diff options
| author | Richard Henderson <richard.henderson@linaro.org> | 2023-07-10 21:42:50 +0100 |
|---|---|---|
| committer | Richard Henderson <richard.henderson@linaro.org> | 2023-07-10 21:42:50 +0100 |
| commit | 94d68c11362240a26ce425f56e2451d88f6814e1 (patch) | |
| tree | 2e345a15e1c0deecfd431d8a84f7c712272ad54c /target | |
| parent | 8d309a3a97e2d3734b74b07f355f860a9f2e880e (diff) | |
| parent | a47842d16653b4f73b5d56ff0c252dd8a329481b (diff) | |
Merge tag 'pull-riscv-to-apply-20230710-1' of https://github.com/alistair23/qemu into staging
Third RISC-V PR for 8.1
* Use xl instead of mxl for disassemble
* Factor out extension tests to cpu_cfg.h
* disas/riscv: Add vendor extension support
* disas/riscv: Add support for XVentanaCondOps
* disas/riscv: Add support for XThead* instructions
* Fix mstatus related problems
* Fix veyron-v1 CPU properties
* Fix the xlen for data address when MPRV=1
* opensbi: Upgrade from v1.2 to v1.3
* Enable 32-bit Spike OpenSBI boot testing
* Support the watchdog timer of HiFive 1 rev b
* Only build qemu-system-riscv$$ on rv$$ host
* Add RVV registers to log
* Restrict ACLINT to TCG
* Add syscall riscv_hwprobe
* Add support for BF16 extensions
* KVM_RISCV_SET_TIMER macro is not configured correctly
* Generate devicetree only after machine initialization is complete
* virt: Convert fdt_load_addr to uint64_t
* KVM: fixes and enhancements
* Add support for the Zfa extension
# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCAAdFiEEaukCtqfKh31tZZKWr3yVEwxTgBMFAmSr+ekACgkQr3yVEwxT
# gBMMGg//ZCcyH3KXB49c2KUIFO6FKYUxN9uC3giZCtuGyEH8T2yDgZVVXnxwU+Ij
# +3Ej6T/ZdWMpePC9qf+xKzHWZk7Qc8Tcg+JgQbga573894yZInRwYl8HsSlEKA+Z
# vlqSBPxTlp9rlDwGP/LjGljyIFqL4konk9zi3FL4ZXTF1iHUGrh/953Y3wIreEfl
# KX5UznnWcgy2BqQT1vihMbM8qCVK6iryH+QZ6LiAsPMSX1rIzk8ectQryILzoIYh
# bMiwCLVMyr4ZrUXjmGTF+7/WcOWwhhyfpdstf2iotKALelZtVHit0wHcty2GYQde
# nvN83jJWu04DGXkPBUsqCUQXczGo1QHjJUH3RIRJzfOby/lGt4pSzHAfKA+iNUht
# ikM3SdBsXMO+ogjTtTcCMb7/m2vsMoQP60VRts9Mh3YVD0cgr7RqpqRoEMugVYnr
# ca8Vijf71mB+y+pq477eV1Q8BoKpr8xa1OlFkNKPC17uMD7HoDMI44QgFOgtYp10
# TMsqqyB75q6PZhSEwm63xbmH0Zpo8kSqT/E3MTtGTyPeuL8TNNNSkCmFaGYmRrbI
# XEp7vG2RaDJOvDomS3nUhA5ruc8SaXd0q25q2gLYQfCsehfFqZAwuNB5xf1zS0M0
# ov1/gwaqU93t6nLbo2cCbb0plkIFKwwJ9KKjD06wJ4KPe0TGFzk=
# =3XFD
# -----END PGP SIGNATURE-----
# gpg: Signature made Mon 10 Jul 2023 01:30:33 PM BST
# gpg: using RSA key 6AE902B6A7CA877D6D659296AF7C95130C538013
# gpg: Good signature from "Alistair Francis <alistair@alistair23.me>" [unknown]
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg: There is no indication that the signature belongs to the owner.
# Primary key fingerprint: 6AE9 02B6 A7CA 877D 6D65 9296 AF7C 9513 0C53 8013
* tag 'pull-riscv-to-apply-20230710-1' of https://github.com/alistair23/qemu: (54 commits)
riscv: Add support for the Zfa extension
target/riscv/kvm.c: read/write (cbom|cboz)_blocksize in KVM
target/riscv/kvm.c: add kvmconfig_get_cfg_addr() helper
target/riscv: update multi-letter extension KVM properties
target/riscv/cpu.c: create KVM mock properties
target/riscv/cpu.c: remove priv_ver check from riscv_isa_string_ext()
target/riscv/cpu.c: add satp_mode properties earlier
target/riscv/kvm.c: add multi-letter extension KVM properties
target/riscv/kvm.c: update KVM MISA bits
target/riscv: add KVM specific MISA properties
target/riscv/cpu: add misa_ext_info_arr[]
target/riscv/kvm.c: init 'misa_ext_mask' with scratch CPU
target/riscv: handle mvendorid/marchid/mimpid for KVM CPUs
target/riscv: read marchid/mimpid in kvm_riscv_init_machine_ids()
target/riscv: use KVM scratch CPUs to init KVM properties
target/riscv/cpu.c: restrict 'marchid' value
target/riscv/cpu.c: restrict 'mimpid' value
target/riscv/cpu.c: restrict 'mvendorid' value
hw/riscv/virt.c: skip 'mmu-type' FDT if satp mode not set
target/riscv: skip features setup for KVM CPUs
...
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Diffstat (limited to 'target')
| -rw-r--r-- | target/riscv/cpu.c | 439 | ||||
| -rw-r--r-- | target/riscv/cpu.h | 56 | ||||
| -rw-r--r-- | target/riscv/cpu_cfg.h | 41 | ||||
| -rw-r--r-- | target/riscv/cpu_helper.c | 12 | ||||
| -rw-r--r-- | target/riscv/csr.c | 41 | ||||
| -rw-r--r-- | target/riscv/fpu_helper.c | 166 | ||||
| -rw-r--r-- | target/riscv/helper.h | 29 | ||||
| -rw-r--r-- | target/riscv/insn32.decode | 38 | ||||
| -rw-r--r-- | target/riscv/insn_trans/trans_rvbf16.c.inc | 175 | ||||
| -rw-r--r-- | target/riscv/insn_trans/trans_rvzfa.c.inc | 521 | ||||
| -rw-r--r-- | target/riscv/insn_trans/trans_rvzfh.c.inc | 12 | ||||
| -rw-r--r-- | target/riscv/kvm.c | 501 | ||||
| -rw-r--r-- | target/riscv/kvm_riscv.h | 1 | ||||
| -rw-r--r-- | target/riscv/op_helper.c | 3 | ||||
| -rw-r--r-- | target/riscv/translate.c | 42 | ||||
| -rw-r--r-- | target/riscv/vector_helper.c | 17 |
16 files changed, 1966 insertions, 128 deletions
diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c index 4035fe0e62..9339c0241d 100644 --- a/target/riscv/cpu.c +++ b/target/riscv/cpu.c @@ -34,16 +34,11 @@ #include "migration/vmstate.h" #include "fpu/softfloat-helpers.h" #include "sysemu/kvm.h" +#include "sysemu/tcg.h" #include "kvm_riscv.h" #include "tcg/tcg.h" /* RISC-V CPU definitions */ - -#define RISCV_CPU_MARCHID ((QEMU_VERSION_MAJOR << 16) | \ - (QEMU_VERSION_MINOR << 8) | \ - (QEMU_VERSION_MICRO)) -#define RISCV_CPU_MIMPID RISCV_CPU_MARCHID - static const char riscv_single_letter_exts[] = "IEMAFDQCPVH"; struct isa_ext_data { @@ -56,6 +51,17 @@ struct isa_ext_data { {#_name, _min_ver, offsetof(struct RISCVCPUConfig, _prop)} /* + * From vector_helper.c + * Note that vector data is stored in host-endian 64-bit chunks, + * so addressing bytes needs a host-endian fixup. + */ +#if HOST_BIG_ENDIAN +#define BYTE(x) ((x) ^ 7) +#else +#define BYTE(x) (x) +#endif + +/* * Here are the ordering rules of extension naming defined by RISC-V * specification : * 1. All extensions should be separated from other multi-letter extensions @@ -83,6 +89,8 @@ static const struct isa_ext_data isa_edata_arr[] = { ISA_EXT_DATA_ENTRY(zifencei, PRIV_VERSION_1_10_0, ext_ifencei), ISA_EXT_DATA_ENTRY(zihintpause, PRIV_VERSION_1_10_0, ext_zihintpause), 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), ISA_EXT_DATA_ENTRY(zfh, PRIV_VERSION_1_11_0, ext_zfh), ISA_EXT_DATA_ENTRY(zfhmin, PRIV_VERSION_1_11_0, ext_zfhmin), ISA_EXT_DATA_ENTRY(zfinx, PRIV_VERSION_1_12_0, ext_zfinx), @@ -114,6 +122,8 @@ static const struct isa_ext_data isa_edata_arr[] = { 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), + ISA_EXT_DATA_ENTRY(zvfbfmin, PRIV_VERSION_1_12_0, ext_zvfbfmin), + 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(zhinx, PRIV_VERSION_1_12_0, ext_zhinx), @@ -183,6 +193,14 @@ const char * const riscv_fpr_regnames[] = { "f30/ft10", "f31/ft11" }; +const char * const riscv_rvv_regnames[] = { + "v0", "v1", "v2", "v3", "v4", "v5", "v6", + "v7", "v8", "v9", "v10", "v11", "v12", "v13", + "v14", "v15", "v16", "v17", "v18", "v19", "v20", + "v21", "v22", "v23", "v24", "v25", "v26", "v27", + "v28", "v29", "v30", "v31" +}; + static const char * const riscv_excp_names[] = { "misaligned_fetch", "fault_fetch", @@ -412,6 +430,7 @@ static void rv64_thead_c906_cpu_init(Object *obj) set_misa(env, MXL_RV64, RVG | RVC | RVS | RVU); env->priv_ver = PRIV_VERSION_1_11_0; + cpu->cfg.ext_zfa = true; cpu->cfg.ext_zfh = true; cpu->cfg.mmu = true; cpu->cfg.ext_xtheadba = true; @@ -444,6 +463,9 @@ static void rv64_veyron_v1_cpu_init(Object *obj) /* Enable ISA extensions */ cpu->cfg.mmu = true; + cpu->cfg.ext_ifencei = true; + cpu->cfg.ext_icsr = true; + cpu->cfg.pmp = true; cpu->cfg.ext_icbom = true; cpu->cfg.cbom_blocksize = 64; cpu->cfg.cboz_blocksize = 64; @@ -608,7 +630,8 @@ static void riscv_cpu_dump_state(CPUState *cs, FILE *f, int flags) { RISCVCPU *cpu = RISCV_CPU(cs); CPURISCVState *env = &cpu->env; - int i; + int i, j; + uint8_t *p; #if !defined(CONFIG_USER_ONLY) if (riscv_has_ext(env, RVH)) { @@ -692,6 +715,41 @@ static void riscv_cpu_dump_state(CPUState *cs, FILE *f, int flags) } } } + if (riscv_has_ext(env, RVV) && (flags & CPU_DUMP_VPU)) { + static const int dump_rvv_csrs[] = { + CSR_VSTART, + CSR_VXSAT, + CSR_VXRM, + CSR_VCSR, + CSR_VL, + CSR_VTYPE, + CSR_VLENB, + }; + for (int i = 0; i < ARRAY_SIZE(dump_rvv_csrs); ++i) { + int csrno = dump_rvv_csrs[i]; + target_ulong val = 0; + RISCVException res = riscv_csrrw_debug(env, csrno, &val, 0, 0); + + /* + * Rely on the smode, hmode, etc, predicates within csr.c + * to do the filtering of the registers that are present. + */ + if (res == RISCV_EXCP_NONE) { + qemu_fprintf(f, " %-8s " TARGET_FMT_lx "\n", + csr_ops[csrno].name, val); + } + } + uint16_t vlenb = cpu->cfg.vlen >> 3; + + for (i = 0; i < 32; i++) { + qemu_fprintf(f, " %-8s ", riscv_rvv_regnames[i]); + p = (uint8_t *)env->vreg; + for (j = vlenb - 1 ; j >= 0; j--) { + qemu_fprintf(f, "%02x", *(p + i * vlenb + BYTE(j))); + } + qemu_fprintf(f, "\n"); + } + } } static void riscv_cpu_set_pc(CPUState *cs, vaddr value) @@ -858,9 +916,10 @@ static void riscv_cpu_reset_hold(Object *obj) static void riscv_cpu_disas_set_info(CPUState *s, disassemble_info *info) { RISCVCPU *cpu = RISCV_CPU(s); + CPURISCVState *env = &cpu->env; info->target_info = &cpu->cfg; - switch (riscv_cpu_mxl(&cpu->env)) { + switch (env->xl) { case MXL_RV32: info->print_insn = print_insn_riscv32; break; @@ -1050,6 +1109,11 @@ void riscv_cpu_validate_set_extensions(RISCVCPU *cpu, Error **errp) return; } + if (cpu->cfg.ext_zfa && !riscv_has_ext(env, RVF)) { + error_setg(errp, "Zfa extension requires F extension"); + return; + } + if (cpu->cfg.ext_zfh) { cpu->cfg.ext_zfhmin = true; } @@ -1059,6 +1123,11 @@ void riscv_cpu_validate_set_extensions(RISCVCPU *cpu, Error **errp) return; } + if (cpu->cfg.ext_zfbfmin && !riscv_has_ext(env, RVF)) { + error_setg(errp, "Zfbfmin extension depends on F extension"); + return; + } + if (riscv_has_ext(env, RVD) && !riscv_has_ext(env, RVF)) { error_setg(errp, "D extension requires F extension"); return; @@ -1109,6 +1178,21 @@ void riscv_cpu_validate_set_extensions(RISCVCPU *cpu, Error **errp) return; } + if (cpu->cfg.ext_zvfbfmin && !cpu->cfg.ext_zfbfmin) { + error_setg(errp, "Zvfbfmin extension depends on Zfbfmin extension"); + return; + } + + if (cpu->cfg.ext_zvfbfmin && !cpu->cfg.ext_zve32f) { + error_setg(errp, "Zvfbfmin extension depends on Zve32f extension"); + return; + } + + if (cpu->cfg.ext_zvfbfwma && !cpu->cfg.ext_zvfbfmin) { + error_setg(errp, "Zvfbfwma extension depends on Zvfbfmin extension"); + return; + } + /* Set the ISA extensions, checks should have happened above */ if (cpu->cfg.ext_zhinx) { cpu->cfg.ext_zhinxmin = true; @@ -1304,20 +1388,12 @@ static void riscv_cpu_validate_misa_priv(CPURISCVState *env, Error **errp) } } -static void riscv_cpu_realize(DeviceState *dev, Error **errp) +static void riscv_cpu_realize_tcg(DeviceState *dev, Error **errp) { - CPUState *cs = CPU(dev); RISCVCPU *cpu = RISCV_CPU(dev); CPURISCVState *env = &cpu->env; - RISCVCPUClass *mcc = RISCV_CPU_GET_CLASS(dev); Error *local_err = NULL; - cpu_exec_realizefn(cs, &local_err); - if (local_err != NULL) { - error_propagate(errp, local_err); - return; - } - riscv_cpu_validate_misa_mxl(cpu, &local_err); if (local_err != NULL) { error_propagate(errp, local_err); @@ -1352,7 +1428,7 @@ static void riscv_cpu_realize(DeviceState *dev, Error **errp) } #ifndef CONFIG_USER_ONLY - cs->tcg_cflags |= CF_PCREL; + CPU(dev)->tcg_cflags |= CF_PCREL; if (cpu->cfg.ext_sstc) { riscv_timer_init(cpu); @@ -1365,6 +1441,28 @@ static void riscv_cpu_realize(DeviceState *dev, Error **errp) } } #endif +} + +static void riscv_cpu_realize(DeviceState *dev, Error **errp) +{ + CPUState *cs = CPU(dev); + RISCVCPU *cpu = RISCV_CPU(dev); + RISCVCPUClass *mcc = RISCV_CPU_GET_CLASS(dev); + Error *local_err = NULL; + + cpu_exec_realizefn(cs, &local_err); + if (local_err != NULL) { + error_propagate(errp, local_err); + return; + } + + if (tcg_enabled()) { + riscv_cpu_realize_tcg(dev, &local_err); + if (local_err != NULL) { + error_propagate(errp, local_err); + return; + } + } riscv_cpu_finalize_features(cpu, &local_err); if (local_err != NULL) { @@ -1545,33 +1643,83 @@ static void cpu_get_misa_ext_cfg(Object *obj, Visitor *v, const char *name, visit_type_bool(v, name, &value, errp); } -static const RISCVCPUMisaExtConfig misa_ext_cfgs[] = { - {.name = "a", .description = "Atomic instructions", - .misa_bit = RVA, .enabled = true}, - {.name = "c", .description = "Compressed instructions", - .misa_bit = RVC, .enabled = true}, - {.name = "d", .description = "Double-precision float point", - .misa_bit = RVD, .enabled = true}, - {.name = "f", .description = "Single-precision float point", - .misa_bit = RVF, .enabled = true}, - {.name = "i", .description = "Base integer instruction set", - .misa_bit = RVI, .enabled = true}, - {.name = "e", .description = "Base integer instruction set (embedded)", - .misa_bit = RVE, .enabled = false}, - {.name = "m", .description = "Integer multiplication and division", - .misa_bit = RVM, .enabled = true}, - {.name = "s", .description = "Supervisor-level instructions", - .misa_bit = RVS, .enabled = true}, - {.name = "u", .description = "User-level instructions", - .misa_bit = RVU, .enabled = true}, - {.name = "h", .description = "Hypervisor", - .misa_bit = RVH, .enabled = true}, - {.name = "x-j", .description = "Dynamic translated languages", - .misa_bit = RVJ, .enabled = false}, - {.name = "v", .description = "Vector operations", - .misa_bit = RVV, .enabled = false}, - {.name = "g", .description = "General purpose (IMAFD_Zicsr_Zifencei)", - .misa_bit = RVG, .enabled = false}, +typedef struct misa_ext_info { + const char *name; + const char *description; +} MISAExtInfo; + +#define MISA_INFO_IDX(_bit) \ + __builtin_ctz(_bit) + +#define MISA_EXT_INFO(_bit, _propname, _descr) \ + [MISA_INFO_IDX(_bit)] = {.name = _propname, .description = _descr} + +static const MISAExtInfo misa_ext_info_arr[] = { + MISA_EXT_INFO(RVA, "a", "Atomic instructions"), + MISA_EXT_INFO(RVC, "c", "Compressed instructions"), + MISA_EXT_INFO(RVD, "d", "Double-precision float point"), + MISA_EXT_INFO(RVF, "f", "Single-precision float point"), + MISA_EXT_INFO(RVI, "i", "Base integer instruction set"), + MISA_EXT_INFO(RVE, "e", "Base integer instruction set (embedded)"), + MISA_EXT_INFO(RVM, "m", "Integer multiplication and division"), + MISA_EXT_INFO(RVS, "s", "Supervisor-level instructions"), + MISA_EXT_INFO(RVU, "u", "User-level instructions"), + MISA_EXT_INFO(RVH, "h", "Hypervisor"), + MISA_EXT_INFO(RVJ, "x-j", "Dynamic translated languages"), + MISA_EXT_INFO(RVV, "v", "Vector operations"), + MISA_EXT_INFO(RVG, "g", "General purpose (IMAFD_Zicsr_Zifencei)"), +}; + +static int riscv_validate_misa_info_idx(uint32_t bit) +{ + int idx; + + /* + * Our lowest valid input (RVA) is 1 and + * __builtin_ctz() is UB with zero. + */ + g_assert(bit != 0); + idx = MISA_INFO_IDX(bit); + + g_assert(idx < ARRAY_SIZE(misa_ext_info_arr)); + return idx; +} + +const char *riscv_get_misa_ext_name(uint32_t bit) +{ + int idx = riscv_validate_misa_info_idx(bit); + const char *val = misa_ext_info_arr[idx].name; + + g_assert(val != NULL); + return val; +} + +const char *riscv_get_misa_ext_description(uint32_t bit) +{ + int idx = riscv_validate_misa_info_idx(bit); + const char *val = misa_ext_info_arr[idx].description; + + g_assert(val != NULL); + return val; +} + +#define MISA_CFG(_bit, _enabled) \ + {.misa_bit = _bit, .enabled = _enabled} + +static RISCVCPUMisaExtConfig misa_ext_cfgs[] = { + MISA_CFG(RVA, true), + MISA_CFG(RVC, true), + MISA_CFG(RVD, true), + MISA_CFG(RVF, true), + MISA_CFG(RVI, true), + MISA_CFG(RVE, false), + MISA_CFG(RVM, true), + MISA_CFG(RVS, true), + MISA_CFG(RVU, true), + MISA_CFG(RVH, true), + MISA_CFG(RVJ, false), + MISA_CFG(RVV, false), + MISA_CFG(RVG, false), }; static void riscv_cpu_add_misa_properties(Object *cpu_obj) @@ -1579,7 +1727,16 @@ static void riscv_cpu_add_misa_properties(Object *cpu_obj) int i; for (i = 0; i < ARRAY_SIZE(misa_ext_cfgs); i++) { - const RISCVCPUMisaExtConfig *misa_cfg = &misa_ext_cfgs[i]; + RISCVCPUMisaExtConfig *misa_cfg = &misa_ext_cfgs[i]; + int bit = misa_cfg->misa_bit; + + misa_cfg->name = riscv_get_misa_ext_name(bit); + misa_cfg->description = riscv_get_misa_ext_description(bit); + + /* Check if KVM already created the property */ + if (object_property_find(cpu_obj, misa_cfg->name)) { + continue; + } object_property_add(cpu_obj, misa_cfg->name, "bool", cpu_get_misa_ext_cfg, @@ -1600,6 +1757,7 @@ static Property riscv_cpu_extensions[] = { DEFINE_PROP_BOOL("Zicsr", RISCVCPU, cfg.ext_icsr, 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), DEFINE_PROP_BOOL("Zfh", RISCVCPU, cfg.ext_zfh, false), DEFINE_PROP_BOOL("Zfhmin", RISCVCPU, cfg.ext_zfhmin, false), DEFINE_PROP_BOOL("Zve32f", RISCVCPU, cfg.ext_zve32f, false), @@ -1683,9 +1841,33 @@ static Property riscv_cpu_extensions[] = { DEFINE_PROP_BOOL("x-zvfh", RISCVCPU, cfg.ext_zvfh, false), DEFINE_PROP_BOOL("x-zvfhmin", RISCVCPU, cfg.ext_zvfhmin, false), + DEFINE_PROP_BOOL("x-zfbfmin", RISCVCPU, cfg.ext_zfbfmin, false), + DEFINE_PROP_BOOL("x-zvfbfmin", RISCVCPU, cfg.ext_zvfbfmin, false), + DEFINE_PROP_BOOL("x-zvfbfwma", RISCVCPU, cfg.ext_zvfbfwma, false), + DEFINE_PROP_END_OF_LIST(), }; + +#ifndef CONFIG_USER_ONLY +static void cpu_set_cfg_unavailable(Object *obj, Visitor *v, + const char *name, + void *opaque, Error **errp) +{ + const char *propname = opaque; + bool value; + + if (!visit_type_bool(v, name, &value, errp)) { + return; + } + + if (value) { + error_setg(errp, "extension %s is not available with KVM", + propname); + } +} +#endif + /* * Add CPU properties with user-facing flags. * @@ -1697,24 +1879,48 @@ static void riscv_cpu_add_user_properties(Object *obj) Property *prop; DeviceState *dev = DEVICE(obj); - riscv_cpu_add_misa_properties(obj); +#ifndef CONFIG_USER_ONLY + riscv_add_satp_mode_properties(obj); - for (prop = riscv_cpu_extensions; prop && prop->name; prop++) { - qdev_property_add_static(dev, prop); + if (kvm_enabled()) { + kvm_riscv_init_user_properties(obj); } +#endif + riscv_cpu_add_misa_properties(obj); + + for (prop = riscv_cpu_extensions; prop && prop->name; prop++) { #ifndef CONFIG_USER_ONLY - riscv_add_satp_mode_properties(obj); + if (kvm_enabled()) { + /* Check if KVM created the property already */ + if (object_property_find(obj, prop->name)) { + continue; + } + + /* + * Set the default to disabled for every extension + * unknown to KVM and error out if the user attempts + * to enable any of them. + * + * We're giving a pass for non-bool properties since they're + * not related to the availability of extensions and can be + * safely ignored as is. + */ + if (prop->info == &qdev_prop_bool) { + object_property_add(obj, prop->name, "bool", + NULL, cpu_set_cfg_unavailable, + NULL, (void *)prop->name); + continue; + } + } #endif + qdev_property_add_static(dev, prop); + } } static Property riscv_cpu_properties[] = { DEFINE_PROP_BOOL("debug", RISCVCPU, cfg.debug, true), - DEFINE_PROP_UINT32("mvendorid", RISCVCPU, cfg.mvendorid, 0), - DEFINE_PROP_UINT64("marchid", RISCVCPU, cfg.marchid, RISCV_CPU_MARCHID), - DEFINE_PROP_UINT64("mimpid", RISCVCPU, cfg.mimpid, RISCV_CPU_MIMPID), - #ifndef CONFIG_USER_ONLY DEFINE_PROP_UINT64("resetvec", RISCVCPU, env.resetvec, DEFAULT_RSTVEC), #endif @@ -1798,6 +2004,119 @@ static const struct TCGCPUOps riscv_tcg_ops = { #endif /* !CONFIG_USER_ONLY */ }; +static bool riscv_cpu_is_dynamic(Object *cpu_obj) +{ + return object_dynamic_cast(cpu_obj, TYPE_RISCV_DYNAMIC_CPU) != NULL; +} + +static void cpu_set_mvendorid(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + bool dynamic_cpu = riscv_cpu_is_dynamic(obj); + RISCVCPU *cpu = RISCV_CPU(obj); + uint32_t prev_val = cpu->cfg.mvendorid; + uint32_t value; + + if (!visit_type_uint32(v, name, &value, errp)) { + return; + } + + if (!dynamic_cpu && prev_val != value) { + error_setg(errp, "Unable to change %s mvendorid (0x%x)", + object_get_typename(obj), prev_val); + return; + } + + cpu->cfg.mvendorid = value; +} + +static void cpu_get_mvendorid(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + bool value = RISCV_CPU(obj)->cfg.mvendorid; + + visit_type_bool(v, name, &value, errp); +} + +static void cpu_set_mimpid(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + bool dynamic_cpu = riscv_cpu_is_dynamic(obj); + RISCVCPU *cpu = RISCV_CPU(obj); + uint64_t prev_val = cpu->cfg.mimpid; + uint64_t value; + + if (!visit_type_uint64(v, name, &value, errp)) { + return; + } + + if (!dynamic_cpu && prev_val != value) { + error_setg(errp, "Unable to change %s mimpid (0x%" PRIu64 ")", + object_get_typename(obj), prev_val); + return; + } + + cpu->cfg.mimpid = value; +} + +static void cpu_get_mimpid(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + bool value = RISCV_CPU(obj)->cfg.mimpid; + + visit_type_bool(v, name, &value, errp); +} + +static void cpu_set_marchid(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + bool dynamic_cpu = riscv_cpu_is_dynamic(obj); + RISCVCPU *cpu = RISCV_CPU(obj); + uint64_t prev_val = cpu->cfg.marchid; + uint64_t value, invalid_val; + uint32_t mxlen = 0; + + if (!visit_type_uint64(v, name, &value, errp)) { + return; + } + + if (!dynamic_cpu && prev_val != value) { + error_setg(errp, "Unable to change %s marchid (0x%" PRIu64 ")", + object_get_typename(obj), prev_val); + return; + } + + switch (riscv_cpu_mxl(&cpu->env)) { + case MXL_RV32: + mxlen = 32; + break; + case MXL_RV64: + case MXL_RV128: + mxlen = 64; + break; + default: + g_assert_not_reached(); + } + + invalid_val = 1LL << (mxlen - 1); + + if (value == invalid_val) { + error_setg(errp, "Unable to set marchid with MSB (%u) bit set " + "and the remaining bits zero", mxlen); + return; + } + + cpu->cfg.marchid = value; +} + +static void cpu_get_marchid(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + bool value = RISCV_CPU(obj)->cfg.marchid; + + visit_type_bool(v, name, &value, errp); +} + static void riscv_cpu_class_init(ObjectClass *c, void *data) { RISCVCPUClass *mcc = RISCV_CPU_CLASS(c); @@ -1829,6 +2148,15 @@ static void riscv_cpu_class_init(ObjectClass *c, void *data) cc->gdb_get_dynamic_xml = riscv_gdb_get_dynamic_xml; cc->tcg_ops = &riscv_tcg_ops; + object_class_property_add(c, "mvendorid", "uint32", cpu_get_mvendorid, + cpu_set_mvendorid, NULL, NULL); + + object_class_property_add(c, "mimpid", "uint64", cpu_get_mimpid, + cpu_set_mimpid, NULL, NULL); + + object_class_property_add(c, "marchid", "uint64", cpu_get_marchid, + cpu_set_marchid, NULL, NULL); + device_class_set_props(dc, riscv_cpu_properties); } @@ -1840,8 +2168,7 @@ static void riscv_isa_string_ext(RISCVCPU *cpu, char **isa_str, int i; for (i = 0; i < ARRAY_SIZE(isa_edata_arr); i++) { - if (cpu->env.priv_ver >= isa_edata_arr[i].min_version && - isa_ext_is_enabled(cpu, &isa_edata_arr[i])) { + if (isa_ext_is_enabled(cpu, &isa_edata_arr[i])) { new = g_strconcat(old, "_", isa_edata_arr[i].name, NULL); g_free(old); old = new; diff --git a/target/riscv/cpu.h b/target/riscv/cpu.h index 7adb8706ac..6ea22e0eea 100644 --- a/target/riscv/cpu.h +++ b/target/riscv/cpu.h @@ -41,7 +41,10 @@ #define RV(x) ((target_ulong)1 << (x - 'A')) -/* Consider updating misa_ext_cfgs[] when adding new MISA bits here */ +/* + * Consider updating misa_ext_info_arr[] and misa_ext_cfgs[] + * when adding new MISA bits here. + */ #define RVI RV('I') #define RVE RV('E') /* E and I are mutually exclusive */ #define RVM RV('M') @@ -56,6 +59,8 @@ #define RVJ RV('J') #define RVG RV('G') +const char *riscv_get_misa_ext_name(uint32_t bit); +const char *riscv_get_misa_ext_description(uint32_t bit); /* Privileged specification version */ enum { @@ -500,6 +505,7 @@ FIELD(TB_FLAGS, ITRIGGER, 22, 1) /* Virtual mode enabled */ FIELD(TB_FLAGS, VIRT_ENABLED, 23, 1) FIELD(TB_FLAGS, PRIV, 24, 2) +FIELD(TB_FLAGS, AXL, 26, 2) #ifdef TARGET_RISCV32 #define riscv_cpu_mxl(env) ((void)(env), MXL_RV32) @@ -516,13 +522,20 @@ static inline const RISCVCPUConfig *riscv_cpu_cfg(CPURISCVState *env) return &env_archcpu(env)->cfg; } -#if defined(TARGET_RISCV32) -#define cpu_recompute_xl(env) ((void)(env), MXL_RV32) -#else -static inline RISCVMXL cpu_recompute_xl(CPURISCVState *env) +#if !defined(CONFIG_USER_ONLY) +static inline int cpu_address_mode(CPURISCVState *env) +{ + int mode = env->priv; + + if (mode == PRV_M && get_field(env->mstatus, MSTATUS_MPRV)) { + mode = get_field(env->mstatus, MSTATUS_MPP); + } + return mode; +} + +static inline RISCVMXL cpu_get_xl(CPURISCVState *env, target_ulong mode) { RISCVMXL xl = env->misa_mxl; -#if !defined(CONFIG_USER_ONLY) /* * When emulating a 32-bit-only cpu, use RV32. * When emulating a 64-bit cpu, and MXL has been reduced to RV32, @@ -530,7 +543,7 @@ static inline RISCVMXL cpu_recompute_xl(CPURISCVState *env) * back to RV64 for lower privs. */ if (xl != MXL_RV32) { - switch (env->priv) { + switch (mode) { case PRV_M: break; case PRV_U: @@ -541,11 +554,38 @@ static inline RISCVMXL cpu_recompute_xl(CPURISCVState *env) break; } } -#endif return xl; } #endif +#if defined(TARGET_RISCV32) +#define cpu_recompute_xl(env) ((void)(env), MXL_RV32) +#else +static inline RISCVMXL cpu_recompute_xl(CPURISCVState *env) +{ +#if !defined(CONFIG_USER_ONLY) + return cpu_get_xl(env, env->priv); +#else + return env->misa_mxl; +#endif +} +#endif + +#if defined(TARGET_RISCV32) +#define cpu_address_xl(env) ((void)(env), MXL_RV32) +#else +static inline RISCVMXL cpu_address_xl(CPURISCVState *env) +{ +#ifdef CONFIG_USER_ONLY + return env->xl; +#else + int mode = cpu_address_mode(env); + + return cpu_get_xl(env, mode); +#endif +} +#endif + static inline int riscv_cpu_xlen(CPURISCVState *env) { return 16 << env->xl; diff --git a/target/riscv/cpu_cfg.h b/target/riscv/cpu_cfg.h index c4a627d335..2bd9510ba3 100644 --- a/target/riscv/cpu_cfg.h +++ b/target/riscv/cpu_cfg.h @@ -75,6 +75,8 @@ struct RISCVCPUConfig { bool ext_svpbmt; bool ext_zdinx; bool ext_zawrs; + bool ext_zfa; + bool ext_zfbfmin; bool ext_zfh; bool ext_zfhmin; bool ext_zfinx; @@ -84,6 +86,8 @@ struct RISCVCPUConfig { bool ext_zve64f; bool ext_zve64d; bool ext_zmmul; + bool ext_zvfbfmin; + bool ext_zvfbfwma; bool ext_zvfh; bool ext_zvfhmin; bool ext_smaia; @@ -133,4 +137,41 @@ struct RISCVCPUConfig { }; typedef struct RISCVCPUConfig RISCVCPUConfig; + +/* Helper functions to test for extensions. */ + +static inline bool always_true_p(const RISCVCPUConfig *cfg __attribute__((__unused__))) +{ + return true; +} + +static inline bool has_xthead_p(const RISCVCPUConfig *cfg) +{ + return cfg->ext_xtheadba || cfg->ext_xtheadbb || + cfg->ext_xtheadbs || cfg->ext_xtheadcmo || + cfg->ext_xtheadcondmov || + cfg->ext_xtheadfmemidx || cfg->ext_xtheadfmv || + cfg->ext_xtheadmac || cfg->ext_xtheadmemidx || + cfg->ext_xtheadmempair || cfg->ext_xtheadsync; +} + +#define MATERIALISE_EXT_PREDICATE(ext) \ + static inline bool has_ ## ext ## _p(const RISCVCPUConfig *cfg) \ + { \ + return cfg->ext_ ## ext ; \ + } + +MATERIALISE_EXT_PREDICATE(xtheadba) +MATERIALISE_EXT_PREDICATE(xtheadbb) +MATERIALISE_EXT_PREDICATE(xtheadbs) +MATERIALISE_EXT_PREDICATE(xtheadcmo) +MATERIALISE_EXT_PREDICATE(xtheadcondmov) +MATERIALISE_EXT_PREDICATE(xtheadfmemidx) +MATERIALISE_EXT_PREDICATE(xtheadfmv) +MATERIALISE_EXT_PREDICATE(xtheadmac) +MATERIALISE_EXT_PREDICATE(xtheadmemidx) +MATERIALISE_EXT_PREDICATE(xtheadmempair) +MATERIALISE_EXT_PREDICATE(xtheadsync) +MATERIALISE_EXT_PREDICATE(XVentanaCondOps) + #endif diff --git a/target/riscv/cpu_helper.c b/target/riscv/cpu_helper.c index a944f25694..9f611d89bb 100644 --- a/target/riscv/cpu_helper.c +++ b/target/riscv/cpu_helper.c @@ -47,7 +47,8 @@ int riscv_cpu_mmu_index(CPURISCVState *env, bool ifetch) if (mode == PRV_M && get_field(status, MSTATUS_MPRV)) { mode = get_field(env->mstatus, MSTATUS_MPP); - virt = get_field(env->mstatus, MSTATUS_MPV); + virt = get_field(env->mstatus, MSTATUS_MPV) && + (mode != PRV_M); if (virt) { status = env->vsstatus; } @@ -134,6 +135,7 @@ void cpu_get_tb_cpu_state(CPURISCVState *env, vaddr *pc, flags = FIELD_DP32(flags, TB_FLAGS, FS, fs); flags = FIELD_DP32(flags, TB_FLAGS, VS, vs); flags = FIELD_DP32(flags, TB_FLAGS, XL, env->xl); + flags = FIELD_DP32(flags, TB_FLAGS, AXL, cpu_address_xl(env)); if (env->cur_pmmask != 0) { flags = FIELD_DP32(flags, TB_FLAGS, PM_MASK_ENABLED, 1); } @@ -147,13 +149,16 @@ void cpu_get_tb_cpu_state(CPURISCVState *env, vaddr *pc, void riscv_cpu_update_mask(CPURISCVState *env) { target_ulong mask = 0, base = 0; + RISCVMXL xl = env->xl; /* * TODO: Current RVJ spec does not specify * how the extension interacts with XLEN. */ #ifndef CONFIG_USER_ONLY + int mode = cpu_address_mode(env); + xl = cpu_get_xl(env, mode); if (riscv_has_ext(env, RVJ)) { - switch (env->priv) { + switch (mode) { case PRV_M: if (env->mmte & M_PM_ENABLE) { mask = env->mpmmask; @@ -177,7 +182,7 @@ void riscv_cpu_update_mask(CPURISCVState *env) } } #endif - if (env->xl == MXL_RV32) { + if (xl == MXL_RV32) { env->cur_pmmask = mask & UINT32_MAX; env->cur_pmbase = base & UINT32_MAX; } else { @@ -1277,7 +1282,6 @@ bool riscv_cpu_tlb_fill(CPUState *cs, vaddr address, int size, if (ret == TRANSLATE_G_STAGE_FAIL) { first_stage_error = false; two_stage_indirect_error = true; - access_type = MMU_DATA_LOAD; } qemu_log_mask(CPU_LOG_MMU, diff --git a/target/riscv/csr.c b/target/riscv/csr.c index 58499b5afc..ea7585329e 100644 --- a/target/riscv/csr.c +++ b/target/riscv/csr.c @@ -1311,11 +1311,9 @@ static RISCVException write_mstatus(CPURISCVState *env, int csrno, } if (xl != MXL_RV32 || env->debugger) { - /* - * RV32: MPV and GVA are not in mstatus. The current plan is to - * add them to mstatush. For now, we just don't support it. - */ - mask |= MSTATUS_MPV | MSTATUS_GVA; + if (riscv_has_ext(env, RVH)) { + mask |= MSTATUS_MPV | MSTATUS_GVA; + } if ((val & MSTATUS64_UXL) != 0) { mask |= MSTATUS64_UXL; } @@ -1323,10 +1321,6 @@ static RISCVException write_mstatus(CPURISCVState *env, int csrno, mstatus = (mstatus & ~mask) | (val & mask); - if (xl > MXL_RV32) { - /* SXL field is for now read only */ - mstatus = set_field(mstatus, MSTATUS64_SXL, xl); - } env->mstatus = mstatus; /* @@ -1335,8 +1329,9 @@ static RISCVException write_mstatus(CPURISCVState *env, int csrno, */ if (env->debugger) { env->xl = cpu_recompute_xl(env); - riscv_cpu_update_mask(env); } + + riscv_cpu_update_mask(env); return RISCV_EXCP_NONE; } @@ -1351,7 +1346,7 @@ static RISCVException write_mstatush(CPURISCVState *env, int csrno, target_ulong val) { uint64_t valh = (uint64_t)val << 32; - uint64_t mask = MSTATUS_MPV | MSTATUS_GVA; + uint64_t mask = riscv_has_ext(env, RVH) ? MSTATUS_MPV | MSTATUS_GVA : 0; env->mstatus = (env->mstatus & ~mask) | (valh & mask); @@ -3639,7 +3634,7 @@ static RISCVException write_mpmmask(CPURISCVState *env, int csrno, uint64_t mstatus; env->mpmmask = val; - if ((env->priv == PRV_M) && (env->mmte & M_PM_ENABLE)) { + if ((cpu_address_mode(env) == PRV_M) && (env->mmte & M_PM_ENABLE)) { env->cur_pmmask = val; } env->mmte |= EXT_STATUS_DIRTY; @@ -3667,8 +3662,11 @@ static RISCVException write_spmmask(CPURISCVState *env, int csrno, return RISCV_EXCP_NONE; } env->spmmask = val; - if ((env->priv == PRV_S) && (env->mmte & S_PM_ENABLE)) { + if ((cpu_address_mode(env) == PRV_S) && (env->mmte & S_PM_ENABLE)) { env->cur_pmmask = val; + if (cpu_get_xl(env, PRV_S) == MXL_RV32) { + env->cur_pmmask &= UINT32_MAX; + } } env->mmte |= EXT_STATUS_DIRTY; @@ -3695,8 +3693,11 @@ static RISCVException write_upmmask(CPURISCVState *env, int csrno, return RISCV_EXCP_NONE; } env->upmmask = val; - if ((env->priv == PRV_U) && (env->mmte & U_PM_ENABLE)) { + if ((cpu_address_mode(env) == PRV_U) && (env->mmte & U_PM_ENABLE)) { env->cur_pmmask = val; + if (cpu_get_xl(env, PRV_U) == MXL_RV32) { + env->cur_pmmask &= UINT32_MAX; + } } env->mmte |= EXT_STATUS_DIRTY; @@ -3719,7 +3720,7 @@ static RISCVException write_mpmbase(CPURISCVState *env, int csrno, uint64_t mstatus; env->mpmbase = val; - if ((env->priv == PRV_M) && (env->mmte & M_PM_ENABLE)) { + if ((cpu_address_mode(env) == PRV_M) && (env->mmte & M_PM_ENABLE)) { env->cur_pmbase = val; } env->mmte |= EXT_STATUS_DIRTY; @@ -3747,8 +3748,11 @@ static RISCVException write_spmbase(CPURISCVState *env, int csrno, return RISCV_EXCP_NONE; } env->spmbase = val; - if ((env->priv == PRV_S) && (env->mmte & S_PM_ENABLE)) { + if ((cpu_address_mode(env) == PRV_S) && (env->mmte & S_PM_ENABLE)) { env->cur_pmbase = val; + if (cpu_get_xl(env, PRV_S) == MXL_RV32) { + env->cur_pmbase &= UINT32_MAX; + } } env->mmte |= EXT_STATUS_DIRTY; @@ -3775,8 +3779,11 @@ static RISCVException write_upmbase(CPURISCVState *env, int csrno, return RISCV_EXCP_NONE; } env->upmbase = val; - if ((env->priv == PRV_U) && (env->mmte & U_PM_ENABLE)) { + if ((cpu_address_mode(env) == PRV_U) && (env->mmte & U_PM_ENABLE)) { env->cur_pmbase = val; + if (cpu_get_xl(env, PRV_U) == MXL_RV32) { + env->cur_pmbase &= UINT32_MAX; + } } env->mmte |= EXT_STATUS_DIRTY; diff --git a/target/riscv/fpu_helper.c b/target/riscv/fpu_helper.c index 5dd14d8390..871a70a316 100644 --- a/target/riscv/fpu_helper.c +++ b/target/riscv/fpu_helper.c @@ -252,6 +252,14 @@ uint64_t helper_fmin_s(CPURISCVState *env, uint64_t rs1, uint64_t rs2) float32_minimum_number(frs1, frs2, &env->fp_status)); } +uint64_t helper_fminm_s(CPURISCVState *env, uint64_t rs1, uint64_t rs2) +{ + float32 frs1 = check_nanbox_s(env, rs1); + float32 frs2 = check_nanbox_s(env, rs2); + float32 ret = float32_min(frs1, frs2, &env->fp_status); + return nanbox_s(env, ret); +} + uint64_t helper_fmax_s(CPURISCVState *env, uint64_t rs1, uint64_t rs2) { float32 frs1 = check_nanbox_s(env, rs1); @@ -261,6 +269,14 @@ uint64_t helper_fmax_s(CPURISCVState *env, uint64_t rs1, uint64_t rs2) float32_maximum_number(frs1, frs2, &env->fp_status)); } +uint64_t helper_fmaxm_s(CPURISCVState *env, uint64_t rs1, uint64_t rs2) +{ + float32 frs1 = check_nanbox_s(env, rs1); + float32 frs2 = check_nanbox_s(env, rs2); + float32 ret = float32_max(frs1, frs2, &env->fp_status); + return nanbox_s(env, ret); +} + uint64_t helper_fsqrt_s(CPURISCVState *env, uint64_t rs1) { float32 frs1 = check_nanbox_s(env, rs1); @@ -274,6 +290,13 @@ target_ulong helper_fle_s(CPURISCVState *env, uint64_t rs1, uint64_t rs2) return float32_le(frs1, frs2, &env->fp_status); } +target_ulong helper_fleq_s(CPURISCVState *env, uint64_t rs1, uint64_t rs2) +{ + float32 frs1 = check_nanbox_s(env, rs1); + float32 frs2 = check_nanbox_s(env, rs2); + return float32_le_quiet(frs1, frs2, &env->fp_status); +} + target_ulong helper_flt_s(CPURISCVState *env, uint64_t rs1, uint64_t rs2) { float32 frs1 = check_nanbox_s(env, rs1); @@ -281,6 +304,13 @@ target_ulong helper_flt_s(CPURISCVState *env, uint64_t rs1, uint64_t rs2) return float32_lt(frs1, frs2, &env->fp_status); } +target_ulong helper_fltq_s(CPURISCVState *env, uint64_t rs1, uint64_t rs2) +{ + float32 frs1 = check_nanbox_s(env, rs1); + float32 frs2 = check_nanbox_s(env, rs2); + return float32_lt_quiet(frs1, frs2, &env->fp_status); +} + target_ulong helper_feq_s(CPURISCVState *env, uint64_t rs1, uint64_t rs2) { float32 frs1 = check_nanbox_s(env, rs1); @@ -338,6 +368,30 @@ target_ulong helper_fclass_s(CPURISCVState *env, uint64_t rs1) return fclass_s(frs1); } +uint64_t helper_fround_s(CPURISCVState *env, uint64_t rs1) +{ + float_status *fs = &env->fp_status; + uint16_t nx_old = get_float_exception_flags(fs) & float_flag_inexact; + float32 frs1 = check_nanbox_s(env, rs1); + + frs1 = float32_round_to_int(frs1, fs); + + /* Restore the original NX flag. */ + uint16_t flags = get_float_exception_flags(fs); + flags &= ~float_flag_inexact; + flags |= nx_old; + set_float_exception_flags(flags, fs); + + return nanbox_s(env, frs1); +} + +uint64_t helper_froundnx_s(CPURISCVState *env, uint64_t rs1) +{ + float32 frs1 = check_nanbox_s(env, rs1); + frs1 = float32_round_to_int(frs1, &env->fp_status); + return nanbox_s(env, frs1); +} + uint64_t helper_fadd_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2) { return float64_add(frs1, frs2, &env->fp_status); @@ -365,6 +419,11 @@ uint64_t helper_fmin_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2) float64_minimum_number(frs1, frs2, &env->fp_status); } +uint64_t helper_fminm_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2) +{ + return float64_min(frs1, frs2, &env->fp_status); +} + uint64_t helper_fmax_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2) { return env->priv_ver < PRIV_VERSION_1_11_0 ? @@ -372,6 +431,11 @@ uint64_t helper_fmax_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2) float64_maximum_number(frs1, frs2, &env->fp_status); } +uint64_t helper_fmaxm_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2) +{ + return float64_max(frs1, frs2, &env->fp_status); +} + uint64_t helper_fcvt_s_d(CPURISCVState *env, uint64_t rs1) { return nanbox_s(env, float64_to_float32(rs1, &env->fp_status)); @@ -393,11 +457,21 @@ target_ulong helper_fle_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2) return float64_le(frs1, frs2, &env->fp_status); } +target_ulong helper_fleq_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2) +{ + return float64_le_quiet(frs1, frs2, &env->fp_status); +} + target_ulong helper_flt_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2) { return float64_lt(frs1, frs2, &env->fp_status); } +target_ulong helper_fltq_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2) +{ + return float64_lt_quiet(frs1, frs2, &env->fp_status); +} + target_ulong helper_feq_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2) { return float64_eq_quiet(frs1, frs2, &env->fp_status); @@ -408,6 +482,11 @@ target_ulong helper_fcvt_w_d(CPURISCVState *env, uint64_t frs1) return float64_to_int32(frs1, &env->fp_status); } +uint64_t helper_fcvtmod_w_d(CPURISCVState *env, uint64_t value) +{ + return float64_to_int32_modulo(value, float_round_to_zero, &env->fp_status); +} + target_ulong helper_fcvt_wu_d(CPURISCVState *env, uint64_t frs1) { return (int32_t)float64_to_uint32(frs1, &env->fp_status); @@ -448,6 +527,27 @@ target_ulong helper_fclass_d(uint64_t frs1) return fclass_d(frs1); } +uint64_t helper_fround_d(CPURISCVState *env, uint64_t frs1) +{ + float_status *fs = &env->fp_status; + uint16_t nx_old = get_float_exception_flags(fs) & float_flag_inexact; + + frs1 = float64_round_to_int(frs1, fs); + + /* Restore the original NX flag. */ + uint16_t flags = get_float_exception_flags(fs); + flags &= ~float_flag_inexact; + flags |= nx_old; + set_float_exception_flags(flags, fs); + + return frs1; +} + +uint64_t helper_froundnx_d(CPURISCVState *env, uint64_t frs1) +{ + return float64_round_to_int(frs1, &env->fp_status); +} + uint64_t helper_fadd_h(CPURISCVState *env, uint64_t rs1, uint64_t rs2) { float16 frs1 = check_nanbox_h(env, rs1); @@ -485,6 +585,14 @@ uint64_t helper_fmin_h(CPURISCVState *env, uint64_t rs1, uint64_t rs2) float16_minimum_number(frs1, frs2, &env->fp_status)); } +uint64_t helper_fminm_h(CPURISCVState *env, uint64_t rs1, uint64_t rs2) +{ + float16 frs1 = check_nanbox_h(env, rs1); + float16 frs2 = check_nanbox_h(env, rs2); + float16 ret = float16_min(frs1, frs2, &env->fp_status); + return nanbox_h(env, ret); +} + uint64_t helper_fmax_h(CPURISCVState *env, uint64_t rs1, uint64_t rs2) { float16 frs1 = check_nanbox_h(env, rs1); @@ -494,6 +602,14 @@ uint64_t helper_fmax_h(CPURISCVState *env, uint64_t rs1, uint64_t rs2) float16_maximum_number(frs1, frs2, &env->fp_status)); } +uint64_t helper_fmaxm_h(CPURISCVState *env, uint64_t rs1, uint64_t rs2) +{ + float16 frs1 = check_nanbox_h(env, rs1); + float16 frs2 = check_nanbox_h(env, rs2); + float16 ret = float16_max(frs1, frs2, &env->fp_status); + return nanbox_h(env, ret); +} + uint64_t helper_fsqrt_h(CPURISCVState *env, uint64_t rs1) { float16 frs1 = check_nanbox_h(env, rs1); @@ -507,6 +623,13 @@ target_ulong helper_fle_h(CPURISCVState *env, uint64_t rs1, uint64_t rs2) return float16_le(frs1, frs2, &env->fp_status); } +target_ulong helper_fleq_h(CPURISCVState *env, uint64_t rs1, uint64_t rs2) +{ + float16 frs1 = check_nanbox_h(env, rs1); + float16 frs2 = check_nanbox_h(env, rs2); + return float16_le_quiet(frs1, frs2, &env->fp_status); +} + target_ulong helper_flt_h(CPURISCVState *env, uint64_t rs1, uint64_t rs2) { float16 frs1 = check_nanbox_h(env, rs1); @@ -514,6 +637,13 @@ target_ulong helper_flt_h(CPURISCVState *env, uint64_t rs1, uint64_t rs2) return float16_lt(frs1, frs2, &env->fp_status); } +target_ulong helper_fltq_h(CPURISCVState *env, uint64_t rs1, uint64_t rs2) +{ + float16 frs1 = check_nanbox_h(env, rs1); + float16 frs2 = check_nanbox_h(env, rs2); + return float16_lt_quiet(frs1, frs2, &env->fp_status); +} + target_ulong helper_feq_h(CPURISCVState *env, uint64_t rs1, uint64_t rs2) { float16 frs1 = check_nanbox_h(env, rs1); @@ -527,6 +657,30 @@ target_ulong helper_fclass_h(CPURISCVState *env, uint64_t rs1) return fclass_h(frs1); } +uint64_t helper_fround_h(CPURISCVState *env, uint64_t rs1) +{ + float_status *fs = &env->fp_status; + uint16_t nx_old = get_float_exception_flags(fs) & float_flag_inexact; + float16 frs1 = check_nanbox_h(env, rs1); + + frs1 = float16_round_to_int(frs1, fs); + + /* Restore the original NX flag. */ + uint16_t flags = get_float_exception_flags(fs); + flags &= ~float_flag_inexact; + flags |= nx_old; + set_float_exception_flags(flags, fs); + + return nanbox_h(env, frs1); +} + +uint64_t helper_froundnx_h(CPURISCVState *env, uint64_t rs1) +{ + float16 frs1 = check_nanbox_s(env, rs1); + frs1 = float16_round_to_int(frs1, &env->fp_status); + return nanbox_h(env, frs1); +} + target_ulong helper_fcvt_w_h(CPURISCVState *env, uint64_t rs1) { float16 frs1 = check_nanbox_h(env, rs1); @@ -593,3 +747,15 @@ uint64_t helper_fcvt_d_h(CPURISCVState *env, uint64_t rs1) float16 frs1 = check_nanbox_h(env, rs1); return float16_to_float64(frs1, true, &env->fp_status); } + +uint64_t helper_fcvt_bf16_s(CPURISCVState *env, uint64_t rs1) +{ + float32 frs1 = check_nanbox_s(env, rs1); + return nanbox_h(env, float32_to_bfloat16(frs1, &env->fp_status)); +} + +uint64_t helper_fcvt_s_bf16(CPURISCVState *env, uint64_t rs1) +{ + float16 frs1 = check_nanbox_h(env, rs1); + return nanbox_s(env, bfloat16_to_float32(frs1, &env->fp_status)); +} diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 98e97810fd..c95adaf08a 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -25,10 +25,14 @@ DEF_HELPER_FLAGS_3(fsub_s, TCG_CALL_NO_RWG, i64, env, i64, i64) DEF_HELPER_FLAGS_3(fmul_s, TCG_CALL_NO_RWG, i64, env, i64, i64) DEF_HELPER_FLAGS_3(fdiv_s, TCG_CALL_NO_RWG, i64, env, i64, i64) DEF_HELPER_FLAGS_3(fmin_s, TCG_CALL_NO_RWG, i64, env, i64, i64) +DEF_HELPER_FLAGS_3(fminm_s, TCG_CALL_NO_RWG, i64, env, i64, i64) DEF_HELPER_FLAGS_3(fmax_s, TCG_CALL_NO_RWG, i64, env, i64, i64) +DEF_HELPER_FLAGS_3(fmaxm_s, TCG_CALL_NO_RWG, i64, env, i64, i64) DEF_HELPER_FLAGS_2(fsqrt_s, TCG_CALL_NO_RWG, i64, env, i64) DEF_HELPER_FLAGS_3(fle_s, TCG_CALL_NO_RWG, tl, env, i64, i64) +DEF_HELPER_FLAGS_3(fleq_s, TCG_CALL_NO_RWG, tl, env, i64, i64) DEF_HELPER_FLAGS_3(flt_s, TCG_CALL_NO_RWG, tl, env, i64, i64) +DEF_HELPER_FLAGS_3(fltq_s, TCG_CALL_NO_RWG, tl, env, i64, i64) DEF_HELPER_FLAGS_3(feq_s, TCG_CALL_NO_RWG, tl, env, i64, i64) DEF_HELPER_FLAGS_2(fcvt_w_s, TCG_CALL_NO_RWG, tl, env, i64) DEF_HELPER_FLAGS_2(fcvt_wu_s, TCG_CALL_NO_RWG, tl, env, i64) @@ -39,6 +43,8 @@ DEF_HELPER_FLAGS_2(fcvt_s_wu, TCG_CALL_NO_RWG, i64, env, tl) DEF_HELPER_FLAGS_2(fcvt_s_l, TCG_CALL_NO_RWG, i64, env, tl) DEF_HELPER_FLAGS_2(fcvt_s_lu, TCG_CALL_NO_RWG, i64, env, tl) DEF_HELPER_FLAGS_2(fclass_s, TCG_CALL_NO_RWG_SE, tl, env, i64) +DEF_HELPER_FLAGS_2(fround_s, TCG_CALL_NO_RWG_SE, i64, env, i64) +DEF_HELPER_FLAGS_2(froundnx_s, TCG_CALL_NO_RWG_SE, i64, env, i64) /* Floating Point - Double Precision */ DEF_HELPER_FLAGS_3(fadd_d, TCG_CALL_NO_RWG, i64, env, i64, i64) @@ -46,14 +52,19 @@ DEF_HELPER_FLAGS_3(fsub_d, TCG_CALL_NO_RWG, i64, env, i64, i64) DEF_HELPER_FLAGS_3(fmul_d, TCG_CALL_NO_RWG, i64, env, i64, i64) DEF_HELPER_FLAGS_3(fdiv_d, TCG_CALL_NO_RWG, i64, env, i64, i64) DEF_HELPER_FLAGS_3(fmin_d, TCG_CALL_NO_RWG, i64, env, i64, i64) +DEF_HELPER_FLAGS_3(fminm_d, TCG_CALL_NO_RWG, i64, env, i64, i64) DEF_HELPER_FLAGS_3(fmax_d, TCG_CALL_NO_RWG, i64, env, i64, i64) +DEF_HELPER_FLAGS_3(fmaxm_d, TCG_CALL_NO_RWG, i64, env, i64, i64) DEF_HELPER_FLAGS_2(fcvt_s_d, TCG_CALL_NO_RWG, i64, env, i64) DEF_HELPER_FLAGS_2(fcvt_d_s, TCG_CALL_NO_RWG, i64, env, i64) DEF_HELPER_FLAGS_2(fsqrt_d, TCG_CALL_NO_RWG, i64, env, i64) DEF_HELPER_FLAGS_3(fle_d, TCG_CALL_NO_RWG, tl, env, i64, i64) +DEF_HELPER_FLAGS_3(fleq_d, TCG_CALL_NO_RWG, tl, env, i64, i64) DEF_HELPER_FLAGS_3(flt_d, TCG_CALL_NO_RWG, tl, env, i64, i64) +DEF_HELPER_FLAGS_3(fltq_d, TCG_CALL_NO_RWG, tl, env, i64, i64) DEF_HELPER_FLAGS_3(feq_d, TCG_CALL_NO_RWG, tl, env, i64, i64) DEF_HELPER_FLAGS_2(fcvt_w_d, TCG_CALL_NO_RWG, tl, env, i64) +DEF_HELPER_FLAGS_2(fcvtmod_w_d, TCG_CALL_NO_RWG, i64, env, i64) DEF_HELPER_FLAGS_2(fcvt_wu_d, TCG_CALL_NO_RWG, tl, env, i64) DEF_HELPER_FLAGS_2(fcvt_l_d, TCG_CALL_NO_RWG, tl, env, i64) DEF_HELPER_FLAGS_2(fcvt_lu_d, TCG_CALL_NO_RWG, tl, env, i64) @@ -62,6 +73,8 @@ DEF_HELPER_FLAGS_2(fcvt_d_wu, TCG_CALL_NO_RWG, i64, env, tl) DEF_HELPER_FLAGS_2(fcvt_d_l, TCG_CALL_NO_RWG, i64, env, tl) DEF_HELPER_FLAGS_2(fcvt_d_lu, TCG_CALL_NO_RWG, i64, env, tl) DEF_HELPER_FLAGS_1(fclass_d, TCG_CALL_NO_RWG_SE, tl, i64) +DEF_HELPER_FLAGS_2(fround_d, TCG_CALL_NO_RWG_SE, i64, env, i64) +DEF_HELPER_FLAGS_2(froundnx_d, TCG_CALL_NO_RWG_SE, i64, env, i64) /* Bitmanip */ DEF_HELPER_FLAGS_2(clmul, TCG_CALL_NO_RWG_SE, tl, tl, tl) @@ -78,10 +91,14 @@ DEF_HELPER_FLAGS_3(fsub_h, TCG_CALL_NO_RWG, i64, env, i64, i64) DEF_HELPER_FLAGS_3(fmul_h, TCG_CALL_NO_RWG, i64, env, i64, i64) DEF_HELPER_FLAGS_3(fdiv_h, TCG_CALL_NO_RWG, i64, env, i64, i64) DEF_HELPER_FLAGS_3(fmin_h, TCG_CALL_NO_RWG, i64, env, i64, i64) +DEF_HELPER_FLAGS_3(fminm_h, TCG_CALL_NO_RWG, i64, env, i64, i64) DEF_HELPER_FLAGS_3(fmax_h, TCG_CALL_NO_RWG, i64, env, i64, i64) +DEF_HELPER_FLAGS_3(fmaxm_h, TCG_CALL_NO_RWG, i64, env, i64, i64) DEF_HELPER_FLAGS_2(fsqrt_h, TCG_CALL_NO_RWG, i64, env, i64) DEF_HELPER_FLAGS_3(fle_h, TCG_CALL_NO_RWG, tl, env, i64, i64) +DEF_HELPER_FLAGS_3(fleq_h, TCG_CALL_NO_RWG, tl, env, i64, i64) DEF_HELPER_FLAGS_3(flt_h, TCG_CALL_NO_RWG, tl, env, i64, i64) +DEF_HELPER_FLAGS_3(fltq_h, TCG_CALL_NO_RWG, tl, env, i64, i64) DEF_HELPER_FLAGS_3(feq_h, TCG_CALL_NO_RWG, tl, env, i64, i64) DEF_HELPER_FLAGS_2(fcvt_s_h, TCG_CALL_NO_RWG, i64, env, i64) DEF_HELPER_FLAGS_2(fcvt_h_s, TCG_CALL_NO_RWG, i64, env, i64) @@ -96,6 +113,8 @@ DEF_HELPER_FLAGS_2(fcvt_h_wu, TCG_CALL_NO_RWG, i64, env, tl) DEF_HELPER_FLAGS_2(fcvt_h_l, TCG_CALL_NO_RWG, i64, env, tl) DEF_HELPER_FLAGS_2(fcvt_h_lu, TCG_CALL_NO_RWG, i64, env, tl) DEF_HELPER_FLAGS_2(fclass_h, TCG_CALL_NO_RWG_SE, tl, env, i64) +DEF_HELPER_FLAGS_2(fround_h, TCG_CALL_NO_RWG_SE, i64, env, i64) +DEF_HELPER_FLAGS_2(froundnx_h, TCG_CALL_NO_RWG_SE, i64, env, i64) /* Cache-block operations */ DEF_HELPER_2(cbo_clean_flush, void, env, tl) @@ -1153,3 +1172,13 @@ DEF_HELPER_FLAGS_3(sm4ks, TCG_CALL_NO_RWG_SE, tl, tl, tl, tl) /* Zce helper */ DEF_HELPER_FLAGS_2(cm_jalt, TCG_CALL_NO_WG, tl, env, i32) + +/* BF16 functions */ +DEF_HELPER_FLAGS_2(fcvt_bf16_s, TCG_CALL_NO_RWG, i64, env, i64) +DEF_HELPER_FLAGS_2(fcvt_s_bf16, TCG_CALL_NO_RWG, i64, env, i64) + +DEF_HELPER_5(vfncvtbf16_f_f_w, void, ptr, ptr, ptr, env, i32) +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) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 73d5d1b045..e341fa9213 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -821,6 +821,32 @@ binvi 01101. ........... 001 ..... 0010011 @sh bset 0010100 .......... 001 ..... 0110011 @r bseti 00101. ........... 001 ..... 0010011 @sh +# *** Zfa Standard Extension *** +fli_s 1111000 00001 ..... 000 ..... 1010011 @r2 +fli_d 1111001 00001 ..... 000 ..... 1010011 @r2 +fli_h 1111010 00001 ..... 000 ..... 1010011 @r2 +fminm_s 0010100 ..... ..... 010 ..... 1010011 @r +fmaxm_s 0010100 ..... ..... 011 ..... 1010011 @r +fminm_d 0010101 ..... ..... 010 ..... 1010011 @r +fmaxm_d 0010101 ..... ..... 011 ..... 1010011 @r +fminm_h 0010110 ..... ..... 010 ..... 1010011 @r +fmaxm_h 0010110 ..... ..... 011 ..... 1010011 @r +fround_s 0100000 00100 ..... ... ..... 1010011 @r2_rm +froundnx_s 0100000 00101 ..... ... ..... 1010011 @r2_rm +fround_d 0100001 00100 ..... ... ..... 1010011 @r2_rm +froundnx_d 0100001 00101 ..... ... ..... 1010011 @r2_rm +fround_h 0100010 00100 ..... ... ..... 1010011 @r2_rm +froundnx_h 0100010 00101 ..... ... ..... 1010011 @r2_rm +fcvtmod_w_d 1100001 01000 ..... 001 ..... 1010011 @r2 +fmvh_x_d 1110001 00001 ..... 000 ..... 1010011 @r2 +fmvp_d_x 1011001 ..... ..... 000 ..... 1010011 @r +fleq_s 1010000 ..... ..... 100 ..... 1010011 @r +fltq_s 1010000 ..... ..... 101 ..... 1010011 @r +fleq_d 1010001 ..... ..... 100 ..... 1010011 @r +fltq_d 1010001 ..... ..... 101 ..... 1010011 @r +fleq_h 1010010 ..... ..... 100 ..... 1010011 @r +fltq_h 1010010 ..... ..... 101 ..... 1010011 @r + # *** RV32 Zfh Extension *** flh ............ ..... 001 ..... 0000111 @i fsh ....... ..... ..... 001 ..... 0100111 @s @@ -908,3 +934,15 @@ sm4ks .. 11010 ..... ..... 000 ..... 0110011 @k_aes # *** RV32 Zicond Standard Extension *** czero_eqz 0000111 ..... ..... 101 ..... 0110011 @r czero_nez 0000111 ..... ..... 111 ..... 0110011 @r + +# *** Zfbfmin Standard Extension *** +fcvt_bf16_s 0100010 01000 ..... ... ..... 1010011 @r2_rm +fcvt_s_bf16 0100000 00110 ..... ... ..... 1010011 @r2_rm + +# *** Zvfbfmin Standard Extension *** +vfncvtbf16_f_f_w 010010 . ..... 11101 001 ..... 1010111 @r2_vm +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 diff --git a/target/riscv/insn_trans/trans_rvbf16.c.inc b/target/riscv/insn_trans/trans_rvbf16.c.inc new file mode 100644 index 0000000000..911bc29908 --- /dev/null +++ b/target/riscv/insn_trans/trans_rvbf16.c.inc @@ -0,0 +1,175 @@ +/* + * RISC-V translation routines for the BF16 Standard Extensions. + * + * Copyright (c) 2020-2023 PLCT Lab + * + * 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/>. + */ + +#define REQUIRE_ZFBFMIN(ctx) do { \ + if (!ctx->cfg_ptr->ext_zfbfmin) { \ + return false; \ + } \ +} while (0) + +#define REQUIRE_ZVFBFMIN(ctx) do { \ + if (!ctx->cfg_ptr->ext_zvfbfmin) { \ + return false; \ + } \ +} while (0) + +#define REQUIRE_ZVFBFWMA(ctx) do { \ + if (!ctx->cfg_ptr->ext_zvfbfwma) { \ + return false; \ + } \ +} while (0) + +static bool trans_fcvt_bf16_s(DisasContext *ctx, arg_fcvt_bf16_s *a) +{ + REQUIRE_FPU; + REQUIRE_ZFBFMIN(ctx); + + TCGv_i64 dest = dest_fpr(ctx, a->rd); + TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1); + + gen_set_rm(ctx, a->rm); + gen_helper_fcvt_bf16_s(dest, cpu_env, src1); + gen_set_fpr_hs(ctx, a->rd, dest); + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fcvt_s_bf16(DisasContext *ctx, arg_fcvt_s_bf16 *a) +{ + REQUIRE_FPU; + REQUIRE_ZFBFMIN(ctx); + + TCGv_i64 dest = dest_fpr(ctx, a->rd); + TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1); + + gen_set_rm(ctx, a->rm); + gen_helper_fcvt_s_bf16(dest, cpu_env, src1); + gen_set_fpr_hs(ctx, a->rd, dest); + mark_fs_dirty(ctx); + return true; +} + +static bool trans_vfncvtbf16_f_f_w(DisasContext *ctx, arg_vfncvtbf16_f_f_w *a) +{ + REQUIRE_FPU; + REQUIRE_ZVFBFMIN(ctx); + + if (opfv_narrow_check(ctx, a) && (ctx->sew == MO_16)) { + uint32_t data = 0; + TCGLabel *over = gen_new_label(); + + gen_set_rm_chkfrm(ctx, 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); + data = FIELD_DP32(data, VDATA, LMUL, ctx->lmul); + data = FIELD_DP32(data, VDATA, VTA, ctx->vta); + data = FIELD_DP32(data, VDATA, VMA, ctx->vma); + tcg_gen_gvec_3_ptr(vreg_ofs(ctx, a->rd), vreg_ofs(ctx, 0), + vreg_ofs(ctx, a->rs2), cpu_env, + ctx->cfg_ptr->vlen / 8, + ctx->cfg_ptr->vlen / 8, data, + gen_helper_vfncvtbf16_f_f_w); + mark_vs_dirty(ctx); + gen_set_label(over); + return true; + } + return false; +} + +static bool trans_vfwcvtbf16_f_f_v(DisasContext *ctx, arg_vfwcvtbf16_f_f_v *a) +{ + REQUIRE_FPU; + REQUIRE_ZVFBFMIN(ctx); + + if (opfv_widen_check(ctx, a) && (ctx->sew == MO_16)) { + uint32_t data = 0; + TCGLabel *over = gen_new_label(); + + gen_set_rm_chkfrm(ctx, 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); + data = FIELD_DP32(data, VDATA, LMUL, ctx->lmul); + data = FIELD_DP32(data, VDATA, VTA, ctx->vta); + data = FIELD_DP32(data, VDATA, VMA, ctx->vma); + tcg_gen_gvec_3_ptr(vreg_ofs(ctx, a->rd), vreg_ofs(ctx, 0), + vreg_ofs(ctx, a->rs2), cpu_env, + ctx->cfg_ptr->vlen / 8, + ctx->cfg_ptr->vlen / 8, data, + gen_helper_vfwcvtbf16_f_f_v); + mark_vs_dirty(ctx); + gen_set_label(over); + return true; + } + return false; +} + +static bool trans_vfwmaccbf16_vv(DisasContext *ctx, arg_vfwmaccbf16_vv *a) +{ + REQUIRE_FPU; + REQUIRE_ZVFBFWMA(ctx); + + if (require_rvv(ctx) && vext_check_isa_ill(ctx) && (ctx->sew == MO_16) && + vext_check_dss(ctx, a->rd, a->rs1, a->rs2, a->vm)) { + uint32_t data = 0; + TCGLabel *over = gen_new_label(); + + gen_set_rm_chkfrm(ctx, 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); + data = FIELD_DP32(data, VDATA, LMUL, ctx->lmul); + data = FIELD_DP32(data, VDATA, VTA, ctx->vta); + data = FIELD_DP32(data, VDATA, VMA, ctx->vma); + tcg_gen_gvec_4_ptr(vreg_ofs(ctx, a->rd), vreg_ofs(ctx, 0), + vreg_ofs(ctx, a->rs1), + vreg_ofs(ctx, a->rs2), cpu_env, + ctx->cfg_ptr->vlen / 8, + ctx->cfg_ptr->vlen / 8, data, + gen_helper_vfwmaccbf16_vv); + mark_vs_dirty(ctx); + gen_set_label(over); + return true; + } + return false; +} + +static bool trans_vfwmaccbf16_vf(DisasContext *ctx, arg_vfwmaccbf16_vf *a) +{ + REQUIRE_FPU; + REQUIRE_ZVFBFWMA(ctx); + + if (require_rvv(ctx) && (ctx->sew == MO_16) && vext_check_isa_ill(ctx) && + vext_check_ds(ctx, a->rd, a->rs2, a->vm)) { + uint32_t data = 0; + + gen_set_rm(ctx, RISCV_FRM_DYN); + data = FIELD_DP32(data, VDATA, VM, a->vm); + data = FIELD_DP32(data, VDATA, LMUL, ctx->lmul); + data = FIELD_DP32(data, VDATA, VTA, ctx->vta); + data = FIELD_DP32(data, VDATA, VMA, ctx->vma); + return opfvf_trans(a->rd, a->rs1, a->rs2, data, + gen_helper_vfwmaccbf16_vf, ctx); + } + + return false; +} diff --git a/target/riscv/insn_trans/trans_rvzfa.c.inc b/target/riscv/insn_trans/trans_rvzfa.c.inc new file mode 100644 index 0000000000..2c715af3e5 --- /dev/null +++ b/target/riscv/insn_trans/trans_rvzfa.c.inc @@ -0,0 +1,521 @@ +/* + * RISC-V translation routines for the Zfa Standard Extension. + * + * Copyright (c) 2023 Christoph Müllner, christoph.muellner@vrull.eu + * + * 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/>. + */ + +#define REQUIRE_ZFA(ctx) do { \ + if (!ctx->cfg_ptr->ext_zfa) { \ + return false; \ + } \ +} while (0) + +#define REQUIRE_ZFH(ctx) do { \ + if (!ctx->cfg_ptr->ext_zfh) { \ + return false; \ + } \ +} while (0) + +static bool trans_fli_s(DisasContext *ctx, arg_fli_s *a) +{ + REQUIRE_FPU; + REQUIRE_ZFA(ctx); + REQUIRE_EXT(ctx, RVF); + + /* Values below are NaN-boxed to avoid a gen_nanbox_s(). */ + static const uint64_t fli_s_table[] = { + 0xffffffffbf800000, /* -1.0 */ + 0xffffffff00800000, /* minimum positive normal */ + 0xffffffff37800000, /* 1.0 * 2^-16 */ + 0xffffffff38000000, /* 1.0 * 2^-15 */ + 0xffffffff3b800000, /* 1.0 * 2^-8 */ + 0xffffffff3c000000, /* 1.0 * 2^-7 */ + 0xffffffff3d800000, /* 1.0 * 2^-4 */ + 0xffffffff3e000000, /* 1.0 * 2^-3 */ + 0xffffffff3e800000, /* 0.25 */ + 0xffffffff3ea00000, /* 0.3125 */ + 0xffffffff3ec00000, /* 0.375 */ + 0xffffffff3ee00000, /* 0.4375 */ + 0xffffffff3f000000, /* 0.5 */ + 0xffffffff3f200000, /* 0.625 */ + 0xffffffff3f400000, /* 0.75 */ + 0xffffffff3f600000, /* 0.875 */ + 0xffffffff3f800000, /* 1.0 */ + 0xffffffff3fa00000, /* 1.25 */ + 0xffffffff3fc00000, /* 1.5 */ + 0xffffffff3fe00000, /* 1.75 */ + 0xffffffff40000000, /* 2.0 */ + 0xffffffff40200000, /* 2.5 */ + 0xffffffff40400000, /* 3 */ + 0xffffffff40800000, /* 4 */ + 0xffffffff41000000, /* 8 */ + 0xffffffff41800000, /* 16 */ + 0xffffffff43000000, /* 2^7 */ + 0xffffffff43800000, /* 2^8 */ + 0xffffffff47000000, /* 2^15 */ + 0xffffffff47800000, /* 2^16 */ + 0xffffffff7f800000, /* +inf */ + 0xffffffff7fc00000, /* Canonical NaN */ + }; + + TCGv_i64 dest = dest_fpr(ctx, a->rd); + tcg_gen_movi_i64(dest, fli_s_table[a->rs1]); + gen_set_fpr_hs(ctx, a->rd, dest); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fli_d(DisasContext *ctx, arg_fli_d *a) +{ + REQUIRE_FPU; + REQUIRE_ZFA(ctx); + REQUIRE_EXT(ctx, RVD); + + static const uint64_t fli_d_table[] = { + 0xbff0000000000000, /* -1.0 */ + 0x0010000000000000, /* minimum positive normal */ + 0x3ef0000000000000, /* 1.0 * 2^-16 */ + 0x3f00000000000000, /* 1.0 * 2^-15 */ + 0x3f70000000000000, /* 1.0 * 2^-8 */ + 0x3f80000000000000, /* 1.0 * 2^-7 */ + 0x3fb0000000000000, /* 1.0 * 2^-4 */ + 0x3fc0000000000000, /* 1.0 * 2^-3 */ + 0x3fd0000000000000, /* 0.25 */ + 0x3fd4000000000000, /* 0.3125 */ + 0x3fd8000000000000, /* 0.375 */ + 0x3fdc000000000000, /* 0.4375 */ + 0x3fe0000000000000, /* 0.5 */ + 0x3fe4000000000000, /* 0.625 */ + 0x3fe8000000000000, /* 0.75 */ + 0x3fec000000000000, /* 0.875 */ + 0x3ff0000000000000, /* 1.0 */ + 0x3ff4000000000000, /* 1.25 */ + 0x3ff8000000000000, /* 1.5 */ + 0x3ffc000000000000, /* 1.75 */ + 0x4000000000000000, /* 2.0 */ + 0x4004000000000000, /* 2.5 */ + 0x4008000000000000, /* 3 */ + 0x4010000000000000, /* 4 */ + 0x4020000000000000, /* 8 */ + 0x4030000000000000, /* 16 */ + 0x4060000000000000, /* 2^7 */ + 0x4070000000000000, /* 2^8 */ + 0x40e0000000000000, /* 2^15 */ + 0x40f0000000000000, /* 2^16 */ + 0x7ff0000000000000, /* +inf */ + 0x7ff8000000000000, /* Canonical NaN */ + }; + + TCGv_i64 dest = dest_fpr(ctx, a->rd); + tcg_gen_movi_i64(dest, fli_d_table[a->rs1]); + gen_set_fpr_d(ctx, a->rd, dest); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fli_h(DisasContext *ctx, arg_fli_h *a) +{ + REQUIRE_FPU; + REQUIRE_ZFA(ctx); + REQUIRE_ZFH(ctx); + + /* Values below are NaN-boxed to avoid a gen_nanbox_h(). */ + static const uint64_t fli_h_table[] = { + 0xffffffffffffbc00, /* -1.0 */ + 0xffffffffffff0400, /* minimum positive normal */ + 0xffffffffffff0100, /* 1.0 * 2^-16 */ + 0xffffffffffff0200, /* 1.0 * 2^-15 */ + 0xffffffffffff1c00, /* 1.0 * 2^-8 */ + 0xffffffffffff2000, /* 1.0 * 2^-7 */ + 0xffffffffffff2c00, /* 1.0 * 2^-4 */ + 0xffffffffffff3000, /* 1.0 * 2^-3 */ + 0xffffffffffff3400, /* 0.25 */ + 0xffffffffffff3500, /* 0.3125 */ + 0xffffffffffff3600, /* 0.375 */ + 0xffffffffffff3700, /* 0.4375 */ + 0xffffffffffff3800, /* 0.5 */ + 0xffffffffffff3900, /* 0.625 */ + 0xffffffffffff3a00, /* 0.75 */ + 0xffffffffffff3b00, /* 0.875 */ + 0xffffffffffff3c00, /* 1.0 */ + 0xffffffffffff3d00, /* 1.25 */ + 0xffffffffffff3e00, /* 1.5 */ + 0xffffffffffff3f00, /* 1.75 */ + 0xffffffffffff4000, /* 2.0 */ + 0xffffffffffff4100, /* 2.5 */ + 0xffffffffffff4200, /* 3 */ + 0xffffffffffff4400, /* 4 */ + 0xffffffffffff4800, /* 8 */ + 0xffffffffffff4c00, /* 16 */ + 0xffffffffffff5800, /* 2^7 */ + 0xffffffffffff5c00, /* 2^8 */ + 0xffffffffffff7800, /* 2^15 */ + 0xffffffffffff7c00, /* 2^16 */ + 0xffffffffffff7c00, /* +inf */ + 0xffffffffffff7e00, /* Canonical NaN */ + }; + + TCGv_i64 dest = dest_fpr(ctx, a->rd); + tcg_gen_movi_i64(dest, fli_h_table[a->rs1]); + gen_set_fpr_hs(ctx, a->rd, dest); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fminm_s(DisasContext *ctx, arg_fminm_s *a) +{ + REQUIRE_FPU; + REQUIRE_ZFA(ctx); + REQUIRE_EXT(ctx, RVF); + + TCGv_i64 dest = dest_fpr(ctx, a->rd); + TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1); + TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2); + + gen_helper_fminm_s(dest, cpu_env, src1, src2); + gen_set_fpr_hs(ctx, a->rd, dest); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fmaxm_s(DisasContext *ctx, arg_fmaxm_s *a) +{ + REQUIRE_FPU; + REQUIRE_ZFA(ctx); + REQUIRE_EXT(ctx, RVF); + + TCGv_i64 dest = dest_fpr(ctx, a->rd); + TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1); + TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2); + + gen_helper_fmaxm_s(dest, cpu_env, src1, src2); + gen_set_fpr_hs(ctx, a->rd, dest); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fminm_d(DisasContext *ctx, arg_fminm_d *a) +{ + REQUIRE_FPU; + REQUIRE_ZFA(ctx); + REQUIRE_EXT(ctx, RVD); + + TCGv_i64 dest = dest_fpr(ctx, a->rd); + TCGv_i64 src1 = get_fpr_d(ctx, a->rs1); + TCGv_i64 src2 = get_fpr_d(ctx, a->rs2); + + gen_helper_fminm_d(dest, cpu_env, src1, src2); + gen_set_fpr_d(ctx, a->rd, dest); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fmaxm_d(DisasContext *ctx, arg_fmaxm_d *a) +{ + REQUIRE_FPU; + REQUIRE_ZFA(ctx); + REQUIRE_EXT(ctx, RVD); + + TCGv_i64 dest = dest_fpr(ctx, a->rd); + TCGv_i64 src1 = get_fpr_d(ctx, a->rs1); + TCGv_i64 src2 = get_fpr_d(ctx, a->rs2); + + gen_helper_fmaxm_d(dest, cpu_env, src1, src2); + gen_set_fpr_d(ctx, a->rd, dest); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fminm_h(DisasContext *ctx, arg_fminm_h *a) +{ + REQUIRE_FPU; + REQUIRE_ZFA(ctx); + REQUIRE_ZFH(ctx); + + TCGv_i64 dest = dest_fpr(ctx, a->rd); + TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1); + TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2); + + gen_helper_fminm_h(dest, cpu_env, src1, src2); + gen_set_fpr_hs(ctx, a->rd, dest); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fmaxm_h(DisasContext *ctx, arg_fmaxm_h *a) +{ + REQUIRE_FPU; + REQUIRE_ZFA(ctx); + REQUIRE_ZFH(ctx); + + TCGv_i64 dest = dest_fpr(ctx, a->rd); + TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1); + TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2); + + gen_helper_fmaxm_h(dest, cpu_env, src1, src2); + gen_set_fpr_hs(ctx, a->rd, dest); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fround_s(DisasContext *ctx, arg_fround_s *a) +{ + REQUIRE_FPU; + REQUIRE_ZFA(ctx); + REQUIRE_EXT(ctx, RVF); + + TCGv_i64 dest = dest_fpr(ctx, a->rd); + TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1); + + gen_set_rm(ctx, a->rm); + gen_helper_fround_s(dest, cpu_env, src1); + gen_set_fpr_hs(ctx, a->rd, dest); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_froundnx_s(DisasContext *ctx, arg_froundnx_s *a) +{ + REQUIRE_FPU; + REQUIRE_ZFA(ctx); + REQUIRE_EXT(ctx, RVF); + + TCGv_i64 dest = dest_fpr(ctx, a->rd); + TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1); + + gen_set_rm(ctx, a->rm); + gen_helper_froundnx_s(dest, cpu_env, src1); + gen_set_fpr_hs(ctx, a->rd, dest); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fround_d(DisasContext *ctx, arg_fround_d *a) +{ + REQUIRE_FPU; + REQUIRE_ZFA(ctx); + REQUIRE_EXT(ctx, RVD); + + TCGv_i64 dest = dest_fpr(ctx, a->rd); + TCGv_i64 src1 = get_fpr_d(ctx, a->rs1); + + gen_set_rm(ctx, a->rm); + gen_helper_fround_d(dest, cpu_env, src1); + gen_set_fpr_hs(ctx, a->rd, dest); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_froundnx_d(DisasContext *ctx, arg_froundnx_d *a) +{ + REQUIRE_FPU; + REQUIRE_ZFA(ctx); + REQUIRE_EXT(ctx, RVD); + + TCGv_i64 dest = dest_fpr(ctx, a->rd); + TCGv_i64 src1 = get_fpr_d(ctx, a->rs1); + + gen_set_rm(ctx, a->rm); + gen_helper_froundnx_d(dest, cpu_env, src1); + gen_set_fpr_hs(ctx, a->rd, dest); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fround_h(DisasContext *ctx, arg_fround_h *a) +{ + REQUIRE_FPU; + REQUIRE_ZFA(ctx); + REQUIRE_ZFH(ctx); + + TCGv_i64 dest = dest_fpr(ctx, a->rd); + TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1); + + gen_set_rm(ctx, a->rm); + gen_helper_fround_h(dest, cpu_env, src1); + gen_set_fpr_hs(ctx, a->rd, dest); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_froundnx_h(DisasContext *ctx, arg_froundnx_h *a) +{ + REQUIRE_FPU; + REQUIRE_ZFA(ctx); + REQUIRE_ZFH(ctx); + + TCGv_i64 dest = dest_fpr(ctx, a->rd); + TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1); + + gen_set_rm(ctx, a->rm); + gen_helper_froundnx_h(dest, cpu_env, src1); + gen_set_fpr_hs(ctx, a->rd, dest); + + mark_fs_dirty(ctx); + return true; +} + +bool trans_fcvtmod_w_d(DisasContext *ctx, arg_fcvtmod_w_d *a) +{ + REQUIRE_FPU; + REQUIRE_ZFA(ctx); + REQUIRE_EXT(ctx, RVD); + + TCGv dst = dest_gpr(ctx, a->rd); + TCGv_i64 src1 = get_fpr_d(ctx, a->rs1); + TCGv_i64 t1 = tcg_temp_new_i64(); + + /* Rounding mode is RTZ. */ + gen_set_rm(ctx, RISCV_FRM_RTZ); + gen_helper_fcvtmod_w_d(t1, cpu_env, src1); + tcg_gen_trunc_i64_tl(dst, t1); + gen_set_gpr(ctx, a->rd, dst); + + return true; +} + +bool trans_fmvh_x_d(DisasContext *ctx, arg_fmvh_x_d *a) +{ + REQUIRE_FPU; + REQUIRE_ZFA(ctx); + REQUIRE_EXT(ctx, RVD); + REQUIRE_32BIT(ctx); + + TCGv dst = dest_gpr(ctx, a->rd); + TCGv_i64 t1 = tcg_temp_new_i64(); + tcg_gen_sari_i64(t1, cpu_fpr[a->rs1], 32); + tcg_gen_trunc_i64_tl(dst, t1); + gen_set_gpr(ctx, a->rd, dst); + return true; +} + +bool trans_fmvp_d_x(DisasContext *ctx, arg_fmvp_d_x *a) +{ + REQUIRE_FPU; + REQUIRE_ZFA(ctx); + REQUIRE_EXT(ctx, RVD); + REQUIRE_32BIT(ctx); + + TCGv src1 = get_gpr(ctx, a->rs1, EXT_NONE); + TCGv src2 = get_gpr(ctx, a->rs2, EXT_NONE); + tcg_gen_concat_tl_i64(cpu_fpr[a->rd], src1, src2); + + mark_fs_dirty(ctx); + return true; +} + +bool trans_fleq_s(DisasContext *ctx, arg_fleq_s *a) +{ + REQUIRE_FPU; + REQUIRE_ZFA(ctx); + REQUIRE_EXT(ctx, RVF); + + TCGv dest = dest_gpr(ctx, a->rd); + TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1); + TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2); + + gen_helper_fleq_s(dest, cpu_env, src1, src2); + gen_set_gpr(ctx, a->rd, dest); + return true; +} + +bool trans_fltq_s(DisasContext *ctx, arg_fltq_s *a) +{ + REQUIRE_FPU; + REQUIRE_ZFA(ctx); + REQUIRE_EXT(ctx, RVF); + + TCGv dest = dest_gpr(ctx, a->rd); + 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_set_gpr(ctx, a->rd, dest); + return true; +} + +bool trans_fleq_d(DisasContext *ctx, arg_fleq_d *a) +{ + REQUIRE_FPU; + REQUIRE_ZFA(ctx); + REQUIRE_EXT(ctx, RVD); + + TCGv dest = dest_gpr(ctx, a->rd); + 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_set_gpr(ctx, a->rd, dest); + return true; +} + +bool trans_fltq_d(DisasContext *ctx, arg_fltq_d *a) +{ + REQUIRE_FPU; + REQUIRE_ZFA(ctx); + REQUIRE_EXT(ctx, RVD); + + TCGv dest = dest_gpr(ctx, a->rd); + 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_set_gpr(ctx, a->rd, dest); + return true; +} + +bool trans_fleq_h(DisasContext *ctx, arg_fleq_h *a) +{ + REQUIRE_FPU; + REQUIRE_ZFA(ctx); + REQUIRE_ZFH(ctx); + + TCGv dest = dest_gpr(ctx, a->rd); + TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1); + TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2); + + gen_helper_fleq_h(dest, cpu_env, src1, src2); + gen_set_gpr(ctx, a->rd, dest); + return true; +} + +bool trans_fltq_h(DisasContext *ctx, arg_fltq_h *a) +{ + REQUIRE_FPU; + REQUIRE_ZFA(ctx); + REQUIRE_ZFH(ctx); + + TCGv dest = dest_gpr(ctx, a->rd); + TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1); + TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2); + + gen_helper_fltq_h(dest, cpu_env, src1, src2); + gen_set_gpr(ctx, a->rd, dest); + return true; +} diff --git a/target/riscv/insn_trans/trans_rvzfh.c.inc b/target/riscv/insn_trans/trans_rvzfh.c.inc index 74dde37ff7..8b1e2519bb 100644 --- a/target/riscv/insn_trans/trans_rvzfh.c.inc +++ b/target/riscv/insn_trans/trans_rvzfh.c.inc @@ -28,8 +28,8 @@ } \ } while (0) -#define REQUIRE_ZFHMIN(ctx) do { \ - if (!ctx->cfg_ptr->ext_zfhmin) { \ +#define REQUIRE_ZFHMIN_OR_ZFBFMIN(ctx) do { \ + if (!ctx->cfg_ptr->ext_zfhmin && !ctx->cfg_ptr->ext_zfbfmin) { \ return false; \ } \ } while (0) @@ -46,7 +46,7 @@ static bool trans_flh(DisasContext *ctx, arg_flh *a) TCGv t0; REQUIRE_FPU; - REQUIRE_ZFHMIN(ctx); + REQUIRE_ZFHMIN_OR_ZFBFMIN(ctx); decode_save_opc(ctx); t0 = get_gpr(ctx, a->rs1, EXT_NONE); @@ -69,7 +69,7 @@ static bool trans_fsh(DisasContext *ctx, arg_fsh *a) TCGv t0; REQUIRE_FPU; - REQUIRE_ZFHMIN(ctx); + REQUIRE_ZFHMIN_OR_ZFBFMIN(ctx); decode_save_opc(ctx); t0 = get_gpr(ctx, a->rs1, EXT_NONE); @@ -574,7 +574,7 @@ static bool trans_fcvt_h_wu(DisasContext *ctx, arg_fcvt_h_wu *a) static bool trans_fmv_x_h(DisasContext *ctx, arg_fmv_x_h *a) { REQUIRE_FPU; - REQUIRE_ZFHMIN(ctx); + REQUIRE_ZFHMIN_OR_ZFBFMIN(ctx); TCGv dest = dest_gpr(ctx, a->rd); @@ -594,7 +594,7 @@ static bool trans_fmv_x_h(DisasContext *ctx, arg_fmv_x_h *a) static bool trans_fmv_h_x(DisasContext *ctx, arg_fmv_h_x *a) { REQUIRE_FPU; - REQUIRE_ZFHMIN(ctx); + REQUIRE_ZFHMIN_OR_ZFBFMIN(ctx); TCGv t0 = get_gpr(ctx, a->rs1, EXT_ZERO); diff --git a/target/riscv/kvm.c b/target/riscv/kvm.c index 0f932a5b96..9d8a8982f9 100644 --- a/target/riscv/kvm.c +++ b/target/riscv/kvm.c @@ -22,8 +22,10 @@ #include <linux/kvm.h> #include "qemu/timer.h" +#include "qapi/error.h" #include "qemu/error-report.h" #include "qemu/main-loop.h" +#include "qapi/visitor.h" #include "sysemu/sysemu.h" #include "sysemu/kvm.h" #include "sysemu/kvm_int.h" @@ -99,12 +101,280 @@ static uint64_t kvm_riscv_reg_id(CPURISCVState *env, uint64_t type, #define KVM_RISCV_SET_TIMER(cs, env, name, reg) \ do { \ - int ret = kvm_set_one_reg(cs, RISCV_TIMER_REG(env, time), ®); \ + int ret = kvm_set_one_reg(cs, RISCV_TIMER_REG(env, name), ®); \ if (ret) { \ abort(); \ } \ } while (0) +typedef struct KVMCPUConfig { + const char *name; + const char *description; + target_ulong offset; + int kvm_reg_id; + bool user_set; + bool supported; +} KVMCPUConfig; + +#define KVM_MISA_CFG(_bit, _reg_id) \ + {.offset = _bit, .kvm_reg_id = _reg_id} + +/* KVM ISA extensions */ +static KVMCPUConfig kvm_misa_ext_cfgs[] = { + KVM_MISA_CFG(RVA, KVM_RISCV_ISA_EXT_A), + KVM_MISA_CFG(RVC, KVM_RISCV_ISA_EXT_C), + KVM_MISA_CFG(RVD, KVM_RISCV_ISA_EXT_D), + KVM_MISA_CFG(RVF, KVM_RISCV_ISA_EXT_F), + KVM_MISA_CFG(RVH, KVM_RISCV_ISA_EXT_H), + KVM_MISA_CFG(RVI, KVM_RISCV_ISA_EXT_I), + KVM_MISA_CFG(RVM, KVM_RISCV_ISA_EXT_M), +}; + +static void kvm_cpu_set_misa_ext_cfg(Object *obj, Visitor *v, + const char *name, + void *opaque, Error **errp) +{ + KVMCPUConfig *misa_ext_cfg = opaque; + target_ulong misa_bit = misa_ext_cfg->offset; + RISCVCPU *cpu = RISCV_CPU(obj); + CPURISCVState *env = &cpu->env; + bool value, host_bit; + + if (!visit_type_bool(v, name, &value, errp)) { + return; + } + + host_bit = env->misa_ext_mask & misa_bit; + + if (value == host_bit) { + return; + } + + if (!value) { + misa_ext_cfg->user_set = true; + return; + } + + /* + * Forbid users to enable extensions that aren't + * available in the hart. + */ + error_setg(errp, "Enabling MISA bit '%s' is not allowed: it's not " + "enabled in the host", misa_ext_cfg->name); +} + +static void kvm_riscv_update_cpu_misa_ext(RISCVCPU *cpu, CPUState *cs) +{ + CPURISCVState *env = &cpu->env; + uint64_t id, reg; + int i, ret; + + for (i = 0; i < ARRAY_SIZE(kvm_misa_ext_cfgs); i++) { + KVMCPUConfig *misa_cfg = &kvm_misa_ext_cfgs[i]; + target_ulong misa_bit = misa_cfg->offset; + + if (!misa_cfg->user_set) { + continue; + } + + /* If we're here we're going to disable the MISA bit */ + reg = 0; + id = kvm_riscv_reg_id(env, KVM_REG_RISCV_ISA_EXT, + misa_cfg->kvm_reg_id); + ret = kvm_set_one_reg(cs, id, ®); + if (ret != 0) { + /* + * We're not checking for -EINVAL because if the bit is about + * to be disabled, it means that it was already enabled by + * KVM. We determined that by fetching the 'isa' register + * during init() time. Any error at this point is worth + * aborting. + */ + error_report("Unable to set KVM reg %s, error %d", + misa_cfg->name, ret); + exit(EXIT_FAILURE); + } + env->misa_ext &= ~misa_bit; + } +} + +#define CPUCFG(_prop) offsetof(struct RISCVCPUConfig, _prop) + +#define KVM_EXT_CFG(_name, _prop, _reg_id) \ + {.name = _name, .offset = CPUCFG(_prop), \ + .kvm_reg_id = _reg_id} + +static KVMCPUConfig kvm_multi_ext_cfgs[] = { + KVM_EXT_CFG("zicbom", ext_icbom, KVM_RISCV_ISA_EXT_ZICBOM), + KVM_EXT_CFG("zicboz", ext_icboz, KVM_RISCV_ISA_EXT_ZICBOZ), + KVM_EXT_CFG("zihintpause", ext_zihintpause, KVM_RISCV_ISA_EXT_ZIHINTPAUSE), + KVM_EXT_CFG("zbb", ext_zbb, KVM_RISCV_ISA_EXT_ZBB), + KVM_EXT_CFG("ssaia", ext_ssaia, KVM_RISCV_ISA_EXT_SSAIA), + KVM_EXT_CFG("sstc", ext_sstc, KVM_RISCV_ISA_EXT_SSTC), + KVM_EXT_CFG("svinval", ext_svinval, KVM_RISCV_ISA_EXT_SVINVAL), + KVM_EXT_CFG("svpbmt", ext_svpbmt, KVM_RISCV_ISA_EXT_SVPBMT), +}; + +static void *kvmconfig_get_cfg_addr(RISCVCPU *cpu, KVMCPUConfig *kvmcfg) +{ + return (void *)&cpu->cfg + kvmcfg->offset; +} + +static void kvm_cpu_cfg_set(RISCVCPU *cpu, KVMCPUConfig *multi_ext, + uint32_t val) +{ + bool *ext_enabled = kvmconfig_get_cfg_addr(cpu, multi_ext); + + *ext_enabled = val; +} + +static uint32_t kvm_cpu_cfg_get(RISCVCPU *cpu, + KVMCPUConfig *multi_ext) +{ + bool *ext_enabled = kvmconfig_get_cfg_addr(cpu, multi_ext); + + return *ext_enabled; +} + +static void kvm_cpu_set_multi_ext_cfg(Object *obj, Visitor *v, + const char *name, + void *opaque, Error **errp) +{ + KVMCPUConfig *multi_ext_cfg = opaque; + RISCVCPU *cpu = RISCV_CPU(obj); + bool value, host_val; + + if (!visit_type_bool(v, name, &value, errp)) { + return; + } + + host_val = kvm_cpu_cfg_get(cpu, multi_ext_cfg); + + /* + * Ignore if the user is setting the same value + * as the host. + */ + if (value == host_val) { + return; + } + + if (!multi_ext_cfg->supported) { + /* + * Error out if the user is trying to enable an + * extension that KVM doesn't support. Ignore + * option otherwise. + */ + if (value) { + error_setg(errp, "KVM does not support disabling extension %s", + multi_ext_cfg->name); + } + + return; + } + + multi_ext_cfg->user_set = true; + kvm_cpu_cfg_set(cpu, multi_ext_cfg, value); +} + +static KVMCPUConfig kvm_cbom_blocksize = { + .name = "cbom_blocksize", + .offset = CPUCFG(cbom_blocksize), + .kvm_reg_id = KVM_REG_RISCV_CONFIG_REG(zicbom_block_size) +}; + +static KVMCPUConfig kvm_cboz_blocksize = { + .name = "cboz_blocksize", + .offset = CPUCFG(cboz_blocksize), + .kvm_reg_id = KVM_REG_RISCV_CONFIG_REG(zicboz_block_size) +}; + +static void kvm_cpu_set_cbomz_blksize(Object *obj, Visitor *v, + const char *name, + void *opaque, Error **errp) +{ + KVMCPUConfig *cbomz_cfg = opaque; + RISCVCPU *cpu = RISCV_CPU(obj); + uint16_t value, *host_val; + + if (!visit_type_uint16(v, name, &value, errp)) { + return; + } + + host_val = kvmconfig_get_cfg_addr(cpu, cbomz_cfg); + + if (value != *host_val) { + error_report("Unable to set %s to a different value than " + "the host (%u)", + cbomz_cfg->name, *host_val); + exit(EXIT_FAILURE); + } + + cbomz_cfg->user_set = true; +} + +static void kvm_riscv_update_cpu_cfg_isa_ext(RISCVCPU *cpu, CPUState *cs) +{ + CPURISCVState *env = &cpu->env; + uint64_t id, reg; + int i, ret; + + for (i = 0; i < ARRAY_SIZE(kvm_multi_ext_cfgs); i++) { + KVMCPUConfig *multi_ext_cfg = &kvm_multi_ext_cfgs[i]; + + if (!multi_ext_cfg->user_set) { + continue; + } + + id = kvm_riscv_reg_id(env, KVM_REG_RISCV_ISA_EXT, + multi_ext_cfg->kvm_reg_id); + reg = kvm_cpu_cfg_get(cpu, multi_ext_cfg); + ret = kvm_set_one_reg(cs, id, ®); + if (ret != 0) { + error_report("Unable to %s extension %s in KVM, error %d", + reg ? "enable" : "disable", + multi_ext_cfg->name, ret); + exit(EXIT_FAILURE); + } + } +} + +static void kvm_riscv_add_cpu_user_properties(Object *cpu_obj) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(kvm_misa_ext_cfgs); i++) { + KVMCPUConfig *misa_cfg = &kvm_misa_ext_cfgs[i]; + int bit = misa_cfg->offset; + + misa_cfg->name = riscv_get_misa_ext_name(bit); + misa_cfg->description = riscv_get_misa_ext_description(bit); + + object_property_add(cpu_obj, misa_cfg->name, "bool", + NULL, + kvm_cpu_set_misa_ext_cfg, + NULL, misa_cfg); + object_property_set_description(cpu_obj, misa_cfg->name, + misa_cfg->description); + } + + for (i = 0; i < ARRAY_SIZE(kvm_multi_ext_cfgs); i++) { + KVMCPUConfig *multi_cfg = &kvm_multi_ext_cfgs[i]; + + object_property_add(cpu_obj, multi_cfg->name, "bool", + NULL, + kvm_cpu_set_multi_ext_cfg, + NULL, multi_cfg); + } + + object_property_add(cpu_obj, "cbom_blocksize", "uint16", + NULL, kvm_cpu_set_cbomz_blksize, + NULL, &kvm_cbom_blocksize); + + object_property_add(cpu_obj, "cboz_blocksize", "uint16", + NULL, kvm_cpu_set_cbomz_blksize, + NULL, &kvm_cboz_blocksize); +} + static int kvm_riscv_get_regs_core(CPUState *cs) { int ret = 0; @@ -309,6 +579,191 @@ static void kvm_riscv_put_regs_timer(CPUState *cs) env->kvm_timer_dirty = false; } +typedef struct KVMScratchCPU { + int kvmfd; + int vmfd; + int cpufd; +} KVMScratchCPU; + +/* + * Heavily inspired by kvm_arm_create_scratch_host_vcpu() + * from target/arm/kvm.c. + */ +static bool kvm_riscv_create_scratch_vcpu(KVMScratchCPU *scratch) +{ + int kvmfd = -1, vmfd = -1, cpufd = -1; + + kvmfd = qemu_open_old("/dev/kvm", O_RDWR); + if (kvmfd < 0) { + goto err; + } + do { + vmfd = ioctl(kvmfd, KVM_CREATE_VM, 0); + } while (vmfd == -1 && errno == EINTR); + if (vmfd < 0) { + goto err; + } + cpufd = ioctl(vmfd, KVM_CREATE_VCPU, 0); + if (cpufd < 0) { + goto err; + } + + scratch->kvmfd = kvmfd; + scratch->vmfd = vmfd; + scratch->cpufd = cpufd; + + return true; + + err: + if (cpufd >= 0) { + close(cpufd); + } + if (vmfd >= 0) { + close(vmfd); + } + if (kvmfd >= 0) { + close(kvmfd); + } + + return false; +} + +static void kvm_riscv_destroy_scratch_vcpu(KVMScratchCPU *scratch) +{ + close(scratch->cpufd); + close(scratch->vmfd); + close(scratch->kvmfd); +} + +static void kvm_riscv_init_machine_ids(RISCVCPU *cpu, KVMScratchCPU *kvmcpu) +{ + CPURISCVState *env = &cpu->env; + struct kvm_one_reg reg; + int ret; + + reg.id = kvm_riscv_reg_id(env, KVM_REG_RISCV_CONFIG, + KVM_REG_RISCV_CONFIG_REG(mvendorid)); + reg.addr = (uint64_t)&cpu->cfg.mvendorid; + ret = ioctl(kvmcpu->cpufd, KVM_GET_ONE_REG, ®); + if (ret != 0) { + error_report("Unable to retrieve mvendorid from host, error %d", ret); + } + + reg.id = kvm_riscv_reg_id(env, KVM_REG_RISCV_CONFIG, + KVM_REG_RISCV_CONFIG_REG(marchid)); + reg.addr = (uint64_t)&cpu->cfg.marchid; + ret = ioctl(kvmcpu->cpufd, KVM_GET_ONE_REG, ®); + if (ret != 0) { + error_report("Unable to retrieve marchid from host, error %d", ret); + } + + reg.id = kvm_riscv_reg_id(env, KVM_REG_RISCV_CONFIG, + KVM_REG_RISCV_CONFIG_REG(mimpid)); + reg.addr = (uint64_t)&cpu->cfg.mimpid; + ret = ioctl(kvmcpu->cpufd, KVM_GET_ONE_REG, ®); + if (ret != 0) { + error_report("Unable to retrieve mimpid from host, error %d", ret); + } +} + +static void kvm_riscv_init_misa_ext_mask(RISCVCPU *cpu, + KVMScratchCPU *kvmcpu) +{ + CPURISCVState *env = &cpu->env; + struct kvm_one_reg reg; + int ret; + + reg.id = kvm_riscv_reg_id(env, KVM_REG_RISCV_CONFIG, + KVM_REG_RISCV_CONFIG_REG(isa)); + reg.addr = (uint64_t)&env->misa_ext_mask; + ret = ioctl(kvmcpu->cpufd, KVM_GET_ONE_REG, ®); + + if (ret) { + error_report("Unable to fetch ISA register from KVM, " + "error %d", ret); + kvm_riscv_destroy_scratch_vcpu(kvmcpu); + exit(EXIT_FAILURE); + } + + env->misa_ext = env->misa_ext_mask; +} + +static void kvm_riscv_read_cbomz_blksize(RISCVCPU *cpu, KVMScratchCPU *kvmcpu, + KVMCPUConfig *cbomz_cfg) +{ + CPURISCVState *env = &cpu->env; + struct kvm_one_reg reg; + int ret; + + reg.id = kvm_riscv_reg_id(env, KVM_REG_RISCV_CONFIG, + cbomz_cfg->kvm_reg_id); + reg.addr = (uint64_t)kvmconfig_get_cfg_addr(cpu, cbomz_cfg); + ret = ioctl(kvmcpu->cpufd, KVM_GET_ONE_REG, ®); + if (ret != 0) { + error_report("Unable to read KVM reg %s, error %d", + cbomz_cfg->name, ret); + exit(EXIT_FAILURE); + } +} + +static void kvm_riscv_init_multiext_cfg(RISCVCPU *cpu, KVMScratchCPU *kvmcpu) +{ + CPURISCVState *env = &cpu->env; + uint64_t val; + int i, ret; + + for (i = 0; i < ARRAY_SIZE(kvm_multi_ext_cfgs); i++) { + KVMCPUConfig *multi_ext_cfg = &kvm_multi_ext_cfgs[i]; + struct kvm_one_reg reg; + + reg.id = kvm_riscv_reg_id(env, KVM_REG_RISCV_ISA_EXT, + multi_ext_cfg->kvm_reg_id); + reg.addr = (uint64_t)&val; + ret = ioctl(kvmcpu->cpufd, KVM_GET_ONE_REG, ®); + if (ret != 0) { + if (errno == EINVAL) { + /* Silently default to 'false' if KVM does not support it. */ + multi_ext_cfg->supported = false; + val = false; + } else { + error_report("Unable to read ISA_EXT KVM register %s, " + "error %d", multi_ext_cfg->name, ret); + kvm_riscv_destroy_scratch_vcpu(kvmcpu); + exit(EXIT_FAILURE); + } + } else { + multi_ext_cfg->supported = true; + } + + kvm_cpu_cfg_set(cpu, multi_ext_cfg, val); + } + + if (cpu->cfg.ext_icbom) { + kvm_riscv_read_cbomz_blksize(cpu, kvmcpu, &kvm_cbom_blocksize); + } + + if (cpu->cfg.ext_icboz) { + kvm_riscv_read_cbomz_blksize(cpu, kvmcpu, &kvm_cboz_blocksize); + } +} + +void kvm_riscv_init_user_properties(Object *cpu_obj) +{ + RISCVCPU *cpu = RISCV_CPU(cpu_obj); + KVMScratchCPU kvmcpu; + + if (!kvm_riscv_create_scratch_vcpu(&kvmcpu)) { + return; + } + + kvm_riscv_add_cpu_user_properties(cpu_obj); + kvm_riscv_init_machine_ids(cpu, &kvmcpu); + kvm_riscv_init_misa_ext_mask(cpu, &kvmcpu); + kvm_riscv_init_multiext_cfg(cpu, &kvmcpu); + + kvm_riscv_destroy_scratch_vcpu(&kvmcpu); +} + const KVMCapabilityInfo kvm_arch_required_capabilities[] = { KVM_CAP_LAST_INFO }; @@ -394,23 +849,49 @@ void kvm_arch_init_irq_routing(KVMState *s) { } -int kvm_arch_init_vcpu(CPUState *cs) +static int kvm_vcpu_set_machine_ids(RISCVCPU *cpu, CPUState *cs) { - int ret = 0; - target_ulong isa; - RISCVCPU *cpu = RISCV_CPU(cs); CPURISCVState *env = &cpu->env; uint64_t id; + int ret; - qemu_add_vm_change_state_handler(kvm_riscv_vm_state_change, cs); + id = kvm_riscv_reg_id(env, KVM_REG_RISCV_CONFIG, + KVM_REG_RISCV_CONFIG_REG(mvendorid)); + ret = kvm_set_one_reg(cs, id, &cpu->cfg.mvendorid); + if (ret != 0) { + return ret; + } id = kvm_riscv_reg_id(env, KVM_REG_RISCV_CONFIG, - KVM_REG_RISCV_CONFIG_REG(isa)); - ret = kvm_get_one_reg(cs, id, &isa); - if (ret) { + KVM_REG_RISCV_CONFIG_REG(marchid)); + ret = kvm_set_one_reg(cs, id, &cpu->cfg.marchid); + if (ret != 0) { return ret; } - env->misa_ext = isa; + + id = kvm_riscv_reg_id(env, KVM_REG_RISCV_CONFIG, + KVM_REG_RISCV_CONFIG_REG(mimpid)); + ret = kvm_set_one_reg(cs, id, &cpu->cfg.mimpid); + + return ret; +} + +int kvm_arch_init_vcpu(CPUState *cs) +{ + int ret = 0; + RISCVCPU *cpu = RISCV_CPU(cs); + + qemu_add_vm_change_state_handler(kvm_riscv_vm_state_change, cs); + + if (!object_dynamic_cast(OBJECT(cpu), TYPE_RISCV_CPU_HOST)) { + ret = kvm_vcpu_set_machine_ids(cpu, cs); + if (ret != 0) { + return ret; + } + } + + kvm_riscv_update_cpu_misa_ext(cpu, cs); + kvm_riscv_update_cpu_cfg_isa_ext(cpu, cs); return ret; } diff --git a/target/riscv/kvm_riscv.h b/target/riscv/kvm_riscv.h index ed281bdce0..e3ba935808 100644 --- a/target/riscv/kvm_riscv.h +++ b/target/riscv/kvm_riscv.h @@ -19,6 +19,7 @@ #ifndef QEMU_KVM_RISCV_H #define QEMU_KVM_RISCV_H +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); diff --git a/target/riscv/op_helper.c b/target/riscv/op_helper.c index f563dc3981..9cdb9cdd06 100644 --- a/target/riscv/op_helper.c +++ b/target/riscv/op_helper.c @@ -335,7 +335,8 @@ target_ulong helper_mret(CPURISCVState *env) riscv_raise_exception(env, RISCV_EXCP_INST_ACCESS_FAULT, GETPC()); } - target_ulong prev_virt = get_field(env->mstatus, MSTATUS_MPV); + target_ulong prev_virt = get_field(env->mstatus, MSTATUS_MPV) && + (prev_priv != PRV_M); mstatus = set_field(mstatus, MSTATUS_MIE, get_field(mstatus, MSTATUS_MPIE)); mstatus = set_field(mstatus, MSTATUS_MPIE, 1); diff --git a/target/riscv/translate.c b/target/riscv/translate.c index 8a33da811e..697df1be9e 100644 --- a/target/riscv/translate.c +++ b/target/riscv/translate.c @@ -64,6 +64,7 @@ typedef struct DisasContext { target_ulong priv_ver; RISCVMXL misa_mxl_max; RISCVMXL xl; + RISCVMXL address_xl; uint32_t misa_ext; uint32_t opcode; RISCVExtStatus mstatus_fs; @@ -121,29 +122,6 @@ static inline bool has_ext(DisasContext *ctx, uint32_t ext) return ctx->misa_ext & ext; } -static bool always_true_p(DisasContext *ctx __attribute__((__unused__))) -{ - return true; -} - -static bool has_xthead_p(DisasContext *ctx __attribute__((__unused__))) -{ - return ctx->cfg_ptr->ext_xtheadba || ctx->cfg_ptr->ext_xtheadbb || - ctx->cfg_ptr->ext_xtheadbs || ctx->cfg_ptr->ext_xtheadcmo || - ctx->cfg_ptr->ext_xtheadcondmov || - ctx->cfg_ptr->ext_xtheadfmemidx || ctx->cfg_ptr->ext_xtheadfmv || - ctx->cfg_ptr->ext_xtheadmac || ctx->cfg_ptr->ext_xtheadmemidx || - ctx->cfg_ptr->ext_xtheadmempair || ctx->cfg_ptr->ext_xtheadsync; -} - -#define MATERIALISE_EXT_PREDICATE(ext) \ - static bool has_ ## ext ## _p(DisasContext *ctx) \ - { \ - return ctx->cfg_ptr->ext_ ## ext ; \ - } - -MATERIALISE_EXT_PREDICATE(XVentanaCondOps); - #ifdef TARGET_RISCV32 #define get_xl(ctx) MXL_RV32 #elif defined(CONFIG_USER_ONLY) @@ -152,6 +130,14 @@ MATERIALISE_EXT_PREDICATE(XVentanaCondOps); #define get_xl(ctx) ((ctx)->xl) #endif +#ifdef TARGET_RISCV32 +#define get_address_xl(ctx) MXL_RV32 +#elif defined(CONFIG_USER_ONLY) +#define get_address_xl(ctx) MXL_RV64 +#else +#define get_address_xl(ctx) ((ctx)->address_xl) +#endif + /* The word size for this machine mode. */ static inline int __attribute__((unused)) get_xlen(DisasContext *ctx) { @@ -598,12 +584,13 @@ static TCGv get_address(DisasContext *ctx, int rs1, int imm) tcg_gen_addi_tl(addr, src1, imm); if (ctx->pm_mask_enabled) { tcg_gen_andc_tl(addr, addr, pm_mask); - } else if (get_xl(ctx) == MXL_RV32) { + } else if (get_address_xl(ctx) == MXL_RV32) { tcg_gen_ext32u_tl(addr, addr); } if (ctx->pm_base_enabled) { tcg_gen_or_tl(addr, addr, pm_base); } + return addr; } @@ -1104,10 +1091,12 @@ static uint32_t opcode_at(DisasContextBase *dcbase, target_ulong pc) #include "insn_trans/trans_rvzicond.c.inc" #include "insn_trans/trans_rvzawrs.c.inc" #include "insn_trans/trans_rvzicbo.c.inc" +#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_privileged.c.inc" #include "insn_trans/trans_svinval.c.inc" +#include "insn_trans/trans_rvbf16.c.inc" #include "decode-xthead.c.inc" #include "insn_trans/trans_xthead.c.inc" #include "insn_trans/trans_xventanacondops.c.inc" @@ -1134,7 +1123,7 @@ static void decode_opc(CPURISCVState *env, DisasContext *ctx, uint16_t opcode) * that are tested in-order until a decoder matches onto the opcode. */ static const struct { - bool (*guard_func)(DisasContext *); + bool (*guard_func)(const RISCVCPUConfig *); bool (*decode_func)(DisasContext *, uint32_t); } decoders[] = { { always_true_p, decode_insn32 }, @@ -1163,7 +1152,7 @@ static void decode_opc(CPURISCVState *env, DisasContext *ctx, uint16_t opcode) ctx->opcode = opcode32; for (size_t i = 0; i < ARRAY_SIZE(decoders); ++i) { - if (decoders[i].guard_func(ctx) && + if (decoders[i].guard_func(ctx->cfg_ptr) && decoders[i].decode_func(ctx, opcode32)) { return; } @@ -1200,6 +1189,7 @@ static void riscv_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) ctx->vl_eq_vlmax = FIELD_EX32(tb_flags, TB_FLAGS, VL_EQ_VLMAX); ctx->misa_mxl_max = env->misa_mxl_max; ctx->xl = FIELD_EX32(tb_flags, TB_FLAGS, XL); + ctx->address_xl = FIELD_EX32(tb_flags, TB_FLAGS, AXL); ctx->cs = cs; ctx->pm_mask_enabled = FIELD_EX32(tb_flags, TB_FLAGS, PM_MASK_ENABLED); ctx->pm_base_enabled = FIELD_EX32(tb_flags, TB_FLAGS, PM_BASE_ENABLED); diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 1e06e7447c..71bb9b4457 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -3554,6 +3554,17 @@ RVVCALL(OPFVF3, vfwmacc_vf_w, WOP_UUU_W, H8, H4, fwmacc32) GEN_VEXT_VF(vfwmacc_vf_h, 4) GEN_VEXT_VF(vfwmacc_vf_w, 8) +static uint32_t fwmaccbf16(uint16_t a, uint16_t b, uint32_t d, float_status *s) +{ + return float32_muladd(bfloat16_to_float32(a, s), + bfloat16_to_float32(b, s), d, 0, s); +} + +RVVCALL(OPFVV3, vfwmaccbf16_vv, WOP_UUU_H, H4, H2, H2, fwmaccbf16) +GEN_VEXT_VV_ENV(vfwmaccbf16_vv, 4) +RVVCALL(OPFVF3, vfwmaccbf16_vf, WOP_UUU_H, H4, H2, fwmacc16) +GEN_VEXT_VF(vfwmaccbf16_vf, 4) + static uint32_t fwnmacc16(uint16_t a, uint16_t b, uint32_t d, float_status *s) { return float32_muladd(float16_to_float32(a, true, s), @@ -4535,6 +4546,9 @@ RVVCALL(OPFVV1, vfwcvt_f_f_v_w, WOP_UU_W, H8, H4, float32_to_float64) GEN_VEXT_V_ENV(vfwcvt_f_f_v_h, 4) GEN_VEXT_V_ENV(vfwcvt_f_f_v_w, 8) +RVVCALL(OPFVV1, vfwcvtbf16_f_f_v, WOP_UU_H, H4, H2, bfloat16_to_float32) +GEN_VEXT_V_ENV(vfwcvtbf16_f_f_v, 4) + /* Narrowing Floating-Point/Integer Type-Convert Instructions */ /* (TD, T2, TX2) */ #define NOP_UU_B uint8_t, uint16_t, uint32_t @@ -4581,6 +4595,9 @@ RVVCALL(OPFVV1, vfncvt_f_f_w_w, NOP_UU_W, H4, H8, float64_to_float32) GEN_VEXT_V_ENV(vfncvt_f_f_w_h, 2) GEN_VEXT_V_ENV(vfncvt_f_f_w_w, 4) +RVVCALL(OPFVV1, vfncvtbf16_f_f_w, NOP_UU_H, H2, H4, float32_to_bfloat16) +GEN_VEXT_V_ENV(vfncvtbf16_f_f_w, 2) + /* * Vector Reduction Operations */ |