egs; \ + \ + if (!s->vstart_eq_zero || !s->vl_eq_vlmax) { \ + /* save opcode for unwinding in case we throw an exception */ \ + decode_save_opc(s); \ + egs = tcg_constant_i32(EGS); \ + gen_helper_egs_check(egs, cpu_env); \ + tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \ + } \ + \ + data = FIELD_DP32(data, VDATA, VM, a->vm); \ + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ + data = FIELD_DP32(data, VDATA, VTA, s->vta); \ + data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s); \ + data = FIELD_DP32(data, VDATA, VMA, s->vma); \ + \ + tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, a->rs1), \ + vreg_ofs(s, a->rs2), cpu_env, \ + s->cfg_ptr->vlen / 8, s->cfg_ptr->vlen / 8, \ + data, gen_helper_##NAME); \ + \ + mark_vs_dirty(s); \ + gen_set_label(over); \ + return true; \ + } \ + return false; \ + } + +static bool vsha_check_sew(DisasContext *s) +{ + return (s->cfg_ptr->ext_zvknha == true && s->sew == MO_32) || + (s->cfg_ptr->ext_zvknhb == true && + (s->sew == MO_32 || s->sew == MO_64)); +} + +static bool vsha_check(DisasContext *s, arg_rmrr *a) +{ + int egw_bytes = ZVKNH_EGS << s->sew; + int mult = 1 << MAX(s->lmul, 0); + return opivv_check(s, a) && + vsha_check_sew(s) && + MAXSZ(s) >= egw_bytes && + !is_overlapped(a->rd, mult, a->rs1, mult) && + !is_overlapped(a->rd, mult, a->rs2, mult) && + s->lmul >= 0; +} + +GEN_VV_UNMASKED_TRANS(vsha2ms_vv, vsha_check, ZVKNH_EGS) + +static bool trans_vsha2cl_vv(DisasContext *s, arg_rmrr *a) +{ + if (vsha_check(s, a)) { + uint32_t data = 0; + TCGLabel *over = gen_new_label(); + TCGv_i32 egs; + + if (!s->vstart_eq_zero || !s->vl_eq_vlmax) { + /* save opcode for unwinding in case we throw an exception */ + decode_save_opc(s); + egs = tcg_constant_i32(ZVKNH_EGS); + gen_helper_egs_check(egs, cpu_env); + tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); + } + + data = FIELD_DP32(data, VDATA, VM, a->vm); + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); + data = FIELD_DP32(data, VDATA, VTA, s->vta); + data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s); + data = FIELD_DP32(data, VDATA, VMA, s->vma); + + tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, a->rs1), + vreg_ofs(s, a->rs2), cpu_env, s->cfg_ptr->vlen / 8, + s->cfg_ptr->vlen / 8, data, + s->sew == MO_32 ? + gen_helper_vsha2cl32_vv : gen_helper_vsha2cl64_vv); + + mark_vs_dirty(s); + gen_set_label(over); + return true; + } + return false; +} + +static bool trans_vsha2ch_vv(DisasContext *s, arg_rmrr *a) +{ + if (vsha_check(s, a)) { + uint32_t data = 0; + TCGLabel *over = gen_new_label(); + TCGv_i32 egs; + + if (!s->vstart_eq_zero || !s->vl_eq_vlmax) { + /* save opcode for unwinding in case we throw an exception */ + decode_save_opc(s); + egs = tcg_constant_i32(ZVKNH_EGS); + gen_helper_egs_check(egs, cpu_env); + tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); + } + + data = FIELD_DP32(data, VDATA, VM, a->vm); + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); + data = FIELD_DP32(data, VDATA, VTA, s->vta); + data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s); + data = FIELD_DP32(data, VDATA, VMA, s->vma); + + tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, a->rs1), + vreg_ofs(s, a->rs2), cpu_env, s->cfg_ptr->vlen / 8, + s->cfg_ptr->vlen / 8, data, + s->sew == MO_32 ? + gen_helper_vsha2ch32_vv : gen_helper_vsha2ch64_vv); + + mark_vs_dirty(s); + gen_set_label(over); + return true; + } + return false; +} + +/* + * Zvksh + */ + +#define ZVKSH_EGS 8 + +static inline bool vsm3_check(DisasContext *s, arg_rmrr *a) +{ + int egw_bytes = ZVKSH_EGS << s->sew; + int mult = 1 << MAX(s->lmul, 0); + return s->cfg_ptr->ext_zvksh == true && + require_rvv(s) && + vext_check_isa_ill(s) && + !is_overlapped(a->rd, mult, a->rs2, mult) && + MAXSZ(s) >= egw_bytes && + s->sew == MO_32; +} + +static inline bool vsm3me_check(DisasContext *s, arg_rmrr *a) +{ + return vsm3_check(s, a) && vext_check_sss(s, a->rd, a->rs1, a->rs2, a->vm); +} + +static inline bool vsm3c_check(DisasContext *s, arg_rmrr *a) +{ + return vsm3_check(s, a) && vext_check_ss(s, a->rd, a->rs2, a->vm); +} + +GEN_VV_UNMASKED_TRANS(vsm3me_vv, vsm3me_check, ZVKSH_EGS) +GEN_VI_UNMASKED_TRANS(vsm3c_vi, vsm3c_check, ZVKSH_EGS) + +/* + * Zvkg + */ + +#define ZVKG_EGS 4 + +static bool vgmul_check(DisasContext *s, arg_rmr *a) +{ + int egw_bytes = ZVKG_EGS << s->sew; + return s->cfg_ptr->ext_zvkg == true && + vext_check_isa_ill(s) && + require_rvv(s) && + MAXSZ(s) >= egw_bytes && + vext_check_ss(s, a->rd, a->rs2, a->vm) && + s->sew == MO_32; +} + +GEN_V_UNMASKED_TRANS(vgmul_vv, vgmul_check, ZVKG_EGS) + +static bool vghsh_check(DisasContext *s, arg_rmrr *a) +{ + int egw_bytes = ZVKG_EGS << s->sew; + return s->cfg_ptr->ext_zvkg == true && + opivv_check(s, a) && + MAXSZ(s) >= egw_bytes && + s->sew == MO_32; +} + +GEN_VV_UNMASKED_TRANS(vghsh_vv, vghsh_check, ZVKG_EGS) + +/* + * Zvksed + */ + +#define ZVKSED_EGS 4 + +static bool zvksed_check(DisasContext *s) +{ + int egw_bytes = ZVKSED_EGS << s->sew; + return s->cfg_ptr->ext_zvksed == true && + require_rvv(s) && + vext_check_isa_ill(s) && + MAXSZ(s) >= egw_bytes && + s->sew == MO_32; +} + +static bool vsm4k_vi_check(DisasContext *s, arg_rmrr *a) +{ + return zvksed_check(s) && + require_align(a->rd, s->lmul) && + require_align(a->rs2, s->lmul); +} + +GEN_VI_UNMASKED_TRANS(vsm4k_vi, vsm4k_vi_check, ZVKSED_EGS) + +static bool vsm4r_vv_check(DisasContext *s, arg_rmr *a) +{ + return zvksed_check(s) && + require_align(a->rd, s->lmul) && + require_align(a->rs2, s->lmul); +} + +GEN_V_UNMASKED_TRANS(vsm4r_vv, vsm4r_vv_check, ZVKSED_EGS) + +static bool vsm4r_vs_check(DisasContext *s, arg_rmr *a) +{ + return zvksed_check(s) && + !is_overlapped(a->rd, 1 << MAX(s->lmul, 0), a->rs2, 1) && + require_align(a->rd, s->lmul); +} + +GEN_V_UNMASKED_TRANS(vsm4r_vs, vsm4r_vs_check, ZVKSED_EGS) diff --git a/target/riscv/insn_trans/trans_rvzfa.c.inc b/target/riscv/insn_trans/trans_rvzfa.c.inc index 2c715af3e5..0fdd2698f6 100644 --- a/target/riscv/insn_trans/trans_rvzfa.c.inc +++ b/target/riscv/insn_trans/trans_rvzfa.c.inc @@ -470,7 +470,7 @@ bool trans_fleq_d(DisasContext *ctx, arg_fleq_d *a) TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1); TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2); - gen_helper_fltq_s(dest, cpu_env, src1, src2); + gen_helper_fleq_d(dest, cpu_env, src1, src2); gen_set_gpr(ctx, a->rd, dest); return true; } @@ -485,7 +485,7 @@ bool trans_fltq_d(DisasContext *ctx, arg_fltq_d *a) TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1); TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2); - gen_helper_fltq_s(dest, cpu_env, src1, src2); + gen_helper_fltq_d(dest, cpu_env, src1, src2); gen_set_gpr(ctx, a->rd, dest); return true; } diff --git a/target/riscv/kvm.c b/target/riscv/kvm.c index dbcf26f27d..c01cfb03f4 100644 --- a/target/riscv/kvm.c +++ b/target/riscv/kvm.c @@ -36,6 +36,7 @@ #include "exec/address-spaces.h" #include "hw/boards.h" #include "hw/irq.h" +#include "hw/intc/riscv_imsic.h" #include "qemu/log.h" #include "hw/loader.h" #include "kvm_riscv.h" @@ -43,6 +44,12 @@ #include "chardev/char-fe.h" #include "migration/migration.h" #include "sysemu/runstate.h" +#include "hw/riscv/numa.h" + +void riscv_kvm_aplic_request(void *opaque, int irq, int level) +{ + kvm_set_irq(kvm_state, irq, !!level); +} static uint64_t kvm_riscv_reg_id(CPURISCVState *env, uint64_t type, uint64_t idx) @@ -926,7 +933,15 @@ int kvm_arch_init(MachineState *ms, KVMState *s) int kvm_arch_irqchip_create(KVMState *s) { - return 0; + if (kvm_kernel_irqchip_split()) { + error_report("-machine kernel_irqchip=split is not supported on RISC-V."); + exit(1); + } + + /* + * We can create the VAIA using the newer device control API. + */ + return kvm_check_extension(s, KVM_CAP_DEVICE_CTRL); } int kvm_arch_process_async_events(CPUState *cs) @@ -1027,6 +1042,190 @@ bool kvm_arch_cpu_check_are_resettable(void) return true; } +static int aia_mode; + +static const char *kvm_aia_mode_str(uint64_t mode) +{ + switch (mode) { + case KVM_DEV_RISCV_AIA_MODE_EMUL: + return "emul"; + case KVM_DEV_RISCV_AIA_MODE_HWACCEL: + return "hwaccel"; + case KVM_DEV_RISCV_AIA_MODE_AUTO: + default: + return "auto"; + }; +} + +static char *riscv_get_kvm_aia(Object *obj, Error **errp) +{ + return g_strdup(kvm_aia_mode_str(aia_mode)); +} + +static void riscv_set_kvm_aia(Object *obj, const char *val, Error **errp) +{ + if (!strcmp(val, "emul")) { + aia_mode = KVM_DEV_RISCV_AIA_MODE_EMUL; + } else if (!strcmp(val, "hwaccel")) { + aia_mode = KVM_DEV_RISCV_AIA_MODE_HWACCEL; + } else if (!strcmp(val, "auto")) { + aia_mode = KVM_DEV_RISCV_AIA_MODE_AUTO; + } else { + error_setg(errp, "Invalid KVM AIA mode"); + error_append_hint(errp, "Valid values are emul, hwaccel, and auto.\n"); + } +} + void kvm_arch_accel_class_init(ObjectClass *oc) { + object_class_property_add_str(oc, "riscv-aia", riscv_get_kvm_aia, + riscv_set_kvm_aia); + object_class_property_set_description(oc, "riscv-aia", + "Set KVM AIA mode. Valid values are " + "emul, hwaccel, and auto. Default " + "is auto."); + object_property_set_default_str(object_class_property_find(oc, "riscv-aia"), + "auto"); +} + +void kvm_riscv_aia_create(MachineState *machine, uint64_t group_shift, + uint64_t aia_irq_num, uint64_t aia_msi_num, + uint64_t aplic_base, uint64_t imsic_base, + uint64_t guest_num) +{ + int ret, i; + int aia_fd = -1; + uint64_t default_aia_mode; + uint64_t socket_count = riscv_socket_count(machine); + uint64_t max_hart_per_socket = 0; + uint64_t socket, base_hart, hart_count, socket_imsic_base, imsic_addr; + uint64_t socket_bits, hart_bits, guest_bits; + + aia_fd = kvm_create_device(kvm_state, KVM_DEV_TYPE_RISCV_AIA, false); + + if (aia_fd < 0) { + error_report("Unable to create in-kernel irqchip"); + exit(1); + } + + ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CONFIG, + KVM_DEV_RISCV_AIA_CONFIG_MODE, + &default_aia_mode, false, NULL); + if (ret < 0) { + error_report("KVM AIA: failed to get current KVM AIA mode"); + exit(1); + } + qemu_log("KVM AIA: default mode is %s\n", + kvm_aia_mode_str(default_aia_mode)); + + if (default_aia_mode != aia_mode) { + ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CONFIG, + KVM_DEV_RISCV_AIA_CONFIG_MODE, + &aia_mode, true, NULL); + if (ret < 0) + warn_report("KVM AIA: failed to set KVM AIA mode"); + else + qemu_log("KVM AIA: set current mode to %s\n", + kvm_aia_mode_str(aia_mode)); + } + + ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CONFIG, + KVM_DEV_RISCV_AIA_CONFIG_SRCS, + &aia_irq_num, true, NULL); + if (ret < 0) { + error_report("KVM AIA: failed to set number of input irq lines"); + exit(1); + } + + ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CONFIG, + KVM_DEV_RISCV_AIA_CONFIG_IDS, + &aia_msi_num, true, NULL); + if (ret < 0) { + error_report("KVM AIA: failed to set number of msi"); + exit(1); + } + + socket_bits = find_last_bit(&socket_count, BITS_PER_LONG) + 1; + ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CONFIG, + KVM_DEV_RISCV_AIA_CONFIG_GROUP_BITS, + &socket_bits, true, NULL); + if (ret < 0) { + error_report("KVM AIA: failed to set group_bits"); + exit(1); + } + + ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CONFIG, + KVM_DEV_RISCV_AIA_CONFIG_GROUP_SHIFT, + &group_shift, true, NULL); + if (ret < 0) { + error_report("KVM AIA: failed to set group_shift"); + exit(1); + } + + guest_bits = guest_num == 0 ? 0 : + find_last_bit(&guest_num, BITS_PER_LONG) + 1; + ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CONFIG, + KVM_DEV_RISCV_AIA_CONFIG_GUEST_BITS, + &guest_bits, true, NULL); + if (ret < 0) { + error_report("KVM AIA: failed to set guest_bits"); + exit(1); + } + + ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_ADDR, + KVM_DEV_RISCV_AIA_ADDR_APLIC, + &aplic_base, true, NULL); + if (ret < 0) { + error_report("KVM AIA: failed to set the base address of APLIC"); + exit(1); + } + + for (socket = 0; socket < socket_count; socket++) { + socket_imsic_base = imsic_base + socket * (1U << group_shift); + hart_count = riscv_socket_hart_count(machine, socket); + base_hart = riscv_socket_first_hartid(machine, socket); + + if (max_hart_per_socket < hart_count) { + max_hart_per_socket = hart_count; + } + + for (i = 0; i < hart_count; i++) { + imsic_addr = socket_imsic_base + i * IMSIC_HART_SIZE(guest_bits); + ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_ADDR, + KVM_DEV_RISCV_AIA_ADDR_IMSIC(i + base_hart), + &imsic_addr, true, NULL); + if (ret < 0) { + error_report("KVM AIA: failed to set the IMSIC address for hart %d", i); + exit(1); + } + } + } + + hart_bits = find_last_bit(&max_hart_per_socket, BITS_PER_LONG) + 1; + ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CONFIG, + KVM_DEV_RISCV_AIA_CONFIG_HART_BITS, + &hart_bits, true, NULL); + if (ret < 0) { + error_report("KVM AIA: failed to set hart_bits"); + exit(1); + } + + if (kvm_has_gsi_routing()) { + for (uint64_t idx = 0; idx < aia_irq_num + 1; ++idx) { + /* KVM AIA only has one APLIC instance */ + kvm_irqchip_add_irq_route(kvm_state, idx, 0, idx); + } + kvm_gsi_routing_allowed = true; + kvm_irqchip_commit_routes(kvm_state); + } + + ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CTRL, + KVM_DEV_RISCV_AIA_CTRL_INIT, + NULL, true, NULL); + if (ret < 0) { + error_report("KVM AIA: initialized fail"); + exit(1); + } + + kvm_msi_via_irqfd_allowed = kvm_irqfds_enabled(); } diff --git a/target/riscv/kvm_riscv.h b/target/riscv/kvm_riscv.h index e3ba935808..de8c209ebc 100644 --- a/target/riscv/kvm_riscv.h +++ b/target/riscv/kvm_riscv.h @@ -22,5 +22,10 @@ void kvm_riscv_init_user_properties(Object *cpu_obj); void kvm_riscv_reset_vcpu(RISCVCPU *cpu); void kvm_riscv_set_irq(RISCVCPU *cpu, int irq, int level); +void kvm_riscv_aia_create(MachineState *machine, uint64_t group_shift, + uint64_t aia_irq_num, uint64_t aia_msi_num, + uint64_t aplic_base, uint64_t imsic_base, + uint64_t guest_num); +void riscv_kvm_aplic_request(void *opaque, int irq, int level); #endif diff --git a/target/riscv/meson.build b/target/riscv/meson.build index 7f56c5f88d..660078bda1 100644 --- a/target/riscv/meson.build +++ b/target/riscv/meson.build @@ -16,11 +16,13 @@ riscv_ss.add(files( 'gdbstub.c', 'op_helper.c', 'vector_helper.c', + 'vector_internals.c', 'bitmanip_helper.c', 'translate.c', 'm128_helper.c', 'crypto_helper.c', - 'zce_helper.c' + 'zce_helper.c', + 'vcrypto_helper.c' )) riscv_ss.add(when: 'CONFIG_KVM', if_true: files('kvm.c'), if_false: files('kvm-stub.c')) diff --git a/target/riscv/pmp.c b/target/riscv/pmp.c index 9d8db493e6..5e60c26031 100644 --- a/target/riscv/pmp.c +++ b/target/riscv/pmp.c @@ -44,6 +44,10 @@ static inline uint8_t pmp_get_a_field(uint8_t cfg) */ static inline int pmp_is_locked(CPURISCVState *env, uint32_t pmp_index) { + /* mseccfg.RLB is set */ + if (MSECCFG_RLB_ISSET(env)) { + return 0; + } if (env->pmp_state.pmp[pmp_index].cfg_reg & PMP_LOCK) { return 1; diff --git a/target/riscv/translate.c b/target/riscv/translate.c index 697df1be9e..7dbf173adb 100644 --- a/target/riscv/translate.c +++ b/target/riscv/translate.c @@ -1094,6 +1094,7 @@ static uint32_t opcode_at(DisasContextBase *dcbase, target_ulong pc) #include "insn_trans/trans_rvzfa.c.inc" #include "insn_trans/trans_rvzfh.c.inc" #include "insn_trans/trans_rvk.c.inc" +#include "insn_trans/trans_rvvk.c.inc" #include "insn_trans/trans_privileged.c.inc" #include "insn_trans/trans_svinval.c.inc" #include "insn_trans/trans_rvbf16.c.inc" diff --git a/target/riscv/vcrypto_helper.c b/target/riscv/vcrypto_helper.c new file mode 100644 index 0000000000..e2d719b13b --- /dev/null +++ b/target/riscv/vcrypto_helper.c @@ -0,0 +1,970 @@ +/* + * RISC-V Vector Crypto Extension Helpers for QEMU. + * + * Copyright (C) 2023 SiFive, Inc. + * Written by Codethink Ltd and SiFive. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2 or later, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qemu/host-utils.h" +#include "qemu/bitops.h" +#include "qemu/bswap.h" +#include "cpu.h" +#include "crypto/aes.h" +#include "crypto/aes-round.h" +#include "crypto/sm4.h" +#include "exec/memop.h" +#include "exec/exec-all.h" +#include "exec/helper-proto.h" +#include "internals.h" +#include "vector_internals.h" + +static uint64_t clmul64(uint64_t y, uint64_t x) +{ + uint64_t result = 0; + for (int j = 63; j >= 0; j--) { + if ((y >> j) & 1) { + result ^= (x << j); + } + } + return result; +} + +static uint64_t clmulh64(uint64_t y, uint64_t x) +{ + uint64_t result = 0; + for (int j = 63; j >= 1; j--) { + if ((y >> j) & 1) { + result ^= (x >> (64 - j)); + } + } + return result; +} + +RVVCALL(OPIVV2, vclmul_vv, OP_UUU_D, H8, H8, H8, clmul64) +GEN_VEXT_VV(vclmul_vv, 8) +RVVCALL(OPIVX2, vclmul_vx, OP_UUU_D, H8, H8, clmul64) +GEN_VEXT_VX(vclmul_vx, 8) +RVVCALL(OPIVV2, vclmulh_vv, OP_UUU_D, H8, H8, H8, clmulh64) +GEN_VEXT_VV(vclmulh_vv, 8) +RVVCALL(OPIVX2, vclmulh_vx, OP_UUU_D, H8, H8, clmulh64) +GEN_VEXT_VX(vclmulh_vx, 8) + +RVVCALL(OPIVV2, vror_vv_b, OP_UUU_B, H1, H1, H1, ror8) +RVVCALL(OPIVV2, vror_vv_h, OP_UUU_H, H2, H2, H2, ror16) +RVVCALL(OPIVV2, vror_vv_w, OP_UUU_W, H4, H4, H4, ror32) +RVVCALL(OPIVV2, vror_vv_d, OP_UUU_D, H8, H8, H8, ror64) +GEN_VEXT_VV(vror_vv_b, 1) +GEN_VEXT_VV(vror_vv_h, 2) +GEN_VEXT_VV(vror_vv_w, 4) +GEN_VEXT_VV(vror_vv_d, 8) + +RVVCALL(OPIVX2, vror_vx_b, OP_UUU_B, H1, H1, ror8) +RVVCALL(OPIVX2, vror_vx_h, OP_UUU_H, H2, H2, ror16) +RVVCALL(OPIVX2, vror_vx_w, OP_UUU_W, H4, H4, ror32) +RVVCALL(OPIVX2, vror_vx_d, OP_UUU_D, H8, H8, ror64) +GEN_VEXT_VX(vror_vx_b, 1) +GEN_VEXT_VX(vror_vx_h, 2) +GEN_VEXT_VX(vror_vx_w, 4) +GEN_VEXT_VX(vror_vx_d, 8) + +RVVCALL(OPIVV2, vrol_vv_b, OP_UUU_B, H1, H1, H1, rol8) +RVVCALL(OPIVV2, vrol_vv_h, OP_UUU_H, H2, H2, H2, rol16) +RVVCALL(OPIVV2, vrol_vv_w, OP_UUU_W, H4, H4, H4, rol32) +RVVCALL(OPIVV2, vrol_vv_d, OP_UUU_D, H8, H8, H8, rol64) +GEN_VEXT_VV(vrol_vv_b, 1) +GEN_VEXT_VV(vrol_vv_h, 2) +GEN_VEXT_VV(vrol_vv_w, 4) +GEN_VEXT_VV(vrol_vv_d, 8) + +RVVCALL(OPIVX2, vrol_vx_b, OP_UUU_B, H1, H1, rol8) +RVVCALL(OPIVX2, vrol_vx_h, OP_UUU_H, H2, H2, rol16) +RVVCALL(OPIVX2, vrol_vx_w, OP_UUU_W, H4, H4, rol32) +RVVCALL(OPIVX2, vrol_vx_d, OP_UUU_D, H8, H8, rol64) +GEN_VEXT_VX(vrol_vx_b, 1) +GEN_VEXT_VX(vrol_vx_h, 2) +GEN_VEXT_VX(vrol_vx_w, 4) +GEN_VEXT_VX(vrol_vx_d, 8) + +static uint64_t brev8(uint64_t val) +{ + val = ((val & 0x5555555555555555ull) << 1) | + ((val & 0xAAAAAAAAAAAAAAAAull) >> 1); + val = ((val & 0x3333333333333333ull) << 2) | + ((val & 0xCCCCCCCCCCCCCCCCull) >> 2); + val = ((val & 0x0F0F0F0F0F0F0F0Full) << 4) | + ((val & 0xF0F0F0F0F0F0F0F0ull) >> 4); + + return val; +} + +RVVCALL(OPIVV1, vbrev8_v_b, OP_UU_B, H1, H1, brev8) +RVVCALL(OPIVV1, vbrev8_v_h, OP_UU_H, H2, H2, brev8) +RVVCALL(OPIVV1, vbrev8_v_w, OP_UU_W, H4, H4, brev8) +RVVCALL(OPIVV1, vbrev8_v_d, OP_UU_D, H8, H8, brev8) +GEN_VEXT_V(vbrev8_v_b, 1) +GEN_VEXT_V(vbrev8_v_h, 2) +GEN_VEXT_V(vbrev8_v_w, 4) +GEN_VEXT_V(vbrev8_v_d, 8) + +#define DO_IDENTITY(a) (a) +RVVCALL(OPIVV1, vrev8_v_b, OP_UU_B, H1, H1, DO_IDENTITY) +RVVCALL(OPIVV1, vrev8_v_h, OP_UU_H, H2, H2, bswap16) +RVVCALL(OPIVV1, vrev8_v_w, OP_UU_W, H4, H4, bswap32) +RVVCALL(OPIVV1, vrev8_v_d, OP_UU_D, H8, H8, bswap64) +GEN_VEXT_V(vrev8_v_b, 1) +GEN_VEXT_V(vrev8_v_h, 2) +GEN_VEXT_V(vrev8_v_w, 4) +GEN_VEXT_V(vrev8_v_d, 8) + +#define DO_ANDN(a, b) ((a) & ~(b)) +RVVCALL(OPIVV2, vandn_vv_b, OP_UUU_B, H1, H1, H1, DO_ANDN) +RVVCALL(OPIVV2, vandn_vv_h, OP_UUU_H, H2, H2, H2, DO_ANDN) +RVVCALL(OPIVV2, vandn_vv_w, OP_UUU_W, H4, H4, H4, DO_ANDN) +RVVCALL(OPIVV2, vandn_vv_d, OP_UUU_D, H8, H8, H8, DO_ANDN) +GEN_VEXT_VV(vandn_vv_b, 1) +GEN_VEXT_VV(vandn_vv_h, 2) +GEN_VEXT_VV(vandn_vv_w, 4) +GEN_VEXT_VV(vandn_vv_d, 8) + +RVVCALL(OPIVX2, vandn_vx_b, OP_UUU_B, H1, H1, DO_ANDN) +RVVCALL(OPIVX2, vandn_vx_h, OP_UUU_H, H2, H2, DO_ANDN) +RVVCALL(OPIVX2, vandn_vx_w, OP_UUU_W, H4, H4, DO_ANDN) +RVVCALL(OPIVX2, vandn_vx_d, OP_UUU_D, H8, H8, DO_ANDN) +GEN_VEXT_VX(vandn_vx_b, 1) +GEN_VEXT_VX(vandn_vx_h, 2) +GEN_VEXT_VX(vandn_vx_w, 4) +GEN_VEXT_VX(vandn_vx_d, 8) + +RVVCALL(OPIVV1, vbrev_v_b, OP_UU_B, H1, H1, revbit8) +RVVCALL(OPIVV1, vbrev_v_h, OP_UU_H, H2, H2, revbit16) +RVVCALL(OPIVV1, vbrev_v_w, OP_UU_W, H4, H4, revbit32) +RVVCALL(OPIVV1, vbrev_v_d, OP_UU_D, H8, H8, revbit64) +GEN_VEXT_V(vbrev_v_b, 1) +GEN_VEXT_V(vbrev_v_h, 2) +GEN_VEXT_V(vbrev_v_w, 4) +GEN_VEXT_V(vbrev_v_d, 8) + +RVVCALL(OPIVV1, vclz_v_b, OP_UU_B, H1, H1, clz8) +RVVCALL(OPIVV1, vclz_v_h, OP_UU_H, H2, H2, clz16) +RVVCALL(OPIVV1, vclz_v_w, OP_UU_W, H4, H4, clz32) +RVVCALL(OPIVV1, vclz_v_d, OP_UU_D, H8, H8, clz64) +GEN_VEXT_V(vclz_v_b, 1) +GEN_VEXT_V(vclz_v_h, 2) +GEN_VEXT_V(vclz_v_w, 4) +GEN_VEXT_V(vclz_v_d, 8) + +RVVCALL(OPIVV1, vctz_v_b, OP_UU_B, H1, H1, ctz8) +RVVCALL(OPIVV1, vctz_v_h, OP_UU_H, H2, H2, ctz16) +RVVCALL(OPIVV1, vctz_v_w, OP_UU_W, H4, H4, ctz32) +RVVCALL(OPIVV1, vctz_v_d, OP_UU_D, H8, H8, ctz64) +GEN_VEXT_V(vctz_v_b, 1) +GEN_VEXT_V(vctz_v_h, 2) +GEN_VEXT_V(vctz_v_w, 4) +GEN_VEXT_V(vctz_v_d, 8) + +RVVCALL(OPIVV1, vcpop_v_b, OP_UU_B, H1, H1, ctpop8) +RVVCALL(OPIVV1, vcpop_v_h, OP_UU_H, H2, H2, ctpop16) +RVVCALL(OPIVV1, vcpop_v_w, OP_UU_W, H4, H4, ctpop32) +RVVCALL(OPIVV1, vcpop_v_d, OP_UU_D, H8, H8, ctpop64) +GEN_VEXT_V(vcpop_v_b, 1) +GEN_VEXT_V(vcpop_v_h, 2) +GEN_VEXT_V(vcpop_v_w, 4) +GEN_VEXT_V(vcpop_v_d, 8) + +#define DO_SLL(N, M) (N << (M & (sizeof(N) * 8 - 1))) +RVVCALL(OPIVV2, vwsll_vv_b, WOP_UUU_B, H2, H1, H1, DO_SLL) +RVVCALL(OPIVV2, vwsll_vv_h, WOP_UUU_H, H4, H2, H2, DO_SLL) +RVVCALL(OPIVV2, vwsll_vv_w, WOP_UUU_W, H8, H4, H4, DO_SLL) +GEN_VEXT_VV(vwsll_vv_b, 2) +GEN_VEXT_VV(vwsll_vv_h, 4) +GEN_VEXT_VV(vwsll_vv_w, 8) + +RVVCALL(OPIVX2, vwsll_vx_b, WOP_UUU_B, H2, H1, DO_SLL) +RVVCALL(OPIVX2, vwsll_vx_h, WOP_UUU_H, H4, H2, DO_SLL) +RVVCALL(OPIVX2, vwsll_vx_w, WOP_UUU_W, H8, H4, DO_SLL) +GEN_VEXT_VX(vwsll_vx_b, 2) +GEN_VEXT_VX(vwsll_vx_h, 4) +GEN_VEXT_VX(vwsll_vx_w, 8) + +void HELPER(egs_check)(uint32_t egs, CPURISCVState *env) +{ + uint32_t vl = env->vl; + uint32_t vstart = env->vstart; + + if (vl % egs != 0 || vstart % egs != 0) { + riscv_raise_exception(env, RISCV_EXCP_ILLEGAL_INST, GETPC()); + } +} + +static inline void xor_round_key(AESState *round_state, AESState *round_key) +{ + round_state->v = round_state->v ^ round_key->v; +} + +#define GEN_ZVKNED_HELPER_VV(NAME, ...) \ + void HELPER(NAME)(void *vd, void *vs2, CPURISCVState *env, \ + uint32_t desc) \ + { \ + uint32_t vl = env->vl; \ + uint32_t total_elems = vext_get_total_elems(env, desc, 4); \ + uint32_t vta = vext_vta(desc); \ + \ + for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { \ + AESState round_key; \ + round_key.d[0] = *((uint64_t *)vs2 + H8(i * 2 + 0)); \ + round_key.d[1] = *((uint64_t *)vs2 + H8(i * 2 + 1)); \ + AESState round_state; \ + round_state.d[0] = *((uint64_t *)vd + H8(i * 2 + 0)); \ + round_state.d[1] = *((uint64_t *)vd + H8(i * 2 + 1)); \ + __VA_ARGS__; \ + *((uint64_t *)vd + H8(i * 2 + 0)) = round_state.d[0]; \ + *((uint64_t *)vd + H8(i * 2 + 1)) = round_state.d[1]; \ + } \ + env->vstart = 0; \ + /* set tail elements to 1s */ \ + vext_set_elems_1s(vd, vta, vl * 4, total_elems * 4); \ + } + +#define GEN_ZVKNED_HELPER_VS(NAME, ...) \ + void HELPER(NAME)(void *vd, void *vs2, CPURISCVState *env, \ + uint32_t desc) \ + { \ + uint32_t vl = env->vl; \ + uint32_t total_elems = vext_get_total_elems(env, desc, 4); \ + uint32_t vta = vext_vta(desc); \ + \ + for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { \ + AESState round_key; \ + round_key.d[0] = *((uint64_t *)vs2 + H8(0)); \ + round_key.d[1] = *((uint64_t *)vs2 + H8(1)); \ + AESState round_state; \ + round_state.d[0] = *((uint64_t *)vd + H8(i * 2 + 0)); \ + round_state.d[1] = *((uint64_t *)vd + H8(i * 2 + 1)); \ + __VA_ARGS__; \ + *((uint64_t *)vd + H8(i * 2 + 0)) = round_state.d[0]; \ + *((uint64_t *)vd + H8(i * 2 + 1)) = round_state.d[1]; \ + } \ + env->vstart = 0; \ + /* set tail elements to 1s */ \ + vext_set_elems_1s(vd, vta, vl * 4, total_elems * 4); \ + } + +GEN_ZVKNED_HELPER_VV(vaesef_vv, aesenc_SB_SR_AK(&round_state, + &round_state, + &round_key, + false);) +GEN_ZVKNED_HELPER_VS(vaesef_vs, aesenc_SB_SR_AK(&round_state, + &round_state, + &round_key, + false);) +GEN_ZVKNED_HELPER_VV(vaesdf_vv, aesdec_ISB_ISR_AK(&round_state, + &round_state, + &round_key, + false);) +GEN_ZVKNED_HELPER_VS(vaesdf_vs, aesdec_ISB_ISR_AK(&round_state, + &round_state, + &round_key, + false);) +GEN_ZVKNED_HELPER_VV(vaesem_vv, aesenc_SB_SR_MC_AK(&round_state, + &round_state, + &round_key, + false);) +GEN_ZVKNED_HELPER_VS(vaesem_vs, aesenc_SB_SR_MC_AK(&round_state, + &round_state, + &round_key, + false);) +GEN_ZVKNED_HELPER_VV(vaesdm_vv, aesdec_ISB_ISR_AK_IMC(&round_state, + &round_state, + &round_key, + false);) +GEN_ZVKNED_HELPER_VS(vaesdm_vs, aesdec_ISB_ISR_AK_IMC(&round_state, + &round_state, + &round_key, + false);) +GEN_ZVKNED_HELPER_VS(vaesz_vs, xor_round_key(&round_state, &round_key);) + +void HELPER(vaeskf1_vi)(void *vd_vptr, void *vs2_vptr, uint32_t uimm, + CPURISCVState *env, uint32_t desc) +{ + uint32_t *vd = vd_vptr; + uint32_t *vs2 = vs2_vptr; + uint32_t vl = env->vl; + uint32_t total_elems = vext_get_total_elems(env, desc, 4); + uint32_t vta = vext_vta(desc); + + uimm &= 0b1111; + if (uimm > 10 || uimm == 0) { + uimm ^= 0b1000; + } + + for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { + uint32_t rk[8], tmp; + static const uint32_t rcon[] = { + 0x00000001, 0x00000002, 0x00000004, 0x00000008, 0x00000010, + 0x00000020, 0x00000040, 0x00000080, 0x0000001B, 0x00000036, + }; + + rk[0] = vs2[i * 4 + H4(0)]; + rk[1] = vs2[i * 4 + H4(1)]; + rk[2] = vs2[i * 4 + H4(2)]; + rk[3] = vs2[i * 4 + H4(3)]; + tmp = ror32(rk[3], 8); + + rk[4] = rk[0] ^ (((uint32_t)AES_sbox[(tmp >> 24) & 0xff] << 24) | + ((uint32_t)AES_sbox[(tmp >> 16) & 0xff] << 16) | + ((uint32_t)AES_sbox[(tmp >> 8) & 0xff] << 8) | + ((uint32_t)AES_sbox[(tmp >> 0) & 0xff] << 0)) + ^ rcon[uimm - 1]; + rk[5] = rk[1] ^ rk[4]; + rk[6] = rk[2] ^ rk[5]; + rk[7] = rk[3] ^ rk[6]; + + vd[i * 4 + H4(0)] = rk[4]; + vd[i * 4 + H4(1)] = rk[5]; + vd[i * 4 + H4(2)] = rk[6]; + vd[i * 4 + H4(3)] = rk[7]; + } + env->vstart = 0; + /* set tail elements to 1s */ + vext_set_elems_1s(vd, vta, vl * 4, total_elems * 4); +} + +void HELPER(vaeskf2_vi)(void *vd_vptr, void *vs2_vptr, uint32_t uimm, + CPURISCVState *env, uint32_t desc) +{ + uint32_t *vd = vd_vptr; + uint32_t *vs2 = vs2_vptr; + uint32_t vl = env->vl; + uint32_t total_elems = vext_get_total_elems(env, desc, 4); + uint32_t vta = vext_vta(desc); + + uimm &= 0b1111; + if (uimm > 14 || uimm < 2) { + uimm ^= 0b1000; + } + + for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { + uint32_t rk[12], tmp; + static const uint32_t rcon[] = { + 0x00000001, 0x00000002, 0x00000004, 0x00000008, 0x00000010, + 0x00000020, 0x00000040, 0x00000080, 0x0000001B, 0x00000036, + }; + + rk[0] = vd[i * 4 + H4(0)]; + rk[1] = vd[i * 4 + H4(1)]; + rk[2] = vd[i * 4 + H4(2)]; + rk[3] = vd[i * 4 + H4(3)]; + rk[4] = vs2[i * 4 + H4(0)]; + rk[5] = vs2[i * 4 + H4(1)]; + rk[6] = vs2[i * 4 + H4(2)]; + rk[7] = vs2[i * 4 + H4(3)]; + + if (uimm % 2 == 0) { + tmp = ror32(rk[7], 8); + rk[8] = rk[0] ^ (((uint32_t)AES_sbox[(tmp >> 24) & 0xff] << 24) | + ((uint32_t)AES_sbox[(tmp >> 16) & 0xff] << 16) | + ((uint32_t)AES_sbox[(tmp >> 8) & 0xff] << 8) | + ((uint32_t)AES_sbox[(tmp >> 0) & 0xff] << 0)) + ^ rcon[(uimm - 1) / 2]; + } else { + rk[8] = rk[0] ^ (((uint32_t)AES_sbox[(rk[7] >> 24) & 0xff] << 24) | + ((uint32_t)AES_sbox[(rk[7] >> 16) & 0xff] << 16) | + ((uint32_t)AES_sbox[(rk[7] >> 8) & 0xff] << 8) | + ((uint32_t)AES_sbox[(rk[7] >> 0) & 0xff] << 0)); + } + rk[9] = rk[1] ^ rk[8]; + rk[10] = rk[2] ^ rk[9]; + rk[11] = rk[3] ^ rk[10]; + + vd[i * 4 + H4(0)] = rk[8]; + vd[i * 4 + H4(1)] = rk[9]; + vd[i * 4 + H4(2)] = rk[10]; + vd[i * 4 + H4(3)] = rk[11]; + } + env->vstart = 0; + /* set tail elements to 1s */ + vext_set_elems_1s(vd, vta, vl * 4, total_elems * 4); +} + +static inline uint32_t sig0_sha256(uint32_t x) +{ + return ror32(x, 7) ^ ror32(x, 18) ^ (x >> 3); +} + +static inline uint32_t sig1_sha256(uint32_t x) +{ + return ror32(x, 17) ^ ror32(x, 19) ^ (x >> 10); +} + +static inline uint64_t sig0_sha512(uint64_t x) +{ + return ror64(x, 1) ^ ror64(x, 8) ^ (x >> 7); +} + +static inline uint64_t sig1_sha512(uint64_t x) +{ + return ror64(x, 19) ^ ror64(x, 61) ^ (x >> 6); +} + +static inline void vsha2ms_e32(uint32_t *vd, uint32_t *vs1, uint32_t *vs2) +{ + uint32_t res[4]; + res[0] = sig1_sha256(vs1[H4(2)]) + vs2[H4(1)] + sig0_sha256(vd[H4(1)]) + + vd[H4(0)]; + res[1] = sig1_sha256(vs1[H4(3)]) + vs2[H4(2)] + sig0_sha256(vd[H4(2)]) + + vd[H4(1)]; + res[2] = + sig1_sha256(res[0]) + vs2[H4(3)] + sig0_sha256(vd[H4(3)]) + vd[H4(2)]; + res[3] = + sig1_sha256(res[1]) + vs1[H4(0)] + sig0_sha256(vs2[H4(0)]) + vd[H4(3)]; + vd[H4(3)] = res[3]; + vd[H4(2)] = res[2]; + vd[H4(1)] = res[1]; + vd[H4(0)] = res[0]; +} + +static inline void vsha2ms_e64(uint64_t *vd, uint64_t *vs1, uint64_t *vs2) +{ + uint64_t res[4]; + res[0] = sig1_sha512(vs1[2]) + vs2[1] + sig0_sha512(vd[1]) + vd[0]; + res[1] = sig1_sha512(vs1[3]) + vs2[2] + sig0_sha512(vd[2]) + vd[1]; + res[2] = sig1_sha512(res[0]) + vs2[3] + sig0_sha512(vd[3]) + vd[2]; + res[3] = sig1_sha512(res[1]) + vs1[0] + sig0_sha512(vs2[0]) + vd[3]; + vd[3] = res[3]; + vd[2] = res[2]; + vd[1] = res[1]; + vd[0] = res[0]; +} + +void HELPER(vsha2ms_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env, + uint32_t desc) +{ + uint32_t sew = FIELD_EX64(env->vtype, VTYPE, VSEW); + uint32_t esz = sew == MO_32 ? 4 : 8; + uint32_t total_elems; + uint32_t vta = vext_vta(desc); + + for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { + if (sew == MO_32) { + vsha2ms_e32(((uint32_t *)vd) + i * 4, ((uint32_t *)vs1) + i * 4, + ((uint32_t *)vs2) + i * 4); + } else { + /* If not 32 then SEW should be 64 */ + vsha2ms_e64(((uint64_t *)vd) + i * 4, ((uint64_t *)vs1) + i * 4, + ((uint64_t *)vs2) + i * 4); + } + } + /* set tail elements to 1s */ + total_elems = vext_get_total_elems(env, desc, esz); + vext_set_elems_1s(vd, vta, env->vl * esz, total_elems * esz); + env->vstart = 0; +} + +static inline uint64_t sum0_64(uint64_t x) +{ + return ror64(x, 28) ^ ror64(x, 34) ^ ror64(x, 39); +} + +static inline uint32_t sum0_32(uint32_t x) +{ + return ror32(x, 2) ^ ror32(x, 13) ^ ror32(x, 22); +} + +static inline uint64_t sum1_64(uint64_t x) +{ + return ror64(x, 14) ^ ror64(x, 18) ^ ror64(x, 41); +} + +static inline uint32_t sum1_32(uint32_t x) +{ + return ror32(x, 6) ^ ror32(x, 11) ^ ror32(x, 25); +} + +#define ch(x, y, z) ((x & y) ^ ((~x) & z)) + +#define maj(x, y, z) ((x & y) ^ (x & z) ^ (y & z)) + +static void vsha2c_64(uint64_t *vs2, uint64_t *vd, uint64_t *vs1) +{ + uint64_t a = vs2[3], b = vs2[2], e = vs2[1], f = vs2[0]; + uint64_t c = vd[3], d = vd[2], g = vd[1], h = vd[0]; + uint64_t W0 = vs1[0], W1 = vs1[1]; + uint64_t T1 = h + sum1_64(e) + ch(e, f, g) + W0; + uint64_t T2 = sum0_64(a) + maj(a, b, c); + + h = g; + g = f; + f = e; + e = d + T1; + d = c; + c = b; + b = a; + a = T1 + T2; + + T1 = h + sum1_64(e) + ch(e, f, g) + W1; + T2 = sum0_64(a) + maj(a, b, c); + h = g; + g = f; + f = e; + e = d + T1; + d = c; + c = b; + b = a; + a = T1 + T2; + + vd[0] = f; + vd[1] = e; + vd[2] = b; + vd[3] = a; +} + +static void vsha2c_32(uint32_t *vs2, uint32_t *vd, uint32_t *vs1) +{ + uint32_t a = vs2[H4(3)], b = vs2[H4(2)], e = vs2[H4(1)], f = vs2[H4(0)]; + uint32_t c = vd[H4(3)], d = vd[H4(2)], g = vd[H4(1)], h = vd[H4(0)]; + uint32_t W0 = vs1[H4(0)], W1 = vs1[H4(1)]; + uint32_t T1 = h + sum1_32(e) + ch(e, f, g) + W0; + uint32_t T2 = sum0_32(a) + maj(a, b, c); + + h = g; + g = f; + f = e; + e = d + T1; + d = c; + c = b; + b = a; + a = T1 + T2; + + T1 = h + sum1_32(e) + ch(e, f, g) + W1; + T2 = sum0_32(a) + maj(a, b, c); + h = g; + g = f; + f = e; + e = d + T1; + d = c; + c = b; + b = a; + a = T1 + T2; + + vd[H4(0)] = f; + vd[H4(1)] = e; + vd[H4(2)] = b; + vd[H4(3)] = a; +} + +void HELPER(vsha2ch32_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env, + uint32_t desc) +{ + const uint32_t esz = 4; + uint32_t total_elems; + uint32_t vta = vext_vta(desc); + + for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { + vsha2c_32(((uint32_t *)vs2) + 4 * i, ((uint32_t *)vd) + 4 * i, + ((uint32_t *)vs1) + 4 * i + 2); + } + + /* set tail elements to 1s */ + total_elems = vext_get_total_elems(env, desc, esz); + vext_set_elems_1s(vd, vta, env->vl * esz, total_elems * esz); + env->vstart = 0; +} + +void HELPER(vsha2ch64_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env, + uint32_t desc) +{ + const uint32_t esz = 8; + uint32_t total_elems; + uint32_t vta = vext_vta(desc); + + for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { + vsha2c_64(((uint64_t *)vs2) + 4 * i, ((uint64_t *)vd) + 4 * i, + ((uint64_t *)vs1) + 4 * i + 2); + } + + /* set tail elements to 1s */ + total_elems = vext_get_total_elems(env, desc, esz); + vext_set_elems_1s(vd, vta, env->vl * esz, total_elems * esz); + env->vstart = 0; +} + +void HELPER(vsha2cl32_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env, + uint32_t desc) +{ + const uint32_t esz = 4; + uint32_t total_elems; + uint32_t vta = vext_vta(desc); + + for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { + vsha2c_32(((uint32_t *)vs2) + 4 * i, ((uint32_t *)vd) + 4 * i, + (((uint32_t *)vs1) + 4 * i)); + } + + /* set tail elements to 1s */ + total_elems = vext_get_total_elems(env, desc, esz); + vext_set_elems_1s(vd, vta, env->vl * esz, total_elems * esz); + env->vstart = 0; +} + +void HELPER(vsha2cl64_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env, + uint32_t desc) +{ + uint32_t esz = 8; + uint32_t total_elems; + uint32_t vta = vext_vta(desc); + + for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { + vsha2c_64(((uint64_t *)vs2) + 4 * i, ((uint64_t *)vd) + 4 * i, + (((uint64_t *)vs1) + 4 * i)); + } + + /* set tail elements to 1s */ + total_elems = vext_get_total_elems(env, desc, esz); + vext_set_elems_1s(vd, vta, env->vl * esz, total_elems * esz); + env->vstart = 0; +} + +static inline uint32_t p1(uint32_t x) +{ + return x ^ rol32(x, 15) ^ rol32(x, 23); +} + +static inline uint32_t zvksh_w(uint32_t m16, uint32_t m9, uint32_t m3, + uint32_t m13, uint32_t m6) +{ + return p1(m16 ^ m9 ^ rol32(m3, 15)) ^ rol32(m13, 7) ^ m6; +} + +void HELPER(vsm3me_vv)(void *vd_vptr, void *vs1_vptr, void *vs2_vptr, + CPURISCVState *env, uint32_t desc) +{ + uint32_t esz = memop_size(FIELD_EX64(env->vtype, VTYPE, VSEW)); + uint32_t total_elems = vext_get_total_elems(env, desc, esz); + uint32_t vta = vext_vta(desc); + uint32_t *vd = vd_vptr; + uint32_t *vs1 = vs1_vptr; + uint32_t *vs2 = vs2_vptr; + + for (int i = env->vstart / 8; i < env->vl / 8; i++) { + uint32_t w[24]; + for (int j = 0; j < 8; j++) { + w[j] = bswap32(vs1[H4((i * 8) + j)]); + w[j + 8] = bswap32(vs2[H4((i * 8) + j)]); + } + for (int j = 0; j < 8; j++) { + w[j + 16] = + zvksh_w(w[j], w[j + 7], w[j + 13], w[j + 3], w[j + 10]); + } + for (int j = 0; j < 8; j++) { + vd[(i * 8) + j] = bswap32(w[H4(j + 16)]); + } + } + vext_set_elems_1s(vd_vptr, vta, env->vl * esz, total_elems * esz); + env->vstart = 0; +} + +static inline uint32_t ff1(uint32_t x, uint32_t y, uint32_t z) +{ + return x ^ y ^ z; +} + +static inline uint32_t ff2(uint32_t x, uint32_t y, uint32_t z) +{ + return (x & y) | (x & z) | (y & z); +} + +static inline uint32_t ff_j(uint32_t x, uint32_t y, uint32_t z, uint32_t j) +{ + return (j <= 15) ? ff1(x, y, z) : ff2(x, y, z); +} + +static inline uint32_t gg1(uint32_t x, uint32_t y, uint32_t z) +{ + return x ^ y ^ z; +} + +static inline uint32_t gg2(uint32_t x, uint32_t y, uint32_t z) +{ + return (x & y) | (~x & z); +} + +static inline uint32_t gg_j(uint32_t x, uint32_t y, uint32_t z, uint32_t j) +{ + return (j <= 15) ? gg1(x, y, z) : gg2(x, y, z); +} + +static inline uint32_t t_j(uint32_t j) +{ + return (j <= 15) ? 0x79cc4519 : 0x7a879d8a; +} + +static inline uint32_t p_0(uint32_t x) +{ + return x ^ rol32(x, 9) ^ rol32(x, 17); +} + +static void sm3c(uint32_t *vd, uint32_t *vs1, uint32_t *vs2, uint32_t uimm) +{ + uint32_t x0, x1; + uint32_t j; + uint32_t ss1, ss2, tt1, tt2; + x0 = vs2[0] ^ vs2[4]; + x1 = vs2[1] ^ vs2[5]; + j = 2 * uimm; + ss1 = rol32(rol32(vs1[0], 12) + vs1[4] + rol32(t_j(j), j % 32), 7); + ss2 = ss1 ^ rol32(vs1[0], 12); + tt1 = ff_j(vs1[0], vs1[1], vs1[2], j) + vs1[3] + ss2 + x0; + tt2 = gg_j(vs1[4], vs1[5], vs1[6], j) + vs1[7] + ss1 + vs2[0]; + vs1[3] = vs1[2]; + vd[3] = rol32(vs1[1], 9); + vs1[1] = vs1[0]; + vd[1] = tt1; + vs1[7] = vs1[6]; + vd[7] = rol32(vs1[5], 19); + vs1[5] = vs1[4]; + vd[5] = p_0(tt2); + j = 2 * uimm + 1; + ss1 = rol32(rol32(vd[1], 12) + vd[5] + rol32(t_j(j), j % 32), 7); + ss2 = ss1 ^ rol32(vd[1], 12); + tt1 = ff_j(vd[1], vs1[1], vd[3], j) + vs1[3] + ss2 + x1; + tt2 = gg_j(vd[5], vs1[5], vd[7], j) + vs1[7] + ss1 + vs2[1]; + vd[2] = rol32(vs1[1], 9); + vd[0] = tt1; + vd[6] = rol32(vs1[5], 19); + vd[4] = p_0(tt2); +} + +void HELPER(vsm3c_vi)(void *vd_vptr, void *vs2_vptr, uint32_t uimm, + CPURISCVState *env, uint32_t desc) +{ + uint32_t esz = memop_size(FIELD_EX64(env->vtype, VTYPE, VSEW)); + uint32_t total_elems = vext_get_total_elems(env, desc, esz); + uint32_t vta = vext_vta(desc); + uint32_t *vd = vd_vptr; + uint32_t *vs2 = vs2_vptr; + uint32_t v1[8], v2[8], v3[8]; + + for (int i = env->vstart / 8; i < env->vl / 8; i++) { + for (int k = 0; k < 8; k++) { + v2[k] = bswap32(vd[H4(i * 8 + k)]); + v3[k] = bswap32(vs2[H4(i * 8 + k)]); + } + sm3c(v1, v2, v3, uimm); + for (int k = 0; k < 8; k++) { + vd[i * 8 + k] = bswap32(v1[H4(k)]); + } + } + vext_set_elems_1s(vd_vptr, vta, env->vl * esz, total_elems * esz); + env->vstart = 0; +} + +void HELPER(vghsh_vv)(void *vd_vptr, void *vs1_vptr, void *vs2_vptr, + CPURISCVState *env, uint32_t desc) +{ + uint64_t *vd = vd_vptr; + uint64_t *vs1 = vs1_vptr; + uint64_t *vs2 = vs2_vptr; + uint32_t vta = vext_vta(desc); + uint32_t total_elems = vext_get_total_elems(env, desc, 4); + + for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { + uint64_t Y[2] = {vd[i * 2 + 0], vd[i * 2 + 1]}; + uint64_t H[2] = {brev8(vs2[i * 2 + 0]), brev8(vs2[i * 2 + 1])}; + uint64_t X[2] = {vs1[i * 2 + 0], vs1[i * 2 + 1]}; + uint64_t Z[2] = {0, 0}; + + uint64_t S[2] = {brev8(Y[0] ^ X[0]), brev8(Y[1] ^ X[1])}; + + for (int j = 0; j < 128; j++) { + if ((S[j / 64] >> (j % 64)) & 1) { + Z[0] ^= H[0]; + Z[1] ^= H[1]; + } + bool reduce = ((H[1] >> 63) & 1); + H[1] = H[1] << 1 | H[0] >> 63; + H[0] = H[0] << 1; + if (reduce) { + H[0] ^= 0x87; + } + } + + vd[i * 2 + 0] = brev8(Z[0]); + vd[i * 2 + 1] = brev8(Z[1]); + } + /* set tail elements to 1s */ + vext_set_elems_1s(vd, vta, env->vl * 4, total_elems * 4); + env->vstart = 0; +} + +void HELPER(vgmul_vv)(void *vd_vptr, void *vs2_vptr, CPURISCVState *env, + uint32_t desc) +{ + uint64_t *vd = vd_vptr; + uint64_t *vs2 = vs2_vptr; + uint32_t vta = vext_vta(desc); + uint32_t total_elems = vext_get_total_elems(env, desc, 4); + + for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { + uint64_t Y[2] = {brev8(vd[i * 2 + 0]), brev8(vd[i * 2 + 1])}; + uint64_t H[2] = {brev8(vs2[i * 2 + 0]), brev8(vs2[i * 2 + 1])}; + uint64_t Z[2] = {0, 0}; + + for (int j = 0; j < 128; j++) { + if ((Y[j / 64] >> (j % 64)) & 1) { + Z[0] ^= H[0]; + Z[1] ^= H[1]; + } + bool reduce = ((H[1] >> 63) & 1); + H[1] = H[1] << 1 | H[0] >> 63; + H[0] = H[0] << 1; + if (reduce) { + H[0] ^= 0x87; + } + } + + vd[i * 2 + 0] = brev8(Z[0]); + vd[i * 2 + 1] = brev8(Z[1]); + } + /* set tail elements to 1s */ + vext_set_elems_1s(vd, vta, env->vl * 4, total_elems * 4); + env->vstart = 0; +} + +void HELPER(vsm4k_vi)(void *vd, void *vs2, uint32_t uimm5, CPURISCVState *env, + uint32_t desc) +{ + const uint32_t egs = 4; + uint32_t rnd = uimm5 & 0x7; + uint32_t group_start = env->vstart / egs; + uint32_t group_end = env->vl / egs; + uint32_t esz = sizeof(uint32_t); + uint32_t total_elems = vext_get_total_elems(env, desc, esz); + + for (uint32_t i = group_start; i < group_end; ++i) { + uint32_t vstart = i * egs; + uint32_t vend = (i + 1) * egs; + uint32_t rk[4] = {0}; + uint32_t tmp[8] = {0}; + + for (uint32_t j = vstart; j < vend; ++j) { + rk[j - vstart] = *((uint32_t *)vs2 + H4(j)); + } + + for (uint32_t j = 0; j < egs; ++j) { + tmp[j] = rk[j]; + } + + for (uint32_t j = 0; j < egs; ++j) { + uint32_t b, s; + b = tmp[j + 1] ^ tmp[j + 2] ^ tmp[j + 3] ^ sm4_ck[rnd * 4 + j]; + + s = sm4_subword(b); + + tmp[j + 4] = tmp[j] ^ (s ^ rol32(s, 13) ^ rol32(s, 23)); + } + + for (uint32_t j = vstart; j < vend; ++j) { + *((uint32_t *)vd + H4(j)) = tmp[egs + (j - vstart)]; + } + } + + env->vstart = 0; + /* set tail elements to 1s */ + vext_set_elems_1s(vd, vext_vta(desc), env->vl * esz, total_elems * esz); +} + +static void do_sm4_round(uint32_t *rk, uint32_t *buf) +{ + const uint32_t egs = 4; + uint32_t s, b; + + for (uint32_t j = egs; j < egs * 2; ++j) { + b = buf[j - 3] ^ buf[j - 2] ^ buf[j - 1] ^ rk[j - 4]; + + s = sm4_subword(b); + + buf[j] = buf[j - 4] ^ (s ^ rol32(s, 2) ^ rol32(s, 10) ^ rol32(s, 18) ^ + rol32(s, 24)); + } +} + +void HELPER(vsm4r_vv)(void *vd, void *vs2, CPURISCVState *env, uint32_t desc) +{ + const uint32_t egs = 4; + uint32_t group_start = env->vstart / egs; + uint32_t group_end = env->vl / egs; + uint32_t esz = sizeof(uint32_t); + uint32_t total_elems = vext_get_total_elems(env, desc, esz); + + for (uint32_t i = group_start; i < group_end; ++i) { + uint32_t vstart = i * egs; + uint32_t vend = (i + 1) * egs; + uint32_t rk[4] = {0}; + uint32_t tmp[8] = {0}; + + for (uint32_t j = vstart; j < vend; ++j) { + rk[j - vstart] = *((uint32_t *)vs2 + H4(j)); + } + + for (uint32_t j = vstart; j < vend; ++j) { + tmp[j - vstart] = *((uint32_t *)vd + H4(j)); + } + + do_sm4_round(rk, tmp); + + for (uint32_t j = vstart; j < vend; ++j) { + *((uint32_t *)vd + H4(j)) = tmp[egs + (j - vstart)]; + } + } + + env->vstart = 0; + /* set tail elements to 1s */ + vext_set_elems_1s(vd, vext_vta(desc), env->vl * esz, total_elems * esz); +} + +void HELPER(vsm4r_vs)(void *vd, void *vs2, CPURISCVState *env, uint32_t desc) +{ + const uint32_t egs = 4; + uint32_t group_start = env->vstart / egs; + uint32_t group_end = env->vl / egs; + uint32_t esz = sizeof(uint32_t); + uint32_t total_elems = vext_get_total_elems(env, desc, esz); + + for (uint32_t i = group_start; i < group_end; ++i) { + uint32_t vstart = i * egs; + uint32_t vend = (i + 1) * egs; + uint32_t rk[4] = {0}; + uint32_t tmp[8] = {0}; + + for (uint32_t j = 0; j < egs; ++j) { + rk[j] = *((uint32_t *)vs2 + H4(j)); + } + + for (uint32_t j = vstart; j < vend; ++j) { + tmp[j - vstart] = *((uint32_t *)vd + H4(j)); + } + + do_sm4_round(rk, tmp); + + for (uint32_t j = vstart; j < vend; ++j) { + *((uint32_t *)vd + H4(j)) = tmp[egs + (j - vstart)]; + } + } + + env->vstart = 0; + /* set tail elements to 1s */ + vext_set_elems_1s(vd, vext_vta(desc), env->vl * esz, total_elems * esz); +} diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index bc9e151aa9..3fb05cc3d6 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -27,6 +27,7 @@ #include "fpu/softfloat.h" #include "tcg/tcg-gvec-desc.h" #include "internals.h" +#include "vector_internals.h" #include <math.h> target_ulong HELPER(vsetvl)(CPURISCVState *env, target_ulong s1, @@ -74,68 +75,6 @@ target_ulong HELPER(vsetvl)(CPURISCVState *env, target_ulong s1, } /* - * Note that vector data is stored in host-endian 64-bit chunks, - * so addressing units smaller than that needs a host-endian fixup. - */ -#if HOST_BIG_ENDIAN -#define H1(x) ((x) ^ 7) -#define H1_2(x) ((x) ^ 6) -#define H1_4(x) ((x) ^ 4) -#define H2(x) ((x) ^ 3) -#define H4(x) ((x) ^ 1) -#define H8(x) ((x)) -#else -#define H1(x) (x) -#define H1_2(x) (x) -#define H1_4(x) (x) -#define H2(x) (x) -#define H4(x) (x) -#define H8(x) (x) -#endif - -static inline uint32_t vext_nf(uint32_t desc) -{ - return FIELD_EX32(simd_data(desc), VDATA, NF); -} - -static inline uint32_t vext_vm(uint32_t desc) -{ - return FIELD_EX32(simd_data(desc), VDATA, VM); -} - -/* - * Encode LMUL to lmul as following: - * LMUL vlmul lmul - * 1 000 0 - * 2 001 1 - * 4 010 2 - * 8 011 3 - * - 100 - - * 1/8 101 -3 - * 1/4 110 -2 - * 1/2 111 -1 - */ -static inline int32_t vext_lmul(uint32_t desc) -{ - return sextract32(FIELD_EX32(simd_data(desc), VDATA, LMUL), 0, 3); -} - -static inline uint32_t vext_vta(uint32_t desc) -{ - return FIELD_EX32(simd_data(desc), VDATA, VTA); -} - -static inline uint32_t vext_vma(uint32_t desc) -{ - return FIELD_EX32(simd_data(desc), VDATA, VMA); -} - -static inline uint32_t vext_vta_all_1s(uint32_t desc) -{ - return FIELD_EX32(simd_data(desc), VDATA, VTA_ALL_1S); -} - -/* * Get the maximum number of elements can be operated. * * log2_esz: log2 of element size in bytes. @@ -153,21 +92,6 @@ static inline uint32_t vext_max_elems(uint32_t desc, uint32_t log2_esz) return scale < 0 ? vlenb >> -scale : vlenb << scale; } -/* - * Get number of total elements, including prestart, body and tail elements. - * Note that when LMUL < 1, the tail includes the elements past VLMAX that - * are held in the same vector register. - */ -static inline uint32_t vext_get_total_elems(CPURISCVState *env, uint32_t desc, - uint32_t esz) -{ - uint32_t vlenb = simd_maxsz(desc); - uint32_t sew = 1 << FIELD_EX64(env->vtype, VTYPE, VSEW); - int8_t emul = ctzl(esz) - ctzl(sew) + vext_lmul(desc) < 0 ? 0 : - ctzl(esz) - ctzl(sew) + vext_lmul(desc); - return (vlenb << emul) / esz; -} - static inline target_ulong adjust_addr(CPURISCVState *env, target_ulong addr) { return (addr & ~env->cur_pmmask) | env->cur_pmbase; @@ -200,20 +124,6 @@ static void probe_pages(CPURISCVState *env, target_ulong addr, } } -/* set agnostic elements to 1s */ -static void vext_set_elems_1s(void *base, uint32_t is_agnostic, uint32_t cnt, - uint32_t tot) -{ - if (is_agnostic == 0) { - /* policy undisturbed */ - return; - } - if (tot - cnt == 0) { - return; - } - memset(base + cnt, -1, tot - cnt); -} - static inline void vext_set_elem_mask(void *v0, int index, uint8_t value) { @@ -223,18 +133,6 @@ static inline void vext_set_elem_mask(void *v0, int index, ((uint64_t *)v0)[idx] = deposit64(old, pos, 1, value); } -/* - * Earlier designs (pre-0.9) had a varying number of bits - * per mask value (MLEN). In the 0.9 design, MLEN=1. - * (Section 4.5) - */ -static inline int vext_elem_mask(void *v0, int index) -{ - int idx = index / 64; - int pos = index % 64; - return (((uint64_t *)v0)[idx] >> pos) & 1; -} - /* elements operations for load and store */ typedef void vext_ldst_elem_fn(CPURISCVState *env, abi_ptr addr, uint32_t idx, void *vd, uintptr_t retaddr); @@ -584,7 +482,7 @@ vext_ldff(void *vd, void *v0, target_ulong base, cpu_mmu_index(env, false)); if (host) { #ifdef CONFIG_USER_ONLY - if (page_check_range(addr, offset, PAGE_READ)) { + if (!page_check_range(addr, offset, PAGE_READ)) { vl = i; goto ProbeSuccess; } @@ -729,25 +627,15 @@ GEN_VEXT_ST_WHOLE(vs8r_v, int8_t, ste_b) * Vector Integer Arithmetic Instructions */ -/* expand macro args before macro */ -#define RVVCALL(macro, ...) macro(__VA_ARGS__) - /* (TD, T1, T2, TX1, TX2) */ #define OP_SSS_B int8_t, int8_t, int8_t, int8_t, int8_t #define OP_SSS_H int16_t, int16_t, int16_t, int16_t, int16_t #define OP_SSS_W int32_t, int32_t, int32_t, int32_t, int32_t #define OP_SSS_D int64_t, int64_t, int64_t, int64_t, int64_t -#define OP_UUU_B uint8_t, uint8_t, uint8_t, uint8_t, uint8_t -#define OP_UUU_H uint16_t, uint16_t, uint16_t, uint16_t, uint16_t -#define OP_UUU_W uint32_t, uint32_t, uint32_t, uint32_t, uint32_t -#define OP_UUU_D uint64_t, uint64_t, uint64_t, uint64_t, uint64_t #define OP_SUS_B int8_t, uint8_t, int8_t, uint8_t, int8_t #define OP_SUS_H int16_t, uint16_t, int16_t, uint16_t, int16_t #define OP_SUS_W int32_t, uint32_t, int32_t, uint32_t, int32_t #define OP_SUS_D int64_t, uint64_t, int64_t, uint64_t, int64_t -#define WOP_UUU_B uint16_t, uint8_t, uint8_t, uint16_t, uint16_t -#define WOP_UUU_H uint32_t, uint16_t, uint16_t, uint32_t, uint32_t -#define WOP_UUU_W uint64_t, uint32_t, uint32_t, uint64_t, uint64_t #define WOP_SSS_B int16_t, int8_t, int8_t, int16_t, int16_t #define WOP_SSS_H int32_t, int16_t, int16_t, int32_t, int32_t #define WOP_SSS_W int64_t, int32_t, int32_t, int64_t, int64_t @@ -764,16 +652,6 @@ GEN_VEXT_ST_WHOLE(vs8r_v, int8_t, ste_b) #define NOP_UUU_H uint16_t, uint16_t, uint32_t, uint16_t, uint32_t #define NOP_UUU_W uint32_t, uint32_t, uint64_t, uint32_t, uint64_t -/* operation of two vector elements */ -typedef void opivv2_fn(void *vd, void *vs1, void *vs2, int i); - -#define OPIVV2(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP) \ -static void do_##NAME(void *vd, void *vs1, void *vs2, int i) \ -{ \ - TX1 s1 = *((T1 *)vs1 + HS1(i)); \ - TX2 s2 = *((T2 *)vs2 + HS2(i)); \ - *((TD *)vd + HD(i)) = OP(s2, s1); \ -} #define DO_SUB(N, M) (N - M) #define DO_RSUB(N, M) (M - N) @@ -786,40 +664,6 @@ RVVCALL(OPIVV2, vsub_vv_h, OP_SSS_H, H2, H2, H2, DO_SUB) RVVCALL(OPIVV2, vsub_vv_w, OP_SSS_W, H4, H4, H4, DO_SUB) RVVCALL(OPIVV2, vsub_vv_d, OP_SSS_D, H8, H8, H8, DO_SUB) -static void do_vext_vv(void *vd, void *v0, void *vs1, void *vs2, - CPURISCVState *env, uint32_t desc, - opivv2_fn *fn, uint32_t esz) -{ - uint32_t vm = vext_vm(desc); - uint32_t vl = env->vl; - uint32_t total_elems = vext_get_total_elems(env, desc, esz); - uint32_t vta = vext_vta(desc); - uint32_t vma = vext_vma(desc); - uint32_t i; - - for (i = env->vstart; i < vl; i++) { - if (!vm && !vext_elem_mask(v0, i)) { - /* set masked-off elements to 1s */ - vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz); - continue; - } - fn(vd, vs1, vs2, i); - } - env->vstart = 0; - /* set tail elements to 1s */ - vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); -} - -/* generate the helpers for OPIVV */ -#define GEN_VEXT_VV(NAME, ESZ) \ -void HELPER(NAME)(void *vd, void *v0, void *vs1, \ - void *vs2, CPURISCVState *env, \ - uint32_t desc) \ -{ \ - do_vext_vv(vd, v0, vs1, vs2, env, desc, \ - do_##NAME, ESZ); \ -} - GEN_VEXT_VV(vadd_vv_b, 1) GEN_VEXT_VV(vadd_vv_h, 2) GEN_VEXT_VV(vadd_vv_w, 4) @@ -829,18 +673,6 @@ GEN_VEXT_VV(vsub_vv_h, 2) GEN_VEXT_VV(vsub_vv_w, 4) GEN_VEXT_VV(vsub_vv_d, 8) -typedef void opivx2_fn(void *vd, target_long s1, void *vs2, int i); - -/* - * (T1)s1 gives the real operator type. - * (TX1)(T1)s1 expands the operator type of widen or narrow operations. - */ -#define OPIVX2(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \ -static void do_##NAME(void *vd, target_long s1, void *vs2, int i) \ -{ \ - TX2 s2 = *((T2 *)vs2 + HS2(i)); \ - *((TD *)vd + HD(i)) = OP(s2, (TX1)(T1)s1); \ -} RVVCALL(OPIVX2, vadd_vx_b, OP_SSS_B, H1, H1, DO_ADD) RVVCALL(OPIVX2, vadd_vx_h, OP_SSS_H, H2, H2, DO_ADD) @@ -855,40 +687,6 @@ RVVCALL(OPIVX2, vrsub_vx_h, OP_SSS_H, H2, H2, DO_RSUB) RVVCALL(OPIVX2, vrsub_vx_w, OP_SSS_W, H4, H4, DO_RSUB) RVVCALL(OPIVX2, vrsub_vx_d, OP_SSS_D, H8, H8, DO_RSUB) -static void do_vext_vx(void *vd, void *v0, target_long s1, void *vs2, - CPURISCVState *env, uint32_t desc, - opivx2_fn fn, uint32_t esz) -{ - uint32_t vm = vext_vm(desc); - uint32_t vl = env->vl; - uint32_t total_elems = vext_get_total_elems(env, desc, esz); - uint32_t vta = vext_vta(desc); - uint32_t vma = vext_vma(desc); - uint32_t i; - - for (i = env->vstart; i < vl; i++) { - if (!vm && !vext_elem_mask(v0, i)) { - /* set masked-off elements to 1s */ - vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz); - continue; - } - fn(vd, s1, vs2, i); - } - env->vstart = 0; - /* set tail elements to 1s */ - vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); -} - -/* generate the helpers for OPIVX */ -#define GEN_VEXT_VX(NAME, ESZ) \ -void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \ - void *vs2, CPURISCVState *env, \ - uint32_t desc) \ -{ \ - do_vext_vx(vd, v0, s1, vs2, env, desc, \ - do_##NAME, ESZ); \ -} - GEN_VEXT_VX(vadd_vx_b, 1) GEN_VEXT_VX(vadd_vx_h, 2) GEN_VEXT_VX(vadd_vx_w, 4) @@ -3637,11 +3435,6 @@ GEN_VEXT_VF(vfwnmsac_vf_h, 4) GEN_VEXT_VF(vfwnmsac_vf_w, 8) /* Vector Floating-Point Square-Root Instruction */ -/* (TD, T2, TX2) */ -#define OP_UU_H uint16_t, uint16_t, uint16_t -#define OP_UU_W uint32_t, uint32_t, uint32_t -#define OP_UU_D uint64_t, uint64_t, uint64_t - #define OPFVV1(NAME, TD, T2, TX2, HD, HS2, OP) \ static void do_##NAME(void *vd, void *vs2, int i, \ CPURISCVState *env) \ @@ -4338,40 +4131,6 @@ GEN_VEXT_CMP_VF(vmfge_vf_w, uint32_t, H4, vmfge32) GEN_VEXT_CMP_VF(vmfge_vf_d, uint64_t, H8, vmfge64) /* Vector Floating-Point Classify Instruction */ -#define OPIVV1(NAME, TD, T2, TX2, HD, HS2, OP) \ -static void do_##NAME(void *vd, void *vs2, int i) \ -{ \ - TX2 s2 = *((T2 *)vs2 + HS2(i)); \ - *((TD *)vd + HD(i)) = OP(s2); \ -} - -#define GEN_VEXT_V(NAME, ESZ) \ -void HELPER(NAME)(void *vd, void *v0, void *vs2, \ - CPURISCVState *env, uint32_t desc) \ -{ \ - uint32_t vm = vext_vm(desc); \ - uint32_t vl = env->vl; \ - uint32_t total_elems = \ - vext_get_total_elems(env, desc, ESZ); \ - uint32_t vta = vext_vta(desc); \ - uint32_t vma = vext_vma(desc); \ - uint32_t i; \ - \ - for (i = env->vstart; i < vl; i++) { \ - if (!vm && !vext_elem_mask(v0, i)) { \ - /* set masked-off elements to 1s */ \ - vext_set_elems_1s(vd, vma, i * ESZ, \ - (i + 1) * ESZ); \ - continue; \ - } \ - do_##NAME(vd, vs2, i); \ - } \ - env->vstart = 0; \ - /* set tail elements to 1s */ \ - vext_set_elems_1s(vd, vta, vl * ESZ, \ - total_elems * ESZ); \ -} - target_ulong fclass_h(uint64_t frs1) { float16 f = frs1; diff --git a/target/riscv/vector_internals.c b/target/riscv/vector_internals.c new file mode 100644 index 0000000000..9cf5c17cde --- /dev/null +++ b/target/riscv/vector_internals.c @@ -0,0 +1,81 @@ +/* + * RISC-V Vector Extension Internals + * + * Copyright (c) 2020 T-Head Semiconductor Co., Ltd. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2 or later, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "vector_internals.h" + +/* set agnostic elements to 1s */ +void vext_set_elems_1s(void *base, uint32_t is_agnostic, uint32_t cnt, + uint32_t tot) +{ + if (is_agnostic == 0) { + /* policy undisturbed */ + return; + } + if (tot - cnt == 0) { + return ; + } + memset(base + cnt, -1, tot - cnt); +} + +void do_vext_vv(void *vd, void *v0, void *vs1, void *vs2, + CPURISCVState *env, uint32_t desc, + opivv2_fn *fn, uint32_t esz) +{ + uint32_t vm = vext_vm(desc); + uint32_t vl = env->vl; + uint32_t total_elems = vext_get_total_elems(env, desc, esz); + uint32_t vta = vext_vta(desc); + uint32_t vma = vext_vma(desc); + uint32_t i; + + for (i = env->vstart; i < vl; i++) { + if (!vm && !vext_elem_mask(v0, i)) { + /* set masked-off elements to 1s */ + vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz); + continue; + } + fn(vd, vs1, vs2, i); + } + env->vstart = 0; + /* set tail elements to 1s */ + vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); +} + +void do_vext_vx(void *vd, void *v0, target_long s1, void *vs2, + CPURISCVState *env, uint32_t desc, + opivx2_fn fn, uint32_t esz) +{ + uint32_t vm = vext_vm(desc); + uint32_t vl = env->vl; + uint32_t total_elems = vext_get_total_elems(env, desc, esz); + uint32_t vta = vext_vta(desc); + uint32_t vma = vext_vma(desc); + uint32_t i; + + for (i = env->vstart; i < vl; i++) { + if (!vm && !vext_elem_mask(v0, i)) { + /* set masked-off elements to 1s */ + vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz); + continue; + } + fn(vd, s1, vs2, i); + } + env->vstart = 0; + /* set tail elements to 1s */ + vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); +} diff --git a/target/riscv/vector_internals.h b/target/riscv/vector_internals.h new file mode 100644 index 0000000000..8133111e5f --- /dev/null +++ b/target/riscv/vector_internals.h @@ -0,0 +1,228 @@ +/* + * RISC-V Vector Extension Internals + * + * Copyright (c) 2020 T-Head Semiconductor Co., Ltd. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2 or later, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef TARGET_RISCV_VECTOR_INTERNALS_H +#define TARGET_RISCV_VECTOR_INTERNALS_H + +#include "qemu/osdep.h" +#include "qemu/bitops.h" +#include "cpu.h" +#include "tcg/tcg-gvec-desc.h" +#include "internals.h" + +static inline uint32_t vext_nf(uint32_t desc) +{ + return FIELD_EX32(simd_data(desc), VDATA, NF); +} + +/* + * Note that vector data is stored in host-endian 64-bit chunks, + * so addressing units smaller than that needs a host-endian fixup. + */ +#if HOST_BIG_ENDIAN +#define H1(x) ((x) ^ 7) +#define H1_2(x) ((x) ^ 6) +#define H1_4(x) ((x) ^ 4) +#define H2(x) ((x) ^ 3) +#define H4(x) ((x) ^ 1) +#define H8(x) ((x)) +#else +#define H1(x) (x) +#define H1_2(x) (x) +#define H1_4(x) (x) +#define H2(x) (x) +#define H4(x) (x) +#define H8(x) (x) +#endif + +/* + * Encode LMUL to lmul as following: + * LMUL vlmul lmul + * 1 000 0 + * 2 001 1 + * 4 010 2 + * 8 011 3 + * - 100 - + * 1/8 101 -3 + * 1/4 110 -2 + * 1/2 111 -1 + */ +static inline int32_t vext_lmul(uint32_t desc) +{ + return sextract32(FIELD_EX32(simd_data(desc), VDATA, LMUL), 0, 3); +} + +static inline uint32_t vext_vm(uint32_t desc) +{ + return FIELD_EX32(simd_data(desc), VDATA, VM); +} + +static inline uint32_t vext_vma(uint32_t desc) +{ + return FIELD_EX32(simd_data(desc), VDATA, VMA); +} + +static inline uint32_t vext_vta(uint32_t desc) +{ + return FIELD_EX32(simd_data(desc), VDATA, VTA); +} + +static inline uint32_t vext_vta_all_1s(uint32_t desc) +{ + return FIELD_EX32(simd_data(desc), VDATA, VTA_ALL_1S); +} + +/* + * Earlier designs (pre-0.9) had a varying number of bits + * per mask value (MLEN). In the 0.9 design, MLEN=1. + * (Section 4.5) + */ +static inline int vext_elem_mask(void *v0, int index) +{ + int idx = index / 64; + int pos = index % 64; + return (((uint64_t *)v0)[idx] >> pos) & 1; +} + +/* + * Get number of total elements, including prestart, body and tail elements. + * Note that when LMUL < 1, the tail includes the elements past VLMAX that + * are held in the same vector register. + */ +static inline uint32_t vext_get_total_elems(CPURISCVState *env, uint32_t desc, + uint32_t esz) +{ + uint32_t vlenb = simd_maxsz(desc); + uint32_t sew = 1 << FIELD_EX64(env->vtype, VTYPE, VSEW); + int8_t emul = ctzl(esz) - ctzl(sew) + vext_lmul(desc) < 0 ? 0 : + ctzl(esz) - ctzl(sew) + vext_lmul(desc); + return (vlenb << emul) / esz; +} + +/* set agnostic elements to 1s */ +void vext_set_elems_1s(void *base, uint32_t is_agnostic, uint32_t cnt, + uint32_t tot); + +/* expand macro args before macro */ +#define RVVCALL(macro, ...) macro(__VA_ARGS__) + +/* (TD, T2, TX2) */ +#define OP_UU_B uint8_t, uint8_t, uint8_t +#define OP_UU_H uint16_t, uint16_t, uint16_t +#define OP_UU_W uint32_t, uint32_t, uint32_t +#define OP_UU_D uint64_t, uint64_t, uint64_t + +/* (TD, T1, T2, TX1, TX2) */ +#define OP_UUU_B uint8_t, uint8_t, uint8_t, uint8_t, uint8_t +#define OP_UUU_H uint16_t, uint16_t, uint16_t, uint16_t, uint16_t +#define OP_UUU_W uint32_t, uint32_t, uint32_t, uint32_t, uint32_t +#define OP_UUU_D uint64_t, uint64_t, uint64_t, uint64_t, uint64_t + +#define OPIVV1(NAME, TD, T2, TX2, HD, HS2, OP) \ +static void do_##NAME(void *vd, void *vs2, int i) \ +{ \ + TX2 s2 = *((T2 *)vs2 + HS2(i)); \ + *((TD *)vd + HD(i)) = OP(s2); \ +} + +#define GEN_VEXT_V(NAME, ESZ) \ +void HELPER(NAME)(void *vd, void *v0, void *vs2, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t vm = vext_vm(desc); \ + uint32_t vl = env->vl; \ + uint32_t total_elems = \ + vext_get_total_elems(env, desc, ESZ); \ + uint32_t vta = vext_vta(desc); \ + uint32_t vma = vext_vma(desc); \ + uint32_t i; \ + \ + for (i = env->vstart; i < vl; i++) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ + /* set masked-off elements to 1s */ \ + vext_set_elems_1s(vd, vma, i * ESZ, \ + (i + 1) * ESZ); \ + continue; \ + } \ + do_##NAME(vd, vs2, i); \ + } \ + env->vstart = 0; \ + /* set tail elements to 1s */ \ + vext_set_elems_1s(vd, vta, vl * ESZ, \ + total_elems * ESZ); \ +} + +/* operation of two vector elements */ +typedef void opivv2_fn(void *vd, void *vs1, void *vs2, int i); + +#define OPIVV2(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP) \ +static void do_##NAME(void *vd, void *vs1, void *vs2, int i) \ +{ \ + TX1 s1 = *((T1 *)vs1 + HS1(i)); \ + TX2 s2 = *((T2 *)vs2 + HS2(i)); \ + *((TD *)vd + HD(i)) = OP(s2, s1); \ +} + +void do_vext_vv(void *vd, void *v0, void *vs1, void *vs2, + CPURISCVState *env, uint32_t desc, + opivv2_fn *fn, uint32_t esz); + +/* generate the helpers for OPIVV */ +#define GEN_VEXT_VV(NAME, ESZ) \ +void HELPER(NAME)(void *vd, void *v0, void *vs1, \ + void *vs2, CPURISCVState *env, \ + uint32_t desc) \ +{ \ + do_vext_vv(vd, v0, vs1, vs2, env, desc, \ + do_##NAME, ESZ); \ +} + +typedef void opivx2_fn(void *vd, target_long s1, void *vs2, int i); + +/* + * (T1)s1 gives the real operator type. + * (TX1)(T1)s1 expands the operator type of widen or narrow operations. + */ +#define OPIVX2(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \ +static void do_##NAME(void *vd, target_long s1, void *vs2, int i) \ +{ \ + TX2 s2 = *((T2 *)vs2 + HS2(i)); \ + *((TD *)vd + HD(i)) = OP(s2, (TX1)(T1)s1); \ +} + +void do_vext_vx(void *vd, void *v0, target_long s1, void *vs2, + CPURISCVState *env, uint32_t desc, + opivx2_fn fn, uint32_t esz); + +/* generate the helpers for OPIVX */ +#define GEN_VEXT_VX(NAME, ESZ) \ +void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \ + void *vs2, CPURISCVState *env, \ + uint32_t desc) \ +{ \ + do_vext_vx(vd, v0, s1, vs2, env, desc, \ + do_##NAME, ESZ); \ +} + +/* Three of the widening shortening macros: */ +/* (TD, T1, T2, TX1, TX2) */ +#define WOP_UUU_B uint16_t, uint8_t, uint8_t, uint16_t, uint16_t +#define WOP_UUU_H uint32_t, uint16_t, uint16_t, uint32_t, uint32_t +#define WOP_UUU_W uint64_t, uint32_t, uint32_t, uint64_t, uint64_t + +#endif /* TARGET_RISCV_VECTOR_INTERNALS_H */ |