diff options
Diffstat (limited to 'target/riscv')
36 files changed, 21363 insertions, 0 deletions
diff --git a/target/riscv/Kconfig b/target/riscv/Kconfig new file mode 100644 index 000000000..b9e5932f1 --- /dev/null +++ b/target/riscv/Kconfig @@ -0,0 +1,5 @@ +config RISCV32 + bool + +config RISCV64 + bool diff --git a/target/riscv/arch_dump.c b/target/riscv/arch_dump.c new file mode 100644 index 000000000..709f621d8 --- /dev/null +++ b/target/riscv/arch_dump.c @@ -0,0 +1,202 @@ +/* Support for writing ELF notes for RISC-V architectures + * + * Copyright (C) 2021 Huawei Technologies Co., Ltd + * + * 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 "cpu.h" +#include "elf.h" +#include "sysemu/dump.h" + +/* struct user_regs_struct from arch/riscv/include/uapi/asm/ptrace.h */ +struct riscv64_user_regs { + uint64_t pc; + uint64_t regs[31]; +} QEMU_PACKED; + +QEMU_BUILD_BUG_ON(sizeof(struct riscv64_user_regs) != 256); + +/* struct elf_prstatus from include/linux/elfcore.h */ +struct riscv64_elf_prstatus { + char pad1[32]; /* 32 == offsetof(struct elf_prstatus, pr_pid) */ + uint32_t pr_pid; + char pad2[76]; /* 76 == offsetof(struct elf_prstatus, pr_reg) - + offsetof(struct elf_prstatus, pr_ppid) */ + struct riscv64_user_regs pr_reg; + char pad3[8]; +} QEMU_PACKED; + +QEMU_BUILD_BUG_ON(sizeof(struct riscv64_elf_prstatus) != 376); + +struct riscv64_note { + Elf64_Nhdr hdr; + char name[8]; /* align_up(sizeof("CORE"), 4) */ + struct riscv64_elf_prstatus prstatus; +} QEMU_PACKED; + +#define RISCV64_NOTE_HEADER_SIZE offsetof(struct riscv64_note, prstatus) +#define RISCV64_PRSTATUS_NOTE_SIZE \ + (RISCV64_NOTE_HEADER_SIZE + sizeof(struct riscv64_elf_prstatus)) + +static void riscv64_note_init(struct riscv64_note *note, DumpState *s, + const char *name, Elf64_Word namesz, + Elf64_Word type, Elf64_Word descsz) +{ + memset(note, 0, sizeof(*note)); + + note->hdr.n_namesz = cpu_to_dump32(s, namesz); + note->hdr.n_descsz = cpu_to_dump32(s, descsz); + note->hdr.n_type = cpu_to_dump32(s, type); + + memcpy(note->name, name, namesz); +} + +int riscv_cpu_write_elf64_note(WriteCoreDumpFunction f, CPUState *cs, + int cpuid, void *opaque) +{ + struct riscv64_note note; + RISCVCPU *cpu = RISCV_CPU(cs); + CPURISCVState *env = &cpu->env; + DumpState *s = opaque; + int ret, i = 0; + const char name[] = "CORE"; + + riscv64_note_init(¬e, s, name, sizeof(name), + NT_PRSTATUS, sizeof(note.prstatus)); + + note.prstatus.pr_pid = cpu_to_dump32(s, cpuid); + + note.prstatus.pr_reg.pc = cpu_to_dump64(s, env->pc); + + for (i = 0; i < 31; i++) { + note.prstatus.pr_reg.regs[i] = cpu_to_dump64(s, env->gpr[i + 1]); + } + + ret = f(¬e, RISCV64_PRSTATUS_NOTE_SIZE, s); + if (ret < 0) { + return -1; + } + + return ret; +} + +struct riscv32_user_regs { + uint32_t pc; + uint32_t regs[31]; +} QEMU_PACKED; + +QEMU_BUILD_BUG_ON(sizeof(struct riscv32_user_regs) != 128); + +struct riscv32_elf_prstatus { + char pad1[24]; /* 24 == offsetof(struct elf_prstatus, pr_pid) */ + uint32_t pr_pid; + char pad2[44]; /* 44 == offsetof(struct elf_prstatus, pr_reg) - + offsetof(struct elf_prstatus, pr_ppid) */ + struct riscv32_user_regs pr_reg; + char pad3[4]; +} QEMU_PACKED; + +QEMU_BUILD_BUG_ON(sizeof(struct riscv32_elf_prstatus) != 204); + +struct riscv32_note { + Elf32_Nhdr hdr; + char name[8]; /* align_up(sizeof("CORE"), 4) */ + struct riscv32_elf_prstatus prstatus; +} QEMU_PACKED; + +#define RISCV32_NOTE_HEADER_SIZE offsetof(struct riscv32_note, prstatus) +#define RISCV32_PRSTATUS_NOTE_SIZE \ + (RISCV32_NOTE_HEADER_SIZE + sizeof(struct riscv32_elf_prstatus)) + +static void riscv32_note_init(struct riscv32_note *note, DumpState *s, + const char *name, Elf32_Word namesz, + Elf32_Word type, Elf32_Word descsz) +{ + memset(note, 0, sizeof(*note)); + + note->hdr.n_namesz = cpu_to_dump32(s, namesz); + note->hdr.n_descsz = cpu_to_dump32(s, descsz); + note->hdr.n_type = cpu_to_dump32(s, type); + + memcpy(note->name, name, namesz); +} + +int riscv_cpu_write_elf32_note(WriteCoreDumpFunction f, CPUState *cs, + int cpuid, void *opaque) +{ + struct riscv32_note note; + RISCVCPU *cpu = RISCV_CPU(cs); + CPURISCVState *env = &cpu->env; + DumpState *s = opaque; + int ret, i; + const char name[] = "CORE"; + + riscv32_note_init(¬e, s, name, sizeof(name), + NT_PRSTATUS, sizeof(note.prstatus)); + + note.prstatus.pr_pid = cpu_to_dump32(s, cpuid); + + note.prstatus.pr_reg.pc = cpu_to_dump32(s, env->pc); + + for (i = 0; i < 31; i++) { + note.prstatus.pr_reg.regs[i] = cpu_to_dump32(s, env->gpr[i + 1]); + } + + ret = f(¬e, RISCV32_PRSTATUS_NOTE_SIZE, s); + if (ret < 0) { + return -1; + } + + return ret; +} + +int cpu_get_dump_info(ArchDumpInfo *info, + const GuestPhysBlockList *guest_phys_blocks) +{ + RISCVCPU *cpu; + CPURISCVState *env; + + if (first_cpu == NULL) { + return -1; + } + cpu = RISCV_CPU(first_cpu); + env = &cpu->env; + + info->d_machine = EM_RISCV; + +#if defined(TARGET_RISCV64) + info->d_class = ELFCLASS64; +#else + info->d_class = ELFCLASS32; +#endif + + info->d_endian = (env->mstatus & MSTATUS_UBE) != 0 + ? ELFDATA2MSB : ELFDATA2LSB; + + return 0; +} + +ssize_t cpu_get_note_size(int class, int machine, int nr_cpus) +{ + size_t note_size; + + if (class == ELFCLASS64) { + note_size = RISCV64_PRSTATUS_NOTE_SIZE; + } else { + note_size = RISCV32_PRSTATUS_NOTE_SIZE; + } + + return note_size * nr_cpus; +} diff --git a/target/riscv/bitmanip_helper.c b/target/riscv/bitmanip_helper.c new file mode 100644 index 000000000..f1b5e5549 --- /dev/null +++ b/target/riscv/bitmanip_helper.c @@ -0,0 +1,51 @@ +/* + * RISC-V Bitmanip Extension Helpers for QEMU. + * + * Copyright (c) 2020 Kito Cheng, kito.cheng@sifive.com + * Copyright (c) 2020 Frank Chang, frank.chang@sifive.com + * Copyright (c) 2021 Philipp Tomsich, philipp.tomsich@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/>. + */ + +#include "qemu/osdep.h" +#include "qemu/host-utils.h" +#include "exec/exec-all.h" +#include "exec/helper-proto.h" +#include "tcg/tcg.h" + +target_ulong HELPER(clmul)(target_ulong rs1, target_ulong rs2) +{ + target_ulong result = 0; + + for (int i = 0; i < TARGET_LONG_BITS; i++) { + if ((rs2 >> i) & 1) { + result ^= (rs1 << i); + } + } + + return result; +} + +target_ulong HELPER(clmulr)(target_ulong rs1, target_ulong rs2) +{ + target_ulong result = 0; + + for (int i = 0; i < TARGET_LONG_BITS; i++) { + if ((rs2 >> i) & 1) { + result ^= (rs1 >> (TARGET_LONG_BITS - i - 1)); + } + } + + return result; +} diff --git a/target/riscv/cpu-param.h b/target/riscv/cpu-param.h new file mode 100644 index 000000000..80eb615f9 --- /dev/null +++ b/target/riscv/cpu-param.h @@ -0,0 +1,32 @@ +/* + * RISC-V cpu parameters for qemu. + * + * Copyright (c) 2017-2018 SiFive, Inc. + * SPDX-License-Identifier: GPL-2.0+ + */ + +#ifndef RISCV_CPU_PARAM_H +#define RISCV_CPU_PARAM_H 1 + +#if defined(TARGET_RISCV64) +# define TARGET_LONG_BITS 64 +# define TARGET_PHYS_ADDR_SPACE_BITS 56 /* 44-bit PPN */ +# define TARGET_VIRT_ADDR_SPACE_BITS 48 /* sv48 */ +#elif defined(TARGET_RISCV32) +# define TARGET_LONG_BITS 32 +# define TARGET_PHYS_ADDR_SPACE_BITS 34 /* 22-bit PPN */ +# define TARGET_VIRT_ADDR_SPACE_BITS 32 /* sv32 */ +#endif +#define TARGET_PAGE_BITS 12 /* 4 KiB Pages */ +/* + * The current MMU Modes are: + * - U mode 0b000 + * - S mode 0b001 + * - M mode 0b011 + * - U mode HLV/HLVX/HSV 0b100 + * - S mode HLV/HLVX/HSV 0b101 + * - M mode HLV/HLVX/HSV 0b111 + */ +#define NB_MMU_MODES 8 + +#endif diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c new file mode 100644 index 000000000..f81299812 --- /dev/null +++ b/target/riscv/cpu.c @@ -0,0 +1,819 @@ +/* + * QEMU RISC-V CPU + * + * Copyright (c) 2016-2017 Sagar Karandikar, sagark@eecs.berkeley.edu + * Copyright (c) 2017-2018 SiFive, Inc. + * + * 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/qemu-print.h" +#include "qemu/ctype.h" +#include "qemu/log.h" +#include "cpu.h" +#include "internals.h" +#include "exec/exec-all.h" +#include "qapi/error.h" +#include "qemu/error-report.h" +#include "hw/qdev-properties.h" +#include "migration/vmstate.h" +#include "fpu/softfloat-helpers.h" + +/* RISC-V CPU definitions */ + +static const char riscv_exts[26] = "IEMAFDQCLBJTPVNSUHKORWXYZG"; + +const char * const riscv_int_regnames[] = { + "x0/zero", "x1/ra", "x2/sp", "x3/gp", "x4/tp", "x5/t0", "x6/t1", + "x7/t2", "x8/s0", "x9/s1", "x10/a0", "x11/a1", "x12/a2", "x13/a3", + "x14/a4", "x15/a5", "x16/a6", "x17/a7", "x18/s2", "x19/s3", "x20/s4", + "x21/s5", "x22/s6", "x23/s7", "x24/s8", "x25/s9", "x26/s10", "x27/s11", + "x28/t3", "x29/t4", "x30/t5", "x31/t6" +}; + +const char * const riscv_fpr_regnames[] = { + "f0/ft0", "f1/ft1", "f2/ft2", "f3/ft3", "f4/ft4", "f5/ft5", + "f6/ft6", "f7/ft7", "f8/fs0", "f9/fs1", "f10/fa0", "f11/fa1", + "f12/fa2", "f13/fa3", "f14/fa4", "f15/fa5", "f16/fa6", "f17/fa7", + "f18/fs2", "f19/fs3", "f20/fs4", "f21/fs5", "f22/fs6", "f23/fs7", + "f24/fs8", "f25/fs9", "f26/fs10", "f27/fs11", "f28/ft8", "f29/ft9", + "f30/ft10", "f31/ft11" +}; + +static const char * const riscv_excp_names[] = { + "misaligned_fetch", + "fault_fetch", + "illegal_instruction", + "breakpoint", + "misaligned_load", + "fault_load", + "misaligned_store", + "fault_store", + "user_ecall", + "supervisor_ecall", + "hypervisor_ecall", + "machine_ecall", + "exec_page_fault", + "load_page_fault", + "reserved", + "store_page_fault", + "reserved", + "reserved", + "reserved", + "reserved", + "guest_exec_page_fault", + "guest_load_page_fault", + "reserved", + "guest_store_page_fault", +}; + +static const char * const riscv_intr_names[] = { + "u_software", + "s_software", + "vs_software", + "m_software", + "u_timer", + "s_timer", + "vs_timer", + "m_timer", + "u_external", + "s_external", + "vs_external", + "m_external", + "reserved", + "reserved", + "reserved", + "reserved" +}; + +const char *riscv_cpu_get_trap_name(target_ulong cause, bool async) +{ + if (async) { + return (cause < ARRAY_SIZE(riscv_intr_names)) ? + riscv_intr_names[cause] : "(unknown)"; + } else { + return (cause < ARRAY_SIZE(riscv_excp_names)) ? + riscv_excp_names[cause] : "(unknown)"; + } +} + +static void set_misa(CPURISCVState *env, RISCVMXL mxl, uint32_t ext) +{ + env->misa_mxl_max = env->misa_mxl = mxl; + env->misa_ext_mask = env->misa_ext = ext; +} + +static void set_priv_version(CPURISCVState *env, int priv_ver) +{ + env->priv_ver = priv_ver; +} + +static void set_vext_version(CPURISCVState *env, int vext_ver) +{ + env->vext_ver = vext_ver; +} + +static void set_feature(CPURISCVState *env, int feature) +{ + env->features |= (1ULL << feature); +} + +static void set_resetvec(CPURISCVState *env, target_ulong resetvec) +{ +#ifndef CONFIG_USER_ONLY + env->resetvec = resetvec; +#endif +} + +static void riscv_any_cpu_init(Object *obj) +{ + CPURISCVState *env = &RISCV_CPU(obj)->env; +#if defined(TARGET_RISCV32) + set_misa(env, MXL_RV32, RVI | RVM | RVA | RVF | RVD | RVC | RVU); +#elif defined(TARGET_RISCV64) + set_misa(env, MXL_RV64, RVI | RVM | RVA | RVF | RVD | RVC | RVU); +#endif + set_priv_version(env, PRIV_VERSION_1_11_0); +} + +#if defined(TARGET_RISCV64) +static void rv64_base_cpu_init(Object *obj) +{ + CPURISCVState *env = &RISCV_CPU(obj)->env; + /* We set this in the realise function */ + set_misa(env, MXL_RV64, 0); +} + +static void rv64_sifive_u_cpu_init(Object *obj) +{ + CPURISCVState *env = &RISCV_CPU(obj)->env; + set_misa(env, MXL_RV64, RVI | RVM | RVA | RVF | RVD | RVC | RVS | RVU); + set_priv_version(env, PRIV_VERSION_1_10_0); +} + +static void rv64_sifive_e_cpu_init(Object *obj) +{ + CPURISCVState *env = &RISCV_CPU(obj)->env; + set_misa(env, MXL_RV64, RVI | RVM | RVA | RVC | RVU); + set_priv_version(env, PRIV_VERSION_1_10_0); + qdev_prop_set_bit(DEVICE(obj), "mmu", false); +} +#else +static void rv32_base_cpu_init(Object *obj) +{ + CPURISCVState *env = &RISCV_CPU(obj)->env; + /* We set this in the realise function */ + set_misa(env, MXL_RV32, 0); +} + +static void rv32_sifive_u_cpu_init(Object *obj) +{ + CPURISCVState *env = &RISCV_CPU(obj)->env; + set_misa(env, MXL_RV32, RVI | RVM | RVA | RVF | RVD | RVC | RVS | RVU); + set_priv_version(env, PRIV_VERSION_1_10_0); +} + +static void rv32_sifive_e_cpu_init(Object *obj) +{ + CPURISCVState *env = &RISCV_CPU(obj)->env; + set_misa(env, MXL_RV32, RVI | RVM | RVA | RVC | RVU); + set_priv_version(env, PRIV_VERSION_1_10_0); + qdev_prop_set_bit(DEVICE(obj), "mmu", false); +} + +static void rv32_ibex_cpu_init(Object *obj) +{ + CPURISCVState *env = &RISCV_CPU(obj)->env; + set_misa(env, MXL_RV32, RVI | RVM | RVC | RVU); + set_priv_version(env, PRIV_VERSION_1_10_0); + qdev_prop_set_bit(DEVICE(obj), "mmu", false); + qdev_prop_set_bit(DEVICE(obj), "x-epmp", true); +} + +static void rv32_imafcu_nommu_cpu_init(Object *obj) +{ + CPURISCVState *env = &RISCV_CPU(obj)->env; + set_misa(env, MXL_RV32, RVI | RVM | RVA | RVF | RVC | RVU); + set_priv_version(env, PRIV_VERSION_1_10_0); + set_resetvec(env, DEFAULT_RSTVEC); + qdev_prop_set_bit(DEVICE(obj), "mmu", false); +} +#endif + +static ObjectClass *riscv_cpu_class_by_name(const char *cpu_model) +{ + ObjectClass *oc; + char *typename; + char **cpuname; + + cpuname = g_strsplit(cpu_model, ",", 1); + typename = g_strdup_printf(RISCV_CPU_TYPE_NAME("%s"), cpuname[0]); + oc = object_class_by_name(typename); + g_strfreev(cpuname); + g_free(typename); + if (!oc || !object_class_dynamic_cast(oc, TYPE_RISCV_CPU) || + object_class_is_abstract(oc)) { + return NULL; + } + return oc; +} + +static void riscv_cpu_dump_state(CPUState *cs, FILE *f, int flags) +{ + RISCVCPU *cpu = RISCV_CPU(cs); + CPURISCVState *env = &cpu->env; + int i; + +#if !defined(CONFIG_USER_ONLY) + if (riscv_has_ext(env, RVH)) { + qemu_fprintf(f, " %s %d\n", "V = ", riscv_cpu_virt_enabled(env)); + } +#endif + qemu_fprintf(f, " %s " TARGET_FMT_lx "\n", "pc ", env->pc); +#ifndef CONFIG_USER_ONLY + { + static const int dump_csrs[] = { + CSR_MHARTID, + CSR_MSTATUS, + CSR_MSTATUSH, + CSR_HSTATUS, + CSR_VSSTATUS, + CSR_MIP, + CSR_MIE, + CSR_MIDELEG, + CSR_HIDELEG, + CSR_MEDELEG, + CSR_HEDELEG, + CSR_MTVEC, + CSR_STVEC, + CSR_VSTVEC, + CSR_MEPC, + CSR_SEPC, + CSR_VSEPC, + CSR_MCAUSE, + CSR_SCAUSE, + CSR_VSCAUSE, + CSR_MTVAL, + CSR_STVAL, + CSR_HTVAL, + CSR_MTVAL2, + CSR_MSCRATCH, + CSR_SSCRATCH, + CSR_SATP, + CSR_MMTE, + CSR_UPMBASE, + CSR_UPMMASK, + CSR_SPMBASE, + CSR_SPMMASK, + CSR_MPMBASE, + CSR_MPMMASK, + }; + + for (int i = 0; i < ARRAY_SIZE(dump_csrs); ++i) { + int csrno = dump_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); + } + } + } +#endif + + for (i = 0; i < 32; i++) { + qemu_fprintf(f, " %-8s " TARGET_FMT_lx, + riscv_int_regnames[i], env->gpr[i]); + if ((i & 3) == 3) { + qemu_fprintf(f, "\n"); + } + } + if (flags & CPU_DUMP_FPU) { + for (i = 0; i < 32; i++) { + qemu_fprintf(f, " %-8s %016" PRIx64, + riscv_fpr_regnames[i], env->fpr[i]); + if ((i & 3) == 3) { + qemu_fprintf(f, "\n"); + } + } + } +} + +static void riscv_cpu_set_pc(CPUState *cs, vaddr value) +{ + RISCVCPU *cpu = RISCV_CPU(cs); + CPURISCVState *env = &cpu->env; + env->pc = value; +} + +static void riscv_cpu_synchronize_from_tb(CPUState *cs, + const TranslationBlock *tb) +{ + RISCVCPU *cpu = RISCV_CPU(cs); + CPURISCVState *env = &cpu->env; + env->pc = tb->pc; +} + +static bool riscv_cpu_has_work(CPUState *cs) +{ +#ifndef CONFIG_USER_ONLY + RISCVCPU *cpu = RISCV_CPU(cs); + CPURISCVState *env = &cpu->env; + /* + * Definition of the WFI instruction requires it to ignore the privilege + * mode and delegation registers, but respect individual enables + */ + return (env->mip & env->mie) != 0; +#else + return true; +#endif +} + +void restore_state_to_opc(CPURISCVState *env, TranslationBlock *tb, + target_ulong *data) +{ + env->pc = data[0]; +} + +static void riscv_cpu_reset(DeviceState *dev) +{ + CPUState *cs = CPU(dev); + RISCVCPU *cpu = RISCV_CPU(cs); + RISCVCPUClass *mcc = RISCV_CPU_GET_CLASS(cpu); + CPURISCVState *env = &cpu->env; + + mcc->parent_reset(dev); +#ifndef CONFIG_USER_ONLY + env->misa_mxl = env->misa_mxl_max; + env->priv = PRV_M; + env->mstatus &= ~(MSTATUS_MIE | MSTATUS_MPRV); + if (env->misa_mxl > MXL_RV32) { + /* + * The reset status of SXL/UXL is undefined, but mstatus is WARL + * and we must ensure that the value after init is valid for read. + */ + env->mstatus = set_field(env->mstatus, MSTATUS64_SXL, env->misa_mxl); + env->mstatus = set_field(env->mstatus, MSTATUS64_UXL, env->misa_mxl); + } + env->mcause = 0; + env->pc = env->resetvec; + env->two_stage_lookup = false; + /* mmte is supposed to have pm.current hardwired to 1 */ + env->mmte |= (PM_EXT_INITIAL | MMTE_M_PM_CURRENT); +#endif + cs->exception_index = RISCV_EXCP_NONE; + env->load_res = -1; + set_default_nan_mode(1, &env->fp_status); +} + +static void riscv_cpu_disas_set_info(CPUState *s, disassemble_info *info) +{ + RISCVCPU *cpu = RISCV_CPU(s); + + switch (riscv_cpu_mxl(&cpu->env)) { + case MXL_RV32: + info->print_insn = print_insn_riscv32; + break; + case MXL_RV64: + info->print_insn = print_insn_riscv64; + break; + default: + g_assert_not_reached(); + } +} + +static void riscv_cpu_realize(DeviceState *dev, Error **errp) +{ + CPUState *cs = CPU(dev); + RISCVCPU *cpu = RISCV_CPU(dev); + CPURISCVState *env = &cpu->env; + RISCVCPUClass *mcc = RISCV_CPU_GET_CLASS(dev); + int priv_version = 0; + Error *local_err = NULL; + + cpu_exec_realizefn(cs, &local_err); + if (local_err != NULL) { + error_propagate(errp, local_err); + return; + } + + if (cpu->cfg.priv_spec) { + if (!g_strcmp0(cpu->cfg.priv_spec, "v1.11.0")) { + priv_version = PRIV_VERSION_1_11_0; + } else if (!g_strcmp0(cpu->cfg.priv_spec, "v1.10.0")) { + priv_version = PRIV_VERSION_1_10_0; + } else { + error_setg(errp, + "Unsupported privilege spec version '%s'", + cpu->cfg.priv_spec); + return; + } + } + + if (priv_version) { + set_priv_version(env, priv_version); + } else if (!env->priv_ver) { + set_priv_version(env, PRIV_VERSION_1_11_0); + } + + if (cpu->cfg.mmu) { + set_feature(env, RISCV_FEATURE_MMU); + } + + if (cpu->cfg.pmp) { + set_feature(env, RISCV_FEATURE_PMP); + + /* + * Enhanced PMP should only be available + * on harts with PMP support + */ + if (cpu->cfg.epmp) { + set_feature(env, RISCV_FEATURE_EPMP); + } + } + + set_resetvec(env, cpu->cfg.resetvec); + + /* Validate that MISA_MXL is set properly. */ + switch (env->misa_mxl_max) { +#ifdef TARGET_RISCV64 + case MXL_RV64: + break; +#endif + case MXL_RV32: + break; + default: + g_assert_not_reached(); + } + assert(env->misa_mxl_max == env->misa_mxl); + + /* If only MISA_EXT is unset for misa, then set it from properties */ + if (env->misa_ext == 0) { + uint32_t ext = 0; + + /* Do some ISA extension error checking */ + if (cpu->cfg.ext_i && cpu->cfg.ext_e) { + error_setg(errp, + "I and E extensions are incompatible"); + return; + } + + if (!cpu->cfg.ext_i && !cpu->cfg.ext_e) { + error_setg(errp, + "Either I or E extension must be set"); + return; + } + + if (cpu->cfg.ext_g && !(cpu->cfg.ext_i & cpu->cfg.ext_m & + cpu->cfg.ext_a & cpu->cfg.ext_f & + cpu->cfg.ext_d)) { + warn_report("Setting G will also set IMAFD"); + cpu->cfg.ext_i = true; + cpu->cfg.ext_m = true; + cpu->cfg.ext_a = true; + cpu->cfg.ext_f = true; + cpu->cfg.ext_d = true; + } + + /* Set the ISA extensions, checks should have happened above */ + if (cpu->cfg.ext_i) { + ext |= RVI; + } + if (cpu->cfg.ext_e) { + ext |= RVE; + } + if (cpu->cfg.ext_m) { + ext |= RVM; + } + if (cpu->cfg.ext_a) { + ext |= RVA; + } + if (cpu->cfg.ext_f) { + ext |= RVF; + } + if (cpu->cfg.ext_d) { + ext |= RVD; + } + if (cpu->cfg.ext_c) { + ext |= RVC; + } + if (cpu->cfg.ext_s) { + ext |= RVS; + } + if (cpu->cfg.ext_u) { + ext |= RVU; + } + if (cpu->cfg.ext_h) { + ext |= RVH; + } + if (cpu->cfg.ext_v) { + int vext_version = VEXT_VERSION_0_07_1; + ext |= RVV; + if (!is_power_of_2(cpu->cfg.vlen)) { + error_setg(errp, + "Vector extension VLEN must be power of 2"); + return; + } + if (cpu->cfg.vlen > RV_VLEN_MAX || cpu->cfg.vlen < 128) { + error_setg(errp, + "Vector extension implementation only supports VLEN " + "in the range [128, %d]", RV_VLEN_MAX); + return; + } + if (!is_power_of_2(cpu->cfg.elen)) { + error_setg(errp, + "Vector extension ELEN must be power of 2"); + return; + } + if (cpu->cfg.elen > 64 || cpu->cfg.vlen < 8) { + error_setg(errp, + "Vector extension implementation only supports ELEN " + "in the range [8, 64]"); + return; + } + if (cpu->cfg.vext_spec) { + if (!g_strcmp0(cpu->cfg.vext_spec, "v0.7.1")) { + vext_version = VEXT_VERSION_0_07_1; + } else { + error_setg(errp, + "Unsupported vector spec version '%s'", + cpu->cfg.vext_spec); + return; + } + } else { + qemu_log("vector version is not specified, " + "use the default value v0.7.1\n"); + } + set_vext_version(env, vext_version); + } + if (cpu->cfg.ext_j) { + ext |= RVJ; + } + + set_misa(env, env->misa_mxl, ext); + } + + riscv_cpu_register_gdb_regs_for_features(cs); + + qemu_init_vcpu(cs); + cpu_reset(cs); + + mcc->parent_realize(dev, errp); +} + +#ifndef CONFIG_USER_ONLY +static void riscv_cpu_set_irq(void *opaque, int irq, int level) +{ + RISCVCPU *cpu = RISCV_CPU(opaque); + + switch (irq) { + case IRQ_U_SOFT: + case IRQ_S_SOFT: + case IRQ_VS_SOFT: + case IRQ_M_SOFT: + case IRQ_U_TIMER: + case IRQ_S_TIMER: + case IRQ_VS_TIMER: + case IRQ_M_TIMER: + case IRQ_U_EXT: + case IRQ_S_EXT: + case IRQ_VS_EXT: + case IRQ_M_EXT: + riscv_cpu_update_mip(cpu, 1 << irq, BOOL_TO_MASK(level)); + break; + default: + g_assert_not_reached(); + } +} +#endif /* CONFIG_USER_ONLY */ + +static void riscv_cpu_init(Object *obj) +{ + RISCVCPU *cpu = RISCV_CPU(obj); + + cpu_set_cpustate_pointers(cpu); + +#ifndef CONFIG_USER_ONLY + qdev_init_gpio_in(DEVICE(cpu), riscv_cpu_set_irq, 12); +#endif /* CONFIG_USER_ONLY */ +} + +static Property riscv_cpu_properties[] = { + /* Defaults for standard extensions */ + DEFINE_PROP_BOOL("i", RISCVCPU, cfg.ext_i, true), + DEFINE_PROP_BOOL("e", RISCVCPU, cfg.ext_e, false), + DEFINE_PROP_BOOL("g", RISCVCPU, cfg.ext_g, true), + DEFINE_PROP_BOOL("m", RISCVCPU, cfg.ext_m, true), + DEFINE_PROP_BOOL("a", RISCVCPU, cfg.ext_a, true), + DEFINE_PROP_BOOL("f", RISCVCPU, cfg.ext_f, true), + DEFINE_PROP_BOOL("d", RISCVCPU, cfg.ext_d, true), + DEFINE_PROP_BOOL("c", RISCVCPU, cfg.ext_c, true), + DEFINE_PROP_BOOL("s", RISCVCPU, cfg.ext_s, true), + DEFINE_PROP_BOOL("u", RISCVCPU, cfg.ext_u, true), + DEFINE_PROP_BOOL("Counters", RISCVCPU, cfg.ext_counters, true), + DEFINE_PROP_BOOL("Zifencei", RISCVCPU, cfg.ext_ifencei, true), + DEFINE_PROP_BOOL("Zicsr", RISCVCPU, cfg.ext_icsr, true), + DEFINE_PROP_BOOL("mmu", RISCVCPU, cfg.mmu, true), + DEFINE_PROP_BOOL("pmp", RISCVCPU, cfg.pmp, true), + + DEFINE_PROP_STRING("priv_spec", RISCVCPU, cfg.priv_spec), + + /* These are experimental so mark with 'x-' */ + DEFINE_PROP_BOOL("x-zba", RISCVCPU, cfg.ext_zba, false), + DEFINE_PROP_BOOL("x-zbb", RISCVCPU, cfg.ext_zbb, false), + DEFINE_PROP_BOOL("x-zbc", RISCVCPU, cfg.ext_zbc, false), + DEFINE_PROP_BOOL("x-zbs", RISCVCPU, cfg.ext_zbs, false), + DEFINE_PROP_BOOL("x-h", RISCVCPU, cfg.ext_h, false), + DEFINE_PROP_BOOL("x-j", RISCVCPU, cfg.ext_j, false), + DEFINE_PROP_BOOL("x-v", RISCVCPU, cfg.ext_v, false), + DEFINE_PROP_STRING("vext_spec", RISCVCPU, cfg.vext_spec), + DEFINE_PROP_UINT16("vlen", RISCVCPU, cfg.vlen, 128), + DEFINE_PROP_UINT16("elen", RISCVCPU, cfg.elen, 64), + /* ePMP 0.9.3 */ + DEFINE_PROP_BOOL("x-epmp", RISCVCPU, cfg.epmp, false), + + DEFINE_PROP_UINT64("resetvec", RISCVCPU, cfg.resetvec, DEFAULT_RSTVEC), + DEFINE_PROP_END_OF_LIST(), +}; + +static gchar *riscv_gdb_arch_name(CPUState *cs) +{ + RISCVCPU *cpu = RISCV_CPU(cs); + CPURISCVState *env = &cpu->env; + + switch (riscv_cpu_mxl(env)) { + case MXL_RV32: + return g_strdup("riscv:rv32"); + case MXL_RV64: + return g_strdup("riscv:rv64"); + default: + g_assert_not_reached(); + } +} + +static const char *riscv_gdb_get_dynamic_xml(CPUState *cs, const char *xmlname) +{ + RISCVCPU *cpu = RISCV_CPU(cs); + + if (strcmp(xmlname, "riscv-csr.xml") == 0) { + return cpu->dyn_csr_xml; + } + + return NULL; +} + +#ifndef CONFIG_USER_ONLY +#include "hw/core/sysemu-cpu-ops.h" + +static const struct SysemuCPUOps riscv_sysemu_ops = { + .get_phys_page_debug = riscv_cpu_get_phys_page_debug, + .write_elf64_note = riscv_cpu_write_elf64_note, + .write_elf32_note = riscv_cpu_write_elf32_note, + .legacy_vmsd = &vmstate_riscv_cpu, +}; +#endif + +#include "hw/core/tcg-cpu-ops.h" + +static const struct TCGCPUOps riscv_tcg_ops = { + .initialize = riscv_translate_init, + .synchronize_from_tb = riscv_cpu_synchronize_from_tb, + +#ifndef CONFIG_USER_ONLY + .tlb_fill = riscv_cpu_tlb_fill, + .cpu_exec_interrupt = riscv_cpu_exec_interrupt, + .do_interrupt = riscv_cpu_do_interrupt, + .do_transaction_failed = riscv_cpu_do_transaction_failed, + .do_unaligned_access = riscv_cpu_do_unaligned_access, +#endif /* !CONFIG_USER_ONLY */ +}; + +static void riscv_cpu_class_init(ObjectClass *c, void *data) +{ + RISCVCPUClass *mcc = RISCV_CPU_CLASS(c); + CPUClass *cc = CPU_CLASS(c); + DeviceClass *dc = DEVICE_CLASS(c); + + device_class_set_parent_realize(dc, riscv_cpu_realize, + &mcc->parent_realize); + + device_class_set_parent_reset(dc, riscv_cpu_reset, &mcc->parent_reset); + + cc->class_by_name = riscv_cpu_class_by_name; + cc->has_work = riscv_cpu_has_work; + cc->dump_state = riscv_cpu_dump_state; + cc->set_pc = riscv_cpu_set_pc; + cc->gdb_read_register = riscv_cpu_gdb_read_register; + cc->gdb_write_register = riscv_cpu_gdb_write_register; + cc->gdb_num_core_regs = 33; +#if defined(TARGET_RISCV32) + cc->gdb_core_xml_file = "riscv-32bit-cpu.xml"; +#elif defined(TARGET_RISCV64) + cc->gdb_core_xml_file = "riscv-64bit-cpu.xml"; +#endif + cc->gdb_stop_before_watchpoint = true; + cc->disas_set_info = riscv_cpu_disas_set_info; +#ifndef CONFIG_USER_ONLY + cc->sysemu_ops = &riscv_sysemu_ops; +#endif + cc->gdb_arch_name = riscv_gdb_arch_name; + cc->gdb_get_dynamic_xml = riscv_gdb_get_dynamic_xml; + cc->tcg_ops = &riscv_tcg_ops; + + device_class_set_props(dc, riscv_cpu_properties); +} + +char *riscv_isa_string(RISCVCPU *cpu) +{ + int i; + const size_t maxlen = sizeof("rv128") + sizeof(riscv_exts) + 1; + char *isa_str = g_new(char, maxlen); + char *p = isa_str + snprintf(isa_str, maxlen, "rv%d", TARGET_LONG_BITS); + for (i = 0; i < sizeof(riscv_exts); i++) { + if (cpu->env.misa_ext & RV(riscv_exts[i])) { + *p++ = qemu_tolower(riscv_exts[i]); + } + } + *p = '\0'; + return isa_str; +} + +static gint riscv_cpu_list_compare(gconstpointer a, gconstpointer b) +{ + ObjectClass *class_a = (ObjectClass *)a; + ObjectClass *class_b = (ObjectClass *)b; + const char *name_a, *name_b; + + name_a = object_class_get_name(class_a); + name_b = object_class_get_name(class_b); + return strcmp(name_a, name_b); +} + +static void riscv_cpu_list_entry(gpointer data, gpointer user_data) +{ + const char *typename = object_class_get_name(OBJECT_CLASS(data)); + int len = strlen(typename) - strlen(RISCV_CPU_TYPE_SUFFIX); + + qemu_printf("%.*s\n", len, typename); +} + +void riscv_cpu_list(void) +{ + GSList *list; + + list = object_class_get_list(TYPE_RISCV_CPU, false); + list = g_slist_sort(list, riscv_cpu_list_compare); + g_slist_foreach(list, riscv_cpu_list_entry, NULL); + g_slist_free(list); +} + +#define DEFINE_CPU(type_name, initfn) \ + { \ + .name = type_name, \ + .parent = TYPE_RISCV_CPU, \ + .instance_init = initfn \ + } + +static const TypeInfo riscv_cpu_type_infos[] = { + { + .name = TYPE_RISCV_CPU, + .parent = TYPE_CPU, + .instance_size = sizeof(RISCVCPU), + .instance_align = __alignof__(RISCVCPU), + .instance_init = riscv_cpu_init, + .abstract = true, + .class_size = sizeof(RISCVCPUClass), + .class_init = riscv_cpu_class_init, + }, + DEFINE_CPU(TYPE_RISCV_CPU_ANY, riscv_any_cpu_init), +#if defined(TARGET_RISCV32) + DEFINE_CPU(TYPE_RISCV_CPU_BASE32, rv32_base_cpu_init), + DEFINE_CPU(TYPE_RISCV_CPU_IBEX, rv32_ibex_cpu_init), + DEFINE_CPU(TYPE_RISCV_CPU_SIFIVE_E31, rv32_sifive_e_cpu_init), + DEFINE_CPU(TYPE_RISCV_CPU_SIFIVE_E34, rv32_imafcu_nommu_cpu_init), + DEFINE_CPU(TYPE_RISCV_CPU_SIFIVE_U34, rv32_sifive_u_cpu_init), +#elif defined(TARGET_RISCV64) + DEFINE_CPU(TYPE_RISCV_CPU_BASE64, rv64_base_cpu_init), + DEFINE_CPU(TYPE_RISCV_CPU_SIFIVE_E51, rv64_sifive_e_cpu_init), + DEFINE_CPU(TYPE_RISCV_CPU_SIFIVE_U54, rv64_sifive_u_cpu_init), + DEFINE_CPU(TYPE_RISCV_CPU_SHAKTI_C, rv64_sifive_u_cpu_init), +#endif +}; + +DEFINE_TYPES(riscv_cpu_type_infos) diff --git a/target/riscv/cpu.h b/target/riscv/cpu.h new file mode 100644 index 000000000..0760c0af9 --- /dev/null +++ b/target/riscv/cpu.h @@ -0,0 +1,495 @@ +/* + * QEMU RISC-V CPU + * + * Copyright (c) 2016-2017 Sagar Karandikar, sagark@eecs.berkeley.edu + * Copyright (c) 2017-2018 SiFive, Inc. + * + * 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 RISCV_CPU_H +#define RISCV_CPU_H + +#include "hw/core/cpu.h" +#include "hw/registerfields.h" +#include "exec/cpu-defs.h" +#include "fpu/softfloat-types.h" +#include "qom/object.h" +#include "cpu_bits.h" + +#define TCG_GUEST_DEFAULT_MO 0 + +#define TYPE_RISCV_CPU "riscv-cpu" + +#define RISCV_CPU_TYPE_SUFFIX "-" TYPE_RISCV_CPU +#define RISCV_CPU_TYPE_NAME(name) (name RISCV_CPU_TYPE_SUFFIX) +#define CPU_RESOLVING_TYPE TYPE_RISCV_CPU + +#define TYPE_RISCV_CPU_ANY RISCV_CPU_TYPE_NAME("any") +#define TYPE_RISCV_CPU_BASE32 RISCV_CPU_TYPE_NAME("rv32") +#define TYPE_RISCV_CPU_BASE64 RISCV_CPU_TYPE_NAME("rv64") +#define TYPE_RISCV_CPU_IBEX RISCV_CPU_TYPE_NAME("lowrisc-ibex") +#define TYPE_RISCV_CPU_SHAKTI_C RISCV_CPU_TYPE_NAME("shakti-c") +#define TYPE_RISCV_CPU_SIFIVE_E31 RISCV_CPU_TYPE_NAME("sifive-e31") +#define TYPE_RISCV_CPU_SIFIVE_E34 RISCV_CPU_TYPE_NAME("sifive-e34") +#define TYPE_RISCV_CPU_SIFIVE_E51 RISCV_CPU_TYPE_NAME("sifive-e51") +#define TYPE_RISCV_CPU_SIFIVE_U34 RISCV_CPU_TYPE_NAME("sifive-u34") +#define TYPE_RISCV_CPU_SIFIVE_U54 RISCV_CPU_TYPE_NAME("sifive-u54") + +#if defined(TARGET_RISCV32) +# define TYPE_RISCV_CPU_BASE TYPE_RISCV_CPU_BASE32 +#elif defined(TARGET_RISCV64) +# define TYPE_RISCV_CPU_BASE TYPE_RISCV_CPU_BASE64 +#endif + +#define RV(x) ((target_ulong)1 << (x - 'A')) + +#define RVI RV('I') +#define RVE RV('E') /* E and I are mutually exclusive */ +#define RVM RV('M') +#define RVA RV('A') +#define RVF RV('F') +#define RVD RV('D') +#define RVV RV('V') +#define RVC RV('C') +#define RVS RV('S') +#define RVU RV('U') +#define RVH RV('H') +#define RVJ RV('J') + +/* S extension denotes that Supervisor mode exists, however it is possible + to have a core that support S mode but does not have an MMU and there + is currently no bit in misa to indicate whether an MMU exists or not + so a cpu features bitfield is required, likewise for optional PMP support */ +enum { + RISCV_FEATURE_MMU, + RISCV_FEATURE_PMP, + RISCV_FEATURE_EPMP, + RISCV_FEATURE_MISA +}; + +#define PRIV_VERSION_1_10_0 0x00011000 +#define PRIV_VERSION_1_11_0 0x00011100 + +#define VEXT_VERSION_0_07_1 0x00000701 + +enum { + TRANSLATE_SUCCESS, + TRANSLATE_FAIL, + TRANSLATE_PMP_FAIL, + TRANSLATE_G_STAGE_FAIL +}; + +#define MMU_USER_IDX 3 + +#define MAX_RISCV_PMPS (16) + +typedef struct CPURISCVState CPURISCVState; + +#if !defined(CONFIG_USER_ONLY) +#include "pmp.h" +#endif + +#define RV_VLEN_MAX 256 + +FIELD(VTYPE, VLMUL, 0, 2) +FIELD(VTYPE, VSEW, 2, 3) +FIELD(VTYPE, VEDIV, 5, 2) +FIELD(VTYPE, RESERVED, 7, sizeof(target_ulong) * 8 - 9) +FIELD(VTYPE, VILL, sizeof(target_ulong) * 8 - 1, 1) + +struct CPURISCVState { + target_ulong gpr[32]; + uint64_t fpr[32]; /* assume both F and D extensions */ + + /* vector coprocessor state. */ + uint64_t vreg[32 * RV_VLEN_MAX / 64] QEMU_ALIGNED(16); + target_ulong vxrm; + target_ulong vxsat; + target_ulong vl; + target_ulong vstart; + target_ulong vtype; + + target_ulong pc; + target_ulong load_res; + target_ulong load_val; + + target_ulong frm; + + target_ulong badaddr; + target_ulong guest_phys_fault_addr; + + target_ulong priv_ver; + target_ulong bext_ver; + target_ulong vext_ver; + + /* RISCVMXL, but uint32_t for vmstate migration */ + uint32_t misa_mxl; /* current mxl */ + uint32_t misa_mxl_max; /* max mxl for this cpu */ + uint32_t misa_ext; /* current extensions */ + uint32_t misa_ext_mask; /* max ext for this cpu */ + + uint32_t features; + +#ifdef CONFIG_USER_ONLY + uint32_t elf_flags; +#endif + +#ifndef CONFIG_USER_ONLY + target_ulong priv; + /* This contains QEMU specific information about the virt state. */ + target_ulong virt; + target_ulong resetvec; + + target_ulong mhartid; + /* + * For RV32 this is 32-bit mstatus and 32-bit mstatush. + * For RV64 this is a 64-bit mstatus. + */ + uint64_t mstatus; + + target_ulong mip; + + uint32_t miclaim; + + target_ulong mie; + target_ulong mideleg; + + target_ulong satp; /* since: priv-1.10.0 */ + target_ulong stval; + target_ulong medeleg; + + target_ulong stvec; + target_ulong sepc; + target_ulong scause; + + target_ulong mtvec; + target_ulong mepc; + target_ulong mcause; + target_ulong mtval; /* since: priv-1.10.0 */ + + /* Hypervisor CSRs */ + target_ulong hstatus; + target_ulong hedeleg; + target_ulong hideleg; + target_ulong hcounteren; + target_ulong htval; + target_ulong htinst; + target_ulong hgatp; + uint64_t htimedelta; + + /* Virtual CSRs */ + /* + * For RV32 this is 32-bit vsstatus and 32-bit vsstatush. + * For RV64 this is a 64-bit vsstatus. + */ + uint64_t vsstatus; + target_ulong vstvec; + target_ulong vsscratch; + target_ulong vsepc; + target_ulong vscause; + target_ulong vstval; + target_ulong vsatp; + + target_ulong mtval2; + target_ulong mtinst; + + /* HS Backup CSRs */ + target_ulong stvec_hs; + target_ulong sscratch_hs; + target_ulong sepc_hs; + target_ulong scause_hs; + target_ulong stval_hs; + target_ulong satp_hs; + uint64_t mstatus_hs; + + /* Signals whether the current exception occurred with two-stage address + translation active. */ + bool two_stage_lookup; + + target_ulong scounteren; + target_ulong mcounteren; + + target_ulong sscratch; + target_ulong mscratch; + + /* temporary htif regs */ + uint64_t mfromhost; + uint64_t mtohost; + uint64_t timecmp; + + /* physical memory protection */ + pmp_table_t pmp_state; + target_ulong mseccfg; + + /* machine specific rdtime callback */ + uint64_t (*rdtime_fn)(uint32_t); + uint32_t rdtime_fn_arg; + + /* True if in debugger mode. */ + bool debugger; + + /* + * CSRs for PointerMasking extension + */ + target_ulong mmte; + target_ulong mpmmask; + target_ulong mpmbase; + target_ulong spmmask; + target_ulong spmbase; + target_ulong upmmask; + target_ulong upmbase; +#endif + + float_status fp_status; + + /* Fields from here on are preserved across CPU reset. */ + QEMUTimer *timer; /* Internal timer */ +}; + +OBJECT_DECLARE_TYPE(RISCVCPU, RISCVCPUClass, + RISCV_CPU) + +/** + * RISCVCPUClass: + * @parent_realize: The parent class' realize handler. + * @parent_reset: The parent class' reset handler. + * + * A RISCV CPU model. + */ +struct RISCVCPUClass { + /*< private >*/ + CPUClass parent_class; + /*< public >*/ + DeviceRealize parent_realize; + DeviceReset parent_reset; +}; + +/** + * RISCVCPU: + * @env: #CPURISCVState + * + * A RISCV CPU. + */ +struct RISCVCPU { + /*< private >*/ + CPUState parent_obj; + /*< public >*/ + CPUNegativeOffsetState neg; + CPURISCVState env; + + char *dyn_csr_xml; + + /* Configuration Settings */ + struct { + bool ext_i; + bool ext_e; + bool ext_g; + bool ext_m; + bool ext_a; + bool ext_f; + bool ext_d; + bool ext_c; + bool ext_s; + bool ext_u; + bool ext_h; + bool ext_j; + bool ext_v; + bool ext_zba; + bool ext_zbb; + bool ext_zbc; + bool ext_zbs; + bool ext_counters; + bool ext_ifencei; + bool ext_icsr; + + char *priv_spec; + char *user_spec; + char *bext_spec; + char *vext_spec; + uint16_t vlen; + uint16_t elen; + bool mmu; + bool pmp; + bool epmp; + uint64_t resetvec; + } cfg; +}; + +static inline int riscv_has_ext(CPURISCVState *env, target_ulong ext) +{ + return (env->misa_ext & ext) != 0; +} + +static inline bool riscv_feature(CPURISCVState *env, int feature) +{ + return env->features & (1ULL << feature); +} + +#include "cpu_user.h" + +extern const char * const riscv_int_regnames[]; +extern const char * const riscv_fpr_regnames[]; + +const char *riscv_cpu_get_trap_name(target_ulong cause, bool async); +void riscv_cpu_do_interrupt(CPUState *cpu); +int riscv_cpu_write_elf64_note(WriteCoreDumpFunction f, CPUState *cs, + int cpuid, void *opaque); +int riscv_cpu_write_elf32_note(WriteCoreDumpFunction f, CPUState *cs, + int cpuid, void *opaque); +int riscv_cpu_gdb_read_register(CPUState *cpu, GByteArray *buf, int reg); +int riscv_cpu_gdb_write_register(CPUState *cpu, uint8_t *buf, int reg); +bool riscv_cpu_fp_enabled(CPURISCVState *env); +bool riscv_cpu_virt_enabled(CPURISCVState *env); +void riscv_cpu_set_virt_enabled(CPURISCVState *env, bool enable); +bool riscv_cpu_two_stage_lookup(int mmu_idx); +int riscv_cpu_mmu_index(CPURISCVState *env, bool ifetch); +hwaddr riscv_cpu_get_phys_page_debug(CPUState *cpu, vaddr addr); +void riscv_cpu_do_unaligned_access(CPUState *cs, vaddr addr, + MMUAccessType access_type, int mmu_idx, + uintptr_t retaddr) QEMU_NORETURN; +bool riscv_cpu_tlb_fill(CPUState *cs, vaddr address, int size, + MMUAccessType access_type, int mmu_idx, + bool probe, uintptr_t retaddr); +void riscv_cpu_do_transaction_failed(CPUState *cs, hwaddr physaddr, + vaddr addr, unsigned size, + MMUAccessType access_type, + int mmu_idx, MemTxAttrs attrs, + MemTxResult response, uintptr_t retaddr); +char *riscv_isa_string(RISCVCPU *cpu); +void riscv_cpu_list(void); + +#define cpu_list riscv_cpu_list +#define cpu_mmu_index riscv_cpu_mmu_index + +#ifndef CONFIG_USER_ONLY +bool riscv_cpu_exec_interrupt(CPUState *cs, int interrupt_request); +void riscv_cpu_swap_hypervisor_regs(CPURISCVState *env); +int riscv_cpu_claim_interrupts(RISCVCPU *cpu, uint32_t interrupts); +uint32_t riscv_cpu_update_mip(RISCVCPU *cpu, uint32_t mask, uint32_t value); +#define BOOL_TO_MASK(x) (-!!(x)) /* helper for riscv_cpu_update_mip value */ +void riscv_cpu_set_rdtime_fn(CPURISCVState *env, uint64_t (*fn)(uint32_t), + uint32_t arg); +#endif +void riscv_cpu_set_mode(CPURISCVState *env, target_ulong newpriv); + +void riscv_translate_init(void); +void QEMU_NORETURN riscv_raise_exception(CPURISCVState *env, + uint32_t exception, uintptr_t pc); + +target_ulong riscv_cpu_get_fflags(CPURISCVState *env); +void riscv_cpu_set_fflags(CPURISCVState *env, target_ulong); + +#define TB_FLAGS_PRIV_MMU_MASK 3 +#define TB_FLAGS_PRIV_HYP_ACCESS_MASK (1 << 2) +#define TB_FLAGS_MSTATUS_FS MSTATUS_FS + +typedef CPURISCVState CPUArchState; +typedef RISCVCPU ArchCPU; +#include "exec/cpu-all.h" + +FIELD(TB_FLAGS, MEM_IDX, 0, 3) +FIELD(TB_FLAGS, VL_EQ_VLMAX, 3, 1) +FIELD(TB_FLAGS, LMUL, 4, 2) +FIELD(TB_FLAGS, SEW, 6, 3) +FIELD(TB_FLAGS, VILL, 9, 1) +/* Is a Hypervisor instruction load/store allowed? */ +FIELD(TB_FLAGS, HLSX, 10, 1) +FIELD(TB_FLAGS, MSTATUS_HS_FS, 11, 2) +/* The combination of MXL/SXL/UXL that applies to the current cpu mode. */ +FIELD(TB_FLAGS, XL, 13, 2) +/* If PointerMasking should be applied */ +FIELD(TB_FLAGS, PM_ENABLED, 15, 1) + +#ifdef TARGET_RISCV32 +#define riscv_cpu_mxl(env) ((void)(env), MXL_RV32) +#else +static inline RISCVMXL riscv_cpu_mxl(CPURISCVState *env) +{ + return env->misa_mxl; +} +#endif + +/* + * A simplification for VLMAX + * = (1 << LMUL) * VLEN / (8 * (1 << SEW)) + * = (VLEN << LMUL) / (8 << SEW) + * = (VLEN << LMUL) >> (SEW + 3) + * = VLEN >> (SEW + 3 - LMUL) + */ +static inline uint32_t vext_get_vlmax(RISCVCPU *cpu, target_ulong vtype) +{ + uint8_t sew, lmul; + + sew = FIELD_EX64(vtype, VTYPE, VSEW); + lmul = FIELD_EX64(vtype, VTYPE, VLMUL); + return cpu->cfg.vlen >> (sew + 3 - lmul); +} + +void cpu_get_tb_cpu_state(CPURISCVState *env, target_ulong *pc, + target_ulong *cs_base, uint32_t *pflags); + +RISCVException riscv_csrrw(CPURISCVState *env, int csrno, + target_ulong *ret_value, + target_ulong new_value, target_ulong write_mask); +RISCVException riscv_csrrw_debug(CPURISCVState *env, int csrno, + target_ulong *ret_value, + target_ulong new_value, + target_ulong write_mask); + +static inline void riscv_csr_write(CPURISCVState *env, int csrno, + target_ulong val) +{ + riscv_csrrw(env, csrno, NULL, val, MAKE_64BIT_MASK(0, TARGET_LONG_BITS)); +} + +static inline target_ulong riscv_csr_read(CPURISCVState *env, int csrno) +{ + target_ulong val = 0; + riscv_csrrw(env, csrno, &val, 0, 0); + return val; +} + +typedef RISCVException (*riscv_csr_predicate_fn)(CPURISCVState *env, + int csrno); +typedef RISCVException (*riscv_csr_read_fn)(CPURISCVState *env, int csrno, + target_ulong *ret_value); +typedef RISCVException (*riscv_csr_write_fn)(CPURISCVState *env, int csrno, + target_ulong new_value); +typedef RISCVException (*riscv_csr_op_fn)(CPURISCVState *env, int csrno, + target_ulong *ret_value, + target_ulong new_value, + target_ulong write_mask); + +typedef struct { + const char *name; + riscv_csr_predicate_fn predicate; + riscv_csr_read_fn read; + riscv_csr_write_fn write; + riscv_csr_op_fn op; +} riscv_csr_operations; + +/* CSR function table constants */ +enum { + CSR_TABLE_SIZE = 0x1000 +}; + +/* CSR function table */ +extern riscv_csr_operations csr_ops[CSR_TABLE_SIZE]; + +void riscv_get_csr_ops(int csrno, riscv_csr_operations *ops); +void riscv_set_csr_ops(int csrno, riscv_csr_operations *ops); + +void riscv_cpu_register_gdb_regs_for_features(CPUState *cs); + +#endif /* RISCV_CPU_H */ diff --git a/target/riscv/cpu_bits.h b/target/riscv/cpu_bits.h new file mode 100644 index 000000000..9913fa9f7 --- /dev/null +++ b/target/riscv/cpu_bits.h @@ -0,0 +1,618 @@ +/* RISC-V ISA constants */ + +#ifndef TARGET_RISCV_CPU_BITS_H +#define TARGET_RISCV_CPU_BITS_H + +#define get_field(reg, mask) (((reg) & \ + (uint64_t)(mask)) / ((mask) & ~((mask) << 1))) +#define set_field(reg, mask, val) (((reg) & ~(uint64_t)(mask)) | \ + (((uint64_t)(val) * ((mask) & ~((mask) << 1))) & \ + (uint64_t)(mask))) + +/* Floating point round mode */ +#define FSR_RD_SHIFT 5 +#define FSR_RD (0x7 << FSR_RD_SHIFT) + +/* Floating point accrued exception flags */ +#define FPEXC_NX 0x01 +#define FPEXC_UF 0x02 +#define FPEXC_OF 0x04 +#define FPEXC_DZ 0x08 +#define FPEXC_NV 0x10 + +/* Floating point status register bits */ +#define FSR_AEXC_SHIFT 0 +#define FSR_NVA (FPEXC_NV << FSR_AEXC_SHIFT) +#define FSR_OFA (FPEXC_OF << FSR_AEXC_SHIFT) +#define FSR_UFA (FPEXC_UF << FSR_AEXC_SHIFT) +#define FSR_DZA (FPEXC_DZ << FSR_AEXC_SHIFT) +#define FSR_NXA (FPEXC_NX << FSR_AEXC_SHIFT) +#define FSR_AEXC (FSR_NVA | FSR_OFA | FSR_UFA | FSR_DZA | FSR_NXA) + +/* Vector Fixed-Point round model */ +#define FSR_VXRM_SHIFT 9 +#define FSR_VXRM (0x3 << FSR_VXRM_SHIFT) + +/* Vector Fixed-Point saturation flag */ +#define FSR_VXSAT_SHIFT 8 +#define FSR_VXSAT (0x1 << FSR_VXSAT_SHIFT) + +/* Control and Status Registers */ + +/* User Trap Setup */ +#define CSR_USTATUS 0x000 +#define CSR_UIE 0x004 +#define CSR_UTVEC 0x005 + +/* User Trap Handling */ +#define CSR_USCRATCH 0x040 +#define CSR_UEPC 0x041 +#define CSR_UCAUSE 0x042 +#define CSR_UTVAL 0x043 +#define CSR_UIP 0x044 + +/* User Floating-Point CSRs */ +#define CSR_FFLAGS 0x001 +#define CSR_FRM 0x002 +#define CSR_FCSR 0x003 + +/* User Vector CSRs */ +#define CSR_VSTART 0x008 +#define CSR_VXSAT 0x009 +#define CSR_VXRM 0x00a +#define CSR_VL 0xc20 +#define CSR_VTYPE 0xc21 + +/* User Timers and Counters */ +#define CSR_CYCLE 0xc00 +#define CSR_TIME 0xc01 +#define CSR_INSTRET 0xc02 +#define CSR_HPMCOUNTER3 0xc03 +#define CSR_HPMCOUNTER4 0xc04 +#define CSR_HPMCOUNTER5 0xc05 +#define CSR_HPMCOUNTER6 0xc06 +#define CSR_HPMCOUNTER7 0xc07 +#define CSR_HPMCOUNTER8 0xc08 +#define CSR_HPMCOUNTER9 0xc09 +#define CSR_HPMCOUNTER10 0xc0a +#define CSR_HPMCOUNTER11 0xc0b +#define CSR_HPMCOUNTER12 0xc0c +#define CSR_HPMCOUNTER13 0xc0d +#define CSR_HPMCOUNTER14 0xc0e +#define CSR_HPMCOUNTER15 0xc0f +#define CSR_HPMCOUNTER16 0xc10 +#define CSR_HPMCOUNTER17 0xc11 +#define CSR_HPMCOUNTER18 0xc12 +#define CSR_HPMCOUNTER19 0xc13 +#define CSR_HPMCOUNTER20 0xc14 +#define CSR_HPMCOUNTER21 0xc15 +#define CSR_HPMCOUNTER22 0xc16 +#define CSR_HPMCOUNTER23 0xc17 +#define CSR_HPMCOUNTER24 0xc18 +#define CSR_HPMCOUNTER25 0xc19 +#define CSR_HPMCOUNTER26 0xc1a +#define CSR_HPMCOUNTER27 0xc1b +#define CSR_HPMCOUNTER28 0xc1c +#define CSR_HPMCOUNTER29 0xc1d +#define CSR_HPMCOUNTER30 0xc1e +#define CSR_HPMCOUNTER31 0xc1f +#define CSR_CYCLEH 0xc80 +#define CSR_TIMEH 0xc81 +#define CSR_INSTRETH 0xc82 +#define CSR_HPMCOUNTER3H 0xc83 +#define CSR_HPMCOUNTER4H 0xc84 +#define CSR_HPMCOUNTER5H 0xc85 +#define CSR_HPMCOUNTER6H 0xc86 +#define CSR_HPMCOUNTER7H 0xc87 +#define CSR_HPMCOUNTER8H 0xc88 +#define CSR_HPMCOUNTER9H 0xc89 +#define CSR_HPMCOUNTER10H 0xc8a +#define CSR_HPMCOUNTER11H 0xc8b +#define CSR_HPMCOUNTER12H 0xc8c +#define CSR_HPMCOUNTER13H 0xc8d +#define CSR_HPMCOUNTER14H 0xc8e +#define CSR_HPMCOUNTER15H 0xc8f +#define CSR_HPMCOUNTER16H 0xc90 +#define CSR_HPMCOUNTER17H 0xc91 +#define CSR_HPMCOUNTER18H 0xc92 +#define CSR_HPMCOUNTER19H 0xc93 +#define CSR_HPMCOUNTER20H 0xc94 +#define CSR_HPMCOUNTER21H 0xc95 +#define CSR_HPMCOUNTER22H 0xc96 +#define CSR_HPMCOUNTER23H 0xc97 +#define CSR_HPMCOUNTER24H 0xc98 +#define CSR_HPMCOUNTER25H 0xc99 +#define CSR_HPMCOUNTER26H 0xc9a +#define CSR_HPMCOUNTER27H 0xc9b +#define CSR_HPMCOUNTER28H 0xc9c +#define CSR_HPMCOUNTER29H 0xc9d +#define CSR_HPMCOUNTER30H 0xc9e +#define CSR_HPMCOUNTER31H 0xc9f + +/* Machine Timers and Counters */ +#define CSR_MCYCLE 0xb00 +#define CSR_MINSTRET 0xb02 +#define CSR_MCYCLEH 0xb80 +#define CSR_MINSTRETH 0xb82 + +/* Machine Information Registers */ +#define CSR_MVENDORID 0xf11 +#define CSR_MARCHID 0xf12 +#define CSR_MIMPID 0xf13 +#define CSR_MHARTID 0xf14 + +/* Machine Trap Setup */ +#define CSR_MSTATUS 0x300 +#define CSR_MISA 0x301 +#define CSR_MEDELEG 0x302 +#define CSR_MIDELEG 0x303 +#define CSR_MIE 0x304 +#define CSR_MTVEC 0x305 +#define CSR_MCOUNTEREN 0x306 + +/* 32-bit only */ +#define CSR_MSTATUSH 0x310 + +/* Machine Trap Handling */ +#define CSR_MSCRATCH 0x340 +#define CSR_MEPC 0x341 +#define CSR_MCAUSE 0x342 +#define CSR_MTVAL 0x343 +#define CSR_MIP 0x344 + +/* Supervisor Trap Setup */ +#define CSR_SSTATUS 0x100 +#define CSR_SEDELEG 0x102 +#define CSR_SIDELEG 0x103 +#define CSR_SIE 0x104 +#define CSR_STVEC 0x105 +#define CSR_SCOUNTEREN 0x106 + +/* Supervisor Trap Handling */ +#define CSR_SSCRATCH 0x140 +#define CSR_SEPC 0x141 +#define CSR_SCAUSE 0x142 +#define CSR_STVAL 0x143 +#define CSR_SIP 0x144 + +/* Supervisor Protection and Translation */ +#define CSR_SPTBR 0x180 +#define CSR_SATP 0x180 + +/* Hpervisor CSRs */ +#define CSR_HSTATUS 0x600 +#define CSR_HEDELEG 0x602 +#define CSR_HIDELEG 0x603 +#define CSR_HIE 0x604 +#define CSR_HCOUNTEREN 0x606 +#define CSR_HGEIE 0x607 +#define CSR_HTVAL 0x643 +#define CSR_HVIP 0x645 +#define CSR_HIP 0x644 +#define CSR_HTINST 0x64A +#define CSR_HGEIP 0xE12 +#define CSR_HGATP 0x680 +#define CSR_HTIMEDELTA 0x605 +#define CSR_HTIMEDELTAH 0x615 + +/* Virtual CSRs */ +#define CSR_VSSTATUS 0x200 +#define CSR_VSIE 0x204 +#define CSR_VSTVEC 0x205 +#define CSR_VSSCRATCH 0x240 +#define CSR_VSEPC 0x241 +#define CSR_VSCAUSE 0x242 +#define CSR_VSTVAL 0x243 +#define CSR_VSIP 0x244 +#define CSR_VSATP 0x280 + +#define CSR_MTINST 0x34a +#define CSR_MTVAL2 0x34b + +/* Enhanced Physical Memory Protection (ePMP) */ +#define CSR_MSECCFG 0x747 +#define CSR_MSECCFGH 0x757 +/* Physical Memory Protection */ +#define CSR_PMPCFG0 0x3a0 +#define CSR_PMPCFG1 0x3a1 +#define CSR_PMPCFG2 0x3a2 +#define CSR_PMPCFG3 0x3a3 +#define CSR_PMPADDR0 0x3b0 +#define CSR_PMPADDR1 0x3b1 +#define CSR_PMPADDR2 0x3b2 +#define CSR_PMPADDR3 0x3b3 +#define CSR_PMPADDR4 0x3b4 +#define CSR_PMPADDR5 0x3b5 +#define CSR_PMPADDR6 0x3b6 +#define CSR_PMPADDR7 0x3b7 +#define CSR_PMPADDR8 0x3b8 +#define CSR_PMPADDR9 0x3b9 +#define CSR_PMPADDR10 0x3ba +#define CSR_PMPADDR11 0x3bb +#define CSR_PMPADDR12 0x3bc +#define CSR_PMPADDR13 0x3bd +#define CSR_PMPADDR14 0x3be +#define CSR_PMPADDR15 0x3bf + +/* Debug/Trace Registers (shared with Debug Mode) */ +#define CSR_TSELECT 0x7a0 +#define CSR_TDATA1 0x7a1 +#define CSR_TDATA2 0x7a2 +#define CSR_TDATA3 0x7a3 + +/* Debug Mode Registers */ +#define CSR_DCSR 0x7b0 +#define CSR_DPC 0x7b1 +#define CSR_DSCRATCH 0x7b2 + +/* Performance Counters */ +#define CSR_MHPMCOUNTER3 0xb03 +#define CSR_MHPMCOUNTER4 0xb04 +#define CSR_MHPMCOUNTER5 0xb05 +#define CSR_MHPMCOUNTER6 0xb06 +#define CSR_MHPMCOUNTER7 0xb07 +#define CSR_MHPMCOUNTER8 0xb08 +#define CSR_MHPMCOUNTER9 0xb09 +#define CSR_MHPMCOUNTER10 0xb0a +#define CSR_MHPMCOUNTER11 0xb0b +#define CSR_MHPMCOUNTER12 0xb0c +#define CSR_MHPMCOUNTER13 0xb0d +#define CSR_MHPMCOUNTER14 0xb0e +#define CSR_MHPMCOUNTER15 0xb0f +#define CSR_MHPMCOUNTER16 0xb10 +#define CSR_MHPMCOUNTER17 0xb11 +#define CSR_MHPMCOUNTER18 0xb12 +#define CSR_MHPMCOUNTER19 0xb13 +#define CSR_MHPMCOUNTER20 0xb14 +#define CSR_MHPMCOUNTER21 0xb15 +#define CSR_MHPMCOUNTER22 0xb16 +#define CSR_MHPMCOUNTER23 0xb17 +#define CSR_MHPMCOUNTER24 0xb18 +#define CSR_MHPMCOUNTER25 0xb19 +#define CSR_MHPMCOUNTER26 0xb1a +#define CSR_MHPMCOUNTER27 0xb1b +#define CSR_MHPMCOUNTER28 0xb1c +#define CSR_MHPMCOUNTER29 0xb1d +#define CSR_MHPMCOUNTER30 0xb1e +#define CSR_MHPMCOUNTER31 0xb1f +#define CSR_MHPMEVENT3 0x323 +#define CSR_MHPMEVENT4 0x324 +#define CSR_MHPMEVENT5 0x325 +#define CSR_MHPMEVENT6 0x326 +#define CSR_MHPMEVENT7 0x327 +#define CSR_MHPMEVENT8 0x328 +#define CSR_MHPMEVENT9 0x329 +#define CSR_MHPMEVENT10 0x32a +#define CSR_MHPMEVENT11 0x32b +#define CSR_MHPMEVENT12 0x32c +#define CSR_MHPMEVENT13 0x32d +#define CSR_MHPMEVENT14 0x32e +#define CSR_MHPMEVENT15 0x32f +#define CSR_MHPMEVENT16 0x330 +#define CSR_MHPMEVENT17 0x331 +#define CSR_MHPMEVENT18 0x332 +#define CSR_MHPMEVENT19 0x333 +#define CSR_MHPMEVENT20 0x334 +#define CSR_MHPMEVENT21 0x335 +#define CSR_MHPMEVENT22 0x336 +#define CSR_MHPMEVENT23 0x337 +#define CSR_MHPMEVENT24 0x338 +#define CSR_MHPMEVENT25 0x339 +#define CSR_MHPMEVENT26 0x33a +#define CSR_MHPMEVENT27 0x33b +#define CSR_MHPMEVENT28 0x33c +#define CSR_MHPMEVENT29 0x33d +#define CSR_MHPMEVENT30 0x33e +#define CSR_MHPMEVENT31 0x33f +#define CSR_MHPMCOUNTER3H 0xb83 +#define CSR_MHPMCOUNTER4H 0xb84 +#define CSR_MHPMCOUNTER5H 0xb85 +#define CSR_MHPMCOUNTER6H 0xb86 +#define CSR_MHPMCOUNTER7H 0xb87 +#define CSR_MHPMCOUNTER8H 0xb88 +#define CSR_MHPMCOUNTER9H 0xb89 +#define CSR_MHPMCOUNTER10H 0xb8a +#define CSR_MHPMCOUNTER11H 0xb8b +#define CSR_MHPMCOUNTER12H 0xb8c +#define CSR_MHPMCOUNTER13H 0xb8d +#define CSR_MHPMCOUNTER14H 0xb8e +#define CSR_MHPMCOUNTER15H 0xb8f +#define CSR_MHPMCOUNTER16H 0xb90 +#define CSR_MHPMCOUNTER17H 0xb91 +#define CSR_MHPMCOUNTER18H 0xb92 +#define CSR_MHPMCOUNTER19H 0xb93 +#define CSR_MHPMCOUNTER20H 0xb94 +#define CSR_MHPMCOUNTER21H 0xb95 +#define CSR_MHPMCOUNTER22H 0xb96 +#define CSR_MHPMCOUNTER23H 0xb97 +#define CSR_MHPMCOUNTER24H 0xb98 +#define CSR_MHPMCOUNTER25H 0xb99 +#define CSR_MHPMCOUNTER26H 0xb9a +#define CSR_MHPMCOUNTER27H 0xb9b +#define CSR_MHPMCOUNTER28H 0xb9c +#define CSR_MHPMCOUNTER29H 0xb9d +#define CSR_MHPMCOUNTER30H 0xb9e +#define CSR_MHPMCOUNTER31H 0xb9f + +/* + * User PointerMasking registers + * NB: actual CSR numbers might be changed in future + */ +#define CSR_UMTE 0x4c0 +#define CSR_UPMMASK 0x4c1 +#define CSR_UPMBASE 0x4c2 + +/* + * Machine PointerMasking registers + * NB: actual CSR numbers might be changed in future + */ +#define CSR_MMTE 0x3c0 +#define CSR_MPMMASK 0x3c1 +#define CSR_MPMBASE 0x3c2 + +/* + * Supervisor PointerMaster registers + * NB: actual CSR numbers might be changed in future + */ +#define CSR_SMTE 0x1c0 +#define CSR_SPMMASK 0x1c1 +#define CSR_SPMBASE 0x1c2 + +/* + * Hypervisor PointerMaster registers + * NB: actual CSR numbers might be changed in future + */ +#define CSR_VSMTE 0x2c0 +#define CSR_VSPMMASK 0x2c1 +#define CSR_VSPMBASE 0x2c2 + +/* mstatus CSR bits */ +#define MSTATUS_UIE 0x00000001 +#define MSTATUS_SIE 0x00000002 +#define MSTATUS_MIE 0x00000008 +#define MSTATUS_UPIE 0x00000010 +#define MSTATUS_SPIE 0x00000020 +#define MSTATUS_UBE 0x00000040 +#define MSTATUS_MPIE 0x00000080 +#define MSTATUS_SPP 0x00000100 +#define MSTATUS_MPP 0x00001800 +#define MSTATUS_FS 0x00006000 +#define MSTATUS_XS 0x00018000 +#define MSTATUS_MPRV 0x00020000 +#define MSTATUS_SUM 0x00040000 /* since: priv-1.10 */ +#define MSTATUS_MXR 0x00080000 +#define MSTATUS_TVM 0x00100000 /* since: priv-1.10 */ +#define MSTATUS_TW 0x00200000 /* since: priv-1.10 */ +#define MSTATUS_TSR 0x00400000 /* since: priv-1.10 */ +#define MSTATUS_GVA 0x4000000000ULL +#define MSTATUS_MPV 0x8000000000ULL + +#define MSTATUS64_UXL 0x0000000300000000ULL +#define MSTATUS64_SXL 0x0000000C00000000ULL + +#define MSTATUS32_SD 0x80000000 +#define MSTATUS64_SD 0x8000000000000000ULL + +#define MISA32_MXL 0xC0000000 +#define MISA64_MXL 0xC000000000000000ULL + +typedef enum { + MXL_RV32 = 1, + MXL_RV64 = 2, + MXL_RV128 = 3, +} RISCVMXL; + +/* sstatus CSR bits */ +#define SSTATUS_UIE 0x00000001 +#define SSTATUS_SIE 0x00000002 +#define SSTATUS_UPIE 0x00000010 +#define SSTATUS_SPIE 0x00000020 +#define SSTATUS_SPP 0x00000100 +#define SSTATUS_FS 0x00006000 +#define SSTATUS_XS 0x00018000 +#define SSTATUS_SUM 0x00040000 /* since: priv-1.10 */ +#define SSTATUS_MXR 0x00080000 + +#define SSTATUS32_SD 0x80000000 +#define SSTATUS64_SD 0x8000000000000000ULL + +/* hstatus CSR bits */ +#define HSTATUS_VSBE 0x00000020 +#define HSTATUS_GVA 0x00000040 +#define HSTATUS_SPV 0x00000080 +#define HSTATUS_SPVP 0x00000100 +#define HSTATUS_HU 0x00000200 +#define HSTATUS_VGEIN 0x0003F000 +#define HSTATUS_VTVM 0x00100000 +#define HSTATUS_VTW 0x00200000 +#define HSTATUS_VTSR 0x00400000 +#define HSTATUS_VSXL 0x300000000 + +#define HSTATUS32_WPRI 0xFF8FF87E +#define HSTATUS64_WPRI 0xFFFFFFFFFF8FF87EULL + +#define COUNTEREN_CY (1 << 0) +#define COUNTEREN_TM (1 << 1) +#define COUNTEREN_IR (1 << 2) +#define COUNTEREN_HPM3 (1 << 3) + +/* Privilege modes */ +#define PRV_U 0 +#define PRV_S 1 +#define PRV_H 2 /* Reserved */ +#define PRV_M 3 + +/* Virtulisation Register Fields */ +#define VIRT_ONOFF 1 + +/* RV32 satp CSR field masks */ +#define SATP32_MODE 0x80000000 +#define SATP32_ASID 0x7fc00000 +#define SATP32_PPN 0x003fffff + +/* RV64 satp CSR field masks */ +#define SATP64_MODE 0xF000000000000000ULL +#define SATP64_ASID 0x0FFFF00000000000ULL +#define SATP64_PPN 0x00000FFFFFFFFFFFULL + +/* VM modes (satp.mode) privileged ISA 1.10 */ +#define VM_1_10_MBARE 0 +#define VM_1_10_SV32 1 +#define VM_1_10_SV39 8 +#define VM_1_10_SV48 9 +#define VM_1_10_SV57 10 +#define VM_1_10_SV64 11 + +/* Page table entry (PTE) fields */ +#define PTE_V 0x001 /* Valid */ +#define PTE_R 0x002 /* Read */ +#define PTE_W 0x004 /* Write */ +#define PTE_X 0x008 /* Execute */ +#define PTE_U 0x010 /* User */ +#define PTE_G 0x020 /* Global */ +#define PTE_A 0x040 /* Accessed */ +#define PTE_D 0x080 /* Dirty */ +#define PTE_SOFT 0x300 /* Reserved for Software */ + +/* Page table PPN shift amount */ +#define PTE_PPN_SHIFT 10 + +/* Leaf page shift amount */ +#define PGSHIFT 12 + +/* Default Reset Vector adress */ +#define DEFAULT_RSTVEC 0x1000 + +/* Exception causes */ +typedef enum RISCVException { + RISCV_EXCP_NONE = -1, /* sentinel value */ + RISCV_EXCP_INST_ADDR_MIS = 0x0, + RISCV_EXCP_INST_ACCESS_FAULT = 0x1, + RISCV_EXCP_ILLEGAL_INST = 0x2, + RISCV_EXCP_BREAKPOINT = 0x3, + RISCV_EXCP_LOAD_ADDR_MIS = 0x4, + RISCV_EXCP_LOAD_ACCESS_FAULT = 0x5, + RISCV_EXCP_STORE_AMO_ADDR_MIS = 0x6, + RISCV_EXCP_STORE_AMO_ACCESS_FAULT = 0x7, + RISCV_EXCP_U_ECALL = 0x8, + RISCV_EXCP_S_ECALL = 0x9, + RISCV_EXCP_VS_ECALL = 0xa, + RISCV_EXCP_M_ECALL = 0xb, + RISCV_EXCP_INST_PAGE_FAULT = 0xc, /* since: priv-1.10.0 */ + RISCV_EXCP_LOAD_PAGE_FAULT = 0xd, /* since: priv-1.10.0 */ + RISCV_EXCP_STORE_PAGE_FAULT = 0xf, /* since: priv-1.10.0 */ + RISCV_EXCP_SEMIHOST = 0x10, + RISCV_EXCP_INST_GUEST_PAGE_FAULT = 0x14, + RISCV_EXCP_LOAD_GUEST_ACCESS_FAULT = 0x15, + RISCV_EXCP_VIRT_INSTRUCTION_FAULT = 0x16, + RISCV_EXCP_STORE_GUEST_AMO_ACCESS_FAULT = 0x17, +} RISCVException; + +#define RISCV_EXCP_INT_FLAG 0x80000000 +#define RISCV_EXCP_INT_MASK 0x7fffffff + +/* Interrupt causes */ +#define IRQ_U_SOFT 0 +#define IRQ_S_SOFT 1 +#define IRQ_VS_SOFT 2 +#define IRQ_M_SOFT 3 +#define IRQ_U_TIMER 4 +#define IRQ_S_TIMER 5 +#define IRQ_VS_TIMER 6 +#define IRQ_M_TIMER 7 +#define IRQ_U_EXT 8 +#define IRQ_S_EXT 9 +#define IRQ_VS_EXT 10 +#define IRQ_M_EXT 11 + +/* mip masks */ +#define MIP_USIP (1 << IRQ_U_SOFT) +#define MIP_SSIP (1 << IRQ_S_SOFT) +#define MIP_VSSIP (1 << IRQ_VS_SOFT) +#define MIP_MSIP (1 << IRQ_M_SOFT) +#define MIP_UTIP (1 << IRQ_U_TIMER) +#define MIP_STIP (1 << IRQ_S_TIMER) +#define MIP_VSTIP (1 << IRQ_VS_TIMER) +#define MIP_MTIP (1 << IRQ_M_TIMER) +#define MIP_UEIP (1 << IRQ_U_EXT) +#define MIP_SEIP (1 << IRQ_S_EXT) +#define MIP_VSEIP (1 << IRQ_VS_EXT) +#define MIP_MEIP (1 << IRQ_M_EXT) + +/* sip masks */ +#define SIP_SSIP MIP_SSIP +#define SIP_STIP MIP_STIP +#define SIP_SEIP MIP_SEIP + +/* MIE masks */ +#define MIE_SEIE (1 << IRQ_S_EXT) +#define MIE_UEIE (1 << IRQ_U_EXT) +#define MIE_STIE (1 << IRQ_S_TIMER) +#define MIE_UTIE (1 << IRQ_U_TIMER) +#define MIE_SSIE (1 << IRQ_S_SOFT) +#define MIE_USIE (1 << IRQ_U_SOFT) + +/* General PointerMasking CSR bits*/ +#define PM_ENABLE 0x00000001ULL +#define PM_CURRENT 0x00000002ULL +#define PM_INSN 0x00000004ULL +#define PM_XS_MASK 0x00000003ULL + +/* PointerMasking XS bits values */ +#define PM_EXT_DISABLE 0x00000000ULL +#define PM_EXT_INITIAL 0x00000001ULL +#define PM_EXT_CLEAN 0x00000002ULL +#define PM_EXT_DIRTY 0x00000003ULL + +/* Offsets for every pair of control bits per each priv level */ +#define XS_OFFSET 0ULL +#define U_OFFSET 2ULL +#define S_OFFSET 5ULL +#define M_OFFSET 8ULL + +#define PM_XS_BITS (PM_XS_MASK << XS_OFFSET) +#define U_PM_ENABLE (PM_ENABLE << U_OFFSET) +#define U_PM_CURRENT (PM_CURRENT << U_OFFSET) +#define U_PM_INSN (PM_INSN << U_OFFSET) +#define S_PM_ENABLE (PM_ENABLE << S_OFFSET) +#define S_PM_CURRENT (PM_CURRENT << S_OFFSET) +#define S_PM_INSN (PM_INSN << S_OFFSET) +#define M_PM_ENABLE (PM_ENABLE << M_OFFSET) +#define M_PM_CURRENT (PM_CURRENT << M_OFFSET) +#define M_PM_INSN (PM_INSN << M_OFFSET) + +/* mmte CSR bits */ +#define MMTE_PM_XS_BITS PM_XS_BITS +#define MMTE_U_PM_ENABLE U_PM_ENABLE +#define MMTE_U_PM_CURRENT U_PM_CURRENT +#define MMTE_U_PM_INSN U_PM_INSN +#define MMTE_S_PM_ENABLE S_PM_ENABLE +#define MMTE_S_PM_CURRENT S_PM_CURRENT +#define MMTE_S_PM_INSN S_PM_INSN +#define MMTE_M_PM_ENABLE M_PM_ENABLE +#define MMTE_M_PM_CURRENT M_PM_CURRENT +#define MMTE_M_PM_INSN M_PM_INSN +#define MMTE_MASK (MMTE_U_PM_ENABLE | MMTE_U_PM_CURRENT | MMTE_U_PM_INSN | \ + MMTE_S_PM_ENABLE | MMTE_S_PM_CURRENT | MMTE_S_PM_INSN | \ + MMTE_M_PM_ENABLE | MMTE_M_PM_CURRENT | MMTE_M_PM_INSN | \ + MMTE_PM_XS_BITS) + +/* (v)smte CSR bits */ +#define SMTE_PM_XS_BITS PM_XS_BITS +#define SMTE_U_PM_ENABLE U_PM_ENABLE +#define SMTE_U_PM_CURRENT U_PM_CURRENT +#define SMTE_U_PM_INSN U_PM_INSN +#define SMTE_S_PM_ENABLE S_PM_ENABLE +#define SMTE_S_PM_CURRENT S_PM_CURRENT +#define SMTE_S_PM_INSN S_PM_INSN +#define SMTE_MASK (SMTE_U_PM_ENABLE | SMTE_U_PM_CURRENT | SMTE_U_PM_INSN | \ + SMTE_S_PM_ENABLE | SMTE_S_PM_CURRENT | SMTE_S_PM_INSN | \ + SMTE_PM_XS_BITS) + +/* umte CSR bits */ +#define UMTE_U_PM_ENABLE U_PM_ENABLE +#define UMTE_U_PM_CURRENT U_PM_CURRENT +#define UMTE_U_PM_INSN U_PM_INSN +#define UMTE_MASK (UMTE_U_PM_ENABLE | MMTE_U_PM_CURRENT | UMTE_U_PM_INSN) + +#endif diff --git a/target/riscv/cpu_helper.c b/target/riscv/cpu_helper.c new file mode 100644 index 000000000..9eeed38c7 --- /dev/null +++ b/target/riscv/cpu_helper.c @@ -0,0 +1,1138 @@ +/* + * RISC-V CPU helpers for qemu. + * + * Copyright (c) 2016-2017 Sagar Karandikar, sagark@eecs.berkeley.edu + * Copyright (c) 2017-2018 SiFive, Inc. + * + * 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/log.h" +#include "qemu/main-loop.h" +#include "cpu.h" +#include "exec/exec-all.h" +#include "tcg/tcg-op.h" +#include "trace.h" +#include "semihosting/common-semi.h" + +int riscv_cpu_mmu_index(CPURISCVState *env, bool ifetch) +{ +#ifdef CONFIG_USER_ONLY + return 0; +#else + return env->priv; +#endif +} + +static RISCVMXL cpu_get_xl(CPURISCVState *env) +{ +#if defined(TARGET_RISCV32) + return MXL_RV32; +#elif defined(CONFIG_USER_ONLY) + return MXL_RV64; +#else + RISCVMXL xl = riscv_cpu_mxl(env); + + /* + * When emulating a 32-bit-only cpu, use RV32. + * When emulating a 64-bit cpu, and MXL has been reduced to RV32, + * MSTATUSH doesn't have UXL/SXL, therefore XLEN cannot be widened + * back to RV64 for lower privs. + */ + if (xl != MXL_RV32) { + switch (env->priv) { + case PRV_M: + break; + case PRV_U: + xl = get_field(env->mstatus, MSTATUS64_UXL); + break; + default: /* PRV_S | PRV_H */ + xl = get_field(env->mstatus, MSTATUS64_SXL); + break; + } + } + return xl; +#endif +} + +void cpu_get_tb_cpu_state(CPURISCVState *env, target_ulong *pc, + target_ulong *cs_base, uint32_t *pflags) +{ + uint32_t flags = 0; + + *pc = env->pc; + *cs_base = 0; + + if (riscv_has_ext(env, RVV)) { + uint32_t vlmax = vext_get_vlmax(env_archcpu(env), env->vtype); + bool vl_eq_vlmax = (env->vstart == 0) && (vlmax == env->vl); + flags = FIELD_DP32(flags, TB_FLAGS, VILL, + FIELD_EX64(env->vtype, VTYPE, VILL)); + flags = FIELD_DP32(flags, TB_FLAGS, SEW, + FIELD_EX64(env->vtype, VTYPE, VSEW)); + flags = FIELD_DP32(flags, TB_FLAGS, LMUL, + FIELD_EX64(env->vtype, VTYPE, VLMUL)); + flags = FIELD_DP32(flags, TB_FLAGS, VL_EQ_VLMAX, vl_eq_vlmax); + } else { + flags = FIELD_DP32(flags, TB_FLAGS, VILL, 1); + } + +#ifdef CONFIG_USER_ONLY + flags |= TB_FLAGS_MSTATUS_FS; +#else + flags |= cpu_mmu_index(env, 0); + if (riscv_cpu_fp_enabled(env)) { + flags |= env->mstatus & MSTATUS_FS; + } + + if (riscv_has_ext(env, RVH)) { + if (env->priv == PRV_M || + (env->priv == PRV_S && !riscv_cpu_virt_enabled(env)) || + (env->priv == PRV_U && !riscv_cpu_virt_enabled(env) && + get_field(env->hstatus, HSTATUS_HU))) { + flags = FIELD_DP32(flags, TB_FLAGS, HLSX, 1); + } + + flags = FIELD_DP32(flags, TB_FLAGS, MSTATUS_HS_FS, + get_field(env->mstatus_hs, MSTATUS_FS)); + } + if (riscv_has_ext(env, RVJ)) { + int priv = flags & TB_FLAGS_PRIV_MMU_MASK; + bool pm_enabled = false; + switch (priv) { + case PRV_U: + pm_enabled = env->mmte & U_PM_ENABLE; + break; + case PRV_S: + pm_enabled = env->mmte & S_PM_ENABLE; + break; + case PRV_M: + pm_enabled = env->mmte & M_PM_ENABLE; + break; + default: + g_assert_not_reached(); + } + flags = FIELD_DP32(flags, TB_FLAGS, PM_ENABLED, pm_enabled); + } +#endif + + flags = FIELD_DP32(flags, TB_FLAGS, XL, cpu_get_xl(env)); + + *pflags = flags; +} + +#ifndef CONFIG_USER_ONLY +static int riscv_cpu_local_irq_pending(CPURISCVState *env) +{ + target_ulong virt_enabled = riscv_cpu_virt_enabled(env); + + target_ulong mstatus_mie = get_field(env->mstatus, MSTATUS_MIE); + target_ulong mstatus_sie = get_field(env->mstatus, MSTATUS_SIE); + + target_ulong pending = env->mip & env->mie; + + target_ulong mie = env->priv < PRV_M || + (env->priv == PRV_M && mstatus_mie); + target_ulong sie = env->priv < PRV_S || + (env->priv == PRV_S && mstatus_sie); + target_ulong hsie = virt_enabled || sie; + target_ulong vsie = virt_enabled && sie; + + target_ulong irqs = + (pending & ~env->mideleg & -mie) | + (pending & env->mideleg & ~env->hideleg & -hsie) | + (pending & env->mideleg & env->hideleg & -vsie); + + if (irqs) { + return ctz64(irqs); /* since non-zero */ + } else { + return RISCV_EXCP_NONE; /* indicates no pending interrupt */ + } +} + +bool riscv_cpu_exec_interrupt(CPUState *cs, int interrupt_request) +{ + if (interrupt_request & CPU_INTERRUPT_HARD) { + RISCVCPU *cpu = RISCV_CPU(cs); + CPURISCVState *env = &cpu->env; + int interruptno = riscv_cpu_local_irq_pending(env); + if (interruptno >= 0) { + cs->exception_index = RISCV_EXCP_INT_FLAG | interruptno; + riscv_cpu_do_interrupt(cs); + return true; + } + } + return false; +} + +/* Return true is floating point support is currently enabled */ +bool riscv_cpu_fp_enabled(CPURISCVState *env) +{ + if (env->mstatus & MSTATUS_FS) { + if (riscv_cpu_virt_enabled(env) && !(env->mstatus_hs & MSTATUS_FS)) { + return false; + } + return true; + } + + return false; +} + +void riscv_cpu_swap_hypervisor_regs(CPURISCVState *env) +{ + uint64_t mstatus_mask = MSTATUS_MXR | MSTATUS_SUM | MSTATUS_FS | + MSTATUS_SPP | MSTATUS_SPIE | MSTATUS_SIE | + MSTATUS64_UXL; + bool current_virt = riscv_cpu_virt_enabled(env); + + g_assert(riscv_has_ext(env, RVH)); + + if (current_virt) { + /* Current V=1 and we are about to change to V=0 */ + env->vsstatus = env->mstatus & mstatus_mask; + env->mstatus &= ~mstatus_mask; + env->mstatus |= env->mstatus_hs; + + env->vstvec = env->stvec; + env->stvec = env->stvec_hs; + + env->vsscratch = env->sscratch; + env->sscratch = env->sscratch_hs; + + env->vsepc = env->sepc; + env->sepc = env->sepc_hs; + + env->vscause = env->scause; + env->scause = env->scause_hs; + + env->vstval = env->stval; + env->stval = env->stval_hs; + + env->vsatp = env->satp; + env->satp = env->satp_hs; + } else { + /* Current V=0 and we are about to change to V=1 */ + env->mstatus_hs = env->mstatus & mstatus_mask; + env->mstatus &= ~mstatus_mask; + env->mstatus |= env->vsstatus; + + env->stvec_hs = env->stvec; + env->stvec = env->vstvec; + + env->sscratch_hs = env->sscratch; + env->sscratch = env->vsscratch; + + env->sepc_hs = env->sepc; + env->sepc = env->vsepc; + + env->scause_hs = env->scause; + env->scause = env->vscause; + + env->stval_hs = env->stval; + env->stval = env->vstval; + + env->satp_hs = env->satp; + env->satp = env->vsatp; + } +} + +bool riscv_cpu_virt_enabled(CPURISCVState *env) +{ + if (!riscv_has_ext(env, RVH)) { + return false; + } + + return get_field(env->virt, VIRT_ONOFF); +} + +void riscv_cpu_set_virt_enabled(CPURISCVState *env, bool enable) +{ + if (!riscv_has_ext(env, RVH)) { + return; + } + + /* Flush the TLB on all virt mode changes. */ + if (get_field(env->virt, VIRT_ONOFF) != enable) { + tlb_flush(env_cpu(env)); + } + + env->virt = set_field(env->virt, VIRT_ONOFF, enable); +} + +bool riscv_cpu_two_stage_lookup(int mmu_idx) +{ + return mmu_idx & TB_FLAGS_PRIV_HYP_ACCESS_MASK; +} + +int riscv_cpu_claim_interrupts(RISCVCPU *cpu, uint32_t interrupts) +{ + CPURISCVState *env = &cpu->env; + if (env->miclaim & interrupts) { + return -1; + } else { + env->miclaim |= interrupts; + return 0; + } +} + +uint32_t riscv_cpu_update_mip(RISCVCPU *cpu, uint32_t mask, uint32_t value) +{ + CPURISCVState *env = &cpu->env; + CPUState *cs = CPU(cpu); + uint32_t old = env->mip; + bool locked = false; + + if (!qemu_mutex_iothread_locked()) { + locked = true; + qemu_mutex_lock_iothread(); + } + + env->mip = (env->mip & ~mask) | (value & mask); + + if (env->mip) { + cpu_interrupt(cs, CPU_INTERRUPT_HARD); + } else { + cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD); + } + + if (locked) { + qemu_mutex_unlock_iothread(); + } + + return old; +} + +void riscv_cpu_set_rdtime_fn(CPURISCVState *env, uint64_t (*fn)(uint32_t), + uint32_t arg) +{ + env->rdtime_fn = fn; + env->rdtime_fn_arg = arg; +} + +void riscv_cpu_set_mode(CPURISCVState *env, target_ulong newpriv) +{ + if (newpriv > PRV_M) { + g_assert_not_reached(); + } + if (newpriv == PRV_H) { + newpriv = PRV_U; + } + /* tlb_flush is unnecessary as mode is contained in mmu_idx */ + env->priv = newpriv; + + /* + * Clear the load reservation - otherwise a reservation placed in one + * context/process can be used by another, resulting in an SC succeeding + * incorrectly. Version 2.2 of the ISA specification explicitly requires + * this behaviour, while later revisions say that the kernel "should" use + * an SC instruction to force the yielding of a load reservation on a + * preemptive context switch. As a result, do both. + */ + env->load_res = -1; +} + +/* + * get_physical_address_pmp - check PMP permission for this physical address + * + * Match the PMP region and check permission for this physical address and it's + * TLB page. Returns 0 if the permission checking was successful + * + * @env: CPURISCVState + * @prot: The returned protection attributes + * @tlb_size: TLB page size containing addr. It could be modified after PMP + * permission checking. NULL if not set TLB page for addr. + * @addr: The physical address to be checked permission + * @access_type: The type of MMU access + * @mode: Indicates current privilege level. + */ +static int get_physical_address_pmp(CPURISCVState *env, int *prot, + target_ulong *tlb_size, hwaddr addr, + int size, MMUAccessType access_type, + int mode) +{ + pmp_priv_t pmp_priv; + target_ulong tlb_size_pmp = 0; + + if (!riscv_feature(env, RISCV_FEATURE_PMP)) { + *prot = PAGE_READ | PAGE_WRITE | PAGE_EXEC; + return TRANSLATE_SUCCESS; + } + + if (!pmp_hart_has_privs(env, addr, size, 1 << access_type, &pmp_priv, + mode)) { + *prot = 0; + return TRANSLATE_PMP_FAIL; + } + + *prot = pmp_priv_to_page_prot(pmp_priv); + if (tlb_size != NULL) { + if (pmp_is_range_in_tlb(env, addr & ~(*tlb_size - 1), &tlb_size_pmp)) { + *tlb_size = tlb_size_pmp; + } + } + + return TRANSLATE_SUCCESS; +} + +/* get_physical_address - get the physical address for this virtual address + * + * Do a page table walk to obtain the physical address corresponding to a + * virtual address. Returns 0 if the translation was successful + * + * Adapted from Spike's mmu_t::translate and mmu_t::walk + * + * @env: CPURISCVState + * @physical: This will be set to the calculated physical address + * @prot: The returned protection attributes + * @addr: The virtual address to be translated + * @fault_pte_addr: If not NULL, this will be set to fault pte address + * when a error occurs on pte address translation. + * This will already be shifted to match htval. + * @access_type: The type of MMU access + * @mmu_idx: Indicates current privilege level + * @first_stage: Are we in first stage translation? + * Second stage is used for hypervisor guest translation + * @two_stage: Are we going to perform two stage translation + * @is_debug: Is this access from a debugger or the monitor? + */ +static int get_physical_address(CPURISCVState *env, hwaddr *physical, + int *prot, target_ulong addr, + target_ulong *fault_pte_addr, + int access_type, int mmu_idx, + bool first_stage, bool two_stage, + bool is_debug) +{ + /* NOTE: the env->pc value visible here will not be + * correct, but the value visible to the exception handler + * (riscv_cpu_do_interrupt) is correct */ + MemTxResult res; + MemTxAttrs attrs = MEMTXATTRS_UNSPECIFIED; + int mode = mmu_idx & TB_FLAGS_PRIV_MMU_MASK; + bool use_background = false; + + /* + * Check if we should use the background registers for the two + * stage translation. We don't need to check if we actually need + * two stage translation as that happened before this function + * was called. Background registers will be used if the guest has + * forced a two stage translation to be on (in HS or M mode). + */ + if (!riscv_cpu_virt_enabled(env) && two_stage) { + use_background = true; + } + + /* MPRV does not affect the virtual-machine load/store + instructions, HLV, HLVX, and HSV. */ + if (riscv_cpu_two_stage_lookup(mmu_idx)) { + mode = get_field(env->hstatus, HSTATUS_SPVP); + } else if (mode == PRV_M && access_type != MMU_INST_FETCH) { + if (get_field(env->mstatus, MSTATUS_MPRV)) { + mode = get_field(env->mstatus, MSTATUS_MPP); + } + } + + if (first_stage == false) { + /* We are in stage 2 translation, this is similar to stage 1. */ + /* Stage 2 is always taken as U-mode */ + mode = PRV_U; + } + + if (mode == PRV_M || !riscv_feature(env, RISCV_FEATURE_MMU)) { + *physical = addr; + *prot = PAGE_READ | PAGE_WRITE | PAGE_EXEC; + return TRANSLATE_SUCCESS; + } + + *prot = 0; + + hwaddr base; + int levels, ptidxbits, ptesize, vm, sum, mxr, widened; + + if (first_stage == true) { + mxr = get_field(env->mstatus, MSTATUS_MXR); + } else { + mxr = get_field(env->vsstatus, MSTATUS_MXR); + } + + if (first_stage == true) { + if (use_background) { + if (riscv_cpu_mxl(env) == MXL_RV32) { + base = (hwaddr)get_field(env->vsatp, SATP32_PPN) << PGSHIFT; + vm = get_field(env->vsatp, SATP32_MODE); + } else { + base = (hwaddr)get_field(env->vsatp, SATP64_PPN) << PGSHIFT; + vm = get_field(env->vsatp, SATP64_MODE); + } + } else { + if (riscv_cpu_mxl(env) == MXL_RV32) { + base = (hwaddr)get_field(env->satp, SATP32_PPN) << PGSHIFT; + vm = get_field(env->satp, SATP32_MODE); + } else { + base = (hwaddr)get_field(env->satp, SATP64_PPN) << PGSHIFT; + vm = get_field(env->satp, SATP64_MODE); + } + } + widened = 0; + } else { + if (riscv_cpu_mxl(env) == MXL_RV32) { + base = (hwaddr)get_field(env->hgatp, SATP32_PPN) << PGSHIFT; + vm = get_field(env->hgatp, SATP32_MODE); + } else { + base = (hwaddr)get_field(env->hgatp, SATP64_PPN) << PGSHIFT; + vm = get_field(env->hgatp, SATP64_MODE); + } + widened = 2; + } + /* status.SUM will be ignored if execute on background */ + sum = get_field(env->mstatus, MSTATUS_SUM) || use_background || is_debug; + switch (vm) { + case VM_1_10_SV32: + levels = 2; ptidxbits = 10; ptesize = 4; break; + case VM_1_10_SV39: + levels = 3; ptidxbits = 9; ptesize = 8; break; + case VM_1_10_SV48: + levels = 4; ptidxbits = 9; ptesize = 8; break; + case VM_1_10_SV57: + levels = 5; ptidxbits = 9; ptesize = 8; break; + case VM_1_10_MBARE: + *physical = addr; + *prot = PAGE_READ | PAGE_WRITE | PAGE_EXEC; + return TRANSLATE_SUCCESS; + default: + g_assert_not_reached(); + } + + CPUState *cs = env_cpu(env); + int va_bits = PGSHIFT + levels * ptidxbits + widened; + target_ulong mask, masked_msbs; + + if (TARGET_LONG_BITS > (va_bits - 1)) { + mask = (1L << (TARGET_LONG_BITS - (va_bits - 1))) - 1; + } else { + mask = 0; + } + masked_msbs = (addr >> (va_bits - 1)) & mask; + + if (masked_msbs != 0 && masked_msbs != mask) { + return TRANSLATE_FAIL; + } + + int ptshift = (levels - 1) * ptidxbits; + int i; + +#if !TCG_OVERSIZED_GUEST +restart: +#endif + for (i = 0; i < levels; i++, ptshift -= ptidxbits) { + target_ulong idx; + if (i == 0) { + idx = (addr >> (PGSHIFT + ptshift)) & + ((1 << (ptidxbits + widened)) - 1); + } else { + idx = (addr >> (PGSHIFT + ptshift)) & + ((1 << ptidxbits) - 1); + } + + /* check that physical address of PTE is legal */ + hwaddr pte_addr; + + if (two_stage && first_stage) { + int vbase_prot; + hwaddr vbase; + + /* Do the second stage translation on the base PTE address. */ + int vbase_ret = get_physical_address(env, &vbase, &vbase_prot, + base, NULL, MMU_DATA_LOAD, + mmu_idx, false, true, + is_debug); + + if (vbase_ret != TRANSLATE_SUCCESS) { + if (fault_pte_addr) { + *fault_pte_addr = (base + idx * ptesize) >> 2; + } + return TRANSLATE_G_STAGE_FAIL; + } + + pte_addr = vbase + idx * ptesize; + } else { + pte_addr = base + idx * ptesize; + } + + int pmp_prot; + int pmp_ret = get_physical_address_pmp(env, &pmp_prot, NULL, pte_addr, + sizeof(target_ulong), + MMU_DATA_LOAD, PRV_S); + if (pmp_ret != TRANSLATE_SUCCESS) { + return TRANSLATE_PMP_FAIL; + } + + target_ulong pte; + if (riscv_cpu_mxl(env) == MXL_RV32) { + pte = address_space_ldl(cs->as, pte_addr, attrs, &res); + } else { + pte = address_space_ldq(cs->as, pte_addr, attrs, &res); + } + + if (res != MEMTX_OK) { + return TRANSLATE_FAIL; + } + + hwaddr ppn = pte >> PTE_PPN_SHIFT; + + if (!(pte & PTE_V)) { + /* Invalid PTE */ + return TRANSLATE_FAIL; + } else if (!(pte & (PTE_R | PTE_W | PTE_X))) { + /* Inner PTE, continue walking */ + base = ppn << PGSHIFT; + } else if ((pte & (PTE_R | PTE_W | PTE_X)) == PTE_W) { + /* Reserved leaf PTE flags: PTE_W */ + return TRANSLATE_FAIL; + } else if ((pte & (PTE_R | PTE_W | PTE_X)) == (PTE_W | PTE_X)) { + /* Reserved leaf PTE flags: PTE_W + PTE_X */ + return TRANSLATE_FAIL; + } else if ((pte & PTE_U) && ((mode != PRV_U) && + (!sum || access_type == MMU_INST_FETCH))) { + /* User PTE flags when not U mode and mstatus.SUM is not set, + or the access type is an instruction fetch */ + return TRANSLATE_FAIL; + } else if (!(pte & PTE_U) && (mode != PRV_S)) { + /* Supervisor PTE flags when not S mode */ + return TRANSLATE_FAIL; + } else if (ppn & ((1ULL << ptshift) - 1)) { + /* Misaligned PPN */ + return TRANSLATE_FAIL; + } else if (access_type == MMU_DATA_LOAD && !((pte & PTE_R) || + ((pte & PTE_X) && mxr))) { + /* Read access check failed */ + return TRANSLATE_FAIL; + } else if (access_type == MMU_DATA_STORE && !(pte & PTE_W)) { + /* Write access check failed */ + return TRANSLATE_FAIL; + } else if (access_type == MMU_INST_FETCH && !(pte & PTE_X)) { + /* Fetch access check failed */ + return TRANSLATE_FAIL; + } else { + /* if necessary, set accessed and dirty bits. */ + target_ulong updated_pte = pte | PTE_A | + (access_type == MMU_DATA_STORE ? PTE_D : 0); + + /* Page table updates need to be atomic with MTTCG enabled */ + if (updated_pte != pte) { + /* + * - if accessed or dirty bits need updating, and the PTE is + * in RAM, then we do so atomically with a compare and swap. + * - if the PTE is in IO space or ROM, then it can't be updated + * and we return TRANSLATE_FAIL. + * - if the PTE changed by the time we went to update it, then + * it is no longer valid and we must re-walk the page table. + */ + MemoryRegion *mr; + hwaddr l = sizeof(target_ulong), addr1; + mr = address_space_translate(cs->as, pte_addr, + &addr1, &l, false, MEMTXATTRS_UNSPECIFIED); + if (memory_region_is_ram(mr)) { + target_ulong *pte_pa = + qemu_map_ram_ptr(mr->ram_block, addr1); +#if TCG_OVERSIZED_GUEST + /* MTTCG is not enabled on oversized TCG guests so + * page table updates do not need to be atomic */ + *pte_pa = pte = updated_pte; +#else + target_ulong old_pte = + qatomic_cmpxchg(pte_pa, pte, updated_pte); + if (old_pte != pte) { + goto restart; + } else { + pte = updated_pte; + } +#endif + } else { + /* misconfigured PTE in ROM (AD bits are not preset) or + * PTE is in IO space and can't be updated atomically */ + return TRANSLATE_FAIL; + } + } + + /* for superpage mappings, make a fake leaf PTE for the TLB's + benefit. */ + target_ulong vpn = addr >> PGSHIFT; + *physical = ((ppn | (vpn & ((1L << ptshift) - 1))) << PGSHIFT) | + (addr & ~TARGET_PAGE_MASK); + + /* set permissions on the TLB entry */ + if ((pte & PTE_R) || ((pte & PTE_X) && mxr)) { + *prot |= PAGE_READ; + } + if ((pte & PTE_X)) { + *prot |= PAGE_EXEC; + } + /* add write permission on stores or if the page is already dirty, + so that we TLB miss on later writes to update the dirty bit */ + if ((pte & PTE_W) && + (access_type == MMU_DATA_STORE || (pte & PTE_D))) { + *prot |= PAGE_WRITE; + } + return TRANSLATE_SUCCESS; + } + } + return TRANSLATE_FAIL; +} + +static void raise_mmu_exception(CPURISCVState *env, target_ulong address, + MMUAccessType access_type, bool pmp_violation, + bool first_stage, bool two_stage) +{ + CPUState *cs = env_cpu(env); + int page_fault_exceptions, vm; + uint64_t stap_mode; + + if (riscv_cpu_mxl(env) == MXL_RV32) { + stap_mode = SATP32_MODE; + } else { + stap_mode = SATP64_MODE; + } + + if (first_stage) { + vm = get_field(env->satp, stap_mode); + } else { + vm = get_field(env->hgatp, stap_mode); + } + + page_fault_exceptions = vm != VM_1_10_MBARE && !pmp_violation; + + switch (access_type) { + case MMU_INST_FETCH: + if (riscv_cpu_virt_enabled(env) && !first_stage) { + cs->exception_index = RISCV_EXCP_INST_GUEST_PAGE_FAULT; + } else { + cs->exception_index = page_fault_exceptions ? + RISCV_EXCP_INST_PAGE_FAULT : RISCV_EXCP_INST_ACCESS_FAULT; + } + break; + case MMU_DATA_LOAD: + if (two_stage && !first_stage) { + cs->exception_index = RISCV_EXCP_LOAD_GUEST_ACCESS_FAULT; + } else { + cs->exception_index = page_fault_exceptions ? + RISCV_EXCP_LOAD_PAGE_FAULT : RISCV_EXCP_LOAD_ACCESS_FAULT; + } + break; + case MMU_DATA_STORE: + if (two_stage && !first_stage) { + cs->exception_index = RISCV_EXCP_STORE_GUEST_AMO_ACCESS_FAULT; + } else { + cs->exception_index = page_fault_exceptions ? + RISCV_EXCP_STORE_PAGE_FAULT : RISCV_EXCP_STORE_AMO_ACCESS_FAULT; + } + break; + default: + g_assert_not_reached(); + } + env->badaddr = address; + env->two_stage_lookup = two_stage; +} + +hwaddr riscv_cpu_get_phys_page_debug(CPUState *cs, vaddr addr) +{ + RISCVCPU *cpu = RISCV_CPU(cs); + CPURISCVState *env = &cpu->env; + hwaddr phys_addr; + int prot; + int mmu_idx = cpu_mmu_index(&cpu->env, false); + + if (get_physical_address(env, &phys_addr, &prot, addr, NULL, 0, mmu_idx, + true, riscv_cpu_virt_enabled(env), true)) { + return -1; + } + + if (riscv_cpu_virt_enabled(env)) { + if (get_physical_address(env, &phys_addr, &prot, phys_addr, NULL, + 0, mmu_idx, false, true, true)) { + return -1; + } + } + + return phys_addr & TARGET_PAGE_MASK; +} + +void riscv_cpu_do_transaction_failed(CPUState *cs, hwaddr physaddr, + vaddr addr, unsigned size, + MMUAccessType access_type, + int mmu_idx, MemTxAttrs attrs, + MemTxResult response, uintptr_t retaddr) +{ + RISCVCPU *cpu = RISCV_CPU(cs); + CPURISCVState *env = &cpu->env; + + if (access_type == MMU_DATA_STORE) { + cs->exception_index = RISCV_EXCP_STORE_AMO_ACCESS_FAULT; + } else if (access_type == MMU_DATA_LOAD) { + cs->exception_index = RISCV_EXCP_LOAD_ACCESS_FAULT; + } else { + cs->exception_index = RISCV_EXCP_INST_ACCESS_FAULT; + } + + env->badaddr = addr; + env->two_stage_lookup = riscv_cpu_virt_enabled(env) || + riscv_cpu_two_stage_lookup(mmu_idx); + riscv_raise_exception(&cpu->env, cs->exception_index, retaddr); +} + +void riscv_cpu_do_unaligned_access(CPUState *cs, vaddr addr, + MMUAccessType access_type, int mmu_idx, + uintptr_t retaddr) +{ + RISCVCPU *cpu = RISCV_CPU(cs); + CPURISCVState *env = &cpu->env; + switch (access_type) { + case MMU_INST_FETCH: + cs->exception_index = RISCV_EXCP_INST_ADDR_MIS; + break; + case MMU_DATA_LOAD: + cs->exception_index = RISCV_EXCP_LOAD_ADDR_MIS; + break; + case MMU_DATA_STORE: + cs->exception_index = RISCV_EXCP_STORE_AMO_ADDR_MIS; + break; + default: + g_assert_not_reached(); + } + env->badaddr = addr; + env->two_stage_lookup = riscv_cpu_virt_enabled(env) || + riscv_cpu_two_stage_lookup(mmu_idx); + riscv_raise_exception(env, cs->exception_index, retaddr); +} + +bool riscv_cpu_tlb_fill(CPUState *cs, vaddr address, int size, + MMUAccessType access_type, int mmu_idx, + bool probe, uintptr_t retaddr) +{ + RISCVCPU *cpu = RISCV_CPU(cs); + CPURISCVState *env = &cpu->env; + vaddr im_address; + hwaddr pa = 0; + int prot, prot2, prot_pmp; + bool pmp_violation = false; + bool first_stage_error = true; + bool two_stage_lookup = false; + int ret = TRANSLATE_FAIL; + int mode = mmu_idx; + /* default TLB page size */ + target_ulong tlb_size = TARGET_PAGE_SIZE; + + env->guest_phys_fault_addr = 0; + + qemu_log_mask(CPU_LOG_MMU, "%s ad %" VADDR_PRIx " rw %d mmu_idx %d\n", + __func__, address, access_type, mmu_idx); + + /* MPRV does not affect the virtual-machine load/store + instructions, HLV, HLVX, and HSV. */ + if (riscv_cpu_two_stage_lookup(mmu_idx)) { + mode = get_field(env->hstatus, HSTATUS_SPVP); + } else if (mode == PRV_M && access_type != MMU_INST_FETCH && + get_field(env->mstatus, MSTATUS_MPRV)) { + mode = get_field(env->mstatus, MSTATUS_MPP); + if (riscv_has_ext(env, RVH) && get_field(env->mstatus, MSTATUS_MPV)) { + two_stage_lookup = true; + } + } + + if (riscv_cpu_virt_enabled(env) || + ((riscv_cpu_two_stage_lookup(mmu_idx) || two_stage_lookup) && + access_type != MMU_INST_FETCH)) { + /* Two stage lookup */ + ret = get_physical_address(env, &pa, &prot, address, + &env->guest_phys_fault_addr, access_type, + mmu_idx, true, true, false); + + /* + * A G-stage exception may be triggered during two state lookup. + * And the env->guest_phys_fault_addr has already been set in + * get_physical_address(). + */ + if (ret == TRANSLATE_G_STAGE_FAIL) { + first_stage_error = false; + access_type = MMU_DATA_LOAD; + } + + qemu_log_mask(CPU_LOG_MMU, + "%s 1st-stage address=%" VADDR_PRIx " ret %d physical " + TARGET_FMT_plx " prot %d\n", + __func__, address, ret, pa, prot); + + if (ret == TRANSLATE_SUCCESS) { + /* Second stage lookup */ + im_address = pa; + + ret = get_physical_address(env, &pa, &prot2, im_address, NULL, + access_type, mmu_idx, false, true, + false); + + qemu_log_mask(CPU_LOG_MMU, + "%s 2nd-stage address=%" VADDR_PRIx " ret %d physical " + TARGET_FMT_plx " prot %d\n", + __func__, im_address, ret, pa, prot2); + + prot &= prot2; + + if (ret == TRANSLATE_SUCCESS) { + ret = get_physical_address_pmp(env, &prot_pmp, &tlb_size, pa, + size, access_type, mode); + + qemu_log_mask(CPU_LOG_MMU, + "%s PMP address=" TARGET_FMT_plx " ret %d prot" + " %d tlb_size " TARGET_FMT_lu "\n", + __func__, pa, ret, prot_pmp, tlb_size); + + prot &= prot_pmp; + } + + if (ret != TRANSLATE_SUCCESS) { + /* + * Guest physical address translation failed, this is a HS + * level exception + */ + first_stage_error = false; + env->guest_phys_fault_addr = (im_address | + (address & + (TARGET_PAGE_SIZE - 1))) >> 2; + } + } + } else { + /* Single stage lookup */ + ret = get_physical_address(env, &pa, &prot, address, NULL, + access_type, mmu_idx, true, false, false); + + qemu_log_mask(CPU_LOG_MMU, + "%s address=%" VADDR_PRIx " ret %d physical " + TARGET_FMT_plx " prot %d\n", + __func__, address, ret, pa, prot); + + if (ret == TRANSLATE_SUCCESS) { + ret = get_physical_address_pmp(env, &prot_pmp, &tlb_size, pa, + size, access_type, mode); + + qemu_log_mask(CPU_LOG_MMU, + "%s PMP address=" TARGET_FMT_plx " ret %d prot" + " %d tlb_size " TARGET_FMT_lu "\n", + __func__, pa, ret, prot_pmp, tlb_size); + + prot &= prot_pmp; + } + } + + if (ret == TRANSLATE_PMP_FAIL) { + pmp_violation = true; + } + + if (ret == TRANSLATE_SUCCESS) { + tlb_set_page(cs, address & ~(tlb_size - 1), pa & ~(tlb_size - 1), + prot, mmu_idx, tlb_size); + return true; + } else if (probe) { + return false; + } else { + raise_mmu_exception(env, address, access_type, pmp_violation, + first_stage_error, + riscv_cpu_virt_enabled(env) || + riscv_cpu_two_stage_lookup(mmu_idx)); + riscv_raise_exception(env, cs->exception_index, retaddr); + } + + return true; +} +#endif /* !CONFIG_USER_ONLY */ + +/* + * Handle Traps + * + * Adapted from Spike's processor_t::take_trap. + * + */ +void riscv_cpu_do_interrupt(CPUState *cs) +{ +#if !defined(CONFIG_USER_ONLY) + + RISCVCPU *cpu = RISCV_CPU(cs); + CPURISCVState *env = &cpu->env; + uint64_t s; + + /* cs->exception is 32-bits wide unlike mcause which is XLEN-bits wide + * so we mask off the MSB and separate into trap type and cause. + */ + bool async = !!(cs->exception_index & RISCV_EXCP_INT_FLAG); + target_ulong cause = cs->exception_index & RISCV_EXCP_INT_MASK; + target_ulong deleg = async ? env->mideleg : env->medeleg; + bool write_tval = false; + target_ulong tval = 0; + target_ulong htval = 0; + target_ulong mtval2 = 0; + + if (cause == RISCV_EXCP_SEMIHOST) { + if (env->priv >= PRV_S) { + env->gpr[xA0] = do_common_semihosting(cs); + env->pc += 4; + return; + } + cause = RISCV_EXCP_BREAKPOINT; + } + + if (!async) { + /* set tval to badaddr for traps with address information */ + switch (cause) { + case RISCV_EXCP_INST_GUEST_PAGE_FAULT: + case RISCV_EXCP_LOAD_GUEST_ACCESS_FAULT: + case RISCV_EXCP_STORE_GUEST_AMO_ACCESS_FAULT: + case RISCV_EXCP_INST_ADDR_MIS: + case RISCV_EXCP_INST_ACCESS_FAULT: + case RISCV_EXCP_LOAD_ADDR_MIS: + case RISCV_EXCP_STORE_AMO_ADDR_MIS: + case RISCV_EXCP_LOAD_ACCESS_FAULT: + case RISCV_EXCP_STORE_AMO_ACCESS_FAULT: + case RISCV_EXCP_INST_PAGE_FAULT: + case RISCV_EXCP_LOAD_PAGE_FAULT: + case RISCV_EXCP_STORE_PAGE_FAULT: + write_tval = true; + tval = env->badaddr; + break; + default: + break; + } + /* ecall is dispatched as one cause so translate based on mode */ + if (cause == RISCV_EXCP_U_ECALL) { + assert(env->priv <= 3); + + if (env->priv == PRV_M) { + cause = RISCV_EXCP_M_ECALL; + } else if (env->priv == PRV_S && riscv_cpu_virt_enabled(env)) { + cause = RISCV_EXCP_VS_ECALL; + } else if (env->priv == PRV_S && !riscv_cpu_virt_enabled(env)) { + cause = RISCV_EXCP_S_ECALL; + } else if (env->priv == PRV_U) { + cause = RISCV_EXCP_U_ECALL; + } + } + } + + trace_riscv_trap(env->mhartid, async, cause, env->pc, tval, + riscv_cpu_get_trap_name(cause, async)); + + qemu_log_mask(CPU_LOG_INT, + "%s: hart:"TARGET_FMT_ld", async:%d, cause:"TARGET_FMT_lx", " + "epc:0x"TARGET_FMT_lx", tval:0x"TARGET_FMT_lx", desc=%s\n", + __func__, env->mhartid, async, cause, env->pc, tval, + riscv_cpu_get_trap_name(cause, async)); + + if (env->priv <= PRV_S && + cause < TARGET_LONG_BITS && ((deleg >> cause) & 1)) { + /* handle the trap in S-mode */ + if (riscv_has_ext(env, RVH)) { + target_ulong hdeleg = async ? env->hideleg : env->hedeleg; + + if (env->two_stage_lookup && write_tval) { + /* + * If we are writing a guest virtual address to stval, set + * this to 1. If we are trapping to VS we will set this to 0 + * later. + */ + env->hstatus = set_field(env->hstatus, HSTATUS_GVA, 1); + } else { + /* For other HS-mode traps, we set this to 0. */ + env->hstatus = set_field(env->hstatus, HSTATUS_GVA, 0); + } + + if (riscv_cpu_virt_enabled(env) && ((hdeleg >> cause) & 1)) { + /* Trap to VS mode */ + /* + * See if we need to adjust cause. Yes if its VS mode interrupt + * no if hypervisor has delegated one of hs mode's interrupt + */ + if (cause == IRQ_VS_TIMER || cause == IRQ_VS_SOFT || + cause == IRQ_VS_EXT) { + cause = cause - 1; + } + env->hstatus = set_field(env->hstatus, HSTATUS_GVA, 0); + } else if (riscv_cpu_virt_enabled(env)) { + /* Trap into HS mode, from virt */ + riscv_cpu_swap_hypervisor_regs(env); + env->hstatus = set_field(env->hstatus, HSTATUS_SPVP, + env->priv); + env->hstatus = set_field(env->hstatus, HSTATUS_SPV, + riscv_cpu_virt_enabled(env)); + + htval = env->guest_phys_fault_addr; + + riscv_cpu_set_virt_enabled(env, 0); + } else { + /* Trap into HS mode */ + env->hstatus = set_field(env->hstatus, HSTATUS_SPV, false); + htval = env->guest_phys_fault_addr; + } + } + + s = env->mstatus; + s = set_field(s, MSTATUS_SPIE, get_field(s, MSTATUS_SIE)); + s = set_field(s, MSTATUS_SPP, env->priv); + s = set_field(s, MSTATUS_SIE, 0); + env->mstatus = s; + env->scause = cause | ((target_ulong)async << (TARGET_LONG_BITS - 1)); + env->sepc = env->pc; + env->stval = tval; + env->htval = htval; + env->pc = (env->stvec >> 2 << 2) + + ((async && (env->stvec & 3) == 1) ? cause * 4 : 0); + riscv_cpu_set_mode(env, PRV_S); + } else { + /* handle the trap in M-mode */ + if (riscv_has_ext(env, RVH)) { + if (riscv_cpu_virt_enabled(env)) { + riscv_cpu_swap_hypervisor_regs(env); + } + env->mstatus = set_field(env->mstatus, MSTATUS_MPV, + riscv_cpu_virt_enabled(env)); + if (riscv_cpu_virt_enabled(env) && tval) { + env->mstatus = set_field(env->mstatus, MSTATUS_GVA, 1); + } + + mtval2 = env->guest_phys_fault_addr; + + /* Trapping to M mode, virt is disabled */ + riscv_cpu_set_virt_enabled(env, 0); + } + + s = env->mstatus; + s = set_field(s, MSTATUS_MPIE, get_field(s, MSTATUS_MIE)); + s = set_field(s, MSTATUS_MPP, env->priv); + s = set_field(s, MSTATUS_MIE, 0); + env->mstatus = s; + env->mcause = cause | ~(((target_ulong)-1) >> async); + env->mepc = env->pc; + env->mtval = tval; + env->mtval2 = mtval2; + env->pc = (env->mtvec >> 2 << 2) + + ((async && (env->mtvec & 3) == 1) ? cause * 4 : 0); + riscv_cpu_set_mode(env, PRV_M); + } + + /* NOTE: it is not necessary to yield load reservations here. It is only + * necessary for an SC from "another hart" to cause a load reservation + * to be yielded. Refer to the memory consistency model section of the + * RISC-V ISA Specification. + */ + + env->two_stage_lookup = false; +#endif + cs->exception_index = RISCV_EXCP_NONE; /* mark handled to qemu */ +} diff --git a/target/riscv/cpu_user.h b/target/riscv/cpu_user.h new file mode 100644 index 000000000..02afad608 --- /dev/null +++ b/target/riscv/cpu_user.h @@ -0,0 +1,19 @@ +#ifndef TARGET_RISCV_CPU_USER_H +#define TARGET_RISCV_CPU_USER_H + +#define xRA 1 /* return address (aka link register) */ +#define xSP 2 /* stack pointer */ +#define xGP 3 /* global pointer */ +#define xTP 4 /* thread pointer */ + +#define xA0 10 /* gpr[10-17] are syscall arguments */ +#define xA1 11 +#define xA2 12 +#define xA3 13 +#define xA4 14 +#define xA5 15 +#define xA6 16 +#define xA7 17 /* syscall number for RVI ABI */ +#define xT0 5 /* syscall number for RVE ABI */ + +#endif diff --git a/target/riscv/csr.c b/target/riscv/csr.c new file mode 100644 index 000000000..9f4195489 --- /dev/null +++ b/target/riscv/csr.c @@ -0,0 +1,2098 @@ +/* + * RISC-V Control and Status Registers. + * + * Copyright (c) 2016-2017 Sagar Karandikar, sagark@eecs.berkeley.edu + * Copyright (c) 2017-2018 SiFive, Inc. + * + * 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/log.h" +#include "cpu.h" +#include "qemu/main-loop.h" +#include "exec/exec-all.h" + +/* CSR function table public API */ +void riscv_get_csr_ops(int csrno, riscv_csr_operations *ops) +{ + *ops = csr_ops[csrno & (CSR_TABLE_SIZE - 1)]; +} + +void riscv_set_csr_ops(int csrno, riscv_csr_operations *ops) +{ + csr_ops[csrno & (CSR_TABLE_SIZE - 1)] = *ops; +} + +/* Predicates */ +static RISCVException fs(CPURISCVState *env, int csrno) +{ +#if !defined(CONFIG_USER_ONLY) + /* loose check condition for fcsr in vector extension */ + if ((csrno == CSR_FCSR) && (env->misa_ext & RVV)) { + return RISCV_EXCP_NONE; + } + if (!env->debugger && !riscv_cpu_fp_enabled(env)) { + return RISCV_EXCP_ILLEGAL_INST; + } +#endif + return RISCV_EXCP_NONE; +} + +static RISCVException vs(CPURISCVState *env, int csrno) +{ + if (env->misa_ext & RVV) { + return RISCV_EXCP_NONE; + } + return RISCV_EXCP_ILLEGAL_INST; +} + +static RISCVException ctr(CPURISCVState *env, int csrno) +{ +#if !defined(CONFIG_USER_ONLY) + CPUState *cs = env_cpu(env); + RISCVCPU *cpu = RISCV_CPU(cs); + + if (!cpu->cfg.ext_counters) { + /* The Counters extensions is not enabled */ + return RISCV_EXCP_ILLEGAL_INST; + } + + if (riscv_cpu_virt_enabled(env)) { + switch (csrno) { + case CSR_CYCLE: + if (!get_field(env->hcounteren, COUNTEREN_CY) && + get_field(env->mcounteren, COUNTEREN_CY)) { + return RISCV_EXCP_VIRT_INSTRUCTION_FAULT; + } + break; + case CSR_TIME: + if (!get_field(env->hcounteren, COUNTEREN_TM) && + get_field(env->mcounteren, COUNTEREN_TM)) { + return RISCV_EXCP_VIRT_INSTRUCTION_FAULT; + } + break; + case CSR_INSTRET: + if (!get_field(env->hcounteren, COUNTEREN_IR) && + get_field(env->mcounteren, COUNTEREN_IR)) { + return RISCV_EXCP_VIRT_INSTRUCTION_FAULT; + } + break; + case CSR_HPMCOUNTER3...CSR_HPMCOUNTER31: + if (!get_field(env->hcounteren, 1 << (csrno - CSR_HPMCOUNTER3)) && + get_field(env->mcounteren, 1 << (csrno - CSR_HPMCOUNTER3))) { + return RISCV_EXCP_VIRT_INSTRUCTION_FAULT; + } + break; + } + if (riscv_cpu_mxl(env) == MXL_RV32) { + switch (csrno) { + case CSR_CYCLEH: + if (!get_field(env->hcounteren, COUNTEREN_CY) && + get_field(env->mcounteren, COUNTEREN_CY)) { + return RISCV_EXCP_VIRT_INSTRUCTION_FAULT; + } + break; + case CSR_TIMEH: + if (!get_field(env->hcounteren, COUNTEREN_TM) && + get_field(env->mcounteren, COUNTEREN_TM)) { + return RISCV_EXCP_VIRT_INSTRUCTION_FAULT; + } + break; + case CSR_INSTRETH: + if (!get_field(env->hcounteren, COUNTEREN_IR) && + get_field(env->mcounteren, COUNTEREN_IR)) { + return RISCV_EXCP_VIRT_INSTRUCTION_FAULT; + } + break; + case CSR_HPMCOUNTER3H...CSR_HPMCOUNTER31H: + if (!get_field(env->hcounteren, 1 << (csrno - CSR_HPMCOUNTER3H)) && + get_field(env->mcounteren, 1 << (csrno - CSR_HPMCOUNTER3H))) { + return RISCV_EXCP_VIRT_INSTRUCTION_FAULT; + } + break; + } + } + } +#endif + return RISCV_EXCP_NONE; +} + +static RISCVException ctr32(CPURISCVState *env, int csrno) +{ + if (riscv_cpu_mxl(env) != MXL_RV32) { + return RISCV_EXCP_ILLEGAL_INST; + } + + return ctr(env, csrno); +} + +#if !defined(CONFIG_USER_ONLY) +static RISCVException any(CPURISCVState *env, int csrno) +{ + return RISCV_EXCP_NONE; +} + +static RISCVException any32(CPURISCVState *env, int csrno) +{ + if (riscv_cpu_mxl(env) != MXL_RV32) { + return RISCV_EXCP_ILLEGAL_INST; + } + + return any(env, csrno); + +} + +static RISCVException smode(CPURISCVState *env, int csrno) +{ + if (riscv_has_ext(env, RVS)) { + return RISCV_EXCP_NONE; + } + + return RISCV_EXCP_ILLEGAL_INST; +} + +static RISCVException hmode(CPURISCVState *env, int csrno) +{ + if (riscv_has_ext(env, RVS) && + riscv_has_ext(env, RVH)) { + /* Hypervisor extension is supported */ + if ((env->priv == PRV_S && !riscv_cpu_virt_enabled(env)) || + env->priv == PRV_M) { + return RISCV_EXCP_NONE; + } else { + return RISCV_EXCP_VIRT_INSTRUCTION_FAULT; + } + } + + return RISCV_EXCP_ILLEGAL_INST; +} + +static RISCVException hmode32(CPURISCVState *env, int csrno) +{ + if (riscv_cpu_mxl(env) != MXL_RV32) { + if (riscv_cpu_virt_enabled(env)) { + return RISCV_EXCP_ILLEGAL_INST; + } else { + return RISCV_EXCP_VIRT_INSTRUCTION_FAULT; + } + } + + return hmode(env, csrno); + +} + +/* Checks if PointerMasking registers could be accessed */ +static RISCVException pointer_masking(CPURISCVState *env, int csrno) +{ + /* Check if j-ext is present */ + if (riscv_has_ext(env, RVJ)) { + return RISCV_EXCP_NONE; + } + return RISCV_EXCP_ILLEGAL_INST; +} + +static RISCVException pmp(CPURISCVState *env, int csrno) +{ + if (riscv_feature(env, RISCV_FEATURE_PMP)) { + return RISCV_EXCP_NONE; + } + + return RISCV_EXCP_ILLEGAL_INST; +} + +static RISCVException epmp(CPURISCVState *env, int csrno) +{ + if (env->priv == PRV_M && riscv_feature(env, RISCV_FEATURE_EPMP)) { + return RISCV_EXCP_NONE; + } + + return RISCV_EXCP_ILLEGAL_INST; +} +#endif + +/* User Floating-Point CSRs */ +static RISCVException read_fflags(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = riscv_cpu_get_fflags(env); + return RISCV_EXCP_NONE; +} + +static RISCVException write_fflags(CPURISCVState *env, int csrno, + target_ulong val) +{ +#if !defined(CONFIG_USER_ONLY) + env->mstatus |= MSTATUS_FS; +#endif + riscv_cpu_set_fflags(env, val & (FSR_AEXC >> FSR_AEXC_SHIFT)); + return RISCV_EXCP_NONE; +} + +static RISCVException read_frm(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->frm; + return RISCV_EXCP_NONE; +} + +static RISCVException write_frm(CPURISCVState *env, int csrno, + target_ulong val) +{ +#if !defined(CONFIG_USER_ONLY) + env->mstatus |= MSTATUS_FS; +#endif + env->frm = val & (FSR_RD >> FSR_RD_SHIFT); + return RISCV_EXCP_NONE; +} + +static RISCVException read_fcsr(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = (riscv_cpu_get_fflags(env) << FSR_AEXC_SHIFT) + | (env->frm << FSR_RD_SHIFT); + if (vs(env, csrno) >= 0) { + *val |= (env->vxrm << FSR_VXRM_SHIFT) + | (env->vxsat << FSR_VXSAT_SHIFT); + } + return RISCV_EXCP_NONE; +} + +static RISCVException write_fcsr(CPURISCVState *env, int csrno, + target_ulong val) +{ +#if !defined(CONFIG_USER_ONLY) + env->mstatus |= MSTATUS_FS; +#endif + env->frm = (val & FSR_RD) >> FSR_RD_SHIFT; + if (vs(env, csrno) >= 0) { + env->vxrm = (val & FSR_VXRM) >> FSR_VXRM_SHIFT; + env->vxsat = (val & FSR_VXSAT) >> FSR_VXSAT_SHIFT; + } + riscv_cpu_set_fflags(env, (val & FSR_AEXC) >> FSR_AEXC_SHIFT); + return RISCV_EXCP_NONE; +} + +static RISCVException read_vtype(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->vtype; + return RISCV_EXCP_NONE; +} + +static RISCVException read_vl(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->vl; + return RISCV_EXCP_NONE; +} + +static RISCVException read_vxrm(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->vxrm; + return RISCV_EXCP_NONE; +} + +static RISCVException write_vxrm(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->vxrm = val; + return RISCV_EXCP_NONE; +} + +static RISCVException read_vxsat(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->vxsat; + return RISCV_EXCP_NONE; +} + +static RISCVException write_vxsat(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->vxsat = val; + return RISCV_EXCP_NONE; +} + +static RISCVException read_vstart(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->vstart; + return RISCV_EXCP_NONE; +} + +static RISCVException write_vstart(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->vstart = val; + return RISCV_EXCP_NONE; +} + +/* User Timers and Counters */ +static RISCVException read_instret(CPURISCVState *env, int csrno, + target_ulong *val) +{ +#if !defined(CONFIG_USER_ONLY) + if (icount_enabled()) { + *val = icount_get(); + } else { + *val = cpu_get_host_ticks(); + } +#else + *val = cpu_get_host_ticks(); +#endif + return RISCV_EXCP_NONE; +} + +static RISCVException read_instreth(CPURISCVState *env, int csrno, + target_ulong *val) +{ +#if !defined(CONFIG_USER_ONLY) + if (icount_enabled()) { + *val = icount_get() >> 32; + } else { + *val = cpu_get_host_ticks() >> 32; + } +#else + *val = cpu_get_host_ticks() >> 32; +#endif + return RISCV_EXCP_NONE; +} + +#if defined(CONFIG_USER_ONLY) +static RISCVException read_time(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = cpu_get_host_ticks(); + return RISCV_EXCP_NONE; +} + +static RISCVException read_timeh(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = cpu_get_host_ticks() >> 32; + return RISCV_EXCP_NONE; +} + +#else /* CONFIG_USER_ONLY */ + +static RISCVException read_time(CPURISCVState *env, int csrno, + target_ulong *val) +{ + uint64_t delta = riscv_cpu_virt_enabled(env) ? env->htimedelta : 0; + + if (!env->rdtime_fn) { + return RISCV_EXCP_ILLEGAL_INST; + } + + *val = env->rdtime_fn(env->rdtime_fn_arg) + delta; + return RISCV_EXCP_NONE; +} + +static RISCVException read_timeh(CPURISCVState *env, int csrno, + target_ulong *val) +{ + uint64_t delta = riscv_cpu_virt_enabled(env) ? env->htimedelta : 0; + + if (!env->rdtime_fn) { + return RISCV_EXCP_ILLEGAL_INST; + } + + *val = (env->rdtime_fn(env->rdtime_fn_arg) + delta) >> 32; + return RISCV_EXCP_NONE; +} + +/* Machine constants */ + +#define M_MODE_INTERRUPTS (MIP_MSIP | MIP_MTIP | MIP_MEIP) +#define S_MODE_INTERRUPTS (MIP_SSIP | MIP_STIP | MIP_SEIP) +#define VS_MODE_INTERRUPTS (MIP_VSSIP | MIP_VSTIP | MIP_VSEIP) + +static const target_ulong delegable_ints = S_MODE_INTERRUPTS | + VS_MODE_INTERRUPTS; +static const target_ulong vs_delegable_ints = VS_MODE_INTERRUPTS; +static const target_ulong all_ints = M_MODE_INTERRUPTS | S_MODE_INTERRUPTS | + VS_MODE_INTERRUPTS; +#define DELEGABLE_EXCPS ((1ULL << (RISCV_EXCP_INST_ADDR_MIS)) | \ + (1ULL << (RISCV_EXCP_INST_ACCESS_FAULT)) | \ + (1ULL << (RISCV_EXCP_ILLEGAL_INST)) | \ + (1ULL << (RISCV_EXCP_BREAKPOINT)) | \ + (1ULL << (RISCV_EXCP_LOAD_ADDR_MIS)) | \ + (1ULL << (RISCV_EXCP_LOAD_ACCESS_FAULT)) | \ + (1ULL << (RISCV_EXCP_STORE_AMO_ADDR_MIS)) | \ + (1ULL << (RISCV_EXCP_STORE_AMO_ACCESS_FAULT)) | \ + (1ULL << (RISCV_EXCP_U_ECALL)) | \ + (1ULL << (RISCV_EXCP_S_ECALL)) | \ + (1ULL << (RISCV_EXCP_VS_ECALL)) | \ + (1ULL << (RISCV_EXCP_M_ECALL)) | \ + (1ULL << (RISCV_EXCP_INST_PAGE_FAULT)) | \ + (1ULL << (RISCV_EXCP_LOAD_PAGE_FAULT)) | \ + (1ULL << (RISCV_EXCP_STORE_PAGE_FAULT)) | \ + (1ULL << (RISCV_EXCP_INST_GUEST_PAGE_FAULT)) | \ + (1ULL << (RISCV_EXCP_LOAD_GUEST_ACCESS_FAULT)) | \ + (1ULL << (RISCV_EXCP_VIRT_INSTRUCTION_FAULT)) | \ + (1ULL << (RISCV_EXCP_STORE_GUEST_AMO_ACCESS_FAULT))) +static const target_ulong vs_delegable_excps = DELEGABLE_EXCPS & + ~((1ULL << (RISCV_EXCP_S_ECALL)) | + (1ULL << (RISCV_EXCP_VS_ECALL)) | + (1ULL << (RISCV_EXCP_M_ECALL)) | + (1ULL << (RISCV_EXCP_INST_GUEST_PAGE_FAULT)) | + (1ULL << (RISCV_EXCP_LOAD_GUEST_ACCESS_FAULT)) | + (1ULL << (RISCV_EXCP_VIRT_INSTRUCTION_FAULT)) | + (1ULL << (RISCV_EXCP_STORE_GUEST_AMO_ACCESS_FAULT))); +static const target_ulong sstatus_v1_10_mask = SSTATUS_SIE | SSTATUS_SPIE | + SSTATUS_UIE | SSTATUS_UPIE | SSTATUS_SPP | SSTATUS_FS | SSTATUS_XS | + SSTATUS_SUM | SSTATUS_MXR; +static const target_ulong sip_writable_mask = SIP_SSIP | MIP_USIP | MIP_UEIP; +static const target_ulong hip_writable_mask = MIP_VSSIP; +static const target_ulong hvip_writable_mask = MIP_VSSIP | MIP_VSTIP | MIP_VSEIP; +static const target_ulong vsip_writable_mask = MIP_VSSIP; + +static const char valid_vm_1_10_32[16] = { + [VM_1_10_MBARE] = 1, + [VM_1_10_SV32] = 1 +}; + +static const char valid_vm_1_10_64[16] = { + [VM_1_10_MBARE] = 1, + [VM_1_10_SV39] = 1, + [VM_1_10_SV48] = 1, + [VM_1_10_SV57] = 1 +}; + +/* Machine Information Registers */ +static RISCVException read_zero(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = 0; + return RISCV_EXCP_NONE; +} + +static RISCVException read_mhartid(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->mhartid; + return RISCV_EXCP_NONE; +} + +/* Machine Trap Setup */ + +/* We do not store SD explicitly, only compute it on demand. */ +static uint64_t add_status_sd(RISCVMXL xl, uint64_t status) +{ + if ((status & MSTATUS_FS) == MSTATUS_FS || + (status & MSTATUS_XS) == MSTATUS_XS) { + switch (xl) { + case MXL_RV32: + return status | MSTATUS32_SD; + case MXL_RV64: + return status | MSTATUS64_SD; + default: + g_assert_not_reached(); + } + } + return status; +} + +static RISCVException read_mstatus(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = add_status_sd(riscv_cpu_mxl(env), env->mstatus); + return RISCV_EXCP_NONE; +} + +static int validate_vm(CPURISCVState *env, target_ulong vm) +{ + if (riscv_cpu_mxl(env) == MXL_RV32) { + return valid_vm_1_10_32[vm & 0xf]; + } else { + return valid_vm_1_10_64[vm & 0xf]; + } +} + +static RISCVException write_mstatus(CPURISCVState *env, int csrno, + target_ulong val) +{ + uint64_t mstatus = env->mstatus; + uint64_t mask = 0; + + /* flush tlb on mstatus fields that affect VM */ + if ((val ^ mstatus) & (MSTATUS_MXR | MSTATUS_MPP | MSTATUS_MPV | + MSTATUS_MPRV | MSTATUS_SUM)) { + tlb_flush(env_cpu(env)); + } + mask = MSTATUS_SIE | MSTATUS_SPIE | MSTATUS_MIE | MSTATUS_MPIE | + MSTATUS_SPP | MSTATUS_FS | MSTATUS_MPRV | MSTATUS_SUM | + MSTATUS_MPP | MSTATUS_MXR | MSTATUS_TVM | MSTATUS_TSR | + MSTATUS_TW; + + if (riscv_cpu_mxl(env) != MXL_RV32) { + /* + * 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; + } + + mstatus = (mstatus & ~mask) | (val & mask); + + if (riscv_cpu_mxl(env) == MXL_RV64) { + /* SXL and UXL fields are for now read only */ + mstatus = set_field(mstatus, MSTATUS64_SXL, MXL_RV64); + mstatus = set_field(mstatus, MSTATUS64_UXL, MXL_RV64); + } + env->mstatus = mstatus; + + return RISCV_EXCP_NONE; +} + +static RISCVException read_mstatush(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->mstatus >> 32; + return RISCV_EXCP_NONE; +} + +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; + + if ((valh ^ env->mstatus) & (MSTATUS_MPV)) { + tlb_flush(env_cpu(env)); + } + + env->mstatus = (env->mstatus & ~mask) | (valh & mask); + + return RISCV_EXCP_NONE; +} + +static RISCVException read_misa(CPURISCVState *env, int csrno, + target_ulong *val) +{ + target_ulong misa; + + switch (env->misa_mxl) { + case MXL_RV32: + misa = (target_ulong)MXL_RV32 << 30; + break; +#ifdef TARGET_RISCV64 + case MXL_RV64: + misa = (target_ulong)MXL_RV64 << 62; + break; +#endif + default: + g_assert_not_reached(); + } + + *val = misa | env->misa_ext; + return RISCV_EXCP_NONE; +} + +static RISCVException write_misa(CPURISCVState *env, int csrno, + target_ulong val) +{ + if (!riscv_feature(env, RISCV_FEATURE_MISA)) { + /* drop write to misa */ + return RISCV_EXCP_NONE; + } + + /* 'I' or 'E' must be present */ + if (!(val & (RVI | RVE))) { + /* It is not, drop write to misa */ + return RISCV_EXCP_NONE; + } + + /* 'E' excludes all other extensions */ + if (val & RVE) { + /* when we support 'E' we can do "val = RVE;" however + * for now we just drop writes if 'E' is present. + */ + return RISCV_EXCP_NONE; + } + + /* + * misa.MXL writes are not supported by QEMU. + * Drop writes to those bits. + */ + + /* Mask extensions that are not supported by this hart */ + val &= env->misa_ext_mask; + + /* Mask extensions that are not supported by QEMU */ + val &= (RVI | RVE | RVM | RVA | RVF | RVD | RVC | RVS | RVU); + + /* 'D' depends on 'F', so clear 'D' if 'F' is not present */ + if ((val & RVD) && !(val & RVF)) { + val &= ~RVD; + } + + /* Suppress 'C' if next instruction is not aligned + * TODO: this should check next_pc + */ + if ((val & RVC) && (GETPC() & ~3) != 0) { + val &= ~RVC; + } + + /* If nothing changed, do nothing. */ + if (val == env->misa_ext) { + return RISCV_EXCP_NONE; + } + + /* flush translation cache */ + tb_flush(env_cpu(env)); + env->misa_ext = val; + return RISCV_EXCP_NONE; +} + +static RISCVException read_medeleg(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->medeleg; + return RISCV_EXCP_NONE; +} + +static RISCVException write_medeleg(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->medeleg = (env->medeleg & ~DELEGABLE_EXCPS) | (val & DELEGABLE_EXCPS); + return RISCV_EXCP_NONE; +} + +static RISCVException read_mideleg(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->mideleg; + return RISCV_EXCP_NONE; +} + +static RISCVException write_mideleg(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->mideleg = (env->mideleg & ~delegable_ints) | (val & delegable_ints); + if (riscv_has_ext(env, RVH)) { + env->mideleg |= VS_MODE_INTERRUPTS; + } + return RISCV_EXCP_NONE; +} + +static RISCVException read_mie(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->mie; + return RISCV_EXCP_NONE; +} + +static RISCVException write_mie(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->mie = (env->mie & ~all_ints) | (val & all_ints); + return RISCV_EXCP_NONE; +} + +static RISCVException read_mtvec(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->mtvec; + return RISCV_EXCP_NONE; +} + +static RISCVException write_mtvec(CPURISCVState *env, int csrno, + target_ulong val) +{ + /* bits [1:0] encode mode; 0 = direct, 1 = vectored, 2 >= reserved */ + if ((val & 3) < 2) { + env->mtvec = val; + } else { + qemu_log_mask(LOG_UNIMP, "CSR_MTVEC: reserved mode not supported\n"); + } + return RISCV_EXCP_NONE; +} + +static RISCVException read_mcounteren(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->mcounteren; + return RISCV_EXCP_NONE; +} + +static RISCVException write_mcounteren(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->mcounteren = val; + return RISCV_EXCP_NONE; +} + +/* Machine Trap Handling */ +static RISCVException read_mscratch(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->mscratch; + return RISCV_EXCP_NONE; +} + +static RISCVException write_mscratch(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->mscratch = val; + return RISCV_EXCP_NONE; +} + +static RISCVException read_mepc(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->mepc; + return RISCV_EXCP_NONE; +} + +static RISCVException write_mepc(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->mepc = val; + return RISCV_EXCP_NONE; +} + +static RISCVException read_mcause(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->mcause; + return RISCV_EXCP_NONE; +} + +static RISCVException write_mcause(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->mcause = val; + return RISCV_EXCP_NONE; +} + +static RISCVException read_mtval(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->mtval; + return RISCV_EXCP_NONE; +} + +static RISCVException write_mtval(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->mtval = val; + return RISCV_EXCP_NONE; +} + +static RISCVException rmw_mip(CPURISCVState *env, int csrno, + target_ulong *ret_value, + target_ulong new_value, target_ulong write_mask) +{ + RISCVCPU *cpu = env_archcpu(env); + /* Allow software control of delegable interrupts not claimed by hardware */ + target_ulong mask = write_mask & delegable_ints & ~env->miclaim; + uint32_t old_mip; + + if (mask) { + old_mip = riscv_cpu_update_mip(cpu, mask, (new_value & mask)); + } else { + old_mip = env->mip; + } + + if (ret_value) { + *ret_value = old_mip; + } + + return RISCV_EXCP_NONE; +} + +/* Supervisor Trap Setup */ +static RISCVException read_sstatus(CPURISCVState *env, int csrno, + target_ulong *val) +{ + target_ulong mask = (sstatus_v1_10_mask); + + /* TODO: Use SXL not MXL. */ + *val = add_status_sd(riscv_cpu_mxl(env), env->mstatus & mask); + return RISCV_EXCP_NONE; +} + +static RISCVException write_sstatus(CPURISCVState *env, int csrno, + target_ulong val) +{ + target_ulong mask = (sstatus_v1_10_mask); + target_ulong newval = (env->mstatus & ~mask) | (val & mask); + return write_mstatus(env, CSR_MSTATUS, newval); +} + +static RISCVException read_vsie(CPURISCVState *env, int csrno, + target_ulong *val) +{ + /* Shift the VS bits to their S bit location in vsie */ + *val = (env->mie & env->hideleg & VS_MODE_INTERRUPTS) >> 1; + return RISCV_EXCP_NONE; +} + +static RISCVException read_sie(CPURISCVState *env, int csrno, + target_ulong *val) +{ + if (riscv_cpu_virt_enabled(env)) { + read_vsie(env, CSR_VSIE, val); + } else { + *val = env->mie & env->mideleg; + } + return RISCV_EXCP_NONE; +} + +static RISCVException write_vsie(CPURISCVState *env, int csrno, + target_ulong val) +{ + /* Shift the S bits to their VS bit location in mie */ + target_ulong newval = (env->mie & ~VS_MODE_INTERRUPTS) | + ((val << 1) & env->hideleg & VS_MODE_INTERRUPTS); + return write_mie(env, CSR_MIE, newval); +} + +static int write_sie(CPURISCVState *env, int csrno, target_ulong val) +{ + if (riscv_cpu_virt_enabled(env)) { + write_vsie(env, CSR_VSIE, val); + } else { + target_ulong newval = (env->mie & ~S_MODE_INTERRUPTS) | + (val & S_MODE_INTERRUPTS); + write_mie(env, CSR_MIE, newval); + } + + return RISCV_EXCP_NONE; +} + +static RISCVException read_stvec(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->stvec; + return RISCV_EXCP_NONE; +} + +static RISCVException write_stvec(CPURISCVState *env, int csrno, + target_ulong val) +{ + /* bits [1:0] encode mode; 0 = direct, 1 = vectored, 2 >= reserved */ + if ((val & 3) < 2) { + env->stvec = val; + } else { + qemu_log_mask(LOG_UNIMP, "CSR_STVEC: reserved mode not supported\n"); + } + return RISCV_EXCP_NONE; +} + +static RISCVException read_scounteren(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->scounteren; + return RISCV_EXCP_NONE; +} + +static RISCVException write_scounteren(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->scounteren = val; + return RISCV_EXCP_NONE; +} + +/* Supervisor Trap Handling */ +static RISCVException read_sscratch(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->sscratch; + return RISCV_EXCP_NONE; +} + +static RISCVException write_sscratch(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->sscratch = val; + return RISCV_EXCP_NONE; +} + +static RISCVException read_sepc(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->sepc; + return RISCV_EXCP_NONE; +} + +static RISCVException write_sepc(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->sepc = val; + return RISCV_EXCP_NONE; +} + +static RISCVException read_scause(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->scause; + return RISCV_EXCP_NONE; +} + +static RISCVException write_scause(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->scause = val; + return RISCV_EXCP_NONE; +} + +static RISCVException read_stval(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->stval; + return RISCV_EXCP_NONE; +} + +static RISCVException write_stval(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->stval = val; + return RISCV_EXCP_NONE; +} + +static RISCVException rmw_vsip(CPURISCVState *env, int csrno, + target_ulong *ret_value, + target_ulong new_value, target_ulong write_mask) +{ + /* Shift the S bits to their VS bit location in mip */ + int ret = rmw_mip(env, 0, ret_value, new_value << 1, + (write_mask << 1) & vsip_writable_mask & env->hideleg); + + if (ret_value) { + *ret_value &= VS_MODE_INTERRUPTS; + /* Shift the VS bits to their S bit location in vsip */ + *ret_value >>= 1; + } + return ret; +} + +static RISCVException rmw_sip(CPURISCVState *env, int csrno, + target_ulong *ret_value, + target_ulong new_value, target_ulong write_mask) +{ + int ret; + + if (riscv_cpu_virt_enabled(env)) { + ret = rmw_vsip(env, CSR_VSIP, ret_value, new_value, write_mask); + } else { + ret = rmw_mip(env, CSR_MSTATUS, ret_value, new_value, + write_mask & env->mideleg & sip_writable_mask); + } + + if (ret_value) { + *ret_value &= env->mideleg; + } + return ret; +} + +/* Supervisor Protection and Translation */ +static RISCVException read_satp(CPURISCVState *env, int csrno, + target_ulong *val) +{ + if (!riscv_feature(env, RISCV_FEATURE_MMU)) { + *val = 0; + return RISCV_EXCP_NONE; + } + + if (env->priv == PRV_S && get_field(env->mstatus, MSTATUS_TVM)) { + return RISCV_EXCP_ILLEGAL_INST; + } else { + *val = env->satp; + } + + return RISCV_EXCP_NONE; +} + +static RISCVException write_satp(CPURISCVState *env, int csrno, + target_ulong val) +{ + target_ulong vm, mask, asid; + + if (!riscv_feature(env, RISCV_FEATURE_MMU)) { + return RISCV_EXCP_NONE; + } + + if (riscv_cpu_mxl(env) == MXL_RV32) { + vm = validate_vm(env, get_field(val, SATP32_MODE)); + mask = (val ^ env->satp) & (SATP32_MODE | SATP32_ASID | SATP32_PPN); + asid = (val ^ env->satp) & SATP32_ASID; + } else { + vm = validate_vm(env, get_field(val, SATP64_MODE)); + mask = (val ^ env->satp) & (SATP64_MODE | SATP64_ASID | SATP64_PPN); + asid = (val ^ env->satp) & SATP64_ASID; + } + + if (vm && mask) { + if (env->priv == PRV_S && get_field(env->mstatus, MSTATUS_TVM)) { + return RISCV_EXCP_ILLEGAL_INST; + } else { + if (asid) { + tlb_flush(env_cpu(env)); + } + env->satp = val; + } + } + return RISCV_EXCP_NONE; +} + +/* Hypervisor Extensions */ +static RISCVException read_hstatus(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->hstatus; + if (riscv_cpu_mxl(env) != MXL_RV32) { + /* We only support 64-bit VSXL */ + *val = set_field(*val, HSTATUS_VSXL, 2); + } + /* We only support little endian */ + *val = set_field(*val, HSTATUS_VSBE, 0); + return RISCV_EXCP_NONE; +} + +static RISCVException write_hstatus(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->hstatus = val; + if (riscv_cpu_mxl(env) != MXL_RV32 && get_field(val, HSTATUS_VSXL) != 2) { + qemu_log_mask(LOG_UNIMP, "QEMU does not support mixed HSXLEN options."); + } + if (get_field(val, HSTATUS_VSBE) != 0) { + qemu_log_mask(LOG_UNIMP, "QEMU does not support big endian guests."); + } + return RISCV_EXCP_NONE; +} + +static RISCVException read_hedeleg(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->hedeleg; + return RISCV_EXCP_NONE; +} + +static RISCVException write_hedeleg(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->hedeleg = val & vs_delegable_excps; + return RISCV_EXCP_NONE; +} + +static RISCVException read_hideleg(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->hideleg; + return RISCV_EXCP_NONE; +} + +static RISCVException write_hideleg(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->hideleg = val & vs_delegable_ints; + return RISCV_EXCP_NONE; +} + +static RISCVException rmw_hvip(CPURISCVState *env, int csrno, + target_ulong *ret_value, + target_ulong new_value, target_ulong write_mask) +{ + int ret = rmw_mip(env, 0, ret_value, new_value, + write_mask & hvip_writable_mask); + + if (ret_value) { + *ret_value &= hvip_writable_mask; + } + return ret; +} + +static RISCVException rmw_hip(CPURISCVState *env, int csrno, + target_ulong *ret_value, + target_ulong new_value, target_ulong write_mask) +{ + int ret = rmw_mip(env, 0, ret_value, new_value, + write_mask & hip_writable_mask); + + if (ret_value) { + *ret_value &= hip_writable_mask; + } + return ret; +} + +static RISCVException read_hie(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->mie & VS_MODE_INTERRUPTS; + return RISCV_EXCP_NONE; +} + +static RISCVException write_hie(CPURISCVState *env, int csrno, + target_ulong val) +{ + target_ulong newval = (env->mie & ~VS_MODE_INTERRUPTS) | (val & VS_MODE_INTERRUPTS); + return write_mie(env, CSR_MIE, newval); +} + +static RISCVException read_hcounteren(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->hcounteren; + return RISCV_EXCP_NONE; +} + +static RISCVException write_hcounteren(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->hcounteren = val; + return RISCV_EXCP_NONE; +} + +static RISCVException write_hgeie(CPURISCVState *env, int csrno, + target_ulong val) +{ + if (val) { + qemu_log_mask(LOG_UNIMP, "No support for a non-zero GEILEN."); + } + return RISCV_EXCP_NONE; +} + +static RISCVException read_htval(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->htval; + return RISCV_EXCP_NONE; +} + +static RISCVException write_htval(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->htval = val; + return RISCV_EXCP_NONE; +} + +static RISCVException read_htinst(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->htinst; + return RISCV_EXCP_NONE; +} + +static RISCVException write_htinst(CPURISCVState *env, int csrno, + target_ulong val) +{ + return RISCV_EXCP_NONE; +} + +static RISCVException write_hgeip(CPURISCVState *env, int csrno, + target_ulong val) +{ + if (val) { + qemu_log_mask(LOG_UNIMP, "No support for a non-zero GEILEN."); + } + return RISCV_EXCP_NONE; +} + +static RISCVException read_hgatp(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->hgatp; + return RISCV_EXCP_NONE; +} + +static RISCVException write_hgatp(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->hgatp = val; + return RISCV_EXCP_NONE; +} + +static RISCVException read_htimedelta(CPURISCVState *env, int csrno, + target_ulong *val) +{ + if (!env->rdtime_fn) { + return RISCV_EXCP_ILLEGAL_INST; + } + + *val = env->htimedelta; + return RISCV_EXCP_NONE; +} + +static RISCVException write_htimedelta(CPURISCVState *env, int csrno, + target_ulong val) +{ + if (!env->rdtime_fn) { + return RISCV_EXCP_ILLEGAL_INST; + } + + if (riscv_cpu_mxl(env) == MXL_RV32) { + env->htimedelta = deposit64(env->htimedelta, 0, 32, (uint64_t)val); + } else { + env->htimedelta = val; + } + return RISCV_EXCP_NONE; +} + +static RISCVException read_htimedeltah(CPURISCVState *env, int csrno, + target_ulong *val) +{ + if (!env->rdtime_fn) { + return RISCV_EXCP_ILLEGAL_INST; + } + + *val = env->htimedelta >> 32; + return RISCV_EXCP_NONE; +} + +static RISCVException write_htimedeltah(CPURISCVState *env, int csrno, + target_ulong val) +{ + if (!env->rdtime_fn) { + return RISCV_EXCP_ILLEGAL_INST; + } + + env->htimedelta = deposit64(env->htimedelta, 32, 32, (uint64_t)val); + return RISCV_EXCP_NONE; +} + +/* Virtual CSR Registers */ +static RISCVException read_vsstatus(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->vsstatus; + return RISCV_EXCP_NONE; +} + +static RISCVException write_vsstatus(CPURISCVState *env, int csrno, + target_ulong val) +{ + uint64_t mask = (target_ulong)-1; + env->vsstatus = (env->vsstatus & ~mask) | (uint64_t)val; + return RISCV_EXCP_NONE; +} + +static int read_vstvec(CPURISCVState *env, int csrno, target_ulong *val) +{ + *val = env->vstvec; + return RISCV_EXCP_NONE; +} + +static RISCVException write_vstvec(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->vstvec = val; + return RISCV_EXCP_NONE; +} + +static RISCVException read_vsscratch(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->vsscratch; + return RISCV_EXCP_NONE; +} + +static RISCVException write_vsscratch(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->vsscratch = val; + return RISCV_EXCP_NONE; +} + +static RISCVException read_vsepc(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->vsepc; + return RISCV_EXCP_NONE; +} + +static RISCVException write_vsepc(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->vsepc = val; + return RISCV_EXCP_NONE; +} + +static RISCVException read_vscause(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->vscause; + return RISCV_EXCP_NONE; +} + +static RISCVException write_vscause(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->vscause = val; + return RISCV_EXCP_NONE; +} + +static RISCVException read_vstval(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->vstval; + return RISCV_EXCP_NONE; +} + +static RISCVException write_vstval(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->vstval = val; + return RISCV_EXCP_NONE; +} + +static RISCVException read_vsatp(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->vsatp; + return RISCV_EXCP_NONE; +} + +static RISCVException write_vsatp(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->vsatp = val; + return RISCV_EXCP_NONE; +} + +static RISCVException read_mtval2(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->mtval2; + return RISCV_EXCP_NONE; +} + +static RISCVException write_mtval2(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->mtval2 = val; + return RISCV_EXCP_NONE; +} + +static RISCVException read_mtinst(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->mtinst; + return RISCV_EXCP_NONE; +} + +static RISCVException write_mtinst(CPURISCVState *env, int csrno, + target_ulong val) +{ + env->mtinst = val; + return RISCV_EXCP_NONE; +} + +/* Physical Memory Protection */ +static RISCVException read_mseccfg(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = mseccfg_csr_read(env); + return RISCV_EXCP_NONE; +} + +static RISCVException write_mseccfg(CPURISCVState *env, int csrno, + target_ulong val) +{ + mseccfg_csr_write(env, val); + return RISCV_EXCP_NONE; +} + +static RISCVException read_pmpcfg(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = pmpcfg_csr_read(env, csrno - CSR_PMPCFG0); + return RISCV_EXCP_NONE; +} + +static RISCVException write_pmpcfg(CPURISCVState *env, int csrno, + target_ulong val) +{ + pmpcfg_csr_write(env, csrno - CSR_PMPCFG0, val); + return RISCV_EXCP_NONE; +} + +static RISCVException read_pmpaddr(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = pmpaddr_csr_read(env, csrno - CSR_PMPADDR0); + return RISCV_EXCP_NONE; +} + +static RISCVException write_pmpaddr(CPURISCVState *env, int csrno, + target_ulong val) +{ + pmpaddr_csr_write(env, csrno - CSR_PMPADDR0, val); + return RISCV_EXCP_NONE; +} + +/* + * Functions to access Pointer Masking feature registers + * We have to check if current priv lvl could modify + * csr in given mode + */ +static bool check_pm_current_disabled(CPURISCVState *env, int csrno) +{ + int csr_priv = get_field(csrno, 0x300); + int pm_current; + + /* + * If priv lvls differ that means we're accessing csr from higher priv lvl, + * so allow the access + */ + if (env->priv != csr_priv) { + return false; + } + switch (env->priv) { + case PRV_M: + pm_current = get_field(env->mmte, M_PM_CURRENT); + break; + case PRV_S: + pm_current = get_field(env->mmte, S_PM_CURRENT); + break; + case PRV_U: + pm_current = get_field(env->mmte, U_PM_CURRENT); + break; + default: + g_assert_not_reached(); + } + /* It's same priv lvl, so we allow to modify csr only if pm.current==1 */ + return !pm_current; +} + +static RISCVException read_mmte(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->mmte & MMTE_MASK; + return RISCV_EXCP_NONE; +} + +static RISCVException write_mmte(CPURISCVState *env, int csrno, + target_ulong val) +{ + uint64_t mstatus; + target_ulong wpri_val = val & MMTE_MASK; + + if (val != wpri_val) { + qemu_log_mask(LOG_GUEST_ERROR, "%s" TARGET_FMT_lx " %s" TARGET_FMT_lx "\n", + "MMTE: WPRI violation written 0x", val, + "vs expected 0x", wpri_val); + } + /* for machine mode pm.current is hardwired to 1 */ + wpri_val |= MMTE_M_PM_CURRENT; + + /* hardwiring pm.instruction bit to 0, since it's not supported yet */ + wpri_val &= ~(MMTE_M_PM_INSN | MMTE_S_PM_INSN | MMTE_U_PM_INSN); + env->mmte = wpri_val | PM_EXT_DIRTY; + + /* Set XS and SD bits, since PM CSRs are dirty */ + mstatus = env->mstatus | MSTATUS_XS; + write_mstatus(env, csrno, mstatus); + return RISCV_EXCP_NONE; +} + +static RISCVException read_smte(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->mmte & SMTE_MASK; + return RISCV_EXCP_NONE; +} + +static RISCVException write_smte(CPURISCVState *env, int csrno, + target_ulong val) +{ + target_ulong wpri_val = val & SMTE_MASK; + + if (val != wpri_val) { + qemu_log_mask(LOG_GUEST_ERROR, "%s" TARGET_FMT_lx " %s" TARGET_FMT_lx "\n", + "SMTE: WPRI violation written 0x", val, + "vs expected 0x", wpri_val); + } + + /* if pm.current==0 we can't modify current PM CSRs */ + if (check_pm_current_disabled(env, csrno)) { + return RISCV_EXCP_NONE; + } + + wpri_val |= (env->mmte & ~SMTE_MASK); + write_mmte(env, csrno, wpri_val); + return RISCV_EXCP_NONE; +} + +static RISCVException read_umte(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->mmte & UMTE_MASK; + return RISCV_EXCP_NONE; +} + +static RISCVException write_umte(CPURISCVState *env, int csrno, + target_ulong val) +{ + target_ulong wpri_val = val & UMTE_MASK; + + if (val != wpri_val) { + qemu_log_mask(LOG_GUEST_ERROR, "%s" TARGET_FMT_lx " %s" TARGET_FMT_lx "\n", + "UMTE: WPRI violation written 0x", val, + "vs expected 0x", wpri_val); + } + + if (check_pm_current_disabled(env, csrno)) { + return RISCV_EXCP_NONE; + } + + wpri_val |= (env->mmte & ~UMTE_MASK); + write_mmte(env, csrno, wpri_val); + return RISCV_EXCP_NONE; +} + +static RISCVException read_mpmmask(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->mpmmask; + return RISCV_EXCP_NONE; +} + +static RISCVException write_mpmmask(CPURISCVState *env, int csrno, + target_ulong val) +{ + uint64_t mstatus; + + env->mpmmask = val; + env->mmte |= PM_EXT_DIRTY; + + /* Set XS and SD bits, since PM CSRs are dirty */ + mstatus = env->mstatus | MSTATUS_XS; + write_mstatus(env, csrno, mstatus); + return RISCV_EXCP_NONE; +} + +static RISCVException read_spmmask(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->spmmask; + return RISCV_EXCP_NONE; +} + +static RISCVException write_spmmask(CPURISCVState *env, int csrno, + target_ulong val) +{ + uint64_t mstatus; + + /* if pm.current==0 we can't modify current PM CSRs */ + if (check_pm_current_disabled(env, csrno)) { + return RISCV_EXCP_NONE; + } + env->spmmask = val; + env->mmte |= PM_EXT_DIRTY; + + /* Set XS and SD bits, since PM CSRs are dirty */ + mstatus = env->mstatus | MSTATUS_XS; + write_mstatus(env, csrno, mstatus); + return RISCV_EXCP_NONE; +} + +static RISCVException read_upmmask(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->upmmask; + return RISCV_EXCP_NONE; +} + +static RISCVException write_upmmask(CPURISCVState *env, int csrno, + target_ulong val) +{ + uint64_t mstatus; + + /* if pm.current==0 we can't modify current PM CSRs */ + if (check_pm_current_disabled(env, csrno)) { + return RISCV_EXCP_NONE; + } + env->upmmask = val; + env->mmte |= PM_EXT_DIRTY; + + /* Set XS and SD bits, since PM CSRs are dirty */ + mstatus = env->mstatus | MSTATUS_XS; + write_mstatus(env, csrno, mstatus); + return RISCV_EXCP_NONE; +} + +static RISCVException read_mpmbase(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->mpmbase; + return RISCV_EXCP_NONE; +} + +static RISCVException write_mpmbase(CPURISCVState *env, int csrno, + target_ulong val) +{ + uint64_t mstatus; + + env->mpmbase = val; + env->mmte |= PM_EXT_DIRTY; + + /* Set XS and SD bits, since PM CSRs are dirty */ + mstatus = env->mstatus | MSTATUS_XS; + write_mstatus(env, csrno, mstatus); + return RISCV_EXCP_NONE; +} + +static RISCVException read_spmbase(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->spmbase; + return RISCV_EXCP_NONE; +} + +static RISCVException write_spmbase(CPURISCVState *env, int csrno, + target_ulong val) +{ + uint64_t mstatus; + + /* if pm.current==0 we can't modify current PM CSRs */ + if (check_pm_current_disabled(env, csrno)) { + return RISCV_EXCP_NONE; + } + env->spmbase = val; + env->mmte |= PM_EXT_DIRTY; + + /* Set XS and SD bits, since PM CSRs are dirty */ + mstatus = env->mstatus | MSTATUS_XS; + write_mstatus(env, csrno, mstatus); + return RISCV_EXCP_NONE; +} + +static RISCVException read_upmbase(CPURISCVState *env, int csrno, + target_ulong *val) +{ + *val = env->upmbase; + return RISCV_EXCP_NONE; +} + +static RISCVException write_upmbase(CPURISCVState *env, int csrno, + target_ulong val) +{ + uint64_t mstatus; + + /* if pm.current==0 we can't modify current PM CSRs */ + if (check_pm_current_disabled(env, csrno)) { + return RISCV_EXCP_NONE; + } + env->upmbase = val; + env->mmte |= PM_EXT_DIRTY; + + /* Set XS and SD bits, since PM CSRs are dirty */ + mstatus = env->mstatus | MSTATUS_XS; + write_mstatus(env, csrno, mstatus); + return RISCV_EXCP_NONE; +} + +#endif + +/* + * riscv_csrrw - read and/or update control and status register + * + * csrr <-> riscv_csrrw(env, csrno, ret_value, 0, 0); + * csrrw <-> riscv_csrrw(env, csrno, ret_value, value, -1); + * csrrs <-> riscv_csrrw(env, csrno, ret_value, -1, value); + * csrrc <-> riscv_csrrw(env, csrno, ret_value, 0, value); + */ + +RISCVException riscv_csrrw(CPURISCVState *env, int csrno, + target_ulong *ret_value, + target_ulong new_value, target_ulong write_mask) +{ + RISCVException ret; + target_ulong old_value; + RISCVCPU *cpu = env_archcpu(env); + int read_only = get_field(csrno, 0xC00) == 3; + + /* check privileges and return RISCV_EXCP_ILLEGAL_INST if check fails */ +#if !defined(CONFIG_USER_ONLY) + int effective_priv = env->priv; + + if (riscv_has_ext(env, RVH) && + env->priv == PRV_S && + !riscv_cpu_virt_enabled(env)) { + /* + * We are in S mode without virtualisation, therefore we are in HS Mode. + * Add 1 to the effective privledge level to allow us to access the + * Hypervisor CSRs. + */ + effective_priv++; + } + + if (!env->debugger && (effective_priv < get_field(csrno, 0x300))) { + return RISCV_EXCP_ILLEGAL_INST; + } +#endif + if (write_mask && read_only) { + return RISCV_EXCP_ILLEGAL_INST; + } + + /* ensure the CSR extension is enabled. */ + if (!cpu->cfg.ext_icsr) { + return RISCV_EXCP_ILLEGAL_INST; + } + + /* check predicate */ + if (!csr_ops[csrno].predicate) { + return RISCV_EXCP_ILLEGAL_INST; + } + ret = csr_ops[csrno].predicate(env, csrno); + if (ret != RISCV_EXCP_NONE) { + return ret; + } + + /* 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; + } + + /* write value if writable and write mask set, otherwise drop writes */ + if (write_mask) { + new_value = (old_value & ~write_mask) | (new_value & write_mask); + if (csr_ops[csrno].write) { + ret = csr_ops[csrno].write(env, csrno, new_value); + if (ret != RISCV_EXCP_NONE) { + return ret; + } + } + } + + /* return old value */ + if (ret_value) { + *ret_value = old_value; + } + + return RISCV_EXCP_NONE; +} + +/* + * Debugger support. If not in user mode, set env->debugger before the + * riscv_csrrw call and clear it after the call. + */ +RISCVException riscv_csrrw_debug(CPURISCVState *env, int csrno, + target_ulong *ret_value, + target_ulong new_value, + target_ulong write_mask) +{ + RISCVException ret; +#if !defined(CONFIG_USER_ONLY) + env->debugger = true; +#endif + ret = riscv_csrrw(env, csrno, ret_value, new_value, write_mask); +#if !defined(CONFIG_USER_ONLY) + env->debugger = false; +#endif + return ret; +} + +/* Control and Status Register function table */ +riscv_csr_operations csr_ops[CSR_TABLE_SIZE] = { + /* User Floating-Point CSRs */ + [CSR_FFLAGS] = { "fflags", fs, read_fflags, write_fflags }, + [CSR_FRM] = { "frm", fs, read_frm, write_frm }, + [CSR_FCSR] = { "fcsr", fs, read_fcsr, write_fcsr }, + /* Vector CSRs */ + [CSR_VSTART] = { "vstart", vs, read_vstart, write_vstart }, + [CSR_VXSAT] = { "vxsat", vs, read_vxsat, write_vxsat }, + [CSR_VXRM] = { "vxrm", vs, read_vxrm, write_vxrm }, + [CSR_VL] = { "vl", vs, read_vl }, + [CSR_VTYPE] = { "vtype", vs, read_vtype }, + /* User Timers and Counters */ + [CSR_CYCLE] = { "cycle", ctr, read_instret }, + [CSR_INSTRET] = { "instret", ctr, read_instret }, + [CSR_CYCLEH] = { "cycleh", ctr32, read_instreth }, + [CSR_INSTRETH] = { "instreth", ctr32, read_instreth }, + + /* + * In privileged mode, the monitor will have to emulate TIME CSRs only if + * rdtime callback is not provided by machine/platform emulation. + */ + [CSR_TIME] = { "time", ctr, read_time }, + [CSR_TIMEH] = { "timeh", ctr32, read_timeh }, + +#if !defined(CONFIG_USER_ONLY) + /* Machine Timers and Counters */ + [CSR_MCYCLE] = { "mcycle", any, read_instret }, + [CSR_MINSTRET] = { "minstret", any, read_instret }, + [CSR_MCYCLEH] = { "mcycleh", any32, read_instreth }, + [CSR_MINSTRETH] = { "minstreth", any32, read_instreth }, + + /* Machine Information Registers */ + [CSR_MVENDORID] = { "mvendorid", any, read_zero }, + [CSR_MARCHID] = { "marchid", any, read_zero }, + [CSR_MIMPID] = { "mimpid", any, read_zero }, + [CSR_MHARTID] = { "mhartid", any, read_mhartid }, + + /* Machine Trap Setup */ + [CSR_MSTATUS] = { "mstatus", any, read_mstatus, write_mstatus }, + [CSR_MISA] = { "misa", any, read_misa, write_misa }, + [CSR_MIDELEG] = { "mideleg", any, read_mideleg, write_mideleg }, + [CSR_MEDELEG] = { "medeleg", any, read_medeleg, write_medeleg }, + [CSR_MIE] = { "mie", any, read_mie, write_mie }, + [CSR_MTVEC] = { "mtvec", any, read_mtvec, write_mtvec }, + [CSR_MCOUNTEREN] = { "mcounteren", any, read_mcounteren, write_mcounteren }, + + [CSR_MSTATUSH] = { "mstatush", any32, read_mstatush, write_mstatush }, + + /* Machine Trap Handling */ + [CSR_MSCRATCH] = { "mscratch", any, read_mscratch, write_mscratch }, + [CSR_MEPC] = { "mepc", any, read_mepc, write_mepc }, + [CSR_MCAUSE] = { "mcause", any, read_mcause, write_mcause }, + [CSR_MTVAL] = { "mtval", any, read_mtval, write_mtval }, + [CSR_MIP] = { "mip", any, NULL, NULL, rmw_mip }, + + /* Supervisor Trap Setup */ + [CSR_SSTATUS] = { "sstatus", smode, read_sstatus, write_sstatus }, + [CSR_SIE] = { "sie", smode, read_sie, write_sie }, + [CSR_STVEC] = { "stvec", smode, read_stvec, write_stvec }, + [CSR_SCOUNTEREN] = { "scounteren", smode, read_scounteren, write_scounteren }, + + /* Supervisor Trap Handling */ + [CSR_SSCRATCH] = { "sscratch", smode, read_sscratch, write_sscratch }, + [CSR_SEPC] = { "sepc", smode, read_sepc, write_sepc }, + [CSR_SCAUSE] = { "scause", smode, read_scause, write_scause }, + [CSR_STVAL] = { "stval", smode, read_stval, write_stval }, + [CSR_SIP] = { "sip", smode, NULL, NULL, rmw_sip }, + + /* Supervisor Protection and Translation */ + [CSR_SATP] = { "satp", smode, read_satp, write_satp }, + + [CSR_HSTATUS] = { "hstatus", hmode, read_hstatus, write_hstatus }, + [CSR_HEDELEG] = { "hedeleg", hmode, read_hedeleg, write_hedeleg }, + [CSR_HIDELEG] = { "hideleg", hmode, read_hideleg, write_hideleg }, + [CSR_HVIP] = { "hvip", hmode, NULL, NULL, rmw_hvip }, + [CSR_HIP] = { "hip", hmode, NULL, NULL, rmw_hip }, + [CSR_HIE] = { "hie", hmode, read_hie, write_hie }, + [CSR_HCOUNTEREN] = { "hcounteren", hmode, read_hcounteren, write_hcounteren }, + [CSR_HGEIE] = { "hgeie", hmode, read_zero, write_hgeie }, + [CSR_HTVAL] = { "htval", hmode, read_htval, write_htval }, + [CSR_HTINST] = { "htinst", hmode, read_htinst, write_htinst }, + [CSR_HGEIP] = { "hgeip", hmode, read_zero, write_hgeip }, + [CSR_HGATP] = { "hgatp", hmode, read_hgatp, write_hgatp }, + [CSR_HTIMEDELTA] = { "htimedelta", hmode, read_htimedelta, write_htimedelta }, + [CSR_HTIMEDELTAH] = { "htimedeltah", hmode32, read_htimedeltah, write_htimedeltah }, + + [CSR_VSSTATUS] = { "vsstatus", hmode, read_vsstatus, write_vsstatus }, + [CSR_VSIP] = { "vsip", hmode, NULL, NULL, rmw_vsip }, + [CSR_VSIE] = { "vsie", hmode, read_vsie, write_vsie }, + [CSR_VSTVEC] = { "vstvec", hmode, read_vstvec, write_vstvec }, + [CSR_VSSCRATCH] = { "vsscratch", hmode, read_vsscratch, write_vsscratch }, + [CSR_VSEPC] = { "vsepc", hmode, read_vsepc, write_vsepc }, + [CSR_VSCAUSE] = { "vscause", hmode, read_vscause, write_vscause }, + [CSR_VSTVAL] = { "vstval", hmode, read_vstval, write_vstval }, + [CSR_VSATP] = { "vsatp", hmode, read_vsatp, write_vsatp }, + + [CSR_MTVAL2] = { "mtval2", hmode, read_mtval2, write_mtval2 }, + [CSR_MTINST] = { "mtinst", hmode, read_mtinst, write_mtinst }, + + /* Physical Memory Protection */ + [CSR_MSECCFG] = { "mseccfg", epmp, read_mseccfg, write_mseccfg }, + [CSR_PMPCFG0] = { "pmpcfg0", pmp, read_pmpcfg, write_pmpcfg }, + [CSR_PMPCFG1] = { "pmpcfg1", pmp, read_pmpcfg, write_pmpcfg }, + [CSR_PMPCFG2] = { "pmpcfg2", pmp, read_pmpcfg, write_pmpcfg }, + [CSR_PMPCFG3] = { "pmpcfg3", pmp, read_pmpcfg, write_pmpcfg }, + [CSR_PMPADDR0] = { "pmpaddr0", pmp, read_pmpaddr, write_pmpaddr }, + [CSR_PMPADDR1] = { "pmpaddr1", pmp, read_pmpaddr, write_pmpaddr }, + [CSR_PMPADDR2] = { "pmpaddr2", pmp, read_pmpaddr, write_pmpaddr }, + [CSR_PMPADDR3] = { "pmpaddr3", pmp, read_pmpaddr, write_pmpaddr }, + [CSR_PMPADDR4] = { "pmpaddr4", pmp, read_pmpaddr, write_pmpaddr }, + [CSR_PMPADDR5] = { "pmpaddr5", pmp, read_pmpaddr, write_pmpaddr }, + [CSR_PMPADDR6] = { "pmpaddr6", pmp, read_pmpaddr, write_pmpaddr }, + [CSR_PMPADDR7] = { "pmpaddr7", pmp, read_pmpaddr, write_pmpaddr }, + [CSR_PMPADDR8] = { "pmpaddr8", pmp, read_pmpaddr, write_pmpaddr }, + [CSR_PMPADDR9] = { "pmpaddr9", pmp, read_pmpaddr, write_pmpaddr }, + [CSR_PMPADDR10] = { "pmpaddr10", pmp, read_pmpaddr, write_pmpaddr }, + [CSR_PMPADDR11] = { "pmpaddr11", pmp, read_pmpaddr, write_pmpaddr }, + [CSR_PMPADDR12] = { "pmpaddr12", pmp, read_pmpaddr, write_pmpaddr }, + [CSR_PMPADDR13] = { "pmpaddr13", pmp, read_pmpaddr, write_pmpaddr }, + [CSR_PMPADDR14] = { "pmpaddr14", pmp, read_pmpaddr, write_pmpaddr }, + [CSR_PMPADDR15] = { "pmpaddr15", pmp, read_pmpaddr, write_pmpaddr }, + + /* User Pointer Masking */ + [CSR_UMTE] = { "umte", pointer_masking, read_umte, write_umte }, + [CSR_UPMMASK] = { "upmmask", pointer_masking, read_upmmask, write_upmmask }, + [CSR_UPMBASE] = { "upmbase", pointer_masking, read_upmbase, write_upmbase }, + /* Machine Pointer Masking */ + [CSR_MMTE] = { "mmte", pointer_masking, read_mmte, write_mmte }, + [CSR_MPMMASK] = { "mpmmask", pointer_masking, read_mpmmask, write_mpmmask }, + [CSR_MPMBASE] = { "mpmbase", pointer_masking, read_mpmbase, write_mpmbase }, + /* Supervisor Pointer Masking */ + [CSR_SMTE] = { "smte", pointer_masking, read_smte, write_smte }, + [CSR_SPMMASK] = { "spmmask", pointer_masking, read_spmmask, write_spmmask }, + [CSR_SPMBASE] = { "spmbase", pointer_masking, read_spmbase, write_spmbase }, + + /* Performance Counters */ + [CSR_HPMCOUNTER3] = { "hpmcounter3", ctr, read_zero }, + [CSR_HPMCOUNTER4] = { "hpmcounter4", ctr, read_zero }, + [CSR_HPMCOUNTER5] = { "hpmcounter5", ctr, read_zero }, + [CSR_HPMCOUNTER6] = { "hpmcounter6", ctr, read_zero }, + [CSR_HPMCOUNTER7] = { "hpmcounter7", ctr, read_zero }, + [CSR_HPMCOUNTER8] = { "hpmcounter8", ctr, read_zero }, + [CSR_HPMCOUNTER9] = { "hpmcounter9", ctr, read_zero }, + [CSR_HPMCOUNTER10] = { "hpmcounter10", ctr, read_zero }, + [CSR_HPMCOUNTER11] = { "hpmcounter11", ctr, read_zero }, + [CSR_HPMCOUNTER12] = { "hpmcounter12", ctr, read_zero }, + [CSR_HPMCOUNTER13] = { "hpmcounter13", ctr, read_zero }, + [CSR_HPMCOUNTER14] = { "hpmcounter14", ctr, read_zero }, + [CSR_HPMCOUNTER15] = { "hpmcounter15", ctr, read_zero }, + [CSR_HPMCOUNTER16] = { "hpmcounter16", ctr, read_zero }, + [CSR_HPMCOUNTER17] = { "hpmcounter17", ctr, read_zero }, + [CSR_HPMCOUNTER18] = { "hpmcounter18", ctr, read_zero }, + [CSR_HPMCOUNTER19] = { "hpmcounter19", ctr, read_zero }, + [CSR_HPMCOUNTER20] = { "hpmcounter20", ctr, read_zero }, + [CSR_HPMCOUNTER21] = { "hpmcounter21", ctr, read_zero }, + [CSR_HPMCOUNTER22] = { "hpmcounter22", ctr, read_zero }, + [CSR_HPMCOUNTER23] = { "hpmcounter23", ctr, read_zero }, + [CSR_HPMCOUNTER24] = { "hpmcounter24", ctr, read_zero }, + [CSR_HPMCOUNTER25] = { "hpmcounter25", ctr, read_zero }, + [CSR_HPMCOUNTER26] = { "hpmcounter26", ctr, read_zero }, + [CSR_HPMCOUNTER27] = { "hpmcounter27", ctr, read_zero }, + [CSR_HPMCOUNTER28] = { "hpmcounter28", ctr, read_zero }, + [CSR_HPMCOUNTER29] = { "hpmcounter29", ctr, read_zero }, + [CSR_HPMCOUNTER30] = { "hpmcounter30", ctr, read_zero }, + [CSR_HPMCOUNTER31] = { "hpmcounter31", ctr, read_zero }, + + [CSR_MHPMCOUNTER3] = { "mhpmcounter3", any, read_zero }, + [CSR_MHPMCOUNTER4] = { "mhpmcounter4", any, read_zero }, + [CSR_MHPMCOUNTER5] = { "mhpmcounter5", any, read_zero }, + [CSR_MHPMCOUNTER6] = { "mhpmcounter6", any, read_zero }, + [CSR_MHPMCOUNTER7] = { "mhpmcounter7", any, read_zero }, + [CSR_MHPMCOUNTER8] = { "mhpmcounter8", any, read_zero }, + [CSR_MHPMCOUNTER9] = { "mhpmcounter9", any, read_zero }, + [CSR_MHPMCOUNTER10] = { "mhpmcounter10", any, read_zero }, + [CSR_MHPMCOUNTER11] = { "mhpmcounter11", any, read_zero }, + [CSR_MHPMCOUNTER12] = { "mhpmcounter12", any, read_zero }, + [CSR_MHPMCOUNTER13] = { "mhpmcounter13", any, read_zero }, + [CSR_MHPMCOUNTER14] = { "mhpmcounter14", any, read_zero }, + [CSR_MHPMCOUNTER15] = { "mhpmcounter15", any, read_zero }, + [CSR_MHPMCOUNTER16] = { "mhpmcounter16", any, read_zero }, + [CSR_MHPMCOUNTER17] = { "mhpmcounter17", any, read_zero }, + [CSR_MHPMCOUNTER18] = { "mhpmcounter18", any, read_zero }, + [CSR_MHPMCOUNTER19] = { "mhpmcounter19", any, read_zero }, + [CSR_MHPMCOUNTER20] = { "mhpmcounter20", any, read_zero }, + [CSR_MHPMCOUNTER21] = { "mhpmcounter21", any, read_zero }, + [CSR_MHPMCOUNTER22] = { "mhpmcounter22", any, read_zero }, + [CSR_MHPMCOUNTER23] = { "mhpmcounter23", any, read_zero }, + [CSR_MHPMCOUNTER24] = { "mhpmcounter24", any, read_zero }, + [CSR_MHPMCOUNTER25] = { "mhpmcounter25", any, read_zero }, + [CSR_MHPMCOUNTER26] = { "mhpmcounter26", any, read_zero }, + [CSR_MHPMCOUNTER27] = { "mhpmcounter27", any, read_zero }, + [CSR_MHPMCOUNTER28] = { "mhpmcounter28", any, read_zero }, + [CSR_MHPMCOUNTER29] = { "mhpmcounter29", any, read_zero }, + [CSR_MHPMCOUNTER30] = { "mhpmcounter30", any, read_zero }, + [CSR_MHPMCOUNTER31] = { "mhpmcounter31", any, read_zero }, + + [CSR_MHPMEVENT3] = { "mhpmevent3", any, read_zero }, + [CSR_MHPMEVENT4] = { "mhpmevent4", any, read_zero }, + [CSR_MHPMEVENT5] = { "mhpmevent5", any, read_zero }, + [CSR_MHPMEVENT6] = { "mhpmevent6", any, read_zero }, + [CSR_MHPMEVENT7] = { "mhpmevent7", any, read_zero }, + [CSR_MHPMEVENT8] = { "mhpmevent8", any, read_zero }, + [CSR_MHPMEVENT9] = { "mhpmevent9", any, read_zero }, + [CSR_MHPMEVENT10] = { "mhpmevent10", any, read_zero }, + [CSR_MHPMEVENT11] = { "mhpmevent11", any, read_zero }, + [CSR_MHPMEVENT12] = { "mhpmevent12", any, read_zero }, + [CSR_MHPMEVENT13] = { "mhpmevent13", any, read_zero }, + [CSR_MHPMEVENT14] = { "mhpmevent14", any, read_zero }, + [CSR_MHPMEVENT15] = { "mhpmevent15", any, read_zero }, + [CSR_MHPMEVENT16] = { "mhpmevent16", any, read_zero }, + [CSR_MHPMEVENT17] = { "mhpmevent17", any, read_zero }, + [CSR_MHPMEVENT18] = { "mhpmevent18", any, read_zero }, + [CSR_MHPMEVENT19] = { "mhpmevent19", any, read_zero }, + [CSR_MHPMEVENT20] = { "mhpmevent20", any, read_zero }, + [CSR_MHPMEVENT21] = { "mhpmevent21", any, read_zero }, + [CSR_MHPMEVENT22] = { "mhpmevent22", any, read_zero }, + [CSR_MHPMEVENT23] = { "mhpmevent23", any, read_zero }, + [CSR_MHPMEVENT24] = { "mhpmevent24", any, read_zero }, + [CSR_MHPMEVENT25] = { "mhpmevent25", any, read_zero }, + [CSR_MHPMEVENT26] = { "mhpmevent26", any, read_zero }, + [CSR_MHPMEVENT27] = { "mhpmevent27", any, read_zero }, + [CSR_MHPMEVENT28] = { "mhpmevent28", any, read_zero }, + [CSR_MHPMEVENT29] = { "mhpmevent29", any, read_zero }, + [CSR_MHPMEVENT30] = { "mhpmevent30", any, read_zero }, + [CSR_MHPMEVENT31] = { "mhpmevent31", any, read_zero }, + + [CSR_HPMCOUNTER3H] = { "hpmcounter3h", ctr32, read_zero }, + [CSR_HPMCOUNTER4H] = { "hpmcounter4h", ctr32, read_zero }, + [CSR_HPMCOUNTER5H] = { "hpmcounter5h", ctr32, read_zero }, + [CSR_HPMCOUNTER6H] = { "hpmcounter6h", ctr32, read_zero }, + [CSR_HPMCOUNTER7H] = { "hpmcounter7h", ctr32, read_zero }, + [CSR_HPMCOUNTER8H] = { "hpmcounter8h", ctr32, read_zero }, + [CSR_HPMCOUNTER9H] = { "hpmcounter9h", ctr32, read_zero }, + [CSR_HPMCOUNTER10H] = { "hpmcounter10h", ctr32, read_zero }, + [CSR_HPMCOUNTER11H] = { "hpmcounter11h", ctr32, read_zero }, + [CSR_HPMCOUNTER12H] = { "hpmcounter12h", ctr32, read_zero }, + [CSR_HPMCOUNTER13H] = { "hpmcounter13h", ctr32, read_zero }, + [CSR_HPMCOUNTER14H] = { "hpmcounter14h", ctr32, read_zero }, + [CSR_HPMCOUNTER15H] = { "hpmcounter15h", ctr32, read_zero }, + [CSR_HPMCOUNTER16H] = { "hpmcounter16h", ctr32, read_zero }, + [CSR_HPMCOUNTER17H] = { "hpmcounter17h", ctr32, read_zero }, + [CSR_HPMCOUNTER18H] = { "hpmcounter18h", ctr32, read_zero }, + [CSR_HPMCOUNTER19H] = { "hpmcounter19h", ctr32, read_zero }, + [CSR_HPMCOUNTER20H] = { "hpmcounter20h", ctr32, read_zero }, + [CSR_HPMCOUNTER21H] = { "hpmcounter21h", ctr32, read_zero }, + [CSR_HPMCOUNTER22H] = { "hpmcounter22h", ctr32, read_zero }, + [CSR_HPMCOUNTER23H] = { "hpmcounter23h", ctr32, read_zero }, + [CSR_HPMCOUNTER24H] = { "hpmcounter24h", ctr32, read_zero }, + [CSR_HPMCOUNTER25H] = { "hpmcounter25h", ctr32, read_zero }, + [CSR_HPMCOUNTER26H] = { "hpmcounter26h", ctr32, read_zero }, + [CSR_HPMCOUNTER27H] = { "hpmcounter27h", ctr32, read_zero }, + [CSR_HPMCOUNTER28H] = { "hpmcounter28h", ctr32, read_zero }, + [CSR_HPMCOUNTER29H] = { "hpmcounter29h", ctr32, read_zero }, + [CSR_HPMCOUNTER30H] = { "hpmcounter30h", ctr32, read_zero }, + [CSR_HPMCOUNTER31H] = { "hpmcounter31h", ctr32, read_zero }, + + [CSR_MHPMCOUNTER3H] = { "mhpmcounter3h", any32, read_zero }, + [CSR_MHPMCOUNTER4H] = { "mhpmcounter4h", any32, read_zero }, + [CSR_MHPMCOUNTER5H] = { "mhpmcounter5h", any32, read_zero }, + [CSR_MHPMCOUNTER6H] = { "mhpmcounter6h", any32, read_zero }, + [CSR_MHPMCOUNTER7H] = { "mhpmcounter7h", any32, read_zero }, + [CSR_MHPMCOUNTER8H] = { "mhpmcounter8h", any32, read_zero }, + [CSR_MHPMCOUNTER9H] = { "mhpmcounter9h", any32, read_zero }, + [CSR_MHPMCOUNTER10H] = { "mhpmcounter10h", any32, read_zero }, + [CSR_MHPMCOUNTER11H] = { "mhpmcounter11h", any32, read_zero }, + [CSR_MHPMCOUNTER12H] = { "mhpmcounter12h", any32, read_zero }, + [CSR_MHPMCOUNTER13H] = { "mhpmcounter13h", any32, read_zero }, + [CSR_MHPMCOUNTER14H] = { "mhpmcounter14h", any32, read_zero }, + [CSR_MHPMCOUNTER15H] = { "mhpmcounter15h", any32, read_zero }, + [CSR_MHPMCOUNTER16H] = { "mhpmcounter16h", any32, read_zero }, + [CSR_MHPMCOUNTER17H] = { "mhpmcounter17h", any32, read_zero }, + [CSR_MHPMCOUNTER18H] = { "mhpmcounter18h", any32, read_zero }, + [CSR_MHPMCOUNTER19H] = { "mhpmcounter19h", any32, read_zero }, + [CSR_MHPMCOUNTER20H] = { "mhpmcounter20h", any32, read_zero }, + [CSR_MHPMCOUNTER21H] = { "mhpmcounter21h", any32, read_zero }, + [CSR_MHPMCOUNTER22H] = { "mhpmcounter22h", any32, read_zero }, + [CSR_MHPMCOUNTER23H] = { "mhpmcounter23h", any32, read_zero }, + [CSR_MHPMCOUNTER24H] = { "mhpmcounter24h", any32, read_zero }, + [CSR_MHPMCOUNTER25H] = { "mhpmcounter25h", any32, read_zero }, + [CSR_MHPMCOUNTER26H] = { "mhpmcounter26h", any32, read_zero }, + [CSR_MHPMCOUNTER27H] = { "mhpmcounter27h", any32, read_zero }, + [CSR_MHPMCOUNTER28H] = { "mhpmcounter28h", any32, read_zero }, + [CSR_MHPMCOUNTER29H] = { "mhpmcounter29h", any32, read_zero }, + [CSR_MHPMCOUNTER30H] = { "mhpmcounter30h", any32, read_zero }, + [CSR_MHPMCOUNTER31H] = { "mhpmcounter31h", any32, read_zero }, +#endif /* !CONFIG_USER_ONLY */ +}; diff --git a/target/riscv/fpu_helper.c b/target/riscv/fpu_helper.c new file mode 100644 index 000000000..d62f47090 --- /dev/null +++ b/target/riscv/fpu_helper.c @@ -0,0 +1,376 @@ +/* + * RISC-V FPU Emulation Helpers for QEMU. + * + * Copyright (c) 2016-2017 Sagar Karandikar, sagark@eecs.berkeley.edu + * + * 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 "cpu.h" +#include "qemu/host-utils.h" +#include "exec/exec-all.h" +#include "exec/helper-proto.h" +#include "fpu/softfloat.h" +#include "internals.h" + +target_ulong riscv_cpu_get_fflags(CPURISCVState *env) +{ + int soft = get_float_exception_flags(&env->fp_status); + target_ulong hard = 0; + + hard |= (soft & float_flag_inexact) ? FPEXC_NX : 0; + hard |= (soft & float_flag_underflow) ? FPEXC_UF : 0; + hard |= (soft & float_flag_overflow) ? FPEXC_OF : 0; + hard |= (soft & float_flag_divbyzero) ? FPEXC_DZ : 0; + hard |= (soft & float_flag_invalid) ? FPEXC_NV : 0; + + return hard; +} + +void riscv_cpu_set_fflags(CPURISCVState *env, target_ulong hard) +{ + int soft = 0; + + soft |= (hard & FPEXC_NX) ? float_flag_inexact : 0; + soft |= (hard & FPEXC_UF) ? float_flag_underflow : 0; + soft |= (hard & FPEXC_OF) ? float_flag_overflow : 0; + soft |= (hard & FPEXC_DZ) ? float_flag_divbyzero : 0; + soft |= (hard & FPEXC_NV) ? float_flag_invalid : 0; + + set_float_exception_flags(soft, &env->fp_status); +} + +void helper_set_rounding_mode(CPURISCVState *env, uint32_t rm) +{ + int softrm; + + if (rm == 7) { + rm = env->frm; + } + switch (rm) { + case 0: + softrm = float_round_nearest_even; + break; + case 1: + softrm = float_round_to_zero; + break; + case 2: + softrm = float_round_down; + break; + case 3: + softrm = float_round_up; + break; + case 4: + softrm = float_round_ties_away; + break; + default: + riscv_raise_exception(env, RISCV_EXCP_ILLEGAL_INST, GETPC()); + } + + set_float_rounding_mode(softrm, &env->fp_status); +} + +static uint64_t do_fmadd_s(CPURISCVState *env, uint64_t rs1, uint64_t rs2, + uint64_t rs3, int flags) +{ + float32 frs1 = check_nanbox_s(rs1); + float32 frs2 = check_nanbox_s(rs2); + float32 frs3 = check_nanbox_s(rs3); + return nanbox_s(float32_muladd(frs1, frs2, frs3, flags, &env->fp_status)); +} + +uint64_t helper_fmadd_s(CPURISCVState *env, uint64_t frs1, uint64_t frs2, + uint64_t frs3) +{ + return do_fmadd_s(env, frs1, frs2, frs3, 0); +} + +uint64_t helper_fmadd_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2, + uint64_t frs3) +{ + return float64_muladd(frs1, frs2, frs3, 0, &env->fp_status); +} + +uint64_t helper_fmsub_s(CPURISCVState *env, uint64_t frs1, uint64_t frs2, + uint64_t frs3) +{ + return do_fmadd_s(env, frs1, frs2, frs3, float_muladd_negate_c); +} + +uint64_t helper_fmsub_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2, + uint64_t frs3) +{ + return float64_muladd(frs1, frs2, frs3, float_muladd_negate_c, + &env->fp_status); +} + +uint64_t helper_fnmsub_s(CPURISCVState *env, uint64_t frs1, uint64_t frs2, + uint64_t frs3) +{ + return do_fmadd_s(env, frs1, frs2, frs3, float_muladd_negate_product); +} + +uint64_t helper_fnmsub_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2, + uint64_t frs3) +{ + return float64_muladd(frs1, frs2, frs3, float_muladd_negate_product, + &env->fp_status); +} + +uint64_t helper_fnmadd_s(CPURISCVState *env, uint64_t frs1, uint64_t frs2, + uint64_t frs3) +{ + return do_fmadd_s(env, frs1, frs2, frs3, + float_muladd_negate_c | float_muladd_negate_product); +} + +uint64_t helper_fnmadd_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2, + uint64_t frs3) +{ + return float64_muladd(frs1, frs2, frs3, float_muladd_negate_c | + float_muladd_negate_product, &env->fp_status); +} + +uint64_t helper_fadd_s(CPURISCVState *env, uint64_t rs1, uint64_t rs2) +{ + float32 frs1 = check_nanbox_s(rs1); + float32 frs2 = check_nanbox_s(rs2); + return nanbox_s(float32_add(frs1, frs2, &env->fp_status)); +} + +uint64_t helper_fsub_s(CPURISCVState *env, uint64_t rs1, uint64_t rs2) +{ + float32 frs1 = check_nanbox_s(rs1); + float32 frs2 = check_nanbox_s(rs2); + return nanbox_s(float32_sub(frs1, frs2, &env->fp_status)); +} + +uint64_t helper_fmul_s(CPURISCVState *env, uint64_t rs1, uint64_t rs2) +{ + float32 frs1 = check_nanbox_s(rs1); + float32 frs2 = check_nanbox_s(rs2); + return nanbox_s(float32_mul(frs1, frs2, &env->fp_status)); +} + +uint64_t helper_fdiv_s(CPURISCVState *env, uint64_t rs1, uint64_t rs2) +{ + float32 frs1 = check_nanbox_s(rs1); + float32 frs2 = check_nanbox_s(rs2); + return nanbox_s(float32_div(frs1, frs2, &env->fp_status)); +} + +uint64_t helper_fmin_s(CPURISCVState *env, uint64_t rs1, uint64_t rs2) +{ + float32 frs1 = check_nanbox_s(rs1); + float32 frs2 = check_nanbox_s(rs2); + return nanbox_s(env->priv_ver < PRIV_VERSION_1_11_0 ? + float32_minnum(frs1, frs2, &env->fp_status) : + float32_minimum_number(frs1, frs2, &env->fp_status)); +} + +uint64_t helper_fmax_s(CPURISCVState *env, uint64_t rs1, uint64_t rs2) +{ + float32 frs1 = check_nanbox_s(rs1); + float32 frs2 = check_nanbox_s(rs2); + return nanbox_s(env->priv_ver < PRIV_VERSION_1_11_0 ? + float32_maxnum(frs1, frs2, &env->fp_status) : + float32_maximum_number(frs1, frs2, &env->fp_status)); +} + +uint64_t helper_fsqrt_s(CPURISCVState *env, uint64_t rs1) +{ + float32 frs1 = check_nanbox_s(rs1); + return nanbox_s(float32_sqrt(frs1, &env->fp_status)); +} + +target_ulong helper_fle_s(CPURISCVState *env, uint64_t rs1, uint64_t rs2) +{ + float32 frs1 = check_nanbox_s(rs1); + float32 frs2 = check_nanbox_s(rs2); + return float32_le(frs1, frs2, &env->fp_status); +} + +target_ulong helper_flt_s(CPURISCVState *env, uint64_t rs1, uint64_t rs2) +{ + float32 frs1 = check_nanbox_s(rs1); + float32 frs2 = check_nanbox_s(rs2); + return float32_lt(frs1, frs2, &env->fp_status); +} + +target_ulong helper_feq_s(CPURISCVState *env, uint64_t rs1, uint64_t rs2) +{ + float32 frs1 = check_nanbox_s(rs1); + float32 frs2 = check_nanbox_s(rs2); + return float32_eq_quiet(frs1, frs2, &env->fp_status); +} + +target_ulong helper_fcvt_w_s(CPURISCVState *env, uint64_t rs1) +{ + float32 frs1 = check_nanbox_s(rs1); + return float32_to_int32(frs1, &env->fp_status); +} + +target_ulong helper_fcvt_wu_s(CPURISCVState *env, uint64_t rs1) +{ + float32 frs1 = check_nanbox_s(rs1); + return (int32_t)float32_to_uint32(frs1, &env->fp_status); +} + +target_ulong helper_fcvt_l_s(CPURISCVState *env, uint64_t rs1) +{ + float32 frs1 = check_nanbox_s(rs1); + return float32_to_int64(frs1, &env->fp_status); +} + +target_ulong helper_fcvt_lu_s(CPURISCVState *env, uint64_t rs1) +{ + float32 frs1 = check_nanbox_s(rs1); + return float32_to_uint64(frs1, &env->fp_status); +} + +uint64_t helper_fcvt_s_w(CPURISCVState *env, target_ulong rs1) +{ + return nanbox_s(int32_to_float32((int32_t)rs1, &env->fp_status)); +} + +uint64_t helper_fcvt_s_wu(CPURISCVState *env, target_ulong rs1) +{ + return nanbox_s(uint32_to_float32((uint32_t)rs1, &env->fp_status)); +} + +uint64_t helper_fcvt_s_l(CPURISCVState *env, target_ulong rs1) +{ + return nanbox_s(int64_to_float32(rs1, &env->fp_status)); +} + +uint64_t helper_fcvt_s_lu(CPURISCVState *env, target_ulong rs1) +{ + return nanbox_s(uint64_to_float32(rs1, &env->fp_status)); +} + +target_ulong helper_fclass_s(uint64_t rs1) +{ + float32 frs1 = check_nanbox_s(rs1); + return fclass_s(frs1); +} + +uint64_t helper_fadd_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2) +{ + return float64_add(frs1, frs2, &env->fp_status); +} + +uint64_t helper_fsub_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2) +{ + return float64_sub(frs1, frs2, &env->fp_status); +} + +uint64_t helper_fmul_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2) +{ + return float64_mul(frs1, frs2, &env->fp_status); +} + +uint64_t helper_fdiv_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2) +{ + return float64_div(frs1, frs2, &env->fp_status); +} + +uint64_t helper_fmin_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2) +{ + return env->priv_ver < PRIV_VERSION_1_11_0 ? + float64_minnum(frs1, frs2, &env->fp_status) : + float64_minimum_number(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 ? + float64_maxnum(frs1, frs2, &env->fp_status) : + float64_maximum_number(frs1, frs2, &env->fp_status); +} + +uint64_t helper_fcvt_s_d(CPURISCVState *env, uint64_t rs1) +{ + return nanbox_s(float64_to_float32(rs1, &env->fp_status)); +} + +uint64_t helper_fcvt_d_s(CPURISCVState *env, uint64_t rs1) +{ + float32 frs1 = check_nanbox_s(rs1); + return float32_to_float64(frs1, &env->fp_status); +} + +uint64_t helper_fsqrt_d(CPURISCVState *env, uint64_t frs1) +{ + return float64_sqrt(frs1, &env->fp_status); +} + +target_ulong helper_fle_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2) +{ + return float64_le(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_feq_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2) +{ + return float64_eq_quiet(frs1, frs2, &env->fp_status); +} + +target_ulong helper_fcvt_w_d(CPURISCVState *env, uint64_t frs1) +{ + return float64_to_int32(frs1, &env->fp_status); +} + +target_ulong helper_fcvt_wu_d(CPURISCVState *env, uint64_t frs1) +{ + return (int32_t)float64_to_uint32(frs1, &env->fp_status); +} + +target_ulong helper_fcvt_l_d(CPURISCVState *env, uint64_t frs1) +{ + return float64_to_int64(frs1, &env->fp_status); +} + +target_ulong helper_fcvt_lu_d(CPURISCVState *env, uint64_t frs1) +{ + return float64_to_uint64(frs1, &env->fp_status); +} + +uint64_t helper_fcvt_d_w(CPURISCVState *env, target_ulong rs1) +{ + return int32_to_float64((int32_t)rs1, &env->fp_status); +} + +uint64_t helper_fcvt_d_wu(CPURISCVState *env, target_ulong rs1) +{ + return uint32_to_float64((uint32_t)rs1, &env->fp_status); +} + +uint64_t helper_fcvt_d_l(CPURISCVState *env, target_ulong rs1) +{ + return int64_to_float64(rs1, &env->fp_status); +} + +uint64_t helper_fcvt_d_lu(CPURISCVState *env, target_ulong rs1) +{ + return uint64_to_float64(rs1, &env->fp_status); +} + +target_ulong helper_fclass_d(uint64_t frs1) +{ + return fclass_d(frs1); +} diff --git a/target/riscv/gdbstub.c b/target/riscv/gdbstub.c new file mode 100644 index 000000000..23429179e --- /dev/null +++ b/target/riscv/gdbstub.c @@ -0,0 +1,212 @@ +/* + * RISC-V GDB Server Stub + * + * Copyright (c) 2016-2017 Sagar Karandikar, sagark@eecs.berkeley.edu + * + * 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 "exec/gdbstub.h" +#include "cpu.h" + +int riscv_cpu_gdb_read_register(CPUState *cs, GByteArray *mem_buf, int n) +{ + RISCVCPU *cpu = RISCV_CPU(cs); + CPURISCVState *env = &cpu->env; + + if (n < 32) { + return gdb_get_regl(mem_buf, env->gpr[n]); + } else if (n == 32) { + return gdb_get_regl(mem_buf, env->pc); + } + return 0; +} + +int riscv_cpu_gdb_write_register(CPUState *cs, uint8_t *mem_buf, int n) +{ + RISCVCPU *cpu = RISCV_CPU(cs); + CPURISCVState *env = &cpu->env; + + if (n == 0) { + /* discard writes to x0 */ + return sizeof(target_ulong); + } else if (n < 32) { + env->gpr[n] = ldtul_p(mem_buf); + return sizeof(target_ulong); + } else if (n == 32) { + env->pc = ldtul_p(mem_buf); + return sizeof(target_ulong); + } + return 0; +} + +static int riscv_gdb_get_fpu(CPURISCVState *env, GByteArray *buf, int n) +{ + if (n < 32) { + if (env->misa_ext & RVD) { + return gdb_get_reg64(buf, env->fpr[n]); + } + if (env->misa_ext & RVF) { + return gdb_get_reg32(buf, env->fpr[n]); + } + /* there is hole between ft11 and fflags in fpu.xml */ + } else if (n < 36 && n > 32) { + target_ulong val = 0; + int result; + /* + * CSR_FFLAGS is at index 1 in csr_register, and gdb says it is FP + * register 33, so we recalculate the map index. + * This also works for CSR_FRM and CSR_FCSR. + */ + result = riscv_csrrw_debug(env, n - 32, &val, + 0, 0); + if (result == RISCV_EXCP_NONE) { + return gdb_get_regl(buf, val); + } + } + return 0; +} + +static int riscv_gdb_set_fpu(CPURISCVState *env, uint8_t *mem_buf, int n) +{ + if (n < 32) { + env->fpr[n] = ldq_p(mem_buf); /* always 64-bit */ + return sizeof(uint64_t); + /* there is hole between ft11 and fflags in fpu.xml */ + } else if (n < 36 && n > 32) { + target_ulong val = ldtul_p(mem_buf); + int result; + /* + * CSR_FFLAGS is at index 1 in csr_register, and gdb says it is FP + * register 33, so we recalculate the map index. + * This also works for CSR_FRM and CSR_FCSR. + */ + result = riscv_csrrw_debug(env, n - 32, NULL, + val, -1); + if (result == RISCV_EXCP_NONE) { + return sizeof(target_ulong); + } + } + return 0; +} + +static int riscv_gdb_get_csr(CPURISCVState *env, GByteArray *buf, int n) +{ + if (n < CSR_TABLE_SIZE) { + target_ulong val = 0; + int result; + + result = riscv_csrrw_debug(env, n, &val, 0, 0); + if (result == RISCV_EXCP_NONE) { + return gdb_get_regl(buf, val); + } + } + return 0; +} + +static int riscv_gdb_set_csr(CPURISCVState *env, uint8_t *mem_buf, int n) +{ + if (n < CSR_TABLE_SIZE) { + target_ulong val = ldtul_p(mem_buf); + int result; + + result = riscv_csrrw_debug(env, n, NULL, val, -1); + if (result == RISCV_EXCP_NONE) { + return sizeof(target_ulong); + } + } + return 0; +} + +static int riscv_gdb_get_virtual(CPURISCVState *cs, GByteArray *buf, int n) +{ + if (n == 0) { +#ifdef CONFIG_USER_ONLY + return gdb_get_regl(buf, 0); +#else + return gdb_get_regl(buf, cs->priv); +#endif + } + return 0; +} + +static int riscv_gdb_set_virtual(CPURISCVState *cs, uint8_t *mem_buf, int n) +{ + if (n == 0) { +#ifndef CONFIG_USER_ONLY + cs->priv = ldtul_p(mem_buf) & 0x3; + if (cs->priv == PRV_H) { + cs->priv = PRV_S; + } +#endif + return sizeof(target_ulong); + } + return 0; +} + +static int riscv_gen_dynamic_csr_xml(CPUState *cs, int base_reg) +{ + RISCVCPU *cpu = RISCV_CPU(cs); + CPURISCVState *env = &cpu->env; + GString *s = g_string_new(NULL); + riscv_csr_predicate_fn predicate; + int bitsize = 16 << env->misa_mxl_max; + int i; + + g_string_printf(s, "<?xml version=\"1.0\"?>"); + g_string_append_printf(s, "<!DOCTYPE feature SYSTEM \"gdb-target.dtd\">"); + g_string_append_printf(s, "<feature name=\"org.gnu.gdb.riscv.csr\">"); + + for (i = 0; i < CSR_TABLE_SIZE; i++) { + predicate = csr_ops[i].predicate; + if (predicate && (predicate(env, i) == RISCV_EXCP_NONE)) { + if (csr_ops[i].name) { + g_string_append_printf(s, "<reg name=\"%s\"", csr_ops[i].name); + } else { + g_string_append_printf(s, "<reg name=\"csr%03x\"", i); + } + g_string_append_printf(s, " bitsize=\"%d\"", bitsize); + g_string_append_printf(s, " regnum=\"%d\"/>", base_reg + i); + } + } + + g_string_append_printf(s, "</feature>"); + + cpu->dyn_csr_xml = g_string_free(s, false); + return CSR_TABLE_SIZE; +} + +void riscv_cpu_register_gdb_regs_for_features(CPUState *cs) +{ + RISCVCPU *cpu = RISCV_CPU(cs); + CPURISCVState *env = &cpu->env; + if (env->misa_ext & RVD) { + gdb_register_coprocessor(cs, riscv_gdb_get_fpu, riscv_gdb_set_fpu, + 36, "riscv-64bit-fpu.xml", 0); + } else if (env->misa_ext & RVF) { + gdb_register_coprocessor(cs, riscv_gdb_get_fpu, riscv_gdb_set_fpu, + 36, "riscv-32bit-fpu.xml", 0); + } +#if defined(TARGET_RISCV32) + gdb_register_coprocessor(cs, riscv_gdb_get_virtual, riscv_gdb_set_virtual, + 1, "riscv-32bit-virtual.xml", 0); +#elif defined(TARGET_RISCV64) + gdb_register_coprocessor(cs, riscv_gdb_get_virtual, riscv_gdb_set_virtual, + 1, "riscv-64bit-virtual.xml", 0); +#endif + + gdb_register_coprocessor(cs, riscv_gdb_get_csr, riscv_gdb_set_csr, + riscv_gen_dynamic_csr_xml(cs, cs->gdb_num_regs), + "riscv-csr.xml", 0); +} diff --git a/target/riscv/helper.h b/target/riscv/helper.h new file mode 100644 index 000000000..c7a537622 --- /dev/null +++ b/target/riscv/helper.h @@ -0,0 +1,1149 @@ +/* Exceptions */ +DEF_HELPER_2(raise_exception, noreturn, env, i32) + +/* Floating Point - rounding mode */ +DEF_HELPER_FLAGS_2(set_rounding_mode, TCG_CALL_NO_WG, void, env, i32) + +/* Floating Point - fused */ +DEF_HELPER_FLAGS_4(fmadd_s, TCG_CALL_NO_RWG, i64, env, i64, i64, i64) +DEF_HELPER_FLAGS_4(fmadd_d, TCG_CALL_NO_RWG, i64, env, i64, i64, i64) +DEF_HELPER_FLAGS_4(fmsub_s, TCG_CALL_NO_RWG, i64, env, i64, i64, i64) +DEF_HELPER_FLAGS_4(fmsub_d, TCG_CALL_NO_RWG, i64, env, i64, i64, i64) +DEF_HELPER_FLAGS_4(fnmsub_s, TCG_CALL_NO_RWG, i64, env, i64, i64, i64) +DEF_HELPER_FLAGS_4(fnmsub_d, TCG_CALL_NO_RWG, i64, env, i64, i64, i64) +DEF_HELPER_FLAGS_4(fnmadd_s, TCG_CALL_NO_RWG, i64, env, i64, i64, i64) +DEF_HELPER_FLAGS_4(fnmadd_d, TCG_CALL_NO_RWG, i64, env, i64, i64, i64) + +/* Floating Point - Single Precision */ +DEF_HELPER_FLAGS_3(fadd_s, TCG_CALL_NO_RWG, i64, env, i64, i64) +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(fmax_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(flt_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) +DEF_HELPER_FLAGS_2(fcvt_l_s, TCG_CALL_NO_RWG, tl, env, i64) +DEF_HELPER_FLAGS_2(fcvt_lu_s, TCG_CALL_NO_RWG, tl, env, i64) +DEF_HELPER_FLAGS_2(fcvt_s_w, TCG_CALL_NO_RWG, i64, env, tl) +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_1(fclass_s, TCG_CALL_NO_RWG_SE, tl, i64) + +/* Floating Point - Double Precision */ +DEF_HELPER_FLAGS_3(fadd_d, TCG_CALL_NO_RWG, i64, env, i64, i64) +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(fmax_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(flt_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(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) +DEF_HELPER_FLAGS_2(fcvt_d_w, TCG_CALL_NO_RWG, i64, env, tl) +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) + +/* Bitmanip */ +DEF_HELPER_FLAGS_2(clmul, TCG_CALL_NO_RWG_SE, tl, tl, tl) +DEF_HELPER_FLAGS_2(clmulr, TCG_CALL_NO_RWG_SE, tl, tl, tl) + +/* Special functions */ +DEF_HELPER_2(csrr, tl, env, int) +DEF_HELPER_3(csrw, void, env, int, tl) +DEF_HELPER_4(csrrw, tl, env, int, tl, tl) +#ifndef CONFIG_USER_ONLY +DEF_HELPER_2(sret, tl, env, tl) +DEF_HELPER_2(mret, tl, env, tl) +DEF_HELPER_1(wfi, void, env) +DEF_HELPER_1(tlb_flush, void, env) +#endif + +/* Hypervisor functions */ +#ifndef CONFIG_USER_ONLY +DEF_HELPER_1(hyp_tlb_flush, void, env) +DEF_HELPER_1(hyp_gvma_tlb_flush, void, env) +DEF_HELPER_2(hyp_hlvx_hu, tl, env, tl) +DEF_HELPER_2(hyp_hlvx_wu, tl, env, tl) +#endif + +/* Vector functions */ +DEF_HELPER_3(vsetvl, tl, env, tl, tl) +DEF_HELPER_5(vlb_v_b, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlb_v_b_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlb_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlb_v_h_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlb_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlb_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlb_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlb_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlh_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlh_v_h_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlh_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlh_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlh_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlh_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlw_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlw_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlw_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlw_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vle_v_b, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vle_v_b_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vle_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vle_v_h_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vle_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vle_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vle_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vle_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbu_v_b, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbu_v_b_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbu_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbu_v_h_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbu_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbu_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbu_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbu_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlhu_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlhu_v_h_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlhu_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlhu_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlhu_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlhu_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlwu_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlwu_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlwu_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlwu_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsb_v_b, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsb_v_b_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsb_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsb_v_h_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsb_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsb_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsb_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsb_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsh_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsh_v_h_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsh_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsh_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsh_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsh_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsw_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsw_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsw_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsw_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vse_v_b, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vse_v_b_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vse_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vse_v_h_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vse_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vse_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vse_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vse_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_6(vlsb_v_b, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vlsb_v_h, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vlsb_v_w, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vlsb_v_d, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vlsh_v_h, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vlsh_v_w, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vlsh_v_d, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vlsw_v_w, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vlsw_v_d, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vlse_v_b, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vlse_v_h, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vlse_v_w, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vlse_v_d, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vlsbu_v_b, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vlsbu_v_h, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vlsbu_v_w, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vlsbu_v_d, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vlshu_v_h, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vlshu_v_w, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vlshu_v_d, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vlswu_v_w, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vlswu_v_d, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vssb_v_b, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vssb_v_h, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vssb_v_w, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vssb_v_d, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vssh_v_h, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vssh_v_w, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vssh_v_d, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vssw_v_w, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vssw_v_d, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vsse_v_b, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vsse_v_h, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vsse_v_w, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vsse_v_d, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vlxb_v_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxb_v_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxb_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxb_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxh_v_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxh_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxh_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxe_v_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxe_v_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxe_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxe_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxbu_v_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxbu_v_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxbu_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxbu_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxhu_v_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxhu_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxhu_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxwu_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxwu_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxb_v_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxb_v_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxb_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxb_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxh_v_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxh_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxh_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxe_v_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxe_v_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxe_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxe_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_5(vlbff_v_b, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbff_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbff_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbff_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlhff_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlhff_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlhff_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlwff_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlwff_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vleff_v_b, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vleff_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vleff_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vleff_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbuff_v_b, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbuff_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbuff_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbuff_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlhuff_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlhuff_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlhuff_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlwuff_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlwuff_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_6(vamoswapw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoswapd_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoaddw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoaddd_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoxorw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoxord_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoandw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoandd_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoorw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoord_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamominw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamomind_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamomaxw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamomaxd_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamominuw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamominud_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamomaxuw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamomaxud_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoswapw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoaddw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoxorw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoandw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoorw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamominw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamomaxw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamominuw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamomaxuw_v_w, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vadd_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vadd_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsub_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsub_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsub_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsub_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vadd_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vadd_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vadd_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vadd_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsub_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsub_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsub_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsub_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vrsub_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vrsub_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vrsub_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vrsub_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_FLAGS_4(vec_rsubs8, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(vec_rsubs16, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(vec_rsubs32, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(vec_rsubs64, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) + +DEF_HELPER_6(vwaddu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwaddu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwaddu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsubu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsubu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsubu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwadd_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsub_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsub_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsub_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwaddu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwaddu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwaddu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsubu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsubu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsubu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwadd_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwadd_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwadd_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsub_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsub_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsub_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwaddu_wv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwaddu_wv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwaddu_wv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsubu_wv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsubu_wv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsubu_wv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwadd_wv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwadd_wv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwadd_wv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsub_wv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsub_wv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsub_wv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwaddu_wx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwaddu_wx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwaddu_wx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsubu_wx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsubu_wx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsubu_wx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwadd_wx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwadd_wx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwadd_wx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsub_wx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsub_wx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsub_wx_w, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vadc_vvm_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vadc_vvm_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vadc_vvm_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vadc_vvm_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsbc_vvm_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsbc_vvm_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsbc_vvm_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsbc_vvm_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmadc_vvm_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmadc_vvm_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmadc_vvm_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmadc_vvm_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsbc_vvm_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsbc_vvm_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsbc_vvm_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsbc_vvm_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vadc_vxm_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vadc_vxm_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vadc_vxm_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vadc_vxm_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsbc_vxm_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsbc_vxm_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsbc_vxm_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsbc_vxm_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmadc_vxm_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmadc_vxm_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmadc_vxm_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmadc_vxm_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsbc_vxm_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsbc_vxm_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsbc_vxm_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsbc_vxm_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vand_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vand_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vand_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vand_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vor_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vor_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vor_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vor_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vxor_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vxor_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vxor_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vxor_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vand_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vand_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vand_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vand_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vor_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vor_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vor_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vor_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vxor_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vxor_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vxor_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vxor_vx_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vsll_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsll_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsll_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsll_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsrl_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsrl_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsrl_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsrl_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsra_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsra_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsra_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsra_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsll_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsll_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsll_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsll_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsrl_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsrl_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsrl_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsrl_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsra_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsra_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsra_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsra_vx_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vnsrl_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnsrl_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnsrl_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnsra_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnsra_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnsra_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnsrl_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnsrl_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnsrl_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnsra_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnsra_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnsra_vx_w, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vmseq_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmseq_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmseq_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmseq_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsne_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsne_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsne_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsne_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsltu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsltu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsltu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsltu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmslt_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmslt_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmslt_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmslt_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsleu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsleu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsleu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsleu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsle_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsle_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsle_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsle_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmseq_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmseq_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmseq_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmseq_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsne_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsne_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsne_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsne_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsltu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsltu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsltu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsltu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmslt_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmslt_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmslt_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmslt_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsleu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsleu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsleu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsleu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsle_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsle_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsle_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsle_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsgtu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsgtu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsgtu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsgtu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsgt_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsgt_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsgt_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsgt_vx_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vminu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vminu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vminu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vminu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmin_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmin_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmin_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmin_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmaxu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmaxu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmaxu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmaxu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmax_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmax_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmax_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmax_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vminu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vminu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vminu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vminu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmin_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmin_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmin_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmin_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmaxu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmaxu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmaxu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmaxu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmax_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmax_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmax_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmax_vx_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vmul_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmul_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmul_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmul_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulh_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulh_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulh_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulh_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulhu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulhu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulhu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulhu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulhsu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulhsu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulhsu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulhsu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmul_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmul_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmul_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmul_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulh_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulh_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulh_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulh_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulhu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulhu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulhu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulhu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulhsu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulhsu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulhsu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulhsu_vx_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vdivu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vdivu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vdivu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vdivu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vdiv_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vdiv_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vdiv_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vdiv_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vremu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vremu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vremu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vremu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vrem_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vrem_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vrem_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vrem_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vdivu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vdivu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vdivu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vdivu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vdiv_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vdiv_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vdiv_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vdiv_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vremu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vremu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vremu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vremu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vrem_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vrem_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vrem_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vrem_vx_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vwmul_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmul_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmul_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmulu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmulu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmulu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmulsu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmulsu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmulsu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmul_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmul_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmul_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmulu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmulu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmulu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmulsu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmulsu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmulsu_vx_w, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vmacc_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmacc_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmacc_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmacc_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnmsac_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnmsac_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnmsac_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnmsac_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmadd_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmadd_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnmsub_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnmsub_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnmsub_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnmsub_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmacc_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmacc_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmacc_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmacc_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnmsac_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnmsac_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnmsac_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnmsac_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmadd_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmadd_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmadd_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmadd_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnmsub_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnmsub_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnmsub_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnmsub_vx_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vwmaccu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmaccu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmaccu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmacc_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmacc_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmacc_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmaccsu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmaccsu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmaccsu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmaccu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmaccu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmaccu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmacc_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmacc_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmacc_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmaccsu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmaccsu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmaccsu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmaccus_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmaccus_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmaccus_vx_w, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vmerge_vvm_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmerge_vvm_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmerge_vvm_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmerge_vvm_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmerge_vxm_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmerge_vxm_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmerge_vxm_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmerge_vxm_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_4(vmv_v_v_b, void, ptr, ptr, env, i32) +DEF_HELPER_4(vmv_v_v_h, void, ptr, ptr, env, i32) +DEF_HELPER_4(vmv_v_v_w, void, ptr, ptr, env, i32) +DEF_HELPER_4(vmv_v_v_d, void, ptr, ptr, env, i32) +DEF_HELPER_4(vmv_v_x_b, void, ptr, i64, env, i32) +DEF_HELPER_4(vmv_v_x_h, void, ptr, i64, env, i32) +DEF_HELPER_4(vmv_v_x_w, void, ptr, i64, env, i32) +DEF_HELPER_4(vmv_v_x_d, void, ptr, i64, env, i32) + +DEF_HELPER_6(vsaddu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsaddu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsaddu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsaddu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsadd_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsadd_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssubu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssubu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssubu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssubu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssub_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssub_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssub_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssub_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsaddu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsaddu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsaddu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsaddu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsadd_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsadd_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsadd_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsadd_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssubu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssubu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssubu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssubu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssub_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssub_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssub_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssub_vx_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vaadd_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vaadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vaadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vaadd_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vasub_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vasub_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vasub_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vasub_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vaadd_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vaadd_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vaadd_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vaadd_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vasub_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vasub_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vasub_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vasub_vx_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vsmul_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsmul_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsmul_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsmul_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsmul_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsmul_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsmul_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsmul_vx_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vwsmaccu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsmaccu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsmaccu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsmacc_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsmacc_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsmacc_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsmaccsu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsmaccsu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsmaccsu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsmaccu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsmaccu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsmaccu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsmacc_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsmacc_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsmacc_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsmaccsu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsmaccsu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsmaccsu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsmaccus_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsmaccus_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsmaccus_vx_w, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vssrl_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssrl_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssrl_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssrl_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssra_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssra_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssra_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssra_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssrl_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssrl_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssrl_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssrl_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssra_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssra_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssra_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssra_vx_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vnclip_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnclip_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnclip_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnclipu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnclipu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnclipu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnclipu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnclipu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnclipu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnclip_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnclip_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnclip_vx_w, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vfadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfadd_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfsub_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfsub_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfsub_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfadd_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfadd_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfadd_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfsub_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfsub_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfsub_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfrsub_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfrsub_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfrsub_vf_d, void, ptr, ptr, i64, ptr, env, i32) + +DEF_HELPER_6(vfwadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfwadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfwsub_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfwsub_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfwadd_wv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfwadd_wv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfwsub_wv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfwsub_wv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfwadd_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfwadd_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfwsub_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfwsub_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfwadd_wf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfwadd_wf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfwsub_wf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfwsub_wf_w, void, ptr, ptr, i64, ptr, env, i32) + +DEF_HELPER_6(vfmul_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmul_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmul_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfdiv_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfdiv_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfdiv_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmul_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmul_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmul_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfdiv_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfdiv_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfdiv_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfrdiv_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfrdiv_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfrdiv_vf_d, void, ptr, ptr, i64, ptr, env, i32) + +DEF_HELPER_6(vfwmul_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfwmul_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfwmul_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfwmul_vf_w, void, ptr, ptr, i64, ptr, env, i32) + +DEF_HELPER_6(vfmacc_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmacc_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmacc_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmacc_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmacc_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmacc_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmsac_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmsac_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmsac_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmsac_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmsac_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmsac_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmadd_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmadd_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmsub_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmsub_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmsub_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmsub_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmsub_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmsub_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmacc_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmacc_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmacc_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmacc_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmacc_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmacc_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmsac_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmsac_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmsac_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmsac_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmsac_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmsac_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmadd_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmadd_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmadd_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmadd_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmadd_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmadd_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmsub_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmsub_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmsub_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmsub_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmsub_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmsub_vf_d, void, ptr, ptr, i64, ptr, env, i32) + +DEF_HELPER_6(vfwmacc_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfwmacc_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfwnmacc_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfwnmacc_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfwmsac_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfwmsac_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfwnmsac_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfwnmsac_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfwmacc_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfwmacc_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfwnmacc_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfwnmacc_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfwmsac_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfwmsac_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfwnmsac_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfwnmsac_vf_w, void, ptr, ptr, i64, ptr, env, i32) + +DEF_HELPER_5(vfsqrt_v_h, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfsqrt_v_w, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfsqrt_v_d, void, ptr, ptr, ptr, env, i32) + +DEF_HELPER_6(vfmin_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmin_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmin_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmax_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmax_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmax_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmin_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmin_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmin_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmax_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmax_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmax_vf_d, void, ptr, ptr, i64, ptr, env, i32) + +DEF_HELPER_6(vfsgnj_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfsgnj_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfsgnj_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfsgnjn_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfsgnjn_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfsgnjn_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfsgnjx_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfsgnjx_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfsgnjx_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfsgnj_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfsgnj_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfsgnj_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfsgnjn_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfsgnjn_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfsgnjn_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfsgnjx_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfsgnjx_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfsgnjx_vf_d, void, ptr, ptr, i64, ptr, env, i32) + +DEF_HELPER_6(vmfeq_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmfeq_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmfeq_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmfne_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmfne_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmfne_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmflt_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmflt_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmflt_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmfle_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmfle_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmfle_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmfeq_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vmfeq_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vmfeq_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vmfne_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vmfne_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vmfne_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vmflt_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vmflt_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vmflt_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vmfle_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vmfle_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vmfle_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vmfgt_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vmfgt_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vmfgt_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vmfge_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vmfge_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vmfge_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vmford_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmford_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmford_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmford_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vmford_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vmford_vf_d, void, ptr, ptr, i64, ptr, env, i32) + +DEF_HELPER_5(vfclass_v_h, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfclass_v_w, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfclass_v_d, void, ptr, ptr, ptr, env, i32) + +DEF_HELPER_6(vfmerge_vfm_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmerge_vfm_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmerge_vfm_d, void, ptr, ptr, i64, ptr, env, i32) + +DEF_HELPER_5(vfcvt_xu_f_v_h, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfcvt_xu_f_v_w, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfcvt_xu_f_v_d, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfcvt_x_f_v_h, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfcvt_x_f_v_w, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfcvt_x_f_v_d, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfcvt_f_xu_v_h, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfcvt_f_xu_v_w, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfcvt_f_xu_v_d, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfcvt_f_x_v_h, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfcvt_f_x_v_w, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfcvt_f_x_v_d, void, ptr, ptr, ptr, env, i32) + +DEF_HELPER_5(vfwcvt_xu_f_v_h, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfwcvt_xu_f_v_w, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfwcvt_x_f_v_h, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfwcvt_x_f_v_w, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfwcvt_f_xu_v_h, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfwcvt_f_xu_v_w, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfwcvt_f_x_v_h, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfwcvt_f_x_v_w, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfwcvt_f_f_v_h, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfwcvt_f_f_v_w, void, ptr, ptr, ptr, env, i32) + +DEF_HELPER_5(vfncvt_xu_f_v_h, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfncvt_xu_f_v_w, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfncvt_x_f_v_h, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfncvt_x_f_v_w, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfncvt_f_xu_v_h, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfncvt_f_xu_v_w, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfncvt_f_x_v_h, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfncvt_f_x_v_w, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfncvt_f_f_v_h, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfncvt_f_f_v_w, void, ptr, ptr, ptr, env, i32) + +DEF_HELPER_6(vredsum_vs_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredsum_vs_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredsum_vs_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredsum_vs_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredmaxu_vs_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredmaxu_vs_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredmaxu_vs_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredmaxu_vs_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredmax_vs_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredmax_vs_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredmax_vs_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredmax_vs_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredminu_vs_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredminu_vs_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredminu_vs_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredminu_vs_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredmin_vs_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredmin_vs_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredmin_vs_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredmin_vs_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredand_vs_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredand_vs_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredand_vs_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredand_vs_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredor_vs_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredor_vs_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredor_vs_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredor_vs_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredxor_vs_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredxor_vs_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredxor_vs_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vredxor_vs_d, void, ptr, ptr, ptr, ptr, env, i32) + +DEF_HELPER_6(vwredsumu_vs_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwredsumu_vs_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwredsumu_vs_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwredsum_vs_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwredsum_vs_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwredsum_vs_w, void, ptr, ptr, ptr, ptr, env, i32) + +DEF_HELPER_6(vfredsum_vs_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfredsum_vs_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfredsum_vs_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfredmax_vs_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfredmax_vs_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfredmax_vs_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfredmin_vs_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfredmin_vs_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfredmin_vs_d, void, ptr, ptr, ptr, ptr, env, i32) + +DEF_HELPER_6(vfwredsum_vs_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfwredsum_vs_w, void, ptr, ptr, ptr, ptr, env, i32) + +DEF_HELPER_6(vmand_mm, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmnand_mm, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmandnot_mm, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmxor_mm, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmor_mm, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmnor_mm, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmornot_mm, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmxnor_mm, void, ptr, ptr, ptr, ptr, env, i32) + +DEF_HELPER_4(vmpopc_m, tl, ptr, ptr, env, i32) + +DEF_HELPER_4(vmfirst_m, tl, ptr, ptr, env, i32) + +DEF_HELPER_5(vmsbf_m, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vmsif_m, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vmsof_m, void, ptr, ptr, ptr, env, i32) + +DEF_HELPER_5(viota_m_b, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(viota_m_h, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(viota_m_w, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(viota_m_d, void, ptr, ptr, ptr, env, i32) + +DEF_HELPER_4(vid_v_b, void, ptr, ptr, env, i32) +DEF_HELPER_4(vid_v_h, void, ptr, ptr, env, i32) +DEF_HELPER_4(vid_v_w, void, ptr, ptr, env, i32) +DEF_HELPER_4(vid_v_d, void, ptr, ptr, env, i32) + +DEF_HELPER_6(vslideup_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslideup_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslideup_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslideup_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslidedown_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslidedown_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslidedown_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslidedown_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslide1up_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslide1up_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslide1up_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslide1up_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslide1down_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslide1down_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslide1down_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslide1down_vx_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vrgather_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vrgather_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vrgather_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vrgather_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vrgather_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vrgather_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vrgather_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vrgather_vx_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vcompress_vm_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vcompress_vm_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vcompress_vm_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vcompress_vm_d, void, ptr, ptr, ptr, ptr, env, i32) diff --git a/target/riscv/insn16.decode b/target/riscv/insn16.decode new file mode 100644 index 000000000..2e9212663 --- /dev/null +++ b/target/riscv/insn16.decode @@ -0,0 +1,162 @@ +# +# RISC-V translation routines for the RVXI Base Integer Instruction Set. +# +# Copyright (c) 2018 Peer Adelt, peer.adelt@hni.uni-paderborn.de +# Bastian Koppelmann, kbastian@mail.uni-paderborn.de +# +# 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/>. + +# Fields: +%rd 7:5 +%rs1_3 7:3 !function=ex_rvc_register +%rs2_3 2:3 !function=ex_rvc_register +%rs2_5 2:5 + +# Immediates: +%imm_ci 12:s1 2:5 +%nzuimm_ciw 7:4 11:2 5:1 6:1 !function=ex_shift_2 +%uimm_cl_d 5:2 10:3 !function=ex_shift_3 +%uimm_cl_w 5:1 10:3 6:1 !function=ex_shift_2 +%imm_cb 12:s1 5:2 2:1 10:2 3:2 !function=ex_shift_1 +%imm_cj 12:s1 8:1 9:2 6:1 7:1 2:1 11:1 3:3 !function=ex_shift_1 + +%shimm_6bit 12:1 2:5 !function=ex_rvc_shifti +%uimm_6bit_ld 2:3 12:1 5:2 !function=ex_shift_3 +%uimm_6bit_lw 2:2 12:1 4:3 !function=ex_shift_2 +%uimm_6bit_sd 7:3 10:3 !function=ex_shift_3 +%uimm_6bit_sw 7:2 9:4 !function=ex_shift_2 + +%imm_addi16sp 12:s1 3:2 5:1 2:1 6:1 !function=ex_shift_4 +%imm_lui 12:s1 2:5 !function=ex_shift_12 + + +# Argument sets imported from insn32.decode: +&empty !extern +&r rd rs1 rs2 !extern +&i imm rs1 rd !extern +&s imm rs1 rs2 !extern +&j imm rd !extern +&b imm rs2 rs1 !extern +&u imm rd !extern +&shift shamt rs1 rd !extern + + +# Formats 16: +@cr .... ..... ..... .. &r rs2=%rs2_5 rs1=%rd %rd +@ci ... . ..... ..... .. &i imm=%imm_ci rs1=%rd %rd +@cl_d ... ... ... .. ... .. &i imm=%uimm_cl_d rs1=%rs1_3 rd=%rs2_3 +@cl_w ... ... ... .. ... .. &i imm=%uimm_cl_w rs1=%rs1_3 rd=%rs2_3 +@cs_2 ... ... ... .. ... .. &r rs2=%rs2_3 rs1=%rs1_3 rd=%rs1_3 +@cs_d ... ... ... .. ... .. &s imm=%uimm_cl_d rs1=%rs1_3 rs2=%rs2_3 +@cs_w ... ... ... .. ... .. &s imm=%uimm_cl_w rs1=%rs1_3 rs2=%rs2_3 +@cj ... ........... .. &j imm=%imm_cj +@cb_z ... ... ... .. ... .. &b imm=%imm_cb rs1=%rs1_3 rs2=0 + +@c_ldsp ... . ..... ..... .. &i imm=%uimm_6bit_ld rs1=2 %rd +@c_lwsp ... . ..... ..... .. &i imm=%uimm_6bit_lw rs1=2 %rd +@c_sdsp ... . ..... ..... .. &s imm=%uimm_6bit_sd rs1=2 rs2=%rs2_5 +@c_swsp ... . ..... ..... .. &s imm=%uimm_6bit_sw rs1=2 rs2=%rs2_5 +@c_li ... . ..... ..... .. &i imm=%imm_ci rs1=0 %rd +@c_lui ... . ..... ..... .. &u imm=%imm_lui %rd +@c_jalr ... . ..... ..... .. &i imm=0 rs1=%rd +@c_mv ... . ..... ..... .. &i imm=0 rs1=%rs2_5 %rd + +@c_addi4spn ... . ..... ..... .. &i imm=%nzuimm_ciw rs1=2 rd=%rs2_3 +@c_addi16sp ... . ..... ..... .. &i imm=%imm_addi16sp rs1=2 rd=2 + +@c_shift ... . .. ... ..... .. \ + &shift rd=%rs1_3 rs1=%rs1_3 shamt=%shimm_6bit +@c_shift2 ... . .. ... ..... .. \ + &shift rd=%rd rs1=%rd shamt=%shimm_6bit + +@c_andi ... . .. ... ..... .. &i imm=%imm_ci rs1=%rs1_3 rd=%rs1_3 + +# *** RV32/64C Standard Extension (Quadrant 0) *** +{ + # Opcode of all zeros is illegal; rd != 0, nzuimm == 0 is reserved. + illegal 000 000 000 00 --- 00 + addi 000 ... ... .. ... 00 @c_addi4spn +} +fld 001 ... ... .. ... 00 @cl_d +lw 010 ... ... .. ... 00 @cl_w +fsd 101 ... ... .. ... 00 @cs_d +sw 110 ... ... .. ... 00 @cs_w + +# *** RV32C and RV64C specific Standard Extension (Quadrant 0) *** +{ + ld 011 ... ... .. ... 00 @cl_d + flw 011 ... ... .. ... 00 @cl_w +} +{ + sd 111 ... ... .. ... 00 @cs_d + fsw 111 ... ... .. ... 00 @cs_w +} + +# *** RV32/64C Standard Extension (Quadrant 1) *** +addi 000 . ..... ..... 01 @ci +addi 010 . ..... ..... 01 @c_li +{ + illegal 011 0 ----- 00000 01 # c.addi16sp and c.lui, RES nzimm=0 + addi 011 . 00010 ..... 01 @c_addi16sp + lui 011 . ..... ..... 01 @c_lui +} +srli 100 . 00 ... ..... 01 @c_shift +srai 100 . 01 ... ..... 01 @c_shift +andi 100 . 10 ... ..... 01 @c_andi +sub 100 0 11 ... 00 ... 01 @cs_2 +xor 100 0 11 ... 01 ... 01 @cs_2 +or 100 0 11 ... 10 ... 01 @cs_2 +and 100 0 11 ... 11 ... 01 @cs_2 +jal 101 ........... 01 @cj rd=0 # C.J +beq 110 ... ... ..... 01 @cb_z +bne 111 ... ... ..... 01 @cb_z + +# *** RV64C and RV32C specific Standard Extension (Quadrant 1) *** +{ + c64_illegal 001 - 00000 ----- 01 # c.addiw, RES rd=0 + addiw 001 . ..... ..... 01 @ci + jal 001 ........... 01 @cj rd=1 # C.JAL +} +subw 100 1 11 ... 00 ... 01 @cs_2 +addw 100 1 11 ... 01 ... 01 @cs_2 + +# *** RV32/64C Standard Extension (Quadrant 2) *** +slli 000 . ..... ..... 10 @c_shift2 +fld 001 . ..... ..... 10 @c_ldsp +{ + illegal 010 - 00000 ----- 10 # c.lwsp, RES rd=0 + lw 010 . ..... ..... 10 @c_lwsp +} +{ + illegal 100 0 00000 00000 10 # c.jr, RES rs1=0 + jalr 100 0 ..... 00000 10 @c_jalr rd=0 # C.JR + addi 100 0 ..... ..... 10 @c_mv +} +{ + ebreak 100 1 00000 00000 10 + jalr 100 1 ..... 00000 10 @c_jalr rd=1 # C.JALR + add 100 1 ..... ..... 10 @cr +} +fsd 101 ...... ..... 10 @c_sdsp +sw 110 . ..... ..... 10 @c_swsp + +# *** RV32C and RV64C specific Standard Extension (Quadrant 2) *** +{ + c64_illegal 011 - 00000 ----- 10 # c.ldsp, RES rd=0 + ld 011 . ..... ..... 10 @c_ldsp + flw 011 . ..... ..... 10 @c_lwsp +} +{ + sd 111 . ..... ..... 10 @c_sdsp + fsw 111 . ..... ..... 10 @c_swsp +} diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode new file mode 100644 index 000000000..2f251dac1 --- /dev/null +++ b/target/riscv/insn32.decode @@ -0,0 +1,728 @@ +# +# RISC-V translation routines for the RVXI Base Integer Instruction Set. +# +# Copyright (c) 2018 Peer Adelt, peer.adelt@hni.uni-paderborn.de +# Bastian Koppelmann, kbastian@mail.uni-paderborn.de +# +# 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/>. + +# Fields: +%rs3 27:5 +%rs2 20:5 +%rs1 15:5 +%rd 7:5 +%sh5 20:5 + +%sh7 20:7 +%csr 20:12 +%rm 12:3 +%nf 29:3 !function=ex_plus_1 + +# immediates: +%imm_i 20:s12 +%imm_s 25:s7 7:5 +%imm_b 31:s1 7:1 25:6 8:4 !function=ex_shift_1 +%imm_j 31:s1 12:8 20:1 21:10 !function=ex_shift_1 +%imm_u 12:s20 !function=ex_shift_12 + +# Argument sets: +&empty +&b imm rs2 rs1 +&i imm rs1 rd +&j imm rd +&r rd rs1 rs2 +&r2 rd rs1 +&r2_s rs1 rs2 +&s imm rs1 rs2 +&u imm rd +&shift shamt rs1 rd +&atomic aq rl rs2 rs1 rd +&rmrr vm rd rs1 rs2 +&rmr vm rd rs2 +&rwdvm vm wd rd rs1 rs2 +&r2nfvm vm rd rs1 nf +&rnfvm vm rd rs1 rs2 nf + +# Formats 32: +@r ....... ..... ..... ... ..... ....... &r %rs2 %rs1 %rd +@i ............ ..... ... ..... ....... &i imm=%imm_i %rs1 %rd +@b ....... ..... ..... ... ..... ....... &b imm=%imm_b %rs2 %rs1 +@s ....... ..... ..... ... ..... ....... &s imm=%imm_s %rs2 %rs1 +@u .................... ..... ....... &u imm=%imm_u %rd +@j .................... ..... ....... &j imm=%imm_j %rd + +@sh ...... ...... ..... ... ..... ....... &shift shamt=%sh7 %rs1 %rd +@csr ............ ..... ... ..... ....... %csr %rs1 %rd + +@atom_ld ..... aq:1 rl:1 ..... ........ ..... ....... &atomic rs2=0 %rs1 %rd +@atom_st ..... aq:1 rl:1 ..... ........ ..... ....... &atomic %rs2 %rs1 %rd + +@r4_rm ..... .. ..... ..... ... ..... ....... %rs3 %rs2 %rs1 %rm %rd +@r_rm ....... ..... ..... ... ..... ....... %rs2 %rs1 %rm %rd +@r2_rm ....... ..... ..... ... ..... ....... %rs1 %rm %rd +@r2 ....... ..... ..... ... ..... ....... &r2 %rs1 %rd +@r2_nfvm ... ... vm:1 ..... ..... ... ..... ....... &r2nfvm %nf %rs1 %rd +@r2_vm ...... vm:1 ..... ..... ... ..... ....... &rmr %rs2 %rd +@r1_vm ...... vm:1 ..... ..... ... ..... ....... %rd +@r_nfvm ... ... vm:1 ..... ..... ... ..... ....... &rnfvm %nf %rs2 %rs1 %rd +@r2rd ....... ..... ..... ... ..... ....... %rs2 %rd +@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 +@r_wdvm ..... wd:1 vm:1 ..... ..... ... ..... ....... &rwdvm %rs2 %rs1 %rd +@r2_zimm . zimm:11 ..... ... ..... ....... %rs1 %rd +@r2_s ....... ..... ..... ... ..... ....... %rs2 %rs1 + +@hfence_gvma ....... ..... ..... ... ..... ....... %rs2 %rs1 +@hfence_vvma ....... ..... ..... ... ..... ....... %rs2 %rs1 + +@sfence_vma ....... ..... ..... ... ..... ....... %rs2 %rs1 +@sfence_vm ....... ..... ..... ... ..... ....... %rs1 + +# Formats 64: +@sh5 ....... ..... ..... ... ..... ....... &shift shamt=%sh5 %rs1 %rd + +# *** Privileged Instructions *** +ecall 000000000000 00000 000 00000 1110011 +ebreak 000000000001 00000 000 00000 1110011 +uret 0000000 00010 00000 000 00000 1110011 +sret 0001000 00010 00000 000 00000 1110011 +mret 0011000 00010 00000 000 00000 1110011 +wfi 0001000 00101 00000 000 00000 1110011 +sfence_vma 0001001 ..... ..... 000 00000 1110011 @sfence_vma +sfence_vm 0001000 00100 ..... 000 00000 1110011 @sfence_vm + +# *** RV32I Base Instruction Set *** +lui .................... ..... 0110111 @u +auipc .................... ..... 0010111 @u +jal .................... ..... 1101111 @j +jalr ............ ..... 000 ..... 1100111 @i +beq ....... ..... ..... 000 ..... 1100011 @b +bne ....... ..... ..... 001 ..... 1100011 @b +blt ....... ..... ..... 100 ..... 1100011 @b +bge ....... ..... ..... 101 ..... 1100011 @b +bltu ....... ..... ..... 110 ..... 1100011 @b +bgeu ....... ..... ..... 111 ..... 1100011 @b +lb ............ ..... 000 ..... 0000011 @i +lh ............ ..... 001 ..... 0000011 @i +lw ............ ..... 010 ..... 0000011 @i +lbu ............ ..... 100 ..... 0000011 @i +lhu ............ ..... 101 ..... 0000011 @i +sb ....... ..... ..... 000 ..... 0100011 @s +sh ....... ..... ..... 001 ..... 0100011 @s +sw ....... ..... ..... 010 ..... 0100011 @s +addi ............ ..... 000 ..... 0010011 @i +slti ............ ..... 010 ..... 0010011 @i +sltiu ............ ..... 011 ..... 0010011 @i +xori ............ ..... 100 ..... 0010011 @i +ori ............ ..... 110 ..... 0010011 @i +andi ............ ..... 111 ..... 0010011 @i +slli 00000. ...... ..... 001 ..... 0010011 @sh +srli 00000. ...... ..... 101 ..... 0010011 @sh +srai 01000. ...... ..... 101 ..... 0010011 @sh +add 0000000 ..... ..... 000 ..... 0110011 @r +sub 0100000 ..... ..... 000 ..... 0110011 @r +sll 0000000 ..... ..... 001 ..... 0110011 @r +slt 0000000 ..... ..... 010 ..... 0110011 @r +sltu 0000000 ..... ..... 011 ..... 0110011 @r +xor 0000000 ..... ..... 100 ..... 0110011 @r +srl 0000000 ..... ..... 101 ..... 0110011 @r +sra 0100000 ..... ..... 101 ..... 0110011 @r +or 0000000 ..... ..... 110 ..... 0110011 @r +and 0000000 ..... ..... 111 ..... 0110011 @r +fence ---- pred:4 succ:4 ----- 000 ----- 0001111 +fence_i ---- ---- ---- ----- 001 ----- 0001111 +csrrw ............ ..... 001 ..... 1110011 @csr +csrrs ............ ..... 010 ..... 1110011 @csr +csrrc ............ ..... 011 ..... 1110011 @csr +csrrwi ............ ..... 101 ..... 1110011 @csr +csrrsi ............ ..... 110 ..... 1110011 @csr +csrrci ............ ..... 111 ..... 1110011 @csr + +# *** RV64I Base Instruction Set (in addition to RV32I) *** +lwu ............ ..... 110 ..... 0000011 @i +ld ............ ..... 011 ..... 0000011 @i +sd ....... ..... ..... 011 ..... 0100011 @s +addiw ............ ..... 000 ..... 0011011 @i +slliw 0000000 ..... ..... 001 ..... 0011011 @sh5 +srliw 0000000 ..... ..... 101 ..... 0011011 @sh5 +sraiw 0100000 ..... ..... 101 ..... 0011011 @sh5 +addw 0000000 ..... ..... 000 ..... 0111011 @r +subw 0100000 ..... ..... 000 ..... 0111011 @r +sllw 0000000 ..... ..... 001 ..... 0111011 @r +srlw 0000000 ..... ..... 101 ..... 0111011 @r +sraw 0100000 ..... ..... 101 ..... 0111011 @r + +# *** RV32M Standard Extension *** +mul 0000001 ..... ..... 000 ..... 0110011 @r +mulh 0000001 ..... ..... 001 ..... 0110011 @r +mulhsu 0000001 ..... ..... 010 ..... 0110011 @r +mulhu 0000001 ..... ..... 011 ..... 0110011 @r +div 0000001 ..... ..... 100 ..... 0110011 @r +divu 0000001 ..... ..... 101 ..... 0110011 @r +rem 0000001 ..... ..... 110 ..... 0110011 @r +remu 0000001 ..... ..... 111 ..... 0110011 @r + +# *** RV64M Standard Extension (in addition to RV32M) *** +mulw 0000001 ..... ..... 000 ..... 0111011 @r +divw 0000001 ..... ..... 100 ..... 0111011 @r +divuw 0000001 ..... ..... 101 ..... 0111011 @r +remw 0000001 ..... ..... 110 ..... 0111011 @r +remuw 0000001 ..... ..... 111 ..... 0111011 @r + +# *** RV32A Standard Extension *** +lr_w 00010 . . 00000 ..... 010 ..... 0101111 @atom_ld +sc_w 00011 . . ..... ..... 010 ..... 0101111 @atom_st +amoswap_w 00001 . . ..... ..... 010 ..... 0101111 @atom_st +amoadd_w 00000 . . ..... ..... 010 ..... 0101111 @atom_st +amoxor_w 00100 . . ..... ..... 010 ..... 0101111 @atom_st +amoand_w 01100 . . ..... ..... 010 ..... 0101111 @atom_st +amoor_w 01000 . . ..... ..... 010 ..... 0101111 @atom_st +amomin_w 10000 . . ..... ..... 010 ..... 0101111 @atom_st +amomax_w 10100 . . ..... ..... 010 ..... 0101111 @atom_st +amominu_w 11000 . . ..... ..... 010 ..... 0101111 @atom_st +amomaxu_w 11100 . . ..... ..... 010 ..... 0101111 @atom_st + +# *** RV64A Standard Extension (in addition to RV32A) *** +lr_d 00010 . . 00000 ..... 011 ..... 0101111 @atom_ld +sc_d 00011 . . ..... ..... 011 ..... 0101111 @atom_st +amoswap_d 00001 . . ..... ..... 011 ..... 0101111 @atom_st +amoadd_d 00000 . . ..... ..... 011 ..... 0101111 @atom_st +amoxor_d 00100 . . ..... ..... 011 ..... 0101111 @atom_st +amoand_d 01100 . . ..... ..... 011 ..... 0101111 @atom_st +amoor_d 01000 . . ..... ..... 011 ..... 0101111 @atom_st +amomin_d 10000 . . ..... ..... 011 ..... 0101111 @atom_st +amomax_d 10100 . . ..... ..... 011 ..... 0101111 @atom_st +amominu_d 11000 . . ..... ..... 011 ..... 0101111 @atom_st +amomaxu_d 11100 . . ..... ..... 011 ..... 0101111 @atom_st + +# *** RV32F Standard Extension *** +flw ............ ..... 010 ..... 0000111 @i +fsw ....... ..... ..... 010 ..... 0100111 @s +fmadd_s ..... 00 ..... ..... ... ..... 1000011 @r4_rm +fmsub_s ..... 00 ..... ..... ... ..... 1000111 @r4_rm +fnmsub_s ..... 00 ..... ..... ... ..... 1001011 @r4_rm +fnmadd_s ..... 00 ..... ..... ... ..... 1001111 @r4_rm +fadd_s 0000000 ..... ..... ... ..... 1010011 @r_rm +fsub_s 0000100 ..... ..... ... ..... 1010011 @r_rm +fmul_s 0001000 ..... ..... ... ..... 1010011 @r_rm +fdiv_s 0001100 ..... ..... ... ..... 1010011 @r_rm +fsqrt_s 0101100 00000 ..... ... ..... 1010011 @r2_rm +fsgnj_s 0010000 ..... ..... 000 ..... 1010011 @r +fsgnjn_s 0010000 ..... ..... 001 ..... 1010011 @r +fsgnjx_s 0010000 ..... ..... 010 ..... 1010011 @r +fmin_s 0010100 ..... ..... 000 ..... 1010011 @r +fmax_s 0010100 ..... ..... 001 ..... 1010011 @r +fcvt_w_s 1100000 00000 ..... ... ..... 1010011 @r2_rm +fcvt_wu_s 1100000 00001 ..... ... ..... 1010011 @r2_rm +fmv_x_w 1110000 00000 ..... 000 ..... 1010011 @r2 +feq_s 1010000 ..... ..... 010 ..... 1010011 @r +flt_s 1010000 ..... ..... 001 ..... 1010011 @r +fle_s 1010000 ..... ..... 000 ..... 1010011 @r +fclass_s 1110000 00000 ..... 001 ..... 1010011 @r2 +fcvt_s_w 1101000 00000 ..... ... ..... 1010011 @r2_rm +fcvt_s_wu 1101000 00001 ..... ... ..... 1010011 @r2_rm +fmv_w_x 1111000 00000 ..... 000 ..... 1010011 @r2 + +# *** RV64F Standard Extension (in addition to RV32F) *** +fcvt_l_s 1100000 00010 ..... ... ..... 1010011 @r2_rm +fcvt_lu_s 1100000 00011 ..... ... ..... 1010011 @r2_rm +fcvt_s_l 1101000 00010 ..... ... ..... 1010011 @r2_rm +fcvt_s_lu 1101000 00011 ..... ... ..... 1010011 @r2_rm + +# *** RV32D Standard Extension *** +fld ............ ..... 011 ..... 0000111 @i +fsd ....... ..... ..... 011 ..... 0100111 @s +fmadd_d ..... 01 ..... ..... ... ..... 1000011 @r4_rm +fmsub_d ..... 01 ..... ..... ... ..... 1000111 @r4_rm +fnmsub_d ..... 01 ..... ..... ... ..... 1001011 @r4_rm +fnmadd_d ..... 01 ..... ..... ... ..... 1001111 @r4_rm +fadd_d 0000001 ..... ..... ... ..... 1010011 @r_rm +fsub_d 0000101 ..... ..... ... ..... 1010011 @r_rm +fmul_d 0001001 ..... ..... ... ..... 1010011 @r_rm +fdiv_d 0001101 ..... ..... ... ..... 1010011 @r_rm +fsqrt_d 0101101 00000 ..... ... ..... 1010011 @r2_rm +fsgnj_d 0010001 ..... ..... 000 ..... 1010011 @r +fsgnjn_d 0010001 ..... ..... 001 ..... 1010011 @r +fsgnjx_d 0010001 ..... ..... 010 ..... 1010011 @r +fmin_d 0010101 ..... ..... 000 ..... 1010011 @r +fmax_d 0010101 ..... ..... 001 ..... 1010011 @r +fcvt_s_d 0100000 00001 ..... ... ..... 1010011 @r2_rm +fcvt_d_s 0100001 00000 ..... ... ..... 1010011 @r2_rm +feq_d 1010001 ..... ..... 010 ..... 1010011 @r +flt_d 1010001 ..... ..... 001 ..... 1010011 @r +fle_d 1010001 ..... ..... 000 ..... 1010011 @r +fclass_d 1110001 00000 ..... 001 ..... 1010011 @r2 +fcvt_w_d 1100001 00000 ..... ... ..... 1010011 @r2_rm +fcvt_wu_d 1100001 00001 ..... ... ..... 1010011 @r2_rm +fcvt_d_w 1101001 00000 ..... ... ..... 1010011 @r2_rm +fcvt_d_wu 1101001 00001 ..... ... ..... 1010011 @r2_rm + +# *** RV64D Standard Extension (in addition to RV32D) *** +fcvt_l_d 1100001 00010 ..... ... ..... 1010011 @r2_rm +fcvt_lu_d 1100001 00011 ..... ... ..... 1010011 @r2_rm +fmv_x_d 1110001 00000 ..... 000 ..... 1010011 @r2 +fcvt_d_l 1101001 00010 ..... ... ..... 1010011 @r2_rm +fcvt_d_lu 1101001 00011 ..... ... ..... 1010011 @r2_rm +fmv_d_x 1111001 00000 ..... 000 ..... 1010011 @r2 + +# *** RV32H Base Instruction Set *** +hlv_b 0110000 00000 ..... 100 ..... 1110011 @r2 +hlv_bu 0110000 00001 ..... 100 ..... 1110011 @r2 +hlv_h 0110010 00000 ..... 100 ..... 1110011 @r2 +hlv_hu 0110010 00001 ..... 100 ..... 1110011 @r2 +hlvx_hu 0110010 00011 ..... 100 ..... 1110011 @r2 +hlv_w 0110100 00000 ..... 100 ..... 1110011 @r2 +hlvx_wu 0110100 00011 ..... 100 ..... 1110011 @r2 +hsv_b 0110001 ..... ..... 100 00000 1110011 @r2_s +hsv_h 0110011 ..... ..... 100 00000 1110011 @r2_s +hsv_w 0110101 ..... ..... 100 00000 1110011 @r2_s +hfence_gvma 0110001 ..... ..... 000 00000 1110011 @hfence_gvma +hfence_vvma 0010001 ..... ..... 000 00000 1110011 @hfence_vvma + +# *** RV64H Base Instruction Set *** +hlv_wu 0110100 00001 ..... 100 ..... 1110011 @r2 +hlv_d 0110110 00000 ..... 100 ..... 1110011 @r2 +hsv_d 0110111 ..... ..... 100 00000 1110011 @r2_s + +# *** Vector loads and stores are encoded within LOADFP/STORE-FP *** +vlb_v ... 100 . 00000 ..... 000 ..... 0000111 @r2_nfvm +vlh_v ... 100 . 00000 ..... 101 ..... 0000111 @r2_nfvm +vlw_v ... 100 . 00000 ..... 110 ..... 0000111 @r2_nfvm +vle_v ... 000 . 00000 ..... 111 ..... 0000111 @r2_nfvm +vlbu_v ... 000 . 00000 ..... 000 ..... 0000111 @r2_nfvm +vlhu_v ... 000 . 00000 ..... 101 ..... 0000111 @r2_nfvm +vlwu_v ... 000 . 00000 ..... 110 ..... 0000111 @r2_nfvm +vlbff_v ... 100 . 10000 ..... 000 ..... 0000111 @r2_nfvm +vlhff_v ... 100 . 10000 ..... 101 ..... 0000111 @r2_nfvm +vlwff_v ... 100 . 10000 ..... 110 ..... 0000111 @r2_nfvm +vleff_v ... 000 . 10000 ..... 111 ..... 0000111 @r2_nfvm +vlbuff_v ... 000 . 10000 ..... 000 ..... 0000111 @r2_nfvm +vlhuff_v ... 000 . 10000 ..... 101 ..... 0000111 @r2_nfvm +vlwuff_v ... 000 . 10000 ..... 110 ..... 0000111 @r2_nfvm +vsb_v ... 000 . 00000 ..... 000 ..... 0100111 @r2_nfvm +vsh_v ... 000 . 00000 ..... 101 ..... 0100111 @r2_nfvm +vsw_v ... 000 . 00000 ..... 110 ..... 0100111 @r2_nfvm +vse_v ... 000 . 00000 ..... 111 ..... 0100111 @r2_nfvm + +vlsb_v ... 110 . ..... ..... 000 ..... 0000111 @r_nfvm +vlsh_v ... 110 . ..... ..... 101 ..... 0000111 @r_nfvm +vlsw_v ... 110 . ..... ..... 110 ..... 0000111 @r_nfvm +vlse_v ... 010 . ..... ..... 111 ..... 0000111 @r_nfvm +vlsbu_v ... 010 . ..... ..... 000 ..... 0000111 @r_nfvm +vlshu_v ... 010 . ..... ..... 101 ..... 0000111 @r_nfvm +vlswu_v ... 010 . ..... ..... 110 ..... 0000111 @r_nfvm +vssb_v ... 010 . ..... ..... 000 ..... 0100111 @r_nfvm +vssh_v ... 010 . ..... ..... 101 ..... 0100111 @r_nfvm +vssw_v ... 010 . ..... ..... 110 ..... 0100111 @r_nfvm +vsse_v ... 010 . ..... ..... 111 ..... 0100111 @r_nfvm + +vlxb_v ... 111 . ..... ..... 000 ..... 0000111 @r_nfvm +vlxh_v ... 111 . ..... ..... 101 ..... 0000111 @r_nfvm +vlxw_v ... 111 . ..... ..... 110 ..... 0000111 @r_nfvm +vlxe_v ... 011 . ..... ..... 111 ..... 0000111 @r_nfvm +vlxbu_v ... 011 . ..... ..... 000 ..... 0000111 @r_nfvm +vlxhu_v ... 011 . ..... ..... 101 ..... 0000111 @r_nfvm +vlxwu_v ... 011 . ..... ..... 110 ..... 0000111 @r_nfvm +# Vector ordered-indexed and unordered-indexed store insns. +vsxb_v ... -11 . ..... ..... 000 ..... 0100111 @r_nfvm +vsxh_v ... -11 . ..... ..... 101 ..... 0100111 @r_nfvm +vsxw_v ... -11 . ..... ..... 110 ..... 0100111 @r_nfvm +vsxe_v ... -11 . ..... ..... 111 ..... 0100111 @r_nfvm + +#*** Vector AMO operations are encoded under the standard AMO major opcode *** +vamoswapw_v 00001 . . ..... ..... 110 ..... 0101111 @r_wdvm +vamoaddw_v 00000 . . ..... ..... 110 ..... 0101111 @r_wdvm +vamoxorw_v 00100 . . ..... ..... 110 ..... 0101111 @r_wdvm +vamoandw_v 01100 . . ..... ..... 110 ..... 0101111 @r_wdvm +vamoorw_v 01000 . . ..... ..... 110 ..... 0101111 @r_wdvm +vamominw_v 10000 . . ..... ..... 110 ..... 0101111 @r_wdvm +vamomaxw_v 10100 . . ..... ..... 110 ..... 0101111 @r_wdvm +vamominuw_v 11000 . . ..... ..... 110 ..... 0101111 @r_wdvm +vamomaxuw_v 11100 . . ..... ..... 110 ..... 0101111 @r_wdvm + +# *** new major opcode OP-V *** +vadd_vv 000000 . ..... ..... 000 ..... 1010111 @r_vm +vadd_vx 000000 . ..... ..... 100 ..... 1010111 @r_vm +vadd_vi 000000 . ..... ..... 011 ..... 1010111 @r_vm +vsub_vv 000010 . ..... ..... 000 ..... 1010111 @r_vm +vsub_vx 000010 . ..... ..... 100 ..... 1010111 @r_vm +vrsub_vx 000011 . ..... ..... 100 ..... 1010111 @r_vm +vrsub_vi 000011 . ..... ..... 011 ..... 1010111 @r_vm +vwaddu_vv 110000 . ..... ..... 010 ..... 1010111 @r_vm +vwaddu_vx 110000 . ..... ..... 110 ..... 1010111 @r_vm +vwadd_vv 110001 . ..... ..... 010 ..... 1010111 @r_vm +vwadd_vx 110001 . ..... ..... 110 ..... 1010111 @r_vm +vwsubu_vv 110010 . ..... ..... 010 ..... 1010111 @r_vm +vwsubu_vx 110010 . ..... ..... 110 ..... 1010111 @r_vm +vwsub_vv 110011 . ..... ..... 010 ..... 1010111 @r_vm +vwsub_vx 110011 . ..... ..... 110 ..... 1010111 @r_vm +vwaddu_wv 110100 . ..... ..... 010 ..... 1010111 @r_vm +vwaddu_wx 110100 . ..... ..... 110 ..... 1010111 @r_vm +vwadd_wv 110101 . ..... ..... 010 ..... 1010111 @r_vm +vwadd_wx 110101 . ..... ..... 110 ..... 1010111 @r_vm +vwsubu_wv 110110 . ..... ..... 010 ..... 1010111 @r_vm +vwsubu_wx 110110 . ..... ..... 110 ..... 1010111 @r_vm +vwsub_wv 110111 . ..... ..... 010 ..... 1010111 @r_vm +vwsub_wx 110111 . ..... ..... 110 ..... 1010111 @r_vm +vadc_vvm 010000 1 ..... ..... 000 ..... 1010111 @r_vm_1 +vadc_vxm 010000 1 ..... ..... 100 ..... 1010111 @r_vm_1 +vadc_vim 010000 1 ..... ..... 011 ..... 1010111 @r_vm_1 +vmadc_vvm 010001 1 ..... ..... 000 ..... 1010111 @r_vm_1 +vmadc_vxm 010001 1 ..... ..... 100 ..... 1010111 @r_vm_1 +vmadc_vim 010001 1 ..... ..... 011 ..... 1010111 @r_vm_1 +vsbc_vvm 010010 1 ..... ..... 000 ..... 1010111 @r_vm_1 +vsbc_vxm 010010 1 ..... ..... 100 ..... 1010111 @r_vm_1 +vmsbc_vvm 010011 1 ..... ..... 000 ..... 1010111 @r_vm_1 +vmsbc_vxm 010011 1 ..... ..... 100 ..... 1010111 @r_vm_1 +vand_vv 001001 . ..... ..... 000 ..... 1010111 @r_vm +vand_vx 001001 . ..... ..... 100 ..... 1010111 @r_vm +vand_vi 001001 . ..... ..... 011 ..... 1010111 @r_vm +vor_vv 001010 . ..... ..... 000 ..... 1010111 @r_vm +vor_vx 001010 . ..... ..... 100 ..... 1010111 @r_vm +vor_vi 001010 . ..... ..... 011 ..... 1010111 @r_vm +vxor_vv 001011 . ..... ..... 000 ..... 1010111 @r_vm +vxor_vx 001011 . ..... ..... 100 ..... 1010111 @r_vm +vxor_vi 001011 . ..... ..... 011 ..... 1010111 @r_vm +vsll_vv 100101 . ..... ..... 000 ..... 1010111 @r_vm +vsll_vx 100101 . ..... ..... 100 ..... 1010111 @r_vm +vsll_vi 100101 . ..... ..... 011 ..... 1010111 @r_vm +vsrl_vv 101000 . ..... ..... 000 ..... 1010111 @r_vm +vsrl_vx 101000 . ..... ..... 100 ..... 1010111 @r_vm +vsrl_vi 101000 . ..... ..... 011 ..... 1010111 @r_vm +vsra_vv 101001 . ..... ..... 000 ..... 1010111 @r_vm +vsra_vx 101001 . ..... ..... 100 ..... 1010111 @r_vm +vsra_vi 101001 . ..... ..... 011 ..... 1010111 @r_vm +vnsrl_vv 101100 . ..... ..... 000 ..... 1010111 @r_vm +vnsrl_vx 101100 . ..... ..... 100 ..... 1010111 @r_vm +vnsrl_vi 101100 . ..... ..... 011 ..... 1010111 @r_vm +vnsra_vv 101101 . ..... ..... 000 ..... 1010111 @r_vm +vnsra_vx 101101 . ..... ..... 100 ..... 1010111 @r_vm +vnsra_vi 101101 . ..... ..... 011 ..... 1010111 @r_vm +vmseq_vv 011000 . ..... ..... 000 ..... 1010111 @r_vm +vmseq_vx 011000 . ..... ..... 100 ..... 1010111 @r_vm +vmseq_vi 011000 . ..... ..... 011 ..... 1010111 @r_vm +vmsne_vv 011001 . ..... ..... 000 ..... 1010111 @r_vm +vmsne_vx 011001 . ..... ..... 100 ..... 1010111 @r_vm +vmsne_vi 011001 . ..... ..... 011 ..... 1010111 @r_vm +vmsltu_vv 011010 . ..... ..... 000 ..... 1010111 @r_vm +vmsltu_vx 011010 . ..... ..... 100 ..... 1010111 @r_vm +vmslt_vv 011011 . ..... ..... 000 ..... 1010111 @r_vm +vmslt_vx 011011 . ..... ..... 100 ..... 1010111 @r_vm +vmsleu_vv 011100 . ..... ..... 000 ..... 1010111 @r_vm +vmsleu_vx 011100 . ..... ..... 100 ..... 1010111 @r_vm +vmsleu_vi 011100 . ..... ..... 011 ..... 1010111 @r_vm +vmsle_vv 011101 . ..... ..... 000 ..... 1010111 @r_vm +vmsle_vx 011101 . ..... ..... 100 ..... 1010111 @r_vm +vmsle_vi 011101 . ..... ..... 011 ..... 1010111 @r_vm +vmsgtu_vx 011110 . ..... ..... 100 ..... 1010111 @r_vm +vmsgtu_vi 011110 . ..... ..... 011 ..... 1010111 @r_vm +vmsgt_vx 011111 . ..... ..... 100 ..... 1010111 @r_vm +vmsgt_vi 011111 . ..... ..... 011 ..... 1010111 @r_vm +vminu_vv 000100 . ..... ..... 000 ..... 1010111 @r_vm +vminu_vx 000100 . ..... ..... 100 ..... 1010111 @r_vm +vmin_vv 000101 . ..... ..... 000 ..... 1010111 @r_vm +vmin_vx 000101 . ..... ..... 100 ..... 1010111 @r_vm +vmaxu_vv 000110 . ..... ..... 000 ..... 1010111 @r_vm +vmaxu_vx 000110 . ..... ..... 100 ..... 1010111 @r_vm +vmax_vv 000111 . ..... ..... 000 ..... 1010111 @r_vm +vmax_vx 000111 . ..... ..... 100 ..... 1010111 @r_vm +vmul_vv 100101 . ..... ..... 010 ..... 1010111 @r_vm +vmul_vx 100101 . ..... ..... 110 ..... 1010111 @r_vm +vmulh_vv 100111 . ..... ..... 010 ..... 1010111 @r_vm +vmulh_vx 100111 . ..... ..... 110 ..... 1010111 @r_vm +vmulhu_vv 100100 . ..... ..... 010 ..... 1010111 @r_vm +vmulhu_vx 100100 . ..... ..... 110 ..... 1010111 @r_vm +vmulhsu_vv 100110 . ..... ..... 010 ..... 1010111 @r_vm +vmulhsu_vx 100110 . ..... ..... 110 ..... 1010111 @r_vm +vdivu_vv 100000 . ..... ..... 010 ..... 1010111 @r_vm +vdivu_vx 100000 . ..... ..... 110 ..... 1010111 @r_vm +vdiv_vv 100001 . ..... ..... 010 ..... 1010111 @r_vm +vdiv_vx 100001 . ..... ..... 110 ..... 1010111 @r_vm +vremu_vv 100010 . ..... ..... 010 ..... 1010111 @r_vm +vremu_vx 100010 . ..... ..... 110 ..... 1010111 @r_vm +vrem_vv 100011 . ..... ..... 010 ..... 1010111 @r_vm +vrem_vx 100011 . ..... ..... 110 ..... 1010111 @r_vm +vwmulu_vv 111000 . ..... ..... 010 ..... 1010111 @r_vm +vwmulu_vx 111000 . ..... ..... 110 ..... 1010111 @r_vm +vwmulsu_vv 111010 . ..... ..... 010 ..... 1010111 @r_vm +vwmulsu_vx 111010 . ..... ..... 110 ..... 1010111 @r_vm +vwmul_vv 111011 . ..... ..... 010 ..... 1010111 @r_vm +vwmul_vx 111011 . ..... ..... 110 ..... 1010111 @r_vm +vmacc_vv 101101 . ..... ..... 010 ..... 1010111 @r_vm +vmacc_vx 101101 . ..... ..... 110 ..... 1010111 @r_vm +vnmsac_vv 101111 . ..... ..... 010 ..... 1010111 @r_vm +vnmsac_vx 101111 . ..... ..... 110 ..... 1010111 @r_vm +vmadd_vv 101001 . ..... ..... 010 ..... 1010111 @r_vm +vmadd_vx 101001 . ..... ..... 110 ..... 1010111 @r_vm +vnmsub_vv 101011 . ..... ..... 010 ..... 1010111 @r_vm +vnmsub_vx 101011 . ..... ..... 110 ..... 1010111 @r_vm +vwmaccu_vv 111100 . ..... ..... 010 ..... 1010111 @r_vm +vwmaccu_vx 111100 . ..... ..... 110 ..... 1010111 @r_vm +vwmacc_vv 111101 . ..... ..... 010 ..... 1010111 @r_vm +vwmacc_vx 111101 . ..... ..... 110 ..... 1010111 @r_vm +vwmaccsu_vv 111110 . ..... ..... 010 ..... 1010111 @r_vm +vwmaccsu_vx 111110 . ..... ..... 110 ..... 1010111 @r_vm +vwmaccus_vx 111111 . ..... ..... 110 ..... 1010111 @r_vm +vmv_v_v 010111 1 00000 ..... 000 ..... 1010111 @r2 +vmv_v_x 010111 1 00000 ..... 100 ..... 1010111 @r2 +vmv_v_i 010111 1 00000 ..... 011 ..... 1010111 @r2 +vmerge_vvm 010111 0 ..... ..... 000 ..... 1010111 @r_vm_0 +vmerge_vxm 010111 0 ..... ..... 100 ..... 1010111 @r_vm_0 +vmerge_vim 010111 0 ..... ..... 011 ..... 1010111 @r_vm_0 +vsaddu_vv 100000 . ..... ..... 000 ..... 1010111 @r_vm +vsaddu_vx 100000 . ..... ..... 100 ..... 1010111 @r_vm +vsaddu_vi 100000 . ..... ..... 011 ..... 1010111 @r_vm +vsadd_vv 100001 . ..... ..... 000 ..... 1010111 @r_vm +vsadd_vx 100001 . ..... ..... 100 ..... 1010111 @r_vm +vsadd_vi 100001 . ..... ..... 011 ..... 1010111 @r_vm +vssubu_vv 100010 . ..... ..... 000 ..... 1010111 @r_vm +vssubu_vx 100010 . ..... ..... 100 ..... 1010111 @r_vm +vssub_vv 100011 . ..... ..... 000 ..... 1010111 @r_vm +vssub_vx 100011 . ..... ..... 100 ..... 1010111 @r_vm +vaadd_vv 100100 . ..... ..... 000 ..... 1010111 @r_vm +vaadd_vx 100100 . ..... ..... 100 ..... 1010111 @r_vm +vaadd_vi 100100 . ..... ..... 011 ..... 1010111 @r_vm +vasub_vv 100110 . ..... ..... 000 ..... 1010111 @r_vm +vasub_vx 100110 . ..... ..... 100 ..... 1010111 @r_vm +vsmul_vv 100111 . ..... ..... 000 ..... 1010111 @r_vm +vsmul_vx 100111 . ..... ..... 100 ..... 1010111 @r_vm +vwsmaccu_vv 111100 . ..... ..... 000 ..... 1010111 @r_vm +vwsmaccu_vx 111100 . ..... ..... 100 ..... 1010111 @r_vm +vwsmacc_vv 111101 . ..... ..... 000 ..... 1010111 @r_vm +vwsmacc_vx 111101 . ..... ..... 100 ..... 1010111 @r_vm +vwsmaccsu_vv 111110 . ..... ..... 000 ..... 1010111 @r_vm +vwsmaccsu_vx 111110 . ..... ..... 100 ..... 1010111 @r_vm +vwsmaccus_vx 111111 . ..... ..... 100 ..... 1010111 @r_vm +vssrl_vv 101010 . ..... ..... 000 ..... 1010111 @r_vm +vssrl_vx 101010 . ..... ..... 100 ..... 1010111 @r_vm +vssrl_vi 101010 . ..... ..... 011 ..... 1010111 @r_vm +vssra_vv 101011 . ..... ..... 000 ..... 1010111 @r_vm +vssra_vx 101011 . ..... ..... 100 ..... 1010111 @r_vm +vssra_vi 101011 . ..... ..... 011 ..... 1010111 @r_vm +vnclipu_vv 101110 . ..... ..... 000 ..... 1010111 @r_vm +vnclipu_vx 101110 . ..... ..... 100 ..... 1010111 @r_vm +vnclipu_vi 101110 . ..... ..... 011 ..... 1010111 @r_vm +vnclip_vv 101111 . ..... ..... 000 ..... 1010111 @r_vm +vnclip_vx 101111 . ..... ..... 100 ..... 1010111 @r_vm +vnclip_vi 101111 . ..... ..... 011 ..... 1010111 @r_vm +vfadd_vv 000000 . ..... ..... 001 ..... 1010111 @r_vm +vfadd_vf 000000 . ..... ..... 101 ..... 1010111 @r_vm +vfsub_vv 000010 . ..... ..... 001 ..... 1010111 @r_vm +vfsub_vf 000010 . ..... ..... 101 ..... 1010111 @r_vm +vfrsub_vf 100111 . ..... ..... 101 ..... 1010111 @r_vm +vfwadd_vv 110000 . ..... ..... 001 ..... 1010111 @r_vm +vfwadd_vf 110000 . ..... ..... 101 ..... 1010111 @r_vm +vfwadd_wv 110100 . ..... ..... 001 ..... 1010111 @r_vm +vfwadd_wf 110100 . ..... ..... 101 ..... 1010111 @r_vm +vfwsub_vv 110010 . ..... ..... 001 ..... 1010111 @r_vm +vfwsub_vf 110010 . ..... ..... 101 ..... 1010111 @r_vm +vfwsub_wv 110110 . ..... ..... 001 ..... 1010111 @r_vm +vfwsub_wf 110110 . ..... ..... 101 ..... 1010111 @r_vm +vfmul_vv 100100 . ..... ..... 001 ..... 1010111 @r_vm +vfmul_vf 100100 . ..... ..... 101 ..... 1010111 @r_vm +vfdiv_vv 100000 . ..... ..... 001 ..... 1010111 @r_vm +vfdiv_vf 100000 . ..... ..... 101 ..... 1010111 @r_vm +vfrdiv_vf 100001 . ..... ..... 101 ..... 1010111 @r_vm +vfwmul_vv 111000 . ..... ..... 001 ..... 1010111 @r_vm +vfwmul_vf 111000 . ..... ..... 101 ..... 1010111 @r_vm +vfmacc_vv 101100 . ..... ..... 001 ..... 1010111 @r_vm +vfnmacc_vv 101101 . ..... ..... 001 ..... 1010111 @r_vm +vfnmacc_vf 101101 . ..... ..... 101 ..... 1010111 @r_vm +vfmacc_vf 101100 . ..... ..... 101 ..... 1010111 @r_vm +vfmsac_vv 101110 . ..... ..... 001 ..... 1010111 @r_vm +vfmsac_vf 101110 . ..... ..... 101 ..... 1010111 @r_vm +vfnmsac_vv 101111 . ..... ..... 001 ..... 1010111 @r_vm +vfnmsac_vf 101111 . ..... ..... 101 ..... 1010111 @r_vm +vfmadd_vv 101000 . ..... ..... 001 ..... 1010111 @r_vm +vfmadd_vf 101000 . ..... ..... 101 ..... 1010111 @r_vm +vfnmadd_vv 101001 . ..... ..... 001 ..... 1010111 @r_vm +vfnmadd_vf 101001 . ..... ..... 101 ..... 1010111 @r_vm +vfmsub_vv 101010 . ..... ..... 001 ..... 1010111 @r_vm +vfmsub_vf 101010 . ..... ..... 101 ..... 1010111 @r_vm +vfnmsub_vv 101011 . ..... ..... 001 ..... 1010111 @r_vm +vfnmsub_vf 101011 . ..... ..... 101 ..... 1010111 @r_vm +vfwmacc_vv 111100 . ..... ..... 001 ..... 1010111 @r_vm +vfwmacc_vf 111100 . ..... ..... 101 ..... 1010111 @r_vm +vfwnmacc_vv 111101 . ..... ..... 001 ..... 1010111 @r_vm +vfwnmacc_vf 111101 . ..... ..... 101 ..... 1010111 @r_vm +vfwmsac_vv 111110 . ..... ..... 001 ..... 1010111 @r_vm +vfwmsac_vf 111110 . ..... ..... 101 ..... 1010111 @r_vm +vfwnmsac_vv 111111 . ..... ..... 001 ..... 1010111 @r_vm +vfwnmsac_vf 111111 . ..... ..... 101 ..... 1010111 @r_vm +vfsqrt_v 100011 . ..... 00000 001 ..... 1010111 @r2_vm +vfmin_vv 000100 . ..... ..... 001 ..... 1010111 @r_vm +vfmin_vf 000100 . ..... ..... 101 ..... 1010111 @r_vm +vfmax_vv 000110 . ..... ..... 001 ..... 1010111 @r_vm +vfmax_vf 000110 . ..... ..... 101 ..... 1010111 @r_vm +vfsgnj_vv 001000 . ..... ..... 001 ..... 1010111 @r_vm +vfsgnj_vf 001000 . ..... ..... 101 ..... 1010111 @r_vm +vfsgnjn_vv 001001 . ..... ..... 001 ..... 1010111 @r_vm +vfsgnjn_vf 001001 . ..... ..... 101 ..... 1010111 @r_vm +vfsgnjx_vv 001010 . ..... ..... 001 ..... 1010111 @r_vm +vfsgnjx_vf 001010 . ..... ..... 101 ..... 1010111 @r_vm +vmfeq_vv 011000 . ..... ..... 001 ..... 1010111 @r_vm +vmfeq_vf 011000 . ..... ..... 101 ..... 1010111 @r_vm +vmfne_vv 011100 . ..... ..... 001 ..... 1010111 @r_vm +vmfne_vf 011100 . ..... ..... 101 ..... 1010111 @r_vm +vmflt_vv 011011 . ..... ..... 001 ..... 1010111 @r_vm +vmflt_vf 011011 . ..... ..... 101 ..... 1010111 @r_vm +vmfle_vv 011001 . ..... ..... 001 ..... 1010111 @r_vm +vmfle_vf 011001 . ..... ..... 101 ..... 1010111 @r_vm +vmfgt_vf 011101 . ..... ..... 101 ..... 1010111 @r_vm +vmfge_vf 011111 . ..... ..... 101 ..... 1010111 @r_vm +vmford_vv 011010 . ..... ..... 001 ..... 1010111 @r_vm +vmford_vf 011010 . ..... ..... 101 ..... 1010111 @r_vm +vfclass_v 100011 . ..... 10000 001 ..... 1010111 @r2_vm +vfmerge_vfm 010111 0 ..... ..... 101 ..... 1010111 @r_vm_0 +vfmv_v_f 010111 1 00000 ..... 101 ..... 1010111 @r2 +vfcvt_xu_f_v 100010 . ..... 00000 001 ..... 1010111 @r2_vm +vfcvt_x_f_v 100010 . ..... 00001 001 ..... 1010111 @r2_vm +vfcvt_f_xu_v 100010 . ..... 00010 001 ..... 1010111 @r2_vm +vfcvt_f_x_v 100010 . ..... 00011 001 ..... 1010111 @r2_vm +vfwcvt_xu_f_v 100010 . ..... 01000 001 ..... 1010111 @r2_vm +vfwcvt_x_f_v 100010 . ..... 01001 001 ..... 1010111 @r2_vm +vfwcvt_f_xu_v 100010 . ..... 01010 001 ..... 1010111 @r2_vm +vfwcvt_f_x_v 100010 . ..... 01011 001 ..... 1010111 @r2_vm +vfwcvt_f_f_v 100010 . ..... 01100 001 ..... 1010111 @r2_vm +vfncvt_xu_f_v 100010 . ..... 10000 001 ..... 1010111 @r2_vm +vfncvt_x_f_v 100010 . ..... 10001 001 ..... 1010111 @r2_vm +vfncvt_f_xu_v 100010 . ..... 10010 001 ..... 1010111 @r2_vm +vfncvt_f_x_v 100010 . ..... 10011 001 ..... 1010111 @r2_vm +vfncvt_f_f_v 100010 . ..... 10100 001 ..... 1010111 @r2_vm +vredsum_vs 000000 . ..... ..... 010 ..... 1010111 @r_vm +vredand_vs 000001 . ..... ..... 010 ..... 1010111 @r_vm +vredor_vs 000010 . ..... ..... 010 ..... 1010111 @r_vm +vredxor_vs 000011 . ..... ..... 010 ..... 1010111 @r_vm +vredminu_vs 000100 . ..... ..... 010 ..... 1010111 @r_vm +vredmin_vs 000101 . ..... ..... 010 ..... 1010111 @r_vm +vredmaxu_vs 000110 . ..... ..... 010 ..... 1010111 @r_vm +vredmax_vs 000111 . ..... ..... 010 ..... 1010111 @r_vm +vwredsumu_vs 110000 . ..... ..... 000 ..... 1010111 @r_vm +vwredsum_vs 110001 . ..... ..... 000 ..... 1010111 @r_vm +# Vector ordered and unordered reduction sum +vfredsum_vs 0000-1 . ..... ..... 001 ..... 1010111 @r_vm +vfredmin_vs 000101 . ..... ..... 001 ..... 1010111 @r_vm +vfredmax_vs 000111 . ..... ..... 001 ..... 1010111 @r_vm +# Vector widening ordered and unordered float reduction sum +vfwredsum_vs 1100-1 . ..... ..... 001 ..... 1010111 @r_vm +vmand_mm 011001 - ..... ..... 010 ..... 1010111 @r +vmnand_mm 011101 - ..... ..... 010 ..... 1010111 @r +vmandnot_mm 011000 - ..... ..... 010 ..... 1010111 @r +vmxor_mm 011011 - ..... ..... 010 ..... 1010111 @r +vmor_mm 011010 - ..... ..... 010 ..... 1010111 @r +vmnor_mm 011110 - ..... ..... 010 ..... 1010111 @r +vmornot_mm 011100 - ..... ..... 010 ..... 1010111 @r +vmxnor_mm 011111 - ..... ..... 010 ..... 1010111 @r +vmpopc_m 010100 . ..... ----- 010 ..... 1010111 @r2_vm +vmfirst_m 010101 . ..... ----- 010 ..... 1010111 @r2_vm +vmsbf_m 010110 . ..... 00001 010 ..... 1010111 @r2_vm +vmsif_m 010110 . ..... 00011 010 ..... 1010111 @r2_vm +vmsof_m 010110 . ..... 00010 010 ..... 1010111 @r2_vm +viota_m 010110 . ..... 10000 010 ..... 1010111 @r2_vm +vid_v 010110 . 00000 10001 010 ..... 1010111 @r1_vm +vext_x_v 001100 1 ..... ..... 010 ..... 1010111 @r +vmv_s_x 001101 1 00000 ..... 110 ..... 1010111 @r2 +vfmv_f_s 001100 1 ..... 00000 001 ..... 1010111 @r2rd +vfmv_s_f 001101 1 00000 ..... 101 ..... 1010111 @r2 +vslideup_vx 001110 . ..... ..... 100 ..... 1010111 @r_vm +vslideup_vi 001110 . ..... ..... 011 ..... 1010111 @r_vm +vslide1up_vx 001110 . ..... ..... 110 ..... 1010111 @r_vm +vslidedown_vx 001111 . ..... ..... 100 ..... 1010111 @r_vm +vslidedown_vi 001111 . ..... ..... 011 ..... 1010111 @r_vm +vslide1down_vx 001111 . ..... ..... 110 ..... 1010111 @r_vm +vrgather_vv 001100 . ..... ..... 000 ..... 1010111 @r_vm +vrgather_vx 001100 . ..... ..... 100 ..... 1010111 @r_vm +vrgather_vi 001100 . ..... ..... 011 ..... 1010111 @r_vm +vcompress_vm 010111 - ..... ..... 010 ..... 1010111 @r + +vsetvli 0 ........... ..... 111 ..... 1010111 @r2_zimm +vsetvl 1000000 ..... ..... 111 ..... 1010111 @r + +#*** Vector AMO operations (in addition to Zvamo) *** +vamoswapd_v 00001 . . ..... ..... 111 ..... 0101111 @r_wdvm +vamoaddd_v 00000 . . ..... ..... 111 ..... 0101111 @r_wdvm +vamoxord_v 00100 . . ..... ..... 111 ..... 0101111 @r_wdvm +vamoandd_v 01100 . . ..... ..... 111 ..... 0101111 @r_wdvm +vamoord_v 01000 . . ..... ..... 111 ..... 0101111 @r_wdvm +vamomind_v 10000 . . ..... ..... 111 ..... 0101111 @r_wdvm +vamomaxd_v 10100 . . ..... ..... 111 ..... 0101111 @r_wdvm +vamominud_v 11000 . . ..... ..... 111 ..... 0101111 @r_wdvm +vamomaxud_v 11100 . . ..... ..... 111 ..... 0101111 @r_wdvm + +# *** RV32 Zba Standard Extension *** +sh1add 0010000 .......... 010 ..... 0110011 @r +sh2add 0010000 .......... 100 ..... 0110011 @r +sh3add 0010000 .......... 110 ..... 0110011 @r + +# *** RV64 Zba Standard Extension (in addition to RV32 Zba) *** +add_uw 0000100 .......... 000 ..... 0111011 @r +sh1add_uw 0010000 .......... 010 ..... 0111011 @r +sh2add_uw 0010000 .......... 100 ..... 0111011 @r +sh3add_uw 0010000 .......... 110 ..... 0111011 @r +slli_uw 00001 ............ 001 ..... 0011011 @sh + +# *** RV32 Zbb Standard Extension *** +andn 0100000 .......... 111 ..... 0110011 @r +clz 011000 000000 ..... 001 ..... 0010011 @r2 +cpop 011000 000010 ..... 001 ..... 0010011 @r2 +ctz 011000 000001 ..... 001 ..... 0010011 @r2 +max 0000101 .......... 110 ..... 0110011 @r +maxu 0000101 .......... 111 ..... 0110011 @r +min 0000101 .......... 100 ..... 0110011 @r +minu 0000101 .......... 101 ..... 0110011 @r +orc_b 001010 000111 ..... 101 ..... 0010011 @r2 +orn 0100000 .......... 110 ..... 0110011 @r +# The encoding for rev8 differs between RV32 and RV64. +# rev8_32 denotes the RV32 variant. +rev8_32 011010 011000 ..... 101 ..... 0010011 @r2 +rol 0110000 .......... 001 ..... 0110011 @r +ror 0110000 .......... 101 ..... 0110011 @r +rori 01100 ............ 101 ..... 0010011 @sh +sext_b 011000 000100 ..... 001 ..... 0010011 @r2 +sext_h 011000 000101 ..... 001 ..... 0010011 @r2 +xnor 0100000 .......... 100 ..... 0110011 @r +# The encoding for zext.h differs between RV32 and RV64. +# zext_h_32 denotes the RV32 variant. +zext_h_32 0000100 00000 ..... 100 ..... 0110011 @r2 + +# *** RV64 Zbb Standard Extension (in addition to RV32 Zbb) *** +clzw 0110000 00000 ..... 001 ..... 0011011 @r2 +ctzw 0110000 00001 ..... 001 ..... 0011011 @r2 +cpopw 0110000 00010 ..... 001 ..... 0011011 @r2 +# The encoding for rev8 differs between RV32 and RV64. +# When executing on RV64, the encoding used in RV32 is an illegal +# instruction, so we use different handler functions to differentiate. +rev8_64 011010 111000 ..... 101 ..... 0010011 @r2 +rolw 0110000 .......... 001 ..... 0111011 @r +roriw 0110000 .......... 101 ..... 0011011 @sh5 +rorw 0110000 .......... 101 ..... 0111011 @r +# The encoding for zext.h differs between RV32 and RV64. +# When executing on RV64, the encoding used in RV32 is an illegal +# instruction, so we use different handler functions to differentiate. +zext_h_64 0000100 00000 ..... 100 ..... 0111011 @r2 + +# *** RV32 Zbc Standard Extension *** +clmul 0000101 .......... 001 ..... 0110011 @r +clmulh 0000101 .......... 011 ..... 0110011 @r +clmulr 0000101 .......... 010 ..... 0110011 @r + +# *** RV32 Zbs Standard Extension *** +bclr 0100100 .......... 001 ..... 0110011 @r +bclri 01001. ........... 001 ..... 0010011 @sh +bext 0100100 .......... 101 ..... 0110011 @r +bexti 01001. ........... 101 ..... 0010011 @sh +binv 0110100 .......... 001 ..... 0110011 @r +binvi 01101. ........... 001 ..... 0010011 @sh +bset 0010100 .......... 001 ..... 0110011 @r +bseti 00101. ........... 001 ..... 0010011 @sh diff --git a/target/riscv/insn_trans/trans_privileged.c.inc b/target/riscv/insn_trans/trans_privileged.c.inc new file mode 100644 index 000000000..75c6ef80a --- /dev/null +++ b/target/riscv/insn_trans/trans_privileged.c.inc @@ -0,0 +1,128 @@ +/* + * RISC-V translation routines for the RISC-V privileged instructions. + * + * Copyright (c) 2016-2017 Sagar Karandikar, sagark@eecs.berkeley.edu + * Copyright (c) 2018 Peer Adelt, peer.adelt@hni.uni-paderborn.de + * Bastian Koppelmann, kbastian@mail.uni-paderborn.de + * + * 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/>. + */ + +static bool trans_ecall(DisasContext *ctx, arg_ecall *a) +{ + /* always generates U-level ECALL, fixed in do_interrupt handler */ + generate_exception(ctx, RISCV_EXCP_U_ECALL); + return true; +} + +static bool trans_ebreak(DisasContext *ctx, arg_ebreak *a) +{ + target_ulong ebreak_addr = ctx->base.pc_next; + target_ulong pre_addr = ebreak_addr - 4; + target_ulong post_addr = ebreak_addr + 4; + uint32_t pre = 0; + uint32_t ebreak = 0; + uint32_t post = 0; + + /* + * The RISC-V semihosting spec specifies the following + * three-instruction sequence to flag a semihosting call: + * + * slli zero, zero, 0x1f 0x01f01013 + * ebreak 0x00100073 + * srai zero, zero, 0x7 0x40705013 + * + * The two shift operations on the zero register are no-ops, used + * here to signify a semihosting exception, rather than a breakpoint. + * + * Uncompressed instructions are required so that the sequence is easy + * to validate. + * + * The three instructions are required to lie in the same page so + * that no exception will be raised when fetching them. + */ + + if ((pre_addr & TARGET_PAGE_MASK) == (post_addr & TARGET_PAGE_MASK)) { + pre = opcode_at(&ctx->base, pre_addr); + ebreak = opcode_at(&ctx->base, ebreak_addr); + post = opcode_at(&ctx->base, post_addr); + } + + if (pre == 0x01f01013 && ebreak == 0x00100073 && post == 0x40705013) { + generate_exception(ctx, RISCV_EXCP_SEMIHOST); + } else { + generate_exception(ctx, RISCV_EXCP_BREAKPOINT); + } + return true; +} + +static bool trans_uret(DisasContext *ctx, arg_uret *a) +{ + return false; +} + +static bool trans_sret(DisasContext *ctx, arg_sret *a) +{ +#ifndef CONFIG_USER_ONLY + tcg_gen_movi_tl(cpu_pc, ctx->base.pc_next); + + if (has_ext(ctx, RVS)) { + gen_helper_sret(cpu_pc, cpu_env, cpu_pc); + tcg_gen_exit_tb(NULL, 0); /* no chaining */ + ctx->base.is_jmp = DISAS_NORETURN; + } else { + return false; + } + return true; +#else + return false; +#endif +} + +static bool trans_mret(DisasContext *ctx, arg_mret *a) +{ +#ifndef CONFIG_USER_ONLY + tcg_gen_movi_tl(cpu_pc, ctx->base.pc_next); + gen_helper_mret(cpu_pc, cpu_env, cpu_pc); + tcg_gen_exit_tb(NULL, 0); /* no chaining */ + ctx->base.is_jmp = DISAS_NORETURN; + return true; +#else + return false; +#endif +} + +static bool trans_wfi(DisasContext *ctx, arg_wfi *a) +{ +#ifndef CONFIG_USER_ONLY + tcg_gen_movi_tl(cpu_pc, ctx->pc_succ_insn); + gen_helper_wfi(cpu_env); + return true; +#else + return false; +#endif +} + +static bool trans_sfence_vma(DisasContext *ctx, arg_sfence_vma *a) +{ +#ifndef CONFIG_USER_ONLY + gen_helper_tlb_flush(cpu_env); + return true; +#endif + return false; +} + +static bool trans_sfence_vm(DisasContext *ctx, arg_sfence_vm *a) +{ + return false; +} diff --git a/target/riscv/insn_trans/trans_rva.c.inc b/target/riscv/insn_trans/trans_rva.c.inc new file mode 100644 index 000000000..40fe132b0 --- /dev/null +++ b/target/riscv/insn_trans/trans_rva.c.inc @@ -0,0 +1,226 @@ +/* + * RISC-V translation routines for the RV64A Standard Extension. + * + * Copyright (c) 2016-2017 Sagar Karandikar, sagark@eecs.berkeley.edu + * Copyright (c) 2018 Peer Adelt, peer.adelt@hni.uni-paderborn.de + * Bastian Koppelmann, kbastian@mail.uni-paderborn.de + * + * 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/>. + */ + +static bool gen_lr(DisasContext *ctx, arg_atomic *a, MemOp mop) +{ + TCGv src1 = get_gpr(ctx, a->rs1, EXT_ZERO); + + if (a->rl) { + tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL); + } + src1 = gen_pm_adjust_address(ctx, src1); + tcg_gen_qemu_ld_tl(load_val, src1, ctx->mem_idx, mop); + if (a->aq) { + tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); + } + + /* Put addr in load_res, data in load_val. */ + tcg_gen_mov_tl(load_res, src1); + gen_set_gpr(ctx, a->rd, load_val); + + return true; +} + +static bool gen_sc(DisasContext *ctx, arg_atomic *a, MemOp mop) +{ + TCGv dest, src1, src2; + TCGLabel *l1 = gen_new_label(); + TCGLabel *l2 = gen_new_label(); + + src1 = get_gpr(ctx, a->rs1, EXT_ZERO); + src1 = gen_pm_adjust_address(ctx, src1); + tcg_gen_brcond_tl(TCG_COND_NE, load_res, src1, l1); + + /* + * Note that the TCG atomic primitives are SC, + * so we can ignore AQ/RL along this path. + */ + dest = dest_gpr(ctx, a->rd); + src2 = get_gpr(ctx, a->rs2, EXT_NONE); + tcg_gen_atomic_cmpxchg_tl(dest, load_res, load_val, src2, + ctx->mem_idx, mop); + tcg_gen_setcond_tl(TCG_COND_NE, dest, dest, load_val); + gen_set_gpr(ctx, a->rd, dest); + tcg_gen_br(l2); + + gen_set_label(l1); + /* + * Address comparison failure. However, we still need to + * provide the memory barrier implied by AQ/RL. + */ + tcg_gen_mb(TCG_MO_ALL + a->aq * TCG_BAR_LDAQ + a->rl * TCG_BAR_STRL); + gen_set_gpr(ctx, a->rd, tcg_constant_tl(1)); + + gen_set_label(l2); + /* + * Clear the load reservation, since an SC must fail if there is + * an SC to any address, in between an LR and SC pair. + */ + tcg_gen_movi_tl(load_res, -1); + + return true; +} + +static bool gen_amo(DisasContext *ctx, arg_atomic *a, + void(*func)(TCGv, TCGv, TCGv, TCGArg, MemOp), + MemOp mop) +{ + TCGv dest = dest_gpr(ctx, a->rd); + TCGv src1 = get_gpr(ctx, a->rs1, EXT_NONE); + TCGv src2 = get_gpr(ctx, a->rs2, EXT_NONE); + + src1 = gen_pm_adjust_address(ctx, src1); + func(dest, src1, src2, ctx->mem_idx, mop); + + gen_set_gpr(ctx, a->rd, dest); + return true; +} + +static bool trans_lr_w(DisasContext *ctx, arg_lr_w *a) +{ + REQUIRE_EXT(ctx, RVA); + return gen_lr(ctx, a, (MO_ALIGN | MO_TESL)); +} + +static bool trans_sc_w(DisasContext *ctx, arg_sc_w *a) +{ + REQUIRE_EXT(ctx, RVA); + return gen_sc(ctx, a, (MO_ALIGN | MO_TESL)); +} + +static bool trans_amoswap_w(DisasContext *ctx, arg_amoswap_w *a) +{ + REQUIRE_EXT(ctx, RVA); + return gen_amo(ctx, a, &tcg_gen_atomic_xchg_tl, (MO_ALIGN | MO_TESL)); +} + +static bool trans_amoadd_w(DisasContext *ctx, arg_amoadd_w *a) +{ + REQUIRE_EXT(ctx, RVA); + return gen_amo(ctx, a, &tcg_gen_atomic_fetch_add_tl, (MO_ALIGN | MO_TESL)); +} + +static bool trans_amoxor_w(DisasContext *ctx, arg_amoxor_w *a) +{ + REQUIRE_EXT(ctx, RVA); + return gen_amo(ctx, a, &tcg_gen_atomic_fetch_xor_tl, (MO_ALIGN | MO_TESL)); +} + +static bool trans_amoand_w(DisasContext *ctx, arg_amoand_w *a) +{ + REQUIRE_EXT(ctx, RVA); + return gen_amo(ctx, a, &tcg_gen_atomic_fetch_and_tl, (MO_ALIGN | MO_TESL)); +} + +static bool trans_amoor_w(DisasContext *ctx, arg_amoor_w *a) +{ + REQUIRE_EXT(ctx, RVA); + return gen_amo(ctx, a, &tcg_gen_atomic_fetch_or_tl, (MO_ALIGN | MO_TESL)); +} + +static bool trans_amomin_w(DisasContext *ctx, arg_amomin_w *a) +{ + REQUIRE_EXT(ctx, RVA); + return gen_amo(ctx, a, &tcg_gen_atomic_fetch_smin_tl, (MO_ALIGN | MO_TESL)); +} + +static bool trans_amomax_w(DisasContext *ctx, arg_amomax_w *a) +{ + REQUIRE_EXT(ctx, RVA); + return gen_amo(ctx, a, &tcg_gen_atomic_fetch_smax_tl, (MO_ALIGN | MO_TESL)); +} + +static bool trans_amominu_w(DisasContext *ctx, arg_amominu_w *a) +{ + REQUIRE_EXT(ctx, RVA); + return gen_amo(ctx, a, &tcg_gen_atomic_fetch_umin_tl, (MO_ALIGN | MO_TESL)); +} + +static bool trans_amomaxu_w(DisasContext *ctx, arg_amomaxu_w *a) +{ + REQUIRE_EXT(ctx, RVA); + return gen_amo(ctx, a, &tcg_gen_atomic_fetch_umax_tl, (MO_ALIGN | MO_TESL)); +} + +static bool trans_lr_d(DisasContext *ctx, arg_lr_d *a) +{ + REQUIRE_64BIT(ctx); + return gen_lr(ctx, a, MO_ALIGN | MO_TEQ); +} + +static bool trans_sc_d(DisasContext *ctx, arg_sc_d *a) +{ + REQUIRE_64BIT(ctx); + return gen_sc(ctx, a, (MO_ALIGN | MO_TEQ)); +} + +static bool trans_amoswap_d(DisasContext *ctx, arg_amoswap_d *a) +{ + REQUIRE_64BIT(ctx); + return gen_amo(ctx, a, &tcg_gen_atomic_xchg_tl, (MO_ALIGN | MO_TEQ)); +} + +static bool trans_amoadd_d(DisasContext *ctx, arg_amoadd_d *a) +{ + REQUIRE_64BIT(ctx); + return gen_amo(ctx, a, &tcg_gen_atomic_fetch_add_tl, (MO_ALIGN | MO_TEQ)); +} + +static bool trans_amoxor_d(DisasContext *ctx, arg_amoxor_d *a) +{ + REQUIRE_64BIT(ctx); + return gen_amo(ctx, a, &tcg_gen_atomic_fetch_xor_tl, (MO_ALIGN | MO_TEQ)); +} + +static bool trans_amoand_d(DisasContext *ctx, arg_amoand_d *a) +{ + REQUIRE_64BIT(ctx); + return gen_amo(ctx, a, &tcg_gen_atomic_fetch_and_tl, (MO_ALIGN | MO_TEQ)); +} + +static bool trans_amoor_d(DisasContext *ctx, arg_amoor_d *a) +{ + REQUIRE_64BIT(ctx); + return gen_amo(ctx, a, &tcg_gen_atomic_fetch_or_tl, (MO_ALIGN | MO_TEQ)); +} + +static bool trans_amomin_d(DisasContext *ctx, arg_amomin_d *a) +{ + REQUIRE_64BIT(ctx); + return gen_amo(ctx, a, &tcg_gen_atomic_fetch_smin_tl, (MO_ALIGN | MO_TEQ)); +} + +static bool trans_amomax_d(DisasContext *ctx, arg_amomax_d *a) +{ + REQUIRE_64BIT(ctx); + return gen_amo(ctx, a, &tcg_gen_atomic_fetch_smax_tl, (MO_ALIGN | MO_TEQ)); +} + +static bool trans_amominu_d(DisasContext *ctx, arg_amominu_d *a) +{ + REQUIRE_64BIT(ctx); + return gen_amo(ctx, a, &tcg_gen_atomic_fetch_umin_tl, (MO_ALIGN | MO_TEQ)); +} + +static bool trans_amomaxu_d(DisasContext *ctx, arg_amomaxu_d *a) +{ + REQUIRE_64BIT(ctx); + return gen_amo(ctx, a, &tcg_gen_atomic_fetch_umax_tl, (MO_ALIGN | MO_TEQ)); +} diff --git a/target/riscv/insn_trans/trans_rvb.c.inc b/target/riscv/insn_trans/trans_rvb.c.inc new file mode 100644 index 000000000..c8d31907c --- /dev/null +++ b/target/riscv/insn_trans/trans_rvb.c.inc @@ -0,0 +1,506 @@ +/* + * RISC-V translation routines for the Zb[abcs] Standard Extension. + * + * Copyright (c) 2020 Kito Cheng, kito.cheng@sifive.com + * Copyright (c) 2020 Frank Chang, frank.chang@sifive.com + * Copyright (c) 2021 Philipp Tomsich, philipp.tomsich@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_ZBA(ctx) do { \ + if (!RISCV_CPU(ctx->cs)->cfg.ext_zba) { \ + return false; \ + } \ +} while (0) + +#define REQUIRE_ZBB(ctx) do { \ + if (!RISCV_CPU(ctx->cs)->cfg.ext_zbb) { \ + return false; \ + } \ +} while (0) + +#define REQUIRE_ZBC(ctx) do { \ + if (!RISCV_CPU(ctx->cs)->cfg.ext_zbc) { \ + return false; \ + } \ +} while (0) + +#define REQUIRE_ZBS(ctx) do { \ + if (!RISCV_CPU(ctx->cs)->cfg.ext_zbs) { \ + return false; \ + } \ +} while (0) + +static void gen_clz(TCGv ret, TCGv arg1) +{ + tcg_gen_clzi_tl(ret, arg1, TARGET_LONG_BITS); +} + +static void gen_clzw(TCGv ret, TCGv arg1) +{ + TCGv t = tcg_temp_new(); + tcg_gen_shli_tl(t, arg1, 32); + tcg_gen_clzi_tl(ret, t, 32); + tcg_temp_free(t); +} + +static bool trans_clz(DisasContext *ctx, arg_clz *a) +{ + REQUIRE_ZBB(ctx); + return gen_unary_per_ol(ctx, a, EXT_NONE, gen_clz, gen_clzw); +} + +static void gen_ctz(TCGv ret, TCGv arg1) +{ + tcg_gen_ctzi_tl(ret, arg1, TARGET_LONG_BITS); +} + +static void gen_ctzw(TCGv ret, TCGv arg1) +{ + tcg_gen_ctzi_tl(ret, arg1, 32); +} + +static bool trans_ctz(DisasContext *ctx, arg_ctz *a) +{ + REQUIRE_ZBB(ctx); + return gen_unary_per_ol(ctx, a, EXT_ZERO, gen_ctz, gen_ctzw); +} + +static bool trans_cpop(DisasContext *ctx, arg_cpop *a) +{ + REQUIRE_ZBB(ctx); + return gen_unary(ctx, a, EXT_ZERO, tcg_gen_ctpop_tl); +} + +static bool trans_andn(DisasContext *ctx, arg_andn *a) +{ + REQUIRE_ZBB(ctx); + return gen_arith(ctx, a, EXT_NONE, tcg_gen_andc_tl); +} + +static bool trans_orn(DisasContext *ctx, arg_orn *a) +{ + REQUIRE_ZBB(ctx); + return gen_arith(ctx, a, EXT_NONE, tcg_gen_orc_tl); +} + +static bool trans_xnor(DisasContext *ctx, arg_xnor *a) +{ + REQUIRE_ZBB(ctx); + return gen_arith(ctx, a, EXT_NONE, tcg_gen_eqv_tl); +} + +static bool trans_min(DisasContext *ctx, arg_min *a) +{ + REQUIRE_ZBB(ctx); + return gen_arith(ctx, a, EXT_SIGN, tcg_gen_smin_tl); +} + +static bool trans_max(DisasContext *ctx, arg_max *a) +{ + REQUIRE_ZBB(ctx); + return gen_arith(ctx, a, EXT_SIGN, tcg_gen_smax_tl); +} + +static bool trans_minu(DisasContext *ctx, arg_minu *a) +{ + REQUIRE_ZBB(ctx); + return gen_arith(ctx, a, EXT_SIGN, tcg_gen_umin_tl); +} + +static bool trans_maxu(DisasContext *ctx, arg_maxu *a) +{ + REQUIRE_ZBB(ctx); + return gen_arith(ctx, a, EXT_SIGN, tcg_gen_umax_tl); +} + +static bool trans_sext_b(DisasContext *ctx, arg_sext_b *a) +{ + REQUIRE_ZBB(ctx); + return gen_unary(ctx, a, EXT_NONE, tcg_gen_ext8s_tl); +} + +static bool trans_sext_h(DisasContext *ctx, arg_sext_h *a) +{ + REQUIRE_ZBB(ctx); + return gen_unary(ctx, a, EXT_NONE, tcg_gen_ext16s_tl); +} + +static void gen_sbop_mask(TCGv ret, TCGv shamt) +{ + tcg_gen_movi_tl(ret, 1); + tcg_gen_shl_tl(ret, ret, shamt); +} + +static void gen_bset(TCGv ret, TCGv arg1, TCGv shamt) +{ + TCGv t = tcg_temp_new(); + + gen_sbop_mask(t, shamt); + tcg_gen_or_tl(ret, arg1, t); + + tcg_temp_free(t); +} + +static bool trans_bset(DisasContext *ctx, arg_bset *a) +{ + REQUIRE_ZBS(ctx); + return gen_shift(ctx, a, EXT_NONE, gen_bset); +} + +static bool trans_bseti(DisasContext *ctx, arg_bseti *a) +{ + REQUIRE_ZBS(ctx); + return gen_shift_imm_tl(ctx, a, EXT_NONE, gen_bset); +} + +static void gen_bclr(TCGv ret, TCGv arg1, TCGv shamt) +{ + TCGv t = tcg_temp_new(); + + gen_sbop_mask(t, shamt); + tcg_gen_andc_tl(ret, arg1, t); + + tcg_temp_free(t); +} + +static bool trans_bclr(DisasContext *ctx, arg_bclr *a) +{ + REQUIRE_ZBS(ctx); + return gen_shift(ctx, a, EXT_NONE, gen_bclr); +} + +static bool trans_bclri(DisasContext *ctx, arg_bclri *a) +{ + REQUIRE_ZBS(ctx); + return gen_shift_imm_tl(ctx, a, EXT_NONE, gen_bclr); +} + +static void gen_binv(TCGv ret, TCGv arg1, TCGv shamt) +{ + TCGv t = tcg_temp_new(); + + gen_sbop_mask(t, shamt); + tcg_gen_xor_tl(ret, arg1, t); + + tcg_temp_free(t); +} + +static bool trans_binv(DisasContext *ctx, arg_binv *a) +{ + REQUIRE_ZBS(ctx); + return gen_shift(ctx, a, EXT_NONE, gen_binv); +} + +static bool trans_binvi(DisasContext *ctx, arg_binvi *a) +{ + REQUIRE_ZBS(ctx); + return gen_shift_imm_tl(ctx, a, EXT_NONE, gen_binv); +} + +static void gen_bext(TCGv ret, TCGv arg1, TCGv shamt) +{ + tcg_gen_shr_tl(ret, arg1, shamt); + tcg_gen_andi_tl(ret, ret, 1); +} + +static bool trans_bext(DisasContext *ctx, arg_bext *a) +{ + REQUIRE_ZBS(ctx); + return gen_shift(ctx, a, EXT_NONE, gen_bext); +} + +static bool trans_bexti(DisasContext *ctx, arg_bexti *a) +{ + REQUIRE_ZBS(ctx); + return gen_shift_imm_tl(ctx, a, EXT_NONE, gen_bext); +} + +static void gen_rorw(TCGv ret, TCGv arg1, TCGv arg2) +{ + TCGv_i32 t1 = tcg_temp_new_i32(); + TCGv_i32 t2 = tcg_temp_new_i32(); + + /* truncate to 32-bits */ + tcg_gen_trunc_tl_i32(t1, arg1); + tcg_gen_trunc_tl_i32(t2, arg2); + + tcg_gen_rotr_i32(t1, t1, t2); + + /* sign-extend 64-bits */ + tcg_gen_ext_i32_tl(ret, t1); + + tcg_temp_free_i32(t1); + tcg_temp_free_i32(t2); +} + +static bool trans_ror(DisasContext *ctx, arg_ror *a) +{ + REQUIRE_ZBB(ctx); + return gen_shift_per_ol(ctx, a, EXT_NONE, tcg_gen_rotr_tl, gen_rorw); +} + +static void gen_roriw(TCGv ret, TCGv arg1, target_long shamt) +{ + TCGv_i32 t1 = tcg_temp_new_i32(); + + tcg_gen_trunc_tl_i32(t1, arg1); + tcg_gen_rotri_i32(t1, t1, shamt); + tcg_gen_ext_i32_tl(ret, t1); + + tcg_temp_free_i32(t1); +} + +static bool trans_rori(DisasContext *ctx, arg_rori *a) +{ + REQUIRE_ZBB(ctx); + return gen_shift_imm_fn_per_ol(ctx, a, EXT_NONE, + tcg_gen_rotri_tl, gen_roriw); +} + +static void gen_rolw(TCGv ret, TCGv arg1, TCGv arg2) +{ + TCGv_i32 t1 = tcg_temp_new_i32(); + TCGv_i32 t2 = tcg_temp_new_i32(); + + /* truncate to 32-bits */ + tcg_gen_trunc_tl_i32(t1, arg1); + tcg_gen_trunc_tl_i32(t2, arg2); + + tcg_gen_rotl_i32(t1, t1, t2); + + /* sign-extend 64-bits */ + tcg_gen_ext_i32_tl(ret, t1); + + tcg_temp_free_i32(t1); + tcg_temp_free_i32(t2); +} + +static bool trans_rol(DisasContext *ctx, arg_rol *a) +{ + REQUIRE_ZBB(ctx); + return gen_shift_per_ol(ctx, a, EXT_NONE, tcg_gen_rotl_tl, gen_rolw); +} + +static void gen_rev8_32(TCGv ret, TCGv src1) +{ + tcg_gen_bswap32_tl(ret, src1, TCG_BSWAP_OS); +} + +static bool trans_rev8_32(DisasContext *ctx, arg_rev8_32 *a) +{ + REQUIRE_32BIT(ctx); + REQUIRE_ZBB(ctx); + return gen_unary(ctx, a, EXT_NONE, gen_rev8_32); +} + +static bool trans_rev8_64(DisasContext *ctx, arg_rev8_64 *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_ZBB(ctx); + return gen_unary(ctx, a, EXT_NONE, tcg_gen_bswap_tl); +} + +static void gen_orc_b(TCGv ret, TCGv source1) +{ + TCGv tmp = tcg_temp_new(); + TCGv low7 = tcg_constant_tl(dup_const_tl(MO_8, 0x7f)); + + /* Set msb in each byte if the byte was non-zero. */ + tcg_gen_and_tl(tmp, source1, low7); + tcg_gen_add_tl(tmp, tmp, low7); + tcg_gen_or_tl(tmp, tmp, source1); + + /* Extract the msb to the lsb in each byte */ + tcg_gen_andc_tl(tmp, tmp, low7); + tcg_gen_shri_tl(tmp, tmp, 7); + + /* Replicate the lsb of each byte across the byte. */ + tcg_gen_muli_tl(ret, tmp, 0xff); + + tcg_temp_free(tmp); +} + +static bool trans_orc_b(DisasContext *ctx, arg_orc_b *a) +{ + REQUIRE_ZBB(ctx); + return gen_unary(ctx, a, EXT_ZERO, gen_orc_b); +} + +#define GEN_SHADD(SHAMT) \ +static void gen_sh##SHAMT##add(TCGv ret, TCGv arg1, TCGv arg2) \ +{ \ + TCGv t = tcg_temp_new(); \ + \ + tcg_gen_shli_tl(t, arg1, SHAMT); \ + tcg_gen_add_tl(ret, t, arg2); \ + \ + tcg_temp_free(t); \ +} + +GEN_SHADD(1) +GEN_SHADD(2) +GEN_SHADD(3) + +#define GEN_TRANS_SHADD(SHAMT) \ +static bool trans_sh##SHAMT##add(DisasContext *ctx, arg_sh##SHAMT##add *a) \ +{ \ + REQUIRE_ZBA(ctx); \ + return gen_arith(ctx, a, EXT_NONE, gen_sh##SHAMT##add); \ +} + +GEN_TRANS_SHADD(1) +GEN_TRANS_SHADD(2) +GEN_TRANS_SHADD(3) + +static bool trans_zext_h_32(DisasContext *ctx, arg_zext_h_32 *a) +{ + REQUIRE_32BIT(ctx); + REQUIRE_ZBB(ctx); + return gen_unary(ctx, a, EXT_NONE, tcg_gen_ext16u_tl); +} + +static bool trans_zext_h_64(DisasContext *ctx, arg_zext_h_64 *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_ZBB(ctx); + return gen_unary(ctx, a, EXT_NONE, tcg_gen_ext16u_tl); +} + +static bool trans_clzw(DisasContext *ctx, arg_clzw *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_ZBB(ctx); + return gen_unary(ctx, a, EXT_NONE, gen_clzw); +} + +static bool trans_ctzw(DisasContext *ctx, arg_ctzw *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_ZBB(ctx); + return gen_unary(ctx, a, EXT_ZERO, gen_ctzw); +} + +static bool trans_cpopw(DisasContext *ctx, arg_cpopw *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_ZBB(ctx); + ctx->ol = MXL_RV32; + return gen_unary(ctx, a, EXT_ZERO, tcg_gen_ctpop_tl); +} + +static bool trans_rorw(DisasContext *ctx, arg_rorw *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_ZBB(ctx); + ctx->ol = MXL_RV32; + return gen_shift(ctx, a, EXT_NONE, gen_rorw); +} + +static bool trans_roriw(DisasContext *ctx, arg_roriw *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_ZBB(ctx); + ctx->ol = MXL_RV32; + return gen_shift_imm_fn(ctx, a, EXT_NONE, gen_roriw); +} + +static bool trans_rolw(DisasContext *ctx, arg_rolw *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_ZBB(ctx); + ctx->ol = MXL_RV32; + return gen_shift(ctx, a, EXT_NONE, gen_rolw); +} + +#define GEN_SHADD_UW(SHAMT) \ +static void gen_sh##SHAMT##add_uw(TCGv ret, TCGv arg1, TCGv arg2) \ +{ \ + TCGv t = tcg_temp_new(); \ + \ + tcg_gen_ext32u_tl(t, arg1); \ + \ + tcg_gen_shli_tl(t, t, SHAMT); \ + tcg_gen_add_tl(ret, t, arg2); \ + \ + tcg_temp_free(t); \ +} + +GEN_SHADD_UW(1) +GEN_SHADD_UW(2) +GEN_SHADD_UW(3) + +#define GEN_TRANS_SHADD_UW(SHAMT) \ +static bool trans_sh##SHAMT##add_uw(DisasContext *ctx, \ + arg_sh##SHAMT##add_uw *a) \ +{ \ + REQUIRE_64BIT(ctx); \ + REQUIRE_ZBA(ctx); \ + return gen_arith(ctx, a, EXT_NONE, gen_sh##SHAMT##add_uw); \ +} + +GEN_TRANS_SHADD_UW(1) +GEN_TRANS_SHADD_UW(2) +GEN_TRANS_SHADD_UW(3) + +static void gen_add_uw(TCGv ret, TCGv arg1, TCGv arg2) +{ + TCGv t = tcg_temp_new(); + tcg_gen_ext32u_tl(t, arg1); + tcg_gen_add_tl(ret, t, arg2); + tcg_temp_free(t); +} + +static bool trans_add_uw(DisasContext *ctx, arg_add_uw *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_ZBA(ctx); + return gen_arith(ctx, a, EXT_NONE, gen_add_uw); +} + +static void gen_slli_uw(TCGv dest, TCGv src, target_long shamt) +{ + tcg_gen_deposit_z_tl(dest, src, shamt, MIN(32, TARGET_LONG_BITS - shamt)); +} + +static bool trans_slli_uw(DisasContext *ctx, arg_slli_uw *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_ZBA(ctx); + return gen_shift_imm_fn(ctx, a, EXT_NONE, gen_slli_uw); +} + +static bool trans_clmul(DisasContext *ctx, arg_clmul *a) +{ + REQUIRE_ZBC(ctx); + return gen_arith(ctx, a, EXT_NONE, gen_helper_clmul); +} + +static void gen_clmulh(TCGv dst, TCGv src1, TCGv src2) +{ + gen_helper_clmulr(dst, src1, src2); + tcg_gen_shri_tl(dst, dst, 1); +} + +static bool trans_clmulh(DisasContext *ctx, arg_clmulr *a) +{ + REQUIRE_ZBC(ctx); + return gen_arith(ctx, a, EXT_NONE, gen_clmulh); +} + +static bool trans_clmulr(DisasContext *ctx, arg_clmulh *a) +{ + REQUIRE_ZBC(ctx); + return gen_arith(ctx, a, EXT_NONE, gen_helper_clmulr); +} diff --git a/target/riscv/insn_trans/trans_rvd.c.inc b/target/riscv/insn_trans/trans_rvd.c.inc new file mode 100644 index 000000000..64fb0046f --- /dev/null +++ b/target/riscv/insn_trans/trans_rvd.c.inc @@ -0,0 +1,449 @@ +/* + * RISC-V translation routines for the RV64D Standard Extension. + * + * Copyright (c) 2016-2017 Sagar Karandikar, sagark@eecs.berkeley.edu + * Copyright (c) 2018 Peer Adelt, peer.adelt@hni.uni-paderborn.de + * Bastian Koppelmann, kbastian@mail.uni-paderborn.de + * + * 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/>. + */ + +static bool trans_fld(DisasContext *ctx, arg_fld *a) +{ + TCGv addr; + + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + + addr = get_gpr(ctx, a->rs1, EXT_NONE); + if (a->imm) { + TCGv temp = temp_new(ctx); + tcg_gen_addi_tl(temp, addr, a->imm); + addr = temp; + } + addr = gen_pm_adjust_address(ctx, addr); + + tcg_gen_qemu_ld_i64(cpu_fpr[a->rd], addr, ctx->mem_idx, MO_TEQ); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fsd(DisasContext *ctx, arg_fsd *a) +{ + TCGv addr; + + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + + addr = get_gpr(ctx, a->rs1, EXT_NONE); + if (a->imm) { + TCGv temp = temp_new(ctx); + tcg_gen_addi_tl(temp, addr, a->imm); + addr = temp; + } + addr = gen_pm_adjust_address(ctx, addr); + + tcg_gen_qemu_st_i64(cpu_fpr[a->rs2], addr, ctx->mem_idx, MO_TEQ); + + return true; +} + +static bool trans_fmadd_d(DisasContext *ctx, arg_fmadd_d *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + gen_set_rm(ctx, a->rm); + gen_helper_fmadd_d(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1], + cpu_fpr[a->rs2], cpu_fpr[a->rs3]); + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fmsub_d(DisasContext *ctx, arg_fmsub_d *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + gen_set_rm(ctx, a->rm); + gen_helper_fmsub_d(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1], + cpu_fpr[a->rs2], cpu_fpr[a->rs3]); + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fnmsub_d(DisasContext *ctx, arg_fnmsub_d *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + gen_set_rm(ctx, a->rm); + gen_helper_fnmsub_d(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1], + cpu_fpr[a->rs2], cpu_fpr[a->rs3]); + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fnmadd_d(DisasContext *ctx, arg_fnmadd_d *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + gen_set_rm(ctx, a->rm); + gen_helper_fnmadd_d(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1], + cpu_fpr[a->rs2], cpu_fpr[a->rs3]); + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fadd_d(DisasContext *ctx, arg_fadd_d *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + + gen_set_rm(ctx, a->rm); + gen_helper_fadd_d(cpu_fpr[a->rd], cpu_env, + cpu_fpr[a->rs1], cpu_fpr[a->rs2]); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fsub_d(DisasContext *ctx, arg_fsub_d *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + + gen_set_rm(ctx, a->rm); + gen_helper_fsub_d(cpu_fpr[a->rd], cpu_env, + cpu_fpr[a->rs1], cpu_fpr[a->rs2]); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fmul_d(DisasContext *ctx, arg_fmul_d *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + + gen_set_rm(ctx, a->rm); + gen_helper_fmul_d(cpu_fpr[a->rd], cpu_env, + cpu_fpr[a->rs1], cpu_fpr[a->rs2]); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fdiv_d(DisasContext *ctx, arg_fdiv_d *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + + gen_set_rm(ctx, a->rm); + gen_helper_fdiv_d(cpu_fpr[a->rd], cpu_env, + cpu_fpr[a->rs1], cpu_fpr[a->rs2]); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fsqrt_d(DisasContext *ctx, arg_fsqrt_d *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + + gen_set_rm(ctx, a->rm); + gen_helper_fsqrt_d(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1]); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fsgnj_d(DisasContext *ctx, arg_fsgnj_d *a) +{ + if (a->rs1 == a->rs2) { /* FMOV */ + tcg_gen_mov_i64(cpu_fpr[a->rd], cpu_fpr[a->rs1]); + } else { + tcg_gen_deposit_i64(cpu_fpr[a->rd], cpu_fpr[a->rs2], + cpu_fpr[a->rs1], 0, 63); + } + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fsgnjn_d(DisasContext *ctx, arg_fsgnjn_d *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + if (a->rs1 == a->rs2) { /* FNEG */ + tcg_gen_xori_i64(cpu_fpr[a->rd], cpu_fpr[a->rs1], INT64_MIN); + } else { + TCGv_i64 t0 = tcg_temp_new_i64(); + tcg_gen_not_i64(t0, cpu_fpr[a->rs2]); + tcg_gen_deposit_i64(cpu_fpr[a->rd], t0, cpu_fpr[a->rs1], 0, 63); + tcg_temp_free_i64(t0); + } + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fsgnjx_d(DisasContext *ctx, arg_fsgnjx_d *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + if (a->rs1 == a->rs2) { /* FABS */ + tcg_gen_andi_i64(cpu_fpr[a->rd], cpu_fpr[a->rs1], ~INT64_MIN); + } else { + TCGv_i64 t0 = tcg_temp_new_i64(); + tcg_gen_andi_i64(t0, cpu_fpr[a->rs2], INT64_MIN); + tcg_gen_xor_i64(cpu_fpr[a->rd], cpu_fpr[a->rs1], t0); + tcg_temp_free_i64(t0); + } + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fmin_d(DisasContext *ctx, arg_fmin_d *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + + gen_helper_fmin_d(cpu_fpr[a->rd], cpu_env, + cpu_fpr[a->rs1], cpu_fpr[a->rs2]); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fmax_d(DisasContext *ctx, arg_fmax_d *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + + gen_helper_fmax_d(cpu_fpr[a->rd], cpu_env, + cpu_fpr[a->rs1], cpu_fpr[a->rs2]); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fcvt_s_d(DisasContext *ctx, arg_fcvt_s_d *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + + gen_set_rm(ctx, a->rm); + gen_helper_fcvt_s_d(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1]); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fcvt_d_s(DisasContext *ctx, arg_fcvt_d_s *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + + gen_set_rm(ctx, a->rm); + gen_helper_fcvt_d_s(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1]); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_feq_d(DisasContext *ctx, arg_feq_d *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + + TCGv dest = dest_gpr(ctx, a->rd); + + gen_helper_feq_d(dest, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]); + gen_set_gpr(ctx, a->rd, dest); + return true; +} + +static bool trans_flt_d(DisasContext *ctx, arg_flt_d *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + + TCGv dest = dest_gpr(ctx, a->rd); + + gen_helper_flt_d(dest, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]); + gen_set_gpr(ctx, a->rd, dest); + return true; +} + +static bool trans_fle_d(DisasContext *ctx, arg_fle_d *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + + TCGv dest = dest_gpr(ctx, a->rd); + + gen_helper_fle_d(dest, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]); + gen_set_gpr(ctx, a->rd, dest); + return true; +} + +static bool trans_fclass_d(DisasContext *ctx, arg_fclass_d *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + + TCGv dest = dest_gpr(ctx, a->rd); + + gen_helper_fclass_d(dest, cpu_fpr[a->rs1]); + gen_set_gpr(ctx, a->rd, dest); + return true; +} + +static bool trans_fcvt_w_d(DisasContext *ctx, arg_fcvt_w_d *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + + TCGv dest = dest_gpr(ctx, a->rd); + + gen_set_rm(ctx, a->rm); + gen_helper_fcvt_w_d(dest, cpu_env, cpu_fpr[a->rs1]); + gen_set_gpr(ctx, a->rd, dest); + return true; +} + +static bool trans_fcvt_wu_d(DisasContext *ctx, arg_fcvt_wu_d *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + + TCGv dest = dest_gpr(ctx, a->rd); + + gen_set_rm(ctx, a->rm); + gen_helper_fcvt_wu_d(dest, cpu_env, cpu_fpr[a->rs1]); + gen_set_gpr(ctx, a->rd, dest); + return true; +} + +static bool trans_fcvt_d_w(DisasContext *ctx, arg_fcvt_d_w *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + + TCGv src = get_gpr(ctx, a->rs1, EXT_SIGN); + + gen_set_rm(ctx, a->rm); + gen_helper_fcvt_d_w(cpu_fpr[a->rd], cpu_env, src); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fcvt_d_wu(DisasContext *ctx, arg_fcvt_d_wu *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + + TCGv src = get_gpr(ctx, a->rs1, EXT_ZERO); + + gen_set_rm(ctx, a->rm); + gen_helper_fcvt_d_wu(cpu_fpr[a->rd], cpu_env, src); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fcvt_l_d(DisasContext *ctx, arg_fcvt_l_d *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + + TCGv dest = dest_gpr(ctx, a->rd); + + gen_set_rm(ctx, a->rm); + gen_helper_fcvt_l_d(dest, cpu_env, cpu_fpr[a->rs1]); + gen_set_gpr(ctx, a->rd, dest); + return true; +} + +static bool trans_fcvt_lu_d(DisasContext *ctx, arg_fcvt_lu_d *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + + TCGv dest = dest_gpr(ctx, a->rd); + + gen_set_rm(ctx, a->rm); + gen_helper_fcvt_lu_d(dest, cpu_env, cpu_fpr[a->rs1]); + gen_set_gpr(ctx, a->rd, dest); + return true; +} + +static bool trans_fmv_x_d(DisasContext *ctx, arg_fmv_x_d *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + +#ifdef TARGET_RISCV64 + gen_set_gpr(ctx, a->rd, cpu_fpr[a->rs1]); + return true; +#else + qemu_build_not_reached(); +#endif +} + +static bool trans_fcvt_d_l(DisasContext *ctx, arg_fcvt_d_l *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + + TCGv src = get_gpr(ctx, a->rs1, EXT_SIGN); + + gen_set_rm(ctx, a->rm); + gen_helper_fcvt_d_l(cpu_fpr[a->rd], cpu_env, src); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fcvt_d_lu(DisasContext *ctx, arg_fcvt_d_lu *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + + TCGv src = get_gpr(ctx, a->rs1, EXT_ZERO); + + gen_set_rm(ctx, a->rm); + gen_helper_fcvt_d_lu(cpu_fpr[a->rd], cpu_env, src); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fmv_d_x(DisasContext *ctx, arg_fmv_d_x *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVD); + +#ifdef TARGET_RISCV64 + tcg_gen_mov_tl(cpu_fpr[a->rd], get_gpr(ctx, a->rs1, EXT_NONE)); + mark_fs_dirty(ctx); + return true; +#else + qemu_build_not_reached(); +#endif +} diff --git a/target/riscv/insn_trans/trans_rvf.c.inc b/target/riscv/insn_trans/trans_rvf.c.inc new file mode 100644 index 000000000..b5459249c --- /dev/null +++ b/target/riscv/insn_trans/trans_rvf.c.inc @@ -0,0 +1,473 @@ +/* + * RISC-V translation routines for the RV64F Standard Extension. + * + * Copyright (c) 2016-2017 Sagar Karandikar, sagark@eecs.berkeley.edu + * Copyright (c) 2018 Peer Adelt, peer.adelt@hni.uni-paderborn.de + * Bastian Koppelmann, kbastian@mail.uni-paderborn.de + * + * 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_FPU do {\ + if (ctx->mstatus_fs == 0) \ + return false; \ +} while (0) + +static bool trans_flw(DisasContext *ctx, arg_flw *a) +{ + TCGv_i64 dest; + TCGv addr; + + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + + addr = get_gpr(ctx, a->rs1, EXT_NONE); + if (a->imm) { + TCGv temp = temp_new(ctx); + tcg_gen_addi_tl(temp, addr, a->imm); + addr = temp; + } + addr = gen_pm_adjust_address(ctx, addr); + + dest = cpu_fpr[a->rd]; + tcg_gen_qemu_ld_i64(dest, addr, ctx->mem_idx, MO_TEUL); + gen_nanbox_s(dest, dest); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fsw(DisasContext *ctx, arg_fsw *a) +{ + TCGv addr; + + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + + addr = get_gpr(ctx, a->rs1, EXT_NONE); + if (a->imm) { + TCGv temp = tcg_temp_new(); + tcg_gen_addi_tl(temp, addr, a->imm); + addr = temp; + } + addr = gen_pm_adjust_address(ctx, addr); + + tcg_gen_qemu_st_i64(cpu_fpr[a->rs2], addr, ctx->mem_idx, MO_TEUL); + + return true; +} + +static bool trans_fmadd_s(DisasContext *ctx, arg_fmadd_s *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + gen_set_rm(ctx, a->rm); + gen_helper_fmadd_s(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1], + cpu_fpr[a->rs2], cpu_fpr[a->rs3]); + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fmsub_s(DisasContext *ctx, arg_fmsub_s *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + gen_set_rm(ctx, a->rm); + gen_helper_fmsub_s(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1], + cpu_fpr[a->rs2], cpu_fpr[a->rs3]); + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fnmsub_s(DisasContext *ctx, arg_fnmsub_s *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + gen_set_rm(ctx, a->rm); + gen_helper_fnmsub_s(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1], + cpu_fpr[a->rs2], cpu_fpr[a->rs3]); + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fnmadd_s(DisasContext *ctx, arg_fnmadd_s *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + gen_set_rm(ctx, a->rm); + gen_helper_fnmadd_s(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1], + cpu_fpr[a->rs2], cpu_fpr[a->rs3]); + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fadd_s(DisasContext *ctx, arg_fadd_s *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + + gen_set_rm(ctx, a->rm); + gen_helper_fadd_s(cpu_fpr[a->rd], cpu_env, + cpu_fpr[a->rs1], cpu_fpr[a->rs2]); + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fsub_s(DisasContext *ctx, arg_fsub_s *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + + gen_set_rm(ctx, a->rm); + gen_helper_fsub_s(cpu_fpr[a->rd], cpu_env, + cpu_fpr[a->rs1], cpu_fpr[a->rs2]); + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fmul_s(DisasContext *ctx, arg_fmul_s *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + + gen_set_rm(ctx, a->rm); + gen_helper_fmul_s(cpu_fpr[a->rd], cpu_env, + cpu_fpr[a->rs1], cpu_fpr[a->rs2]); + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fdiv_s(DisasContext *ctx, arg_fdiv_s *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + + gen_set_rm(ctx, a->rm); + gen_helper_fdiv_s(cpu_fpr[a->rd], cpu_env, + cpu_fpr[a->rs1], cpu_fpr[a->rs2]); + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fsqrt_s(DisasContext *ctx, arg_fsqrt_s *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + + gen_set_rm(ctx, a->rm); + gen_helper_fsqrt_s(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1]); + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fsgnj_s(DisasContext *ctx, arg_fsgnj_s *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + + if (a->rs1 == a->rs2) { /* FMOV */ + gen_check_nanbox_s(cpu_fpr[a->rd], cpu_fpr[a->rs1]); + } else { /* FSGNJ */ + TCGv_i64 rs1 = tcg_temp_new_i64(); + TCGv_i64 rs2 = tcg_temp_new_i64(); + + gen_check_nanbox_s(rs1, cpu_fpr[a->rs1]); + gen_check_nanbox_s(rs2, cpu_fpr[a->rs2]); + + /* This formulation retains the nanboxing of rs2. */ + tcg_gen_deposit_i64(cpu_fpr[a->rd], rs2, rs1, 0, 31); + tcg_temp_free_i64(rs1); + tcg_temp_free_i64(rs2); + } + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fsgnjn_s(DisasContext *ctx, arg_fsgnjn_s *a) +{ + TCGv_i64 rs1, rs2, mask; + + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + + rs1 = tcg_temp_new_i64(); + gen_check_nanbox_s(rs1, cpu_fpr[a->rs1]); + + if (a->rs1 == a->rs2) { /* FNEG */ + tcg_gen_xori_i64(cpu_fpr[a->rd], rs1, MAKE_64BIT_MASK(31, 1)); + } else { + rs2 = tcg_temp_new_i64(); + gen_check_nanbox_s(rs2, cpu_fpr[a->rs2]); + + /* + * Replace bit 31 in rs1 with inverse in rs2. + * This formulation retains the nanboxing of rs1. + */ + mask = tcg_constant_i64(~MAKE_64BIT_MASK(31, 1)); + tcg_gen_nor_i64(rs2, rs2, mask); + tcg_gen_and_i64(rs1, mask, rs1); + tcg_gen_or_i64(cpu_fpr[a->rd], rs1, rs2); + + tcg_temp_free_i64(rs2); + } + tcg_temp_free_i64(rs1); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fsgnjx_s(DisasContext *ctx, arg_fsgnjx_s *a) +{ + TCGv_i64 rs1, rs2; + + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + + rs1 = tcg_temp_new_i64(); + gen_check_nanbox_s(rs1, cpu_fpr[a->rs1]); + + if (a->rs1 == a->rs2) { /* FABS */ + tcg_gen_andi_i64(cpu_fpr[a->rd], rs1, ~MAKE_64BIT_MASK(31, 1)); + } else { + rs2 = tcg_temp_new_i64(); + gen_check_nanbox_s(rs2, cpu_fpr[a->rs2]); + + /* + * Xor bit 31 in rs1 with that in rs2. + * This formulation retains the nanboxing of rs1. + */ + tcg_gen_andi_i64(rs2, rs2, MAKE_64BIT_MASK(31, 1)); + tcg_gen_xor_i64(cpu_fpr[a->rd], rs1, rs2); + + tcg_temp_free_i64(rs2); + } + tcg_temp_free_i64(rs1); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fmin_s(DisasContext *ctx, arg_fmin_s *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + + gen_helper_fmin_s(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1], + cpu_fpr[a->rs2]); + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fmax_s(DisasContext *ctx, arg_fmax_s *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + + gen_helper_fmax_s(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1], + cpu_fpr[a->rs2]); + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fcvt_w_s(DisasContext *ctx, arg_fcvt_w_s *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + + TCGv dest = dest_gpr(ctx, a->rd); + + gen_set_rm(ctx, a->rm); + gen_helper_fcvt_w_s(dest, cpu_env, cpu_fpr[a->rs1]); + gen_set_gpr(ctx, a->rd, dest); + return true; +} + +static bool trans_fcvt_wu_s(DisasContext *ctx, arg_fcvt_wu_s *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + + TCGv dest = dest_gpr(ctx, a->rd); + + gen_set_rm(ctx, a->rm); + gen_helper_fcvt_wu_s(dest, cpu_env, cpu_fpr[a->rs1]); + gen_set_gpr(ctx, a->rd, dest); + return true; +} + +static bool trans_fmv_x_w(DisasContext *ctx, arg_fmv_x_w *a) +{ + /* NOTE: This was FMV.X.S in an earlier version of the ISA spec! */ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + + TCGv dest = dest_gpr(ctx, a->rd); + +#if defined(TARGET_RISCV64) + tcg_gen_ext32s_tl(dest, cpu_fpr[a->rs1]); +#else + tcg_gen_extrl_i64_i32(dest, cpu_fpr[a->rs1]); +#endif + + gen_set_gpr(ctx, a->rd, dest); + return true; +} + +static bool trans_feq_s(DisasContext *ctx, arg_feq_s *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + + TCGv dest = dest_gpr(ctx, a->rd); + + gen_helper_feq_s(dest, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]); + gen_set_gpr(ctx, a->rd, dest); + return true; +} + +static bool trans_flt_s(DisasContext *ctx, arg_flt_s *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + + TCGv dest = dest_gpr(ctx, a->rd); + + gen_helper_flt_s(dest, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]); + gen_set_gpr(ctx, a->rd, dest); + return true; +} + +static bool trans_fle_s(DisasContext *ctx, arg_fle_s *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + + TCGv dest = dest_gpr(ctx, a->rd); + + gen_helper_fle_s(dest, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]); + gen_set_gpr(ctx, a->rd, dest); + return true; +} + +static bool trans_fclass_s(DisasContext *ctx, arg_fclass_s *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + + TCGv dest = dest_gpr(ctx, a->rd); + + gen_helper_fclass_s(dest, cpu_fpr[a->rs1]); + gen_set_gpr(ctx, a->rd, dest); + return true; +} + +static bool trans_fcvt_s_w(DisasContext *ctx, arg_fcvt_s_w *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + + TCGv src = get_gpr(ctx, a->rs1, EXT_SIGN); + + gen_set_rm(ctx, a->rm); + gen_helper_fcvt_s_w(cpu_fpr[a->rd], cpu_env, src); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fcvt_s_wu(DisasContext *ctx, arg_fcvt_s_wu *a) +{ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + + TCGv src = get_gpr(ctx, a->rs1, EXT_ZERO); + + gen_set_rm(ctx, a->rm); + gen_helper_fcvt_s_wu(cpu_fpr[a->rd], cpu_env, src); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fmv_w_x(DisasContext *ctx, arg_fmv_w_x *a) +{ + /* NOTE: This was FMV.S.X in an earlier version of the ISA spec! */ + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + + TCGv src = get_gpr(ctx, a->rs1, EXT_ZERO); + + tcg_gen_extu_tl_i64(cpu_fpr[a->rd], src); + gen_nanbox_s(cpu_fpr[a->rd], cpu_fpr[a->rd]); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fcvt_l_s(DisasContext *ctx, arg_fcvt_l_s *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + + TCGv dest = dest_gpr(ctx, a->rd); + + gen_set_rm(ctx, a->rm); + gen_helper_fcvt_l_s(dest, cpu_env, cpu_fpr[a->rs1]); + gen_set_gpr(ctx, a->rd, dest); + return true; +} + +static bool trans_fcvt_lu_s(DisasContext *ctx, arg_fcvt_lu_s *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + + TCGv dest = dest_gpr(ctx, a->rd); + + gen_set_rm(ctx, a->rm); + gen_helper_fcvt_lu_s(dest, cpu_env, cpu_fpr[a->rs1]); + gen_set_gpr(ctx, a->rd, dest); + return true; +} + +static bool trans_fcvt_s_l(DisasContext *ctx, arg_fcvt_s_l *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + + TCGv src = get_gpr(ctx, a->rs1, EXT_SIGN); + + gen_set_rm(ctx, a->rm); + gen_helper_fcvt_s_l(cpu_fpr[a->rd], cpu_env, src); + + mark_fs_dirty(ctx); + return true; +} + +static bool trans_fcvt_s_lu(DisasContext *ctx, arg_fcvt_s_lu *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); + + TCGv src = get_gpr(ctx, a->rs1, EXT_ZERO); + + gen_set_rm(ctx, a->rm); + gen_helper_fcvt_s_lu(cpu_fpr[a->rd], cpu_env, src); + + mark_fs_dirty(ctx); + return true; +} diff --git a/target/riscv/insn_trans/trans_rvh.c.inc b/target/riscv/insn_trans/trans_rvh.c.inc new file mode 100644 index 000000000..ecbf77ff9 --- /dev/null +++ b/target/riscv/insn_trans/trans_rvh.c.inc @@ -0,0 +1,186 @@ +/* + * RISC-V translation routines for the RVXI Base Integer Instruction Set. + * + * Copyright (c) 2020 Western Digital + * + * 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 CONFIG_USER_ONLY +static bool check_access(DisasContext *ctx) +{ + if (!ctx->hlsx) { + if (ctx->virt_enabled) { + generate_exception(ctx, RISCV_EXCP_VIRT_INSTRUCTION_FAULT); + } else { + generate_exception(ctx, RISCV_EXCP_ILLEGAL_INST); + } + return false; + } + return true; +} +#endif + +static bool do_hlv(DisasContext *ctx, arg_r2 *a, MemOp mop) +{ +#ifdef CONFIG_USER_ONLY + return false; +#else + if (check_access(ctx)) { + TCGv dest = dest_gpr(ctx, a->rd); + TCGv addr = get_gpr(ctx, a->rs1, EXT_NONE); + int mem_idx = ctx->mem_idx | TB_FLAGS_PRIV_HYP_ACCESS_MASK; + tcg_gen_qemu_ld_tl(dest, addr, mem_idx, mop); + gen_set_gpr(ctx, a->rd, dest); + } + return true; +#endif +} + +static bool trans_hlv_b(DisasContext *ctx, arg_hlv_b *a) +{ + REQUIRE_EXT(ctx, RVH); + return do_hlv(ctx, a, MO_SB); +} + +static bool trans_hlv_h(DisasContext *ctx, arg_hlv_h *a) +{ + REQUIRE_EXT(ctx, RVH); + return do_hlv(ctx, a, MO_TESW); +} + +static bool trans_hlv_w(DisasContext *ctx, arg_hlv_w *a) +{ + REQUIRE_EXT(ctx, RVH); + return do_hlv(ctx, a, MO_TESL); +} + +static bool trans_hlv_bu(DisasContext *ctx, arg_hlv_bu *a) +{ + REQUIRE_EXT(ctx, RVH); + return do_hlv(ctx, a, MO_UB); +} + +static bool trans_hlv_hu(DisasContext *ctx, arg_hlv_hu *a) +{ + REQUIRE_EXT(ctx, RVH); + return do_hlv(ctx, a, MO_TEUW); +} + +static bool do_hsv(DisasContext *ctx, arg_r2_s *a, MemOp mop) +{ +#ifdef CONFIG_USER_ONLY + return false; +#else + if (check_access(ctx)) { + TCGv addr = get_gpr(ctx, a->rs1, EXT_NONE); + TCGv data = get_gpr(ctx, a->rs2, EXT_NONE); + int mem_idx = ctx->mem_idx | TB_FLAGS_PRIV_HYP_ACCESS_MASK; + tcg_gen_qemu_st_tl(data, addr, mem_idx, mop); + } + return true; +#endif +} + +static bool trans_hsv_b(DisasContext *ctx, arg_hsv_b *a) +{ + REQUIRE_EXT(ctx, RVH); + return do_hsv(ctx, a, MO_SB); +} + +static bool trans_hsv_h(DisasContext *ctx, arg_hsv_h *a) +{ + REQUIRE_EXT(ctx, RVH); + return do_hsv(ctx, a, MO_TESW); +} + +static bool trans_hsv_w(DisasContext *ctx, arg_hsv_w *a) +{ + REQUIRE_EXT(ctx, RVH); + return do_hsv(ctx, a, MO_TESL); +} + +static bool trans_hlv_wu(DisasContext *ctx, arg_hlv_wu *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_EXT(ctx, RVH); + return do_hlv(ctx, a, MO_TEUL); +} + +static bool trans_hlv_d(DisasContext *ctx, arg_hlv_d *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_EXT(ctx, RVH); + return do_hlv(ctx, a, MO_TEQ); +} + +static bool trans_hsv_d(DisasContext *ctx, arg_hsv_d *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_EXT(ctx, RVH); + return do_hsv(ctx, a, MO_TEQ); +} + +#ifndef CONFIG_USER_ONLY +static bool do_hlvx(DisasContext *ctx, arg_r2 *a, + void (*func)(TCGv, TCGv_env, TCGv)) +{ + if (check_access(ctx)) { + TCGv dest = dest_gpr(ctx, a->rd); + TCGv addr = get_gpr(ctx, a->rs1, EXT_NONE); + func(dest, cpu_env, addr); + gen_set_gpr(ctx, a->rd, dest); + } + return true; +} +#endif + +static bool trans_hlvx_hu(DisasContext *ctx, arg_hlvx_hu *a) +{ + REQUIRE_EXT(ctx, RVH); +#ifndef CONFIG_USER_ONLY + return do_hlvx(ctx, a, gen_helper_hyp_hlvx_hu); +#else + return false; +#endif +} + +static bool trans_hlvx_wu(DisasContext *ctx, arg_hlvx_wu *a) +{ + REQUIRE_EXT(ctx, RVH); +#ifndef CONFIG_USER_ONLY + return do_hlvx(ctx, a, gen_helper_hyp_hlvx_wu); +#else + return false; +#endif +} + +static bool trans_hfence_gvma(DisasContext *ctx, arg_sfence_vma *a) +{ + REQUIRE_EXT(ctx, RVH); +#ifndef CONFIG_USER_ONLY + gen_helper_hyp_gvma_tlb_flush(cpu_env); + return true; +#endif + return false; +} + +static bool trans_hfence_vvma(DisasContext *ctx, arg_sfence_vma *a) +{ + REQUIRE_EXT(ctx, RVH); +#ifndef CONFIG_USER_ONLY + gen_helper_hyp_tlb_flush(cpu_env); + return true; +#endif + return false; +} diff --git a/target/riscv/insn_trans/trans_rvi.c.inc b/target/riscv/insn_trans/trans_rvi.c.inc new file mode 100644 index 000000000..e51dbc41c --- /dev/null +++ b/target/riscv/insn_trans/trans_rvi.c.inc @@ -0,0 +1,577 @@ +/* + * RISC-V translation routines for the RVXI Base Integer Instruction Set. + * + * Copyright (c) 2016-2017 Sagar Karandikar, sagark@eecs.berkeley.edu + * Copyright (c) 2018 Peer Adelt, peer.adelt@hni.uni-paderborn.de + * Bastian Koppelmann, kbastian@mail.uni-paderborn.de + * + * 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/>. + */ + +static bool trans_illegal(DisasContext *ctx, arg_empty *a) +{ + gen_exception_illegal(ctx); + return true; +} + +static bool trans_c64_illegal(DisasContext *ctx, arg_empty *a) +{ + REQUIRE_64BIT(ctx); + return trans_illegal(ctx, a); +} + +static bool trans_lui(DisasContext *ctx, arg_lui *a) +{ + if (a->rd != 0) { + tcg_gen_movi_tl(cpu_gpr[a->rd], a->imm); + } + return true; +} + +static bool trans_auipc(DisasContext *ctx, arg_auipc *a) +{ + if (a->rd != 0) { + tcg_gen_movi_tl(cpu_gpr[a->rd], a->imm + ctx->base.pc_next); + } + return true; +} + +static bool trans_jal(DisasContext *ctx, arg_jal *a) +{ + gen_jal(ctx, a->rd, a->imm); + return true; +} + +static bool trans_jalr(DisasContext *ctx, arg_jalr *a) +{ + TCGLabel *misaligned = NULL; + + tcg_gen_addi_tl(cpu_pc, get_gpr(ctx, a->rs1, EXT_NONE), a->imm); + tcg_gen_andi_tl(cpu_pc, cpu_pc, (target_ulong)-2); + + if (!has_ext(ctx, RVC)) { + TCGv t0 = tcg_temp_new(); + + misaligned = gen_new_label(); + tcg_gen_andi_tl(t0, cpu_pc, 0x2); + tcg_gen_brcondi_tl(TCG_COND_NE, t0, 0x0, misaligned); + tcg_temp_free(t0); + } + + if (a->rd != 0) { + tcg_gen_movi_tl(cpu_gpr[a->rd], ctx->pc_succ_insn); + } + tcg_gen_lookup_and_goto_ptr(); + + if (misaligned) { + gen_set_label(misaligned); + gen_exception_inst_addr_mis(ctx); + } + ctx->base.is_jmp = DISAS_NORETURN; + + return true; +} + +static bool gen_branch(DisasContext *ctx, arg_b *a, TCGCond cond) +{ + TCGLabel *l = gen_new_label(); + TCGv src1 = get_gpr(ctx, a->rs1, EXT_SIGN); + TCGv src2 = get_gpr(ctx, a->rs2, EXT_SIGN); + + tcg_gen_brcond_tl(cond, src1, src2, l); + gen_goto_tb(ctx, 1, ctx->pc_succ_insn); + + gen_set_label(l); /* branch taken */ + + if (!has_ext(ctx, RVC) && ((ctx->base.pc_next + a->imm) & 0x3)) { + /* misaligned */ + gen_exception_inst_addr_mis(ctx); + } else { + gen_goto_tb(ctx, 0, ctx->base.pc_next + a->imm); + } + ctx->base.is_jmp = DISAS_NORETURN; + + return true; +} + +static bool trans_beq(DisasContext *ctx, arg_beq *a) +{ + return gen_branch(ctx, a, TCG_COND_EQ); +} + +static bool trans_bne(DisasContext *ctx, arg_bne *a) +{ + return gen_branch(ctx, a, TCG_COND_NE); +} + +static bool trans_blt(DisasContext *ctx, arg_blt *a) +{ + return gen_branch(ctx, a, TCG_COND_LT); +} + +static bool trans_bge(DisasContext *ctx, arg_bge *a) +{ + return gen_branch(ctx, a, TCG_COND_GE); +} + +static bool trans_bltu(DisasContext *ctx, arg_bltu *a) +{ + return gen_branch(ctx, a, TCG_COND_LTU); +} + +static bool trans_bgeu(DisasContext *ctx, arg_bgeu *a) +{ + return gen_branch(ctx, a, TCG_COND_GEU); +} + +static bool gen_load(DisasContext *ctx, arg_lb *a, MemOp memop) +{ + TCGv dest = dest_gpr(ctx, a->rd); + TCGv addr = get_gpr(ctx, a->rs1, EXT_NONE); + + if (a->imm) { + TCGv temp = temp_new(ctx); + tcg_gen_addi_tl(temp, addr, a->imm); + addr = temp; + } + addr = gen_pm_adjust_address(ctx, addr); + + tcg_gen_qemu_ld_tl(dest, addr, ctx->mem_idx, memop); + gen_set_gpr(ctx, a->rd, dest); + return true; +} + +static bool trans_lb(DisasContext *ctx, arg_lb *a) +{ + return gen_load(ctx, a, MO_SB); +} + +static bool trans_lh(DisasContext *ctx, arg_lh *a) +{ + return gen_load(ctx, a, MO_TESW); +} + +static bool trans_lw(DisasContext *ctx, arg_lw *a) +{ + return gen_load(ctx, a, MO_TESL); +} + +static bool trans_lbu(DisasContext *ctx, arg_lbu *a) +{ + return gen_load(ctx, a, MO_UB); +} + +static bool trans_lhu(DisasContext *ctx, arg_lhu *a) +{ + return gen_load(ctx, a, MO_TEUW); +} + +static bool gen_store(DisasContext *ctx, arg_sb *a, MemOp memop) +{ + TCGv addr = get_gpr(ctx, a->rs1, EXT_NONE); + TCGv data = get_gpr(ctx, a->rs2, EXT_NONE); + + if (a->imm) { + TCGv temp = temp_new(ctx); + tcg_gen_addi_tl(temp, addr, a->imm); + addr = temp; + } + addr = gen_pm_adjust_address(ctx, addr); + + tcg_gen_qemu_st_tl(data, addr, ctx->mem_idx, memop); + return true; +} + +static bool trans_sb(DisasContext *ctx, arg_sb *a) +{ + return gen_store(ctx, a, MO_SB); +} + +static bool trans_sh(DisasContext *ctx, arg_sh *a) +{ + return gen_store(ctx, a, MO_TESW); +} + +static bool trans_sw(DisasContext *ctx, arg_sw *a) +{ + return gen_store(ctx, a, MO_TESL); +} + +static bool trans_lwu(DisasContext *ctx, arg_lwu *a) +{ + REQUIRE_64BIT(ctx); + return gen_load(ctx, a, MO_TEUL); +} + +static bool trans_ld(DisasContext *ctx, arg_ld *a) +{ + REQUIRE_64BIT(ctx); + return gen_load(ctx, a, MO_TEQ); +} + +static bool trans_sd(DisasContext *ctx, arg_sd *a) +{ + REQUIRE_64BIT(ctx); + return gen_store(ctx, a, MO_TEQ); +} + +static bool trans_addi(DisasContext *ctx, arg_addi *a) +{ + return gen_arith_imm_fn(ctx, a, EXT_NONE, tcg_gen_addi_tl); +} + +static void gen_slt(TCGv ret, TCGv s1, TCGv s2) +{ + tcg_gen_setcond_tl(TCG_COND_LT, ret, s1, s2); +} + +static void gen_sltu(TCGv ret, TCGv s1, TCGv s2) +{ + tcg_gen_setcond_tl(TCG_COND_LTU, ret, s1, s2); +} + +static bool trans_slti(DisasContext *ctx, arg_slti *a) +{ + return gen_arith_imm_tl(ctx, a, EXT_SIGN, gen_slt); +} + +static bool trans_sltiu(DisasContext *ctx, arg_sltiu *a) +{ + return gen_arith_imm_tl(ctx, a, EXT_SIGN, gen_sltu); +} + +static bool trans_xori(DisasContext *ctx, arg_xori *a) +{ + return gen_arith_imm_fn(ctx, a, EXT_NONE, tcg_gen_xori_tl); +} + +static bool trans_ori(DisasContext *ctx, arg_ori *a) +{ + return gen_arith_imm_fn(ctx, a, EXT_NONE, tcg_gen_ori_tl); +} + +static bool trans_andi(DisasContext *ctx, arg_andi *a) +{ + return gen_arith_imm_fn(ctx, a, EXT_NONE, tcg_gen_andi_tl); +} + +static bool trans_slli(DisasContext *ctx, arg_slli *a) +{ + return gen_shift_imm_fn(ctx, a, EXT_NONE, tcg_gen_shli_tl); +} + +static void gen_srliw(TCGv dst, TCGv src, target_long shamt) +{ + tcg_gen_extract_tl(dst, src, shamt, 32 - shamt); +} + +static bool trans_srli(DisasContext *ctx, arg_srli *a) +{ + return gen_shift_imm_fn_per_ol(ctx, a, EXT_NONE, + tcg_gen_shri_tl, gen_srliw); +} + +static void gen_sraiw(TCGv dst, TCGv src, target_long shamt) +{ + tcg_gen_sextract_tl(dst, src, shamt, 32 - shamt); +} + +static bool trans_srai(DisasContext *ctx, arg_srai *a) +{ + return gen_shift_imm_fn_per_ol(ctx, a, EXT_NONE, + tcg_gen_sari_tl, gen_sraiw); +} + +static bool trans_add(DisasContext *ctx, arg_add *a) +{ + return gen_arith(ctx, a, EXT_NONE, tcg_gen_add_tl); +} + +static bool trans_sub(DisasContext *ctx, arg_sub *a) +{ + return gen_arith(ctx, a, EXT_NONE, tcg_gen_sub_tl); +} + +static bool trans_sll(DisasContext *ctx, arg_sll *a) +{ + return gen_shift(ctx, a, EXT_NONE, tcg_gen_shl_tl); +} + +static bool trans_slt(DisasContext *ctx, arg_slt *a) +{ + return gen_arith(ctx, a, EXT_SIGN, gen_slt); +} + +static bool trans_sltu(DisasContext *ctx, arg_sltu *a) +{ + return gen_arith(ctx, a, EXT_SIGN, gen_sltu); +} + +static bool trans_xor(DisasContext *ctx, arg_xor *a) +{ + return gen_arith(ctx, a, EXT_NONE, tcg_gen_xor_tl); +} + +static bool trans_srl(DisasContext *ctx, arg_srl *a) +{ + return gen_shift(ctx, a, EXT_ZERO, tcg_gen_shr_tl); +} + +static bool trans_sra(DisasContext *ctx, arg_sra *a) +{ + return gen_shift(ctx, a, EXT_SIGN, tcg_gen_sar_tl); +} + +static bool trans_or(DisasContext *ctx, arg_or *a) +{ + return gen_arith(ctx, a, EXT_NONE, tcg_gen_or_tl); +} + +static bool trans_and(DisasContext *ctx, arg_and *a) +{ + return gen_arith(ctx, a, EXT_NONE, tcg_gen_and_tl); +} + +static bool trans_addiw(DisasContext *ctx, arg_addiw *a) +{ + REQUIRE_64BIT(ctx); + ctx->ol = MXL_RV32; + return gen_arith_imm_fn(ctx, a, EXT_NONE, tcg_gen_addi_tl); +} + +static bool trans_slliw(DisasContext *ctx, arg_slliw *a) +{ + REQUIRE_64BIT(ctx); + ctx->ol = MXL_RV32; + return gen_shift_imm_fn(ctx, a, EXT_NONE, tcg_gen_shli_tl); +} + +static bool trans_srliw(DisasContext *ctx, arg_srliw *a) +{ + REQUIRE_64BIT(ctx); + ctx->ol = MXL_RV32; + return gen_shift_imm_fn(ctx, a, EXT_NONE, gen_srliw); +} + +static bool trans_sraiw(DisasContext *ctx, arg_sraiw *a) +{ + REQUIRE_64BIT(ctx); + ctx->ol = MXL_RV32; + return gen_shift_imm_fn(ctx, a, EXT_NONE, gen_sraiw); +} + +static bool trans_addw(DisasContext *ctx, arg_addw *a) +{ + REQUIRE_64BIT(ctx); + ctx->ol = MXL_RV32; + return gen_arith(ctx, a, EXT_NONE, tcg_gen_add_tl); +} + +static bool trans_subw(DisasContext *ctx, arg_subw *a) +{ + REQUIRE_64BIT(ctx); + ctx->ol = MXL_RV32; + return gen_arith(ctx, a, EXT_NONE, tcg_gen_sub_tl); +} + +static bool trans_sllw(DisasContext *ctx, arg_sllw *a) +{ + REQUIRE_64BIT(ctx); + ctx->ol = MXL_RV32; + return gen_shift(ctx, a, EXT_NONE, tcg_gen_shl_tl); +} + +static bool trans_srlw(DisasContext *ctx, arg_srlw *a) +{ + REQUIRE_64BIT(ctx); + ctx->ol = MXL_RV32; + return gen_shift(ctx, a, EXT_ZERO, tcg_gen_shr_tl); +} + +static bool trans_sraw(DisasContext *ctx, arg_sraw *a) +{ + REQUIRE_64BIT(ctx); + ctx->ol = MXL_RV32; + return gen_shift(ctx, a, EXT_SIGN, tcg_gen_sar_tl); +} + +static bool trans_fence(DisasContext *ctx, arg_fence *a) +{ + /* FENCE is a full memory barrier. */ + tcg_gen_mb(TCG_MO_ALL | TCG_BAR_SC); + return true; +} + +static bool trans_fence_i(DisasContext *ctx, arg_fence_i *a) +{ + if (!ctx->ext_ifencei) { + return false; + } + + /* + * FENCE_I is a no-op in QEMU, + * however we need to end the translation block + */ + tcg_gen_movi_tl(cpu_pc, ctx->pc_succ_insn); + tcg_gen_exit_tb(NULL, 0); + ctx->base.is_jmp = DISAS_NORETURN; + return true; +} + +static bool do_csr_post(DisasContext *ctx) +{ + /* We may have changed important cpu state -- exit to main loop. */ + tcg_gen_movi_tl(cpu_pc, ctx->pc_succ_insn); + tcg_gen_exit_tb(NULL, 0); + ctx->base.is_jmp = DISAS_NORETURN; + return true; +} + +static bool do_csrr(DisasContext *ctx, int rd, int rc) +{ + TCGv dest = dest_gpr(ctx, rd); + TCGv_i32 csr = tcg_constant_i32(rc); + + if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) { + gen_io_start(); + } + gen_helper_csrr(dest, cpu_env, csr); + gen_set_gpr(ctx, rd, dest); + return do_csr_post(ctx); +} + +static bool do_csrw(DisasContext *ctx, int rc, TCGv src) +{ + TCGv_i32 csr = tcg_constant_i32(rc); + + if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) { + gen_io_start(); + } + gen_helper_csrw(cpu_env, csr, src); + return do_csr_post(ctx); +} + +static bool do_csrrw(DisasContext *ctx, int rd, int rc, TCGv src, TCGv mask) +{ + TCGv dest = dest_gpr(ctx, rd); + TCGv_i32 csr = tcg_constant_i32(rc); + + if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) { + gen_io_start(); + } + gen_helper_csrrw(dest, cpu_env, csr, src, mask); + gen_set_gpr(ctx, rd, dest); + return do_csr_post(ctx); +} + +static bool trans_csrrw(DisasContext *ctx, arg_csrrw *a) +{ + TCGv src = get_gpr(ctx, a->rs1, EXT_NONE); + + /* + * If rd == 0, the insn shall not read the csr, nor cause any of the + * side effects that might occur on a csr read. + */ + if (a->rd == 0) { + return do_csrw(ctx, a->csr, src); + } + + TCGv mask = tcg_constant_tl(-1); + return do_csrrw(ctx, a->rd, a->csr, src, mask); +} + +static bool trans_csrrs(DisasContext *ctx, arg_csrrs *a) +{ + /* + * If rs1 == 0, the insn shall not write to the csr at all, nor + * cause any of the side effects that might occur on a csr write. + * Note that if rs1 specifies a register other than x0, holding + * a zero value, the instruction will still attempt to write the + * unmodified value back to the csr and will cause side effects. + */ + if (a->rs1 == 0) { + return do_csrr(ctx, a->rd, a->csr); + } + + TCGv ones = tcg_constant_tl(-1); + TCGv mask = get_gpr(ctx, a->rs1, EXT_ZERO); + return do_csrrw(ctx, a->rd, a->csr, ones, mask); +} + +static bool trans_csrrc(DisasContext *ctx, arg_csrrc *a) +{ + /* + * If rs1 == 0, the insn shall not write to the csr at all, nor + * cause any of the side effects that might occur on a csr write. + * Note that if rs1 specifies a register other than x0, holding + * a zero value, the instruction will still attempt to write the + * unmodified value back to the csr and will cause side effects. + */ + if (a->rs1 == 0) { + return do_csrr(ctx, a->rd, a->csr); + } + + TCGv mask = get_gpr(ctx, a->rs1, EXT_ZERO); + return do_csrrw(ctx, a->rd, a->csr, ctx->zero, mask); +} + +static bool trans_csrrwi(DisasContext *ctx, arg_csrrwi *a) +{ + TCGv src = tcg_constant_tl(a->rs1); + + /* + * If rd == 0, the insn shall not read the csr, nor cause any of the + * side effects that might occur on a csr read. + */ + if (a->rd == 0) { + return do_csrw(ctx, a->csr, src); + } + + TCGv mask = tcg_constant_tl(-1); + return do_csrrw(ctx, a->rd, a->csr, src, mask); +} + +static bool trans_csrrsi(DisasContext *ctx, arg_csrrsi *a) +{ + /* + * If rs1 == 0, the insn shall not write to the csr at all, nor + * cause any of the side effects that might occur on a csr write. + * Note that if rs1 specifies a register other than x0, holding + * a zero value, the instruction will still attempt to write the + * unmodified value back to the csr and will cause side effects. + */ + if (a->rs1 == 0) { + return do_csrr(ctx, a->rd, a->csr); + } + + TCGv ones = tcg_constant_tl(-1); + TCGv mask = tcg_constant_tl(a->rs1); + return do_csrrw(ctx, a->rd, a->csr, ones, mask); +} + +static bool trans_csrrci(DisasContext *ctx, arg_csrrci *a) +{ + /* + * If rs1 == 0, the insn shall not write to the csr at all, nor + * cause any of the side effects that might occur on a csr write. + * Note that if rs1 specifies a register other than x0, holding + * a zero value, the instruction will still attempt to write the + * unmodified value back to the csr and will cause side effects. + */ + if (a->rs1 == 0) { + return do_csrr(ctx, a->rd, a->csr); + } + + TCGv mask = tcg_constant_tl(a->rs1); + return do_csrrw(ctx, a->rd, a->csr, ctx->zero, mask); +} diff --git a/target/riscv/insn_trans/trans_rvm.c.inc b/target/riscv/insn_trans/trans_rvm.c.inc new file mode 100644 index 000000000..2af0e5c13 --- /dev/null +++ b/target/riscv/insn_trans/trans_rvm.c.inc @@ -0,0 +1,271 @@ +/* + * RISC-V translation routines for the RV64M Standard Extension. + * + * Copyright (c) 2016-2017 Sagar Karandikar, sagark@eecs.berkeley.edu + * Copyright (c) 2018 Peer Adelt, peer.adelt@hni.uni-paderborn.de + * Bastian Koppelmann, kbastian@mail.uni-paderborn.de + * + * 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/>. + */ + + +static bool trans_mul(DisasContext *ctx, arg_mul *a) +{ + REQUIRE_EXT(ctx, RVM); + return gen_arith(ctx, a, EXT_NONE, tcg_gen_mul_tl); +} + +static void gen_mulh(TCGv ret, TCGv s1, TCGv s2) +{ + TCGv discard = tcg_temp_new(); + + tcg_gen_muls2_tl(discard, ret, s1, s2); + tcg_temp_free(discard); +} + +static void gen_mulh_w(TCGv ret, TCGv s1, TCGv s2) +{ + tcg_gen_mul_tl(ret, s1, s2); + tcg_gen_sari_tl(ret, ret, 32); +} + +static bool trans_mulh(DisasContext *ctx, arg_mulh *a) +{ + REQUIRE_EXT(ctx, RVM); + return gen_arith_per_ol(ctx, a, EXT_SIGN, gen_mulh, gen_mulh_w); +} + +static void gen_mulhsu(TCGv ret, TCGv arg1, TCGv arg2) +{ + TCGv rl = tcg_temp_new(); + TCGv rh = tcg_temp_new(); + + tcg_gen_mulu2_tl(rl, rh, arg1, arg2); + /* fix up for one negative */ + tcg_gen_sari_tl(rl, arg1, TARGET_LONG_BITS - 1); + tcg_gen_and_tl(rl, rl, arg2); + tcg_gen_sub_tl(ret, rh, rl); + + tcg_temp_free(rl); + tcg_temp_free(rh); +} + +static void gen_mulhsu_w(TCGv ret, TCGv arg1, TCGv arg2) +{ + TCGv t1 = tcg_temp_new(); + TCGv t2 = tcg_temp_new(); + + tcg_gen_ext32s_tl(t1, arg1); + tcg_gen_ext32u_tl(t2, arg2); + tcg_gen_mul_tl(ret, t1, t2); + tcg_temp_free(t1); + tcg_temp_free(t2); + tcg_gen_sari_tl(ret, ret, 32); +} + +static bool trans_mulhsu(DisasContext *ctx, arg_mulhsu *a) +{ + REQUIRE_EXT(ctx, RVM); + return gen_arith_per_ol(ctx, a, EXT_NONE, gen_mulhsu, gen_mulhsu_w); +} + +static void gen_mulhu(TCGv ret, TCGv s1, TCGv s2) +{ + TCGv discard = tcg_temp_new(); + + tcg_gen_mulu2_tl(discard, ret, s1, s2); + tcg_temp_free(discard); +} + +static bool trans_mulhu(DisasContext *ctx, arg_mulhu *a) +{ + REQUIRE_EXT(ctx, RVM); + /* gen_mulh_w works for either sign as input. */ + return gen_arith_per_ol(ctx, a, EXT_ZERO, gen_mulhu, gen_mulh_w); +} + +static void gen_div(TCGv ret, TCGv source1, TCGv source2) +{ + TCGv temp1, temp2, zero, one, mone, min; + + temp1 = tcg_temp_new(); + temp2 = tcg_temp_new(); + zero = tcg_constant_tl(0); + one = tcg_constant_tl(1); + mone = tcg_constant_tl(-1); + min = tcg_constant_tl(1ull << (TARGET_LONG_BITS - 1)); + + /* + * If overflow, set temp2 to 1, else source2. + * This produces the required result of min. + */ + tcg_gen_setcond_tl(TCG_COND_EQ, temp1, source1, min); + tcg_gen_setcond_tl(TCG_COND_EQ, temp2, source2, mone); + tcg_gen_and_tl(temp1, temp1, temp2); + tcg_gen_movcond_tl(TCG_COND_NE, temp2, temp1, zero, one, source2); + + /* + * If div by zero, set temp1 to -1 and temp2 to 1 to + * produce the required result of -1. + */ + tcg_gen_movcond_tl(TCG_COND_EQ, temp1, source2, zero, mone, source1); + tcg_gen_movcond_tl(TCG_COND_EQ, temp2, source2, zero, one, temp2); + + tcg_gen_div_tl(ret, temp1, temp2); + + tcg_temp_free(temp1); + tcg_temp_free(temp2); +} + +static bool trans_div(DisasContext *ctx, arg_div *a) +{ + REQUIRE_EXT(ctx, RVM); + return gen_arith(ctx, a, EXT_SIGN, gen_div); +} + +static void gen_divu(TCGv ret, TCGv source1, TCGv source2) +{ + TCGv temp1, temp2, zero, one, max; + + temp1 = tcg_temp_new(); + temp2 = tcg_temp_new(); + zero = tcg_constant_tl(0); + one = tcg_constant_tl(1); + max = tcg_constant_tl(~0); + + /* + * If div by zero, set temp1 to max and temp2 to 1 to + * produce the required result of max. + */ + tcg_gen_movcond_tl(TCG_COND_EQ, temp1, source2, zero, max, source1); + tcg_gen_movcond_tl(TCG_COND_EQ, temp2, source2, zero, one, source2); + tcg_gen_divu_tl(ret, temp1, temp2); + + tcg_temp_free(temp1); + tcg_temp_free(temp2); +} + +static bool trans_divu(DisasContext *ctx, arg_divu *a) +{ + REQUIRE_EXT(ctx, RVM); + return gen_arith(ctx, a, EXT_ZERO, gen_divu); +} + +static void gen_rem(TCGv ret, TCGv source1, TCGv source2) +{ + TCGv temp1, temp2, zero, one, mone, min; + + temp1 = tcg_temp_new(); + temp2 = tcg_temp_new(); + zero = tcg_constant_tl(0); + one = tcg_constant_tl(1); + mone = tcg_constant_tl(-1); + min = tcg_constant_tl(1ull << (TARGET_LONG_BITS - 1)); + + /* + * If overflow, set temp1 to 0, else source1. + * This avoids a possible host trap, and produces the required result of 0. + */ + tcg_gen_setcond_tl(TCG_COND_EQ, temp1, source1, min); + tcg_gen_setcond_tl(TCG_COND_EQ, temp2, source2, mone); + tcg_gen_and_tl(temp1, temp1, temp2); + tcg_gen_movcond_tl(TCG_COND_NE, temp1, temp1, zero, zero, source1); + + /* + * If div by zero, set temp2 to 1, else source2. + * This avoids a possible host trap, but produces an incorrect result. + */ + tcg_gen_movcond_tl(TCG_COND_EQ, temp2, source2, zero, one, source2); + + tcg_gen_rem_tl(temp1, temp1, temp2); + + /* If div by zero, the required result is the original dividend. */ + tcg_gen_movcond_tl(TCG_COND_EQ, ret, source2, zero, source1, temp1); + + tcg_temp_free(temp1); + tcg_temp_free(temp2); +} + +static bool trans_rem(DisasContext *ctx, arg_rem *a) +{ + REQUIRE_EXT(ctx, RVM); + return gen_arith(ctx, a, EXT_SIGN, gen_rem); +} + +static void gen_remu(TCGv ret, TCGv source1, TCGv source2) +{ + TCGv temp, zero, one; + + temp = tcg_temp_new(); + zero = tcg_constant_tl(0); + one = tcg_constant_tl(1); + + /* + * If div by zero, set temp to 1, else source2. + * This avoids a possible host trap, but produces an incorrect result. + */ + tcg_gen_movcond_tl(TCG_COND_EQ, temp, source2, zero, one, source2); + + tcg_gen_remu_tl(temp, source1, temp); + + /* If div by zero, the required result is the original dividend. */ + tcg_gen_movcond_tl(TCG_COND_EQ, ret, source2, zero, source1, temp); + + tcg_temp_free(temp); +} + +static bool trans_remu(DisasContext *ctx, arg_remu *a) +{ + REQUIRE_EXT(ctx, RVM); + return gen_arith(ctx, a, EXT_ZERO, gen_remu); +} + +static bool trans_mulw(DisasContext *ctx, arg_mulw *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_EXT(ctx, RVM); + ctx->ol = MXL_RV32; + return gen_arith(ctx, a, EXT_NONE, tcg_gen_mul_tl); +} + +static bool trans_divw(DisasContext *ctx, arg_divw *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_EXT(ctx, RVM); + ctx->ol = MXL_RV32; + return gen_arith(ctx, a, EXT_SIGN, gen_div); +} + +static bool trans_divuw(DisasContext *ctx, arg_divuw *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_EXT(ctx, RVM); + ctx->ol = MXL_RV32; + return gen_arith(ctx, a, EXT_ZERO, gen_divu); +} + +static bool trans_remw(DisasContext *ctx, arg_remw *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_EXT(ctx, RVM); + ctx->ol = MXL_RV32; + return gen_arith(ctx, a, EXT_SIGN, gen_rem); +} + +static bool trans_remuw(DisasContext *ctx, arg_remuw *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_EXT(ctx, RVM); + ctx->ol = MXL_RV32; + return gen_arith(ctx, a, EXT_ZERO, gen_remu); +} diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc new file mode 100644 index 000000000..17ee3babe --- /dev/null +++ b/target/riscv/insn_trans/trans_rvv.c.inc @@ -0,0 +1,2867 @@ +/* + * RISC-V translation routines for the RVV Standard Extension. + * + * 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 "tcg/tcg-op-gvec.h" +#include "tcg/tcg-gvec-desc.h" +#include "internals.h" + +static bool trans_vsetvl(DisasContext *ctx, arg_vsetvl *a) +{ + TCGv s1, s2, dst; + + if (!has_ext(ctx, RVV)) { + return false; + } + + s2 = get_gpr(ctx, a->rs2, EXT_ZERO); + dst = dest_gpr(ctx, a->rd); + + /* Using x0 as the rs1 register specifier, encodes an infinite AVL */ + if (a->rs1 == 0) { + /* As the mask is at least one bit, RV_VLEN_MAX is >= VLMAX */ + s1 = tcg_constant_tl(RV_VLEN_MAX); + } else { + s1 = get_gpr(ctx, a->rs1, EXT_ZERO); + } + gen_helper_vsetvl(dst, cpu_env, s1, s2); + gen_set_gpr(ctx, a->rd, dst); + + tcg_gen_movi_tl(cpu_pc, ctx->pc_succ_insn); + tcg_gen_lookup_and_goto_ptr(); + ctx->base.is_jmp = DISAS_NORETURN; + return true; +} + +static bool trans_vsetvli(DisasContext *ctx, arg_vsetvli *a) +{ + TCGv s1, s2, dst; + + if (!has_ext(ctx, RVV)) { + return false; + } + + s2 = tcg_constant_tl(a->zimm); + dst = dest_gpr(ctx, a->rd); + + /* Using x0 as the rs1 register specifier, encodes an infinite AVL */ + if (a->rs1 == 0) { + /* As the mask is at least one bit, RV_VLEN_MAX is >= VLMAX */ + s1 = tcg_constant_tl(RV_VLEN_MAX); + } else { + s1 = get_gpr(ctx, a->rs1, EXT_ZERO); + } + gen_helper_vsetvl(dst, cpu_env, s1, s2); + gen_set_gpr(ctx, a->rd, dst); + + gen_goto_tb(ctx, 0, ctx->pc_succ_insn); + ctx->base.is_jmp = DISAS_NORETURN; + return true; +} + +/* vector register offset from env */ +static uint32_t vreg_ofs(DisasContext *s, int reg) +{ + return offsetof(CPURISCVState, vreg) + reg * s->vlen / 8; +} + +/* check functions */ + +/* + * In cpu_get_tb_cpu_state(), set VILL if RVV was not present. + * So RVV is also be checked in this function. + */ +static bool vext_check_isa_ill(DisasContext *s) +{ + return !s->vill; +} + +/* + * There are two rules check here. + * + * 1. Vector register numbers are multiples of LMUL. (Section 3.2) + * + * 2. For all widening instructions, the destination LMUL value must also be + * a supported LMUL value. (Section 11.2) + */ +static bool vext_check_reg(DisasContext *s, uint32_t reg, bool widen) +{ + /* + * The destination vector register group results are arranged as if both + * SEW and LMUL were at twice their current settings. (Section 11.2). + */ + int legal = widen ? 2 << s->lmul : 1 << s->lmul; + + return !((s->lmul == 0x3 && widen) || (reg % legal)); +} + +/* + * There are two rules check here. + * + * 1. The destination vector register group for a masked vector instruction can + * only overlap the source mask register (v0) when LMUL=1. (Section 5.3) + * + * 2. In widen instructions and some other insturctions, like vslideup.vx, + * there is no need to check whether LMUL=1. + */ +static bool vext_check_overlap_mask(DisasContext *s, uint32_t vd, bool vm, + bool force) +{ + return (vm != 0 || vd != 0) || (!force && (s->lmul == 0)); +} + +/* The LMUL setting must be such that LMUL * NFIELDS <= 8. (Section 7.8) */ +static bool vext_check_nf(DisasContext *s, uint32_t nf) +{ + return (1 << s->lmul) * nf <= 8; +} + +/* + * The destination vector register group cannot overlap a source vector register + * group of a different element width. (Section 11.2) + */ +static inline bool vext_check_overlap_group(int rd, int dlen, int rs, int slen) +{ + return ((rd >= rs + slen) || (rs >= rd + dlen)); +} +/* common translation macro */ +#define GEN_VEXT_TRANS(NAME, SEQ, ARGTYPE, OP, CHECK) \ +static bool trans_##NAME(DisasContext *s, arg_##ARGTYPE *a)\ +{ \ + if (CHECK(s, a)) { \ + return OP(s, a, SEQ); \ + } \ + return false; \ +} + +/* + *** unit stride load and store + */ +typedef void gen_helper_ldst_us(TCGv_ptr, TCGv_ptr, TCGv, + TCGv_env, TCGv_i32); + +static bool ldst_us_trans(uint32_t vd, uint32_t rs1, uint32_t data, + gen_helper_ldst_us *fn, DisasContext *s) +{ + TCGv_ptr dest, mask; + TCGv base; + TCGv_i32 desc; + + TCGLabel *over = gen_new_label(); + tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); + + dest = tcg_temp_new_ptr(); + mask = tcg_temp_new_ptr(); + base = get_gpr(s, rs1, EXT_NONE); + + /* + * As simd_desc supports at most 256 bytes, and in this implementation, + * the max vector group length is 2048 bytes. So split it into two parts. + * + * The first part is vlen in bytes, encoded in maxsz of simd_desc. + * The second part is lmul, encoded in data of simd_desc. + */ + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + + tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, vd)); + tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0)); + + fn(dest, mask, base, cpu_env, desc); + + tcg_temp_free_ptr(dest); + tcg_temp_free_ptr(mask); + gen_set_label(over); + return true; +} + +static bool ld_us_op(DisasContext *s, arg_r2nfvm *a, uint8_t seq) +{ + uint32_t data = 0; + gen_helper_ldst_us *fn; + static gen_helper_ldst_us * const fns[2][7][4] = { + /* masked unit stride load */ + { { gen_helper_vlb_v_b_mask, gen_helper_vlb_v_h_mask, + gen_helper_vlb_v_w_mask, gen_helper_vlb_v_d_mask }, + { NULL, gen_helper_vlh_v_h_mask, + gen_helper_vlh_v_w_mask, gen_helper_vlh_v_d_mask }, + { NULL, NULL, + gen_helper_vlw_v_w_mask, gen_helper_vlw_v_d_mask }, + { gen_helper_vle_v_b_mask, gen_helper_vle_v_h_mask, + gen_helper_vle_v_w_mask, gen_helper_vle_v_d_mask }, + { gen_helper_vlbu_v_b_mask, gen_helper_vlbu_v_h_mask, + gen_helper_vlbu_v_w_mask, gen_helper_vlbu_v_d_mask }, + { NULL, gen_helper_vlhu_v_h_mask, + gen_helper_vlhu_v_w_mask, gen_helper_vlhu_v_d_mask }, + { NULL, NULL, + gen_helper_vlwu_v_w_mask, gen_helper_vlwu_v_d_mask } }, + /* unmasked unit stride load */ + { { gen_helper_vlb_v_b, gen_helper_vlb_v_h, + gen_helper_vlb_v_w, gen_helper_vlb_v_d }, + { NULL, gen_helper_vlh_v_h, + gen_helper_vlh_v_w, gen_helper_vlh_v_d }, + { NULL, NULL, + gen_helper_vlw_v_w, gen_helper_vlw_v_d }, + { gen_helper_vle_v_b, gen_helper_vle_v_h, + gen_helper_vle_v_w, gen_helper_vle_v_d }, + { gen_helper_vlbu_v_b, gen_helper_vlbu_v_h, + gen_helper_vlbu_v_w, gen_helper_vlbu_v_d }, + { NULL, gen_helper_vlhu_v_h, + gen_helper_vlhu_v_w, gen_helper_vlhu_v_d }, + { NULL, NULL, + gen_helper_vlwu_v_w, gen_helper_vlwu_v_d } } + }; + + fn = fns[a->vm][seq][s->sew]; + if (fn == NULL) { + return false; + } + + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); + data = FIELD_DP32(data, VDATA, VM, a->vm); + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); + data = FIELD_DP32(data, VDATA, NF, a->nf); + return ldst_us_trans(a->rd, a->rs1, data, fn, s); +} + +static bool ld_us_check(DisasContext *s, arg_r2nfvm* a) +{ + return (vext_check_isa_ill(s) && + vext_check_overlap_mask(s, a->rd, a->vm, false) && + vext_check_reg(s, a->rd, false) && + vext_check_nf(s, a->nf)); +} + +GEN_VEXT_TRANS(vlb_v, 0, r2nfvm, ld_us_op, ld_us_check) +GEN_VEXT_TRANS(vlh_v, 1, r2nfvm, ld_us_op, ld_us_check) +GEN_VEXT_TRANS(vlw_v, 2, r2nfvm, ld_us_op, ld_us_check) +GEN_VEXT_TRANS(vle_v, 3, r2nfvm, ld_us_op, ld_us_check) +GEN_VEXT_TRANS(vlbu_v, 4, r2nfvm, ld_us_op, ld_us_check) +GEN_VEXT_TRANS(vlhu_v, 5, r2nfvm, ld_us_op, ld_us_check) +GEN_VEXT_TRANS(vlwu_v, 6, r2nfvm, ld_us_op, ld_us_check) + +static bool st_us_op(DisasContext *s, arg_r2nfvm *a, uint8_t seq) +{ + uint32_t data = 0; + gen_helper_ldst_us *fn; + static gen_helper_ldst_us * const fns[2][4][4] = { + /* masked unit stride load and store */ + { { gen_helper_vsb_v_b_mask, gen_helper_vsb_v_h_mask, + gen_helper_vsb_v_w_mask, gen_helper_vsb_v_d_mask }, + { NULL, gen_helper_vsh_v_h_mask, + gen_helper_vsh_v_w_mask, gen_helper_vsh_v_d_mask }, + { NULL, NULL, + gen_helper_vsw_v_w_mask, gen_helper_vsw_v_d_mask }, + { gen_helper_vse_v_b_mask, gen_helper_vse_v_h_mask, + gen_helper_vse_v_w_mask, gen_helper_vse_v_d_mask } }, + /* unmasked unit stride store */ + { { gen_helper_vsb_v_b, gen_helper_vsb_v_h, + gen_helper_vsb_v_w, gen_helper_vsb_v_d }, + { NULL, gen_helper_vsh_v_h, + gen_helper_vsh_v_w, gen_helper_vsh_v_d }, + { NULL, NULL, + gen_helper_vsw_v_w, gen_helper_vsw_v_d }, + { gen_helper_vse_v_b, gen_helper_vse_v_h, + gen_helper_vse_v_w, gen_helper_vse_v_d } } + }; + + fn = fns[a->vm][seq][s->sew]; + if (fn == NULL) { + return false; + } + + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); + data = FIELD_DP32(data, VDATA, VM, a->vm); + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); + data = FIELD_DP32(data, VDATA, NF, a->nf); + return ldst_us_trans(a->rd, a->rs1, data, fn, s); +} + +static bool st_us_check(DisasContext *s, arg_r2nfvm* a) +{ + return (vext_check_isa_ill(s) && + vext_check_reg(s, a->rd, false) && + vext_check_nf(s, a->nf)); +} + +GEN_VEXT_TRANS(vsb_v, 0, r2nfvm, st_us_op, st_us_check) +GEN_VEXT_TRANS(vsh_v, 1, r2nfvm, st_us_op, st_us_check) +GEN_VEXT_TRANS(vsw_v, 2, r2nfvm, st_us_op, st_us_check) +GEN_VEXT_TRANS(vse_v, 3, r2nfvm, st_us_op, st_us_check) + +/* + *** stride load and store + */ +typedef void gen_helper_ldst_stride(TCGv_ptr, TCGv_ptr, TCGv, + TCGv, TCGv_env, TCGv_i32); + +static bool ldst_stride_trans(uint32_t vd, uint32_t rs1, uint32_t rs2, + uint32_t data, gen_helper_ldst_stride *fn, + DisasContext *s) +{ + TCGv_ptr dest, mask; + TCGv base, stride; + TCGv_i32 desc; + + TCGLabel *over = gen_new_label(); + tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); + + dest = tcg_temp_new_ptr(); + mask = tcg_temp_new_ptr(); + base = get_gpr(s, rs1, EXT_NONE); + stride = get_gpr(s, rs2, EXT_NONE); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + + tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, vd)); + tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0)); + + fn(dest, mask, base, stride, cpu_env, desc); + + tcg_temp_free_ptr(dest); + tcg_temp_free_ptr(mask); + gen_set_label(over); + return true; +} + +static bool ld_stride_op(DisasContext *s, arg_rnfvm *a, uint8_t seq) +{ + uint32_t data = 0; + gen_helper_ldst_stride *fn; + static gen_helper_ldst_stride * const fns[7][4] = { + { gen_helper_vlsb_v_b, gen_helper_vlsb_v_h, + gen_helper_vlsb_v_w, gen_helper_vlsb_v_d }, + { NULL, gen_helper_vlsh_v_h, + gen_helper_vlsh_v_w, gen_helper_vlsh_v_d }, + { NULL, NULL, + gen_helper_vlsw_v_w, gen_helper_vlsw_v_d }, + { gen_helper_vlse_v_b, gen_helper_vlse_v_h, + gen_helper_vlse_v_w, gen_helper_vlse_v_d }, + { gen_helper_vlsbu_v_b, gen_helper_vlsbu_v_h, + gen_helper_vlsbu_v_w, gen_helper_vlsbu_v_d }, + { NULL, gen_helper_vlshu_v_h, + gen_helper_vlshu_v_w, gen_helper_vlshu_v_d }, + { NULL, NULL, + gen_helper_vlswu_v_w, gen_helper_vlswu_v_d }, + }; + + fn = fns[seq][s->sew]; + if (fn == NULL) { + return false; + } + + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); + data = FIELD_DP32(data, VDATA, VM, a->vm); + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); + data = FIELD_DP32(data, VDATA, NF, a->nf); + return ldst_stride_trans(a->rd, a->rs1, a->rs2, data, fn, s); +} + +static bool ld_stride_check(DisasContext *s, arg_rnfvm* a) +{ + return (vext_check_isa_ill(s) && + vext_check_overlap_mask(s, a->rd, a->vm, false) && + vext_check_reg(s, a->rd, false) && + vext_check_nf(s, a->nf)); +} + +GEN_VEXT_TRANS(vlsb_v, 0, rnfvm, ld_stride_op, ld_stride_check) +GEN_VEXT_TRANS(vlsh_v, 1, rnfvm, ld_stride_op, ld_stride_check) +GEN_VEXT_TRANS(vlsw_v, 2, rnfvm, ld_stride_op, ld_stride_check) +GEN_VEXT_TRANS(vlse_v, 3, rnfvm, ld_stride_op, ld_stride_check) +GEN_VEXT_TRANS(vlsbu_v, 4, rnfvm, ld_stride_op, ld_stride_check) +GEN_VEXT_TRANS(vlshu_v, 5, rnfvm, ld_stride_op, ld_stride_check) +GEN_VEXT_TRANS(vlswu_v, 6, rnfvm, ld_stride_op, ld_stride_check) + +static bool st_stride_op(DisasContext *s, arg_rnfvm *a, uint8_t seq) +{ + uint32_t data = 0; + gen_helper_ldst_stride *fn; + static gen_helper_ldst_stride * const fns[4][4] = { + /* masked stride store */ + { gen_helper_vssb_v_b, gen_helper_vssb_v_h, + gen_helper_vssb_v_w, gen_helper_vssb_v_d }, + { NULL, gen_helper_vssh_v_h, + gen_helper_vssh_v_w, gen_helper_vssh_v_d }, + { NULL, NULL, + gen_helper_vssw_v_w, gen_helper_vssw_v_d }, + { gen_helper_vsse_v_b, gen_helper_vsse_v_h, + gen_helper_vsse_v_w, gen_helper_vsse_v_d } + }; + + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); + data = FIELD_DP32(data, VDATA, VM, a->vm); + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); + data = FIELD_DP32(data, VDATA, NF, a->nf); + fn = fns[seq][s->sew]; + if (fn == NULL) { + return false; + } + + return ldst_stride_trans(a->rd, a->rs1, a->rs2, data, fn, s); +} + +static bool st_stride_check(DisasContext *s, arg_rnfvm* a) +{ + return (vext_check_isa_ill(s) && + vext_check_reg(s, a->rd, false) && + vext_check_nf(s, a->nf)); +} + +GEN_VEXT_TRANS(vssb_v, 0, rnfvm, st_stride_op, st_stride_check) +GEN_VEXT_TRANS(vssh_v, 1, rnfvm, st_stride_op, st_stride_check) +GEN_VEXT_TRANS(vssw_v, 2, rnfvm, st_stride_op, st_stride_check) +GEN_VEXT_TRANS(vsse_v, 3, rnfvm, st_stride_op, st_stride_check) + +/* + *** index load and store + */ +typedef void gen_helper_ldst_index(TCGv_ptr, TCGv_ptr, TCGv, + TCGv_ptr, TCGv_env, TCGv_i32); + +static bool ldst_index_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, + uint32_t data, gen_helper_ldst_index *fn, + DisasContext *s) +{ + TCGv_ptr dest, mask, index; + TCGv base; + TCGv_i32 desc; + + TCGLabel *over = gen_new_label(); + tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); + + dest = tcg_temp_new_ptr(); + mask = tcg_temp_new_ptr(); + index = tcg_temp_new_ptr(); + base = get_gpr(s, rs1, EXT_NONE); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + + tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, vd)); + tcg_gen_addi_ptr(index, cpu_env, vreg_ofs(s, vs2)); + tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0)); + + fn(dest, mask, base, index, cpu_env, desc); + + tcg_temp_free_ptr(dest); + tcg_temp_free_ptr(mask); + tcg_temp_free_ptr(index); + gen_set_label(over); + return true; +} + +static bool ld_index_op(DisasContext *s, arg_rnfvm *a, uint8_t seq) +{ + uint32_t data = 0; + gen_helper_ldst_index *fn; + static gen_helper_ldst_index * const fns[7][4] = { + { gen_helper_vlxb_v_b, gen_helper_vlxb_v_h, + gen_helper_vlxb_v_w, gen_helper_vlxb_v_d }, + { NULL, gen_helper_vlxh_v_h, + gen_helper_vlxh_v_w, gen_helper_vlxh_v_d }, + { NULL, NULL, + gen_helper_vlxw_v_w, gen_helper_vlxw_v_d }, + { gen_helper_vlxe_v_b, gen_helper_vlxe_v_h, + gen_helper_vlxe_v_w, gen_helper_vlxe_v_d }, + { gen_helper_vlxbu_v_b, gen_helper_vlxbu_v_h, + gen_helper_vlxbu_v_w, gen_helper_vlxbu_v_d }, + { NULL, gen_helper_vlxhu_v_h, + gen_helper_vlxhu_v_w, gen_helper_vlxhu_v_d }, + { NULL, NULL, + gen_helper_vlxwu_v_w, gen_helper_vlxwu_v_d }, + }; + + fn = fns[seq][s->sew]; + if (fn == NULL) { + return false; + } + + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); + data = FIELD_DP32(data, VDATA, VM, a->vm); + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); + data = FIELD_DP32(data, VDATA, NF, a->nf); + return ldst_index_trans(a->rd, a->rs1, a->rs2, data, fn, s); +} + +/* + * For vector indexed segment loads, the destination vector register + * groups cannot overlap the source vector register group (specified by + * `vs2`), else an illegal instruction exception is raised. + */ +static bool ld_index_check(DisasContext *s, arg_rnfvm* a) +{ + return (vext_check_isa_ill(s) && + vext_check_overlap_mask(s, a->rd, a->vm, false) && + vext_check_reg(s, a->rd, false) && + vext_check_reg(s, a->rs2, false) && + vext_check_nf(s, a->nf) && + ((a->nf == 1) || + vext_check_overlap_group(a->rd, a->nf << s->lmul, + a->rs2, 1 << s->lmul))); +} + +GEN_VEXT_TRANS(vlxb_v, 0, rnfvm, ld_index_op, ld_index_check) +GEN_VEXT_TRANS(vlxh_v, 1, rnfvm, ld_index_op, ld_index_check) +GEN_VEXT_TRANS(vlxw_v, 2, rnfvm, ld_index_op, ld_index_check) +GEN_VEXT_TRANS(vlxe_v, 3, rnfvm, ld_index_op, ld_index_check) +GEN_VEXT_TRANS(vlxbu_v, 4, rnfvm, ld_index_op, ld_index_check) +GEN_VEXT_TRANS(vlxhu_v, 5, rnfvm, ld_index_op, ld_index_check) +GEN_VEXT_TRANS(vlxwu_v, 6, rnfvm, ld_index_op, ld_index_check) + +static bool st_index_op(DisasContext *s, arg_rnfvm *a, uint8_t seq) +{ + uint32_t data = 0; + gen_helper_ldst_index *fn; + static gen_helper_ldst_index * const fns[4][4] = { + { gen_helper_vsxb_v_b, gen_helper_vsxb_v_h, + gen_helper_vsxb_v_w, gen_helper_vsxb_v_d }, + { NULL, gen_helper_vsxh_v_h, + gen_helper_vsxh_v_w, gen_helper_vsxh_v_d }, + { NULL, NULL, + gen_helper_vsxw_v_w, gen_helper_vsxw_v_d }, + { gen_helper_vsxe_v_b, gen_helper_vsxe_v_h, + gen_helper_vsxe_v_w, gen_helper_vsxe_v_d } + }; + + fn = fns[seq][s->sew]; + if (fn == NULL) { + return false; + } + + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); + data = FIELD_DP32(data, VDATA, VM, a->vm); + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); + data = FIELD_DP32(data, VDATA, NF, a->nf); + return ldst_index_trans(a->rd, a->rs1, a->rs2, data, fn, s); +} + +static bool st_index_check(DisasContext *s, arg_rnfvm* a) +{ + return (vext_check_isa_ill(s) && + vext_check_reg(s, a->rd, false) && + vext_check_reg(s, a->rs2, false) && + vext_check_nf(s, a->nf)); +} + +GEN_VEXT_TRANS(vsxb_v, 0, rnfvm, st_index_op, st_index_check) +GEN_VEXT_TRANS(vsxh_v, 1, rnfvm, st_index_op, st_index_check) +GEN_VEXT_TRANS(vsxw_v, 2, rnfvm, st_index_op, st_index_check) +GEN_VEXT_TRANS(vsxe_v, 3, rnfvm, st_index_op, st_index_check) + +/* + *** unit stride fault-only-first load + */ +static bool ldff_trans(uint32_t vd, uint32_t rs1, uint32_t data, + gen_helper_ldst_us *fn, DisasContext *s) +{ + TCGv_ptr dest, mask; + TCGv base; + TCGv_i32 desc; + + TCGLabel *over = gen_new_label(); + tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); + + dest = tcg_temp_new_ptr(); + mask = tcg_temp_new_ptr(); + base = get_gpr(s, rs1, EXT_NONE); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + + tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, vd)); + tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0)); + + fn(dest, mask, base, cpu_env, desc); + + tcg_temp_free_ptr(dest); + tcg_temp_free_ptr(mask); + gen_set_label(over); + return true; +} + +static bool ldff_op(DisasContext *s, arg_r2nfvm *a, uint8_t seq) +{ + uint32_t data = 0; + gen_helper_ldst_us *fn; + static gen_helper_ldst_us * const fns[7][4] = { + { gen_helper_vlbff_v_b, gen_helper_vlbff_v_h, + gen_helper_vlbff_v_w, gen_helper_vlbff_v_d }, + { NULL, gen_helper_vlhff_v_h, + gen_helper_vlhff_v_w, gen_helper_vlhff_v_d }, + { NULL, NULL, + gen_helper_vlwff_v_w, gen_helper_vlwff_v_d }, + { gen_helper_vleff_v_b, gen_helper_vleff_v_h, + gen_helper_vleff_v_w, gen_helper_vleff_v_d }, + { gen_helper_vlbuff_v_b, gen_helper_vlbuff_v_h, + gen_helper_vlbuff_v_w, gen_helper_vlbuff_v_d }, + { NULL, gen_helper_vlhuff_v_h, + gen_helper_vlhuff_v_w, gen_helper_vlhuff_v_d }, + { NULL, NULL, + gen_helper_vlwuff_v_w, gen_helper_vlwuff_v_d } + }; + + fn = fns[seq][s->sew]; + if (fn == NULL) { + return false; + } + + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); + data = FIELD_DP32(data, VDATA, VM, a->vm); + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); + data = FIELD_DP32(data, VDATA, NF, a->nf); + return ldff_trans(a->rd, a->rs1, data, fn, s); +} + +GEN_VEXT_TRANS(vlbff_v, 0, r2nfvm, ldff_op, ld_us_check) +GEN_VEXT_TRANS(vlhff_v, 1, r2nfvm, ldff_op, ld_us_check) +GEN_VEXT_TRANS(vlwff_v, 2, r2nfvm, ldff_op, ld_us_check) +GEN_VEXT_TRANS(vleff_v, 3, r2nfvm, ldff_op, ld_us_check) +GEN_VEXT_TRANS(vlbuff_v, 4, r2nfvm, ldff_op, ld_us_check) +GEN_VEXT_TRANS(vlhuff_v, 5, r2nfvm, ldff_op, ld_us_check) +GEN_VEXT_TRANS(vlwuff_v, 6, r2nfvm, ldff_op, ld_us_check) + +/* + *** vector atomic operation + */ +typedef void gen_helper_amo(TCGv_ptr, TCGv_ptr, TCGv, TCGv_ptr, + TCGv_env, TCGv_i32); + +static bool amo_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, + uint32_t data, gen_helper_amo *fn, DisasContext *s) +{ + TCGv_ptr dest, mask, index; + TCGv base; + TCGv_i32 desc; + + TCGLabel *over = gen_new_label(); + tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); + + dest = tcg_temp_new_ptr(); + mask = tcg_temp_new_ptr(); + index = tcg_temp_new_ptr(); + base = get_gpr(s, rs1, EXT_NONE); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + + tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, vd)); + tcg_gen_addi_ptr(index, cpu_env, vreg_ofs(s, vs2)); + tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0)); + + fn(dest, mask, base, index, cpu_env, desc); + + tcg_temp_free_ptr(dest); + tcg_temp_free_ptr(mask); + tcg_temp_free_ptr(index); + gen_set_label(over); + return true; +} + +static bool amo_op(DisasContext *s, arg_rwdvm *a, uint8_t seq) +{ + uint32_t data = 0; + gen_helper_amo *fn; + static gen_helper_amo *const fnsw[9] = { + /* no atomic operation */ + gen_helper_vamoswapw_v_w, + gen_helper_vamoaddw_v_w, + gen_helper_vamoxorw_v_w, + gen_helper_vamoandw_v_w, + gen_helper_vamoorw_v_w, + gen_helper_vamominw_v_w, + gen_helper_vamomaxw_v_w, + gen_helper_vamominuw_v_w, + gen_helper_vamomaxuw_v_w + }; + static gen_helper_amo *const fnsd[18] = { + gen_helper_vamoswapw_v_d, + gen_helper_vamoaddw_v_d, + gen_helper_vamoxorw_v_d, + gen_helper_vamoandw_v_d, + gen_helper_vamoorw_v_d, + gen_helper_vamominw_v_d, + gen_helper_vamomaxw_v_d, + gen_helper_vamominuw_v_d, + gen_helper_vamomaxuw_v_d, + gen_helper_vamoswapd_v_d, + gen_helper_vamoaddd_v_d, + gen_helper_vamoxord_v_d, + gen_helper_vamoandd_v_d, + gen_helper_vamoord_v_d, + gen_helper_vamomind_v_d, + gen_helper_vamomaxd_v_d, + gen_helper_vamominud_v_d, + gen_helper_vamomaxud_v_d + }; + + if (tb_cflags(s->base.tb) & CF_PARALLEL) { + gen_helper_exit_atomic(cpu_env); + s->base.is_jmp = DISAS_NORETURN; + return true; + } + + switch (s->sew) { + case 0 ... 2: + assert(seq < ARRAY_SIZE(fnsw)); + fn = fnsw[seq]; + break; + case 3: + /* XLEN check done in amo_check(). */ + assert(seq < ARRAY_SIZE(fnsd)); + fn = fnsd[seq]; + break; + default: + g_assert_not_reached(); + } + + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); + data = FIELD_DP32(data, VDATA, VM, a->vm); + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); + data = FIELD_DP32(data, VDATA, WD, a->wd); + return amo_trans(a->rd, a->rs1, a->rs2, data, fn, s); +} +/* + * There are two rules check here. + * + * 1. SEW must be at least as wide as the AMO memory element size. + * + * 2. If SEW is greater than XLEN, an illegal instruction exception is raised. + */ +static bool amo_check(DisasContext *s, arg_rwdvm* a) +{ + return (!s->vill && has_ext(s, RVA) && + (!a->wd || vext_check_overlap_mask(s, a->rd, a->vm, false)) && + vext_check_reg(s, a->rd, false) && + vext_check_reg(s, a->rs2, false) && + ((1 << s->sew) <= sizeof(target_ulong)) && + ((1 << s->sew) >= 4)); +} + +static bool amo_check64(DisasContext *s, arg_rwdvm* a) +{ + REQUIRE_64BIT(s); + return amo_check(s, a); +} + +GEN_VEXT_TRANS(vamoswapw_v, 0, rwdvm, amo_op, amo_check) +GEN_VEXT_TRANS(vamoaddw_v, 1, rwdvm, amo_op, amo_check) +GEN_VEXT_TRANS(vamoxorw_v, 2, rwdvm, amo_op, amo_check) +GEN_VEXT_TRANS(vamoandw_v, 3, rwdvm, amo_op, amo_check) +GEN_VEXT_TRANS(vamoorw_v, 4, rwdvm, amo_op, amo_check) +GEN_VEXT_TRANS(vamominw_v, 5, rwdvm, amo_op, amo_check) +GEN_VEXT_TRANS(vamomaxw_v, 6, rwdvm, amo_op, amo_check) +GEN_VEXT_TRANS(vamominuw_v, 7, rwdvm, amo_op, amo_check) +GEN_VEXT_TRANS(vamomaxuw_v, 8, rwdvm, amo_op, amo_check) +GEN_VEXT_TRANS(vamoswapd_v, 9, rwdvm, amo_op, amo_check64) +GEN_VEXT_TRANS(vamoaddd_v, 10, rwdvm, amo_op, amo_check64) +GEN_VEXT_TRANS(vamoxord_v, 11, rwdvm, amo_op, amo_check64) +GEN_VEXT_TRANS(vamoandd_v, 12, rwdvm, amo_op, amo_check64) +GEN_VEXT_TRANS(vamoord_v, 13, rwdvm, amo_op, amo_check64) +GEN_VEXT_TRANS(vamomind_v, 14, rwdvm, amo_op, amo_check64) +GEN_VEXT_TRANS(vamomaxd_v, 15, rwdvm, amo_op, amo_check64) +GEN_VEXT_TRANS(vamominud_v, 16, rwdvm, amo_op, amo_check64) +GEN_VEXT_TRANS(vamomaxud_v, 17, rwdvm, amo_op, amo_check64) + +/* + *** Vector Integer Arithmetic Instructions + */ +#define MAXSZ(s) (s->vlen >> (3 - s->lmul)) + +static bool opivv_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_overlap_mask(s, a->rd, a->vm, false) && + vext_check_reg(s, a->rd, false) && + vext_check_reg(s, a->rs2, false) && + vext_check_reg(s, a->rs1, false)); +} + +typedef void GVecGen3Fn(unsigned, uint32_t, uint32_t, + uint32_t, uint32_t, uint32_t); + +static inline bool +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); + + if (a->vm && s->vl_eq_vlmax) { + gvec_fn(s->sew, vreg_ofs(s, a->rd), + vreg_ofs(s, a->rs2), vreg_ofs(s, a->rs1), + MAXSZ(s), MAXSZ(s)); + } else { + uint32_t data = 0; + + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); + data = FIELD_DP32(data, VDATA, VM, a->vm); + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); + 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->vlen / 8, s->vlen / 8, data, fn); + } + gen_set_label(over); + return true; +} + +/* OPIVV with GVEC IR */ +#define GEN_OPIVV_GVEC_TRANS(NAME, SUF) \ +static bool trans_##NAME(DisasContext *s, arg_rmrr *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]); \ +} + +GEN_OPIVV_GVEC_TRANS(vadd_vv, add) +GEN_OPIVV_GVEC_TRANS(vsub_vv, sub) + +typedef void gen_helper_opivx(TCGv_ptr, TCGv_ptr, TCGv, TCGv_ptr, + TCGv_env, TCGv_i32); + +static bool opivx_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, uint32_t vm, + gen_helper_opivx *fn, DisasContext *s) +{ + TCGv_ptr dest, src2, mask; + TCGv src1; + TCGv_i32 desc; + uint32_t data = 0; + + TCGLabel *over = gen_new_label(); + tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); + + dest = tcg_temp_new_ptr(); + mask = tcg_temp_new_ptr(); + src2 = tcg_temp_new_ptr(); + src1 = get_gpr(s, rs1, EXT_NONE); + + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); + data = FIELD_DP32(data, VDATA, VM, vm); + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + + tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, vd)); + tcg_gen_addi_ptr(src2, cpu_env, vreg_ofs(s, vs2)); + tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0)); + + fn(dest, mask, src1, src2, cpu_env, desc); + + tcg_temp_free_ptr(dest); + tcg_temp_free_ptr(mask); + tcg_temp_free_ptr(src2); + gen_set_label(over); + return true; +} + +static bool opivx_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_overlap_mask(s, a->rd, a->vm, false) && + vext_check_reg(s, a->rd, false) && + vext_check_reg(s, a->rs2, false)); +} + +typedef void GVecGen2sFn(unsigned, uint32_t, uint32_t, TCGv_i64, + uint32_t, uint32_t); + +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) { + TCGv_i64 src1 = tcg_temp_new_i64(); + + tcg_gen_ext_tl_i64(src1, get_gpr(s, a->rs1, EXT_SIGN)); + gvec_fn(s->sew, vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2), + src1, MAXSZ(s), MAXSZ(s)); + + tcg_temp_free_i64(src1); + return true; + } + return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fn, s); +} + +/* OPIVX with GVEC IR */ +#define GEN_OPIVX_GVEC_TRANS(NAME, SUF) \ +static bool trans_##NAME(DisasContext *s, arg_rmrr *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]); \ +} + +GEN_OPIVX_GVEC_TRANS(vadd_vx, adds) +GEN_OPIVX_GVEC_TRANS(vsub_vx, subs) + +static void gen_vec_rsub8_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + tcg_gen_vec_sub8_i64(d, b, a); +} + +static void gen_vec_rsub16_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + tcg_gen_vec_sub16_i64(d, b, a); +} + +static void gen_rsub_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2) +{ + tcg_gen_sub_i32(ret, arg2, arg1); +} + +static void gen_rsub_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2) +{ + tcg_gen_sub_i64(ret, arg2, arg1); +} + +static void gen_rsub_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b) +{ + tcg_gen_sub_vec(vece, r, b, a); +} + +static void tcg_gen_gvec_rsubs(unsigned vece, uint32_t dofs, uint32_t aofs, + TCGv_i64 c, uint32_t oprsz, uint32_t maxsz) +{ + static const TCGOpcode vecop_list[] = { INDEX_op_sub_vec, 0 }; + static const GVecGen2s rsub_op[4] = { + { .fni8 = gen_vec_rsub8_i64, + .fniv = gen_rsub_vec, + .fno = gen_helper_vec_rsubs8, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fni8 = gen_vec_rsub16_i64, + .fniv = gen_rsub_vec, + .fno = gen_helper_vec_rsubs16, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_rsub_i32, + .fniv = gen_rsub_vec, + .fno = gen_helper_vec_rsubs32, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fni8 = gen_rsub_i64, + .fniv = gen_rsub_vec, + .fno = gen_helper_vec_rsubs64, + .opt_opc = vecop_list, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .vece = MO_64 }, + }; + + tcg_debug_assert(vece <= MO_64); + tcg_gen_gvec_2s(dofs, aofs, oprsz, maxsz, c, &rsub_op[vece]); +} + +GEN_OPIVX_GVEC_TRANS(vrsub_vx, rsubs) + +static bool opivi_trans(uint32_t vd, uint32_t imm, uint32_t vs2, uint32_t vm, + gen_helper_opivx *fn, DisasContext *s, int zx) +{ + TCGv_ptr dest, src2, mask; + TCGv src1; + TCGv_i32 desc; + uint32_t data = 0; + + TCGLabel *over = gen_new_label(); + tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); + + dest = tcg_temp_new_ptr(); + mask = tcg_temp_new_ptr(); + src2 = tcg_temp_new_ptr(); + if (zx) { + src1 = tcg_constant_tl(imm); + } else { + src1 = tcg_constant_tl(sextract64(imm, 0, 5)); + } + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); + data = FIELD_DP32(data, VDATA, VM, vm); + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + + tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, vd)); + tcg_gen_addi_ptr(src2, cpu_env, vreg_ofs(s, vs2)); + tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0)); + + fn(dest, mask, src1, src2, cpu_env, desc); + + tcg_temp_free_ptr(dest); + tcg_temp_free_ptr(mask); + tcg_temp_free_ptr(src2); + gen_set_label(over); + return true; +} + +typedef void GVecGen2iFn(unsigned, uint32_t, uint32_t, int64_t, + uint32_t, uint32_t); + +static inline bool +do_opivi_gvec(DisasContext *s, arg_rmrr *a, GVecGen2iFn *gvec_fn, + gen_helper_opivx *fn, int zx) +{ + if (!opivx_check(s, a)) { + return false; + } + + if (a->vm && s->vl_eq_vlmax) { + if (zx) { + gvec_fn(s->sew, vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2), + extract64(a->rs1, 0, 5), MAXSZ(s), MAXSZ(s)); + } else { + gvec_fn(s->sew, vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2), + sextract64(a->rs1, 0, 5), MAXSZ(s), MAXSZ(s)); + } + } else { + return opivi_trans(a->rd, a->rs1, a->rs2, a->vm, fn, s, zx); + } + return true; +} + +/* OPIVI with GVEC IR */ +#define GEN_OPIVI_GVEC_TRANS(NAME, ZX, OPIVX, SUF) \ +static bool trans_##NAME(DisasContext *s, arg_rmrr *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], ZX); \ +} + +GEN_OPIVI_GVEC_TRANS(vadd_vi, 0, vadd_vx, addi) + +static void tcg_gen_gvec_rsubi(unsigned vece, uint32_t dofs, uint32_t aofs, + int64_t c, uint32_t oprsz, uint32_t maxsz) +{ + TCGv_i64 tmp = tcg_constant_i64(c); + tcg_gen_gvec_rsubs(vece, dofs, aofs, tmp, oprsz, maxsz); +} + +GEN_OPIVI_GVEC_TRANS(vrsub_vi, 0, vrsub_vx, rsubi) + +/* Vector Widening Integer Add/Subtract */ + +/* OPIVV with WIDEN */ +static bool opivv_widen_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_overlap_mask(s, a->rd, a->vm, true) && + vext_check_reg(s, a->rd, true) && + vext_check_reg(s, a->rs2, false) && + vext_check_reg(s, a->rs1, false) && + vext_check_overlap_group(a->rd, 2 << s->lmul, a->rs2, + 1 << s->lmul) && + vext_check_overlap_group(a->rd, 2 << s->lmul, a->rs1, + 1 << s->lmul) && + (s->lmul < 0x3) && (s->sew < 0x3)); +} + +static bool do_opivv_widen(DisasContext *s, arg_rmrr *a, + gen_helper_gvec_4_ptr *fn, + bool (*checkfn)(DisasContext *, arg_rmrr *)) +{ + if (checkfn(s, a)) { + uint32_t data = 0; + TCGLabel *over = gen_new_label(); + tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); + + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); + data = FIELD_DP32(data, VDATA, VM, a->vm); + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); + 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->vlen / 8, s->vlen / 8, + data, fn); + gen_set_label(over); + return true; + } + return false; +} + +#define GEN_OPIVV_WIDEN_TRANS(NAME, CHECK) \ +static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ +{ \ + static gen_helper_gvec_4_ptr * const fns[3] = { \ + gen_helper_##NAME##_b, \ + gen_helper_##NAME##_h, \ + gen_helper_##NAME##_w \ + }; \ + return do_opivv_widen(s, a, fns[s->sew], CHECK); \ +} + +GEN_OPIVV_WIDEN_TRANS(vwaddu_vv, opivv_widen_check) +GEN_OPIVV_WIDEN_TRANS(vwadd_vv, opivv_widen_check) +GEN_OPIVV_WIDEN_TRANS(vwsubu_vv, opivv_widen_check) +GEN_OPIVV_WIDEN_TRANS(vwsub_vv, opivv_widen_check) + +/* OPIVX with WIDEN */ +static bool opivx_widen_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_overlap_mask(s, a->rd, a->vm, true) && + vext_check_reg(s, a->rd, true) && + vext_check_reg(s, a->rs2, false) && + vext_check_overlap_group(a->rd, 2 << s->lmul, a->rs2, + 1 << s->lmul) && + (s->lmul < 0x3) && (s->sew < 0x3)); +} + +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]); \ +} + +GEN_OPIVX_WIDEN_TRANS(vwaddu_vx) +GEN_OPIVX_WIDEN_TRANS(vwadd_vx) +GEN_OPIVX_WIDEN_TRANS(vwsubu_vx) +GEN_OPIVX_WIDEN_TRANS(vwsub_vx) + +/* WIDEN OPIVV with WIDEN */ +static bool opiwv_widen_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_overlap_mask(s, a->rd, a->vm, true) && + vext_check_reg(s, a->rd, true) && + vext_check_reg(s, a->rs2, true) && + vext_check_reg(s, a->rs1, false) && + vext_check_overlap_group(a->rd, 2 << s->lmul, a->rs1, + 1 << s->lmul) && + (s->lmul < 0x3) && (s->sew < 0x3)); +} + +static bool do_opiwv_widen(DisasContext *s, arg_rmrr *a, + gen_helper_gvec_4_ptr *fn) +{ + 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); + + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); + data = FIELD_DP32(data, VDATA, VM, a->vm); + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); + 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->vlen / 8, s->vlen / 8, data, fn); + gen_set_label(over); + return true; + } + return false; +} + +#define GEN_OPIWV_WIDEN_TRANS(NAME) \ +static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ +{ \ + static gen_helper_gvec_4_ptr * const fns[3] = { \ + gen_helper_##NAME##_b, \ + gen_helper_##NAME##_h, \ + gen_helper_##NAME##_w \ + }; \ + return do_opiwv_widen(s, a, fns[s->sew]); \ +} + +GEN_OPIWV_WIDEN_TRANS(vwaddu_wv) +GEN_OPIWV_WIDEN_TRANS(vwadd_wv) +GEN_OPIWV_WIDEN_TRANS(vwsubu_wv) +GEN_OPIWV_WIDEN_TRANS(vwsub_wv) + +/* WIDEN OPIVX with WIDEN */ +static bool opiwx_widen_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_overlap_mask(s, a->rd, a->vm, true) && + vext_check_reg(s, a->rd, true) && + vext_check_reg(s, a->rs2, true) && + (s->lmul < 0x3) && (s->sew < 0x3)); +} + +static bool do_opiwx_widen(DisasContext *s, arg_rmrr *a, + gen_helper_opivx *fn) +{ + if (opiwx_widen_check(s, a)) { + return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fn, s); + } + return false; +} + +#define GEN_OPIWX_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_opiwx_widen(s, a, fns[s->sew]); \ +} + +GEN_OPIWX_WIDEN_TRANS(vwaddu_wx) +GEN_OPIWX_WIDEN_TRANS(vwadd_wx) +GEN_OPIWX_WIDEN_TRANS(vwsubu_wx) +GEN_OPIWX_WIDEN_TRANS(vwsub_wx) + +/* 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); \ + \ + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ + data = FIELD_DP32(data, VDATA, VM, a->vm); \ + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ + 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->vlen / 8, s->vlen / 8, data, \ + fns[s->sew]); \ + gen_set_label(over); \ + return true; \ + } \ + return false; \ +} + +/* + * For vadc and vsbc, an illegal instruction exception is raised if the + * destination vector register is v0 and LMUL > 1. (Section 12.3) + */ +static bool opivv_vadc_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_reg(s, a->rd, false) && + vext_check_reg(s, a->rs2, false) && + vext_check_reg(s, a->rs1, false) && + ((a->rd != 0) || (s->lmul == 0))); +} + +GEN_OPIVV_TRANS(vadc_vvm, opivv_vadc_check) +GEN_OPIVV_TRANS(vsbc_vvm, opivv_vadc_check) + +/* + * For vmadc and vmsbc, an illegal instruction exception is raised if the + * destination vector register overlaps a source vector register group. + */ +static bool opivv_vmadc_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_reg(s, a->rs2, false) && + vext_check_reg(s, a->rs1, false) && + vext_check_overlap_group(a->rd, 1, a->rs1, 1 << s->lmul) && + vext_check_overlap_group(a->rd, 1, a->rs2, 1 << s->lmul)); +} + +GEN_OPIVV_TRANS(vmadc_vvm, opivv_vmadc_check) +GEN_OPIVV_TRANS(vmsbc_vvm, opivv_vmadc_check) + +static bool opivx_vadc_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_reg(s, a->rd, false) && + vext_check_reg(s, a->rs2, false) && + ((a->rd != 0) || (s->lmul == 0))); +} + +/* OPIVX without GVEC IR */ +#define GEN_OPIVX_TRANS(NAME, 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 opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fns[s->sew], s);\ + } \ + return false; \ +} + +GEN_OPIVX_TRANS(vadc_vxm, opivx_vadc_check) +GEN_OPIVX_TRANS(vsbc_vxm, opivx_vadc_check) + +static bool opivx_vmadc_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_reg(s, a->rs2, false) && + vext_check_overlap_group(a->rd, 1, a->rs2, 1 << s->lmul)); +} + +GEN_OPIVX_TRANS(vmadc_vxm, opivx_vmadc_check) +GEN_OPIVX_TRANS(vmsbc_vxm, opivx_vmadc_check) + +/* OPIVI without GVEC IR */ +#define GEN_OPIVI_TRANS(NAME, ZX, OPIVX, 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 opivi_trans(a->rd, a->rs1, a->rs2, a->vm, \ + fns[s->sew], s, ZX); \ + } \ + return false; \ +} + +GEN_OPIVI_TRANS(vadc_vim, 0, vadc_vxm, opivx_vadc_check) +GEN_OPIVI_TRANS(vmadc_vim, 0, vmadc_vxm, opivx_vmadc_check) + +/* Vector Bitwise Logical Instructions */ +GEN_OPIVV_GVEC_TRANS(vand_vv, and) +GEN_OPIVV_GVEC_TRANS(vor_vv, or) +GEN_OPIVV_GVEC_TRANS(vxor_vv, xor) +GEN_OPIVX_GVEC_TRANS(vand_vx, ands) +GEN_OPIVX_GVEC_TRANS(vor_vx, ors) +GEN_OPIVX_GVEC_TRANS(vxor_vx, xors) +GEN_OPIVI_GVEC_TRANS(vand_vi, 0, vand_vx, andi) +GEN_OPIVI_GVEC_TRANS(vor_vi, 0, vor_vx, ori) +GEN_OPIVI_GVEC_TRANS(vxor_vi, 0, vxor_vx, xori) + +/* Vector Single-Width Bit Shift Instructions */ +GEN_OPIVV_GVEC_TRANS(vsll_vv, shlv) +GEN_OPIVV_GVEC_TRANS(vsrl_vv, shrv) +GEN_OPIVV_GVEC_TRANS(vsra_vv, sarv) + +typedef void GVecGen2sFn32(unsigned, uint32_t, uint32_t, TCGv_i32, + uint32_t, uint32_t); + +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) { + TCGv_i32 src1 = tcg_temp_new_i32(); + + tcg_gen_trunc_tl_i32(src1, get_gpr(s, a->rs1, EXT_NONE)); + tcg_gen_extract_i32(src1, src1, 0, s->sew + 3); + gvec_fn(s->sew, vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2), + src1, MAXSZ(s), MAXSZ(s)); + + tcg_temp_free_i32(src1); + return true; + } + return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fn, s); +} + +#define GEN_OPIVX_GVEC_SHIFT_TRANS(NAME, SUF) \ +static bool trans_##NAME(DisasContext *s, arg_rmrr *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]); \ +} + +GEN_OPIVX_GVEC_SHIFT_TRANS(vsll_vx, shls) +GEN_OPIVX_GVEC_SHIFT_TRANS(vsrl_vx, shrs) +GEN_OPIVX_GVEC_SHIFT_TRANS(vsra_vx, sars) + +GEN_OPIVI_GVEC_TRANS(vsll_vi, 1, vsll_vx, shli) +GEN_OPIVI_GVEC_TRANS(vsrl_vi, 1, vsrl_vx, shri) +GEN_OPIVI_GVEC_TRANS(vsra_vi, 1, vsra_vx, sari) + +/* Vector Narrowing Integer Right Shift Instructions */ +static bool opivv_narrow_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_overlap_mask(s, a->rd, a->vm, false) && + vext_check_reg(s, a->rd, false) && + vext_check_reg(s, a->rs2, true) && + vext_check_reg(s, a->rs1, false) && + vext_check_overlap_group(a->rd, 1 << s->lmul, a->rs2, + 2 << s->lmul) && + (s->lmul < 0x3) && (s->sew < 0x3)); +} + +/* OPIVV with NARROW */ +#define GEN_OPIVV_NARROW_TRANS(NAME) \ +static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ +{ \ + if (opivv_narrow_check(s, a)) { \ + uint32_t data = 0; \ + static gen_helper_gvec_4_ptr * const fns[3] = { \ + gen_helper_##NAME##_b, \ + gen_helper_##NAME##_h, \ + gen_helper_##NAME##_w, \ + }; \ + TCGLabel *over = gen_new_label(); \ + tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ + \ + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ + data = FIELD_DP32(data, VDATA, VM, a->vm); \ + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ + 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->vlen / 8, s->vlen / 8, data, \ + fns[s->sew]); \ + gen_set_label(over); \ + return true; \ + } \ + return false; \ +} +GEN_OPIVV_NARROW_TRANS(vnsra_vv) +GEN_OPIVV_NARROW_TRANS(vnsrl_vv) + +static bool opivx_narrow_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_overlap_mask(s, a->rd, a->vm, false) && + vext_check_reg(s, a->rd, false) && + vext_check_reg(s, a->rs2, true) && + vext_check_overlap_group(a->rd, 1 << s->lmul, a->rs2, + 2 << s->lmul) && + (s->lmul < 0x3) && (s->sew < 0x3)); +} + +/* OPIVX with NARROW */ +#define GEN_OPIVX_NARROW_TRANS(NAME) \ +static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ +{ \ + if (opivx_narrow_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_NARROW_TRANS(vnsra_vx) +GEN_OPIVX_NARROW_TRANS(vnsrl_vx) + +/* OPIVI with NARROW */ +#define GEN_OPIVI_NARROW_TRANS(NAME, ZX, OPIVX) \ +static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ +{ \ + if (opivx_narrow_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, ZX); \ + } \ + return false; \ +} + +GEN_OPIVI_NARROW_TRANS(vnsra_vi, 1, vnsra_vx) +GEN_OPIVI_NARROW_TRANS(vnsrl_vi, 1, vnsrl_vx) + +/* Vector Integer Comparison Instructions */ +/* + * For all comparison instructions, an illegal instruction exception is raised + * if the destination vector register overlaps a source vector register group + * and LMUL > 1. + */ +static bool opivv_cmp_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_reg(s, a->rs2, false) && + vext_check_reg(s, a->rs1, false) && + ((vext_check_overlap_group(a->rd, 1, a->rs1, 1 << s->lmul) && + vext_check_overlap_group(a->rd, 1, a->rs2, 1 << s->lmul)) || + (s->lmul == 0))); +} +GEN_OPIVV_TRANS(vmseq_vv, opivv_cmp_check) +GEN_OPIVV_TRANS(vmsne_vv, opivv_cmp_check) +GEN_OPIVV_TRANS(vmsltu_vv, opivv_cmp_check) +GEN_OPIVV_TRANS(vmslt_vv, opivv_cmp_check) +GEN_OPIVV_TRANS(vmsleu_vv, opivv_cmp_check) +GEN_OPIVV_TRANS(vmsle_vv, opivv_cmp_check) + +static bool opivx_cmp_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_reg(s, a->rs2, false) && + (vext_check_overlap_group(a->rd, 1, a->rs2, 1 << s->lmul) || + (s->lmul == 0))); +} + +GEN_OPIVX_TRANS(vmseq_vx, opivx_cmp_check) +GEN_OPIVX_TRANS(vmsne_vx, opivx_cmp_check) +GEN_OPIVX_TRANS(vmsltu_vx, opivx_cmp_check) +GEN_OPIVX_TRANS(vmslt_vx, opivx_cmp_check) +GEN_OPIVX_TRANS(vmsleu_vx, opivx_cmp_check) +GEN_OPIVX_TRANS(vmsle_vx, opivx_cmp_check) +GEN_OPIVX_TRANS(vmsgtu_vx, opivx_cmp_check) +GEN_OPIVX_TRANS(vmsgt_vx, opivx_cmp_check) + +GEN_OPIVI_TRANS(vmseq_vi, 0, vmseq_vx, opivx_cmp_check) +GEN_OPIVI_TRANS(vmsne_vi, 0, vmsne_vx, opivx_cmp_check) +GEN_OPIVI_TRANS(vmsleu_vi, 1, vmsleu_vx, opivx_cmp_check) +GEN_OPIVI_TRANS(vmsle_vi, 0, vmsle_vx, opivx_cmp_check) +GEN_OPIVI_TRANS(vmsgtu_vi, 1, vmsgtu_vx, opivx_cmp_check) +GEN_OPIVI_TRANS(vmsgt_vi, 0, vmsgt_vx, opivx_cmp_check) + +/* Vector Integer Min/Max Instructions */ +GEN_OPIVV_GVEC_TRANS(vminu_vv, umin) +GEN_OPIVV_GVEC_TRANS(vmin_vv, smin) +GEN_OPIVV_GVEC_TRANS(vmaxu_vv, umax) +GEN_OPIVV_GVEC_TRANS(vmax_vv, smax) +GEN_OPIVX_TRANS(vminu_vx, opivx_check) +GEN_OPIVX_TRANS(vmin_vx, opivx_check) +GEN_OPIVX_TRANS(vmaxu_vx, opivx_check) +GEN_OPIVX_TRANS(vmax_vx, opivx_check) + +/* Vector Single-Width Integer Multiply Instructions */ +GEN_OPIVV_GVEC_TRANS(vmul_vv, mul) +GEN_OPIVV_TRANS(vmulh_vv, opivv_check) +GEN_OPIVV_TRANS(vmulhu_vv, opivv_check) +GEN_OPIVV_TRANS(vmulhsu_vv, opivv_check) +GEN_OPIVX_GVEC_TRANS(vmul_vx, muls) +GEN_OPIVX_TRANS(vmulh_vx, opivx_check) +GEN_OPIVX_TRANS(vmulhu_vx, opivx_check) +GEN_OPIVX_TRANS(vmulhsu_vx, opivx_check) + +/* Vector Integer Divide Instructions */ +GEN_OPIVV_TRANS(vdivu_vv, opivv_check) +GEN_OPIVV_TRANS(vdiv_vv, opivv_check) +GEN_OPIVV_TRANS(vremu_vv, opivv_check) +GEN_OPIVV_TRANS(vrem_vv, opivv_check) +GEN_OPIVX_TRANS(vdivu_vx, opivx_check) +GEN_OPIVX_TRANS(vdiv_vx, opivx_check) +GEN_OPIVX_TRANS(vremu_vx, opivx_check) +GEN_OPIVX_TRANS(vrem_vx, opivx_check) + +/* Vector Widening Integer Multiply Instructions */ +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) + +/* Vector Single-Width Integer Multiply-Add Instructions */ +GEN_OPIVV_TRANS(vmacc_vv, opivv_check) +GEN_OPIVV_TRANS(vnmsac_vv, opivv_check) +GEN_OPIVV_TRANS(vmadd_vv, opivv_check) +GEN_OPIVV_TRANS(vnmsub_vv, opivv_check) +GEN_OPIVX_TRANS(vmacc_vx, opivx_check) +GEN_OPIVX_TRANS(vnmsac_vx, opivx_check) +GEN_OPIVX_TRANS(vmadd_vx, opivx_check) +GEN_OPIVX_TRANS(vnmsub_vx, opivx_check) + +/* Vector Widening Integer Multiply-Add Instructions */ +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) + +/* Vector Integer Merge and Move Instructions */ +static bool trans_vmv_v_v(DisasContext *s, arg_vmv_v_v *a) +{ + if (vext_check_isa_ill(s) && + vext_check_reg(s, a->rd, false) && + vext_check_reg(s, a->rs1, false)) { + + if (s->vl_eq_vlmax) { + tcg_gen_gvec_mov(s->sew, vreg_ofs(s, a->rd), + vreg_ofs(s, a->rs1), + MAXSZ(s), MAXSZ(s)); + } else { + uint32_t data = FIELD_DP32(0, VDATA, LMUL, s->lmul); + static gen_helper_gvec_2_ptr * const fns[4] = { + gen_helper_vmv_v_v_b, gen_helper_vmv_v_v_h, + 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_gvec_2_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, a->rs1), + cpu_env, s->vlen / 8, s->vlen / 8, data, + fns[s->sew]); + gen_set_label(over); + } + return true; + } + return false; +} + +typedef void gen_helper_vmv_vx(TCGv_ptr, TCGv_i64, TCGv_env, TCGv_i32); +static bool trans_vmv_v_x(DisasContext *s, arg_vmv_v_x *a) +{ + if (vext_check_isa_ill(s) && + vext_check_reg(s, a->rd, false)) { + + TCGv s1; + TCGLabel *over = gen_new_label(); + tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); + + s1 = get_gpr(s, a->rs1, EXT_SIGN); + + if (s->vl_eq_vlmax) { + tcg_gen_gvec_dup_tl(s->sew, vreg_ofs(s, a->rd), + MAXSZ(s), MAXSZ(s), s1); + } else { + TCGv_i32 desc; + TCGv_i64 s1_i64 = tcg_temp_new_i64(); + TCGv_ptr dest = tcg_temp_new_ptr(); + uint32_t data = FIELD_DP32(0, VDATA, LMUL, s->lmul); + static gen_helper_vmv_vx * const fns[4] = { + gen_helper_vmv_v_x_b, gen_helper_vmv_v_x_h, + gen_helper_vmv_v_x_w, gen_helper_vmv_v_x_d, + }; + + tcg_gen_ext_tl_i64(s1_i64, s1); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, a->rd)); + fns[s->sew](dest, s1_i64, cpu_env, desc); + + tcg_temp_free_ptr(dest); + tcg_temp_free_i64(s1_i64); + } + + gen_set_label(over); + return true; + } + return false; +} + +static bool trans_vmv_v_i(DisasContext *s, arg_vmv_v_i *a) +{ + if (vext_check_isa_ill(s) && + vext_check_reg(s, a->rd, false)) { + + int64_t simm = sextract64(a->rs1, 0, 5); + if (s->vl_eq_vlmax) { + tcg_gen_gvec_dup_imm(s->sew, vreg_ofs(s, a->rd), + MAXSZ(s), MAXSZ(s), simm); + } else { + TCGv_i32 desc; + TCGv_i64 s1; + TCGv_ptr dest; + uint32_t data = FIELD_DP32(0, VDATA, LMUL, s->lmul); + static gen_helper_vmv_vx * const fns[4] = { + gen_helper_vmv_v_x_b, gen_helper_vmv_v_x_h, + 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); + + s1 = tcg_constant_i64(simm); + dest = tcg_temp_new_ptr(); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, a->rd)); + fns[s->sew](dest, s1, cpu_env, desc); + + tcg_temp_free_ptr(dest); + gen_set_label(over); + } + return true; + } + return false; +} + +GEN_OPIVV_TRANS(vmerge_vvm, opivv_vadc_check) +GEN_OPIVX_TRANS(vmerge_vxm, opivx_vadc_check) +GEN_OPIVI_TRANS(vmerge_vim, 0, vmerge_vxm, opivx_vadc_check) + +/* + *** Vector Fixed-Point Arithmetic Instructions + */ + +/* Vector Single-Width Saturating Add and Subtract */ +GEN_OPIVV_TRANS(vsaddu_vv, opivv_check) +GEN_OPIVV_TRANS(vsadd_vv, opivv_check) +GEN_OPIVV_TRANS(vssubu_vv, opivv_check) +GEN_OPIVV_TRANS(vssub_vv, opivv_check) +GEN_OPIVX_TRANS(vsaddu_vx, opivx_check) +GEN_OPIVX_TRANS(vsadd_vx, opivx_check) +GEN_OPIVX_TRANS(vssubu_vx, opivx_check) +GEN_OPIVX_TRANS(vssub_vx, opivx_check) +GEN_OPIVI_TRANS(vsaddu_vi, 1, vsaddu_vx, opivx_check) +GEN_OPIVI_TRANS(vsadd_vi, 0, vsadd_vx, opivx_check) + +/* Vector Single-Width Averaging Add and Subtract */ +GEN_OPIVV_TRANS(vaadd_vv, opivv_check) +GEN_OPIVV_TRANS(vasub_vv, opivv_check) +GEN_OPIVX_TRANS(vaadd_vx, opivx_check) +GEN_OPIVX_TRANS(vasub_vx, opivx_check) +GEN_OPIVI_TRANS(vaadd_vi, 0, vaadd_vx, opivx_check) + +/* Vector Single-Width Fractional Multiply with Rounding and Saturation */ +GEN_OPIVV_TRANS(vsmul_vv, opivv_check) +GEN_OPIVX_TRANS(vsmul_vx, opivx_check) + +/* Vector Widening Saturating Scaled Multiply-Add */ +GEN_OPIVV_WIDEN_TRANS(vwsmaccu_vv, opivv_widen_check) +GEN_OPIVV_WIDEN_TRANS(vwsmacc_vv, opivv_widen_check) +GEN_OPIVV_WIDEN_TRANS(vwsmaccsu_vv, opivv_widen_check) +GEN_OPIVX_WIDEN_TRANS(vwsmaccu_vx) +GEN_OPIVX_WIDEN_TRANS(vwsmacc_vx) +GEN_OPIVX_WIDEN_TRANS(vwsmaccsu_vx) +GEN_OPIVX_WIDEN_TRANS(vwsmaccus_vx) + +/* Vector Single-Width Scaling Shift Instructions */ +GEN_OPIVV_TRANS(vssrl_vv, opivv_check) +GEN_OPIVV_TRANS(vssra_vv, opivv_check) +GEN_OPIVX_TRANS(vssrl_vx, opivx_check) +GEN_OPIVX_TRANS(vssra_vx, opivx_check) +GEN_OPIVI_TRANS(vssrl_vi, 1, vssrl_vx, opivx_check) +GEN_OPIVI_TRANS(vssra_vi, 0, vssra_vx, opivx_check) + +/* Vector Narrowing Fixed-Point Clip Instructions */ +GEN_OPIVV_NARROW_TRANS(vnclipu_vv) +GEN_OPIVV_NARROW_TRANS(vnclip_vv) +GEN_OPIVX_NARROW_TRANS(vnclipu_vx) +GEN_OPIVX_NARROW_TRANS(vnclip_vx) +GEN_OPIVI_NARROW_TRANS(vnclipu_vi, 1, vnclipu_vx) +GEN_OPIVI_NARROW_TRANS(vnclip_vi, 1, vnclip_vx) + +/* + *** Vector Float Point Arithmetic Instructions + */ +/* Vector Single-Width Floating-Point Add/Subtract Instructions */ + +/* + * If the current SEW does not correspond to a supported IEEE floating-point + * type, an illegal instruction exception is raised. + */ +static bool opfvv_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_overlap_mask(s, a->rd, a->vm, false) && + vext_check_reg(s, a->rd, false) && + vext_check_reg(s, a->rs2, false) && + vext_check_reg(s, a->rs1, false) && + (s->sew != 0)); +} + +/* OPFVV without GVEC IR */ +#define GEN_OPFVV_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[3] = { \ + gen_helper_##NAME##_h, \ + gen_helper_##NAME##_w, \ + gen_helper_##NAME##_d, \ + }; \ + TCGLabel *over = gen_new_label(); \ + gen_set_rm(s, 7); \ + tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ + \ + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ + data = FIELD_DP32(data, VDATA, VM, a->vm); \ + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ + 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->vlen / 8, s->vlen / 8, data, \ + fns[s->sew - 1]); \ + gen_set_label(over); \ + return true; \ + } \ + return false; \ +} +GEN_OPFVV_TRANS(vfadd_vv, opfvv_check) +GEN_OPFVV_TRANS(vfsub_vv, opfvv_check) + +typedef void gen_helper_opfvf(TCGv_ptr, TCGv_ptr, TCGv_i64, TCGv_ptr, + TCGv_env, TCGv_i32); + +static bool opfvf_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, + uint32_t data, gen_helper_opfvf *fn, DisasContext *s) +{ + TCGv_ptr dest, src2, mask; + TCGv_i32 desc; + + TCGLabel *over = gen_new_label(); + tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); + + dest = tcg_temp_new_ptr(); + mask = tcg_temp_new_ptr(); + src2 = tcg_temp_new_ptr(); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + + tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, vd)); + tcg_gen_addi_ptr(src2, cpu_env, vreg_ofs(s, vs2)); + tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0)); + + fn(dest, mask, cpu_fpr[rs1], src2, cpu_env, desc); + + tcg_temp_free_ptr(dest); + tcg_temp_free_ptr(mask); + tcg_temp_free_ptr(src2); + gen_set_label(over); + return true; +} + +static bool opfvf_check(DisasContext *s, arg_rmrr *a) +{ +/* + * If the current SEW does not correspond to a supported IEEE floating-point + * type, an illegal instruction exception is raised + */ + return (vext_check_isa_ill(s) && + vext_check_overlap_mask(s, a->rd, a->vm, false) && + vext_check_reg(s, a->rd, false) && + vext_check_reg(s, a->rs2, false) && + (s->sew != 0)); +} + +/* OPFVF without GVEC IR */ +#define GEN_OPFVF_TRANS(NAME, CHECK) \ +static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ +{ \ + if (CHECK(s, a)) { \ + uint32_t data = 0; \ + static gen_helper_opfvf *const fns[3] = { \ + gen_helper_##NAME##_h, \ + gen_helper_##NAME##_w, \ + gen_helper_##NAME##_d, \ + }; \ + gen_set_rm(s, 7); \ + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ + data = FIELD_DP32(data, VDATA, VM, a->vm); \ + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ + return opfvf_trans(a->rd, a->rs1, a->rs2, data, \ + fns[s->sew - 1], s); \ + } \ + return false; \ +} + +GEN_OPFVF_TRANS(vfadd_vf, opfvf_check) +GEN_OPFVF_TRANS(vfsub_vf, opfvf_check) +GEN_OPFVF_TRANS(vfrsub_vf, opfvf_check) + +/* Vector Widening Floating-Point Add/Subtract Instructions */ +static bool opfvv_widen_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_overlap_mask(s, a->rd, a->vm, true) && + vext_check_reg(s, a->rd, true) && + vext_check_reg(s, a->rs2, false) && + vext_check_reg(s, a->rs1, false) && + vext_check_overlap_group(a->rd, 2 << s->lmul, a->rs2, + 1 << s->lmul) && + vext_check_overlap_group(a->rd, 2 << s->lmul, a->rs1, + 1 << s->lmul) && + (s->lmul < 0x3) && (s->sew < 0x3) && (s->sew != 0)); +} + +/* OPFVV with WIDEN */ +#define GEN_OPFVV_WIDEN_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[2] = { \ + gen_helper_##NAME##_h, gen_helper_##NAME##_w, \ + }; \ + TCGLabel *over = gen_new_label(); \ + gen_set_rm(s, 7); \ + tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ + \ + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ + data = FIELD_DP32(data, VDATA, VM, a->vm); \ + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ + 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->vlen / 8, s->vlen / 8, data, \ + fns[s->sew - 1]); \ + gen_set_label(over); \ + return true; \ + } \ + return false; \ +} + +GEN_OPFVV_WIDEN_TRANS(vfwadd_vv, opfvv_widen_check) +GEN_OPFVV_WIDEN_TRANS(vfwsub_vv, opfvv_widen_check) + +static bool opfvf_widen_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_overlap_mask(s, a->rd, a->vm, true) && + vext_check_reg(s, a->rd, true) && + vext_check_reg(s, a->rs2, false) && + vext_check_overlap_group(a->rd, 2 << s->lmul, a->rs2, + 1 << s->lmul) && + (s->lmul < 0x3) && (s->sew < 0x3) && (s->sew != 0)); +} + +/* OPFVF with WIDEN */ +#define GEN_OPFVF_WIDEN_TRANS(NAME) \ +static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ +{ \ + if (opfvf_widen_check(s, a)) { \ + uint32_t data = 0; \ + static gen_helper_opfvf *const fns[2] = { \ + gen_helper_##NAME##_h, gen_helper_##NAME##_w, \ + }; \ + gen_set_rm(s, 7); \ + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ + data = FIELD_DP32(data, VDATA, VM, a->vm); \ + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ + return opfvf_trans(a->rd, a->rs1, a->rs2, data, \ + fns[s->sew - 1], s); \ + } \ + return false; \ +} + +GEN_OPFVF_WIDEN_TRANS(vfwadd_vf) +GEN_OPFVF_WIDEN_TRANS(vfwsub_vf) + +static bool opfwv_widen_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_overlap_mask(s, a->rd, a->vm, true) && + vext_check_reg(s, a->rd, true) && + vext_check_reg(s, a->rs2, true) && + vext_check_reg(s, a->rs1, false) && + vext_check_overlap_group(a->rd, 2 << s->lmul, a->rs1, + 1 << s->lmul) && + (s->lmul < 0x3) && (s->sew < 0x3) && (s->sew != 0)); +} + +/* WIDEN OPFVV with WIDEN */ +#define GEN_OPFWV_WIDEN_TRANS(NAME) \ +static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ +{ \ + if (opfwv_widen_check(s, a)) { \ + uint32_t data = 0; \ + static gen_helper_gvec_4_ptr * const fns[2] = { \ + gen_helper_##NAME##_h, gen_helper_##NAME##_w, \ + }; \ + TCGLabel *over = gen_new_label(); \ + gen_set_rm(s, 7); \ + tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ + \ + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ + data = FIELD_DP32(data, VDATA, VM, a->vm); \ + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ + 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->vlen / 8, s->vlen / 8, data, \ + fns[s->sew - 1]); \ + gen_set_label(over); \ + return true; \ + } \ + return false; \ +} + +GEN_OPFWV_WIDEN_TRANS(vfwadd_wv) +GEN_OPFWV_WIDEN_TRANS(vfwsub_wv) + +static bool opfwf_widen_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_overlap_mask(s, a->rd, a->vm, true) && + vext_check_reg(s, a->rd, true) && + vext_check_reg(s, a->rs2, true) && + (s->lmul < 0x3) && (s->sew < 0x3) && (s->sew != 0)); +} + +/* WIDEN OPFVF with WIDEN */ +#define GEN_OPFWF_WIDEN_TRANS(NAME) \ +static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ +{ \ + if (opfwf_widen_check(s, a)) { \ + uint32_t data = 0; \ + static gen_helper_opfvf *const fns[2] = { \ + gen_helper_##NAME##_h, gen_helper_##NAME##_w, \ + }; \ + gen_set_rm(s, 7); \ + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ + data = FIELD_DP32(data, VDATA, VM, a->vm); \ + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ + return opfvf_trans(a->rd, a->rs1, a->rs2, data, \ + fns[s->sew - 1], s); \ + } \ + return false; \ +} + +GEN_OPFWF_WIDEN_TRANS(vfwadd_wf) +GEN_OPFWF_WIDEN_TRANS(vfwsub_wf) + +/* Vector Single-Width Floating-Point Multiply/Divide Instructions */ +GEN_OPFVV_TRANS(vfmul_vv, opfvv_check) +GEN_OPFVV_TRANS(vfdiv_vv, opfvv_check) +GEN_OPFVF_TRANS(vfmul_vf, opfvf_check) +GEN_OPFVF_TRANS(vfdiv_vf, opfvf_check) +GEN_OPFVF_TRANS(vfrdiv_vf, opfvf_check) + +/* Vector Widening Floating-Point Multiply */ +GEN_OPFVV_WIDEN_TRANS(vfwmul_vv, opfvv_widen_check) +GEN_OPFVF_WIDEN_TRANS(vfwmul_vf) + +/* Vector Single-Width Floating-Point Fused Multiply-Add Instructions */ +GEN_OPFVV_TRANS(vfmacc_vv, opfvv_check) +GEN_OPFVV_TRANS(vfnmacc_vv, opfvv_check) +GEN_OPFVV_TRANS(vfmsac_vv, opfvv_check) +GEN_OPFVV_TRANS(vfnmsac_vv, opfvv_check) +GEN_OPFVV_TRANS(vfmadd_vv, opfvv_check) +GEN_OPFVV_TRANS(vfnmadd_vv, opfvv_check) +GEN_OPFVV_TRANS(vfmsub_vv, opfvv_check) +GEN_OPFVV_TRANS(vfnmsub_vv, opfvv_check) +GEN_OPFVF_TRANS(vfmacc_vf, opfvf_check) +GEN_OPFVF_TRANS(vfnmacc_vf, opfvf_check) +GEN_OPFVF_TRANS(vfmsac_vf, opfvf_check) +GEN_OPFVF_TRANS(vfnmsac_vf, opfvf_check) +GEN_OPFVF_TRANS(vfmadd_vf, opfvf_check) +GEN_OPFVF_TRANS(vfnmadd_vf, opfvf_check) +GEN_OPFVF_TRANS(vfmsub_vf, opfvf_check) +GEN_OPFVF_TRANS(vfnmsub_vf, opfvf_check) + +/* Vector Widening Floating-Point Fused Multiply-Add Instructions */ +GEN_OPFVV_WIDEN_TRANS(vfwmacc_vv, opfvv_widen_check) +GEN_OPFVV_WIDEN_TRANS(vfwnmacc_vv, opfvv_widen_check) +GEN_OPFVV_WIDEN_TRANS(vfwmsac_vv, opfvv_widen_check) +GEN_OPFVV_WIDEN_TRANS(vfwnmsac_vv, opfvv_widen_check) +GEN_OPFVF_WIDEN_TRANS(vfwmacc_vf) +GEN_OPFVF_WIDEN_TRANS(vfwnmacc_vf) +GEN_OPFVF_WIDEN_TRANS(vfwmsac_vf) +GEN_OPFVF_WIDEN_TRANS(vfwnmsac_vf) + +/* Vector Floating-Point Square-Root Instruction */ + +/* + * If the current SEW does not correspond to a supported IEEE floating-point + * type, an illegal instruction exception is raised + */ +static bool opfv_check(DisasContext *s, arg_rmr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_overlap_mask(s, a->rd, a->vm, false) && + vext_check_reg(s, a->rd, false) && + vext_check_reg(s, a->rs2, false) && + (s->sew != 0)); +} + +#define GEN_OPFV_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[3] = { \ + gen_helper_##NAME##_h, \ + gen_helper_##NAME##_w, \ + gen_helper_##NAME##_d, \ + }; \ + TCGLabel *over = gen_new_label(); \ + gen_set_rm(s, 7); \ + tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ + \ + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ + data = FIELD_DP32(data, VDATA, VM, a->vm); \ + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ + tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ + vreg_ofs(s, a->rs2), cpu_env, \ + s->vlen / 8, s->vlen / 8, data, \ + fns[s->sew - 1]); \ + gen_set_label(over); \ + return true; \ + } \ + return false; \ +} + +GEN_OPFV_TRANS(vfsqrt_v, opfv_check) + +/* Vector Floating-Point MIN/MAX Instructions */ +GEN_OPFVV_TRANS(vfmin_vv, opfvv_check) +GEN_OPFVV_TRANS(vfmax_vv, opfvv_check) +GEN_OPFVF_TRANS(vfmin_vf, opfvf_check) +GEN_OPFVF_TRANS(vfmax_vf, opfvf_check) + +/* Vector Floating-Point Sign-Injection Instructions */ +GEN_OPFVV_TRANS(vfsgnj_vv, opfvv_check) +GEN_OPFVV_TRANS(vfsgnjn_vv, opfvv_check) +GEN_OPFVV_TRANS(vfsgnjx_vv, opfvv_check) +GEN_OPFVF_TRANS(vfsgnj_vf, opfvf_check) +GEN_OPFVF_TRANS(vfsgnjn_vf, opfvf_check) +GEN_OPFVF_TRANS(vfsgnjx_vf, opfvf_check) + +/* Vector Floating-Point Compare Instructions */ +static bool opfvv_cmp_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_reg(s, a->rs2, false) && + vext_check_reg(s, a->rs1, false) && + (s->sew != 0) && + ((vext_check_overlap_group(a->rd, 1, a->rs1, 1 << s->lmul) && + vext_check_overlap_group(a->rd, 1, a->rs2, 1 << s->lmul)) || + (s->lmul == 0))); +} + +GEN_OPFVV_TRANS(vmfeq_vv, opfvv_cmp_check) +GEN_OPFVV_TRANS(vmfne_vv, opfvv_cmp_check) +GEN_OPFVV_TRANS(vmflt_vv, opfvv_cmp_check) +GEN_OPFVV_TRANS(vmfle_vv, opfvv_cmp_check) +GEN_OPFVV_TRANS(vmford_vv, opfvv_cmp_check) + +static bool opfvf_cmp_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_reg(s, a->rs2, false) && + (s->sew != 0) && + (vext_check_overlap_group(a->rd, 1, a->rs2, 1 << s->lmul) || + (s->lmul == 0))); +} + +GEN_OPFVF_TRANS(vmfeq_vf, opfvf_cmp_check) +GEN_OPFVF_TRANS(vmfne_vf, opfvf_cmp_check) +GEN_OPFVF_TRANS(vmflt_vf, opfvf_cmp_check) +GEN_OPFVF_TRANS(vmfle_vf, opfvf_cmp_check) +GEN_OPFVF_TRANS(vmfgt_vf, opfvf_cmp_check) +GEN_OPFVF_TRANS(vmfge_vf, opfvf_cmp_check) +GEN_OPFVF_TRANS(vmford_vf, opfvf_cmp_check) + +/* Vector Floating-Point Classify Instruction */ +GEN_OPFV_TRANS(vfclass_v, opfv_check) + +/* Vector Floating-Point Merge Instruction */ +GEN_OPFVF_TRANS(vfmerge_vfm, opfvf_check) + +static bool trans_vfmv_v_f(DisasContext *s, arg_vfmv_v_f *a) +{ + if (vext_check_isa_ill(s) && + vext_check_reg(s, a->rd, false) && + (s->sew != 0)) { + + if (s->vl_eq_vlmax) { + tcg_gen_gvec_dup_i64(s->sew, vreg_ofs(s, a->rd), + MAXSZ(s), MAXSZ(s), cpu_fpr[a->rs1]); + } else { + TCGv_ptr dest; + TCGv_i32 desc; + uint32_t data = FIELD_DP32(0, VDATA, LMUL, s->lmul); + static gen_helper_vmv_vx * const fns[3] = { + gen_helper_vmv_v_x_h, + 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); + + dest = tcg_temp_new_ptr(); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, a->rd)); + fns[s->sew - 1](dest, cpu_fpr[a->rs1], cpu_env, desc); + + tcg_temp_free_ptr(dest); + gen_set_label(over); + } + return true; + } + return false; +} + +/* Single-Width Floating-Point/Integer Type-Convert Instructions */ +GEN_OPFV_TRANS(vfcvt_xu_f_v, opfv_check) +GEN_OPFV_TRANS(vfcvt_x_f_v, opfv_check) +GEN_OPFV_TRANS(vfcvt_f_xu_v, opfv_check) +GEN_OPFV_TRANS(vfcvt_f_x_v, opfv_check) + +/* Widening Floating-Point/Integer Type-Convert Instructions */ + +/* + * If the current SEW does not correspond to a supported IEEE floating-point + * type, an illegal instruction exception is raised + */ +static bool opfv_widen_check(DisasContext *s, arg_rmr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_overlap_mask(s, a->rd, a->vm, true) && + vext_check_reg(s, a->rd, true) && + vext_check_reg(s, a->rs2, false) && + vext_check_overlap_group(a->rd, 2 << s->lmul, a->rs2, + 1 << s->lmul) && + (s->lmul < 0x3) && (s->sew < 0x3) && (s->sew != 0)); +} + +#define GEN_OPFV_WIDEN_TRANS(NAME) \ +static bool trans_##NAME(DisasContext *s, arg_rmr *a) \ +{ \ + if (opfv_widen_check(s, a)) { \ + uint32_t data = 0; \ + static gen_helper_gvec_3_ptr * const fns[2] = { \ + gen_helper_##NAME##_h, \ + gen_helper_##NAME##_w, \ + }; \ + TCGLabel *over = gen_new_label(); \ + gen_set_rm(s, 7); \ + tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ + \ + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ + data = FIELD_DP32(data, VDATA, VM, a->vm); \ + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ + tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ + vreg_ofs(s, a->rs2), cpu_env, \ + s->vlen / 8, s->vlen / 8, data, \ + fns[s->sew - 1]); \ + gen_set_label(over); \ + return true; \ + } \ + return false; \ +} + +GEN_OPFV_WIDEN_TRANS(vfwcvt_xu_f_v) +GEN_OPFV_WIDEN_TRANS(vfwcvt_x_f_v) +GEN_OPFV_WIDEN_TRANS(vfwcvt_f_xu_v) +GEN_OPFV_WIDEN_TRANS(vfwcvt_f_x_v) +GEN_OPFV_WIDEN_TRANS(vfwcvt_f_f_v) + +/* Narrowing Floating-Point/Integer Type-Convert Instructions */ + +/* + * If the current SEW does not correspond to a supported IEEE floating-point + * type, an illegal instruction exception is raised + */ +static bool opfv_narrow_check(DisasContext *s, arg_rmr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_overlap_mask(s, a->rd, a->vm, false) && + vext_check_reg(s, a->rd, false) && + vext_check_reg(s, a->rs2, true) && + vext_check_overlap_group(a->rd, 1 << s->lmul, a->rs2, + 2 << s->lmul) && + (s->lmul < 0x3) && (s->sew < 0x3) && (s->sew != 0)); +} + +#define GEN_OPFV_NARROW_TRANS(NAME) \ +static bool trans_##NAME(DisasContext *s, arg_rmr *a) \ +{ \ + if (opfv_narrow_check(s, a)) { \ + uint32_t data = 0; \ + static gen_helper_gvec_3_ptr * const fns[2] = { \ + gen_helper_##NAME##_h, \ + gen_helper_##NAME##_w, \ + }; \ + TCGLabel *over = gen_new_label(); \ + gen_set_rm(s, 7); \ + tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ + \ + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ + data = FIELD_DP32(data, VDATA, VM, a->vm); \ + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ + tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ + vreg_ofs(s, a->rs2), cpu_env, \ + s->vlen / 8, s->vlen / 8, data, \ + fns[s->sew - 1]); \ + gen_set_label(over); \ + return true; \ + } \ + return false; \ +} + +GEN_OPFV_NARROW_TRANS(vfncvt_xu_f_v) +GEN_OPFV_NARROW_TRANS(vfncvt_x_f_v) +GEN_OPFV_NARROW_TRANS(vfncvt_f_xu_v) +GEN_OPFV_NARROW_TRANS(vfncvt_f_x_v) +GEN_OPFV_NARROW_TRANS(vfncvt_f_f_v) + +/* + *** Vector Reduction Operations + */ +/* Vector Single-Width Integer Reduction Instructions */ +static bool reduction_check(DisasContext *s, arg_rmrr *a) +{ + return vext_check_isa_ill(s) && vext_check_reg(s, a->rs2, false); +} + +GEN_OPIVV_TRANS(vredsum_vs, reduction_check) +GEN_OPIVV_TRANS(vredmaxu_vs, reduction_check) +GEN_OPIVV_TRANS(vredmax_vs, reduction_check) +GEN_OPIVV_TRANS(vredminu_vs, reduction_check) +GEN_OPIVV_TRANS(vredmin_vs, reduction_check) +GEN_OPIVV_TRANS(vredand_vs, reduction_check) +GEN_OPIVV_TRANS(vredor_vs, reduction_check) +GEN_OPIVV_TRANS(vredxor_vs, reduction_check) + +/* Vector Widening Integer Reduction Instructions */ +GEN_OPIVV_WIDEN_TRANS(vwredsum_vs, reduction_check) +GEN_OPIVV_WIDEN_TRANS(vwredsumu_vs, reduction_check) + +/* Vector Single-Width Floating-Point Reduction Instructions */ +GEN_OPFVV_TRANS(vfredsum_vs, reduction_check) +GEN_OPFVV_TRANS(vfredmax_vs, reduction_check) +GEN_OPFVV_TRANS(vfredmin_vs, reduction_check) + +/* Vector Widening Floating-Point Reduction Instructions */ +GEN_OPFVV_WIDEN_TRANS(vfwredsum_vs, reduction_check) + +/* + *** Vector Mask Operations + */ + +/* Vector Mask-Register Logical Instructions */ +#define GEN_MM_TRANS(NAME) \ +static bool trans_##NAME(DisasContext *s, arg_r *a) \ +{ \ + if (vext_check_isa_ill(s)) { \ + 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); \ + \ + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ + 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->vlen / 8, s->vlen / 8, data, fn); \ + gen_set_label(over); \ + return true; \ + } \ + return false; \ +} + +GEN_MM_TRANS(vmand_mm) +GEN_MM_TRANS(vmnand_mm) +GEN_MM_TRANS(vmandnot_mm) +GEN_MM_TRANS(vmxor_mm) +GEN_MM_TRANS(vmor_mm) +GEN_MM_TRANS(vmnor_mm) +GEN_MM_TRANS(vmornot_mm) +GEN_MM_TRANS(vmxnor_mm) + +/* Vector mask population count vmpopc */ +static bool trans_vmpopc_m(DisasContext *s, arg_rmr *a) +{ + if (vext_check_isa_ill(s)) { + TCGv_ptr src2, mask; + TCGv dst; + TCGv_i32 desc; + uint32_t data = 0; + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); + data = FIELD_DP32(data, VDATA, VM, a->vm); + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); + + mask = tcg_temp_new_ptr(); + src2 = tcg_temp_new_ptr(); + dst = dest_gpr(s, a->rd); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + + tcg_gen_addi_ptr(src2, cpu_env, vreg_ofs(s, a->rs2)); + tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0)); + + gen_helper_vmpopc_m(dst, mask, src2, cpu_env, desc); + gen_set_gpr(s, a->rd, dst); + + tcg_temp_free_ptr(mask); + tcg_temp_free_ptr(src2); + return true; + } + return false; +} + +/* vmfirst find-first-set mask bit */ +static bool trans_vmfirst_m(DisasContext *s, arg_rmr *a) +{ + if (vext_check_isa_ill(s)) { + TCGv_ptr src2, mask; + TCGv dst; + TCGv_i32 desc; + uint32_t data = 0; + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); + data = FIELD_DP32(data, VDATA, VM, a->vm); + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); + + mask = tcg_temp_new_ptr(); + src2 = tcg_temp_new_ptr(); + dst = dest_gpr(s, a->rd); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + + tcg_gen_addi_ptr(src2, cpu_env, vreg_ofs(s, a->rs2)); + tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0)); + + gen_helper_vmfirst_m(dst, mask, src2, cpu_env, desc); + gen_set_gpr(s, a->rd, dst); + + tcg_temp_free_ptr(mask); + tcg_temp_free_ptr(src2); + return true; + } + return false; +} + +/* vmsbf.m set-before-first mask bit */ +/* vmsif.m set-includ-first mask bit */ +/* vmsof.m set-only-first mask bit */ +#define GEN_M_TRANS(NAME) \ +static bool trans_##NAME(DisasContext *s, arg_rmr *a) \ +{ \ + if (vext_check_isa_ill(s)) { \ + uint32_t data = 0; \ + gen_helper_gvec_3_ptr *fn = gen_helper_##NAME; \ + TCGLabel *over = gen_new_label(); \ + tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ + \ + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ + data = FIELD_DP32(data, VDATA, VM, a->vm); \ + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ + tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), \ + vreg_ofs(s, 0), vreg_ofs(s, a->rs2), \ + cpu_env, s->vlen / 8, s->vlen / 8, \ + data, fn); \ + gen_set_label(over); \ + return true; \ + } \ + return false; \ +} + +GEN_M_TRANS(vmsbf_m) +GEN_M_TRANS(vmsif_m) +GEN_M_TRANS(vmsof_m) + +/* Vector Iota Instruction */ +static bool trans_viota_m(DisasContext *s, arg_viota_m *a) +{ + if (vext_check_isa_ill(s) && + vext_check_reg(s, a->rd, false) && + vext_check_overlap_group(a->rd, 1 << s->lmul, a->rs2, 1) && + (a->vm != 0 || a->rd != 0)) { + uint32_t data = 0; + TCGLabel *over = gen_new_label(); + tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); + + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); + data = FIELD_DP32(data, VDATA, VM, a->vm); + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); + static gen_helper_gvec_3_ptr * const fns[4] = { + gen_helper_viota_m_b, gen_helper_viota_m_h, + gen_helper_viota_m_w, gen_helper_viota_m_d, + }; + tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), + vreg_ofs(s, a->rs2), cpu_env, + s->vlen / 8, s->vlen / 8, data, fns[s->sew]); + gen_set_label(over); + return true; + } + return false; +} + +/* Vector Element Index Instruction */ +static bool trans_vid_v(DisasContext *s, arg_vid_v *a) +{ + if (vext_check_isa_ill(s) && + vext_check_reg(s, a->rd, false) && + vext_check_overlap_mask(s, a->rd, a->vm, false)) { + uint32_t data = 0; + TCGLabel *over = gen_new_label(); + tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); + + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); + data = FIELD_DP32(data, VDATA, VM, a->vm); + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); + static gen_helper_gvec_2_ptr * const fns[4] = { + gen_helper_vid_v_b, gen_helper_vid_v_h, + gen_helper_vid_v_w, gen_helper_vid_v_d, + }; + tcg_gen_gvec_2_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), + cpu_env, s->vlen / 8, s->vlen / 8, + data, fns[s->sew]); + gen_set_label(over); + return true; + } + return false; +} + +/* + *** Vector Permutation Instructions + */ + +/* Integer Extract Instruction */ + +static void load_element(TCGv_i64 dest, TCGv_ptr base, + int ofs, int sew) +{ + switch (sew) { + case MO_8: + tcg_gen_ld8u_i64(dest, base, ofs); + break; + case MO_16: + tcg_gen_ld16u_i64(dest, base, ofs); + break; + case MO_32: + tcg_gen_ld32u_i64(dest, base, ofs); + break; + case MO_64: + tcg_gen_ld_i64(dest, base, ofs); + break; + default: + g_assert_not_reached(); + break; + } +} + +/* offset of the idx element with base regsiter r */ +static uint32_t endian_ofs(DisasContext *s, int r, int idx) +{ +#ifdef HOST_WORDS_BIGENDIAN + return vreg_ofs(s, r) + ((idx ^ (7 >> s->sew)) << s->sew); +#else + return vreg_ofs(s, r) + (idx << s->sew); +#endif +} + +/* adjust the index according to the endian */ +static void endian_adjust(TCGv_i32 ofs, int sew) +{ +#ifdef HOST_WORDS_BIGENDIAN + tcg_gen_xori_i32(ofs, ofs, 7 >> sew); +#endif +} + +/* Load idx >= VLMAX ? 0 : vreg[idx] */ +static void vec_element_loadx(DisasContext *s, TCGv_i64 dest, + int vreg, TCGv idx, int vlmax) +{ + TCGv_i32 ofs = tcg_temp_new_i32(); + TCGv_ptr base = tcg_temp_new_ptr(); + TCGv_i64 t_idx = tcg_temp_new_i64(); + TCGv_i64 t_vlmax, t_zero; + + /* + * Mask the index to the length so that we do + * not produce an out-of-range load. + */ + tcg_gen_trunc_tl_i32(ofs, idx); + tcg_gen_andi_i32(ofs, ofs, vlmax - 1); + + /* Convert the index to an offset. */ + endian_adjust(ofs, s->sew); + tcg_gen_shli_i32(ofs, ofs, s->sew); + + /* Convert the index to a pointer. */ + tcg_gen_ext_i32_ptr(base, ofs); + tcg_gen_add_ptr(base, base, cpu_env); + + /* Perform the load. */ + load_element(dest, base, + vreg_ofs(s, vreg), s->sew); + tcg_temp_free_ptr(base); + tcg_temp_free_i32(ofs); + + /* Flush out-of-range indexing to zero. */ + t_vlmax = tcg_constant_i64(vlmax); + t_zero = tcg_constant_i64(0); + tcg_gen_extu_tl_i64(t_idx, idx); + + tcg_gen_movcond_i64(TCG_COND_LTU, dest, t_idx, + t_vlmax, dest, t_zero); + + tcg_temp_free_i64(t_idx); +} + +static void vec_element_loadi(DisasContext *s, TCGv_i64 dest, + int vreg, int idx) +{ + load_element(dest, cpu_env, endian_ofs(s, vreg, idx), s->sew); +} + +static bool trans_vext_x_v(DisasContext *s, arg_r *a) +{ + TCGv_i64 tmp = tcg_temp_new_i64(); + TCGv dest = dest_gpr(s, a->rd); + + if (a->rs1 == 0) { + /* Special case vmv.x.s rd, vs2. */ + vec_element_loadi(s, tmp, a->rs2, 0); + } else { + /* This instruction ignores LMUL and vector register groups */ + int vlmax = s->vlen >> (3 + s->sew); + vec_element_loadx(s, tmp, a->rs2, cpu_gpr[a->rs1], vlmax); + } + + tcg_gen_trunc_i64_tl(dest, tmp); + gen_set_gpr(s, a->rd, dest); + + tcg_temp_free_i64(tmp); + return true; +} + +/* Integer Scalar Move Instruction */ + +static void store_element(TCGv_i64 val, TCGv_ptr base, + int ofs, int sew) +{ + switch (sew) { + case MO_8: + tcg_gen_st8_i64(val, base, ofs); + break; + case MO_16: + tcg_gen_st16_i64(val, base, ofs); + break; + case MO_32: + tcg_gen_st32_i64(val, base, ofs); + break; + case MO_64: + tcg_gen_st_i64(val, base, ofs); + break; + default: + g_assert_not_reached(); + break; + } +} + +/* + * Store vreg[idx] = val. + * The index must be in range of VLMAX. + */ +static void vec_element_storei(DisasContext *s, int vreg, + int idx, TCGv_i64 val) +{ + store_element(val, cpu_env, endian_ofs(s, vreg, idx), s->sew); +} + +/* vmv.s.x vd, rs1 # vd[0] = rs1 */ +static bool trans_vmv_s_x(DisasContext *s, arg_vmv_s_x *a) +{ + if (vext_check_isa_ill(s)) { + /* This instruction ignores LMUL and vector register groups */ + int maxsz = s->vlen >> 3; + TCGv_i64 t1; + TCGLabel *over = gen_new_label(); + + tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); + tcg_gen_gvec_dup_imm(SEW64, vreg_ofs(s, a->rd), maxsz, maxsz, 0); + if (a->rs1 == 0) { + goto done; + } + + t1 = tcg_temp_new_i64(); + tcg_gen_extu_tl_i64(t1, cpu_gpr[a->rs1]); + vec_element_storei(s, a->rd, 0, t1); + tcg_temp_free_i64(t1); + done: + gen_set_label(over); + return true; + } + return false; +} + +/* Floating-Point Scalar Move Instructions */ +static bool trans_vfmv_f_s(DisasContext *s, arg_vfmv_f_s *a) +{ + if (!s->vill && has_ext(s, RVF) && + (s->mstatus_fs != 0) && (s->sew != 0)) { + unsigned int len = 8 << s->sew; + + vec_element_loadi(s, cpu_fpr[a->rd], a->rs2, 0); + if (len < 64) { + tcg_gen_ori_i64(cpu_fpr[a->rd], cpu_fpr[a->rd], + MAKE_64BIT_MASK(len, 64 - len)); + } + + mark_fs_dirty(s); + return true; + } + return false; +} + +/* vfmv.s.f vd, rs1 # vd[0] = rs1 (vs2=0) */ +static bool trans_vfmv_s_f(DisasContext *s, arg_vfmv_s_f *a) +{ + if (!s->vill && has_ext(s, RVF) && (s->sew != 0)) { + TCGv_i64 t1; + /* The instructions ignore LMUL and vector register group. */ + uint32_t vlmax = s->vlen >> 3; + + /* if vl == 0, skip vector register write back */ + TCGLabel *over = gen_new_label(); + tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); + + /* zeroed all elements */ + tcg_gen_gvec_dup_imm(SEW64, vreg_ofs(s, a->rd), vlmax, vlmax, 0); + + /* NaN-box f[rs1] as necessary for SEW */ + t1 = tcg_temp_new_i64(); + if (s->sew == MO_64 && !has_ext(s, RVD)) { + tcg_gen_ori_i64(t1, cpu_fpr[a->rs1], MAKE_64BIT_MASK(32, 32)); + } else { + tcg_gen_mov_i64(t1, cpu_fpr[a->rs1]); + } + vec_element_storei(s, a->rd, 0, t1); + tcg_temp_free_i64(t1); + gen_set_label(over); + return true; + } + return false; +} + +/* Vector Slide Instructions */ +static bool slideup_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_overlap_mask(s, a->rd, a->vm, true) && + vext_check_reg(s, a->rd, false) && + vext_check_reg(s, a->rs2, false) && + (a->rd != a->rs2)); +} + +GEN_OPIVX_TRANS(vslideup_vx, slideup_check) +GEN_OPIVX_TRANS(vslide1up_vx, slideup_check) +GEN_OPIVI_TRANS(vslideup_vi, 1, vslideup_vx, slideup_check) + +GEN_OPIVX_TRANS(vslidedown_vx, opivx_check) +GEN_OPIVX_TRANS(vslide1down_vx, opivx_check) +GEN_OPIVI_TRANS(vslidedown_vi, 1, vslidedown_vx, opivx_check) + +/* Vector Register Gather Instruction */ +static bool vrgather_vv_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_overlap_mask(s, a->rd, a->vm, true) && + vext_check_reg(s, a->rd, false) && + vext_check_reg(s, a->rs1, false) && + vext_check_reg(s, a->rs2, false) && + (a->rd != a->rs2) && (a->rd != a->rs1)); +} + +GEN_OPIVV_TRANS(vrgather_vv, vrgather_vv_check) + +static bool vrgather_vx_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_overlap_mask(s, a->rd, a->vm, true) && + vext_check_reg(s, a->rd, false) && + vext_check_reg(s, a->rs2, false) && + (a->rd != a->rs2)); +} + +/* vrgather.vx vd, vs2, rs1, vm # vd[i] = (x[rs1] >= VLMAX) ? 0 : vs2[rs1] */ +static bool trans_vrgather_vx(DisasContext *s, arg_rmrr *a) +{ + if (!vrgather_vx_check(s, a)) { + return false; + } + + if (a->vm && s->vl_eq_vlmax) { + int vlmax = s->vlen / s->mlen; + TCGv_i64 dest = tcg_temp_new_i64(); + + if (a->rs1 == 0) { + vec_element_loadi(s, dest, a->rs2, 0); + } else { + vec_element_loadx(s, dest, a->rs2, cpu_gpr[a->rs1], vlmax); + } + + tcg_gen_gvec_dup_i64(s->sew, vreg_ofs(s, a->rd), + MAXSZ(s), MAXSZ(s), dest); + tcg_temp_free_i64(dest); + } else { + static gen_helper_opivx * const fns[4] = { + gen_helper_vrgather_vx_b, gen_helper_vrgather_vx_h, + gen_helper_vrgather_vx_w, gen_helper_vrgather_vx_d + }; + return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fns[s->sew], s); + } + return true; +} + +/* vrgather.vi vd, vs2, imm, vm # vd[i] = (imm >= VLMAX) ? 0 : vs2[imm] */ +static bool trans_vrgather_vi(DisasContext *s, arg_rmrr *a) +{ + if (!vrgather_vx_check(s, a)) { + return false; + } + + if (a->vm && s->vl_eq_vlmax) { + if (a->rs1 >= s->vlen / s->mlen) { + tcg_gen_gvec_dup_imm(SEW64, vreg_ofs(s, a->rd), + MAXSZ(s), MAXSZ(s), 0); + } else { + tcg_gen_gvec_dup_mem(s->sew, vreg_ofs(s, a->rd), + endian_ofs(s, a->rs2, a->rs1), + MAXSZ(s), MAXSZ(s)); + } + } else { + static gen_helper_opivx * const fns[4] = { + gen_helper_vrgather_vx_b, gen_helper_vrgather_vx_h, + gen_helper_vrgather_vx_w, gen_helper_vrgather_vx_d + }; + return opivi_trans(a->rd, a->rs1, a->rs2, a->vm, fns[s->sew], s, 1); + } + return true; +} + +/* Vector Compress Instruction */ +static bool vcompress_vm_check(DisasContext *s, arg_r *a) +{ + return (vext_check_isa_ill(s) && + vext_check_reg(s, a->rd, false) && + vext_check_reg(s, a->rs2, false) && + vext_check_overlap_group(a->rd, 1 << s->lmul, a->rs1, 1) && + (a->rd != a->rs2)); +} + +static bool trans_vcompress_vm(DisasContext *s, arg_r *a) +{ + if (vcompress_vm_check(s, a)) { + uint32_t data = 0; + static gen_helper_gvec_4_ptr * const fns[4] = { + gen_helper_vcompress_vm_b, gen_helper_vcompress_vm_h, + gen_helper_vcompress_vm_w, gen_helper_vcompress_vm_d, + }; + TCGLabel *over = gen_new_label(); + tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); + + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); + 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->vlen / 8, s->vlen / 8, data, + fns[s->sew]); + gen_set_label(over); + return true; + } + return false; +} diff --git a/target/riscv/instmap.h b/target/riscv/instmap.h new file mode 100644 index 000000000..40b6d2b64 --- /dev/null +++ b/target/riscv/instmap.h @@ -0,0 +1,369 @@ +/* + * RISC-V emulation for qemu: Instruction decode helpers + * + * Copyright (c) 2016-2017 Sagar Karandikar, sagark@eecs.berkeley.edu + * + * 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_INSTMAP_H +#define TARGET_RISCV_INSTMAP_H + +#define MASK_OP_MAJOR(op) (op & 0x7F) +enum { + /* rv32i, rv64i, rv32m */ + OPC_RISC_LUI = (0x37), + OPC_RISC_AUIPC = (0x17), + OPC_RISC_JAL = (0x6F), + OPC_RISC_JALR = (0x67), + OPC_RISC_BRANCH = (0x63), + OPC_RISC_LOAD = (0x03), + OPC_RISC_STORE = (0x23), + OPC_RISC_ARITH_IMM = (0x13), + OPC_RISC_ARITH = (0x33), + OPC_RISC_FENCE = (0x0F), + OPC_RISC_SYSTEM = (0x73), + + /* rv64i, rv64m */ + OPC_RISC_ARITH_IMM_W = (0x1B), + OPC_RISC_ARITH_W = (0x3B), + + /* rv32a, rv64a */ + OPC_RISC_ATOMIC = (0x2F), + + /* floating point */ + OPC_RISC_FP_LOAD = (0x7), + OPC_RISC_FP_STORE = (0x27), + + OPC_RISC_FMADD = (0x43), + OPC_RISC_FMSUB = (0x47), + OPC_RISC_FNMSUB = (0x4B), + OPC_RISC_FNMADD = (0x4F), + + OPC_RISC_FP_ARITH = (0x53), +}; + +#define MASK_OP_ARITH(op) (MASK_OP_MAJOR(op) | (op & ((0x7 << 12) | \ + (0x7F << 25)))) +enum { + OPC_RISC_ADD = OPC_RISC_ARITH | (0x0 << 12) | (0x00 << 25), + OPC_RISC_SUB = OPC_RISC_ARITH | (0x0 << 12) | (0x20 << 25), + OPC_RISC_SLL = OPC_RISC_ARITH | (0x1 << 12) | (0x00 << 25), + OPC_RISC_SLT = OPC_RISC_ARITH | (0x2 << 12) | (0x00 << 25), + OPC_RISC_SLTU = OPC_RISC_ARITH | (0x3 << 12) | (0x00 << 25), + OPC_RISC_XOR = OPC_RISC_ARITH | (0x4 << 12) | (0x00 << 25), + OPC_RISC_SRL = OPC_RISC_ARITH | (0x5 << 12) | (0x00 << 25), + OPC_RISC_SRA = OPC_RISC_ARITH | (0x5 << 12) | (0x20 << 25), + OPC_RISC_OR = OPC_RISC_ARITH | (0x6 << 12) | (0x00 << 25), + OPC_RISC_AND = OPC_RISC_ARITH | (0x7 << 12) | (0x00 << 25), + + /* RV64M */ + OPC_RISC_MUL = OPC_RISC_ARITH | (0x0 << 12) | (0x01 << 25), + OPC_RISC_MULH = OPC_RISC_ARITH | (0x1 << 12) | (0x01 << 25), + OPC_RISC_MULHSU = OPC_RISC_ARITH | (0x2 << 12) | (0x01 << 25), + OPC_RISC_MULHU = OPC_RISC_ARITH | (0x3 << 12) | (0x01 << 25), + + OPC_RISC_DIV = OPC_RISC_ARITH | (0x4 << 12) | (0x01 << 25), + OPC_RISC_DIVU = OPC_RISC_ARITH | (0x5 << 12) | (0x01 << 25), + OPC_RISC_REM = OPC_RISC_ARITH | (0x6 << 12) | (0x01 << 25), + OPC_RISC_REMU = OPC_RISC_ARITH | (0x7 << 12) | (0x01 << 25), +}; + + +#define MASK_OP_ARITH_IMM(op) (MASK_OP_MAJOR(op) | (op & (0x7 << 12))) +enum { + OPC_RISC_ADDI = OPC_RISC_ARITH_IMM | (0x0 << 12), + OPC_RISC_SLTI = OPC_RISC_ARITH_IMM | (0x2 << 12), + OPC_RISC_SLTIU = OPC_RISC_ARITH_IMM | (0x3 << 12), + OPC_RISC_XORI = OPC_RISC_ARITH_IMM | (0x4 << 12), + OPC_RISC_ORI = OPC_RISC_ARITH_IMM | (0x6 << 12), + OPC_RISC_ANDI = OPC_RISC_ARITH_IMM | (0x7 << 12), + OPC_RISC_SLLI = OPC_RISC_ARITH_IMM | (0x1 << 12), /* additional part of + IMM */ + OPC_RISC_SHIFT_RIGHT_I = OPC_RISC_ARITH_IMM | (0x5 << 12) /* SRAI, SRLI */ +}; + +#define MASK_OP_BRANCH(op) (MASK_OP_MAJOR(op) | (op & (0x7 << 12))) +enum { + OPC_RISC_BEQ = OPC_RISC_BRANCH | (0x0 << 12), + OPC_RISC_BNE = OPC_RISC_BRANCH | (0x1 << 12), + OPC_RISC_BLT = OPC_RISC_BRANCH | (0x4 << 12), + OPC_RISC_BGE = OPC_RISC_BRANCH | (0x5 << 12), + OPC_RISC_BLTU = OPC_RISC_BRANCH | (0x6 << 12), + OPC_RISC_BGEU = OPC_RISC_BRANCH | (0x7 << 12) +}; + +enum { + OPC_RISC_ADDIW = OPC_RISC_ARITH_IMM_W | (0x0 << 12), + OPC_RISC_SLLIW = OPC_RISC_ARITH_IMM_W | (0x1 << 12), /* additional part of + IMM */ + OPC_RISC_SHIFT_RIGHT_IW = OPC_RISC_ARITH_IMM_W | (0x5 << 12) /* SRAI, SRLI + */ +}; + +enum { + OPC_RISC_ADDW = OPC_RISC_ARITH_W | (0x0 << 12) | (0x00 << 25), + OPC_RISC_SUBW = OPC_RISC_ARITH_W | (0x0 << 12) | (0x20 << 25), + OPC_RISC_SLLW = OPC_RISC_ARITH_W | (0x1 << 12) | (0x00 << 25), + OPC_RISC_SRLW = OPC_RISC_ARITH_W | (0x5 << 12) | (0x00 << 25), + OPC_RISC_SRAW = OPC_RISC_ARITH_W | (0x5 << 12) | (0x20 << 25), + + /* RV64M */ + OPC_RISC_MULW = OPC_RISC_ARITH_W | (0x0 << 12) | (0x01 << 25), + OPC_RISC_DIVW = OPC_RISC_ARITH_W | (0x4 << 12) | (0x01 << 25), + OPC_RISC_DIVUW = OPC_RISC_ARITH_W | (0x5 << 12) | (0x01 << 25), + OPC_RISC_REMW = OPC_RISC_ARITH_W | (0x6 << 12) | (0x01 << 25), + OPC_RISC_REMUW = OPC_RISC_ARITH_W | (0x7 << 12) | (0x01 << 25), +}; + +#define MASK_OP_LOAD(op) (MASK_OP_MAJOR(op) | (op & (0x7 << 12))) +enum { + OPC_RISC_LB = OPC_RISC_LOAD | (0x0 << 12), + OPC_RISC_LH = OPC_RISC_LOAD | (0x1 << 12), + OPC_RISC_LW = OPC_RISC_LOAD | (0x2 << 12), + OPC_RISC_LD = OPC_RISC_LOAD | (0x3 << 12), + OPC_RISC_LBU = OPC_RISC_LOAD | (0x4 << 12), + OPC_RISC_LHU = OPC_RISC_LOAD | (0x5 << 12), + OPC_RISC_LWU = OPC_RISC_LOAD | (0x6 << 12), +}; + +#define MASK_OP_STORE(op) (MASK_OP_MAJOR(op) | (op & (0x7 << 12))) +enum { + OPC_RISC_SB = OPC_RISC_STORE | (0x0 << 12), + OPC_RISC_SH = OPC_RISC_STORE | (0x1 << 12), + OPC_RISC_SW = OPC_RISC_STORE | (0x2 << 12), + OPC_RISC_SD = OPC_RISC_STORE | (0x3 << 12), +}; + +#define MASK_OP_JALR(op) (MASK_OP_MAJOR(op) | (op & (0x7 << 12))) +/* no enum since OPC_RISC_JALR is the actual value */ + +#define MASK_OP_ATOMIC(op) \ + (MASK_OP_MAJOR(op) | (op & ((0x7 << 12) | (0x7F << 25)))) +#define MASK_OP_ATOMIC_NO_AQ_RL_SZ(op) \ + (MASK_OP_MAJOR(op) | (op & (0x1F << 27))) + +enum { + OPC_RISC_LR = OPC_RISC_ATOMIC | (0x02 << 27), + OPC_RISC_SC = OPC_RISC_ATOMIC | (0x03 << 27), + OPC_RISC_AMOSWAP = OPC_RISC_ATOMIC | (0x01 << 27), + OPC_RISC_AMOADD = OPC_RISC_ATOMIC | (0x00 << 27), + OPC_RISC_AMOXOR = OPC_RISC_ATOMIC | (0x04 << 27), + OPC_RISC_AMOAND = OPC_RISC_ATOMIC | (0x0C << 27), + OPC_RISC_AMOOR = OPC_RISC_ATOMIC | (0x08 << 27), + OPC_RISC_AMOMIN = OPC_RISC_ATOMIC | (0x10 << 27), + OPC_RISC_AMOMAX = OPC_RISC_ATOMIC | (0x14 << 27), + OPC_RISC_AMOMINU = OPC_RISC_ATOMIC | (0x18 << 27), + OPC_RISC_AMOMAXU = OPC_RISC_ATOMIC | (0x1C << 27), +}; + +#define MASK_OP_SYSTEM(op) (MASK_OP_MAJOR(op) | (op & (0x7 << 12))) +enum { + OPC_RISC_ECALL = OPC_RISC_SYSTEM | (0x0 << 12), + OPC_RISC_EBREAK = OPC_RISC_SYSTEM | (0x0 << 12), + OPC_RISC_ERET = OPC_RISC_SYSTEM | (0x0 << 12), + OPC_RISC_MRTS = OPC_RISC_SYSTEM | (0x0 << 12), + OPC_RISC_MRTH = OPC_RISC_SYSTEM | (0x0 << 12), + OPC_RISC_HRTS = OPC_RISC_SYSTEM | (0x0 << 12), + OPC_RISC_WFI = OPC_RISC_SYSTEM | (0x0 << 12), + OPC_RISC_SFENCEVM = OPC_RISC_SYSTEM | (0x0 << 12), + + OPC_RISC_CSRRW = OPC_RISC_SYSTEM | (0x1 << 12), + OPC_RISC_CSRRS = OPC_RISC_SYSTEM | (0x2 << 12), + OPC_RISC_CSRRC = OPC_RISC_SYSTEM | (0x3 << 12), + OPC_RISC_CSRRWI = OPC_RISC_SYSTEM | (0x5 << 12), + OPC_RISC_CSRRSI = OPC_RISC_SYSTEM | (0x6 << 12), + OPC_RISC_CSRRCI = OPC_RISC_SYSTEM | (0x7 << 12), +}; + +#define MASK_OP_FP_LOAD(op) (MASK_OP_MAJOR(op) | (op & (0x7 << 12))) +enum { + OPC_RISC_FLW = OPC_RISC_FP_LOAD | (0x2 << 12), + OPC_RISC_FLD = OPC_RISC_FP_LOAD | (0x3 << 12), +}; + +#define MASK_OP_FP_STORE(op) (MASK_OP_MAJOR(op) | (op & (0x7 << 12))) +enum { + OPC_RISC_FSW = OPC_RISC_FP_STORE | (0x2 << 12), + OPC_RISC_FSD = OPC_RISC_FP_STORE | (0x3 << 12), +}; + +#define MASK_OP_FP_FMADD(op) (MASK_OP_MAJOR(op) | (op & (0x3 << 25))) +enum { + OPC_RISC_FMADD_S = OPC_RISC_FMADD | (0x0 << 25), + OPC_RISC_FMADD_D = OPC_RISC_FMADD | (0x1 << 25), +}; + +#define MASK_OP_FP_FMSUB(op) (MASK_OP_MAJOR(op) | (op & (0x3 << 25))) +enum { + OPC_RISC_FMSUB_S = OPC_RISC_FMSUB | (0x0 << 25), + OPC_RISC_FMSUB_D = OPC_RISC_FMSUB | (0x1 << 25), +}; + +#define MASK_OP_FP_FNMADD(op) (MASK_OP_MAJOR(op) | (op & (0x3 << 25))) +enum { + OPC_RISC_FNMADD_S = OPC_RISC_FNMADD | (0x0 << 25), + OPC_RISC_FNMADD_D = OPC_RISC_FNMADD | (0x1 << 25), +}; + +#define MASK_OP_FP_FNMSUB(op) (MASK_OP_MAJOR(op) | (op & (0x3 << 25))) +enum { + OPC_RISC_FNMSUB_S = OPC_RISC_FNMSUB | (0x0 << 25), + OPC_RISC_FNMSUB_D = OPC_RISC_FNMSUB | (0x1 << 25), +}; + +#define MASK_OP_FP_ARITH(op) (MASK_OP_MAJOR(op) | (op & (0x7F << 25))) +enum { + /* float */ + OPC_RISC_FADD_S = OPC_RISC_FP_ARITH | (0x0 << 25), + OPC_RISC_FSUB_S = OPC_RISC_FP_ARITH | (0x4 << 25), + OPC_RISC_FMUL_S = OPC_RISC_FP_ARITH | (0x8 << 25), + OPC_RISC_FDIV_S = OPC_RISC_FP_ARITH | (0xC << 25), + + OPC_RISC_FSGNJ_S = OPC_RISC_FP_ARITH | (0x10 << 25), + OPC_RISC_FSGNJN_S = OPC_RISC_FP_ARITH | (0x10 << 25), + OPC_RISC_FSGNJX_S = OPC_RISC_FP_ARITH | (0x10 << 25), + + OPC_RISC_FMIN_S = OPC_RISC_FP_ARITH | (0x14 << 25), + OPC_RISC_FMAX_S = OPC_RISC_FP_ARITH | (0x14 << 25), + + OPC_RISC_FSQRT_S = OPC_RISC_FP_ARITH | (0x2C << 25), + + OPC_RISC_FEQ_S = OPC_RISC_FP_ARITH | (0x50 << 25), + OPC_RISC_FLT_S = OPC_RISC_FP_ARITH | (0x50 << 25), + OPC_RISC_FLE_S = OPC_RISC_FP_ARITH | (0x50 << 25), + + OPC_RISC_FCVT_W_S = OPC_RISC_FP_ARITH | (0x60 << 25), + OPC_RISC_FCVT_WU_S = OPC_RISC_FP_ARITH | (0x60 << 25), + OPC_RISC_FCVT_L_S = OPC_RISC_FP_ARITH | (0x60 << 25), + OPC_RISC_FCVT_LU_S = OPC_RISC_FP_ARITH | (0x60 << 25), + + OPC_RISC_FCVT_S_W = OPC_RISC_FP_ARITH | (0x68 << 25), + OPC_RISC_FCVT_S_WU = OPC_RISC_FP_ARITH | (0x68 << 25), + OPC_RISC_FCVT_S_L = OPC_RISC_FP_ARITH | (0x68 << 25), + OPC_RISC_FCVT_S_LU = OPC_RISC_FP_ARITH | (0x68 << 25), + + OPC_RISC_FMV_X_S = OPC_RISC_FP_ARITH | (0x70 << 25), + OPC_RISC_FCLASS_S = OPC_RISC_FP_ARITH | (0x70 << 25), + + OPC_RISC_FMV_S_X = OPC_RISC_FP_ARITH | (0x78 << 25), + + /* double */ + OPC_RISC_FADD_D = OPC_RISC_FP_ARITH | (0x1 << 25), + OPC_RISC_FSUB_D = OPC_RISC_FP_ARITH | (0x5 << 25), + OPC_RISC_FMUL_D = OPC_RISC_FP_ARITH | (0x9 << 25), + OPC_RISC_FDIV_D = OPC_RISC_FP_ARITH | (0xD << 25), + + OPC_RISC_FSGNJ_D = OPC_RISC_FP_ARITH | (0x11 << 25), + OPC_RISC_FSGNJN_D = OPC_RISC_FP_ARITH | (0x11 << 25), + OPC_RISC_FSGNJX_D = OPC_RISC_FP_ARITH | (0x11 << 25), + + OPC_RISC_FMIN_D = OPC_RISC_FP_ARITH | (0x15 << 25), + OPC_RISC_FMAX_D = OPC_RISC_FP_ARITH | (0x15 << 25), + + OPC_RISC_FCVT_S_D = OPC_RISC_FP_ARITH | (0x20 << 25), + + OPC_RISC_FCVT_D_S = OPC_RISC_FP_ARITH | (0x21 << 25), + + OPC_RISC_FSQRT_D = OPC_RISC_FP_ARITH | (0x2D << 25), + + OPC_RISC_FEQ_D = OPC_RISC_FP_ARITH | (0x51 << 25), + OPC_RISC_FLT_D = OPC_RISC_FP_ARITH | (0x51 << 25), + OPC_RISC_FLE_D = OPC_RISC_FP_ARITH | (0x51 << 25), + + OPC_RISC_FCVT_W_D = OPC_RISC_FP_ARITH | (0x61 << 25), + OPC_RISC_FCVT_WU_D = OPC_RISC_FP_ARITH | (0x61 << 25), + OPC_RISC_FCVT_L_D = OPC_RISC_FP_ARITH | (0x61 << 25), + OPC_RISC_FCVT_LU_D = OPC_RISC_FP_ARITH | (0x61 << 25), + + OPC_RISC_FCVT_D_W = OPC_RISC_FP_ARITH | (0x69 << 25), + OPC_RISC_FCVT_D_WU = OPC_RISC_FP_ARITH | (0x69 << 25), + OPC_RISC_FCVT_D_L = OPC_RISC_FP_ARITH | (0x69 << 25), + OPC_RISC_FCVT_D_LU = OPC_RISC_FP_ARITH | (0x69 << 25), + + OPC_RISC_FMV_X_D = OPC_RISC_FP_ARITH | (0x71 << 25), + OPC_RISC_FCLASS_D = OPC_RISC_FP_ARITH | (0x71 << 25), + + OPC_RISC_FMV_D_X = OPC_RISC_FP_ARITH | (0x79 << 25), +}; + +#define GET_B_IMM(inst) ((extract32(inst, 8, 4) << 1) \ + | (extract32(inst, 25, 6) << 5) \ + | (extract32(inst, 7, 1) << 11) \ + | (sextract64(inst, 31, 1) << 12)) + +#define GET_STORE_IMM(inst) ((extract32(inst, 7, 5)) \ + | (sextract64(inst, 25, 7) << 5)) + +#define GET_JAL_IMM(inst) ((extract32(inst, 21, 10) << 1) \ + | (extract32(inst, 20, 1) << 11) \ + | (extract32(inst, 12, 8) << 12) \ + | (sextract64(inst, 31, 1) << 20)) + +#define GET_RM(inst) extract32(inst, 12, 3) +#define GET_RS3(inst) extract32(inst, 27, 5) +#define GET_RS1(inst) extract32(inst, 15, 5) +#define GET_RS2(inst) extract32(inst, 20, 5) +#define GET_RD(inst) extract32(inst, 7, 5) +#define GET_IMM(inst) sextract64(inst, 20, 12) + +/* RVC decoding macros */ +#define GET_C_IMM(inst) (extract32(inst, 2, 5) \ + | (sextract64(inst, 12, 1) << 5)) +#define GET_C_ZIMM(inst) (extract32(inst, 2, 5) \ + | (extract32(inst, 12, 1) << 5)) +#define GET_C_ADDI4SPN_IMM(inst) ((extract32(inst, 6, 1) << 2) \ + | (extract32(inst, 5, 1) << 3) \ + | (extract32(inst, 11, 2) << 4) \ + | (extract32(inst, 7, 4) << 6)) +#define GET_C_ADDI16SP_IMM(inst) ((extract32(inst, 6, 1) << 4) \ + | (extract32(inst, 2, 1) << 5) \ + | (extract32(inst, 5, 1) << 6) \ + | (extract32(inst, 3, 2) << 7) \ + | (sextract64(inst, 12, 1) << 9)) +#define GET_C_LWSP_IMM(inst) ((extract32(inst, 4, 3) << 2) \ + | (extract32(inst, 12, 1) << 5) \ + | (extract32(inst, 2, 2) << 6)) +#define GET_C_LDSP_IMM(inst) ((extract32(inst, 5, 2) << 3) \ + | (extract32(inst, 12, 1) << 5) \ + | (extract32(inst, 2, 3) << 6)) +#define GET_C_SWSP_IMM(inst) ((extract32(inst, 9, 4) << 2) \ + | (extract32(inst, 7, 2) << 6)) +#define GET_C_SDSP_IMM(inst) ((extract32(inst, 10, 3) << 3) \ + | (extract32(inst, 7, 3) << 6)) +#define GET_C_LW_IMM(inst) ((extract32(inst, 6, 1) << 2) \ + | (extract32(inst, 10, 3) << 3) \ + | (extract32(inst, 5, 1) << 6)) +#define GET_C_LD_IMM(inst) ((extract16(inst, 10, 3) << 3) \ + | (extract16(inst, 5, 2) << 6)) +#define GET_C_J_IMM(inst) ((extract32(inst, 3, 3) << 1) \ + | (extract32(inst, 11, 1) << 4) \ + | (extract32(inst, 2, 1) << 5) \ + | (extract32(inst, 7, 1) << 6) \ + | (extract32(inst, 6, 1) << 7) \ + | (extract32(inst, 9, 2) << 8) \ + | (extract32(inst, 8, 1) << 10) \ + | (sextract64(inst, 12, 1) << 11)) +#define GET_C_B_IMM(inst) ((extract32(inst, 3, 2) << 1) \ + | (extract32(inst, 10, 2) << 3) \ + | (extract32(inst, 2, 1) << 5) \ + | (extract32(inst, 5, 2) << 6) \ + | (sextract64(inst, 12, 1) << 8)) +#define GET_C_SIMM3(inst) extract32(inst, 10, 3) +#define GET_C_RD(inst) GET_RD(inst) +#define GET_C_RS1(inst) GET_RD(inst) +#define GET_C_RS2(inst) extract32(inst, 2, 5) +#define GET_C_RS1S(inst) (8 + extract16(inst, 7, 3)) +#define GET_C_RS2S(inst) (8 + extract16(inst, 2, 3)) + +#endif diff --git a/target/riscv/internals.h b/target/riscv/internals.h new file mode 100644 index 000000000..b15ad394b --- /dev/null +++ b/target/riscv/internals.h @@ -0,0 +1,61 @@ +/* + * QEMU RISC-V CPU -- internal functions and types + * + * 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 RISCV_CPU_INTERNALS_H +#define RISCV_CPU_INTERNALS_H + +#include "hw/registerfields.h" + +/* share data between vector helpers and decode code */ +FIELD(VDATA, MLEN, 0, 8) +FIELD(VDATA, VM, 8, 1) +FIELD(VDATA, LMUL, 9, 2) +FIELD(VDATA, NF, 11, 4) +FIELD(VDATA, WD, 11, 1) + +/* float point classify helpers */ +target_ulong fclass_h(uint64_t frs1); +target_ulong fclass_s(uint64_t frs1); +target_ulong fclass_d(uint64_t frs1); + +#define SEW8 0 +#define SEW16 1 +#define SEW32 2 +#define SEW64 3 + +#ifndef CONFIG_USER_ONLY +extern const VMStateDescription vmstate_riscv_cpu; +#endif + +static inline uint64_t nanbox_s(float32 f) +{ + return f | MAKE_64BIT_MASK(32, 32); +} + +static inline float32 check_nanbox_s(uint64_t f) +{ + uint64_t mask = MAKE_64BIT_MASK(32, 32); + + if (likely((f & mask) == mask)) { + return (uint32_t)f; + } else { + return 0x7fc00000u; /* default qnan */ + } +} + +#endif diff --git a/target/riscv/machine.c b/target/riscv/machine.c new file mode 100644 index 000000000..ad8248ebf --- /dev/null +++ b/target/riscv/machine.c @@ -0,0 +1,223 @@ +/* + * RISC-V VMState Description + * + * Copyright (c) 2020 Huawei Technologies Co., Ltd + * + * 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 "cpu.h" +#include "qemu/error-report.h" +#include "sysemu/kvm.h" +#include "migration/cpu.h" + +static bool pmp_needed(void *opaque) +{ + RISCVCPU *cpu = opaque; + CPURISCVState *env = &cpu->env; + + return riscv_feature(env, RISCV_FEATURE_PMP); +} + +static int pmp_post_load(void *opaque, int version_id) +{ + RISCVCPU *cpu = opaque; + CPURISCVState *env = &cpu->env; + int i; + + for (i = 0; i < MAX_RISCV_PMPS; i++) { + pmp_update_rule_addr(env, i); + } + pmp_update_rule_nums(env); + + return 0; +} + +static const VMStateDescription vmstate_pmp_entry = { + .name = "cpu/pmp/entry", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINTTL(addr_reg, pmp_entry_t), + VMSTATE_UINT8(cfg_reg, pmp_entry_t), + VMSTATE_END_OF_LIST() + } +}; + +static const VMStateDescription vmstate_pmp = { + .name = "cpu/pmp", + .version_id = 1, + .minimum_version_id = 1, + .needed = pmp_needed, + .post_load = pmp_post_load, + .fields = (VMStateField[]) { + VMSTATE_STRUCT_ARRAY(env.pmp_state.pmp, RISCVCPU, MAX_RISCV_PMPS, + 0, vmstate_pmp_entry, pmp_entry_t), + VMSTATE_END_OF_LIST() + } +}; + +static bool hyper_needed(void *opaque) +{ + RISCVCPU *cpu = opaque; + CPURISCVState *env = &cpu->env; + + return riscv_has_ext(env, RVH); +} + +static const VMStateDescription vmstate_hyper = { + .name = "cpu/hyper", + .version_id = 1, + .minimum_version_id = 1, + .needed = hyper_needed, + .fields = (VMStateField[]) { + VMSTATE_UINTTL(env.hstatus, RISCVCPU), + VMSTATE_UINTTL(env.hedeleg, RISCVCPU), + VMSTATE_UINTTL(env.hideleg, RISCVCPU), + VMSTATE_UINTTL(env.hcounteren, RISCVCPU), + VMSTATE_UINTTL(env.htval, RISCVCPU), + VMSTATE_UINTTL(env.htinst, RISCVCPU), + VMSTATE_UINTTL(env.hgatp, RISCVCPU), + VMSTATE_UINT64(env.htimedelta, RISCVCPU), + + VMSTATE_UINT64(env.vsstatus, RISCVCPU), + VMSTATE_UINTTL(env.vstvec, RISCVCPU), + VMSTATE_UINTTL(env.vsscratch, RISCVCPU), + VMSTATE_UINTTL(env.vsepc, RISCVCPU), + VMSTATE_UINTTL(env.vscause, RISCVCPU), + VMSTATE_UINTTL(env.vstval, RISCVCPU), + VMSTATE_UINTTL(env.vsatp, RISCVCPU), + + VMSTATE_UINTTL(env.mtval2, RISCVCPU), + VMSTATE_UINTTL(env.mtinst, RISCVCPU), + + VMSTATE_UINTTL(env.stvec_hs, RISCVCPU), + VMSTATE_UINTTL(env.sscratch_hs, RISCVCPU), + VMSTATE_UINTTL(env.sepc_hs, RISCVCPU), + VMSTATE_UINTTL(env.scause_hs, RISCVCPU), + VMSTATE_UINTTL(env.stval_hs, RISCVCPU), + VMSTATE_UINTTL(env.satp_hs, RISCVCPU), + VMSTATE_UINT64(env.mstatus_hs, RISCVCPU), + + VMSTATE_END_OF_LIST() + } +}; + +static bool vector_needed(void *opaque) +{ + RISCVCPU *cpu = opaque; + CPURISCVState *env = &cpu->env; + + return riscv_has_ext(env, RVV); +} + +static const VMStateDescription vmstate_vector = { + .name = "cpu/vector", + .version_id = 1, + .minimum_version_id = 1, + .needed = vector_needed, + .fields = (VMStateField[]) { + VMSTATE_UINT64_ARRAY(env.vreg, RISCVCPU, 32 * RV_VLEN_MAX / 64), + VMSTATE_UINTTL(env.vxrm, RISCVCPU), + VMSTATE_UINTTL(env.vxsat, RISCVCPU), + VMSTATE_UINTTL(env.vl, RISCVCPU), + VMSTATE_UINTTL(env.vstart, RISCVCPU), + VMSTATE_UINTTL(env.vtype, RISCVCPU), + VMSTATE_END_OF_LIST() + } +}; + +static bool pointermasking_needed(void *opaque) +{ + RISCVCPU *cpu = opaque; + CPURISCVState *env = &cpu->env; + + return riscv_has_ext(env, RVJ); +} + +static const VMStateDescription vmstate_pointermasking = { + .name = "cpu/pointer_masking", + .version_id = 1, + .minimum_version_id = 1, + .needed = pointermasking_needed, + .fields = (VMStateField[]) { + VMSTATE_UINTTL(env.mmte, RISCVCPU), + VMSTATE_UINTTL(env.mpmmask, RISCVCPU), + VMSTATE_UINTTL(env.mpmbase, RISCVCPU), + VMSTATE_UINTTL(env.spmmask, RISCVCPU), + VMSTATE_UINTTL(env.spmbase, RISCVCPU), + VMSTATE_UINTTL(env.upmmask, RISCVCPU), + VMSTATE_UINTTL(env.upmbase, RISCVCPU), + + VMSTATE_END_OF_LIST() + } +}; + +const VMStateDescription vmstate_riscv_cpu = { + .name = "cpu", + .version_id = 3, + .minimum_version_id = 3, + .fields = (VMStateField[]) { + VMSTATE_UINTTL_ARRAY(env.gpr, RISCVCPU, 32), + VMSTATE_UINT64_ARRAY(env.fpr, RISCVCPU, 32), + VMSTATE_UINTTL(env.pc, RISCVCPU), + VMSTATE_UINTTL(env.load_res, RISCVCPU), + VMSTATE_UINTTL(env.load_val, RISCVCPU), + VMSTATE_UINTTL(env.frm, RISCVCPU), + VMSTATE_UINTTL(env.badaddr, RISCVCPU), + VMSTATE_UINTTL(env.guest_phys_fault_addr, RISCVCPU), + VMSTATE_UINTTL(env.priv_ver, RISCVCPU), + VMSTATE_UINTTL(env.vext_ver, RISCVCPU), + VMSTATE_UINT32(env.misa_mxl, RISCVCPU), + VMSTATE_UINT32(env.misa_ext, RISCVCPU), + VMSTATE_UINT32(env.misa_mxl_max, RISCVCPU), + VMSTATE_UINT32(env.misa_ext_mask, RISCVCPU), + VMSTATE_UINT32(env.features, RISCVCPU), + VMSTATE_UINTTL(env.priv, RISCVCPU), + VMSTATE_UINTTL(env.virt, RISCVCPU), + VMSTATE_UINTTL(env.resetvec, RISCVCPU), + VMSTATE_UINTTL(env.mhartid, RISCVCPU), + VMSTATE_UINT64(env.mstatus, RISCVCPU), + VMSTATE_UINTTL(env.mip, RISCVCPU), + VMSTATE_UINT32(env.miclaim, RISCVCPU), + VMSTATE_UINTTL(env.mie, RISCVCPU), + VMSTATE_UINTTL(env.mideleg, RISCVCPU), + VMSTATE_UINTTL(env.satp, RISCVCPU), + VMSTATE_UINTTL(env.stval, RISCVCPU), + VMSTATE_UINTTL(env.medeleg, RISCVCPU), + VMSTATE_UINTTL(env.stvec, RISCVCPU), + VMSTATE_UINTTL(env.sepc, RISCVCPU), + VMSTATE_UINTTL(env.scause, RISCVCPU), + VMSTATE_UINTTL(env.mtvec, RISCVCPU), + VMSTATE_UINTTL(env.mepc, RISCVCPU), + VMSTATE_UINTTL(env.mcause, RISCVCPU), + VMSTATE_UINTTL(env.mtval, RISCVCPU), + VMSTATE_UINTTL(env.scounteren, RISCVCPU), + VMSTATE_UINTTL(env.mcounteren, RISCVCPU), + VMSTATE_UINTTL(env.sscratch, RISCVCPU), + VMSTATE_UINTTL(env.mscratch, RISCVCPU), + VMSTATE_UINT64(env.mfromhost, RISCVCPU), + VMSTATE_UINT64(env.mtohost, RISCVCPU), + VMSTATE_UINT64(env.timecmp, RISCVCPU), + + VMSTATE_END_OF_LIST() + }, + .subsections = (const VMStateDescription * []) { + &vmstate_pmp, + &vmstate_hyper, + &vmstate_vector, + &vmstate_pointermasking, + NULL + } +}; diff --git a/target/riscv/meson.build b/target/riscv/meson.build new file mode 100644 index 000000000..d5e0bc93e --- /dev/null +++ b/target/riscv/meson.build @@ -0,0 +1,32 @@ +# FIXME extra_args should accept files() +dir = meson.current_source_dir() + +gen = [ + decodetree.process('insn16.decode', extra_args: ['--static-decode=decode_insn16', '--insnwidth=16']), + decodetree.process('insn32.decode', extra_args: '--static-decode=decode_insn32'), +] + +riscv_ss = ss.source_set() +riscv_ss.add(gen) +riscv_ss.add(files( + 'cpu.c', + 'cpu_helper.c', + 'csr.c', + 'fpu_helper.c', + 'gdbstub.c', + 'op_helper.c', + 'vector_helper.c', + 'bitmanip_helper.c', + 'translate.c', +)) + +riscv_softmmu_ss = ss.source_set() +riscv_softmmu_ss.add(files( + 'arch_dump.c', + 'pmp.c', + 'monitor.c', + 'machine.c' +)) + +target_arch += {'riscv': riscv_ss} +target_softmmu_arch += {'riscv': riscv_softmmu_ss} diff --git a/target/riscv/monitor.c b/target/riscv/monitor.c new file mode 100644 index 000000000..7efb4b62c --- /dev/null +++ b/target/riscv/monitor.c @@ -0,0 +1,236 @@ +/* + * QEMU monitor for RISC-V + * + * Copyright (c) 2019 Bin Meng <bmeng.cn@gmail.com> + * + * RISC-V specific monitor commands implementation + * + * 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 "cpu.h" +#include "cpu_bits.h" +#include "monitor/monitor.h" +#include "monitor/hmp-target.h" + +#ifdef TARGET_RISCV64 +#define PTE_HEADER_FIELDS "vaddr paddr "\ + "size attr\n" +#define PTE_HEADER_DELIMITER "---------------- ---------------- "\ + "---------------- -------\n" +#else +#define PTE_HEADER_FIELDS "vaddr paddr size attr\n" +#define PTE_HEADER_DELIMITER "-------- ---------------- -------- -------\n" +#endif + +/* Perform linear address sign extension */ +static target_ulong addr_canonical(int va_bits, target_ulong addr) +{ +#ifdef TARGET_RISCV64 + if (addr & (1UL << (va_bits - 1))) { + addr |= (hwaddr)-(1L << va_bits); + } +#endif + + return addr; +} + +static void print_pte_header(Monitor *mon) +{ + monitor_printf(mon, PTE_HEADER_FIELDS); + monitor_printf(mon, PTE_HEADER_DELIMITER); +} + +static void print_pte(Monitor *mon, int va_bits, target_ulong vaddr, + hwaddr paddr, target_ulong size, int attr) +{ + /* santity check on vaddr */ + if (vaddr >= (1UL << va_bits)) { + return; + } + + if (!size) { + return; + } + + monitor_printf(mon, TARGET_FMT_lx " " TARGET_FMT_plx " " TARGET_FMT_lx + " %c%c%c%c%c%c%c\n", + addr_canonical(va_bits, vaddr), + paddr, size, + attr & PTE_R ? 'r' : '-', + attr & PTE_W ? 'w' : '-', + attr & PTE_X ? 'x' : '-', + attr & PTE_U ? 'u' : '-', + attr & PTE_G ? 'g' : '-', + attr & PTE_A ? 'a' : '-', + attr & PTE_D ? 'd' : '-'); +} + +static void walk_pte(Monitor *mon, hwaddr base, target_ulong start, + int level, int ptidxbits, int ptesize, int va_bits, + target_ulong *vbase, hwaddr *pbase, hwaddr *last_paddr, + target_ulong *last_size, int *last_attr) +{ + hwaddr pte_addr; + hwaddr paddr; + target_ulong pgsize; + target_ulong pte; + int ptshift; + int attr; + int idx; + + if (level < 0) { + return; + } + + ptshift = level * ptidxbits; + pgsize = 1UL << (PGSHIFT + ptshift); + + for (idx = 0; idx < (1UL << ptidxbits); idx++) { + pte_addr = base + idx * ptesize; + cpu_physical_memory_read(pte_addr, &pte, ptesize); + + paddr = (hwaddr)(pte >> PTE_PPN_SHIFT) << PGSHIFT; + attr = pte & 0xff; + + /* PTE has to be valid */ + if (attr & PTE_V) { + if (attr & (PTE_R | PTE_W | PTE_X)) { + /* + * A leaf PTE has been found + * + * If current PTE's permission bits differ from the last one, + * or current PTE's ppn does not make a contiguous physical + * address block together with the last one, print out the last + * contiguous mapped block details. + */ + if ((*last_attr != attr) || + (*last_paddr + *last_size != paddr)) { + print_pte(mon, va_bits, *vbase, *pbase, + *last_paddr + *last_size - *pbase, *last_attr); + + *vbase = start; + *pbase = paddr; + *last_attr = attr; + } + + *last_paddr = paddr; + *last_size = pgsize; + } else { + /* pointer to the next level of the page table */ + walk_pte(mon, paddr, start, level - 1, ptidxbits, ptesize, + va_bits, vbase, pbase, last_paddr, + last_size, last_attr); + } + } + + start += pgsize; + } + +} + +static void mem_info_svxx(Monitor *mon, CPUArchState *env) +{ + int levels, ptidxbits, ptesize, vm, va_bits; + hwaddr base; + target_ulong vbase; + hwaddr pbase; + hwaddr last_paddr; + target_ulong last_size; + int last_attr; + + if (riscv_cpu_mxl(env) == MXL_RV32) { + base = (hwaddr)get_field(env->satp, SATP32_PPN) << PGSHIFT; + vm = get_field(env->satp, SATP32_MODE); + } else { + base = (hwaddr)get_field(env->satp, SATP64_PPN) << PGSHIFT; + vm = get_field(env->satp, SATP64_MODE); + } + + switch (vm) { + case VM_1_10_SV32: + levels = 2; + ptidxbits = 10; + ptesize = 4; + break; + case VM_1_10_SV39: + levels = 3; + ptidxbits = 9; + ptesize = 8; + break; + case VM_1_10_SV48: + levels = 4; + ptidxbits = 9; + ptesize = 8; + break; + case VM_1_10_SV57: + levels = 5; + ptidxbits = 9; + ptesize = 8; + break; + default: + g_assert_not_reached(); + break; + } + + /* calculate virtual address bits */ + va_bits = PGSHIFT + levels * ptidxbits; + + /* print header */ + print_pte_header(mon); + + vbase = -1; + pbase = -1; + last_paddr = -1; + last_size = 0; + last_attr = 0; + + /* walk page tables, starting from address 0 */ + walk_pte(mon, base, 0, levels - 1, ptidxbits, ptesize, va_bits, + &vbase, &pbase, &last_paddr, &last_size, &last_attr); + + /* don't forget the last one */ + print_pte(mon, va_bits, vbase, pbase, + last_paddr + last_size - pbase, last_attr); +} + +void hmp_info_mem(Monitor *mon, const QDict *qdict) +{ + CPUArchState *env; + + env = mon_get_cpu_env(mon); + if (!env) { + monitor_printf(mon, "No CPU available\n"); + return; + } + + if (!riscv_feature(env, RISCV_FEATURE_MMU)) { + monitor_printf(mon, "S-mode MMU unavailable\n"); + return; + } + + if (riscv_cpu_mxl(env) == MXL_RV32) { + if (!(env->satp & SATP32_MODE)) { + monitor_printf(mon, "No translation or protection\n"); + return; + } + } else { + if (!(env->satp & SATP64_MODE)) { + monitor_printf(mon, "No translation or protection\n"); + return; + } + } + + mem_info_svxx(mon, env); +} diff --git a/target/riscv/op_helper.c b/target/riscv/op_helper.c new file mode 100644 index 000000000..ee7c24efe --- /dev/null +++ b/target/riscv/op_helper.c @@ -0,0 +1,249 @@ +/* + * RISC-V Emulation Helpers for QEMU. + * + * Copyright (c) 2016-2017 Sagar Karandikar, sagark@eecs.berkeley.edu + * Copyright (c) 2017-2018 SiFive, Inc. + * + * 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 "cpu.h" +#include "qemu/main-loop.h" +#include "exec/exec-all.h" +#include "exec/helper-proto.h" + +/* Exceptions processing helpers */ +void QEMU_NORETURN riscv_raise_exception(CPURISCVState *env, + uint32_t exception, uintptr_t pc) +{ + CPUState *cs = env_cpu(env); + cs->exception_index = exception; + cpu_loop_exit_restore(cs, pc); +} + +void helper_raise_exception(CPURISCVState *env, uint32_t exception) +{ + riscv_raise_exception(env, exception, 0); +} + +target_ulong helper_csrr(CPURISCVState *env, int csr) +{ + target_ulong val = 0; + RISCVException ret = riscv_csrrw(env, csr, &val, 0, 0); + + if (ret != RISCV_EXCP_NONE) { + riscv_raise_exception(env, ret, GETPC()); + } + return val; +} + +void helper_csrw(CPURISCVState *env, int csr, target_ulong src) +{ + RISCVException ret = riscv_csrrw(env, csr, NULL, src, -1); + + if (ret != RISCV_EXCP_NONE) { + riscv_raise_exception(env, ret, GETPC()); + } +} + +target_ulong helper_csrrw(CPURISCVState *env, int csr, + target_ulong src, target_ulong write_mask) +{ + target_ulong val = 0; + RISCVException ret = riscv_csrrw(env, csr, &val, src, write_mask); + + if (ret != RISCV_EXCP_NONE) { + riscv_raise_exception(env, ret, GETPC()); + } + return val; +} + +#ifndef CONFIG_USER_ONLY + +target_ulong helper_sret(CPURISCVState *env, target_ulong cpu_pc_deb) +{ + uint64_t mstatus; + target_ulong prev_priv, prev_virt; + + if (!(env->priv >= PRV_S)) { + riscv_raise_exception(env, RISCV_EXCP_ILLEGAL_INST, GETPC()); + } + + target_ulong retpc = env->sepc; + if (!riscv_has_ext(env, RVC) && (retpc & 0x3)) { + riscv_raise_exception(env, RISCV_EXCP_INST_ADDR_MIS, GETPC()); + } + + if (get_field(env->mstatus, MSTATUS_TSR) && !(env->priv >= PRV_M)) { + riscv_raise_exception(env, RISCV_EXCP_ILLEGAL_INST, GETPC()); + } + + if (riscv_has_ext(env, RVH) && riscv_cpu_virt_enabled(env) && + get_field(env->hstatus, HSTATUS_VTSR)) { + riscv_raise_exception(env, RISCV_EXCP_VIRT_INSTRUCTION_FAULT, GETPC()); + } + + mstatus = env->mstatus; + + if (riscv_has_ext(env, RVH) && !riscv_cpu_virt_enabled(env)) { + /* We support Hypervisor extensions and virtulisation is disabled */ + target_ulong hstatus = env->hstatus; + + prev_priv = get_field(mstatus, MSTATUS_SPP); + prev_virt = get_field(hstatus, HSTATUS_SPV); + + hstatus = set_field(hstatus, HSTATUS_SPV, 0); + mstatus = set_field(mstatus, MSTATUS_SPP, 0); + mstatus = set_field(mstatus, SSTATUS_SIE, + get_field(mstatus, SSTATUS_SPIE)); + mstatus = set_field(mstatus, SSTATUS_SPIE, 1); + + env->mstatus = mstatus; + env->hstatus = hstatus; + + if (prev_virt) { + riscv_cpu_swap_hypervisor_regs(env); + } + + riscv_cpu_set_virt_enabled(env, prev_virt); + } else { + prev_priv = get_field(mstatus, MSTATUS_SPP); + + mstatus = set_field(mstatus, MSTATUS_SIE, + get_field(mstatus, MSTATUS_SPIE)); + mstatus = set_field(mstatus, MSTATUS_SPIE, 1); + mstatus = set_field(mstatus, MSTATUS_SPP, PRV_U); + env->mstatus = mstatus; + } + + riscv_cpu_set_mode(env, prev_priv); + + return retpc; +} + +target_ulong helper_mret(CPURISCVState *env, target_ulong cpu_pc_deb) +{ + if (!(env->priv >= PRV_M)) { + riscv_raise_exception(env, RISCV_EXCP_ILLEGAL_INST, GETPC()); + } + + target_ulong retpc = env->mepc; + if (!riscv_has_ext(env, RVC) && (retpc & 0x3)) { + riscv_raise_exception(env, RISCV_EXCP_INST_ADDR_MIS, GETPC()); + } + + uint64_t mstatus = env->mstatus; + target_ulong prev_priv = get_field(mstatus, MSTATUS_MPP); + + if (!pmp_get_num_rules(env) && (prev_priv != PRV_M)) { + riscv_raise_exception(env, RISCV_EXCP_ILLEGAL_INST, GETPC()); + } + + target_ulong prev_virt = get_field(env->mstatus, MSTATUS_MPV); + mstatus = set_field(mstatus, MSTATUS_MIE, + get_field(mstatus, MSTATUS_MPIE)); + mstatus = set_field(mstatus, MSTATUS_MPIE, 1); + mstatus = set_field(mstatus, MSTATUS_MPP, PRV_U); + mstatus = set_field(mstatus, MSTATUS_MPV, 0); + env->mstatus = mstatus; + riscv_cpu_set_mode(env, prev_priv); + + if (riscv_has_ext(env, RVH)) { + if (prev_virt) { + riscv_cpu_swap_hypervisor_regs(env); + } + + riscv_cpu_set_virt_enabled(env, prev_virt); + } + + return retpc; +} + +void helper_wfi(CPURISCVState *env) +{ + CPUState *cs = env_cpu(env); + bool rvs = riscv_has_ext(env, RVS); + bool prv_u = env->priv == PRV_U; + bool prv_s = env->priv == PRV_S; + + if (((prv_s || (!rvs && prv_u)) && get_field(env->mstatus, MSTATUS_TW)) || + (rvs && prv_u && !riscv_cpu_virt_enabled(env))) { + riscv_raise_exception(env, RISCV_EXCP_ILLEGAL_INST, GETPC()); + } else if (riscv_cpu_virt_enabled(env) && (prv_u || + (prv_s && get_field(env->hstatus, HSTATUS_VTW)))) { + riscv_raise_exception(env, RISCV_EXCP_VIRT_INSTRUCTION_FAULT, GETPC()); + } else { + cs->halted = 1; + cs->exception_index = EXCP_HLT; + cpu_loop_exit(cs); + } +} + +void helper_tlb_flush(CPURISCVState *env) +{ + CPUState *cs = env_cpu(env); + if (!(env->priv >= PRV_S) || + (env->priv == PRV_S && + get_field(env->mstatus, MSTATUS_TVM))) { + riscv_raise_exception(env, RISCV_EXCP_ILLEGAL_INST, GETPC()); + } else if (riscv_has_ext(env, RVH) && riscv_cpu_virt_enabled(env) && + get_field(env->hstatus, HSTATUS_VTVM)) { + riscv_raise_exception(env, RISCV_EXCP_VIRT_INSTRUCTION_FAULT, GETPC()); + } else { + tlb_flush(cs); + } +} + +void helper_hyp_tlb_flush(CPURISCVState *env) +{ + CPUState *cs = env_cpu(env); + + if (env->priv == PRV_S && riscv_cpu_virt_enabled(env)) { + riscv_raise_exception(env, RISCV_EXCP_VIRT_INSTRUCTION_FAULT, GETPC()); + } + + if (env->priv == PRV_M || + (env->priv == PRV_S && !riscv_cpu_virt_enabled(env))) { + tlb_flush(cs); + return; + } + + riscv_raise_exception(env, RISCV_EXCP_ILLEGAL_INST, GETPC()); +} + +void helper_hyp_gvma_tlb_flush(CPURISCVState *env) +{ + if (env->priv == PRV_S && !riscv_cpu_virt_enabled(env) && + get_field(env->mstatus, MSTATUS_TVM)) { + riscv_raise_exception(env, RISCV_EXCP_ILLEGAL_INST, GETPC()); + } + + helper_hyp_tlb_flush(env); +} + +target_ulong helper_hyp_hlvx_hu(CPURISCVState *env, target_ulong address) +{ + int mmu_idx = cpu_mmu_index(env, true) | TB_FLAGS_PRIV_HYP_ACCESS_MASK; + + return cpu_lduw_mmuidx_ra(env, address, mmu_idx, GETPC()); +} + +target_ulong helper_hyp_hlvx_wu(CPURISCVState *env, target_ulong address) +{ + int mmu_idx = cpu_mmu_index(env, true) | TB_FLAGS_PRIV_HYP_ACCESS_MASK; + + return cpu_ldl_mmuidx_ra(env, address, mmu_idx, GETPC()); +} + +#endif /* !CONFIG_USER_ONLY */ diff --git a/target/riscv/pmp.c b/target/riscv/pmp.c new file mode 100644 index 000000000..54abf4258 --- /dev/null +++ b/target/riscv/pmp.c @@ -0,0 +1,664 @@ +/* + * QEMU RISC-V PMP (Physical Memory Protection) + * + * Author: Daire McNamara, daire.mcnamara@emdalo.com + * Ivan Griffin, ivan.griffin@emdalo.com + * + * This provides a RISC-V Physical Memory Protection implementation + * + * 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/log.h" +#include "qapi/error.h" +#include "cpu.h" +#include "trace.h" +#include "exec/exec-all.h" + +static void pmp_write_cfg(CPURISCVState *env, uint32_t addr_index, + uint8_t val); +static uint8_t pmp_read_cfg(CPURISCVState *env, uint32_t addr_index); +static void pmp_update_rule(CPURISCVState *env, uint32_t pmp_index); + +/* + * Accessor method to extract address matching type 'a field' from cfg reg + */ +static inline uint8_t pmp_get_a_field(uint8_t cfg) +{ + uint8_t a = cfg >> 3; + return a & 0x3; +} + +/* + * Check whether a PMP is locked or not. + */ +static inline int pmp_is_locked(CPURISCVState *env, uint32_t pmp_index) +{ + + if (env->pmp_state.pmp[pmp_index].cfg_reg & PMP_LOCK) { + return 1; + } + + /* Top PMP has no 'next' to check */ + if ((pmp_index + 1u) >= MAX_RISCV_PMPS) { + return 0; + } + + return 0; +} + +/* + * Count the number of active rules. + */ +uint32_t pmp_get_num_rules(CPURISCVState *env) +{ + return env->pmp_state.num_rules; +} + +/* + * Accessor to get the cfg reg for a specific PMP/HART + */ +static inline uint8_t pmp_read_cfg(CPURISCVState *env, uint32_t pmp_index) +{ + if (pmp_index < MAX_RISCV_PMPS) { + return env->pmp_state.pmp[pmp_index].cfg_reg; + } + + return 0; +} + + +/* + * Accessor to set the cfg reg for a specific PMP/HART + * Bounds checks and relevant lock bit. + */ +static void pmp_write_cfg(CPURISCVState *env, uint32_t pmp_index, uint8_t val) +{ + if (pmp_index < MAX_RISCV_PMPS) { + bool locked = true; + + if (riscv_feature(env, RISCV_FEATURE_EPMP)) { + /* mseccfg.RLB is set */ + if (MSECCFG_RLB_ISSET(env)) { + locked = false; + } + + /* mseccfg.MML is not set */ + if (!MSECCFG_MML_ISSET(env) && !pmp_is_locked(env, pmp_index)) { + locked = false; + } + + /* mseccfg.MML is set */ + if (MSECCFG_MML_ISSET(env)) { + /* not adding execute bit */ + if ((val & PMP_LOCK) != 0 && (val & PMP_EXEC) != PMP_EXEC) { + locked = false; + } + /* shared region and not adding X bit */ + if ((val & PMP_LOCK) != PMP_LOCK && + (val & 0x7) != (PMP_WRITE | PMP_EXEC)) { + locked = false; + } + } + } else { + if (!pmp_is_locked(env, pmp_index)) { + locked = false; + } + } + + if (locked) { + qemu_log_mask(LOG_GUEST_ERROR, "ignoring pmpcfg write - locked\n"); + } else { + env->pmp_state.pmp[pmp_index].cfg_reg = val; + pmp_update_rule(env, pmp_index); + } + } else { + qemu_log_mask(LOG_GUEST_ERROR, + "ignoring pmpcfg write - out of bounds\n"); + } +} + +static void pmp_decode_napot(target_ulong a, target_ulong *sa, target_ulong *ea) +{ + /* + aaaa...aaa0 8-byte NAPOT range + aaaa...aa01 16-byte NAPOT range + aaaa...a011 32-byte NAPOT range + ... + aa01...1111 2^XLEN-byte NAPOT range + a011...1111 2^(XLEN+1)-byte NAPOT range + 0111...1111 2^(XLEN+2)-byte NAPOT range + 1111...1111 Reserved + */ + if (a == -1) { + *sa = 0u; + *ea = -1; + return; + } else { + target_ulong t1 = ctz64(~a); + target_ulong base = (a & ~(((target_ulong)1 << t1) - 1)) << 2; + target_ulong range = ((target_ulong)1 << (t1 + 3)) - 1; + *sa = base; + *ea = base + range; + } +} + +void pmp_update_rule_addr(CPURISCVState *env, uint32_t pmp_index) +{ + uint8_t this_cfg = env->pmp_state.pmp[pmp_index].cfg_reg; + target_ulong this_addr = env->pmp_state.pmp[pmp_index].addr_reg; + target_ulong prev_addr = 0u; + target_ulong sa = 0u; + target_ulong ea = 0u; + + if (pmp_index >= 1u) { + prev_addr = env->pmp_state.pmp[pmp_index - 1].addr_reg; + } + + switch (pmp_get_a_field(this_cfg)) { + case PMP_AMATCH_OFF: + sa = 0u; + ea = -1; + break; + + case PMP_AMATCH_TOR: + sa = prev_addr << 2; /* shift up from [xx:0] to [xx+2:2] */ + ea = (this_addr << 2) - 1u; + break; + + case PMP_AMATCH_NA4: + sa = this_addr << 2; /* shift up from [xx:0] to [xx+2:2] */ + ea = (sa + 4u) - 1u; + break; + + case PMP_AMATCH_NAPOT: + pmp_decode_napot(this_addr, &sa, &ea); + break; + + default: + sa = 0u; + ea = 0u; + break; + } + + env->pmp_state.addr[pmp_index].sa = sa; + env->pmp_state.addr[pmp_index].ea = ea; +} + +void pmp_update_rule_nums(CPURISCVState *env) +{ + int i; + + env->pmp_state.num_rules = 0; + for (i = 0; i < MAX_RISCV_PMPS; i++) { + const uint8_t a_field = + pmp_get_a_field(env->pmp_state.pmp[i].cfg_reg); + if (PMP_AMATCH_OFF != a_field) { + env->pmp_state.num_rules++; + } + } +} + +/* Convert cfg/addr reg values here into simple 'sa' --> start address and 'ea' + * end address values. + * This function is called relatively infrequently whereas the check that + * an address is within a pmp rule is called often, so optimise that one + */ +static void pmp_update_rule(CPURISCVState *env, uint32_t pmp_index) +{ + pmp_update_rule_addr(env, pmp_index); + pmp_update_rule_nums(env); +} + +static int pmp_is_in_range(CPURISCVState *env, int pmp_index, target_ulong addr) +{ + int result = 0; + + if ((addr >= env->pmp_state.addr[pmp_index].sa) + && (addr <= env->pmp_state.addr[pmp_index].ea)) { + result = 1; + } else { + result = 0; + } + + return result; +} + +/* + * Check if the address has required RWX privs when no PMP entry is matched. + */ +static bool pmp_hart_has_privs_default(CPURISCVState *env, target_ulong addr, + target_ulong size, pmp_priv_t privs, pmp_priv_t *allowed_privs, + target_ulong mode) +{ + bool ret; + + if (riscv_feature(env, RISCV_FEATURE_EPMP)) { + if (MSECCFG_MMWP_ISSET(env)) { + /* + * The Machine Mode Whitelist Policy (mseccfg.MMWP) is set + * so we default to deny all, even for M-mode. + */ + *allowed_privs = 0; + return false; + } else if (MSECCFG_MML_ISSET(env)) { + /* + * The Machine Mode Lockdown (mseccfg.MML) bit is set + * so we can only execute code in M-mode with an applicable + * rule. Other modes are disabled. + */ + if (mode == PRV_M && !(privs & PMP_EXEC)) { + ret = true; + *allowed_privs = PMP_READ | PMP_WRITE; + } else { + ret = false; + *allowed_privs = 0; + } + + return ret; + } + } + + if ((!riscv_feature(env, RISCV_FEATURE_PMP)) || (mode == PRV_M)) { + /* + * Privileged spec v1.10 states if HW doesn't implement any PMP entry + * or no PMP entry matches an M-Mode access, the access succeeds. + */ + ret = true; + *allowed_privs = PMP_READ | PMP_WRITE | PMP_EXEC; + } else { + /* + * Other modes are not allowed to succeed if they don't * match a rule, + * but there are rules. We've checked for no rule earlier in this + * function. + */ + ret = false; + *allowed_privs = 0; + } + + return ret; +} + + +/* + * Public Interface + */ + +/* + * Check if the address has required RWX privs to complete desired operation + */ +bool pmp_hart_has_privs(CPURISCVState *env, target_ulong addr, + target_ulong size, pmp_priv_t privs, pmp_priv_t *allowed_privs, + target_ulong mode) +{ + int i = 0; + int ret = -1; + int pmp_size = 0; + target_ulong s = 0; + target_ulong e = 0; + + /* Short cut if no rules */ + if (0 == pmp_get_num_rules(env)) { + return pmp_hart_has_privs_default(env, addr, size, privs, + allowed_privs, mode); + } + + if (size == 0) { + if (riscv_feature(env, RISCV_FEATURE_MMU)) { + /* + * If size is unknown (0), assume that all bytes + * from addr to the end of the page will be accessed. + */ + pmp_size = -(addr | TARGET_PAGE_MASK); + } else { + pmp_size = sizeof(target_ulong); + } + } else { + pmp_size = size; + } + + /* 1.10 draft priv spec states there is an implicit order + from low to high */ + for (i = 0; i < MAX_RISCV_PMPS; i++) { + s = pmp_is_in_range(env, i, addr); + e = pmp_is_in_range(env, i, addr + pmp_size - 1); + + /* partially inside */ + if ((s + e) == 1) { + qemu_log_mask(LOG_GUEST_ERROR, + "pmp violation - access is partially inside\n"); + ret = 0; + break; + } + + /* fully inside */ + const uint8_t a_field = + pmp_get_a_field(env->pmp_state.pmp[i].cfg_reg); + + /* + * Convert the PMP permissions to match the truth table in the + * ePMP spec. + */ + const uint8_t epmp_operation = + ((env->pmp_state.pmp[i].cfg_reg & PMP_LOCK) >> 4) | + ((env->pmp_state.pmp[i].cfg_reg & PMP_READ) << 2) | + (env->pmp_state.pmp[i].cfg_reg & PMP_WRITE) | + ((env->pmp_state.pmp[i].cfg_reg & PMP_EXEC) >> 2); + + if (((s + e) == 2) && (PMP_AMATCH_OFF != a_field)) { + /* + * If the PMP entry is not off and the address is in range, + * do the priv check + */ + if (!MSECCFG_MML_ISSET(env)) { + /* + * If mseccfg.MML Bit is not set, do pmp priv check + * This will always apply to regular PMP. + */ + *allowed_privs = PMP_READ | PMP_WRITE | PMP_EXEC; + if ((mode != PRV_M) || pmp_is_locked(env, i)) { + *allowed_privs &= env->pmp_state.pmp[i].cfg_reg; + } + } else { + /* + * If mseccfg.MML Bit set, do the enhanced pmp priv check + */ + if (mode == PRV_M) { + switch (epmp_operation) { + case 0: + case 1: + case 4: + case 5: + case 6: + case 7: + case 8: + *allowed_privs = 0; + break; + case 2: + case 3: + case 14: + *allowed_privs = PMP_READ | PMP_WRITE; + break; + case 9: + case 10: + *allowed_privs = PMP_EXEC; + break; + case 11: + case 13: + *allowed_privs = PMP_READ | PMP_EXEC; + break; + case 12: + case 15: + *allowed_privs = PMP_READ; + break; + default: + g_assert_not_reached(); + } + } else { + switch (epmp_operation) { + case 0: + case 8: + case 9: + case 12: + case 13: + case 14: + *allowed_privs = 0; + break; + case 1: + case 10: + case 11: + *allowed_privs = PMP_EXEC; + break; + case 2: + case 4: + case 15: + *allowed_privs = PMP_READ; + break; + case 3: + case 6: + *allowed_privs = PMP_READ | PMP_WRITE; + break; + case 5: + *allowed_privs = PMP_READ | PMP_EXEC; + break; + case 7: + *allowed_privs = PMP_READ | PMP_WRITE | PMP_EXEC; + break; + default: + g_assert_not_reached(); + } + } + } + + ret = ((privs & *allowed_privs) == privs); + break; + } + } + + /* No rule matched */ + if (ret == -1) { + return pmp_hart_has_privs_default(env, addr, size, privs, + allowed_privs, mode); + } + + return ret == 1 ? true : false; +} + +/* + * Handle a write to a pmpcfg CSR + */ +void pmpcfg_csr_write(CPURISCVState *env, uint32_t reg_index, + target_ulong val) +{ + int i; + uint8_t cfg_val; + + trace_pmpcfg_csr_write(env->mhartid, reg_index, val); + + if ((reg_index & 1) && (sizeof(target_ulong) == 8)) { + qemu_log_mask(LOG_GUEST_ERROR, + "ignoring pmpcfg write - incorrect address\n"); + return; + } + + for (i = 0; i < sizeof(target_ulong); i++) { + cfg_val = (val >> 8 * i) & 0xff; + pmp_write_cfg(env, (reg_index * 4) + i, cfg_val); + } + + /* If PMP permission of any addr has been changed, flush TLB pages. */ + tlb_flush(env_cpu(env)); +} + + +/* + * Handle a read from a pmpcfg CSR + */ +target_ulong pmpcfg_csr_read(CPURISCVState *env, uint32_t reg_index) +{ + int i; + target_ulong cfg_val = 0; + target_ulong val = 0; + + for (i = 0; i < sizeof(target_ulong); i++) { + val = pmp_read_cfg(env, (reg_index * 4) + i); + cfg_val |= (val << (i * 8)); + } + trace_pmpcfg_csr_read(env->mhartid, reg_index, cfg_val); + + return cfg_val; +} + + +/* + * Handle a write to a pmpaddr CSR + */ +void pmpaddr_csr_write(CPURISCVState *env, uint32_t addr_index, + target_ulong val) +{ + trace_pmpaddr_csr_write(env->mhartid, addr_index, val); + + if (addr_index < MAX_RISCV_PMPS) { + /* + * In TOR mode, need to check the lock bit of the next pmp + * (if there is a next). + */ + if (addr_index + 1 < MAX_RISCV_PMPS) { + uint8_t pmp_cfg = env->pmp_state.pmp[addr_index + 1].cfg_reg; + + if (pmp_cfg & PMP_LOCK && + PMP_AMATCH_TOR == pmp_get_a_field(pmp_cfg)) { + qemu_log_mask(LOG_GUEST_ERROR, + "ignoring pmpaddr write - pmpcfg + 1 locked\n"); + return; + } + } + + if (!pmp_is_locked(env, addr_index)) { + env->pmp_state.pmp[addr_index].addr_reg = val; + pmp_update_rule(env, addr_index); + } else { + qemu_log_mask(LOG_GUEST_ERROR, + "ignoring pmpaddr write - locked\n"); + } + } else { + qemu_log_mask(LOG_GUEST_ERROR, + "ignoring pmpaddr write - out of bounds\n"); + } +} + + +/* + * Handle a read from a pmpaddr CSR + */ +target_ulong pmpaddr_csr_read(CPURISCVState *env, uint32_t addr_index) +{ + target_ulong val = 0; + + if (addr_index < MAX_RISCV_PMPS) { + val = env->pmp_state.pmp[addr_index].addr_reg; + trace_pmpaddr_csr_read(env->mhartid, addr_index, val); + } else { + qemu_log_mask(LOG_GUEST_ERROR, + "ignoring pmpaddr read - out of bounds\n"); + } + + return val; +} + +/* + * Handle a write to a mseccfg CSR + */ +void mseccfg_csr_write(CPURISCVState *env, target_ulong val) +{ + int i; + + trace_mseccfg_csr_write(env->mhartid, val); + + /* RLB cannot be enabled if it's already 0 and if any regions are locked */ + if (!MSECCFG_RLB_ISSET(env)) { + for (i = 0; i < MAX_RISCV_PMPS; i++) { + if (pmp_is_locked(env, i)) { + val &= ~MSECCFG_RLB; + break; + } + } + } + + /* Sticky bits */ + val |= (env->mseccfg & (MSECCFG_MMWP | MSECCFG_MML)); + + env->mseccfg = val; +} + +/* + * Handle a read from a mseccfg CSR + */ +target_ulong mseccfg_csr_read(CPURISCVState *env) +{ + trace_mseccfg_csr_read(env->mhartid, env->mseccfg); + return env->mseccfg; +} + +/* + * Calculate the TLB size if the start address or the end address of + * PMP entry is presented in the TLB page. + */ +static target_ulong pmp_get_tlb_size(CPURISCVState *env, int pmp_index, + target_ulong tlb_sa, target_ulong tlb_ea) +{ + target_ulong pmp_sa = env->pmp_state.addr[pmp_index].sa; + target_ulong pmp_ea = env->pmp_state.addr[pmp_index].ea; + + if (pmp_sa >= tlb_sa && pmp_ea <= tlb_ea) { + return pmp_ea - pmp_sa + 1; + } + + if (pmp_sa >= tlb_sa && pmp_sa <= tlb_ea && pmp_ea >= tlb_ea) { + return tlb_ea - pmp_sa + 1; + } + + if (pmp_ea <= tlb_ea && pmp_ea >= tlb_sa && pmp_sa <= tlb_sa) { + return pmp_ea - tlb_sa + 1; + } + + return 0; +} + +/* + * Check is there a PMP entry which range covers this page. If so, + * try to find the minimum granularity for the TLB size. + */ +bool pmp_is_range_in_tlb(CPURISCVState *env, hwaddr tlb_sa, + target_ulong *tlb_size) +{ + int i; + target_ulong val; + target_ulong tlb_ea = (tlb_sa + TARGET_PAGE_SIZE - 1); + + for (i = 0; i < MAX_RISCV_PMPS; i++) { + val = pmp_get_tlb_size(env, i, tlb_sa, tlb_ea); + if (val) { + if (*tlb_size == 0 || *tlb_size > val) { + *tlb_size = val; + } + } + } + + if (*tlb_size != 0) { + return true; + } + + return false; +} + +/* + * Convert PMP privilege to TLB page privilege. + */ +int pmp_priv_to_page_prot(pmp_priv_t pmp_priv) +{ + int prot = 0; + + if (pmp_priv & PMP_READ) { + prot |= PAGE_READ; + } + if (pmp_priv & PMP_WRITE) { + prot |= PAGE_WRITE; + } + if (pmp_priv & PMP_EXEC) { + prot |= PAGE_EXEC; + } + + return prot; +} diff --git a/target/riscv/pmp.h b/target/riscv/pmp.h new file mode 100644 index 000000000..a9a0b363a --- /dev/null +++ b/target/riscv/pmp.h @@ -0,0 +1,85 @@ +/* + * QEMU RISC-V PMP (Physical Memory Protection) + * + * Author: Daire McNamara, daire.mcnamara@emdalo.com + * Ivan Griffin, ivan.griffin@emdalo.com + * + * This provides a RISC-V Physical Memory Protection interface + * + * 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 RISCV_PMP_H +#define RISCV_PMP_H + +typedef enum { + PMP_READ = 1 << 0, + PMP_WRITE = 1 << 1, + PMP_EXEC = 1 << 2, + PMP_LOCK = 1 << 7 +} pmp_priv_t; + +typedef enum { + PMP_AMATCH_OFF, /* Null (off) */ + PMP_AMATCH_TOR, /* Top of Range */ + PMP_AMATCH_NA4, /* Naturally aligned four-byte region */ + PMP_AMATCH_NAPOT /* Naturally aligned power-of-two region */ +} pmp_am_t; + +typedef enum { + MSECCFG_MML = 1 << 0, + MSECCFG_MMWP = 1 << 1, + MSECCFG_RLB = 1 << 2 +} mseccfg_field_t; + +typedef struct { + target_ulong addr_reg; + uint8_t cfg_reg; +} pmp_entry_t; + +typedef struct { + target_ulong sa; + target_ulong ea; +} pmp_addr_t; + +typedef struct { + pmp_entry_t pmp[MAX_RISCV_PMPS]; + pmp_addr_t addr[MAX_RISCV_PMPS]; + uint32_t num_rules; +} pmp_table_t; + +void pmpcfg_csr_write(CPURISCVState *env, uint32_t reg_index, + target_ulong val); +target_ulong pmpcfg_csr_read(CPURISCVState *env, uint32_t reg_index); + +void mseccfg_csr_write(CPURISCVState *env, target_ulong val); +target_ulong mseccfg_csr_read(CPURISCVState *env); + +void pmpaddr_csr_write(CPURISCVState *env, uint32_t addr_index, + target_ulong val); +target_ulong pmpaddr_csr_read(CPURISCVState *env, uint32_t addr_index); +bool pmp_hart_has_privs(CPURISCVState *env, target_ulong addr, + target_ulong size, pmp_priv_t privs, pmp_priv_t *allowed_privs, + target_ulong mode); +bool pmp_is_range_in_tlb(CPURISCVState *env, hwaddr tlb_sa, + target_ulong *tlb_size); +void pmp_update_rule_addr(CPURISCVState *env, uint32_t pmp_index); +void pmp_update_rule_nums(CPURISCVState *env); +uint32_t pmp_get_num_rules(CPURISCVState *env); +int pmp_priv_to_page_prot(pmp_priv_t pmp_priv); + +#define MSECCFG_MML_ISSET(env) get_field(env->mseccfg, MSECCFG_MML) +#define MSECCFG_MMWP_ISSET(env) get_field(env->mseccfg, MSECCFG_MMWP) +#define MSECCFG_RLB_ISSET(env) get_field(env->mseccfg, MSECCFG_RLB) + +#endif diff --git a/target/riscv/trace-events b/target/riscv/trace-events new file mode 100644 index 000000000..49ec4d3b7 --- /dev/null +++ b/target/riscv/trace-events @@ -0,0 +1,11 @@ +# cpu_helper.c +riscv_trap(uint64_t hartid, bool async, uint64_t cause, uint64_t epc, uint64_t tval, const char *desc) "hart:%"PRId64", async:%d, cause:%"PRId64", epc:0x%"PRIx64", tval:0x%"PRIx64", desc=%s" + +# pmp.c +pmpcfg_csr_read(uint64_t mhartid, uint32_t reg_index, uint64_t val) "hart %" PRIu64 ": read reg%" PRIu32", val: 0x%" PRIx64 +pmpcfg_csr_write(uint64_t mhartid, uint32_t reg_index, uint64_t val) "hart %" PRIu64 ": write reg%" PRIu32", val: 0x%" PRIx64 +pmpaddr_csr_read(uint64_t mhartid, uint32_t addr_index, uint64_t val) "hart %" PRIu64 ": read addr%" PRIu32", val: 0x%" PRIx64 +pmpaddr_csr_write(uint64_t mhartid, uint32_t addr_index, uint64_t val) "hart %" PRIu64 ": write addr%" PRIu32", val: 0x%" PRIx64 + +mseccfg_csr_read(uint64_t mhartid, uint64_t val) "hart %" PRIu64 ": read mseccfg, val: 0x%" PRIx64 +mseccfg_csr_write(uint64_t mhartid, uint64_t val) "hart %" PRIu64 ": write mseccfg, val: 0x%" PRIx64 diff --git a/target/riscv/trace.h b/target/riscv/trace.h new file mode 100644 index 000000000..03a89fcd9 --- /dev/null +++ b/target/riscv/trace.h @@ -0,0 +1 @@ +#include "trace/trace-target_riscv.h" diff --git a/target/riscv/translate.c b/target/riscv/translate.c new file mode 100644 index 000000000..1d57bc97b --- /dev/null +++ b/target/riscv/translate.c @@ -0,0 +1,773 @@ +/* + * RISC-V emulation for qemu: main translation routines. + * + * Copyright (c) 2016-2017 Sagar Karandikar, sagark@eecs.berkeley.edu + * + * 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/log.h" +#include "cpu.h" +#include "tcg/tcg-op.h" +#include "disas/disas.h" +#include "exec/cpu_ldst.h" +#include "exec/exec-all.h" +#include "exec/helper-proto.h" +#include "exec/helper-gen.h" + +#include "exec/translator.h" +#include "exec/log.h" + +#include "instmap.h" + +/* global register indices */ +static TCGv cpu_gpr[32], cpu_pc, cpu_vl; +static TCGv_i64 cpu_fpr[32]; /* assume F and D extensions */ +static TCGv load_res; +static TCGv load_val; +/* globals for PM CSRs */ +static TCGv pm_mask[4]; +static TCGv pm_base[4]; + +#include "exec/gen-icount.h" + +/* + * If an operation is being performed on less than TARGET_LONG_BITS, + * it may require the inputs to be sign- or zero-extended; which will + * depend on the exact operation being performed. + */ +typedef enum { + EXT_NONE, + EXT_SIGN, + EXT_ZERO, +} DisasExtend; + +typedef struct DisasContext { + DisasContextBase base; + /* pc_succ_insn points to the instruction following base.pc_next */ + target_ulong pc_succ_insn; + target_ulong priv_ver; + RISCVMXL xl; + uint32_t misa_ext; + uint32_t opcode; + uint32_t mstatus_fs; + uint32_t mstatus_hs_fs; + uint32_t mem_idx; + /* Remember the rounding mode encoded in the previous fp instruction, + which we have already installed into env->fp_status. Or -1 for + no previous fp instruction. Note that we exit the TB when writing + to any system register, which includes CSR_FRM, so we do not have + to reset this known value. */ + int frm; + RISCVMXL ol; + bool virt_enabled; + bool ext_ifencei; + bool hlsx; + /* vector extension */ + bool vill; + uint8_t lmul; + uint8_t sew; + uint16_t vlen; + uint16_t mlen; + bool vl_eq_vlmax; + uint8_t ntemp; + CPUState *cs; + TCGv zero; + /* Space for 3 operands plus 1 extra for address computation. */ + TCGv temp[4]; + /* PointerMasking extension */ + bool pm_enabled; + TCGv pm_mask; + TCGv pm_base; +} DisasContext; + +static inline bool has_ext(DisasContext *ctx, uint32_t ext) +{ + return ctx->misa_ext & ext; +} + +#ifdef TARGET_RISCV32 +#define get_xl(ctx) MXL_RV32 +#elif defined(CONFIG_USER_ONLY) +#define get_xl(ctx) MXL_RV64 +#else +#define get_xl(ctx) ((ctx)->xl) +#endif + +/* The word size for this machine mode. */ +static inline int __attribute__((unused)) get_xlen(DisasContext *ctx) +{ + return 16 << get_xl(ctx); +} + +/* The operation length, as opposed to the xlen. */ +#ifdef TARGET_RISCV32 +#define get_ol(ctx) MXL_RV32 +#else +#define get_ol(ctx) ((ctx)->ol) +#endif + +static inline int get_olen(DisasContext *ctx) +{ + return 16 << get_ol(ctx); +} + +/* + * RISC-V requires NaN-boxing of narrower width floating point values. + * This applies when a 32-bit value is assigned to a 64-bit FP register. + * For consistency and simplicity, we nanbox results even when the RVD + * extension is not present. + */ +static void gen_nanbox_s(TCGv_i64 out, TCGv_i64 in) +{ + tcg_gen_ori_i64(out, in, MAKE_64BIT_MASK(32, 32)); +} + +/* + * A narrow n-bit operation, where n < FLEN, checks that input operands + * are correctly Nan-boxed, i.e., all upper FLEN - n bits are 1. + * If so, the least-significant bits of the input are used, otherwise the + * input value is treated as an n-bit canonical NaN (v2.2 section 9.2). + * + * Here, the result is always nan-boxed, even the canonical nan. + */ +static void gen_check_nanbox_s(TCGv_i64 out, TCGv_i64 in) +{ + TCGv_i64 t_max = tcg_constant_i64(0xffffffff00000000ull); + TCGv_i64 t_nan = tcg_constant_i64(0xffffffff7fc00000ull); + + tcg_gen_movcond_i64(TCG_COND_GEU, out, in, t_max, in, t_nan); +} + +static void generate_exception(DisasContext *ctx, int excp) +{ + tcg_gen_movi_tl(cpu_pc, ctx->base.pc_next); + gen_helper_raise_exception(cpu_env, tcg_constant_i32(excp)); + ctx->base.is_jmp = DISAS_NORETURN; +} + +static void generate_exception_mtval(DisasContext *ctx, int excp) +{ + tcg_gen_movi_tl(cpu_pc, ctx->base.pc_next); + tcg_gen_st_tl(cpu_pc, cpu_env, offsetof(CPURISCVState, badaddr)); + gen_helper_raise_exception(cpu_env, tcg_constant_i32(excp)); + ctx->base.is_jmp = DISAS_NORETURN; +} + +static void gen_exception_illegal(DisasContext *ctx) +{ + generate_exception(ctx, RISCV_EXCP_ILLEGAL_INST); +} + +static void gen_exception_inst_addr_mis(DisasContext *ctx) +{ + generate_exception_mtval(ctx, RISCV_EXCP_INST_ADDR_MIS); +} + +static void gen_goto_tb(DisasContext *ctx, int n, target_ulong dest) +{ + if (translator_use_goto_tb(&ctx->base, dest)) { + tcg_gen_goto_tb(n); + tcg_gen_movi_tl(cpu_pc, dest); + tcg_gen_exit_tb(ctx->base.tb, n); + } else { + tcg_gen_movi_tl(cpu_pc, dest); + tcg_gen_lookup_and_goto_ptr(); + } +} + +/* + * Wrappers for getting reg values. + * + * The $zero register does not have cpu_gpr[0] allocated -- we supply the + * constant zero as a source, and an uninitialized sink as destination. + * + * Further, we may provide an extension for word operations. + */ +static TCGv temp_new(DisasContext *ctx) +{ + assert(ctx->ntemp < ARRAY_SIZE(ctx->temp)); + return ctx->temp[ctx->ntemp++] = tcg_temp_new(); +} + +static TCGv get_gpr(DisasContext *ctx, int reg_num, DisasExtend ext) +{ + TCGv t; + + if (reg_num == 0) { + return ctx->zero; + } + + switch (get_ol(ctx)) { + case MXL_RV32: + switch (ext) { + case EXT_NONE: + break; + case EXT_SIGN: + t = temp_new(ctx); + tcg_gen_ext32s_tl(t, cpu_gpr[reg_num]); + return t; + case EXT_ZERO: + t = temp_new(ctx); + tcg_gen_ext32u_tl(t, cpu_gpr[reg_num]); + return t; + default: + g_assert_not_reached(); + } + break; + case MXL_RV64: + break; + default: + g_assert_not_reached(); + } + return cpu_gpr[reg_num]; +} + +static TCGv dest_gpr(DisasContext *ctx, int reg_num) +{ + if (reg_num == 0 || get_olen(ctx) < TARGET_LONG_BITS) { + return temp_new(ctx); + } + return cpu_gpr[reg_num]; +} + +static void gen_set_gpr(DisasContext *ctx, int reg_num, TCGv t) +{ + if (reg_num != 0) { + switch (get_ol(ctx)) { + case MXL_RV32: + tcg_gen_ext32s_tl(cpu_gpr[reg_num], t); + break; + case MXL_RV64: + tcg_gen_mov_tl(cpu_gpr[reg_num], t); + break; + default: + g_assert_not_reached(); + } + } +} + +static void gen_jal(DisasContext *ctx, int rd, target_ulong imm) +{ + target_ulong next_pc; + + /* check misaligned: */ + next_pc = ctx->base.pc_next + imm; + if (!has_ext(ctx, RVC)) { + if ((next_pc & 0x3) != 0) { + gen_exception_inst_addr_mis(ctx); + return; + } + } + if (rd != 0) { + tcg_gen_movi_tl(cpu_gpr[rd], ctx->pc_succ_insn); + } + + gen_goto_tb(ctx, 0, ctx->base.pc_next + imm); /* must use this for safety */ + ctx->base.is_jmp = DISAS_NORETURN; +} + +/* + * Generates address adjustment for PointerMasking + */ +static TCGv gen_pm_adjust_address(DisasContext *s, TCGv src) +{ + TCGv temp; + if (!s->pm_enabled) { + /* Load unmodified address */ + return src; + } else { + temp = temp_new(s); + tcg_gen_andc_tl(temp, src, s->pm_mask); + tcg_gen_or_tl(temp, temp, s->pm_base); + return temp; + } +} + +#ifndef CONFIG_USER_ONLY +/* The states of mstatus_fs are: + * 0 = disabled, 1 = initial, 2 = clean, 3 = dirty + * We will have already diagnosed disabled state, + * and need to turn initial/clean into dirty. + */ +static void mark_fs_dirty(DisasContext *ctx) +{ + TCGv tmp; + + if (ctx->mstatus_fs != MSTATUS_FS) { + /* Remember the state change for the rest of the TB. */ + ctx->mstatus_fs = MSTATUS_FS; + + tmp = tcg_temp_new(); + tcg_gen_ld_tl(tmp, cpu_env, offsetof(CPURISCVState, mstatus)); + tcg_gen_ori_tl(tmp, tmp, MSTATUS_FS); + tcg_gen_st_tl(tmp, cpu_env, offsetof(CPURISCVState, mstatus)); + tcg_temp_free(tmp); + } + + if (ctx->virt_enabled && ctx->mstatus_hs_fs != MSTATUS_FS) { + /* Remember the stage change for the rest of the TB. */ + ctx->mstatus_hs_fs = MSTATUS_FS; + + tmp = tcg_temp_new(); + tcg_gen_ld_tl(tmp, cpu_env, offsetof(CPURISCVState, mstatus_hs)); + tcg_gen_ori_tl(tmp, tmp, MSTATUS_FS); + tcg_gen_st_tl(tmp, cpu_env, offsetof(CPURISCVState, mstatus_hs)); + tcg_temp_free(tmp); + } +} +#else +static inline void mark_fs_dirty(DisasContext *ctx) { } +#endif + +static void gen_set_rm(DisasContext *ctx, int rm) +{ + if (ctx->frm == rm) { + return; + } + ctx->frm = rm; + gen_helper_set_rounding_mode(cpu_env, tcg_constant_i32(rm)); +} + +static int ex_plus_1(DisasContext *ctx, int nf) +{ + return nf + 1; +} + +#define EX_SH(amount) \ + static int ex_shift_##amount(DisasContext *ctx, int imm) \ + { \ + return imm << amount; \ + } +EX_SH(1) +EX_SH(2) +EX_SH(3) +EX_SH(4) +EX_SH(12) + +#define REQUIRE_EXT(ctx, ext) do { \ + if (!has_ext(ctx, ext)) { \ + return false; \ + } \ +} while (0) + +#define REQUIRE_32BIT(ctx) do { \ + if (get_xl(ctx) != MXL_RV32) { \ + return false; \ + } \ +} while (0) + +#define REQUIRE_64BIT(ctx) do { \ + if (get_xl(ctx) < MXL_RV64) { \ + return false; \ + } \ +} while (0) + +static int ex_rvc_register(DisasContext *ctx, int reg) +{ + return 8 + reg; +} + +static int ex_rvc_shifti(DisasContext *ctx, int imm) +{ + /* For RV128 a shamt of 0 means a shift by 64. */ + return imm ? imm : 64; +} + +/* Include the auto-generated decoder for 32 bit insn */ +#include "decode-insn32.c.inc" + +static bool gen_arith_imm_fn(DisasContext *ctx, arg_i *a, DisasExtend ext, + void (*func)(TCGv, TCGv, target_long)) +{ + TCGv dest = dest_gpr(ctx, a->rd); + TCGv src1 = get_gpr(ctx, a->rs1, ext); + + func(dest, src1, a->imm); + + gen_set_gpr(ctx, a->rd, dest); + return true; +} + +static bool gen_arith_imm_tl(DisasContext *ctx, arg_i *a, DisasExtend ext, + void (*func)(TCGv, TCGv, TCGv)) +{ + TCGv dest = dest_gpr(ctx, a->rd); + TCGv src1 = get_gpr(ctx, a->rs1, ext); + TCGv src2 = tcg_constant_tl(a->imm); + + func(dest, src1, src2); + + gen_set_gpr(ctx, a->rd, dest); + return true; +} + +static bool gen_arith(DisasContext *ctx, arg_r *a, DisasExtend ext, + void (*func)(TCGv, TCGv, TCGv)) +{ + TCGv dest = dest_gpr(ctx, a->rd); + TCGv src1 = get_gpr(ctx, a->rs1, ext); + TCGv src2 = get_gpr(ctx, a->rs2, ext); + + func(dest, src1, src2); + + gen_set_gpr(ctx, a->rd, dest); + return true; +} + +static bool gen_arith_per_ol(DisasContext *ctx, arg_r *a, DisasExtend ext, + void (*f_tl)(TCGv, TCGv, TCGv), + void (*f_32)(TCGv, TCGv, TCGv)) +{ + int olen = get_olen(ctx); + + if (olen != TARGET_LONG_BITS) { + if (olen == 32) { + f_tl = f_32; + } else { + g_assert_not_reached(); + } + } + return gen_arith(ctx, a, ext, f_tl); +} + +static bool gen_shift_imm_fn(DisasContext *ctx, arg_shift *a, DisasExtend ext, + void (*func)(TCGv, TCGv, target_long)) +{ + TCGv dest, src1; + int max_len = get_olen(ctx); + + if (a->shamt >= max_len) { + return false; + } + + dest = dest_gpr(ctx, a->rd); + src1 = get_gpr(ctx, a->rs1, ext); + + func(dest, src1, a->shamt); + + gen_set_gpr(ctx, a->rd, dest); + return true; +} + +static bool gen_shift_imm_fn_per_ol(DisasContext *ctx, arg_shift *a, + DisasExtend ext, + void (*f_tl)(TCGv, TCGv, target_long), + void (*f_32)(TCGv, TCGv, target_long)) +{ + int olen = get_olen(ctx); + if (olen != TARGET_LONG_BITS) { + if (olen == 32) { + f_tl = f_32; + } else { + g_assert_not_reached(); + } + } + return gen_shift_imm_fn(ctx, a, ext, f_tl); +} + +static bool gen_shift_imm_tl(DisasContext *ctx, arg_shift *a, DisasExtend ext, + void (*func)(TCGv, TCGv, TCGv)) +{ + TCGv dest, src1, src2; + int max_len = get_olen(ctx); + + if (a->shamt >= max_len) { + return false; + } + + dest = dest_gpr(ctx, a->rd); + src1 = get_gpr(ctx, a->rs1, ext); + src2 = tcg_constant_tl(a->shamt); + + func(dest, src1, src2); + + gen_set_gpr(ctx, a->rd, dest); + return true; +} + +static bool gen_shift(DisasContext *ctx, arg_r *a, DisasExtend ext, + void (*func)(TCGv, TCGv, TCGv)) +{ + TCGv dest = dest_gpr(ctx, a->rd); + TCGv src1 = get_gpr(ctx, a->rs1, ext); + TCGv src2 = get_gpr(ctx, a->rs2, EXT_NONE); + TCGv ext2 = tcg_temp_new(); + + tcg_gen_andi_tl(ext2, src2, get_olen(ctx) - 1); + func(dest, src1, ext2); + + gen_set_gpr(ctx, a->rd, dest); + tcg_temp_free(ext2); + return true; +} + +static bool gen_shift_per_ol(DisasContext *ctx, arg_r *a, DisasExtend ext, + void (*f_tl)(TCGv, TCGv, TCGv), + void (*f_32)(TCGv, TCGv, TCGv)) +{ + int olen = get_olen(ctx); + if (olen != TARGET_LONG_BITS) { + if (olen == 32) { + f_tl = f_32; + } else { + g_assert_not_reached(); + } + } + return gen_shift(ctx, a, ext, f_tl); +} + +static bool gen_unary(DisasContext *ctx, arg_r2 *a, DisasExtend ext, + void (*func)(TCGv, TCGv)) +{ + TCGv dest = dest_gpr(ctx, a->rd); + TCGv src1 = get_gpr(ctx, a->rs1, ext); + + func(dest, src1); + + gen_set_gpr(ctx, a->rd, dest); + return true; +} + +static bool gen_unary_per_ol(DisasContext *ctx, arg_r2 *a, DisasExtend ext, + void (*f_tl)(TCGv, TCGv), + void (*f_32)(TCGv, TCGv)) +{ + int olen = get_olen(ctx); + + if (olen != TARGET_LONG_BITS) { + if (olen == 32) { + f_tl = f_32; + } else { + g_assert_not_reached(); + } + } + return gen_unary(ctx, a, ext, f_tl); +} + +static uint32_t opcode_at(DisasContextBase *dcbase, target_ulong pc) +{ + DisasContext *ctx = container_of(dcbase, DisasContext, base); + CPUState *cpu = ctx->cs; + CPURISCVState *env = cpu->env_ptr; + + return cpu_ldl_code(env, pc); +} + +/* Include insn module translation function */ +#include "insn_trans/trans_rvi.c.inc" +#include "insn_trans/trans_rvm.c.inc" +#include "insn_trans/trans_rva.c.inc" +#include "insn_trans/trans_rvf.c.inc" +#include "insn_trans/trans_rvd.c.inc" +#include "insn_trans/trans_rvh.c.inc" +#include "insn_trans/trans_rvv.c.inc" +#include "insn_trans/trans_rvb.c.inc" +#include "insn_trans/trans_privileged.c.inc" + +/* Include the auto-generated decoder for 16 bit insn */ +#include "decode-insn16.c.inc" + +static void decode_opc(CPURISCVState *env, DisasContext *ctx, uint16_t opcode) +{ + /* check for compressed insn */ + if (extract16(opcode, 0, 2) != 3) { + if (!has_ext(ctx, RVC)) { + gen_exception_illegal(ctx); + } else { + ctx->pc_succ_insn = ctx->base.pc_next + 2; + if (!decode_insn16(ctx, opcode)) { + gen_exception_illegal(ctx); + } + } + } else { + uint32_t opcode32 = opcode; + opcode32 = deposit32(opcode32, 16, 16, + translator_lduw(env, &ctx->base, + ctx->base.pc_next + 2)); + ctx->pc_succ_insn = ctx->base.pc_next + 4; + if (!decode_insn32(ctx, opcode32)) { + gen_exception_illegal(ctx); + } + } +} + +static void riscv_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) +{ + DisasContext *ctx = container_of(dcbase, DisasContext, base); + CPURISCVState *env = cs->env_ptr; + RISCVCPU *cpu = RISCV_CPU(cs); + uint32_t tb_flags = ctx->base.tb->flags; + + ctx->pc_succ_insn = ctx->base.pc_first; + ctx->mem_idx = FIELD_EX32(tb_flags, TB_FLAGS, MEM_IDX); + ctx->mstatus_fs = tb_flags & TB_FLAGS_MSTATUS_FS; + ctx->priv_ver = env->priv_ver; +#if !defined(CONFIG_USER_ONLY) + if (riscv_has_ext(env, RVH)) { + ctx->virt_enabled = riscv_cpu_virt_enabled(env); + } else { + ctx->virt_enabled = false; + } +#else + ctx->virt_enabled = false; +#endif + ctx->misa_ext = env->misa_ext; + ctx->frm = -1; /* unknown rounding mode */ + ctx->ext_ifencei = cpu->cfg.ext_ifencei; + ctx->vlen = cpu->cfg.vlen; + ctx->mstatus_hs_fs = FIELD_EX32(tb_flags, TB_FLAGS, MSTATUS_HS_FS); + ctx->hlsx = FIELD_EX32(tb_flags, TB_FLAGS, HLSX); + ctx->vill = FIELD_EX32(tb_flags, TB_FLAGS, VILL); + ctx->sew = FIELD_EX32(tb_flags, TB_FLAGS, SEW); + ctx->lmul = FIELD_EX32(tb_flags, TB_FLAGS, LMUL); + ctx->mlen = 1 << (ctx->sew + 3 - ctx->lmul); + ctx->vl_eq_vlmax = FIELD_EX32(tb_flags, TB_FLAGS, VL_EQ_VLMAX); + ctx->xl = FIELD_EX32(tb_flags, TB_FLAGS, XL); + ctx->cs = cs; + ctx->ntemp = 0; + memset(ctx->temp, 0, sizeof(ctx->temp)); + ctx->pm_enabled = FIELD_EX32(tb_flags, TB_FLAGS, PM_ENABLED); + int priv = tb_flags & TB_FLAGS_PRIV_MMU_MASK; + ctx->pm_mask = pm_mask[priv]; + ctx->pm_base = pm_base[priv]; + + ctx->zero = tcg_constant_tl(0); +} + +static void riscv_tr_tb_start(DisasContextBase *db, CPUState *cpu) +{ +} + +static void riscv_tr_insn_start(DisasContextBase *dcbase, CPUState *cpu) +{ + DisasContext *ctx = container_of(dcbase, DisasContext, base); + + tcg_gen_insn_start(ctx->base.pc_next); +} + +static void riscv_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) +{ + DisasContext *ctx = container_of(dcbase, DisasContext, base); + CPURISCVState *env = cpu->env_ptr; + uint16_t opcode16 = translator_lduw(env, &ctx->base, ctx->base.pc_next); + + ctx->ol = ctx->xl; + decode_opc(env, ctx, opcode16); + ctx->base.pc_next = ctx->pc_succ_insn; + + for (int i = ctx->ntemp - 1; i >= 0; --i) { + tcg_temp_free(ctx->temp[i]); + ctx->temp[i] = NULL; + } + ctx->ntemp = 0; + + if (ctx->base.is_jmp == DISAS_NEXT) { + target_ulong page_start; + + page_start = ctx->base.pc_first & TARGET_PAGE_MASK; + if (ctx->base.pc_next - page_start >= TARGET_PAGE_SIZE) { + ctx->base.is_jmp = DISAS_TOO_MANY; + } + } +} + +static void riscv_tr_tb_stop(DisasContextBase *dcbase, CPUState *cpu) +{ + DisasContext *ctx = container_of(dcbase, DisasContext, base); + + switch (ctx->base.is_jmp) { + case DISAS_TOO_MANY: + gen_goto_tb(ctx, 0, ctx->base.pc_next); + break; + case DISAS_NORETURN: + break; + default: + g_assert_not_reached(); + } +} + +static void riscv_tr_disas_log(const DisasContextBase *dcbase, CPUState *cpu) +{ +#ifndef CONFIG_USER_ONLY + RISCVCPU *rvcpu = RISCV_CPU(cpu); + CPURISCVState *env = &rvcpu->env; +#endif + + qemu_log("IN: %s\n", lookup_symbol(dcbase->pc_first)); +#ifndef CONFIG_USER_ONLY + qemu_log("Priv: "TARGET_FMT_ld"; Virt: "TARGET_FMT_ld"\n", env->priv, env->virt); +#endif + log_target_disas(cpu, dcbase->pc_first, dcbase->tb->size); +} + +static const TranslatorOps riscv_tr_ops = { + .init_disas_context = riscv_tr_init_disas_context, + .tb_start = riscv_tr_tb_start, + .insn_start = riscv_tr_insn_start, + .translate_insn = riscv_tr_translate_insn, + .tb_stop = riscv_tr_tb_stop, + .disas_log = riscv_tr_disas_log, +}; + +void gen_intermediate_code(CPUState *cs, TranslationBlock *tb, int max_insns) +{ + DisasContext ctx; + + translator_loop(&riscv_tr_ops, &ctx.base, cs, tb, max_insns); +} + +void riscv_translate_init(void) +{ + int i; + + /* + * cpu_gpr[0] is a placeholder for the zero register. Do not use it. + * Use the gen_set_gpr and get_gpr helper functions when accessing regs, + * unless you specifically block reads/writes to reg 0. + */ + cpu_gpr[0] = NULL; + + for (i = 1; i < 32; i++) { + cpu_gpr[i] = tcg_global_mem_new(cpu_env, + offsetof(CPURISCVState, gpr[i]), riscv_int_regnames[i]); + } + + for (i = 0; i < 32; i++) { + cpu_fpr[i] = tcg_global_mem_new_i64(cpu_env, + offsetof(CPURISCVState, fpr[i]), riscv_fpr_regnames[i]); + } + + cpu_pc = tcg_global_mem_new(cpu_env, offsetof(CPURISCVState, pc), "pc"); + cpu_vl = tcg_global_mem_new(cpu_env, offsetof(CPURISCVState, vl), "vl"); + load_res = tcg_global_mem_new(cpu_env, offsetof(CPURISCVState, load_res), + "load_res"); + load_val = tcg_global_mem_new(cpu_env, offsetof(CPURISCVState, load_val), + "load_val"); +#ifndef CONFIG_USER_ONLY + /* Assign PM CSRs to tcg globals */ + pm_mask[PRV_U] = + tcg_global_mem_new(cpu_env, offsetof(CPURISCVState, upmmask), "upmmask"); + pm_base[PRV_U] = + tcg_global_mem_new(cpu_env, offsetof(CPURISCVState, upmbase), "upmbase"); + pm_mask[PRV_S] = + tcg_global_mem_new(cpu_env, offsetof(CPURISCVState, spmmask), "spmmask"); + pm_base[PRV_S] = + tcg_global_mem_new(cpu_env, offsetof(CPURISCVState, spmbase), "spmbase"); + pm_mask[PRV_M] = + tcg_global_mem_new(cpu_env, offsetof(CPURISCVState, mpmmask), "mpmmask"); + pm_base[PRV_M] = + tcg_global_mem_new(cpu_env, offsetof(CPURISCVState, mpmbase), "mpmbase"); +#endif +} diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c new file mode 100644 index 000000000..12c31aa4b --- /dev/null +++ b/target/riscv/vector_helper.c @@ -0,0 +1,4872 @@ +/* + * RISC-V Vector Extension Helpers for QEMU. + * + * 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 "qemu/osdep.h" +#include "cpu.h" +#include "exec/memop.h" +#include "exec/exec-all.h" +#include "exec/helper-proto.h" +#include "fpu/softfloat.h" +#include "tcg/tcg-gvec-desc.h" +#include "internals.h" +#include <math.h> + +target_ulong HELPER(vsetvl)(CPURISCVState *env, target_ulong s1, + target_ulong s2) +{ + int vlmax, vl; + RISCVCPU *cpu = env_archcpu(env); + uint16_t sew = 8 << FIELD_EX64(s2, VTYPE, VSEW); + uint8_t ediv = FIELD_EX64(s2, VTYPE, VEDIV); + bool vill = FIELD_EX64(s2, VTYPE, VILL); + target_ulong reserved = FIELD_EX64(s2, VTYPE, RESERVED); + + if ((sew > cpu->cfg.elen) || vill || (ediv != 0) || (reserved != 0)) { + /* only set vill bit. */ + env->vtype = FIELD_DP64(0, VTYPE, VILL, 1); + env->vl = 0; + env->vstart = 0; + return 0; + } + + vlmax = vext_get_vlmax(cpu, s2); + if (s1 <= vlmax) { + vl = s1; + } else { + vl = vlmax; + } + env->vl = vl; + env->vtype = s2; + env->vstart = 0; + return vl; +} + +/* + * Note that vector data is stored in host-endian 64-bit chunks, + * so addressing units smaller than that needs a host-endian fixup. + */ +#ifdef HOST_WORDS_BIGENDIAN +#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_mlen(uint32_t desc) +{ + return FIELD_EX32(simd_data(desc), VDATA, MLEN); +} + +static inline uint32_t vext_vm(uint32_t desc) +{ + return FIELD_EX32(simd_data(desc), VDATA, VM); +} + +static inline uint32_t vext_lmul(uint32_t desc) +{ + return FIELD_EX32(simd_data(desc), VDATA, LMUL); +} + +static uint32_t vext_wd(uint32_t desc) +{ + return (simd_data(desc) >> 11) & 0x1; +} + +/* + * Get vector group length in bytes. Its range is [64, 2048]. + * + * As simd_desc support at most 256, the max vlen is 512 bits. + * So vlen in bytes is encoded as maxsz. + */ +static inline uint32_t vext_maxsz(uint32_t desc) +{ + return simd_maxsz(desc) << vext_lmul(desc); +} + +/* + * This function checks watchpoint before real load operation. + * + * In softmmu mode, the TLB API probe_access is enough for watchpoint check. + * In user mode, there is no watchpoint support now. + * + * It will trigger an exception if there is no mapping in TLB + * and page table walk can't fill the TLB entry. Then the guest + * software can return here after process the exception or never return. + */ +static void probe_pages(CPURISCVState *env, target_ulong addr, + target_ulong len, uintptr_t ra, + MMUAccessType access_type) +{ + target_ulong pagelen = -(addr | TARGET_PAGE_MASK); + target_ulong curlen = MIN(pagelen, len); + + probe_access(env, addr, curlen, access_type, + cpu_mmu_index(env, false), ra); + if (len > curlen) { + addr += curlen; + curlen = len - curlen; + probe_access(env, addr, curlen, access_type, + cpu_mmu_index(env, false), ra); + } +} + +#ifdef HOST_WORDS_BIGENDIAN +static void vext_clear(void *tail, uint32_t cnt, uint32_t tot) +{ + /* + * Split the remaining range to two parts. + * The first part is in the last uint64_t unit. + * The second part start from the next uint64_t unit. + */ + int part1 = 0, part2 = tot - cnt; + if (cnt % 8) { + part1 = 8 - (cnt % 8); + part2 = tot - cnt - part1; + memset(QEMU_ALIGN_PTR_DOWN(tail, 8), 0, part1); + memset(QEMU_ALIGN_PTR_UP(tail, 8), 0, part2); + } else { + memset(tail, 0, part2); + } +} +#else +static void vext_clear(void *tail, uint32_t cnt, uint32_t tot) +{ + memset(tail, 0, tot - cnt); +} +#endif + +static void clearb(void *vd, uint32_t idx, uint32_t cnt, uint32_t tot) +{ + int8_t *cur = ((int8_t *)vd + H1(idx)); + vext_clear(cur, cnt, tot); +} + +static void clearh(void *vd, uint32_t idx, uint32_t cnt, uint32_t tot) +{ + int16_t *cur = ((int16_t *)vd + H2(idx)); + vext_clear(cur, cnt, tot); +} + +static void clearl(void *vd, uint32_t idx, uint32_t cnt, uint32_t tot) +{ + int32_t *cur = ((int32_t *)vd + H4(idx)); + vext_clear(cur, cnt, tot); +} + +static void clearq(void *vd, uint32_t idx, uint32_t cnt, uint32_t tot) +{ + int64_t *cur = (int64_t *)vd + idx; + vext_clear(cur, cnt, tot); +} + +static inline void vext_set_elem_mask(void *v0, int mlen, int index, + uint8_t value) +{ + int idx = (index * mlen) / 64; + int pos = (index * mlen) % 64; + uint64_t old = ((uint64_t *)v0)[idx]; + ((uint64_t *)v0)[idx] = deposit64(old, pos, mlen, value); +} + +static inline int vext_elem_mask(void *v0, int mlen, int index) +{ + int idx = (index * mlen) / 64; + int pos = (index * mlen) % 64; + return (((uint64_t *)v0)[idx] >> pos) & 1; +} + +/* elements operations for load and store */ +typedef void vext_ldst_elem_fn(CPURISCVState *env, target_ulong addr, + uint32_t idx, void *vd, uintptr_t retaddr); +typedef void clear_fn(void *vd, uint32_t idx, uint32_t cnt, uint32_t tot); + +#define GEN_VEXT_LD_ELEM(NAME, MTYPE, ETYPE, H, LDSUF) \ +static void NAME(CPURISCVState *env, abi_ptr addr, \ + uint32_t idx, void *vd, uintptr_t retaddr)\ +{ \ + MTYPE data; \ + ETYPE *cur = ((ETYPE *)vd + H(idx)); \ + data = cpu_##LDSUF##_data_ra(env, addr, retaddr); \ + *cur = data; \ +} \ + +GEN_VEXT_LD_ELEM(ldb_b, int8_t, int8_t, H1, ldsb) +GEN_VEXT_LD_ELEM(ldb_h, int8_t, int16_t, H2, ldsb) +GEN_VEXT_LD_ELEM(ldb_w, int8_t, int32_t, H4, ldsb) +GEN_VEXT_LD_ELEM(ldb_d, int8_t, int64_t, H8, ldsb) +GEN_VEXT_LD_ELEM(ldh_h, int16_t, int16_t, H2, ldsw) +GEN_VEXT_LD_ELEM(ldh_w, int16_t, int32_t, H4, ldsw) +GEN_VEXT_LD_ELEM(ldh_d, int16_t, int64_t, H8, ldsw) +GEN_VEXT_LD_ELEM(ldw_w, int32_t, int32_t, H4, ldl) +GEN_VEXT_LD_ELEM(ldw_d, int32_t, int64_t, H8, ldl) +GEN_VEXT_LD_ELEM(lde_b, int8_t, int8_t, H1, ldsb) +GEN_VEXT_LD_ELEM(lde_h, int16_t, int16_t, H2, ldsw) +GEN_VEXT_LD_ELEM(lde_w, int32_t, int32_t, H4, ldl) +GEN_VEXT_LD_ELEM(lde_d, int64_t, int64_t, H8, ldq) +GEN_VEXT_LD_ELEM(ldbu_b, uint8_t, uint8_t, H1, ldub) +GEN_VEXT_LD_ELEM(ldbu_h, uint8_t, uint16_t, H2, ldub) +GEN_VEXT_LD_ELEM(ldbu_w, uint8_t, uint32_t, H4, ldub) +GEN_VEXT_LD_ELEM(ldbu_d, uint8_t, uint64_t, H8, ldub) +GEN_VEXT_LD_ELEM(ldhu_h, uint16_t, uint16_t, H2, lduw) +GEN_VEXT_LD_ELEM(ldhu_w, uint16_t, uint32_t, H4, lduw) +GEN_VEXT_LD_ELEM(ldhu_d, uint16_t, uint64_t, H8, lduw) +GEN_VEXT_LD_ELEM(ldwu_w, uint32_t, uint32_t, H4, ldl) +GEN_VEXT_LD_ELEM(ldwu_d, uint32_t, uint64_t, H8, ldl) + +#define GEN_VEXT_ST_ELEM(NAME, ETYPE, H, STSUF) \ +static void NAME(CPURISCVState *env, abi_ptr addr, \ + uint32_t idx, void *vd, uintptr_t retaddr)\ +{ \ + ETYPE data = *((ETYPE *)vd + H(idx)); \ + cpu_##STSUF##_data_ra(env, addr, data, retaddr); \ +} + +GEN_VEXT_ST_ELEM(stb_b, int8_t, H1, stb) +GEN_VEXT_ST_ELEM(stb_h, int16_t, H2, stb) +GEN_VEXT_ST_ELEM(stb_w, int32_t, H4, stb) +GEN_VEXT_ST_ELEM(stb_d, int64_t, H8, stb) +GEN_VEXT_ST_ELEM(sth_h, int16_t, H2, stw) +GEN_VEXT_ST_ELEM(sth_w, int32_t, H4, stw) +GEN_VEXT_ST_ELEM(sth_d, int64_t, H8, stw) +GEN_VEXT_ST_ELEM(stw_w, int32_t, H4, stl) +GEN_VEXT_ST_ELEM(stw_d, int64_t, H8, stl) +GEN_VEXT_ST_ELEM(ste_b, int8_t, H1, stb) +GEN_VEXT_ST_ELEM(ste_h, int16_t, H2, stw) +GEN_VEXT_ST_ELEM(ste_w, int32_t, H4, stl) +GEN_VEXT_ST_ELEM(ste_d, int64_t, H8, stq) + +/* + *** stride: access vector element from strided memory + */ +static void +vext_ldst_stride(void *vd, void *v0, target_ulong base, + target_ulong stride, CPURISCVState *env, + uint32_t desc, uint32_t vm, + vext_ldst_elem_fn *ldst_elem, clear_fn *clear_elem, + uint32_t esz, uint32_t msz, uintptr_t ra, + MMUAccessType access_type) +{ + uint32_t i, k; + uint32_t nf = vext_nf(desc); + uint32_t mlen = vext_mlen(desc); + uint32_t vlmax = vext_maxsz(desc) / esz; + + /* probe every access*/ + for (i = 0; i < env->vl; i++) { + if (!vm && !vext_elem_mask(v0, mlen, i)) { + continue; + } + probe_pages(env, base + stride * i, nf * msz, ra, access_type); + } + /* do real access */ + for (i = 0; i < env->vl; i++) { + k = 0; + if (!vm && !vext_elem_mask(v0, mlen, i)) { + continue; + } + while (k < nf) { + target_ulong addr = base + stride * i + k * msz; + ldst_elem(env, addr, i + k * vlmax, vd, ra); + k++; + } + } + /* clear tail elements */ + if (clear_elem) { + for (k = 0; k < nf; k++) { + clear_elem(vd, env->vl + k * vlmax, env->vl * esz, vlmax * esz); + } + } +} + +#define GEN_VEXT_LD_STRIDE(NAME, MTYPE, ETYPE, LOAD_FN, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void * v0, target_ulong base, \ + target_ulong stride, CPURISCVState *env, \ + uint32_t desc) \ +{ \ + uint32_t vm = vext_vm(desc); \ + vext_ldst_stride(vd, v0, base, stride, env, desc, vm, LOAD_FN, \ + CLEAR_FN, sizeof(ETYPE), sizeof(MTYPE), \ + GETPC(), MMU_DATA_LOAD); \ +} + +GEN_VEXT_LD_STRIDE(vlsb_v_b, int8_t, int8_t, ldb_b, clearb) +GEN_VEXT_LD_STRIDE(vlsb_v_h, int8_t, int16_t, ldb_h, clearh) +GEN_VEXT_LD_STRIDE(vlsb_v_w, int8_t, int32_t, ldb_w, clearl) +GEN_VEXT_LD_STRIDE(vlsb_v_d, int8_t, int64_t, ldb_d, clearq) +GEN_VEXT_LD_STRIDE(vlsh_v_h, int16_t, int16_t, ldh_h, clearh) +GEN_VEXT_LD_STRIDE(vlsh_v_w, int16_t, int32_t, ldh_w, clearl) +GEN_VEXT_LD_STRIDE(vlsh_v_d, int16_t, int64_t, ldh_d, clearq) +GEN_VEXT_LD_STRIDE(vlsw_v_w, int32_t, int32_t, ldw_w, clearl) +GEN_VEXT_LD_STRIDE(vlsw_v_d, int32_t, int64_t, ldw_d, clearq) +GEN_VEXT_LD_STRIDE(vlse_v_b, int8_t, int8_t, lde_b, clearb) +GEN_VEXT_LD_STRIDE(vlse_v_h, int16_t, int16_t, lde_h, clearh) +GEN_VEXT_LD_STRIDE(vlse_v_w, int32_t, int32_t, lde_w, clearl) +GEN_VEXT_LD_STRIDE(vlse_v_d, int64_t, int64_t, lde_d, clearq) +GEN_VEXT_LD_STRIDE(vlsbu_v_b, uint8_t, uint8_t, ldbu_b, clearb) +GEN_VEXT_LD_STRIDE(vlsbu_v_h, uint8_t, uint16_t, ldbu_h, clearh) +GEN_VEXT_LD_STRIDE(vlsbu_v_w, uint8_t, uint32_t, ldbu_w, clearl) +GEN_VEXT_LD_STRIDE(vlsbu_v_d, uint8_t, uint64_t, ldbu_d, clearq) +GEN_VEXT_LD_STRIDE(vlshu_v_h, uint16_t, uint16_t, ldhu_h, clearh) +GEN_VEXT_LD_STRIDE(vlshu_v_w, uint16_t, uint32_t, ldhu_w, clearl) +GEN_VEXT_LD_STRIDE(vlshu_v_d, uint16_t, uint64_t, ldhu_d, clearq) +GEN_VEXT_LD_STRIDE(vlswu_v_w, uint32_t, uint32_t, ldwu_w, clearl) +GEN_VEXT_LD_STRIDE(vlswu_v_d, uint32_t, uint64_t, ldwu_d, clearq) + +#define GEN_VEXT_ST_STRIDE(NAME, MTYPE, ETYPE, STORE_FN) \ +void HELPER(NAME)(void *vd, void *v0, target_ulong base, \ + target_ulong stride, CPURISCVState *env, \ + uint32_t desc) \ +{ \ + uint32_t vm = vext_vm(desc); \ + vext_ldst_stride(vd, v0, base, stride, env, desc, vm, STORE_FN, \ + NULL, sizeof(ETYPE), sizeof(MTYPE), \ + GETPC(), MMU_DATA_STORE); \ +} + +GEN_VEXT_ST_STRIDE(vssb_v_b, int8_t, int8_t, stb_b) +GEN_VEXT_ST_STRIDE(vssb_v_h, int8_t, int16_t, stb_h) +GEN_VEXT_ST_STRIDE(vssb_v_w, int8_t, int32_t, stb_w) +GEN_VEXT_ST_STRIDE(vssb_v_d, int8_t, int64_t, stb_d) +GEN_VEXT_ST_STRIDE(vssh_v_h, int16_t, int16_t, sth_h) +GEN_VEXT_ST_STRIDE(vssh_v_w, int16_t, int32_t, sth_w) +GEN_VEXT_ST_STRIDE(vssh_v_d, int16_t, int64_t, sth_d) +GEN_VEXT_ST_STRIDE(vssw_v_w, int32_t, int32_t, stw_w) +GEN_VEXT_ST_STRIDE(vssw_v_d, int32_t, int64_t, stw_d) +GEN_VEXT_ST_STRIDE(vsse_v_b, int8_t, int8_t, ste_b) +GEN_VEXT_ST_STRIDE(vsse_v_h, int16_t, int16_t, ste_h) +GEN_VEXT_ST_STRIDE(vsse_v_w, int32_t, int32_t, ste_w) +GEN_VEXT_ST_STRIDE(vsse_v_d, int64_t, int64_t, ste_d) + +/* + *** unit-stride: access elements stored contiguously in memory + */ + +/* unmasked unit-stride load and store operation*/ +static void +vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc, + vext_ldst_elem_fn *ldst_elem, clear_fn *clear_elem, + uint32_t esz, uint32_t msz, uintptr_t ra, + MMUAccessType access_type) +{ + uint32_t i, k; + uint32_t nf = vext_nf(desc); + uint32_t vlmax = vext_maxsz(desc) / esz; + + /* probe every access */ + probe_pages(env, base, env->vl * nf * msz, ra, access_type); + /* load bytes from guest memory */ + for (i = 0; i < env->vl; i++) { + k = 0; + while (k < nf) { + target_ulong addr = base + (i * nf + k) * msz; + ldst_elem(env, addr, i + k * vlmax, vd, ra); + k++; + } + } + /* clear tail elements */ + if (clear_elem) { + for (k = 0; k < nf; k++) { + clear_elem(vd, env->vl + k * vlmax, env->vl * esz, vlmax * esz); + } + } +} + +/* + * masked unit-stride load and store operation will be a special case of stride, + * stride = NF * sizeof (MTYPE) + */ + +#define GEN_VEXT_LD_US(NAME, MTYPE, ETYPE, LOAD_FN, CLEAR_FN) \ +void HELPER(NAME##_mask)(void *vd, void *v0, target_ulong base, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t stride = vext_nf(desc) * sizeof(MTYPE); \ + vext_ldst_stride(vd, v0, base, stride, env, desc, false, LOAD_FN, \ + CLEAR_FN, sizeof(ETYPE), sizeof(MTYPE), \ + GETPC(), MMU_DATA_LOAD); \ +} \ + \ +void HELPER(NAME)(void *vd, void *v0, target_ulong base, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + vext_ldst_us(vd, base, env, desc, LOAD_FN, CLEAR_FN, \ + sizeof(ETYPE), sizeof(MTYPE), GETPC(), MMU_DATA_LOAD); \ +} + +GEN_VEXT_LD_US(vlb_v_b, int8_t, int8_t, ldb_b, clearb) +GEN_VEXT_LD_US(vlb_v_h, int8_t, int16_t, ldb_h, clearh) +GEN_VEXT_LD_US(vlb_v_w, int8_t, int32_t, ldb_w, clearl) +GEN_VEXT_LD_US(vlb_v_d, int8_t, int64_t, ldb_d, clearq) +GEN_VEXT_LD_US(vlh_v_h, int16_t, int16_t, ldh_h, clearh) +GEN_VEXT_LD_US(vlh_v_w, int16_t, int32_t, ldh_w, clearl) +GEN_VEXT_LD_US(vlh_v_d, int16_t, int64_t, ldh_d, clearq) +GEN_VEXT_LD_US(vlw_v_w, int32_t, int32_t, ldw_w, clearl) +GEN_VEXT_LD_US(vlw_v_d, int32_t, int64_t, ldw_d, clearq) +GEN_VEXT_LD_US(vle_v_b, int8_t, int8_t, lde_b, clearb) +GEN_VEXT_LD_US(vle_v_h, int16_t, int16_t, lde_h, clearh) +GEN_VEXT_LD_US(vle_v_w, int32_t, int32_t, lde_w, clearl) +GEN_VEXT_LD_US(vle_v_d, int64_t, int64_t, lde_d, clearq) +GEN_VEXT_LD_US(vlbu_v_b, uint8_t, uint8_t, ldbu_b, clearb) +GEN_VEXT_LD_US(vlbu_v_h, uint8_t, uint16_t, ldbu_h, clearh) +GEN_VEXT_LD_US(vlbu_v_w, uint8_t, uint32_t, ldbu_w, clearl) +GEN_VEXT_LD_US(vlbu_v_d, uint8_t, uint64_t, ldbu_d, clearq) +GEN_VEXT_LD_US(vlhu_v_h, uint16_t, uint16_t, ldhu_h, clearh) +GEN_VEXT_LD_US(vlhu_v_w, uint16_t, uint32_t, ldhu_w, clearl) +GEN_VEXT_LD_US(vlhu_v_d, uint16_t, uint64_t, ldhu_d, clearq) +GEN_VEXT_LD_US(vlwu_v_w, uint32_t, uint32_t, ldwu_w, clearl) +GEN_VEXT_LD_US(vlwu_v_d, uint32_t, uint64_t, ldwu_d, clearq) + +#define GEN_VEXT_ST_US(NAME, MTYPE, ETYPE, STORE_FN) \ +void HELPER(NAME##_mask)(void *vd, void *v0, target_ulong base, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t stride = vext_nf(desc) * sizeof(MTYPE); \ + vext_ldst_stride(vd, v0, base, stride, env, desc, false, STORE_FN, \ + NULL, sizeof(ETYPE), sizeof(MTYPE), \ + GETPC(), MMU_DATA_STORE); \ +} \ + \ +void HELPER(NAME)(void *vd, void *v0, target_ulong base, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + vext_ldst_us(vd, base, env, desc, STORE_FN, NULL, \ + sizeof(ETYPE), sizeof(MTYPE), GETPC(), MMU_DATA_STORE);\ +} + +GEN_VEXT_ST_US(vsb_v_b, int8_t, int8_t , stb_b) +GEN_VEXT_ST_US(vsb_v_h, int8_t, int16_t, stb_h) +GEN_VEXT_ST_US(vsb_v_w, int8_t, int32_t, stb_w) +GEN_VEXT_ST_US(vsb_v_d, int8_t, int64_t, stb_d) +GEN_VEXT_ST_US(vsh_v_h, int16_t, int16_t, sth_h) +GEN_VEXT_ST_US(vsh_v_w, int16_t, int32_t, sth_w) +GEN_VEXT_ST_US(vsh_v_d, int16_t, int64_t, sth_d) +GEN_VEXT_ST_US(vsw_v_w, int32_t, int32_t, stw_w) +GEN_VEXT_ST_US(vsw_v_d, int32_t, int64_t, stw_d) +GEN_VEXT_ST_US(vse_v_b, int8_t, int8_t , ste_b) +GEN_VEXT_ST_US(vse_v_h, int16_t, int16_t, ste_h) +GEN_VEXT_ST_US(vse_v_w, int32_t, int32_t, ste_w) +GEN_VEXT_ST_US(vse_v_d, int64_t, int64_t, ste_d) + +/* + *** index: access vector element from indexed memory + */ +typedef target_ulong vext_get_index_addr(target_ulong base, + uint32_t idx, void *vs2); + +#define GEN_VEXT_GET_INDEX_ADDR(NAME, ETYPE, H) \ +static target_ulong NAME(target_ulong base, \ + uint32_t idx, void *vs2) \ +{ \ + return (base + *((ETYPE *)vs2 + H(idx))); \ +} + +GEN_VEXT_GET_INDEX_ADDR(idx_b, int8_t, H1) +GEN_VEXT_GET_INDEX_ADDR(idx_h, int16_t, H2) +GEN_VEXT_GET_INDEX_ADDR(idx_w, int32_t, H4) +GEN_VEXT_GET_INDEX_ADDR(idx_d, int64_t, H8) + +static inline void +vext_ldst_index(void *vd, void *v0, target_ulong base, + void *vs2, CPURISCVState *env, uint32_t desc, + vext_get_index_addr get_index_addr, + vext_ldst_elem_fn *ldst_elem, + clear_fn *clear_elem, + uint32_t esz, uint32_t msz, uintptr_t ra, + MMUAccessType access_type) +{ + uint32_t i, k; + uint32_t nf = vext_nf(desc); + uint32_t vm = vext_vm(desc); + uint32_t mlen = vext_mlen(desc); + uint32_t vlmax = vext_maxsz(desc) / esz; + + /* probe every access*/ + for (i = 0; i < env->vl; i++) { + if (!vm && !vext_elem_mask(v0, mlen, i)) { + continue; + } + probe_pages(env, get_index_addr(base, i, vs2), nf * msz, ra, + access_type); + } + /* load bytes from guest memory */ + for (i = 0; i < env->vl; i++) { + k = 0; + if (!vm && !vext_elem_mask(v0, mlen, i)) { + continue; + } + while (k < nf) { + abi_ptr addr = get_index_addr(base, i, vs2) + k * msz; + ldst_elem(env, addr, i + k * vlmax, vd, ra); + k++; + } + } + /* clear tail elements */ + if (clear_elem) { + for (k = 0; k < nf; k++) { + clear_elem(vd, env->vl + k * vlmax, env->vl * esz, vlmax * esz); + } + } +} + +#define GEN_VEXT_LD_INDEX(NAME, MTYPE, ETYPE, INDEX_FN, LOAD_FN, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, target_ulong base, \ + void *vs2, CPURISCVState *env, uint32_t desc) \ +{ \ + vext_ldst_index(vd, v0, base, vs2, env, desc, INDEX_FN, \ + LOAD_FN, CLEAR_FN, sizeof(ETYPE), sizeof(MTYPE), \ + GETPC(), MMU_DATA_LOAD); \ +} + +GEN_VEXT_LD_INDEX(vlxb_v_b, int8_t, int8_t, idx_b, ldb_b, clearb) +GEN_VEXT_LD_INDEX(vlxb_v_h, int8_t, int16_t, idx_h, ldb_h, clearh) +GEN_VEXT_LD_INDEX(vlxb_v_w, int8_t, int32_t, idx_w, ldb_w, clearl) +GEN_VEXT_LD_INDEX(vlxb_v_d, int8_t, int64_t, idx_d, ldb_d, clearq) +GEN_VEXT_LD_INDEX(vlxh_v_h, int16_t, int16_t, idx_h, ldh_h, clearh) +GEN_VEXT_LD_INDEX(vlxh_v_w, int16_t, int32_t, idx_w, ldh_w, clearl) +GEN_VEXT_LD_INDEX(vlxh_v_d, int16_t, int64_t, idx_d, ldh_d, clearq) +GEN_VEXT_LD_INDEX(vlxw_v_w, int32_t, int32_t, idx_w, ldw_w, clearl) +GEN_VEXT_LD_INDEX(vlxw_v_d, int32_t, int64_t, idx_d, ldw_d, clearq) +GEN_VEXT_LD_INDEX(vlxe_v_b, int8_t, int8_t, idx_b, lde_b, clearb) +GEN_VEXT_LD_INDEX(vlxe_v_h, int16_t, int16_t, idx_h, lde_h, clearh) +GEN_VEXT_LD_INDEX(vlxe_v_w, int32_t, int32_t, idx_w, lde_w, clearl) +GEN_VEXT_LD_INDEX(vlxe_v_d, int64_t, int64_t, idx_d, lde_d, clearq) +GEN_VEXT_LD_INDEX(vlxbu_v_b, uint8_t, uint8_t, idx_b, ldbu_b, clearb) +GEN_VEXT_LD_INDEX(vlxbu_v_h, uint8_t, uint16_t, idx_h, ldbu_h, clearh) +GEN_VEXT_LD_INDEX(vlxbu_v_w, uint8_t, uint32_t, idx_w, ldbu_w, clearl) +GEN_VEXT_LD_INDEX(vlxbu_v_d, uint8_t, uint64_t, idx_d, ldbu_d, clearq) +GEN_VEXT_LD_INDEX(vlxhu_v_h, uint16_t, uint16_t, idx_h, ldhu_h, clearh) +GEN_VEXT_LD_INDEX(vlxhu_v_w, uint16_t, uint32_t, idx_w, ldhu_w, clearl) +GEN_VEXT_LD_INDEX(vlxhu_v_d, uint16_t, uint64_t, idx_d, ldhu_d, clearq) +GEN_VEXT_LD_INDEX(vlxwu_v_w, uint32_t, uint32_t, idx_w, ldwu_w, clearl) +GEN_VEXT_LD_INDEX(vlxwu_v_d, uint32_t, uint64_t, idx_d, ldwu_d, clearq) + +#define GEN_VEXT_ST_INDEX(NAME, MTYPE, ETYPE, INDEX_FN, STORE_FN)\ +void HELPER(NAME)(void *vd, void *v0, target_ulong base, \ + void *vs2, CPURISCVState *env, uint32_t desc) \ +{ \ + vext_ldst_index(vd, v0, base, vs2, env, desc, INDEX_FN, \ + STORE_FN, NULL, sizeof(ETYPE), sizeof(MTYPE),\ + GETPC(), MMU_DATA_STORE); \ +} + +GEN_VEXT_ST_INDEX(vsxb_v_b, int8_t, int8_t, idx_b, stb_b) +GEN_VEXT_ST_INDEX(vsxb_v_h, int8_t, int16_t, idx_h, stb_h) +GEN_VEXT_ST_INDEX(vsxb_v_w, int8_t, int32_t, idx_w, stb_w) +GEN_VEXT_ST_INDEX(vsxb_v_d, int8_t, int64_t, idx_d, stb_d) +GEN_VEXT_ST_INDEX(vsxh_v_h, int16_t, int16_t, idx_h, sth_h) +GEN_VEXT_ST_INDEX(vsxh_v_w, int16_t, int32_t, idx_w, sth_w) +GEN_VEXT_ST_INDEX(vsxh_v_d, int16_t, int64_t, idx_d, sth_d) +GEN_VEXT_ST_INDEX(vsxw_v_w, int32_t, int32_t, idx_w, stw_w) +GEN_VEXT_ST_INDEX(vsxw_v_d, int32_t, int64_t, idx_d, stw_d) +GEN_VEXT_ST_INDEX(vsxe_v_b, int8_t, int8_t, idx_b, ste_b) +GEN_VEXT_ST_INDEX(vsxe_v_h, int16_t, int16_t, idx_h, ste_h) +GEN_VEXT_ST_INDEX(vsxe_v_w, int32_t, int32_t, idx_w, ste_w) +GEN_VEXT_ST_INDEX(vsxe_v_d, int64_t, int64_t, idx_d, ste_d) + +/* + *** unit-stride fault-only-fisrt load instructions + */ +static inline void +vext_ldff(void *vd, void *v0, target_ulong base, + CPURISCVState *env, uint32_t desc, + vext_ldst_elem_fn *ldst_elem, + clear_fn *clear_elem, + uint32_t esz, uint32_t msz, uintptr_t ra) +{ + void *host; + uint32_t i, k, vl = 0; + uint32_t mlen = vext_mlen(desc); + uint32_t nf = vext_nf(desc); + uint32_t vm = vext_vm(desc); + uint32_t vlmax = vext_maxsz(desc) / esz; + target_ulong addr, offset, remain; + + /* probe every access*/ + for (i = 0; i < env->vl; i++) { + if (!vm && !vext_elem_mask(v0, mlen, i)) { + continue; + } + addr = base + nf * i * msz; + if (i == 0) { + probe_pages(env, addr, nf * msz, ra, MMU_DATA_LOAD); + } else { + /* if it triggers an exception, no need to check watchpoint */ + remain = nf * msz; + while (remain > 0) { + offset = -(addr | TARGET_PAGE_MASK); + host = tlb_vaddr_to_host(env, addr, MMU_DATA_LOAD, + cpu_mmu_index(env, false)); + if (host) { +#ifdef CONFIG_USER_ONLY + if (page_check_range(addr, nf * msz, PAGE_READ) < 0) { + vl = i; + goto ProbeSuccess; + } +#else + probe_pages(env, addr, nf * msz, ra, MMU_DATA_LOAD); +#endif + } else { + vl = i; + goto ProbeSuccess; + } + if (remain <= offset) { + break; + } + remain -= offset; + addr += offset; + } + } + } +ProbeSuccess: + /* load bytes from guest memory */ + if (vl != 0) { + env->vl = vl; + } + for (i = 0; i < env->vl; i++) { + k = 0; + if (!vm && !vext_elem_mask(v0, mlen, i)) { + continue; + } + while (k < nf) { + target_ulong addr = base + (i * nf + k) * msz; + ldst_elem(env, addr, i + k * vlmax, vd, ra); + k++; + } + } + /* clear tail elements */ + if (vl != 0) { + return; + } + for (k = 0; k < nf; k++) { + clear_elem(vd, env->vl + k * vlmax, env->vl * esz, vlmax * esz); + } +} + +#define GEN_VEXT_LDFF(NAME, MTYPE, ETYPE, LOAD_FN, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, target_ulong base, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + vext_ldff(vd, v0, base, env, desc, LOAD_FN, CLEAR_FN, \ + sizeof(ETYPE), sizeof(MTYPE), GETPC()); \ +} + +GEN_VEXT_LDFF(vlbff_v_b, int8_t, int8_t, ldb_b, clearb) +GEN_VEXT_LDFF(vlbff_v_h, int8_t, int16_t, ldb_h, clearh) +GEN_VEXT_LDFF(vlbff_v_w, int8_t, int32_t, ldb_w, clearl) +GEN_VEXT_LDFF(vlbff_v_d, int8_t, int64_t, ldb_d, clearq) +GEN_VEXT_LDFF(vlhff_v_h, int16_t, int16_t, ldh_h, clearh) +GEN_VEXT_LDFF(vlhff_v_w, int16_t, int32_t, ldh_w, clearl) +GEN_VEXT_LDFF(vlhff_v_d, int16_t, int64_t, ldh_d, clearq) +GEN_VEXT_LDFF(vlwff_v_w, int32_t, int32_t, ldw_w, clearl) +GEN_VEXT_LDFF(vlwff_v_d, int32_t, int64_t, ldw_d, clearq) +GEN_VEXT_LDFF(vleff_v_b, int8_t, int8_t, lde_b, clearb) +GEN_VEXT_LDFF(vleff_v_h, int16_t, int16_t, lde_h, clearh) +GEN_VEXT_LDFF(vleff_v_w, int32_t, int32_t, lde_w, clearl) +GEN_VEXT_LDFF(vleff_v_d, int64_t, int64_t, lde_d, clearq) +GEN_VEXT_LDFF(vlbuff_v_b, uint8_t, uint8_t, ldbu_b, clearb) +GEN_VEXT_LDFF(vlbuff_v_h, uint8_t, uint16_t, ldbu_h, clearh) +GEN_VEXT_LDFF(vlbuff_v_w, uint8_t, uint32_t, ldbu_w, clearl) +GEN_VEXT_LDFF(vlbuff_v_d, uint8_t, uint64_t, ldbu_d, clearq) +GEN_VEXT_LDFF(vlhuff_v_h, uint16_t, uint16_t, ldhu_h, clearh) +GEN_VEXT_LDFF(vlhuff_v_w, uint16_t, uint32_t, ldhu_w, clearl) +GEN_VEXT_LDFF(vlhuff_v_d, uint16_t, uint64_t, ldhu_d, clearq) +GEN_VEXT_LDFF(vlwuff_v_w, uint32_t, uint32_t, ldwu_w, clearl) +GEN_VEXT_LDFF(vlwuff_v_d, uint32_t, uint64_t, ldwu_d, clearq) + +/* + *** Vector AMO Operations (Zvamo) + */ +typedef void vext_amo_noatomic_fn(void *vs3, target_ulong addr, + uint32_t wd, uint32_t idx, CPURISCVState *env, + uintptr_t retaddr); + +/* no atomic opreation for vector atomic insructions */ +#define DO_SWAP(N, M) (M) +#define DO_AND(N, M) (N & M) +#define DO_XOR(N, M) (N ^ M) +#define DO_OR(N, M) (N | M) +#define DO_ADD(N, M) (N + M) + +#define GEN_VEXT_AMO_NOATOMIC_OP(NAME, ESZ, MSZ, H, DO_OP, SUF) \ +static void \ +vext_##NAME##_noatomic_op(void *vs3, target_ulong addr, \ + uint32_t wd, uint32_t idx, \ + CPURISCVState *env, uintptr_t retaddr)\ +{ \ + typedef int##ESZ##_t ETYPE; \ + typedef int##MSZ##_t MTYPE; \ + typedef uint##MSZ##_t UMTYPE __attribute__((unused)); \ + ETYPE *pe3 = (ETYPE *)vs3 + H(idx); \ + MTYPE a = cpu_ld##SUF##_data(env, addr), b = *pe3; \ + \ + cpu_st##SUF##_data(env, addr, DO_OP(a, b)); \ + if (wd) { \ + *pe3 = a; \ + } \ +} + +/* Signed min/max */ +#define DO_MAX(N, M) ((N) >= (M) ? (N) : (M)) +#define DO_MIN(N, M) ((N) >= (M) ? (M) : (N)) + +/* Unsigned min/max */ +#define DO_MAXU(N, M) DO_MAX((UMTYPE)N, (UMTYPE)M) +#define DO_MINU(N, M) DO_MIN((UMTYPE)N, (UMTYPE)M) + +GEN_VEXT_AMO_NOATOMIC_OP(vamoswapw_v_w, 32, 32, H4, DO_SWAP, l) +GEN_VEXT_AMO_NOATOMIC_OP(vamoaddw_v_w, 32, 32, H4, DO_ADD, l) +GEN_VEXT_AMO_NOATOMIC_OP(vamoxorw_v_w, 32, 32, H4, DO_XOR, l) +GEN_VEXT_AMO_NOATOMIC_OP(vamoandw_v_w, 32, 32, H4, DO_AND, l) +GEN_VEXT_AMO_NOATOMIC_OP(vamoorw_v_w, 32, 32, H4, DO_OR, l) +GEN_VEXT_AMO_NOATOMIC_OP(vamominw_v_w, 32, 32, H4, DO_MIN, l) +GEN_VEXT_AMO_NOATOMIC_OP(vamomaxw_v_w, 32, 32, H4, DO_MAX, l) +GEN_VEXT_AMO_NOATOMIC_OP(vamominuw_v_w, 32, 32, H4, DO_MINU, l) +GEN_VEXT_AMO_NOATOMIC_OP(vamomaxuw_v_w, 32, 32, H4, DO_MAXU, l) +GEN_VEXT_AMO_NOATOMIC_OP(vamoswapw_v_d, 64, 32, H8, DO_SWAP, l) +GEN_VEXT_AMO_NOATOMIC_OP(vamoswapd_v_d, 64, 64, H8, DO_SWAP, q) +GEN_VEXT_AMO_NOATOMIC_OP(vamoaddw_v_d, 64, 32, H8, DO_ADD, l) +GEN_VEXT_AMO_NOATOMIC_OP(vamoaddd_v_d, 64, 64, H8, DO_ADD, q) +GEN_VEXT_AMO_NOATOMIC_OP(vamoxorw_v_d, 64, 32, H8, DO_XOR, l) +GEN_VEXT_AMO_NOATOMIC_OP(vamoxord_v_d, 64, 64, H8, DO_XOR, q) +GEN_VEXT_AMO_NOATOMIC_OP(vamoandw_v_d, 64, 32, H8, DO_AND, l) +GEN_VEXT_AMO_NOATOMIC_OP(vamoandd_v_d, 64, 64, H8, DO_AND, q) +GEN_VEXT_AMO_NOATOMIC_OP(vamoorw_v_d, 64, 32, H8, DO_OR, l) +GEN_VEXT_AMO_NOATOMIC_OP(vamoord_v_d, 64, 64, H8, DO_OR, q) +GEN_VEXT_AMO_NOATOMIC_OP(vamominw_v_d, 64, 32, H8, DO_MIN, l) +GEN_VEXT_AMO_NOATOMIC_OP(vamomind_v_d, 64, 64, H8, DO_MIN, q) +GEN_VEXT_AMO_NOATOMIC_OP(vamomaxw_v_d, 64, 32, H8, DO_MAX, l) +GEN_VEXT_AMO_NOATOMIC_OP(vamomaxd_v_d, 64, 64, H8, DO_MAX, q) +GEN_VEXT_AMO_NOATOMIC_OP(vamominuw_v_d, 64, 32, H8, DO_MINU, l) +GEN_VEXT_AMO_NOATOMIC_OP(vamominud_v_d, 64, 64, H8, DO_MINU, q) +GEN_VEXT_AMO_NOATOMIC_OP(vamomaxuw_v_d, 64, 32, H8, DO_MAXU, l) +GEN_VEXT_AMO_NOATOMIC_OP(vamomaxud_v_d, 64, 64, H8, DO_MAXU, q) + +static inline void +vext_amo_noatomic(void *vs3, void *v0, target_ulong base, + void *vs2, CPURISCVState *env, uint32_t desc, + vext_get_index_addr get_index_addr, + vext_amo_noatomic_fn *noatomic_op, + clear_fn *clear_elem, + uint32_t esz, uint32_t msz, uintptr_t ra) +{ + uint32_t i; + target_long addr; + uint32_t wd = vext_wd(desc); + uint32_t vm = vext_vm(desc); + uint32_t mlen = vext_mlen(desc); + uint32_t vlmax = vext_maxsz(desc) / esz; + + for (i = 0; i < env->vl; i++) { + if (!vm && !vext_elem_mask(v0, mlen, i)) { + continue; + } + probe_pages(env, get_index_addr(base, i, vs2), msz, ra, MMU_DATA_LOAD); + probe_pages(env, get_index_addr(base, i, vs2), msz, ra, MMU_DATA_STORE); + } + for (i = 0; i < env->vl; i++) { + if (!vm && !vext_elem_mask(v0, mlen, i)) { + continue; + } + addr = get_index_addr(base, i, vs2); + noatomic_op(vs3, addr, wd, i, env, ra); + } + clear_elem(vs3, env->vl, env->vl * esz, vlmax * esz); +} + +#define GEN_VEXT_AMO(NAME, MTYPE, ETYPE, INDEX_FN, CLEAR_FN) \ +void HELPER(NAME)(void *vs3, void *v0, target_ulong base, \ + void *vs2, CPURISCVState *env, uint32_t desc) \ +{ \ + vext_amo_noatomic(vs3, v0, base, vs2, env, desc, \ + INDEX_FN, vext_##NAME##_noatomic_op, \ + CLEAR_FN, sizeof(ETYPE), sizeof(MTYPE), \ + GETPC()); \ +} + +GEN_VEXT_AMO(vamoswapw_v_d, int32_t, int64_t, idx_d, clearq) +GEN_VEXT_AMO(vamoswapd_v_d, int64_t, int64_t, idx_d, clearq) +GEN_VEXT_AMO(vamoaddw_v_d, int32_t, int64_t, idx_d, clearq) +GEN_VEXT_AMO(vamoaddd_v_d, int64_t, int64_t, idx_d, clearq) +GEN_VEXT_AMO(vamoxorw_v_d, int32_t, int64_t, idx_d, clearq) +GEN_VEXT_AMO(vamoxord_v_d, int64_t, int64_t, idx_d, clearq) +GEN_VEXT_AMO(vamoandw_v_d, int32_t, int64_t, idx_d, clearq) +GEN_VEXT_AMO(vamoandd_v_d, int64_t, int64_t, idx_d, clearq) +GEN_VEXT_AMO(vamoorw_v_d, int32_t, int64_t, idx_d, clearq) +GEN_VEXT_AMO(vamoord_v_d, int64_t, int64_t, idx_d, clearq) +GEN_VEXT_AMO(vamominw_v_d, int32_t, int64_t, idx_d, clearq) +GEN_VEXT_AMO(vamomind_v_d, int64_t, int64_t, idx_d, clearq) +GEN_VEXT_AMO(vamomaxw_v_d, int32_t, int64_t, idx_d, clearq) +GEN_VEXT_AMO(vamomaxd_v_d, int64_t, int64_t, idx_d, clearq) +GEN_VEXT_AMO(vamominuw_v_d, uint32_t, uint64_t, idx_d, clearq) +GEN_VEXT_AMO(vamominud_v_d, uint64_t, uint64_t, idx_d, clearq) +GEN_VEXT_AMO(vamomaxuw_v_d, uint32_t, uint64_t, idx_d, clearq) +GEN_VEXT_AMO(vamomaxud_v_d, uint64_t, uint64_t, idx_d, clearq) +GEN_VEXT_AMO(vamoswapw_v_w, int32_t, int32_t, idx_w, clearl) +GEN_VEXT_AMO(vamoaddw_v_w, int32_t, int32_t, idx_w, clearl) +GEN_VEXT_AMO(vamoxorw_v_w, int32_t, int32_t, idx_w, clearl) +GEN_VEXT_AMO(vamoandw_v_w, int32_t, int32_t, idx_w, clearl) +GEN_VEXT_AMO(vamoorw_v_w, int32_t, int32_t, idx_w, clearl) +GEN_VEXT_AMO(vamominw_v_w, int32_t, int32_t, idx_w, clearl) +GEN_VEXT_AMO(vamomaxw_v_w, int32_t, int32_t, idx_w, clearl) +GEN_VEXT_AMO(vamominuw_v_w, uint32_t, uint32_t, idx_w, clearl) +GEN_VEXT_AMO(vamomaxuw_v_w, uint32_t, uint32_t, idx_w, clearl) + +/* + *** 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 +#define WOP_SUS_B int16_t, uint8_t, int8_t, uint16_t, int16_t +#define WOP_SUS_H int32_t, uint16_t, int16_t, uint32_t, int32_t +#define WOP_SUS_W int64_t, uint32_t, int32_t, uint64_t, int64_t +#define WOP_SSU_B int16_t, int8_t, uint8_t, int16_t, uint16_t +#define WOP_SSU_H int32_t, int16_t, uint16_t, int32_t, uint32_t +#define WOP_SSU_W int64_t, int32_t, uint32_t, int64_t, uint64_t +#define NOP_SSS_B int8_t, int8_t, int16_t, int8_t, int16_t +#define NOP_SSS_H int16_t, int16_t, int32_t, int16_t, int32_t +#define NOP_SSS_W int32_t, int32_t, int64_t, int32_t, int64_t +#define NOP_UUU_B uint8_t, uint8_t, uint16_t, uint8_t, uint16_t +#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) + +RVVCALL(OPIVV2, vadd_vv_b, OP_SSS_B, H1, H1, H1, DO_ADD) +RVVCALL(OPIVV2, vadd_vv_h, OP_SSS_H, H2, H2, H2, DO_ADD) +RVVCALL(OPIVV2, vadd_vv_w, OP_SSS_W, H4, H4, H4, DO_ADD) +RVVCALL(OPIVV2, vadd_vv_d, OP_SSS_D, H8, H8, H8, DO_ADD) +RVVCALL(OPIVV2, vsub_vv_b, OP_SSS_B, H1, H1, H1, DO_SUB) +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, + uint32_t esz, uint32_t dsz, + opivv2_fn *fn, clear_fn *clearfn) +{ + uint32_t vlmax = vext_maxsz(desc) / esz; + uint32_t mlen = vext_mlen(desc); + uint32_t vm = vext_vm(desc); + uint32_t vl = env->vl; + uint32_t i; + + for (i = 0; i < vl; i++) { + if (!vm && !vext_elem_mask(v0, mlen, i)) { + continue; + } + fn(vd, vs1, vs2, i); + } + clearfn(vd, vl, vl * dsz, vlmax * dsz); +} + +/* generate the helpers for OPIVV */ +#define GEN_VEXT_VV(NAME, ESZ, DSZ, CLEAR_FN) \ +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, ESZ, DSZ, \ + do_##NAME, CLEAR_FN); \ +} + +GEN_VEXT_VV(vadd_vv_b, 1, 1, clearb) +GEN_VEXT_VV(vadd_vv_h, 2, 2, clearh) +GEN_VEXT_VV(vadd_vv_w, 4, 4, clearl) +GEN_VEXT_VV(vadd_vv_d, 8, 8, clearq) +GEN_VEXT_VV(vsub_vv_b, 1, 1, clearb) +GEN_VEXT_VV(vsub_vv_h, 2, 2, clearh) +GEN_VEXT_VV(vsub_vv_w, 4, 4, clearl) +GEN_VEXT_VV(vsub_vv_d, 8, 8, clearq) + +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) +RVVCALL(OPIVX2, vadd_vx_w, OP_SSS_W, H4, H4, DO_ADD) +RVVCALL(OPIVX2, vadd_vx_d, OP_SSS_D, H8, H8, DO_ADD) +RVVCALL(OPIVX2, vsub_vx_b, OP_SSS_B, H1, H1, DO_SUB) +RVVCALL(OPIVX2, vsub_vx_h, OP_SSS_H, H2, H2, DO_SUB) +RVVCALL(OPIVX2, vsub_vx_w, OP_SSS_W, H4, H4, DO_SUB) +RVVCALL(OPIVX2, vsub_vx_d, OP_SSS_D, H8, H8, DO_SUB) +RVVCALL(OPIVX2, vrsub_vx_b, OP_SSS_B, H1, H1, DO_RSUB) +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, + uint32_t esz, uint32_t dsz, + opivx2_fn fn, clear_fn *clearfn) +{ + uint32_t vlmax = vext_maxsz(desc) / esz; + uint32_t mlen = vext_mlen(desc); + uint32_t vm = vext_vm(desc); + uint32_t vl = env->vl; + uint32_t i; + + for (i = 0; i < vl; i++) { + if (!vm && !vext_elem_mask(v0, mlen, i)) { + continue; + } + fn(vd, s1, vs2, i); + } + clearfn(vd, vl, vl * dsz, vlmax * dsz); +} + +/* generate the helpers for OPIVX */ +#define GEN_VEXT_VX(NAME, ESZ, DSZ, CLEAR_FN) \ +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, ESZ, DSZ, \ + do_##NAME, CLEAR_FN); \ +} + +GEN_VEXT_VX(vadd_vx_b, 1, 1, clearb) +GEN_VEXT_VX(vadd_vx_h, 2, 2, clearh) +GEN_VEXT_VX(vadd_vx_w, 4, 4, clearl) +GEN_VEXT_VX(vadd_vx_d, 8, 8, clearq) +GEN_VEXT_VX(vsub_vx_b, 1, 1, clearb) +GEN_VEXT_VX(vsub_vx_h, 2, 2, clearh) +GEN_VEXT_VX(vsub_vx_w, 4, 4, clearl) +GEN_VEXT_VX(vsub_vx_d, 8, 8, clearq) +GEN_VEXT_VX(vrsub_vx_b, 1, 1, clearb) +GEN_VEXT_VX(vrsub_vx_h, 2, 2, clearh) +GEN_VEXT_VX(vrsub_vx_w, 4, 4, clearl) +GEN_VEXT_VX(vrsub_vx_d, 8, 8, clearq) + +void HELPER(vec_rsubs8)(void *d, void *a, uint64_t b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(uint8_t)) { + *(uint8_t *)(d + i) = (uint8_t)b - *(uint8_t *)(a + i); + } +} + +void HELPER(vec_rsubs16)(void *d, void *a, uint64_t b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(uint16_t)) { + *(uint16_t *)(d + i) = (uint16_t)b - *(uint16_t *)(a + i); + } +} + +void HELPER(vec_rsubs32)(void *d, void *a, uint64_t b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(uint32_t)) { + *(uint32_t *)(d + i) = (uint32_t)b - *(uint32_t *)(a + i); + } +} + +void HELPER(vec_rsubs64)(void *d, void *a, uint64_t b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(uint64_t)) { + *(uint64_t *)(d + i) = b - *(uint64_t *)(a + i); + } +} + +/* Vector Widening Integer Add/Subtract */ +#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 +#define WOP_WUUU_B uint16_t, uint8_t, uint16_t, uint16_t, uint16_t +#define WOP_WUUU_H uint32_t, uint16_t, uint32_t, uint32_t, uint32_t +#define WOP_WUUU_W uint64_t, uint32_t, uint64_t, uint64_t, uint64_t +#define WOP_WSSS_B int16_t, int8_t, int16_t, int16_t, int16_t +#define WOP_WSSS_H int32_t, int16_t, int32_t, int32_t, int32_t +#define WOP_WSSS_W int64_t, int32_t, int64_t, int64_t, int64_t +RVVCALL(OPIVV2, vwaddu_vv_b, WOP_UUU_B, H2, H1, H1, DO_ADD) +RVVCALL(OPIVV2, vwaddu_vv_h, WOP_UUU_H, H4, H2, H2, DO_ADD) +RVVCALL(OPIVV2, vwaddu_vv_w, WOP_UUU_W, H8, H4, H4, DO_ADD) +RVVCALL(OPIVV2, vwsubu_vv_b, WOP_UUU_B, H2, H1, H1, DO_SUB) +RVVCALL(OPIVV2, vwsubu_vv_h, WOP_UUU_H, H4, H2, H2, DO_SUB) +RVVCALL(OPIVV2, vwsubu_vv_w, WOP_UUU_W, H8, H4, H4, DO_SUB) +RVVCALL(OPIVV2, vwadd_vv_b, WOP_SSS_B, H2, H1, H1, DO_ADD) +RVVCALL(OPIVV2, vwadd_vv_h, WOP_SSS_H, H4, H2, H2, DO_ADD) +RVVCALL(OPIVV2, vwadd_vv_w, WOP_SSS_W, H8, H4, H4, DO_ADD) +RVVCALL(OPIVV2, vwsub_vv_b, WOP_SSS_B, H2, H1, H1, DO_SUB) +RVVCALL(OPIVV2, vwsub_vv_h, WOP_SSS_H, H4, H2, H2, DO_SUB) +RVVCALL(OPIVV2, vwsub_vv_w, WOP_SSS_W, H8, H4, H4, DO_SUB) +RVVCALL(OPIVV2, vwaddu_wv_b, WOP_WUUU_B, H2, H1, H1, DO_ADD) +RVVCALL(OPIVV2, vwaddu_wv_h, WOP_WUUU_H, H4, H2, H2, DO_ADD) +RVVCALL(OPIVV2, vwaddu_wv_w, WOP_WUUU_W, H8, H4, H4, DO_ADD) +RVVCALL(OPIVV2, vwsubu_wv_b, WOP_WUUU_B, H2, H1, H1, DO_SUB) +RVVCALL(OPIVV2, vwsubu_wv_h, WOP_WUUU_H, H4, H2, H2, DO_SUB) +RVVCALL(OPIVV2, vwsubu_wv_w, WOP_WUUU_W, H8, H4, H4, DO_SUB) +RVVCALL(OPIVV2, vwadd_wv_b, WOP_WSSS_B, H2, H1, H1, DO_ADD) +RVVCALL(OPIVV2, vwadd_wv_h, WOP_WSSS_H, H4, H2, H2, DO_ADD) +RVVCALL(OPIVV2, vwadd_wv_w, WOP_WSSS_W, H8, H4, H4, DO_ADD) +RVVCALL(OPIVV2, vwsub_wv_b, WOP_WSSS_B, H2, H1, H1, DO_SUB) +RVVCALL(OPIVV2, vwsub_wv_h, WOP_WSSS_H, H4, H2, H2, DO_SUB) +RVVCALL(OPIVV2, vwsub_wv_w, WOP_WSSS_W, H8, H4, H4, DO_SUB) +GEN_VEXT_VV(vwaddu_vv_b, 1, 2, clearh) +GEN_VEXT_VV(vwaddu_vv_h, 2, 4, clearl) +GEN_VEXT_VV(vwaddu_vv_w, 4, 8, clearq) +GEN_VEXT_VV(vwsubu_vv_b, 1, 2, clearh) +GEN_VEXT_VV(vwsubu_vv_h, 2, 4, clearl) +GEN_VEXT_VV(vwsubu_vv_w, 4, 8, clearq) +GEN_VEXT_VV(vwadd_vv_b, 1, 2, clearh) +GEN_VEXT_VV(vwadd_vv_h, 2, 4, clearl) +GEN_VEXT_VV(vwadd_vv_w, 4, 8, clearq) +GEN_VEXT_VV(vwsub_vv_b, 1, 2, clearh) +GEN_VEXT_VV(vwsub_vv_h, 2, 4, clearl) +GEN_VEXT_VV(vwsub_vv_w, 4, 8, clearq) +GEN_VEXT_VV(vwaddu_wv_b, 1, 2, clearh) +GEN_VEXT_VV(vwaddu_wv_h, 2, 4, clearl) +GEN_VEXT_VV(vwaddu_wv_w, 4, 8, clearq) +GEN_VEXT_VV(vwsubu_wv_b, 1, 2, clearh) +GEN_VEXT_VV(vwsubu_wv_h, 2, 4, clearl) +GEN_VEXT_VV(vwsubu_wv_w, 4, 8, clearq) +GEN_VEXT_VV(vwadd_wv_b, 1, 2, clearh) +GEN_VEXT_VV(vwadd_wv_h, 2, 4, clearl) +GEN_VEXT_VV(vwadd_wv_w, 4, 8, clearq) +GEN_VEXT_VV(vwsub_wv_b, 1, 2, clearh) +GEN_VEXT_VV(vwsub_wv_h, 2, 4, clearl) +GEN_VEXT_VV(vwsub_wv_w, 4, 8, clearq) + +RVVCALL(OPIVX2, vwaddu_vx_b, WOP_UUU_B, H2, H1, DO_ADD) +RVVCALL(OPIVX2, vwaddu_vx_h, WOP_UUU_H, H4, H2, DO_ADD) +RVVCALL(OPIVX2, vwaddu_vx_w, WOP_UUU_W, H8, H4, DO_ADD) +RVVCALL(OPIVX2, vwsubu_vx_b, WOP_UUU_B, H2, H1, DO_SUB) +RVVCALL(OPIVX2, vwsubu_vx_h, WOP_UUU_H, H4, H2, DO_SUB) +RVVCALL(OPIVX2, vwsubu_vx_w, WOP_UUU_W, H8, H4, DO_SUB) +RVVCALL(OPIVX2, vwadd_vx_b, WOP_SSS_B, H2, H1, DO_ADD) +RVVCALL(OPIVX2, vwadd_vx_h, WOP_SSS_H, H4, H2, DO_ADD) +RVVCALL(OPIVX2, vwadd_vx_w, WOP_SSS_W, H8, H4, DO_ADD) +RVVCALL(OPIVX2, vwsub_vx_b, WOP_SSS_B, H2, H1, DO_SUB) +RVVCALL(OPIVX2, vwsub_vx_h, WOP_SSS_H, H4, H2, DO_SUB) +RVVCALL(OPIVX2, vwsub_vx_w, WOP_SSS_W, H8, H4, DO_SUB) +RVVCALL(OPIVX2, vwaddu_wx_b, WOP_WUUU_B, H2, H1, DO_ADD) +RVVCALL(OPIVX2, vwaddu_wx_h, WOP_WUUU_H, H4, H2, DO_ADD) +RVVCALL(OPIVX2, vwaddu_wx_w, WOP_WUUU_W, H8, H4, DO_ADD) +RVVCALL(OPIVX2, vwsubu_wx_b, WOP_WUUU_B, H2, H1, DO_SUB) +RVVCALL(OPIVX2, vwsubu_wx_h, WOP_WUUU_H, H4, H2, DO_SUB) +RVVCALL(OPIVX2, vwsubu_wx_w, WOP_WUUU_W, H8, H4, DO_SUB) +RVVCALL(OPIVX2, vwadd_wx_b, WOP_WSSS_B, H2, H1, DO_ADD) +RVVCALL(OPIVX2, vwadd_wx_h, WOP_WSSS_H, H4, H2, DO_ADD) +RVVCALL(OPIVX2, vwadd_wx_w, WOP_WSSS_W, H8, H4, DO_ADD) +RVVCALL(OPIVX2, vwsub_wx_b, WOP_WSSS_B, H2, H1, DO_SUB) +RVVCALL(OPIVX2, vwsub_wx_h, WOP_WSSS_H, H4, H2, DO_SUB) +RVVCALL(OPIVX2, vwsub_wx_w, WOP_WSSS_W, H8, H4, DO_SUB) +GEN_VEXT_VX(vwaddu_vx_b, 1, 2, clearh) +GEN_VEXT_VX(vwaddu_vx_h, 2, 4, clearl) +GEN_VEXT_VX(vwaddu_vx_w, 4, 8, clearq) +GEN_VEXT_VX(vwsubu_vx_b, 1, 2, clearh) +GEN_VEXT_VX(vwsubu_vx_h, 2, 4, clearl) +GEN_VEXT_VX(vwsubu_vx_w, 4, 8, clearq) +GEN_VEXT_VX(vwadd_vx_b, 1, 2, clearh) +GEN_VEXT_VX(vwadd_vx_h, 2, 4, clearl) +GEN_VEXT_VX(vwadd_vx_w, 4, 8, clearq) +GEN_VEXT_VX(vwsub_vx_b, 1, 2, clearh) +GEN_VEXT_VX(vwsub_vx_h, 2, 4, clearl) +GEN_VEXT_VX(vwsub_vx_w, 4, 8, clearq) +GEN_VEXT_VX(vwaddu_wx_b, 1, 2, clearh) +GEN_VEXT_VX(vwaddu_wx_h, 2, 4, clearl) +GEN_VEXT_VX(vwaddu_wx_w, 4, 8, clearq) +GEN_VEXT_VX(vwsubu_wx_b, 1, 2, clearh) +GEN_VEXT_VX(vwsubu_wx_h, 2, 4, clearl) +GEN_VEXT_VX(vwsubu_wx_w, 4, 8, clearq) +GEN_VEXT_VX(vwadd_wx_b, 1, 2, clearh) +GEN_VEXT_VX(vwadd_wx_h, 2, 4, clearl) +GEN_VEXT_VX(vwadd_wx_w, 4, 8, clearq) +GEN_VEXT_VX(vwsub_wx_b, 1, 2, clearh) +GEN_VEXT_VX(vwsub_wx_h, 2, 4, clearl) +GEN_VEXT_VX(vwsub_wx_w, 4, 8, clearq) + +/* Vector Integer Add-with-Carry / Subtract-with-Borrow Instructions */ +#define DO_VADC(N, M, C) (N + M + C) +#define DO_VSBC(N, M, C) (N - M - C) + +#define GEN_VEXT_VADC_VVM(NAME, ETYPE, H, DO_OP, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vl = env->vl; \ + uint32_t esz = sizeof(ETYPE); \ + uint32_t vlmax = vext_maxsz(desc) / esz; \ + uint32_t i; \ + \ + for (i = 0; i < vl; i++) { \ + ETYPE s1 = *((ETYPE *)vs1 + H(i)); \ + ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ + uint8_t carry = vext_elem_mask(v0, mlen, i); \ + \ + *((ETYPE *)vd + H(i)) = DO_OP(s2, s1, carry); \ + } \ + CLEAR_FN(vd, vl, vl * esz, vlmax * esz); \ +} + +GEN_VEXT_VADC_VVM(vadc_vvm_b, uint8_t, H1, DO_VADC, clearb) +GEN_VEXT_VADC_VVM(vadc_vvm_h, uint16_t, H2, DO_VADC, clearh) +GEN_VEXT_VADC_VVM(vadc_vvm_w, uint32_t, H4, DO_VADC, clearl) +GEN_VEXT_VADC_VVM(vadc_vvm_d, uint64_t, H8, DO_VADC, clearq) + +GEN_VEXT_VADC_VVM(vsbc_vvm_b, uint8_t, H1, DO_VSBC, clearb) +GEN_VEXT_VADC_VVM(vsbc_vvm_h, uint16_t, H2, DO_VSBC, clearh) +GEN_VEXT_VADC_VVM(vsbc_vvm_w, uint32_t, H4, DO_VSBC, clearl) +GEN_VEXT_VADC_VVM(vsbc_vvm_d, uint64_t, H8, DO_VSBC, clearq) + +#define GEN_VEXT_VADC_VXM(NAME, ETYPE, H, DO_OP, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vl = env->vl; \ + uint32_t esz = sizeof(ETYPE); \ + uint32_t vlmax = vext_maxsz(desc) / esz; \ + uint32_t i; \ + \ + for (i = 0; i < vl; i++) { \ + ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ + uint8_t carry = vext_elem_mask(v0, mlen, i); \ + \ + *((ETYPE *)vd + H(i)) = DO_OP(s2, (ETYPE)(target_long)s1, carry);\ + } \ + CLEAR_FN(vd, vl, vl * esz, vlmax * esz); \ +} + +GEN_VEXT_VADC_VXM(vadc_vxm_b, uint8_t, H1, DO_VADC, clearb) +GEN_VEXT_VADC_VXM(vadc_vxm_h, uint16_t, H2, DO_VADC, clearh) +GEN_VEXT_VADC_VXM(vadc_vxm_w, uint32_t, H4, DO_VADC, clearl) +GEN_VEXT_VADC_VXM(vadc_vxm_d, uint64_t, H8, DO_VADC, clearq) + +GEN_VEXT_VADC_VXM(vsbc_vxm_b, uint8_t, H1, DO_VSBC, clearb) +GEN_VEXT_VADC_VXM(vsbc_vxm_h, uint16_t, H2, DO_VSBC, clearh) +GEN_VEXT_VADC_VXM(vsbc_vxm_w, uint32_t, H4, DO_VSBC, clearl) +GEN_VEXT_VADC_VXM(vsbc_vxm_d, uint64_t, H8, DO_VSBC, clearq) + +#define DO_MADC(N, M, C) (C ? (__typeof(N))(N + M + 1) <= N : \ + (__typeof(N))(N + M) < N) +#define DO_MSBC(N, M, C) (C ? N <= M : N < M) + +#define GEN_VEXT_VMADC_VVM(NAME, ETYPE, H, DO_OP) \ +void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vl = env->vl; \ + uint32_t vlmax = vext_maxsz(desc) / sizeof(ETYPE); \ + uint32_t i; \ + \ + for (i = 0; i < vl; i++) { \ + ETYPE s1 = *((ETYPE *)vs1 + H(i)); \ + ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ + uint8_t carry = vext_elem_mask(v0, mlen, i); \ + \ + vext_set_elem_mask(vd, mlen, i, DO_OP(s2, s1, carry));\ + } \ + for (; i < vlmax; i++) { \ + vext_set_elem_mask(vd, mlen, i, 0); \ + } \ +} + +GEN_VEXT_VMADC_VVM(vmadc_vvm_b, uint8_t, H1, DO_MADC) +GEN_VEXT_VMADC_VVM(vmadc_vvm_h, uint16_t, H2, DO_MADC) +GEN_VEXT_VMADC_VVM(vmadc_vvm_w, uint32_t, H4, DO_MADC) +GEN_VEXT_VMADC_VVM(vmadc_vvm_d, uint64_t, H8, DO_MADC) + +GEN_VEXT_VMADC_VVM(vmsbc_vvm_b, uint8_t, H1, DO_MSBC) +GEN_VEXT_VMADC_VVM(vmsbc_vvm_h, uint16_t, H2, DO_MSBC) +GEN_VEXT_VMADC_VVM(vmsbc_vvm_w, uint32_t, H4, DO_MSBC) +GEN_VEXT_VMADC_VVM(vmsbc_vvm_d, uint64_t, H8, DO_MSBC) + +#define GEN_VEXT_VMADC_VXM(NAME, ETYPE, H, DO_OP) \ +void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \ + void *vs2, CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vl = env->vl; \ + uint32_t vlmax = vext_maxsz(desc) / sizeof(ETYPE); \ + uint32_t i; \ + \ + for (i = 0; i < vl; i++) { \ + ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ + uint8_t carry = vext_elem_mask(v0, mlen, i); \ + \ + vext_set_elem_mask(vd, mlen, i, \ + DO_OP(s2, (ETYPE)(target_long)s1, carry)); \ + } \ + for (; i < vlmax; i++) { \ + vext_set_elem_mask(vd, mlen, i, 0); \ + } \ +} + +GEN_VEXT_VMADC_VXM(vmadc_vxm_b, uint8_t, H1, DO_MADC) +GEN_VEXT_VMADC_VXM(vmadc_vxm_h, uint16_t, H2, DO_MADC) +GEN_VEXT_VMADC_VXM(vmadc_vxm_w, uint32_t, H4, DO_MADC) +GEN_VEXT_VMADC_VXM(vmadc_vxm_d, uint64_t, H8, DO_MADC) + +GEN_VEXT_VMADC_VXM(vmsbc_vxm_b, uint8_t, H1, DO_MSBC) +GEN_VEXT_VMADC_VXM(vmsbc_vxm_h, uint16_t, H2, DO_MSBC) +GEN_VEXT_VMADC_VXM(vmsbc_vxm_w, uint32_t, H4, DO_MSBC) +GEN_VEXT_VMADC_VXM(vmsbc_vxm_d, uint64_t, H8, DO_MSBC) + +/* Vector Bitwise Logical Instructions */ +RVVCALL(OPIVV2, vand_vv_b, OP_SSS_B, H1, H1, H1, DO_AND) +RVVCALL(OPIVV2, vand_vv_h, OP_SSS_H, H2, H2, H2, DO_AND) +RVVCALL(OPIVV2, vand_vv_w, OP_SSS_W, H4, H4, H4, DO_AND) +RVVCALL(OPIVV2, vand_vv_d, OP_SSS_D, H8, H8, H8, DO_AND) +RVVCALL(OPIVV2, vor_vv_b, OP_SSS_B, H1, H1, H1, DO_OR) +RVVCALL(OPIVV2, vor_vv_h, OP_SSS_H, H2, H2, H2, DO_OR) +RVVCALL(OPIVV2, vor_vv_w, OP_SSS_W, H4, H4, H4, DO_OR) +RVVCALL(OPIVV2, vor_vv_d, OP_SSS_D, H8, H8, H8, DO_OR) +RVVCALL(OPIVV2, vxor_vv_b, OP_SSS_B, H1, H1, H1, DO_XOR) +RVVCALL(OPIVV2, vxor_vv_h, OP_SSS_H, H2, H2, H2, DO_XOR) +RVVCALL(OPIVV2, vxor_vv_w, OP_SSS_W, H4, H4, H4, DO_XOR) +RVVCALL(OPIVV2, vxor_vv_d, OP_SSS_D, H8, H8, H8, DO_XOR) +GEN_VEXT_VV(vand_vv_b, 1, 1, clearb) +GEN_VEXT_VV(vand_vv_h, 2, 2, clearh) +GEN_VEXT_VV(vand_vv_w, 4, 4, clearl) +GEN_VEXT_VV(vand_vv_d, 8, 8, clearq) +GEN_VEXT_VV(vor_vv_b, 1, 1, clearb) +GEN_VEXT_VV(vor_vv_h, 2, 2, clearh) +GEN_VEXT_VV(vor_vv_w, 4, 4, clearl) +GEN_VEXT_VV(vor_vv_d, 8, 8, clearq) +GEN_VEXT_VV(vxor_vv_b, 1, 1, clearb) +GEN_VEXT_VV(vxor_vv_h, 2, 2, clearh) +GEN_VEXT_VV(vxor_vv_w, 4, 4, clearl) +GEN_VEXT_VV(vxor_vv_d, 8, 8, clearq) + +RVVCALL(OPIVX2, vand_vx_b, OP_SSS_B, H1, H1, DO_AND) +RVVCALL(OPIVX2, vand_vx_h, OP_SSS_H, H2, H2, DO_AND) +RVVCALL(OPIVX2, vand_vx_w, OP_SSS_W, H4, H4, DO_AND) +RVVCALL(OPIVX2, vand_vx_d, OP_SSS_D, H8, H8, DO_AND) +RVVCALL(OPIVX2, vor_vx_b, OP_SSS_B, H1, H1, DO_OR) +RVVCALL(OPIVX2, vor_vx_h, OP_SSS_H, H2, H2, DO_OR) +RVVCALL(OPIVX2, vor_vx_w, OP_SSS_W, H4, H4, DO_OR) +RVVCALL(OPIVX2, vor_vx_d, OP_SSS_D, H8, H8, DO_OR) +RVVCALL(OPIVX2, vxor_vx_b, OP_SSS_B, H1, H1, DO_XOR) +RVVCALL(OPIVX2, vxor_vx_h, OP_SSS_H, H2, H2, DO_XOR) +RVVCALL(OPIVX2, vxor_vx_w, OP_SSS_W, H4, H4, DO_XOR) +RVVCALL(OPIVX2, vxor_vx_d, OP_SSS_D, H8, H8, DO_XOR) +GEN_VEXT_VX(vand_vx_b, 1, 1, clearb) +GEN_VEXT_VX(vand_vx_h, 2, 2, clearh) +GEN_VEXT_VX(vand_vx_w, 4, 4, clearl) +GEN_VEXT_VX(vand_vx_d, 8, 8, clearq) +GEN_VEXT_VX(vor_vx_b, 1, 1, clearb) +GEN_VEXT_VX(vor_vx_h, 2, 2, clearh) +GEN_VEXT_VX(vor_vx_w, 4, 4, clearl) +GEN_VEXT_VX(vor_vx_d, 8, 8, clearq) +GEN_VEXT_VX(vxor_vx_b, 1, 1, clearb) +GEN_VEXT_VX(vxor_vx_h, 2, 2, clearh) +GEN_VEXT_VX(vxor_vx_w, 4, 4, clearl) +GEN_VEXT_VX(vxor_vx_d, 8, 8, clearq) + +/* Vector Single-Width Bit Shift Instructions */ +#define DO_SLL(N, M) (N << (M)) +#define DO_SRL(N, M) (N >> (M)) + +/* generate the helpers for shift instructions with two vector operators */ +#define GEN_VEXT_SHIFT_VV(NAME, TS1, TS2, HS1, HS2, OP, MASK, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, void *vs1, \ + void *vs2, CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vm = vext_vm(desc); \ + uint32_t vl = env->vl; \ + uint32_t esz = sizeof(TS1); \ + uint32_t vlmax = vext_maxsz(desc) / esz; \ + uint32_t i; \ + \ + for (i = 0; i < vl; i++) { \ + if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + continue; \ + } \ + TS1 s1 = *((TS1 *)vs1 + HS1(i)); \ + TS2 s2 = *((TS2 *)vs2 + HS2(i)); \ + *((TS1 *)vd + HS1(i)) = OP(s2, s1 & MASK); \ + } \ + CLEAR_FN(vd, vl, vl * esz, vlmax * esz); \ +} + +GEN_VEXT_SHIFT_VV(vsll_vv_b, uint8_t, uint8_t, H1, H1, DO_SLL, 0x7, clearb) +GEN_VEXT_SHIFT_VV(vsll_vv_h, uint16_t, uint16_t, H2, H2, DO_SLL, 0xf, clearh) +GEN_VEXT_SHIFT_VV(vsll_vv_w, uint32_t, uint32_t, H4, H4, DO_SLL, 0x1f, clearl) +GEN_VEXT_SHIFT_VV(vsll_vv_d, uint64_t, uint64_t, H8, H8, DO_SLL, 0x3f, clearq) + +GEN_VEXT_SHIFT_VV(vsrl_vv_b, uint8_t, uint8_t, H1, H1, DO_SRL, 0x7, clearb) +GEN_VEXT_SHIFT_VV(vsrl_vv_h, uint16_t, uint16_t, H2, H2, DO_SRL, 0xf, clearh) +GEN_VEXT_SHIFT_VV(vsrl_vv_w, uint32_t, uint32_t, H4, H4, DO_SRL, 0x1f, clearl) +GEN_VEXT_SHIFT_VV(vsrl_vv_d, uint64_t, uint64_t, H8, H8, DO_SRL, 0x3f, clearq) + +GEN_VEXT_SHIFT_VV(vsra_vv_b, uint8_t, int8_t, H1, H1, DO_SRL, 0x7, clearb) +GEN_VEXT_SHIFT_VV(vsra_vv_h, uint16_t, int16_t, H2, H2, DO_SRL, 0xf, clearh) +GEN_VEXT_SHIFT_VV(vsra_vv_w, uint32_t, int32_t, H4, H4, DO_SRL, 0x1f, clearl) +GEN_VEXT_SHIFT_VV(vsra_vv_d, uint64_t, int64_t, H8, H8, DO_SRL, 0x3f, clearq) + +/* generate the helpers for shift instructions with one vector and one scalar */ +#define GEN_VEXT_SHIFT_VX(NAME, TD, TS2, HD, HS2, OP, MASK, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \ + void *vs2, CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vm = vext_vm(desc); \ + uint32_t vl = env->vl; \ + uint32_t esz = sizeof(TD); \ + uint32_t vlmax = vext_maxsz(desc) / esz; \ + uint32_t i; \ + \ + for (i = 0; i < vl; i++) { \ + if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + continue; \ + } \ + TS2 s2 = *((TS2 *)vs2 + HS2(i)); \ + *((TD *)vd + HD(i)) = OP(s2, s1 & MASK); \ + } \ + CLEAR_FN(vd, vl, vl * esz, vlmax * esz); \ +} + +GEN_VEXT_SHIFT_VX(vsll_vx_b, uint8_t, int8_t, H1, H1, DO_SLL, 0x7, clearb) +GEN_VEXT_SHIFT_VX(vsll_vx_h, uint16_t, int16_t, H2, H2, DO_SLL, 0xf, clearh) +GEN_VEXT_SHIFT_VX(vsll_vx_w, uint32_t, int32_t, H4, H4, DO_SLL, 0x1f, clearl) +GEN_VEXT_SHIFT_VX(vsll_vx_d, uint64_t, int64_t, H8, H8, DO_SLL, 0x3f, clearq) + +GEN_VEXT_SHIFT_VX(vsrl_vx_b, uint8_t, uint8_t, H1, H1, DO_SRL, 0x7, clearb) +GEN_VEXT_SHIFT_VX(vsrl_vx_h, uint16_t, uint16_t, H2, H2, DO_SRL, 0xf, clearh) +GEN_VEXT_SHIFT_VX(vsrl_vx_w, uint32_t, uint32_t, H4, H4, DO_SRL, 0x1f, clearl) +GEN_VEXT_SHIFT_VX(vsrl_vx_d, uint64_t, uint64_t, H8, H8, DO_SRL, 0x3f, clearq) + +GEN_VEXT_SHIFT_VX(vsra_vx_b, int8_t, int8_t, H1, H1, DO_SRL, 0x7, clearb) +GEN_VEXT_SHIFT_VX(vsra_vx_h, int16_t, int16_t, H2, H2, DO_SRL, 0xf, clearh) +GEN_VEXT_SHIFT_VX(vsra_vx_w, int32_t, int32_t, H4, H4, DO_SRL, 0x1f, clearl) +GEN_VEXT_SHIFT_VX(vsra_vx_d, int64_t, int64_t, H8, H8, DO_SRL, 0x3f, clearq) + +/* Vector Narrowing Integer Right Shift Instructions */ +GEN_VEXT_SHIFT_VV(vnsrl_vv_b, uint8_t, uint16_t, H1, H2, DO_SRL, 0xf, clearb) +GEN_VEXT_SHIFT_VV(vnsrl_vv_h, uint16_t, uint32_t, H2, H4, DO_SRL, 0x1f, clearh) +GEN_VEXT_SHIFT_VV(vnsrl_vv_w, uint32_t, uint64_t, H4, H8, DO_SRL, 0x3f, clearl) +GEN_VEXT_SHIFT_VV(vnsra_vv_b, uint8_t, int16_t, H1, H2, DO_SRL, 0xf, clearb) +GEN_VEXT_SHIFT_VV(vnsra_vv_h, uint16_t, int32_t, H2, H4, DO_SRL, 0x1f, clearh) +GEN_VEXT_SHIFT_VV(vnsra_vv_w, uint32_t, int64_t, H4, H8, DO_SRL, 0x3f, clearl) +GEN_VEXT_SHIFT_VX(vnsrl_vx_b, uint8_t, uint16_t, H1, H2, DO_SRL, 0xf, clearb) +GEN_VEXT_SHIFT_VX(vnsrl_vx_h, uint16_t, uint32_t, H2, H4, DO_SRL, 0x1f, clearh) +GEN_VEXT_SHIFT_VX(vnsrl_vx_w, uint32_t, uint64_t, H4, H8, DO_SRL, 0x3f, clearl) +GEN_VEXT_SHIFT_VX(vnsra_vx_b, int8_t, int16_t, H1, H2, DO_SRL, 0xf, clearb) +GEN_VEXT_SHIFT_VX(vnsra_vx_h, int16_t, int32_t, H2, H4, DO_SRL, 0x1f, clearh) +GEN_VEXT_SHIFT_VX(vnsra_vx_w, int32_t, int64_t, H4, H8, DO_SRL, 0x3f, clearl) + +/* Vector Integer Comparison Instructions */ +#define DO_MSEQ(N, M) (N == M) +#define DO_MSNE(N, M) (N != M) +#define DO_MSLT(N, M) (N < M) +#define DO_MSLE(N, M) (N <= M) +#define DO_MSGT(N, M) (N > M) + +#define GEN_VEXT_CMP_VV(NAME, ETYPE, H, DO_OP) \ +void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vm = vext_vm(desc); \ + uint32_t vl = env->vl; \ + uint32_t vlmax = vext_maxsz(desc) / sizeof(ETYPE); \ + uint32_t i; \ + \ + for (i = 0; i < vl; i++) { \ + ETYPE s1 = *((ETYPE *)vs1 + H(i)); \ + ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ + if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + continue; \ + } \ + vext_set_elem_mask(vd, mlen, i, DO_OP(s2, s1)); \ + } \ + for (; i < vlmax; i++) { \ + vext_set_elem_mask(vd, mlen, i, 0); \ + } \ +} + +GEN_VEXT_CMP_VV(vmseq_vv_b, uint8_t, H1, DO_MSEQ) +GEN_VEXT_CMP_VV(vmseq_vv_h, uint16_t, H2, DO_MSEQ) +GEN_VEXT_CMP_VV(vmseq_vv_w, uint32_t, H4, DO_MSEQ) +GEN_VEXT_CMP_VV(vmseq_vv_d, uint64_t, H8, DO_MSEQ) + +GEN_VEXT_CMP_VV(vmsne_vv_b, uint8_t, H1, DO_MSNE) +GEN_VEXT_CMP_VV(vmsne_vv_h, uint16_t, H2, DO_MSNE) +GEN_VEXT_CMP_VV(vmsne_vv_w, uint32_t, H4, DO_MSNE) +GEN_VEXT_CMP_VV(vmsne_vv_d, uint64_t, H8, DO_MSNE) + +GEN_VEXT_CMP_VV(vmsltu_vv_b, uint8_t, H1, DO_MSLT) +GEN_VEXT_CMP_VV(vmsltu_vv_h, uint16_t, H2, DO_MSLT) +GEN_VEXT_CMP_VV(vmsltu_vv_w, uint32_t, H4, DO_MSLT) +GEN_VEXT_CMP_VV(vmsltu_vv_d, uint64_t, H8, DO_MSLT) + +GEN_VEXT_CMP_VV(vmslt_vv_b, int8_t, H1, DO_MSLT) +GEN_VEXT_CMP_VV(vmslt_vv_h, int16_t, H2, DO_MSLT) +GEN_VEXT_CMP_VV(vmslt_vv_w, int32_t, H4, DO_MSLT) +GEN_VEXT_CMP_VV(vmslt_vv_d, int64_t, H8, DO_MSLT) + +GEN_VEXT_CMP_VV(vmsleu_vv_b, uint8_t, H1, DO_MSLE) +GEN_VEXT_CMP_VV(vmsleu_vv_h, uint16_t, H2, DO_MSLE) +GEN_VEXT_CMP_VV(vmsleu_vv_w, uint32_t, H4, DO_MSLE) +GEN_VEXT_CMP_VV(vmsleu_vv_d, uint64_t, H8, DO_MSLE) + +GEN_VEXT_CMP_VV(vmsle_vv_b, int8_t, H1, DO_MSLE) +GEN_VEXT_CMP_VV(vmsle_vv_h, int16_t, H2, DO_MSLE) +GEN_VEXT_CMP_VV(vmsle_vv_w, int32_t, H4, DO_MSLE) +GEN_VEXT_CMP_VV(vmsle_vv_d, int64_t, H8, DO_MSLE) + +#define GEN_VEXT_CMP_VX(NAME, ETYPE, H, DO_OP) \ +void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vm = vext_vm(desc); \ + uint32_t vl = env->vl; \ + uint32_t vlmax = vext_maxsz(desc) / sizeof(ETYPE); \ + uint32_t i; \ + \ + for (i = 0; i < vl; i++) { \ + ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ + if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + continue; \ + } \ + vext_set_elem_mask(vd, mlen, i, \ + DO_OP(s2, (ETYPE)(target_long)s1)); \ + } \ + for (; i < vlmax; i++) { \ + vext_set_elem_mask(vd, mlen, i, 0); \ + } \ +} + +GEN_VEXT_CMP_VX(vmseq_vx_b, uint8_t, H1, DO_MSEQ) +GEN_VEXT_CMP_VX(vmseq_vx_h, uint16_t, H2, DO_MSEQ) +GEN_VEXT_CMP_VX(vmseq_vx_w, uint32_t, H4, DO_MSEQ) +GEN_VEXT_CMP_VX(vmseq_vx_d, uint64_t, H8, DO_MSEQ) + +GEN_VEXT_CMP_VX(vmsne_vx_b, uint8_t, H1, DO_MSNE) +GEN_VEXT_CMP_VX(vmsne_vx_h, uint16_t, H2, DO_MSNE) +GEN_VEXT_CMP_VX(vmsne_vx_w, uint32_t, H4, DO_MSNE) +GEN_VEXT_CMP_VX(vmsne_vx_d, uint64_t, H8, DO_MSNE) + +GEN_VEXT_CMP_VX(vmsltu_vx_b, uint8_t, H1, DO_MSLT) +GEN_VEXT_CMP_VX(vmsltu_vx_h, uint16_t, H2, DO_MSLT) +GEN_VEXT_CMP_VX(vmsltu_vx_w, uint32_t, H4, DO_MSLT) +GEN_VEXT_CMP_VX(vmsltu_vx_d, uint64_t, H8, DO_MSLT) + +GEN_VEXT_CMP_VX(vmslt_vx_b, int8_t, H1, DO_MSLT) +GEN_VEXT_CMP_VX(vmslt_vx_h, int16_t, H2, DO_MSLT) +GEN_VEXT_CMP_VX(vmslt_vx_w, int32_t, H4, DO_MSLT) +GEN_VEXT_CMP_VX(vmslt_vx_d, int64_t, H8, DO_MSLT) + +GEN_VEXT_CMP_VX(vmsleu_vx_b, uint8_t, H1, DO_MSLE) +GEN_VEXT_CMP_VX(vmsleu_vx_h, uint16_t, H2, DO_MSLE) +GEN_VEXT_CMP_VX(vmsleu_vx_w, uint32_t, H4, DO_MSLE) +GEN_VEXT_CMP_VX(vmsleu_vx_d, uint64_t, H8, DO_MSLE) + +GEN_VEXT_CMP_VX(vmsle_vx_b, int8_t, H1, DO_MSLE) +GEN_VEXT_CMP_VX(vmsle_vx_h, int16_t, H2, DO_MSLE) +GEN_VEXT_CMP_VX(vmsle_vx_w, int32_t, H4, DO_MSLE) +GEN_VEXT_CMP_VX(vmsle_vx_d, int64_t, H8, DO_MSLE) + +GEN_VEXT_CMP_VX(vmsgtu_vx_b, uint8_t, H1, DO_MSGT) +GEN_VEXT_CMP_VX(vmsgtu_vx_h, uint16_t, H2, DO_MSGT) +GEN_VEXT_CMP_VX(vmsgtu_vx_w, uint32_t, H4, DO_MSGT) +GEN_VEXT_CMP_VX(vmsgtu_vx_d, uint64_t, H8, DO_MSGT) + +GEN_VEXT_CMP_VX(vmsgt_vx_b, int8_t, H1, DO_MSGT) +GEN_VEXT_CMP_VX(vmsgt_vx_h, int16_t, H2, DO_MSGT) +GEN_VEXT_CMP_VX(vmsgt_vx_w, int32_t, H4, DO_MSGT) +GEN_VEXT_CMP_VX(vmsgt_vx_d, int64_t, H8, DO_MSGT) + +/* Vector Integer Min/Max Instructions */ +RVVCALL(OPIVV2, vminu_vv_b, OP_UUU_B, H1, H1, H1, DO_MIN) +RVVCALL(OPIVV2, vminu_vv_h, OP_UUU_H, H2, H2, H2, DO_MIN) +RVVCALL(OPIVV2, vminu_vv_w, OP_UUU_W, H4, H4, H4, DO_MIN) +RVVCALL(OPIVV2, vminu_vv_d, OP_UUU_D, H8, H8, H8, DO_MIN) +RVVCALL(OPIVV2, vmin_vv_b, OP_SSS_B, H1, H1, H1, DO_MIN) +RVVCALL(OPIVV2, vmin_vv_h, OP_SSS_H, H2, H2, H2, DO_MIN) +RVVCALL(OPIVV2, vmin_vv_w, OP_SSS_W, H4, H4, H4, DO_MIN) +RVVCALL(OPIVV2, vmin_vv_d, OP_SSS_D, H8, H8, H8, DO_MIN) +RVVCALL(OPIVV2, vmaxu_vv_b, OP_UUU_B, H1, H1, H1, DO_MAX) +RVVCALL(OPIVV2, vmaxu_vv_h, OP_UUU_H, H2, H2, H2, DO_MAX) +RVVCALL(OPIVV2, vmaxu_vv_w, OP_UUU_W, H4, H4, H4, DO_MAX) +RVVCALL(OPIVV2, vmaxu_vv_d, OP_UUU_D, H8, H8, H8, DO_MAX) +RVVCALL(OPIVV2, vmax_vv_b, OP_SSS_B, H1, H1, H1, DO_MAX) +RVVCALL(OPIVV2, vmax_vv_h, OP_SSS_H, H2, H2, H2, DO_MAX) +RVVCALL(OPIVV2, vmax_vv_w, OP_SSS_W, H4, H4, H4, DO_MAX) +RVVCALL(OPIVV2, vmax_vv_d, OP_SSS_D, H8, H8, H8, DO_MAX) +GEN_VEXT_VV(vminu_vv_b, 1, 1, clearb) +GEN_VEXT_VV(vminu_vv_h, 2, 2, clearh) +GEN_VEXT_VV(vminu_vv_w, 4, 4, clearl) +GEN_VEXT_VV(vminu_vv_d, 8, 8, clearq) +GEN_VEXT_VV(vmin_vv_b, 1, 1, clearb) +GEN_VEXT_VV(vmin_vv_h, 2, 2, clearh) +GEN_VEXT_VV(vmin_vv_w, 4, 4, clearl) +GEN_VEXT_VV(vmin_vv_d, 8, 8, clearq) +GEN_VEXT_VV(vmaxu_vv_b, 1, 1, clearb) +GEN_VEXT_VV(vmaxu_vv_h, 2, 2, clearh) +GEN_VEXT_VV(vmaxu_vv_w, 4, 4, clearl) +GEN_VEXT_VV(vmaxu_vv_d, 8, 8, clearq) +GEN_VEXT_VV(vmax_vv_b, 1, 1, clearb) +GEN_VEXT_VV(vmax_vv_h, 2, 2, clearh) +GEN_VEXT_VV(vmax_vv_w, 4, 4, clearl) +GEN_VEXT_VV(vmax_vv_d, 8, 8, clearq) + +RVVCALL(OPIVX2, vminu_vx_b, OP_UUU_B, H1, H1, DO_MIN) +RVVCALL(OPIVX2, vminu_vx_h, OP_UUU_H, H2, H2, DO_MIN) +RVVCALL(OPIVX2, vminu_vx_w, OP_UUU_W, H4, H4, DO_MIN) +RVVCALL(OPIVX2, vminu_vx_d, OP_UUU_D, H8, H8, DO_MIN) +RVVCALL(OPIVX2, vmin_vx_b, OP_SSS_B, H1, H1, DO_MIN) +RVVCALL(OPIVX2, vmin_vx_h, OP_SSS_H, H2, H2, DO_MIN) +RVVCALL(OPIVX2, vmin_vx_w, OP_SSS_W, H4, H4, DO_MIN) +RVVCALL(OPIVX2, vmin_vx_d, OP_SSS_D, H8, H8, DO_MIN) +RVVCALL(OPIVX2, vmaxu_vx_b, OP_UUU_B, H1, H1, DO_MAX) +RVVCALL(OPIVX2, vmaxu_vx_h, OP_UUU_H, H2, H2, DO_MAX) +RVVCALL(OPIVX2, vmaxu_vx_w, OP_UUU_W, H4, H4, DO_MAX) +RVVCALL(OPIVX2, vmaxu_vx_d, OP_UUU_D, H8, H8, DO_MAX) +RVVCALL(OPIVX2, vmax_vx_b, OP_SSS_B, H1, H1, DO_MAX) +RVVCALL(OPIVX2, vmax_vx_h, OP_SSS_H, H2, H2, DO_MAX) +RVVCALL(OPIVX2, vmax_vx_w, OP_SSS_W, H4, H4, DO_MAX) +RVVCALL(OPIVX2, vmax_vx_d, OP_SSS_D, H8, H8, DO_MAX) +GEN_VEXT_VX(vminu_vx_b, 1, 1, clearb) +GEN_VEXT_VX(vminu_vx_h, 2, 2, clearh) +GEN_VEXT_VX(vminu_vx_w, 4, 4, clearl) +GEN_VEXT_VX(vminu_vx_d, 8, 8, clearq) +GEN_VEXT_VX(vmin_vx_b, 1, 1, clearb) +GEN_VEXT_VX(vmin_vx_h, 2, 2, clearh) +GEN_VEXT_VX(vmin_vx_w, 4, 4, clearl) +GEN_VEXT_VX(vmin_vx_d, 8, 8, clearq) +GEN_VEXT_VX(vmaxu_vx_b, 1, 1, clearb) +GEN_VEXT_VX(vmaxu_vx_h, 2, 2, clearh) +GEN_VEXT_VX(vmaxu_vx_w, 4, 4, clearl) +GEN_VEXT_VX(vmaxu_vx_d, 8, 8, clearq) +GEN_VEXT_VX(vmax_vx_b, 1, 1, clearb) +GEN_VEXT_VX(vmax_vx_h, 2, 2, clearh) +GEN_VEXT_VX(vmax_vx_w, 4, 4, clearl) +GEN_VEXT_VX(vmax_vx_d, 8, 8, clearq) + +/* Vector Single-Width Integer Multiply Instructions */ +#define DO_MUL(N, M) (N * M) +RVVCALL(OPIVV2, vmul_vv_b, OP_SSS_B, H1, H1, H1, DO_MUL) +RVVCALL(OPIVV2, vmul_vv_h, OP_SSS_H, H2, H2, H2, DO_MUL) +RVVCALL(OPIVV2, vmul_vv_w, OP_SSS_W, H4, H4, H4, DO_MUL) +RVVCALL(OPIVV2, vmul_vv_d, OP_SSS_D, H8, H8, H8, DO_MUL) +GEN_VEXT_VV(vmul_vv_b, 1, 1, clearb) +GEN_VEXT_VV(vmul_vv_h, 2, 2, clearh) +GEN_VEXT_VV(vmul_vv_w, 4, 4, clearl) +GEN_VEXT_VV(vmul_vv_d, 8, 8, clearq) + +static int8_t do_mulh_b(int8_t s2, int8_t s1) +{ + return (int16_t)s2 * (int16_t)s1 >> 8; +} + +static int16_t do_mulh_h(int16_t s2, int16_t s1) +{ + return (int32_t)s2 * (int32_t)s1 >> 16; +} + +static int32_t do_mulh_w(int32_t s2, int32_t s1) +{ + return (int64_t)s2 * (int64_t)s1 >> 32; +} + +static int64_t do_mulh_d(int64_t s2, int64_t s1) +{ + uint64_t hi_64, lo_64; + + muls64(&lo_64, &hi_64, s1, s2); + return hi_64; +} + +static uint8_t do_mulhu_b(uint8_t s2, uint8_t s1) +{ + return (uint16_t)s2 * (uint16_t)s1 >> 8; +} + +static uint16_t do_mulhu_h(uint16_t s2, uint16_t s1) +{ + return (uint32_t)s2 * (uint32_t)s1 >> 16; +} + +static uint32_t do_mulhu_w(uint32_t s2, uint32_t s1) +{ + return (uint64_t)s2 * (uint64_t)s1 >> 32; +} + +static uint64_t do_mulhu_d(uint64_t s2, uint64_t s1) +{ + uint64_t hi_64, lo_64; + + mulu64(&lo_64, &hi_64, s2, s1); + return hi_64; +} + +static int8_t do_mulhsu_b(int8_t s2, uint8_t s1) +{ + return (int16_t)s2 * (uint16_t)s1 >> 8; +} + +static int16_t do_mulhsu_h(int16_t s2, uint16_t s1) +{ + return (int32_t)s2 * (uint32_t)s1 >> 16; +} + +static int32_t do_mulhsu_w(int32_t s2, uint32_t s1) +{ + return (int64_t)s2 * (uint64_t)s1 >> 32; +} + +/* + * Let A = signed operand, + * B = unsigned operand + * P = mulu64(A, B), unsigned product + * + * LET X = 2 ** 64 - A, 2's complement of A + * SP = signed product + * THEN + * IF A < 0 + * SP = -X * B + * = -(2 ** 64 - A) * B + * = A * B - 2 ** 64 * B + * = P - 2 ** 64 * B + * ELSE + * SP = P + * THEN + * HI_P -= (A < 0 ? B : 0) + */ + +static int64_t do_mulhsu_d(int64_t s2, uint64_t s1) +{ + uint64_t hi_64, lo_64; + + mulu64(&lo_64, &hi_64, s2, s1); + + hi_64 -= s2 < 0 ? s1 : 0; + return hi_64; +} + +RVVCALL(OPIVV2, vmulh_vv_b, OP_SSS_B, H1, H1, H1, do_mulh_b) +RVVCALL(OPIVV2, vmulh_vv_h, OP_SSS_H, H2, H2, H2, do_mulh_h) +RVVCALL(OPIVV2, vmulh_vv_w, OP_SSS_W, H4, H4, H4, do_mulh_w) +RVVCALL(OPIVV2, vmulh_vv_d, OP_SSS_D, H8, H8, H8, do_mulh_d) +RVVCALL(OPIVV2, vmulhu_vv_b, OP_UUU_B, H1, H1, H1, do_mulhu_b) +RVVCALL(OPIVV2, vmulhu_vv_h, OP_UUU_H, H2, H2, H2, do_mulhu_h) +RVVCALL(OPIVV2, vmulhu_vv_w, OP_UUU_W, H4, H4, H4, do_mulhu_w) +RVVCALL(OPIVV2, vmulhu_vv_d, OP_UUU_D, H8, H8, H8, do_mulhu_d) +RVVCALL(OPIVV2, vmulhsu_vv_b, OP_SUS_B, H1, H1, H1, do_mulhsu_b) +RVVCALL(OPIVV2, vmulhsu_vv_h, OP_SUS_H, H2, H2, H2, do_mulhsu_h) +RVVCALL(OPIVV2, vmulhsu_vv_w, OP_SUS_W, H4, H4, H4, do_mulhsu_w) +RVVCALL(OPIVV2, vmulhsu_vv_d, OP_SUS_D, H8, H8, H8, do_mulhsu_d) +GEN_VEXT_VV(vmulh_vv_b, 1, 1, clearb) +GEN_VEXT_VV(vmulh_vv_h, 2, 2, clearh) +GEN_VEXT_VV(vmulh_vv_w, 4, 4, clearl) +GEN_VEXT_VV(vmulh_vv_d, 8, 8, clearq) +GEN_VEXT_VV(vmulhu_vv_b, 1, 1, clearb) +GEN_VEXT_VV(vmulhu_vv_h, 2, 2, clearh) +GEN_VEXT_VV(vmulhu_vv_w, 4, 4, clearl) +GEN_VEXT_VV(vmulhu_vv_d, 8, 8, clearq) +GEN_VEXT_VV(vmulhsu_vv_b, 1, 1, clearb) +GEN_VEXT_VV(vmulhsu_vv_h, 2, 2, clearh) +GEN_VEXT_VV(vmulhsu_vv_w, 4, 4, clearl) +GEN_VEXT_VV(vmulhsu_vv_d, 8, 8, clearq) + +RVVCALL(OPIVX2, vmul_vx_b, OP_SSS_B, H1, H1, DO_MUL) +RVVCALL(OPIVX2, vmul_vx_h, OP_SSS_H, H2, H2, DO_MUL) +RVVCALL(OPIVX2, vmul_vx_w, OP_SSS_W, H4, H4, DO_MUL) +RVVCALL(OPIVX2, vmul_vx_d, OP_SSS_D, H8, H8, DO_MUL) +RVVCALL(OPIVX2, vmulh_vx_b, OP_SSS_B, H1, H1, do_mulh_b) +RVVCALL(OPIVX2, vmulh_vx_h, OP_SSS_H, H2, H2, do_mulh_h) +RVVCALL(OPIVX2, vmulh_vx_w, OP_SSS_W, H4, H4, do_mulh_w) +RVVCALL(OPIVX2, vmulh_vx_d, OP_SSS_D, H8, H8, do_mulh_d) +RVVCALL(OPIVX2, vmulhu_vx_b, OP_UUU_B, H1, H1, do_mulhu_b) +RVVCALL(OPIVX2, vmulhu_vx_h, OP_UUU_H, H2, H2, do_mulhu_h) +RVVCALL(OPIVX2, vmulhu_vx_w, OP_UUU_W, H4, H4, do_mulhu_w) +RVVCALL(OPIVX2, vmulhu_vx_d, OP_UUU_D, H8, H8, do_mulhu_d) +RVVCALL(OPIVX2, vmulhsu_vx_b, OP_SUS_B, H1, H1, do_mulhsu_b) +RVVCALL(OPIVX2, vmulhsu_vx_h, OP_SUS_H, H2, H2, do_mulhsu_h) +RVVCALL(OPIVX2, vmulhsu_vx_w, OP_SUS_W, H4, H4, do_mulhsu_w) +RVVCALL(OPIVX2, vmulhsu_vx_d, OP_SUS_D, H8, H8, do_mulhsu_d) +GEN_VEXT_VX(vmul_vx_b, 1, 1, clearb) +GEN_VEXT_VX(vmul_vx_h, 2, 2, clearh) +GEN_VEXT_VX(vmul_vx_w, 4, 4, clearl) +GEN_VEXT_VX(vmul_vx_d, 8, 8, clearq) +GEN_VEXT_VX(vmulh_vx_b, 1, 1, clearb) +GEN_VEXT_VX(vmulh_vx_h, 2, 2, clearh) +GEN_VEXT_VX(vmulh_vx_w, 4, 4, clearl) +GEN_VEXT_VX(vmulh_vx_d, 8, 8, clearq) +GEN_VEXT_VX(vmulhu_vx_b, 1, 1, clearb) +GEN_VEXT_VX(vmulhu_vx_h, 2, 2, clearh) +GEN_VEXT_VX(vmulhu_vx_w, 4, 4, clearl) +GEN_VEXT_VX(vmulhu_vx_d, 8, 8, clearq) +GEN_VEXT_VX(vmulhsu_vx_b, 1, 1, clearb) +GEN_VEXT_VX(vmulhsu_vx_h, 2, 2, clearh) +GEN_VEXT_VX(vmulhsu_vx_w, 4, 4, clearl) +GEN_VEXT_VX(vmulhsu_vx_d, 8, 8, clearq) + +/* Vector Integer Divide Instructions */ +#define DO_DIVU(N, M) (unlikely(M == 0) ? (__typeof(N))(-1) : N / M) +#define DO_REMU(N, M) (unlikely(M == 0) ? N : N % M) +#define DO_DIV(N, M) (unlikely(M == 0) ? (__typeof(N))(-1) :\ + unlikely((N == -N) && (M == (__typeof(N))(-1))) ? N : N / M) +#define DO_REM(N, M) (unlikely(M == 0) ? N :\ + unlikely((N == -N) && (M == (__typeof(N))(-1))) ? 0 : N % M) + +RVVCALL(OPIVV2, vdivu_vv_b, OP_UUU_B, H1, H1, H1, DO_DIVU) +RVVCALL(OPIVV2, vdivu_vv_h, OP_UUU_H, H2, H2, H2, DO_DIVU) +RVVCALL(OPIVV2, vdivu_vv_w, OP_UUU_W, H4, H4, H4, DO_DIVU) +RVVCALL(OPIVV2, vdivu_vv_d, OP_UUU_D, H8, H8, H8, DO_DIVU) +RVVCALL(OPIVV2, vdiv_vv_b, OP_SSS_B, H1, H1, H1, DO_DIV) +RVVCALL(OPIVV2, vdiv_vv_h, OP_SSS_H, H2, H2, H2, DO_DIV) +RVVCALL(OPIVV2, vdiv_vv_w, OP_SSS_W, H4, H4, H4, DO_DIV) +RVVCALL(OPIVV2, vdiv_vv_d, OP_SSS_D, H8, H8, H8, DO_DIV) +RVVCALL(OPIVV2, vremu_vv_b, OP_UUU_B, H1, H1, H1, DO_REMU) +RVVCALL(OPIVV2, vremu_vv_h, OP_UUU_H, H2, H2, H2, DO_REMU) +RVVCALL(OPIVV2, vremu_vv_w, OP_UUU_W, H4, H4, H4, DO_REMU) +RVVCALL(OPIVV2, vremu_vv_d, OP_UUU_D, H8, H8, H8, DO_REMU) +RVVCALL(OPIVV2, vrem_vv_b, OP_SSS_B, H1, H1, H1, DO_REM) +RVVCALL(OPIVV2, vrem_vv_h, OP_SSS_H, H2, H2, H2, DO_REM) +RVVCALL(OPIVV2, vrem_vv_w, OP_SSS_W, H4, H4, H4, DO_REM) +RVVCALL(OPIVV2, vrem_vv_d, OP_SSS_D, H8, H8, H8, DO_REM) +GEN_VEXT_VV(vdivu_vv_b, 1, 1, clearb) +GEN_VEXT_VV(vdivu_vv_h, 2, 2, clearh) +GEN_VEXT_VV(vdivu_vv_w, 4, 4, clearl) +GEN_VEXT_VV(vdivu_vv_d, 8, 8, clearq) +GEN_VEXT_VV(vdiv_vv_b, 1, 1, clearb) +GEN_VEXT_VV(vdiv_vv_h, 2, 2, clearh) +GEN_VEXT_VV(vdiv_vv_w, 4, 4, clearl) +GEN_VEXT_VV(vdiv_vv_d, 8, 8, clearq) +GEN_VEXT_VV(vremu_vv_b, 1, 1, clearb) +GEN_VEXT_VV(vremu_vv_h, 2, 2, clearh) +GEN_VEXT_VV(vremu_vv_w, 4, 4, clearl) +GEN_VEXT_VV(vremu_vv_d, 8, 8, clearq) +GEN_VEXT_VV(vrem_vv_b, 1, 1, clearb) +GEN_VEXT_VV(vrem_vv_h, 2, 2, clearh) +GEN_VEXT_VV(vrem_vv_w, 4, 4, clearl) +GEN_VEXT_VV(vrem_vv_d, 8, 8, clearq) + +RVVCALL(OPIVX2, vdivu_vx_b, OP_UUU_B, H1, H1, DO_DIVU) +RVVCALL(OPIVX2, vdivu_vx_h, OP_UUU_H, H2, H2, DO_DIVU) +RVVCALL(OPIVX2, vdivu_vx_w, OP_UUU_W, H4, H4, DO_DIVU) +RVVCALL(OPIVX2, vdivu_vx_d, OP_UUU_D, H8, H8, DO_DIVU) +RVVCALL(OPIVX2, vdiv_vx_b, OP_SSS_B, H1, H1, DO_DIV) +RVVCALL(OPIVX2, vdiv_vx_h, OP_SSS_H, H2, H2, DO_DIV) +RVVCALL(OPIVX2, vdiv_vx_w, OP_SSS_W, H4, H4, DO_DIV) +RVVCALL(OPIVX2, vdiv_vx_d, OP_SSS_D, H8, H8, DO_DIV) +RVVCALL(OPIVX2, vremu_vx_b, OP_UUU_B, H1, H1, DO_REMU) +RVVCALL(OPIVX2, vremu_vx_h, OP_UUU_H, H2, H2, DO_REMU) +RVVCALL(OPIVX2, vremu_vx_w, OP_UUU_W, H4, H4, DO_REMU) +RVVCALL(OPIVX2, vremu_vx_d, OP_UUU_D, H8, H8, DO_REMU) +RVVCALL(OPIVX2, vrem_vx_b, OP_SSS_B, H1, H1, DO_REM) +RVVCALL(OPIVX2, vrem_vx_h, OP_SSS_H, H2, H2, DO_REM) +RVVCALL(OPIVX2, vrem_vx_w, OP_SSS_W, H4, H4, DO_REM) +RVVCALL(OPIVX2, vrem_vx_d, OP_SSS_D, H8, H8, DO_REM) +GEN_VEXT_VX(vdivu_vx_b, 1, 1, clearb) +GEN_VEXT_VX(vdivu_vx_h, 2, 2, clearh) +GEN_VEXT_VX(vdivu_vx_w, 4, 4, clearl) +GEN_VEXT_VX(vdivu_vx_d, 8, 8, clearq) +GEN_VEXT_VX(vdiv_vx_b, 1, 1, clearb) +GEN_VEXT_VX(vdiv_vx_h, 2, 2, clearh) +GEN_VEXT_VX(vdiv_vx_w, 4, 4, clearl) +GEN_VEXT_VX(vdiv_vx_d, 8, 8, clearq) +GEN_VEXT_VX(vremu_vx_b, 1, 1, clearb) +GEN_VEXT_VX(vremu_vx_h, 2, 2, clearh) +GEN_VEXT_VX(vremu_vx_w, 4, 4, clearl) +GEN_VEXT_VX(vremu_vx_d, 8, 8, clearq) +GEN_VEXT_VX(vrem_vx_b, 1, 1, clearb) +GEN_VEXT_VX(vrem_vx_h, 2, 2, clearh) +GEN_VEXT_VX(vrem_vx_w, 4, 4, clearl) +GEN_VEXT_VX(vrem_vx_d, 8, 8, clearq) + +/* Vector Widening Integer Multiply Instructions */ +RVVCALL(OPIVV2, vwmul_vv_b, WOP_SSS_B, H2, H1, H1, DO_MUL) +RVVCALL(OPIVV2, vwmul_vv_h, WOP_SSS_H, H4, H2, H2, DO_MUL) +RVVCALL(OPIVV2, vwmul_vv_w, WOP_SSS_W, H8, H4, H4, DO_MUL) +RVVCALL(OPIVV2, vwmulu_vv_b, WOP_UUU_B, H2, H1, H1, DO_MUL) +RVVCALL(OPIVV2, vwmulu_vv_h, WOP_UUU_H, H4, H2, H2, DO_MUL) +RVVCALL(OPIVV2, vwmulu_vv_w, WOP_UUU_W, H8, H4, H4, DO_MUL) +RVVCALL(OPIVV2, vwmulsu_vv_b, WOP_SUS_B, H2, H1, H1, DO_MUL) +RVVCALL(OPIVV2, vwmulsu_vv_h, WOP_SUS_H, H4, H2, H2, DO_MUL) +RVVCALL(OPIVV2, vwmulsu_vv_w, WOP_SUS_W, H8, H4, H4, DO_MUL) +GEN_VEXT_VV(vwmul_vv_b, 1, 2, clearh) +GEN_VEXT_VV(vwmul_vv_h, 2, 4, clearl) +GEN_VEXT_VV(vwmul_vv_w, 4, 8, clearq) +GEN_VEXT_VV(vwmulu_vv_b, 1, 2, clearh) +GEN_VEXT_VV(vwmulu_vv_h, 2, 4, clearl) +GEN_VEXT_VV(vwmulu_vv_w, 4, 8, clearq) +GEN_VEXT_VV(vwmulsu_vv_b, 1, 2, clearh) +GEN_VEXT_VV(vwmulsu_vv_h, 2, 4, clearl) +GEN_VEXT_VV(vwmulsu_vv_w, 4, 8, clearq) + +RVVCALL(OPIVX2, vwmul_vx_b, WOP_SSS_B, H2, H1, DO_MUL) +RVVCALL(OPIVX2, vwmul_vx_h, WOP_SSS_H, H4, H2, DO_MUL) +RVVCALL(OPIVX2, vwmul_vx_w, WOP_SSS_W, H8, H4, DO_MUL) +RVVCALL(OPIVX2, vwmulu_vx_b, WOP_UUU_B, H2, H1, DO_MUL) +RVVCALL(OPIVX2, vwmulu_vx_h, WOP_UUU_H, H4, H2, DO_MUL) +RVVCALL(OPIVX2, vwmulu_vx_w, WOP_UUU_W, H8, H4, DO_MUL) +RVVCALL(OPIVX2, vwmulsu_vx_b, WOP_SUS_B, H2, H1, DO_MUL) +RVVCALL(OPIVX2, vwmulsu_vx_h, WOP_SUS_H, H4, H2, DO_MUL) +RVVCALL(OPIVX2, vwmulsu_vx_w, WOP_SUS_W, H8, H4, DO_MUL) +GEN_VEXT_VX(vwmul_vx_b, 1, 2, clearh) +GEN_VEXT_VX(vwmul_vx_h, 2, 4, clearl) +GEN_VEXT_VX(vwmul_vx_w, 4, 8, clearq) +GEN_VEXT_VX(vwmulu_vx_b, 1, 2, clearh) +GEN_VEXT_VX(vwmulu_vx_h, 2, 4, clearl) +GEN_VEXT_VX(vwmulu_vx_w, 4, 8, clearq) +GEN_VEXT_VX(vwmulsu_vx_b, 1, 2, clearh) +GEN_VEXT_VX(vwmulsu_vx_h, 2, 4, clearl) +GEN_VEXT_VX(vwmulsu_vx_w, 4, 8, clearq) + +/* Vector Single-Width Integer Multiply-Add Instructions */ +#define OPIVV3(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 d = *((TD *)vd + HD(i)); \ + *((TD *)vd + HD(i)) = OP(s2, s1, d); \ +} + +#define DO_MACC(N, M, D) (M * N + D) +#define DO_NMSAC(N, M, D) (-(M * N) + D) +#define DO_MADD(N, M, D) (M * D + N) +#define DO_NMSUB(N, M, D) (-(M * D) + N) +RVVCALL(OPIVV3, vmacc_vv_b, OP_SSS_B, H1, H1, H1, DO_MACC) +RVVCALL(OPIVV3, vmacc_vv_h, OP_SSS_H, H2, H2, H2, DO_MACC) +RVVCALL(OPIVV3, vmacc_vv_w, OP_SSS_W, H4, H4, H4, DO_MACC) +RVVCALL(OPIVV3, vmacc_vv_d, OP_SSS_D, H8, H8, H8, DO_MACC) +RVVCALL(OPIVV3, vnmsac_vv_b, OP_SSS_B, H1, H1, H1, DO_NMSAC) +RVVCALL(OPIVV3, vnmsac_vv_h, OP_SSS_H, H2, H2, H2, DO_NMSAC) +RVVCALL(OPIVV3, vnmsac_vv_w, OP_SSS_W, H4, H4, H4, DO_NMSAC) +RVVCALL(OPIVV3, vnmsac_vv_d, OP_SSS_D, H8, H8, H8, DO_NMSAC) +RVVCALL(OPIVV3, vmadd_vv_b, OP_SSS_B, H1, H1, H1, DO_MADD) +RVVCALL(OPIVV3, vmadd_vv_h, OP_SSS_H, H2, H2, H2, DO_MADD) +RVVCALL(OPIVV3, vmadd_vv_w, OP_SSS_W, H4, H4, H4, DO_MADD) +RVVCALL(OPIVV3, vmadd_vv_d, OP_SSS_D, H8, H8, H8, DO_MADD) +RVVCALL(OPIVV3, vnmsub_vv_b, OP_SSS_B, H1, H1, H1, DO_NMSUB) +RVVCALL(OPIVV3, vnmsub_vv_h, OP_SSS_H, H2, H2, H2, DO_NMSUB) +RVVCALL(OPIVV3, vnmsub_vv_w, OP_SSS_W, H4, H4, H4, DO_NMSUB) +RVVCALL(OPIVV3, vnmsub_vv_d, OP_SSS_D, H8, H8, H8, DO_NMSUB) +GEN_VEXT_VV(vmacc_vv_b, 1, 1, clearb) +GEN_VEXT_VV(vmacc_vv_h, 2, 2, clearh) +GEN_VEXT_VV(vmacc_vv_w, 4, 4, clearl) +GEN_VEXT_VV(vmacc_vv_d, 8, 8, clearq) +GEN_VEXT_VV(vnmsac_vv_b, 1, 1, clearb) +GEN_VEXT_VV(vnmsac_vv_h, 2, 2, clearh) +GEN_VEXT_VV(vnmsac_vv_w, 4, 4, clearl) +GEN_VEXT_VV(vnmsac_vv_d, 8, 8, clearq) +GEN_VEXT_VV(vmadd_vv_b, 1, 1, clearb) +GEN_VEXT_VV(vmadd_vv_h, 2, 2, clearh) +GEN_VEXT_VV(vmadd_vv_w, 4, 4, clearl) +GEN_VEXT_VV(vmadd_vv_d, 8, 8, clearq) +GEN_VEXT_VV(vnmsub_vv_b, 1, 1, clearb) +GEN_VEXT_VV(vnmsub_vv_h, 2, 2, clearh) +GEN_VEXT_VV(vnmsub_vv_w, 4, 4, clearl) +GEN_VEXT_VV(vnmsub_vv_d, 8, 8, clearq) + +#define OPIVX3(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 d = *((TD *)vd + HD(i)); \ + *((TD *)vd + HD(i)) = OP(s2, (TX1)(T1)s1, d); \ +} + +RVVCALL(OPIVX3, vmacc_vx_b, OP_SSS_B, H1, H1, DO_MACC) +RVVCALL(OPIVX3, vmacc_vx_h, OP_SSS_H, H2, H2, DO_MACC) +RVVCALL(OPIVX3, vmacc_vx_w, OP_SSS_W, H4, H4, DO_MACC) +RVVCALL(OPIVX3, vmacc_vx_d, OP_SSS_D, H8, H8, DO_MACC) +RVVCALL(OPIVX3, vnmsac_vx_b, OP_SSS_B, H1, H1, DO_NMSAC) +RVVCALL(OPIVX3, vnmsac_vx_h, OP_SSS_H, H2, H2, DO_NMSAC) +RVVCALL(OPIVX3, vnmsac_vx_w, OP_SSS_W, H4, H4, DO_NMSAC) +RVVCALL(OPIVX3, vnmsac_vx_d, OP_SSS_D, H8, H8, DO_NMSAC) +RVVCALL(OPIVX3, vmadd_vx_b, OP_SSS_B, H1, H1, DO_MADD) +RVVCALL(OPIVX3, vmadd_vx_h, OP_SSS_H, H2, H2, DO_MADD) +RVVCALL(OPIVX3, vmadd_vx_w, OP_SSS_W, H4, H4, DO_MADD) +RVVCALL(OPIVX3, vmadd_vx_d, OP_SSS_D, H8, H8, DO_MADD) +RVVCALL(OPIVX3, vnmsub_vx_b, OP_SSS_B, H1, H1, DO_NMSUB) +RVVCALL(OPIVX3, vnmsub_vx_h, OP_SSS_H, H2, H2, DO_NMSUB) +RVVCALL(OPIVX3, vnmsub_vx_w, OP_SSS_W, H4, H4, DO_NMSUB) +RVVCALL(OPIVX3, vnmsub_vx_d, OP_SSS_D, H8, H8, DO_NMSUB) +GEN_VEXT_VX(vmacc_vx_b, 1, 1, clearb) +GEN_VEXT_VX(vmacc_vx_h, 2, 2, clearh) +GEN_VEXT_VX(vmacc_vx_w, 4, 4, clearl) +GEN_VEXT_VX(vmacc_vx_d, 8, 8, clearq) +GEN_VEXT_VX(vnmsac_vx_b, 1, 1, clearb) +GEN_VEXT_VX(vnmsac_vx_h, 2, 2, clearh) +GEN_VEXT_VX(vnmsac_vx_w, 4, 4, clearl) +GEN_VEXT_VX(vnmsac_vx_d, 8, 8, clearq) +GEN_VEXT_VX(vmadd_vx_b, 1, 1, clearb) +GEN_VEXT_VX(vmadd_vx_h, 2, 2, clearh) +GEN_VEXT_VX(vmadd_vx_w, 4, 4, clearl) +GEN_VEXT_VX(vmadd_vx_d, 8, 8, clearq) +GEN_VEXT_VX(vnmsub_vx_b, 1, 1, clearb) +GEN_VEXT_VX(vnmsub_vx_h, 2, 2, clearh) +GEN_VEXT_VX(vnmsub_vx_w, 4, 4, clearl) +GEN_VEXT_VX(vnmsub_vx_d, 8, 8, clearq) + +/* Vector Widening Integer Multiply-Add Instructions */ +RVVCALL(OPIVV3, vwmaccu_vv_b, WOP_UUU_B, H2, H1, H1, DO_MACC) +RVVCALL(OPIVV3, vwmaccu_vv_h, WOP_UUU_H, H4, H2, H2, DO_MACC) +RVVCALL(OPIVV3, vwmaccu_vv_w, WOP_UUU_W, H8, H4, H4, DO_MACC) +RVVCALL(OPIVV3, vwmacc_vv_b, WOP_SSS_B, H2, H1, H1, DO_MACC) +RVVCALL(OPIVV3, vwmacc_vv_h, WOP_SSS_H, H4, H2, H2, DO_MACC) +RVVCALL(OPIVV3, vwmacc_vv_w, WOP_SSS_W, H8, H4, H4, DO_MACC) +RVVCALL(OPIVV3, vwmaccsu_vv_b, WOP_SSU_B, H2, H1, H1, DO_MACC) +RVVCALL(OPIVV3, vwmaccsu_vv_h, WOP_SSU_H, H4, H2, H2, DO_MACC) +RVVCALL(OPIVV3, vwmaccsu_vv_w, WOP_SSU_W, H8, H4, H4, DO_MACC) +GEN_VEXT_VV(vwmaccu_vv_b, 1, 2, clearh) +GEN_VEXT_VV(vwmaccu_vv_h, 2, 4, clearl) +GEN_VEXT_VV(vwmaccu_vv_w, 4, 8, clearq) +GEN_VEXT_VV(vwmacc_vv_b, 1, 2, clearh) +GEN_VEXT_VV(vwmacc_vv_h, 2, 4, clearl) +GEN_VEXT_VV(vwmacc_vv_w, 4, 8, clearq) +GEN_VEXT_VV(vwmaccsu_vv_b, 1, 2, clearh) +GEN_VEXT_VV(vwmaccsu_vv_h, 2, 4, clearl) +GEN_VEXT_VV(vwmaccsu_vv_w, 4, 8, clearq) + +RVVCALL(OPIVX3, vwmaccu_vx_b, WOP_UUU_B, H2, H1, DO_MACC) +RVVCALL(OPIVX3, vwmaccu_vx_h, WOP_UUU_H, H4, H2, DO_MACC) +RVVCALL(OPIVX3, vwmaccu_vx_w, WOP_UUU_W, H8, H4, DO_MACC) +RVVCALL(OPIVX3, vwmacc_vx_b, WOP_SSS_B, H2, H1, DO_MACC) +RVVCALL(OPIVX3, vwmacc_vx_h, WOP_SSS_H, H4, H2, DO_MACC) +RVVCALL(OPIVX3, vwmacc_vx_w, WOP_SSS_W, H8, H4, DO_MACC) +RVVCALL(OPIVX3, vwmaccsu_vx_b, WOP_SSU_B, H2, H1, DO_MACC) +RVVCALL(OPIVX3, vwmaccsu_vx_h, WOP_SSU_H, H4, H2, DO_MACC) +RVVCALL(OPIVX3, vwmaccsu_vx_w, WOP_SSU_W, H8, H4, DO_MACC) +RVVCALL(OPIVX3, vwmaccus_vx_b, WOP_SUS_B, H2, H1, DO_MACC) +RVVCALL(OPIVX3, vwmaccus_vx_h, WOP_SUS_H, H4, H2, DO_MACC) +RVVCALL(OPIVX3, vwmaccus_vx_w, WOP_SUS_W, H8, H4, DO_MACC) +GEN_VEXT_VX(vwmaccu_vx_b, 1, 2, clearh) +GEN_VEXT_VX(vwmaccu_vx_h, 2, 4, clearl) +GEN_VEXT_VX(vwmaccu_vx_w, 4, 8, clearq) +GEN_VEXT_VX(vwmacc_vx_b, 1, 2, clearh) +GEN_VEXT_VX(vwmacc_vx_h, 2, 4, clearl) +GEN_VEXT_VX(vwmacc_vx_w, 4, 8, clearq) +GEN_VEXT_VX(vwmaccsu_vx_b, 1, 2, clearh) +GEN_VEXT_VX(vwmaccsu_vx_h, 2, 4, clearl) +GEN_VEXT_VX(vwmaccsu_vx_w, 4, 8, clearq) +GEN_VEXT_VX(vwmaccus_vx_b, 1, 2, clearh) +GEN_VEXT_VX(vwmaccus_vx_h, 2, 4, clearl) +GEN_VEXT_VX(vwmaccus_vx_w, 4, 8, clearq) + +/* Vector Integer Merge and Move Instructions */ +#define GEN_VEXT_VMV_VV(NAME, ETYPE, H, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *vs1, CPURISCVState *env, \ + uint32_t desc) \ +{ \ + uint32_t vl = env->vl; \ + uint32_t esz = sizeof(ETYPE); \ + uint32_t vlmax = vext_maxsz(desc) / esz; \ + uint32_t i; \ + \ + for (i = 0; i < vl; i++) { \ + ETYPE s1 = *((ETYPE *)vs1 + H(i)); \ + *((ETYPE *)vd + H(i)) = s1; \ + } \ + CLEAR_FN(vd, vl, vl * esz, vlmax * esz); \ +} + +GEN_VEXT_VMV_VV(vmv_v_v_b, int8_t, H1, clearb) +GEN_VEXT_VMV_VV(vmv_v_v_h, int16_t, H2, clearh) +GEN_VEXT_VMV_VV(vmv_v_v_w, int32_t, H4, clearl) +GEN_VEXT_VMV_VV(vmv_v_v_d, int64_t, H8, clearq) + +#define GEN_VEXT_VMV_VX(NAME, ETYPE, H, CLEAR_FN) \ +void HELPER(NAME)(void *vd, uint64_t s1, CPURISCVState *env, \ + uint32_t desc) \ +{ \ + uint32_t vl = env->vl; \ + uint32_t esz = sizeof(ETYPE); \ + uint32_t vlmax = vext_maxsz(desc) / esz; \ + uint32_t i; \ + \ + for (i = 0; i < vl; i++) { \ + *((ETYPE *)vd + H(i)) = (ETYPE)s1; \ + } \ + CLEAR_FN(vd, vl, vl * esz, vlmax * esz); \ +} + +GEN_VEXT_VMV_VX(vmv_v_x_b, int8_t, H1, clearb) +GEN_VEXT_VMV_VX(vmv_v_x_h, int16_t, H2, clearh) +GEN_VEXT_VMV_VX(vmv_v_x_w, int32_t, H4, clearl) +GEN_VEXT_VMV_VX(vmv_v_x_d, int64_t, H8, clearq) + +#define GEN_VEXT_VMERGE_VV(NAME, ETYPE, H, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vl = env->vl; \ + uint32_t esz = sizeof(ETYPE); \ + uint32_t vlmax = vext_maxsz(desc) / esz; \ + uint32_t i; \ + \ + for (i = 0; i < vl; i++) { \ + ETYPE *vt = (!vext_elem_mask(v0, mlen, i) ? vs2 : vs1); \ + *((ETYPE *)vd + H(i)) = *(vt + H(i)); \ + } \ + CLEAR_FN(vd, vl, vl * esz, vlmax * esz); \ +} + +GEN_VEXT_VMERGE_VV(vmerge_vvm_b, int8_t, H1, clearb) +GEN_VEXT_VMERGE_VV(vmerge_vvm_h, int16_t, H2, clearh) +GEN_VEXT_VMERGE_VV(vmerge_vvm_w, int32_t, H4, clearl) +GEN_VEXT_VMERGE_VV(vmerge_vvm_d, int64_t, H8, clearq) + +#define GEN_VEXT_VMERGE_VX(NAME, ETYPE, H, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \ + void *vs2, CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vl = env->vl; \ + uint32_t esz = sizeof(ETYPE); \ + uint32_t vlmax = vext_maxsz(desc) / esz; \ + uint32_t i; \ + \ + for (i = 0; i < vl; i++) { \ + ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ + ETYPE d = (!vext_elem_mask(v0, mlen, i) ? s2 : \ + (ETYPE)(target_long)s1); \ + *((ETYPE *)vd + H(i)) = d; \ + } \ + CLEAR_FN(vd, vl, vl * esz, vlmax * esz); \ +} + +GEN_VEXT_VMERGE_VX(vmerge_vxm_b, int8_t, H1, clearb) +GEN_VEXT_VMERGE_VX(vmerge_vxm_h, int16_t, H2, clearh) +GEN_VEXT_VMERGE_VX(vmerge_vxm_w, int32_t, H4, clearl) +GEN_VEXT_VMERGE_VX(vmerge_vxm_d, int64_t, H8, clearq) + +/* + *** Vector Fixed-Point Arithmetic Instructions + */ + +/* Vector Single-Width Saturating Add and Subtract */ + +/* + * As fixed point instructions probably have round mode and saturation, + * define common macros for fixed point here. + */ +typedef void opivv2_rm_fn(void *vd, void *vs1, void *vs2, int i, + CPURISCVState *env, int vxrm); + +#define OPIVV2_RM(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP) \ +static inline void \ +do_##NAME(void *vd, void *vs1, void *vs2, int i, \ + CPURISCVState *env, int vxrm) \ +{ \ + TX1 s1 = *((T1 *)vs1 + HS1(i)); \ + TX2 s2 = *((T2 *)vs2 + HS2(i)); \ + *((TD *)vd + HD(i)) = OP(env, vxrm, s2, s1); \ +} + +static inline void +vext_vv_rm_1(void *vd, void *v0, void *vs1, void *vs2, + CPURISCVState *env, + uint32_t vl, uint32_t vm, uint32_t mlen, int vxrm, + opivv2_rm_fn *fn) +{ + for (uint32_t i = 0; i < vl; i++) { + if (!vm && !vext_elem_mask(v0, mlen, i)) { + continue; + } + fn(vd, vs1, vs2, i, env, vxrm); + } +} + +static inline void +vext_vv_rm_2(void *vd, void *v0, void *vs1, void *vs2, + CPURISCVState *env, + uint32_t desc, uint32_t esz, uint32_t dsz, + opivv2_rm_fn *fn, clear_fn *clearfn) +{ + uint32_t vlmax = vext_maxsz(desc) / esz; + uint32_t mlen = vext_mlen(desc); + uint32_t vm = vext_vm(desc); + uint32_t vl = env->vl; + + switch (env->vxrm) { + case 0: /* rnu */ + vext_vv_rm_1(vd, v0, vs1, vs2, + env, vl, vm, mlen, 0, fn); + break; + case 1: /* rne */ + vext_vv_rm_1(vd, v0, vs1, vs2, + env, vl, vm, mlen, 1, fn); + break; + case 2: /* rdn */ + vext_vv_rm_1(vd, v0, vs1, vs2, + env, vl, vm, mlen, 2, fn); + break; + default: /* rod */ + vext_vv_rm_1(vd, v0, vs1, vs2, + env, vl, vm, mlen, 3, fn); + break; + } + + clearfn(vd, vl, vl * dsz, vlmax * dsz); +} + +/* generate helpers for fixed point instructions with OPIVV format */ +#define GEN_VEXT_VV_RM(NAME, ESZ, DSZ, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + vext_vv_rm_2(vd, v0, vs1, vs2, env, desc, ESZ, DSZ, \ + do_##NAME, CLEAR_FN); \ +} + +static inline uint8_t saddu8(CPURISCVState *env, int vxrm, uint8_t a, uint8_t b) +{ + uint8_t res = a + b; + if (res < a) { + res = UINT8_MAX; + env->vxsat = 0x1; + } + return res; +} + +static inline uint16_t saddu16(CPURISCVState *env, int vxrm, uint16_t a, + uint16_t b) +{ + uint16_t res = a + b; + if (res < a) { + res = UINT16_MAX; + env->vxsat = 0x1; + } + return res; +} + +static inline uint32_t saddu32(CPURISCVState *env, int vxrm, uint32_t a, + uint32_t b) +{ + uint32_t res = a + b; + if (res < a) { + res = UINT32_MAX; + env->vxsat = 0x1; + } + return res; +} + +static inline uint64_t saddu64(CPURISCVState *env, int vxrm, uint64_t a, + uint64_t b) +{ + uint64_t res = a + b; + if (res < a) { + res = UINT64_MAX; + env->vxsat = 0x1; + } + return res; +} + +RVVCALL(OPIVV2_RM, vsaddu_vv_b, OP_UUU_B, H1, H1, H1, saddu8) +RVVCALL(OPIVV2_RM, vsaddu_vv_h, OP_UUU_H, H2, H2, H2, saddu16) +RVVCALL(OPIVV2_RM, vsaddu_vv_w, OP_UUU_W, H4, H4, H4, saddu32) +RVVCALL(OPIVV2_RM, vsaddu_vv_d, OP_UUU_D, H8, H8, H8, saddu64) +GEN_VEXT_VV_RM(vsaddu_vv_b, 1, 1, clearb) +GEN_VEXT_VV_RM(vsaddu_vv_h, 2, 2, clearh) +GEN_VEXT_VV_RM(vsaddu_vv_w, 4, 4, clearl) +GEN_VEXT_VV_RM(vsaddu_vv_d, 8, 8, clearq) + +typedef void opivx2_rm_fn(void *vd, target_long s1, void *vs2, int i, + CPURISCVState *env, int vxrm); + +#define OPIVX2_RM(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \ +static inline void \ +do_##NAME(void *vd, target_long s1, void *vs2, int i, \ + CPURISCVState *env, int vxrm) \ +{ \ + TX2 s2 = *((T2 *)vs2 + HS2(i)); \ + *((TD *)vd + HD(i)) = OP(env, vxrm, s2, (TX1)(T1)s1); \ +} + +static inline void +vext_vx_rm_1(void *vd, void *v0, target_long s1, void *vs2, + CPURISCVState *env, + uint32_t vl, uint32_t vm, uint32_t mlen, int vxrm, + opivx2_rm_fn *fn) +{ + for (uint32_t i = 0; i < vl; i++) { + if (!vm && !vext_elem_mask(v0, mlen, i)) { + continue; + } + fn(vd, s1, vs2, i, env, vxrm); + } +} + +static inline void +vext_vx_rm_2(void *vd, void *v0, target_long s1, void *vs2, + CPURISCVState *env, + uint32_t desc, uint32_t esz, uint32_t dsz, + opivx2_rm_fn *fn, clear_fn *clearfn) +{ + uint32_t vlmax = vext_maxsz(desc) / esz; + uint32_t mlen = vext_mlen(desc); + uint32_t vm = vext_vm(desc); + uint32_t vl = env->vl; + + switch (env->vxrm) { + case 0: /* rnu */ + vext_vx_rm_1(vd, v0, s1, vs2, + env, vl, vm, mlen, 0, fn); + break; + case 1: /* rne */ + vext_vx_rm_1(vd, v0, s1, vs2, + env, vl, vm, mlen, 1, fn); + break; + case 2: /* rdn */ + vext_vx_rm_1(vd, v0, s1, vs2, + env, vl, vm, mlen, 2, fn); + break; + default: /* rod */ + vext_vx_rm_1(vd, v0, s1, vs2, + env, vl, vm, mlen, 3, fn); + break; + } + + clearfn(vd, vl, vl * dsz, vlmax * dsz); +} + +/* generate helpers for fixed point instructions with OPIVX format */ +#define GEN_VEXT_VX_RM(NAME, ESZ, DSZ, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \ + void *vs2, CPURISCVState *env, uint32_t desc) \ +{ \ + vext_vx_rm_2(vd, v0, s1, vs2, env, desc, ESZ, DSZ, \ + do_##NAME, CLEAR_FN); \ +} + +RVVCALL(OPIVX2_RM, vsaddu_vx_b, OP_UUU_B, H1, H1, saddu8) +RVVCALL(OPIVX2_RM, vsaddu_vx_h, OP_UUU_H, H2, H2, saddu16) +RVVCALL(OPIVX2_RM, vsaddu_vx_w, OP_UUU_W, H4, H4, saddu32) +RVVCALL(OPIVX2_RM, vsaddu_vx_d, OP_UUU_D, H8, H8, saddu64) +GEN_VEXT_VX_RM(vsaddu_vx_b, 1, 1, clearb) +GEN_VEXT_VX_RM(vsaddu_vx_h, 2, 2, clearh) +GEN_VEXT_VX_RM(vsaddu_vx_w, 4, 4, clearl) +GEN_VEXT_VX_RM(vsaddu_vx_d, 8, 8, clearq) + +static inline int8_t sadd8(CPURISCVState *env, int vxrm, int8_t a, int8_t b) +{ + int8_t res = a + b; + if ((res ^ a) & (res ^ b) & INT8_MIN) { + res = a > 0 ? INT8_MAX : INT8_MIN; + env->vxsat = 0x1; + } + return res; +} + +static inline int16_t sadd16(CPURISCVState *env, int vxrm, int16_t a, int16_t b) +{ + int16_t res = a + b; + if ((res ^ a) & (res ^ b) & INT16_MIN) { + res = a > 0 ? INT16_MAX : INT16_MIN; + env->vxsat = 0x1; + } + return res; +} + +static inline int32_t sadd32(CPURISCVState *env, int vxrm, int32_t a, int32_t b) +{ + int32_t res = a + b; + if ((res ^ a) & (res ^ b) & INT32_MIN) { + res = a > 0 ? INT32_MAX : INT32_MIN; + env->vxsat = 0x1; + } + return res; +} + +static inline int64_t sadd64(CPURISCVState *env, int vxrm, int64_t a, int64_t b) +{ + int64_t res = a + b; + if ((res ^ a) & (res ^ b) & INT64_MIN) { + res = a > 0 ? INT64_MAX : INT64_MIN; + env->vxsat = 0x1; + } + return res; +} + +RVVCALL(OPIVV2_RM, vsadd_vv_b, OP_SSS_B, H1, H1, H1, sadd8) +RVVCALL(OPIVV2_RM, vsadd_vv_h, OP_SSS_H, H2, H2, H2, sadd16) +RVVCALL(OPIVV2_RM, vsadd_vv_w, OP_SSS_W, H4, H4, H4, sadd32) +RVVCALL(OPIVV2_RM, vsadd_vv_d, OP_SSS_D, H8, H8, H8, sadd64) +GEN_VEXT_VV_RM(vsadd_vv_b, 1, 1, clearb) +GEN_VEXT_VV_RM(vsadd_vv_h, 2, 2, clearh) +GEN_VEXT_VV_RM(vsadd_vv_w, 4, 4, clearl) +GEN_VEXT_VV_RM(vsadd_vv_d, 8, 8, clearq) + +RVVCALL(OPIVX2_RM, vsadd_vx_b, OP_SSS_B, H1, H1, sadd8) +RVVCALL(OPIVX2_RM, vsadd_vx_h, OP_SSS_H, H2, H2, sadd16) +RVVCALL(OPIVX2_RM, vsadd_vx_w, OP_SSS_W, H4, H4, sadd32) +RVVCALL(OPIVX2_RM, vsadd_vx_d, OP_SSS_D, H8, H8, sadd64) +GEN_VEXT_VX_RM(vsadd_vx_b, 1, 1, clearb) +GEN_VEXT_VX_RM(vsadd_vx_h, 2, 2, clearh) +GEN_VEXT_VX_RM(vsadd_vx_w, 4, 4, clearl) +GEN_VEXT_VX_RM(vsadd_vx_d, 8, 8, clearq) + +static inline uint8_t ssubu8(CPURISCVState *env, int vxrm, uint8_t a, uint8_t b) +{ + uint8_t res = a - b; + if (res > a) { + res = 0; + env->vxsat = 0x1; + } + return res; +} + +static inline uint16_t ssubu16(CPURISCVState *env, int vxrm, uint16_t a, + uint16_t b) +{ + uint16_t res = a - b; + if (res > a) { + res = 0; + env->vxsat = 0x1; + } + return res; +} + +static inline uint32_t ssubu32(CPURISCVState *env, int vxrm, uint32_t a, + uint32_t b) +{ + uint32_t res = a - b; + if (res > a) { + res = 0; + env->vxsat = 0x1; + } + return res; +} + +static inline uint64_t ssubu64(CPURISCVState *env, int vxrm, uint64_t a, + uint64_t b) +{ + uint64_t res = a - b; + if (res > a) { + res = 0; + env->vxsat = 0x1; + } + return res; +} + +RVVCALL(OPIVV2_RM, vssubu_vv_b, OP_UUU_B, H1, H1, H1, ssubu8) +RVVCALL(OPIVV2_RM, vssubu_vv_h, OP_UUU_H, H2, H2, H2, ssubu16) +RVVCALL(OPIVV2_RM, vssubu_vv_w, OP_UUU_W, H4, H4, H4, ssubu32) +RVVCALL(OPIVV2_RM, vssubu_vv_d, OP_UUU_D, H8, H8, H8, ssubu64) +GEN_VEXT_VV_RM(vssubu_vv_b, 1, 1, clearb) +GEN_VEXT_VV_RM(vssubu_vv_h, 2, 2, clearh) +GEN_VEXT_VV_RM(vssubu_vv_w, 4, 4, clearl) +GEN_VEXT_VV_RM(vssubu_vv_d, 8, 8, clearq) + +RVVCALL(OPIVX2_RM, vssubu_vx_b, OP_UUU_B, H1, H1, ssubu8) +RVVCALL(OPIVX2_RM, vssubu_vx_h, OP_UUU_H, H2, H2, ssubu16) +RVVCALL(OPIVX2_RM, vssubu_vx_w, OP_UUU_W, H4, H4, ssubu32) +RVVCALL(OPIVX2_RM, vssubu_vx_d, OP_UUU_D, H8, H8, ssubu64) +GEN_VEXT_VX_RM(vssubu_vx_b, 1, 1, clearb) +GEN_VEXT_VX_RM(vssubu_vx_h, 2, 2, clearh) +GEN_VEXT_VX_RM(vssubu_vx_w, 4, 4, clearl) +GEN_VEXT_VX_RM(vssubu_vx_d, 8, 8, clearq) + +static inline int8_t ssub8(CPURISCVState *env, int vxrm, int8_t a, int8_t b) +{ + int8_t res = a - b; + if ((res ^ a) & (a ^ b) & INT8_MIN) { + res = a >= 0 ? INT8_MAX : INT8_MIN; + env->vxsat = 0x1; + } + return res; +} + +static inline int16_t ssub16(CPURISCVState *env, int vxrm, int16_t a, int16_t b) +{ + int16_t res = a - b; + if ((res ^ a) & (a ^ b) & INT16_MIN) { + res = a >= 0 ? INT16_MAX : INT16_MIN; + env->vxsat = 0x1; + } + return res; +} + +static inline int32_t ssub32(CPURISCVState *env, int vxrm, int32_t a, int32_t b) +{ + int32_t res = a - b; + if ((res ^ a) & (a ^ b) & INT32_MIN) { + res = a >= 0 ? INT32_MAX : INT32_MIN; + env->vxsat = 0x1; + } + return res; +} + +static inline int64_t ssub64(CPURISCVState *env, int vxrm, int64_t a, int64_t b) +{ + int64_t res = a - b; + if ((res ^ a) & (a ^ b) & INT64_MIN) { + res = a >= 0 ? INT64_MAX : INT64_MIN; + env->vxsat = 0x1; + } + return res; +} + +RVVCALL(OPIVV2_RM, vssub_vv_b, OP_SSS_B, H1, H1, H1, ssub8) +RVVCALL(OPIVV2_RM, vssub_vv_h, OP_SSS_H, H2, H2, H2, ssub16) +RVVCALL(OPIVV2_RM, vssub_vv_w, OP_SSS_W, H4, H4, H4, ssub32) +RVVCALL(OPIVV2_RM, vssub_vv_d, OP_SSS_D, H8, H8, H8, ssub64) +GEN_VEXT_VV_RM(vssub_vv_b, 1, 1, clearb) +GEN_VEXT_VV_RM(vssub_vv_h, 2, 2, clearh) +GEN_VEXT_VV_RM(vssub_vv_w, 4, 4, clearl) +GEN_VEXT_VV_RM(vssub_vv_d, 8, 8, clearq) + +RVVCALL(OPIVX2_RM, vssub_vx_b, OP_SSS_B, H1, H1, ssub8) +RVVCALL(OPIVX2_RM, vssub_vx_h, OP_SSS_H, H2, H2, ssub16) +RVVCALL(OPIVX2_RM, vssub_vx_w, OP_SSS_W, H4, H4, ssub32) +RVVCALL(OPIVX2_RM, vssub_vx_d, OP_SSS_D, H8, H8, ssub64) +GEN_VEXT_VX_RM(vssub_vx_b, 1, 1, clearb) +GEN_VEXT_VX_RM(vssub_vx_h, 2, 2, clearh) +GEN_VEXT_VX_RM(vssub_vx_w, 4, 4, clearl) +GEN_VEXT_VX_RM(vssub_vx_d, 8, 8, clearq) + +/* Vector Single-Width Averaging Add and Subtract */ +static inline uint8_t get_round(int vxrm, uint64_t v, uint8_t shift) +{ + uint8_t d = extract64(v, shift, 1); + uint8_t d1; + uint64_t D1, D2; + + if (shift == 0 || shift > 64) { + return 0; + } + + d1 = extract64(v, shift - 1, 1); + D1 = extract64(v, 0, shift); + if (vxrm == 0) { /* round-to-nearest-up (add +0.5 LSB) */ + return d1; + } else if (vxrm == 1) { /* round-to-nearest-even */ + if (shift > 1) { + D2 = extract64(v, 0, shift - 1); + return d1 & ((D2 != 0) | d); + } else { + return d1 & d; + } + } else if (vxrm == 3) { /* round-to-odd (OR bits into LSB, aka "jam") */ + return !d & (D1 != 0); + } + return 0; /* round-down (truncate) */ +} + +static inline int32_t aadd32(CPURISCVState *env, int vxrm, int32_t a, int32_t b) +{ + int64_t res = (int64_t)a + b; + uint8_t round = get_round(vxrm, res, 1); + + return (res >> 1) + round; +} + +static inline int64_t aadd64(CPURISCVState *env, int vxrm, int64_t a, int64_t b) +{ + int64_t res = a + b; + uint8_t round = get_round(vxrm, res, 1); + int64_t over = (res ^ a) & (res ^ b) & INT64_MIN; + + /* With signed overflow, bit 64 is inverse of bit 63. */ + return ((res >> 1) ^ over) + round; +} + +RVVCALL(OPIVV2_RM, vaadd_vv_b, OP_SSS_B, H1, H1, H1, aadd32) +RVVCALL(OPIVV2_RM, vaadd_vv_h, OP_SSS_H, H2, H2, H2, aadd32) +RVVCALL(OPIVV2_RM, vaadd_vv_w, OP_SSS_W, H4, H4, H4, aadd32) +RVVCALL(OPIVV2_RM, vaadd_vv_d, OP_SSS_D, H8, H8, H8, aadd64) +GEN_VEXT_VV_RM(vaadd_vv_b, 1, 1, clearb) +GEN_VEXT_VV_RM(vaadd_vv_h, 2, 2, clearh) +GEN_VEXT_VV_RM(vaadd_vv_w, 4, 4, clearl) +GEN_VEXT_VV_RM(vaadd_vv_d, 8, 8, clearq) + +RVVCALL(OPIVX2_RM, vaadd_vx_b, OP_SSS_B, H1, H1, aadd32) +RVVCALL(OPIVX2_RM, vaadd_vx_h, OP_SSS_H, H2, H2, aadd32) +RVVCALL(OPIVX2_RM, vaadd_vx_w, OP_SSS_W, H4, H4, aadd32) +RVVCALL(OPIVX2_RM, vaadd_vx_d, OP_SSS_D, H8, H8, aadd64) +GEN_VEXT_VX_RM(vaadd_vx_b, 1, 1, clearb) +GEN_VEXT_VX_RM(vaadd_vx_h, 2, 2, clearh) +GEN_VEXT_VX_RM(vaadd_vx_w, 4, 4, clearl) +GEN_VEXT_VX_RM(vaadd_vx_d, 8, 8, clearq) + +static inline int32_t asub32(CPURISCVState *env, int vxrm, int32_t a, int32_t b) +{ + int64_t res = (int64_t)a - b; + uint8_t round = get_round(vxrm, res, 1); + + return (res >> 1) + round; +} + +static inline int64_t asub64(CPURISCVState *env, int vxrm, int64_t a, int64_t b) +{ + int64_t res = (int64_t)a - b; + uint8_t round = get_round(vxrm, res, 1); + int64_t over = (res ^ a) & (a ^ b) & INT64_MIN; + + /* With signed overflow, bit 64 is inverse of bit 63. */ + return ((res >> 1) ^ over) + round; +} + +RVVCALL(OPIVV2_RM, vasub_vv_b, OP_SSS_B, H1, H1, H1, asub32) +RVVCALL(OPIVV2_RM, vasub_vv_h, OP_SSS_H, H2, H2, H2, asub32) +RVVCALL(OPIVV2_RM, vasub_vv_w, OP_SSS_W, H4, H4, H4, asub32) +RVVCALL(OPIVV2_RM, vasub_vv_d, OP_SSS_D, H8, H8, H8, asub64) +GEN_VEXT_VV_RM(vasub_vv_b, 1, 1, clearb) +GEN_VEXT_VV_RM(vasub_vv_h, 2, 2, clearh) +GEN_VEXT_VV_RM(vasub_vv_w, 4, 4, clearl) +GEN_VEXT_VV_RM(vasub_vv_d, 8, 8, clearq) + +RVVCALL(OPIVX2_RM, vasub_vx_b, OP_SSS_B, H1, H1, asub32) +RVVCALL(OPIVX2_RM, vasub_vx_h, OP_SSS_H, H2, H2, asub32) +RVVCALL(OPIVX2_RM, vasub_vx_w, OP_SSS_W, H4, H4, asub32) +RVVCALL(OPIVX2_RM, vasub_vx_d, OP_SSS_D, H8, H8, asub64) +GEN_VEXT_VX_RM(vasub_vx_b, 1, 1, clearb) +GEN_VEXT_VX_RM(vasub_vx_h, 2, 2, clearh) +GEN_VEXT_VX_RM(vasub_vx_w, 4, 4, clearl) +GEN_VEXT_VX_RM(vasub_vx_d, 8, 8, clearq) + +/* Vector Single-Width Fractional Multiply with Rounding and Saturation */ +static inline int8_t vsmul8(CPURISCVState *env, int vxrm, int8_t a, int8_t b) +{ + uint8_t round; + int16_t res; + + res = (int16_t)a * (int16_t)b; + round = get_round(vxrm, res, 7); + res = (res >> 7) + round; + + if (res > INT8_MAX) { + env->vxsat = 0x1; + return INT8_MAX; + } else if (res < INT8_MIN) { + env->vxsat = 0x1; + return INT8_MIN; + } else { + return res; + } +} + +static int16_t vsmul16(CPURISCVState *env, int vxrm, int16_t a, int16_t b) +{ + uint8_t round; + int32_t res; + + res = (int32_t)a * (int32_t)b; + round = get_round(vxrm, res, 15); + res = (res >> 15) + round; + + if (res > INT16_MAX) { + env->vxsat = 0x1; + return INT16_MAX; + } else if (res < INT16_MIN) { + env->vxsat = 0x1; + return INT16_MIN; + } else { + return res; + } +} + +static int32_t vsmul32(CPURISCVState *env, int vxrm, int32_t a, int32_t b) +{ + uint8_t round; + int64_t res; + + res = (int64_t)a * (int64_t)b; + round = get_round(vxrm, res, 31); + res = (res >> 31) + round; + + if (res > INT32_MAX) { + env->vxsat = 0x1; + return INT32_MAX; + } else if (res < INT32_MIN) { + env->vxsat = 0x1; + return INT32_MIN; + } else { + return res; + } +} + +static int64_t vsmul64(CPURISCVState *env, int vxrm, int64_t a, int64_t b) +{ + uint8_t round; + uint64_t hi_64, lo_64; + int64_t res; + + if (a == INT64_MIN && b == INT64_MIN) { + env->vxsat = 1; + return INT64_MAX; + } + + muls64(&lo_64, &hi_64, a, b); + round = get_round(vxrm, lo_64, 63); + /* + * Cannot overflow, as there are always + * 2 sign bits after multiply. + */ + res = (hi_64 << 1) | (lo_64 >> 63); + if (round) { + if (res == INT64_MAX) { + env->vxsat = 1; + } else { + res += 1; + } + } + return res; +} + +RVVCALL(OPIVV2_RM, vsmul_vv_b, OP_SSS_B, H1, H1, H1, vsmul8) +RVVCALL(OPIVV2_RM, vsmul_vv_h, OP_SSS_H, H2, H2, H2, vsmul16) +RVVCALL(OPIVV2_RM, vsmul_vv_w, OP_SSS_W, H4, H4, H4, vsmul32) +RVVCALL(OPIVV2_RM, vsmul_vv_d, OP_SSS_D, H8, H8, H8, vsmul64) +GEN_VEXT_VV_RM(vsmul_vv_b, 1, 1, clearb) +GEN_VEXT_VV_RM(vsmul_vv_h, 2, 2, clearh) +GEN_VEXT_VV_RM(vsmul_vv_w, 4, 4, clearl) +GEN_VEXT_VV_RM(vsmul_vv_d, 8, 8, clearq) + +RVVCALL(OPIVX2_RM, vsmul_vx_b, OP_SSS_B, H1, H1, vsmul8) +RVVCALL(OPIVX2_RM, vsmul_vx_h, OP_SSS_H, H2, H2, vsmul16) +RVVCALL(OPIVX2_RM, vsmul_vx_w, OP_SSS_W, H4, H4, vsmul32) +RVVCALL(OPIVX2_RM, vsmul_vx_d, OP_SSS_D, H8, H8, vsmul64) +GEN_VEXT_VX_RM(vsmul_vx_b, 1, 1, clearb) +GEN_VEXT_VX_RM(vsmul_vx_h, 2, 2, clearh) +GEN_VEXT_VX_RM(vsmul_vx_w, 4, 4, clearl) +GEN_VEXT_VX_RM(vsmul_vx_d, 8, 8, clearq) + +/* Vector Widening Saturating Scaled Multiply-Add */ +static inline uint16_t +vwsmaccu8(CPURISCVState *env, int vxrm, uint8_t a, uint8_t b, + uint16_t c) +{ + uint8_t round; + uint16_t res = (uint16_t)a * b; + + round = get_round(vxrm, res, 4); + res = (res >> 4) + round; + return saddu16(env, vxrm, c, res); +} + +static inline uint32_t +vwsmaccu16(CPURISCVState *env, int vxrm, uint16_t a, uint16_t b, + uint32_t c) +{ + uint8_t round; + uint32_t res = (uint32_t)a * b; + + round = get_round(vxrm, res, 8); + res = (res >> 8) + round; + return saddu32(env, vxrm, c, res); +} + +static inline uint64_t +vwsmaccu32(CPURISCVState *env, int vxrm, uint32_t a, uint32_t b, + uint64_t c) +{ + uint8_t round; + uint64_t res = (uint64_t)a * b; + + round = get_round(vxrm, res, 16); + res = (res >> 16) + round; + return saddu64(env, vxrm, c, res); +} + +#define OPIVV3_RM(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP) \ +static inline void \ +do_##NAME(void *vd, void *vs1, void *vs2, int i, \ + CPURISCVState *env, int vxrm) \ +{ \ + TX1 s1 = *((T1 *)vs1 + HS1(i)); \ + TX2 s2 = *((T2 *)vs2 + HS2(i)); \ + TD d = *((TD *)vd + HD(i)); \ + *((TD *)vd + HD(i)) = OP(env, vxrm, s2, s1, d); \ +} + +RVVCALL(OPIVV3_RM, vwsmaccu_vv_b, WOP_UUU_B, H2, H1, H1, vwsmaccu8) +RVVCALL(OPIVV3_RM, vwsmaccu_vv_h, WOP_UUU_H, H4, H2, H2, vwsmaccu16) +RVVCALL(OPIVV3_RM, vwsmaccu_vv_w, WOP_UUU_W, H8, H4, H4, vwsmaccu32) +GEN_VEXT_VV_RM(vwsmaccu_vv_b, 1, 2, clearh) +GEN_VEXT_VV_RM(vwsmaccu_vv_h, 2, 4, clearl) +GEN_VEXT_VV_RM(vwsmaccu_vv_w, 4, 8, clearq) + +#define OPIVX3_RM(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \ +static inline void \ +do_##NAME(void *vd, target_long s1, void *vs2, int i, \ + CPURISCVState *env, int vxrm) \ +{ \ + TX2 s2 = *((T2 *)vs2 + HS2(i)); \ + TD d = *((TD *)vd + HD(i)); \ + *((TD *)vd + HD(i)) = OP(env, vxrm, s2, (TX1)(T1)s1, d); \ +} + +RVVCALL(OPIVX3_RM, vwsmaccu_vx_b, WOP_UUU_B, H2, H1, vwsmaccu8) +RVVCALL(OPIVX3_RM, vwsmaccu_vx_h, WOP_UUU_H, H4, H2, vwsmaccu16) +RVVCALL(OPIVX3_RM, vwsmaccu_vx_w, WOP_UUU_W, H8, H4, vwsmaccu32) +GEN_VEXT_VX_RM(vwsmaccu_vx_b, 1, 2, clearh) +GEN_VEXT_VX_RM(vwsmaccu_vx_h, 2, 4, clearl) +GEN_VEXT_VX_RM(vwsmaccu_vx_w, 4, 8, clearq) + +static inline int16_t +vwsmacc8(CPURISCVState *env, int vxrm, int8_t a, int8_t b, int16_t c) +{ + uint8_t round; + int16_t res = (int16_t)a * b; + + round = get_round(vxrm, res, 4); + res = (res >> 4) + round; + return sadd16(env, vxrm, c, res); +} + +static inline int32_t +vwsmacc16(CPURISCVState *env, int vxrm, int16_t a, int16_t b, int32_t c) +{ + uint8_t round; + int32_t res = (int32_t)a * b; + + round = get_round(vxrm, res, 8); + res = (res >> 8) + round; + return sadd32(env, vxrm, c, res); + +} + +static inline int64_t +vwsmacc32(CPURISCVState *env, int vxrm, int32_t a, int32_t b, int64_t c) +{ + uint8_t round; + int64_t res = (int64_t)a * b; + + round = get_round(vxrm, res, 16); + res = (res >> 16) + round; + return sadd64(env, vxrm, c, res); +} + +RVVCALL(OPIVV3_RM, vwsmacc_vv_b, WOP_SSS_B, H2, H1, H1, vwsmacc8) +RVVCALL(OPIVV3_RM, vwsmacc_vv_h, WOP_SSS_H, H4, H2, H2, vwsmacc16) +RVVCALL(OPIVV3_RM, vwsmacc_vv_w, WOP_SSS_W, H8, H4, H4, vwsmacc32) +GEN_VEXT_VV_RM(vwsmacc_vv_b, 1, 2, clearh) +GEN_VEXT_VV_RM(vwsmacc_vv_h, 2, 4, clearl) +GEN_VEXT_VV_RM(vwsmacc_vv_w, 4, 8, clearq) +RVVCALL(OPIVX3_RM, vwsmacc_vx_b, WOP_SSS_B, H2, H1, vwsmacc8) +RVVCALL(OPIVX3_RM, vwsmacc_vx_h, WOP_SSS_H, H4, H2, vwsmacc16) +RVVCALL(OPIVX3_RM, vwsmacc_vx_w, WOP_SSS_W, H8, H4, vwsmacc32) +GEN_VEXT_VX_RM(vwsmacc_vx_b, 1, 2, clearh) +GEN_VEXT_VX_RM(vwsmacc_vx_h, 2, 4, clearl) +GEN_VEXT_VX_RM(vwsmacc_vx_w, 4, 8, clearq) + +static inline int16_t +vwsmaccsu8(CPURISCVState *env, int vxrm, uint8_t a, int8_t b, int16_t c) +{ + uint8_t round; + int16_t res = a * (int16_t)b; + + round = get_round(vxrm, res, 4); + res = (res >> 4) + round; + return ssub16(env, vxrm, c, res); +} + +static inline int32_t +vwsmaccsu16(CPURISCVState *env, int vxrm, uint16_t a, int16_t b, uint32_t c) +{ + uint8_t round; + int32_t res = a * (int32_t)b; + + round = get_round(vxrm, res, 8); + res = (res >> 8) + round; + return ssub32(env, vxrm, c, res); +} + +static inline int64_t +vwsmaccsu32(CPURISCVState *env, int vxrm, uint32_t a, int32_t b, int64_t c) +{ + uint8_t round; + int64_t res = a * (int64_t)b; + + round = get_round(vxrm, res, 16); + res = (res >> 16) + round; + return ssub64(env, vxrm, c, res); +} + +RVVCALL(OPIVV3_RM, vwsmaccsu_vv_b, WOP_SSU_B, H2, H1, H1, vwsmaccsu8) +RVVCALL(OPIVV3_RM, vwsmaccsu_vv_h, WOP_SSU_H, H4, H2, H2, vwsmaccsu16) +RVVCALL(OPIVV3_RM, vwsmaccsu_vv_w, WOP_SSU_W, H8, H4, H4, vwsmaccsu32) +GEN_VEXT_VV_RM(vwsmaccsu_vv_b, 1, 2, clearh) +GEN_VEXT_VV_RM(vwsmaccsu_vv_h, 2, 4, clearl) +GEN_VEXT_VV_RM(vwsmaccsu_vv_w, 4, 8, clearq) +RVVCALL(OPIVX3_RM, vwsmaccsu_vx_b, WOP_SSU_B, H2, H1, vwsmaccsu8) +RVVCALL(OPIVX3_RM, vwsmaccsu_vx_h, WOP_SSU_H, H4, H2, vwsmaccsu16) +RVVCALL(OPIVX3_RM, vwsmaccsu_vx_w, WOP_SSU_W, H8, H4, vwsmaccsu32) +GEN_VEXT_VX_RM(vwsmaccsu_vx_b, 1, 2, clearh) +GEN_VEXT_VX_RM(vwsmaccsu_vx_h, 2, 4, clearl) +GEN_VEXT_VX_RM(vwsmaccsu_vx_w, 4, 8, clearq) + +static inline int16_t +vwsmaccus8(CPURISCVState *env, int vxrm, int8_t a, uint8_t b, int16_t c) +{ + uint8_t round; + int16_t res = (int16_t)a * b; + + round = get_round(vxrm, res, 4); + res = (res >> 4) + round; + return ssub16(env, vxrm, c, res); +} + +static inline int32_t +vwsmaccus16(CPURISCVState *env, int vxrm, int16_t a, uint16_t b, int32_t c) +{ + uint8_t round; + int32_t res = (int32_t)a * b; + + round = get_round(vxrm, res, 8); + res = (res >> 8) + round; + return ssub32(env, vxrm, c, res); +} + +static inline int64_t +vwsmaccus32(CPURISCVState *env, int vxrm, int32_t a, uint32_t b, int64_t c) +{ + uint8_t round; + int64_t res = (int64_t)a * b; + + round = get_round(vxrm, res, 16); + res = (res >> 16) + round; + return ssub64(env, vxrm, c, res); +} + +RVVCALL(OPIVX3_RM, vwsmaccus_vx_b, WOP_SUS_B, H2, H1, vwsmaccus8) +RVVCALL(OPIVX3_RM, vwsmaccus_vx_h, WOP_SUS_H, H4, H2, vwsmaccus16) +RVVCALL(OPIVX3_RM, vwsmaccus_vx_w, WOP_SUS_W, H8, H4, vwsmaccus32) +GEN_VEXT_VX_RM(vwsmaccus_vx_b, 1, 2, clearh) +GEN_VEXT_VX_RM(vwsmaccus_vx_h, 2, 4, clearl) +GEN_VEXT_VX_RM(vwsmaccus_vx_w, 4, 8, clearq) + +/* Vector Single-Width Scaling Shift Instructions */ +static inline uint8_t +vssrl8(CPURISCVState *env, int vxrm, uint8_t a, uint8_t b) +{ + uint8_t round, shift = b & 0x7; + uint8_t res; + + round = get_round(vxrm, a, shift); + res = (a >> shift) + round; + return res; +} +static inline uint16_t +vssrl16(CPURISCVState *env, int vxrm, uint16_t a, uint16_t b) +{ + uint8_t round, shift = b & 0xf; + uint16_t res; + + round = get_round(vxrm, a, shift); + res = (a >> shift) + round; + return res; +} +static inline uint32_t +vssrl32(CPURISCVState *env, int vxrm, uint32_t a, uint32_t b) +{ + uint8_t round, shift = b & 0x1f; + uint32_t res; + + round = get_round(vxrm, a, shift); + res = (a >> shift) + round; + return res; +} +static inline uint64_t +vssrl64(CPURISCVState *env, int vxrm, uint64_t a, uint64_t b) +{ + uint8_t round, shift = b & 0x3f; + uint64_t res; + + round = get_round(vxrm, a, shift); + res = (a >> shift) + round; + return res; +} +RVVCALL(OPIVV2_RM, vssrl_vv_b, OP_UUU_B, H1, H1, H1, vssrl8) +RVVCALL(OPIVV2_RM, vssrl_vv_h, OP_UUU_H, H2, H2, H2, vssrl16) +RVVCALL(OPIVV2_RM, vssrl_vv_w, OP_UUU_W, H4, H4, H4, vssrl32) +RVVCALL(OPIVV2_RM, vssrl_vv_d, OP_UUU_D, H8, H8, H8, vssrl64) +GEN_VEXT_VV_RM(vssrl_vv_b, 1, 1, clearb) +GEN_VEXT_VV_RM(vssrl_vv_h, 2, 2, clearh) +GEN_VEXT_VV_RM(vssrl_vv_w, 4, 4, clearl) +GEN_VEXT_VV_RM(vssrl_vv_d, 8, 8, clearq) + +RVVCALL(OPIVX2_RM, vssrl_vx_b, OP_UUU_B, H1, H1, vssrl8) +RVVCALL(OPIVX2_RM, vssrl_vx_h, OP_UUU_H, H2, H2, vssrl16) +RVVCALL(OPIVX2_RM, vssrl_vx_w, OP_UUU_W, H4, H4, vssrl32) +RVVCALL(OPIVX2_RM, vssrl_vx_d, OP_UUU_D, H8, H8, vssrl64) +GEN_VEXT_VX_RM(vssrl_vx_b, 1, 1, clearb) +GEN_VEXT_VX_RM(vssrl_vx_h, 2, 2, clearh) +GEN_VEXT_VX_RM(vssrl_vx_w, 4, 4, clearl) +GEN_VEXT_VX_RM(vssrl_vx_d, 8, 8, clearq) + +static inline int8_t +vssra8(CPURISCVState *env, int vxrm, int8_t a, int8_t b) +{ + uint8_t round, shift = b & 0x7; + int8_t res; + + round = get_round(vxrm, a, shift); + res = (a >> shift) + round; + return res; +} +static inline int16_t +vssra16(CPURISCVState *env, int vxrm, int16_t a, int16_t b) +{ + uint8_t round, shift = b & 0xf; + int16_t res; + + round = get_round(vxrm, a, shift); + res = (a >> shift) + round; + return res; +} +static inline int32_t +vssra32(CPURISCVState *env, int vxrm, int32_t a, int32_t b) +{ + uint8_t round, shift = b & 0x1f; + int32_t res; + + round = get_round(vxrm, a, shift); + res = (a >> shift) + round; + return res; +} +static inline int64_t +vssra64(CPURISCVState *env, int vxrm, int64_t a, int64_t b) +{ + uint8_t round, shift = b & 0x3f; + int64_t res; + + round = get_round(vxrm, a, shift); + res = (a >> shift) + round; + return res; +} + +RVVCALL(OPIVV2_RM, vssra_vv_b, OP_SSS_B, H1, H1, H1, vssra8) +RVVCALL(OPIVV2_RM, vssra_vv_h, OP_SSS_H, H2, H2, H2, vssra16) +RVVCALL(OPIVV2_RM, vssra_vv_w, OP_SSS_W, H4, H4, H4, vssra32) +RVVCALL(OPIVV2_RM, vssra_vv_d, OP_SSS_D, H8, H8, H8, vssra64) +GEN_VEXT_VV_RM(vssra_vv_b, 1, 1, clearb) +GEN_VEXT_VV_RM(vssra_vv_h, 2, 2, clearh) +GEN_VEXT_VV_RM(vssra_vv_w, 4, 4, clearl) +GEN_VEXT_VV_RM(vssra_vv_d, 8, 8, clearq) + +RVVCALL(OPIVX2_RM, vssra_vx_b, OP_SSS_B, H1, H1, vssra8) +RVVCALL(OPIVX2_RM, vssra_vx_h, OP_SSS_H, H2, H2, vssra16) +RVVCALL(OPIVX2_RM, vssra_vx_w, OP_SSS_W, H4, H4, vssra32) +RVVCALL(OPIVX2_RM, vssra_vx_d, OP_SSS_D, H8, H8, vssra64) +GEN_VEXT_VX_RM(vssra_vx_b, 1, 1, clearb) +GEN_VEXT_VX_RM(vssra_vx_h, 2, 2, clearh) +GEN_VEXT_VX_RM(vssra_vx_w, 4, 4, clearl) +GEN_VEXT_VX_RM(vssra_vx_d, 8, 8, clearq) + +/* Vector Narrowing Fixed-Point Clip Instructions */ +static inline int8_t +vnclip8(CPURISCVState *env, int vxrm, int16_t a, int8_t b) +{ + uint8_t round, shift = b & 0xf; + int16_t res; + + round = get_round(vxrm, a, shift); + res = (a >> shift) + round; + if (res > INT8_MAX) { + env->vxsat = 0x1; + return INT8_MAX; + } else if (res < INT8_MIN) { + env->vxsat = 0x1; + return INT8_MIN; + } else { + return res; + } +} + +static inline int16_t +vnclip16(CPURISCVState *env, int vxrm, int32_t a, int16_t b) +{ + uint8_t round, shift = b & 0x1f; + int32_t res; + + round = get_round(vxrm, a, shift); + res = (a >> shift) + round; + if (res > INT16_MAX) { + env->vxsat = 0x1; + return INT16_MAX; + } else if (res < INT16_MIN) { + env->vxsat = 0x1; + return INT16_MIN; + } else { + return res; + } +} + +static inline int32_t +vnclip32(CPURISCVState *env, int vxrm, int64_t a, int32_t b) +{ + uint8_t round, shift = b & 0x3f; + int64_t res; + + round = get_round(vxrm, a, shift); + res = (a >> shift) + round; + if (res > INT32_MAX) { + env->vxsat = 0x1; + return INT32_MAX; + } else if (res < INT32_MIN) { + env->vxsat = 0x1; + return INT32_MIN; + } else { + return res; + } +} + +RVVCALL(OPIVV2_RM, vnclip_vv_b, NOP_SSS_B, H1, H2, H1, vnclip8) +RVVCALL(OPIVV2_RM, vnclip_vv_h, NOP_SSS_H, H2, H4, H2, vnclip16) +RVVCALL(OPIVV2_RM, vnclip_vv_w, NOP_SSS_W, H4, H8, H4, vnclip32) +GEN_VEXT_VV_RM(vnclip_vv_b, 1, 1, clearb) +GEN_VEXT_VV_RM(vnclip_vv_h, 2, 2, clearh) +GEN_VEXT_VV_RM(vnclip_vv_w, 4, 4, clearl) + +RVVCALL(OPIVX2_RM, vnclip_vx_b, NOP_SSS_B, H1, H2, vnclip8) +RVVCALL(OPIVX2_RM, vnclip_vx_h, NOP_SSS_H, H2, H4, vnclip16) +RVVCALL(OPIVX2_RM, vnclip_vx_w, NOP_SSS_W, H4, H8, vnclip32) +GEN_VEXT_VX_RM(vnclip_vx_b, 1, 1, clearb) +GEN_VEXT_VX_RM(vnclip_vx_h, 2, 2, clearh) +GEN_VEXT_VX_RM(vnclip_vx_w, 4, 4, clearl) + +static inline uint8_t +vnclipu8(CPURISCVState *env, int vxrm, uint16_t a, uint8_t b) +{ + uint8_t round, shift = b & 0xf; + uint16_t res; + + round = get_round(vxrm, a, shift); + res = (a >> shift) + round; + if (res > UINT8_MAX) { + env->vxsat = 0x1; + return UINT8_MAX; + } else { + return res; + } +} + +static inline uint16_t +vnclipu16(CPURISCVState *env, int vxrm, uint32_t a, uint16_t b) +{ + uint8_t round, shift = b & 0x1f; + uint32_t res; + + round = get_round(vxrm, a, shift); + res = (a >> shift) + round; + if (res > UINT16_MAX) { + env->vxsat = 0x1; + return UINT16_MAX; + } else { + return res; + } +} + +static inline uint32_t +vnclipu32(CPURISCVState *env, int vxrm, uint64_t a, uint32_t b) +{ + uint8_t round, shift = b & 0x3f; + int64_t res; + + round = get_round(vxrm, a, shift); + res = (a >> shift) + round; + if (res > UINT32_MAX) { + env->vxsat = 0x1; + return UINT32_MAX; + } else { + return res; + } +} + +RVVCALL(OPIVV2_RM, vnclipu_vv_b, NOP_UUU_B, H1, H2, H1, vnclipu8) +RVVCALL(OPIVV2_RM, vnclipu_vv_h, NOP_UUU_H, H2, H4, H2, vnclipu16) +RVVCALL(OPIVV2_RM, vnclipu_vv_w, NOP_UUU_W, H4, H8, H4, vnclipu32) +GEN_VEXT_VV_RM(vnclipu_vv_b, 1, 1, clearb) +GEN_VEXT_VV_RM(vnclipu_vv_h, 2, 2, clearh) +GEN_VEXT_VV_RM(vnclipu_vv_w, 4, 4, clearl) + +RVVCALL(OPIVX2_RM, vnclipu_vx_b, NOP_UUU_B, H1, H2, vnclipu8) +RVVCALL(OPIVX2_RM, vnclipu_vx_h, NOP_UUU_H, H2, H4, vnclipu16) +RVVCALL(OPIVX2_RM, vnclipu_vx_w, NOP_UUU_W, H4, H8, vnclipu32) +GEN_VEXT_VX_RM(vnclipu_vx_b, 1, 1, clearb) +GEN_VEXT_VX_RM(vnclipu_vx_h, 2, 2, clearh) +GEN_VEXT_VX_RM(vnclipu_vx_w, 4, 4, clearl) + +/* + *** Vector Float Point Arithmetic Instructions + */ +/* Vector Single-Width Floating-Point Add/Subtract Instructions */ +#define OPFVV2(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP) \ +static void do_##NAME(void *vd, void *vs1, void *vs2, int i, \ + CPURISCVState *env) \ +{ \ + TX1 s1 = *((T1 *)vs1 + HS1(i)); \ + TX2 s2 = *((T2 *)vs2 + HS2(i)); \ + *((TD *)vd + HD(i)) = OP(s2, s1, &env->fp_status); \ +} + +#define GEN_VEXT_VV_ENV(NAME, ESZ, DSZ, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, void *vs1, \ + void *vs2, CPURISCVState *env, \ + uint32_t desc) \ +{ \ + uint32_t vlmax = vext_maxsz(desc) / ESZ; \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vm = vext_vm(desc); \ + uint32_t vl = env->vl; \ + uint32_t i; \ + \ + for (i = 0; i < vl; i++) { \ + if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + continue; \ + } \ + do_##NAME(vd, vs1, vs2, i, env); \ + } \ + CLEAR_FN(vd, vl, vl * DSZ, vlmax * DSZ); \ +} + +RVVCALL(OPFVV2, vfadd_vv_h, OP_UUU_H, H2, H2, H2, float16_add) +RVVCALL(OPFVV2, vfadd_vv_w, OP_UUU_W, H4, H4, H4, float32_add) +RVVCALL(OPFVV2, vfadd_vv_d, OP_UUU_D, H8, H8, H8, float64_add) +GEN_VEXT_VV_ENV(vfadd_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfadd_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfadd_vv_d, 8, 8, clearq) + +#define OPFVF2(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \ +static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \ + CPURISCVState *env) \ +{ \ + TX2 s2 = *((T2 *)vs2 + HS2(i)); \ + *((TD *)vd + HD(i)) = OP(s2, (TX1)(T1)s1, &env->fp_status);\ +} + +#define GEN_VEXT_VF(NAME, ESZ, DSZ, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, uint64_t s1, \ + void *vs2, CPURISCVState *env, \ + uint32_t desc) \ +{ \ + uint32_t vlmax = vext_maxsz(desc) / ESZ; \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vm = vext_vm(desc); \ + uint32_t vl = env->vl; \ + uint32_t i; \ + \ + for (i = 0; i < vl; i++) { \ + if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + continue; \ + } \ + do_##NAME(vd, s1, vs2, i, env); \ + } \ + CLEAR_FN(vd, vl, vl * DSZ, vlmax * DSZ); \ +} + +RVVCALL(OPFVF2, vfadd_vf_h, OP_UUU_H, H2, H2, float16_add) +RVVCALL(OPFVF2, vfadd_vf_w, OP_UUU_W, H4, H4, float32_add) +RVVCALL(OPFVF2, vfadd_vf_d, OP_UUU_D, H8, H8, float64_add) +GEN_VEXT_VF(vfadd_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfadd_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfadd_vf_d, 8, 8, clearq) + +RVVCALL(OPFVV2, vfsub_vv_h, OP_UUU_H, H2, H2, H2, float16_sub) +RVVCALL(OPFVV2, vfsub_vv_w, OP_UUU_W, H4, H4, H4, float32_sub) +RVVCALL(OPFVV2, vfsub_vv_d, OP_UUU_D, H8, H8, H8, float64_sub) +GEN_VEXT_VV_ENV(vfsub_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfsub_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfsub_vv_d, 8, 8, clearq) +RVVCALL(OPFVF2, vfsub_vf_h, OP_UUU_H, H2, H2, float16_sub) +RVVCALL(OPFVF2, vfsub_vf_w, OP_UUU_W, H4, H4, float32_sub) +RVVCALL(OPFVF2, vfsub_vf_d, OP_UUU_D, H8, H8, float64_sub) +GEN_VEXT_VF(vfsub_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfsub_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfsub_vf_d, 8, 8, clearq) + +static uint16_t float16_rsub(uint16_t a, uint16_t b, float_status *s) +{ + return float16_sub(b, a, s); +} + +static uint32_t float32_rsub(uint32_t a, uint32_t b, float_status *s) +{ + return float32_sub(b, a, s); +} + +static uint64_t float64_rsub(uint64_t a, uint64_t b, float_status *s) +{ + return float64_sub(b, a, s); +} + +RVVCALL(OPFVF2, vfrsub_vf_h, OP_UUU_H, H2, H2, float16_rsub) +RVVCALL(OPFVF2, vfrsub_vf_w, OP_UUU_W, H4, H4, float32_rsub) +RVVCALL(OPFVF2, vfrsub_vf_d, OP_UUU_D, H8, H8, float64_rsub) +GEN_VEXT_VF(vfrsub_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfrsub_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfrsub_vf_d, 8, 8, clearq) + +/* Vector Widening Floating-Point Add/Subtract Instructions */ +static uint32_t vfwadd16(uint16_t a, uint16_t b, float_status *s) +{ + return float32_add(float16_to_float32(a, true, s), + float16_to_float32(b, true, s), s); +} + +static uint64_t vfwadd32(uint32_t a, uint32_t b, float_status *s) +{ + return float64_add(float32_to_float64(a, s), + float32_to_float64(b, s), s); + +} + +RVVCALL(OPFVV2, vfwadd_vv_h, WOP_UUU_H, H4, H2, H2, vfwadd16) +RVVCALL(OPFVV2, vfwadd_vv_w, WOP_UUU_W, H8, H4, H4, vfwadd32) +GEN_VEXT_VV_ENV(vfwadd_vv_h, 2, 4, clearl) +GEN_VEXT_VV_ENV(vfwadd_vv_w, 4, 8, clearq) +RVVCALL(OPFVF2, vfwadd_vf_h, WOP_UUU_H, H4, H2, vfwadd16) +RVVCALL(OPFVF2, vfwadd_vf_w, WOP_UUU_W, H8, H4, vfwadd32) +GEN_VEXT_VF(vfwadd_vf_h, 2, 4, clearl) +GEN_VEXT_VF(vfwadd_vf_w, 4, 8, clearq) + +static uint32_t vfwsub16(uint16_t a, uint16_t b, float_status *s) +{ + return float32_sub(float16_to_float32(a, true, s), + float16_to_float32(b, true, s), s); +} + +static uint64_t vfwsub32(uint32_t a, uint32_t b, float_status *s) +{ + return float64_sub(float32_to_float64(a, s), + float32_to_float64(b, s), s); + +} + +RVVCALL(OPFVV2, vfwsub_vv_h, WOP_UUU_H, H4, H2, H2, vfwsub16) +RVVCALL(OPFVV2, vfwsub_vv_w, WOP_UUU_W, H8, H4, H4, vfwsub32) +GEN_VEXT_VV_ENV(vfwsub_vv_h, 2, 4, clearl) +GEN_VEXT_VV_ENV(vfwsub_vv_w, 4, 8, clearq) +RVVCALL(OPFVF2, vfwsub_vf_h, WOP_UUU_H, H4, H2, vfwsub16) +RVVCALL(OPFVF2, vfwsub_vf_w, WOP_UUU_W, H8, H4, vfwsub32) +GEN_VEXT_VF(vfwsub_vf_h, 2, 4, clearl) +GEN_VEXT_VF(vfwsub_vf_w, 4, 8, clearq) + +static uint32_t vfwaddw16(uint32_t a, uint16_t b, float_status *s) +{ + return float32_add(a, float16_to_float32(b, true, s), s); +} + +static uint64_t vfwaddw32(uint64_t a, uint32_t b, float_status *s) +{ + return float64_add(a, float32_to_float64(b, s), s); +} + +RVVCALL(OPFVV2, vfwadd_wv_h, WOP_WUUU_H, H4, H2, H2, vfwaddw16) +RVVCALL(OPFVV2, vfwadd_wv_w, WOP_WUUU_W, H8, H4, H4, vfwaddw32) +GEN_VEXT_VV_ENV(vfwadd_wv_h, 2, 4, clearl) +GEN_VEXT_VV_ENV(vfwadd_wv_w, 4, 8, clearq) +RVVCALL(OPFVF2, vfwadd_wf_h, WOP_WUUU_H, H4, H2, vfwaddw16) +RVVCALL(OPFVF2, vfwadd_wf_w, WOP_WUUU_W, H8, H4, vfwaddw32) +GEN_VEXT_VF(vfwadd_wf_h, 2, 4, clearl) +GEN_VEXT_VF(vfwadd_wf_w, 4, 8, clearq) + +static uint32_t vfwsubw16(uint32_t a, uint16_t b, float_status *s) +{ + return float32_sub(a, float16_to_float32(b, true, s), s); +} + +static uint64_t vfwsubw32(uint64_t a, uint32_t b, float_status *s) +{ + return float64_sub(a, float32_to_float64(b, s), s); +} + +RVVCALL(OPFVV2, vfwsub_wv_h, WOP_WUUU_H, H4, H2, H2, vfwsubw16) +RVVCALL(OPFVV2, vfwsub_wv_w, WOP_WUUU_W, H8, H4, H4, vfwsubw32) +GEN_VEXT_VV_ENV(vfwsub_wv_h, 2, 4, clearl) +GEN_VEXT_VV_ENV(vfwsub_wv_w, 4, 8, clearq) +RVVCALL(OPFVF2, vfwsub_wf_h, WOP_WUUU_H, H4, H2, vfwsubw16) +RVVCALL(OPFVF2, vfwsub_wf_w, WOP_WUUU_W, H8, H4, vfwsubw32) +GEN_VEXT_VF(vfwsub_wf_h, 2, 4, clearl) +GEN_VEXT_VF(vfwsub_wf_w, 4, 8, clearq) + +/* Vector Single-Width Floating-Point Multiply/Divide Instructions */ +RVVCALL(OPFVV2, vfmul_vv_h, OP_UUU_H, H2, H2, H2, float16_mul) +RVVCALL(OPFVV2, vfmul_vv_w, OP_UUU_W, H4, H4, H4, float32_mul) +RVVCALL(OPFVV2, vfmul_vv_d, OP_UUU_D, H8, H8, H8, float64_mul) +GEN_VEXT_VV_ENV(vfmul_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfmul_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfmul_vv_d, 8, 8, clearq) +RVVCALL(OPFVF2, vfmul_vf_h, OP_UUU_H, H2, H2, float16_mul) +RVVCALL(OPFVF2, vfmul_vf_w, OP_UUU_W, H4, H4, float32_mul) +RVVCALL(OPFVF2, vfmul_vf_d, OP_UUU_D, H8, H8, float64_mul) +GEN_VEXT_VF(vfmul_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfmul_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfmul_vf_d, 8, 8, clearq) + +RVVCALL(OPFVV2, vfdiv_vv_h, OP_UUU_H, H2, H2, H2, float16_div) +RVVCALL(OPFVV2, vfdiv_vv_w, OP_UUU_W, H4, H4, H4, float32_div) +RVVCALL(OPFVV2, vfdiv_vv_d, OP_UUU_D, H8, H8, H8, float64_div) +GEN_VEXT_VV_ENV(vfdiv_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfdiv_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfdiv_vv_d, 8, 8, clearq) +RVVCALL(OPFVF2, vfdiv_vf_h, OP_UUU_H, H2, H2, float16_div) +RVVCALL(OPFVF2, vfdiv_vf_w, OP_UUU_W, H4, H4, float32_div) +RVVCALL(OPFVF2, vfdiv_vf_d, OP_UUU_D, H8, H8, float64_div) +GEN_VEXT_VF(vfdiv_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfdiv_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfdiv_vf_d, 8, 8, clearq) + +static uint16_t float16_rdiv(uint16_t a, uint16_t b, float_status *s) +{ + return float16_div(b, a, s); +} + +static uint32_t float32_rdiv(uint32_t a, uint32_t b, float_status *s) +{ + return float32_div(b, a, s); +} + +static uint64_t float64_rdiv(uint64_t a, uint64_t b, float_status *s) +{ + return float64_div(b, a, s); +} + +RVVCALL(OPFVF2, vfrdiv_vf_h, OP_UUU_H, H2, H2, float16_rdiv) +RVVCALL(OPFVF2, vfrdiv_vf_w, OP_UUU_W, H4, H4, float32_rdiv) +RVVCALL(OPFVF2, vfrdiv_vf_d, OP_UUU_D, H8, H8, float64_rdiv) +GEN_VEXT_VF(vfrdiv_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfrdiv_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfrdiv_vf_d, 8, 8, clearq) + +/* Vector Widening Floating-Point Multiply */ +static uint32_t vfwmul16(uint16_t a, uint16_t b, float_status *s) +{ + return float32_mul(float16_to_float32(a, true, s), + float16_to_float32(b, true, s), s); +} + +static uint64_t vfwmul32(uint32_t a, uint32_t b, float_status *s) +{ + return float64_mul(float32_to_float64(a, s), + float32_to_float64(b, s), s); + +} +RVVCALL(OPFVV2, vfwmul_vv_h, WOP_UUU_H, H4, H2, H2, vfwmul16) +RVVCALL(OPFVV2, vfwmul_vv_w, WOP_UUU_W, H8, H4, H4, vfwmul32) +GEN_VEXT_VV_ENV(vfwmul_vv_h, 2, 4, clearl) +GEN_VEXT_VV_ENV(vfwmul_vv_w, 4, 8, clearq) +RVVCALL(OPFVF2, vfwmul_vf_h, WOP_UUU_H, H4, H2, vfwmul16) +RVVCALL(OPFVF2, vfwmul_vf_w, WOP_UUU_W, H8, H4, vfwmul32) +GEN_VEXT_VF(vfwmul_vf_h, 2, 4, clearl) +GEN_VEXT_VF(vfwmul_vf_w, 4, 8, clearq) + +/* Vector Single-Width Floating-Point Fused Multiply-Add Instructions */ +#define OPFVV3(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP) \ +static void do_##NAME(void *vd, void *vs1, void *vs2, int i, \ + CPURISCVState *env) \ +{ \ + TX1 s1 = *((T1 *)vs1 + HS1(i)); \ + TX2 s2 = *((T2 *)vs2 + HS2(i)); \ + TD d = *((TD *)vd + HD(i)); \ + *((TD *)vd + HD(i)) = OP(s2, s1, d, &env->fp_status); \ +} + +static uint16_t fmacc16(uint16_t a, uint16_t b, uint16_t d, float_status *s) +{ + return float16_muladd(a, b, d, 0, s); +} + +static uint32_t fmacc32(uint32_t a, uint32_t b, uint32_t d, float_status *s) +{ + return float32_muladd(a, b, d, 0, s); +} + +static uint64_t fmacc64(uint64_t a, uint64_t b, uint64_t d, float_status *s) +{ + return float64_muladd(a, b, d, 0, s); +} + +RVVCALL(OPFVV3, vfmacc_vv_h, OP_UUU_H, H2, H2, H2, fmacc16) +RVVCALL(OPFVV3, vfmacc_vv_w, OP_UUU_W, H4, H4, H4, fmacc32) +RVVCALL(OPFVV3, vfmacc_vv_d, OP_UUU_D, H8, H8, H8, fmacc64) +GEN_VEXT_VV_ENV(vfmacc_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfmacc_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfmacc_vv_d, 8, 8, clearq) + +#define OPFVF3(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \ +static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \ + CPURISCVState *env) \ +{ \ + TX2 s2 = *((T2 *)vs2 + HS2(i)); \ + TD d = *((TD *)vd + HD(i)); \ + *((TD *)vd + HD(i)) = OP(s2, (TX1)(T1)s1, d, &env->fp_status);\ +} + +RVVCALL(OPFVF3, vfmacc_vf_h, OP_UUU_H, H2, H2, fmacc16) +RVVCALL(OPFVF3, vfmacc_vf_w, OP_UUU_W, H4, H4, fmacc32) +RVVCALL(OPFVF3, vfmacc_vf_d, OP_UUU_D, H8, H8, fmacc64) +GEN_VEXT_VF(vfmacc_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfmacc_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfmacc_vf_d, 8, 8, clearq) + +static uint16_t fnmacc16(uint16_t a, uint16_t b, uint16_t d, float_status *s) +{ + return float16_muladd(a, b, d, + float_muladd_negate_c | float_muladd_negate_product, s); +} + +static uint32_t fnmacc32(uint32_t a, uint32_t b, uint32_t d, float_status *s) +{ + return float32_muladd(a, b, d, + float_muladd_negate_c | float_muladd_negate_product, s); +} + +static uint64_t fnmacc64(uint64_t a, uint64_t b, uint64_t d, float_status *s) +{ + return float64_muladd(a, b, d, + float_muladd_negate_c | float_muladd_negate_product, s); +} + +RVVCALL(OPFVV3, vfnmacc_vv_h, OP_UUU_H, H2, H2, H2, fnmacc16) +RVVCALL(OPFVV3, vfnmacc_vv_w, OP_UUU_W, H4, H4, H4, fnmacc32) +RVVCALL(OPFVV3, vfnmacc_vv_d, OP_UUU_D, H8, H8, H8, fnmacc64) +GEN_VEXT_VV_ENV(vfnmacc_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfnmacc_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfnmacc_vv_d, 8, 8, clearq) +RVVCALL(OPFVF3, vfnmacc_vf_h, OP_UUU_H, H2, H2, fnmacc16) +RVVCALL(OPFVF3, vfnmacc_vf_w, OP_UUU_W, H4, H4, fnmacc32) +RVVCALL(OPFVF3, vfnmacc_vf_d, OP_UUU_D, H8, H8, fnmacc64) +GEN_VEXT_VF(vfnmacc_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfnmacc_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfnmacc_vf_d, 8, 8, clearq) + +static uint16_t fmsac16(uint16_t a, uint16_t b, uint16_t d, float_status *s) +{ + return float16_muladd(a, b, d, float_muladd_negate_c, s); +} + +static uint32_t fmsac32(uint32_t a, uint32_t b, uint32_t d, float_status *s) +{ + return float32_muladd(a, b, d, float_muladd_negate_c, s); +} + +static uint64_t fmsac64(uint64_t a, uint64_t b, uint64_t d, float_status *s) +{ + return float64_muladd(a, b, d, float_muladd_negate_c, s); +} + +RVVCALL(OPFVV3, vfmsac_vv_h, OP_UUU_H, H2, H2, H2, fmsac16) +RVVCALL(OPFVV3, vfmsac_vv_w, OP_UUU_W, H4, H4, H4, fmsac32) +RVVCALL(OPFVV3, vfmsac_vv_d, OP_UUU_D, H8, H8, H8, fmsac64) +GEN_VEXT_VV_ENV(vfmsac_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfmsac_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfmsac_vv_d, 8, 8, clearq) +RVVCALL(OPFVF3, vfmsac_vf_h, OP_UUU_H, H2, H2, fmsac16) +RVVCALL(OPFVF3, vfmsac_vf_w, OP_UUU_W, H4, H4, fmsac32) +RVVCALL(OPFVF3, vfmsac_vf_d, OP_UUU_D, H8, H8, fmsac64) +GEN_VEXT_VF(vfmsac_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfmsac_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfmsac_vf_d, 8, 8, clearq) + +static uint16_t fnmsac16(uint16_t a, uint16_t b, uint16_t d, float_status *s) +{ + return float16_muladd(a, b, d, float_muladd_negate_product, s); +} + +static uint32_t fnmsac32(uint32_t a, uint32_t b, uint32_t d, float_status *s) +{ + return float32_muladd(a, b, d, float_muladd_negate_product, s); +} + +static uint64_t fnmsac64(uint64_t a, uint64_t b, uint64_t d, float_status *s) +{ + return float64_muladd(a, b, d, float_muladd_negate_product, s); +} + +RVVCALL(OPFVV3, vfnmsac_vv_h, OP_UUU_H, H2, H2, H2, fnmsac16) +RVVCALL(OPFVV3, vfnmsac_vv_w, OP_UUU_W, H4, H4, H4, fnmsac32) +RVVCALL(OPFVV3, vfnmsac_vv_d, OP_UUU_D, H8, H8, H8, fnmsac64) +GEN_VEXT_VV_ENV(vfnmsac_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfnmsac_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfnmsac_vv_d, 8, 8, clearq) +RVVCALL(OPFVF3, vfnmsac_vf_h, OP_UUU_H, H2, H2, fnmsac16) +RVVCALL(OPFVF3, vfnmsac_vf_w, OP_UUU_W, H4, H4, fnmsac32) +RVVCALL(OPFVF3, vfnmsac_vf_d, OP_UUU_D, H8, H8, fnmsac64) +GEN_VEXT_VF(vfnmsac_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfnmsac_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfnmsac_vf_d, 8, 8, clearq) + +static uint16_t fmadd16(uint16_t a, uint16_t b, uint16_t d, float_status *s) +{ + return float16_muladd(d, b, a, 0, s); +} + +static uint32_t fmadd32(uint32_t a, uint32_t b, uint32_t d, float_status *s) +{ + return float32_muladd(d, b, a, 0, s); +} + +static uint64_t fmadd64(uint64_t a, uint64_t b, uint64_t d, float_status *s) +{ + return float64_muladd(d, b, a, 0, s); +} + +RVVCALL(OPFVV3, vfmadd_vv_h, OP_UUU_H, H2, H2, H2, fmadd16) +RVVCALL(OPFVV3, vfmadd_vv_w, OP_UUU_W, H4, H4, H4, fmadd32) +RVVCALL(OPFVV3, vfmadd_vv_d, OP_UUU_D, H8, H8, H8, fmadd64) +GEN_VEXT_VV_ENV(vfmadd_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfmadd_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfmadd_vv_d, 8, 8, clearq) +RVVCALL(OPFVF3, vfmadd_vf_h, OP_UUU_H, H2, H2, fmadd16) +RVVCALL(OPFVF3, vfmadd_vf_w, OP_UUU_W, H4, H4, fmadd32) +RVVCALL(OPFVF3, vfmadd_vf_d, OP_UUU_D, H8, H8, fmadd64) +GEN_VEXT_VF(vfmadd_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfmadd_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfmadd_vf_d, 8, 8, clearq) + +static uint16_t fnmadd16(uint16_t a, uint16_t b, uint16_t d, float_status *s) +{ + return float16_muladd(d, b, a, + float_muladd_negate_c | float_muladd_negate_product, s); +} + +static uint32_t fnmadd32(uint32_t a, uint32_t b, uint32_t d, float_status *s) +{ + return float32_muladd(d, b, a, + float_muladd_negate_c | float_muladd_negate_product, s); +} + +static uint64_t fnmadd64(uint64_t a, uint64_t b, uint64_t d, float_status *s) +{ + return float64_muladd(d, b, a, + float_muladd_negate_c | float_muladd_negate_product, s); +} + +RVVCALL(OPFVV3, vfnmadd_vv_h, OP_UUU_H, H2, H2, H2, fnmadd16) +RVVCALL(OPFVV3, vfnmadd_vv_w, OP_UUU_W, H4, H4, H4, fnmadd32) +RVVCALL(OPFVV3, vfnmadd_vv_d, OP_UUU_D, H8, H8, H8, fnmadd64) +GEN_VEXT_VV_ENV(vfnmadd_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfnmadd_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfnmadd_vv_d, 8, 8, clearq) +RVVCALL(OPFVF3, vfnmadd_vf_h, OP_UUU_H, H2, H2, fnmadd16) +RVVCALL(OPFVF3, vfnmadd_vf_w, OP_UUU_W, H4, H4, fnmadd32) +RVVCALL(OPFVF3, vfnmadd_vf_d, OP_UUU_D, H8, H8, fnmadd64) +GEN_VEXT_VF(vfnmadd_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfnmadd_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfnmadd_vf_d, 8, 8, clearq) + +static uint16_t fmsub16(uint16_t a, uint16_t b, uint16_t d, float_status *s) +{ + return float16_muladd(d, b, a, float_muladd_negate_c, s); +} + +static uint32_t fmsub32(uint32_t a, uint32_t b, uint32_t d, float_status *s) +{ + return float32_muladd(d, b, a, float_muladd_negate_c, s); +} + +static uint64_t fmsub64(uint64_t a, uint64_t b, uint64_t d, float_status *s) +{ + return float64_muladd(d, b, a, float_muladd_negate_c, s); +} + +RVVCALL(OPFVV3, vfmsub_vv_h, OP_UUU_H, H2, H2, H2, fmsub16) +RVVCALL(OPFVV3, vfmsub_vv_w, OP_UUU_W, H4, H4, H4, fmsub32) +RVVCALL(OPFVV3, vfmsub_vv_d, OP_UUU_D, H8, H8, H8, fmsub64) +GEN_VEXT_VV_ENV(vfmsub_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfmsub_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfmsub_vv_d, 8, 8, clearq) +RVVCALL(OPFVF3, vfmsub_vf_h, OP_UUU_H, H2, H2, fmsub16) +RVVCALL(OPFVF3, vfmsub_vf_w, OP_UUU_W, H4, H4, fmsub32) +RVVCALL(OPFVF3, vfmsub_vf_d, OP_UUU_D, H8, H8, fmsub64) +GEN_VEXT_VF(vfmsub_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfmsub_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfmsub_vf_d, 8, 8, clearq) + +static uint16_t fnmsub16(uint16_t a, uint16_t b, uint16_t d, float_status *s) +{ + return float16_muladd(d, b, a, float_muladd_negate_product, s); +} + +static uint32_t fnmsub32(uint32_t a, uint32_t b, uint32_t d, float_status *s) +{ + return float32_muladd(d, b, a, float_muladd_negate_product, s); +} + +static uint64_t fnmsub64(uint64_t a, uint64_t b, uint64_t d, float_status *s) +{ + return float64_muladd(d, b, a, float_muladd_negate_product, s); +} + +RVVCALL(OPFVV3, vfnmsub_vv_h, OP_UUU_H, H2, H2, H2, fnmsub16) +RVVCALL(OPFVV3, vfnmsub_vv_w, OP_UUU_W, H4, H4, H4, fnmsub32) +RVVCALL(OPFVV3, vfnmsub_vv_d, OP_UUU_D, H8, H8, H8, fnmsub64) +GEN_VEXT_VV_ENV(vfnmsub_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfnmsub_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfnmsub_vv_d, 8, 8, clearq) +RVVCALL(OPFVF3, vfnmsub_vf_h, OP_UUU_H, H2, H2, fnmsub16) +RVVCALL(OPFVF3, vfnmsub_vf_w, OP_UUU_W, H4, H4, fnmsub32) +RVVCALL(OPFVF3, vfnmsub_vf_d, OP_UUU_D, H8, H8, fnmsub64) +GEN_VEXT_VF(vfnmsub_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfnmsub_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfnmsub_vf_d, 8, 8, clearq) + +/* Vector Widening Floating-Point Fused Multiply-Add Instructions */ +static uint32_t fwmacc16(uint16_t a, uint16_t b, uint32_t d, float_status *s) +{ + return float32_muladd(float16_to_float32(a, true, s), + float16_to_float32(b, true, s), d, 0, s); +} + +static uint64_t fwmacc32(uint32_t a, uint32_t b, uint64_t d, float_status *s) +{ + return float64_muladd(float32_to_float64(a, s), + float32_to_float64(b, s), d, 0, s); +} + +RVVCALL(OPFVV3, vfwmacc_vv_h, WOP_UUU_H, H4, H2, H2, fwmacc16) +RVVCALL(OPFVV3, vfwmacc_vv_w, WOP_UUU_W, H8, H4, H4, fwmacc32) +GEN_VEXT_VV_ENV(vfwmacc_vv_h, 2, 4, clearl) +GEN_VEXT_VV_ENV(vfwmacc_vv_w, 4, 8, clearq) +RVVCALL(OPFVF3, vfwmacc_vf_h, WOP_UUU_H, H4, H2, fwmacc16) +RVVCALL(OPFVF3, vfwmacc_vf_w, WOP_UUU_W, H8, H4, fwmacc32) +GEN_VEXT_VF(vfwmacc_vf_h, 2, 4, clearl) +GEN_VEXT_VF(vfwmacc_vf_w, 4, 8, clearq) + +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), + float16_to_float32(b, true, s), d, + float_muladd_negate_c | float_muladd_negate_product, s); +} + +static uint64_t fwnmacc32(uint32_t a, uint32_t b, uint64_t d, float_status *s) +{ + return float64_muladd(float32_to_float64(a, s), + float32_to_float64(b, s), d, + float_muladd_negate_c | float_muladd_negate_product, s); +} + +RVVCALL(OPFVV3, vfwnmacc_vv_h, WOP_UUU_H, H4, H2, H2, fwnmacc16) +RVVCALL(OPFVV3, vfwnmacc_vv_w, WOP_UUU_W, H8, H4, H4, fwnmacc32) +GEN_VEXT_VV_ENV(vfwnmacc_vv_h, 2, 4, clearl) +GEN_VEXT_VV_ENV(vfwnmacc_vv_w, 4, 8, clearq) +RVVCALL(OPFVF3, vfwnmacc_vf_h, WOP_UUU_H, H4, H2, fwnmacc16) +RVVCALL(OPFVF3, vfwnmacc_vf_w, WOP_UUU_W, H8, H4, fwnmacc32) +GEN_VEXT_VF(vfwnmacc_vf_h, 2, 4, clearl) +GEN_VEXT_VF(vfwnmacc_vf_w, 4, 8, clearq) + +static uint32_t fwmsac16(uint16_t a, uint16_t b, uint32_t d, float_status *s) +{ + return float32_muladd(float16_to_float32(a, true, s), + float16_to_float32(b, true, s), d, + float_muladd_negate_c, s); +} + +static uint64_t fwmsac32(uint32_t a, uint32_t b, uint64_t d, float_status *s) +{ + return float64_muladd(float32_to_float64(a, s), + float32_to_float64(b, s), d, + float_muladd_negate_c, s); +} + +RVVCALL(OPFVV3, vfwmsac_vv_h, WOP_UUU_H, H4, H2, H2, fwmsac16) +RVVCALL(OPFVV3, vfwmsac_vv_w, WOP_UUU_W, H8, H4, H4, fwmsac32) +GEN_VEXT_VV_ENV(vfwmsac_vv_h, 2, 4, clearl) +GEN_VEXT_VV_ENV(vfwmsac_vv_w, 4, 8, clearq) +RVVCALL(OPFVF3, vfwmsac_vf_h, WOP_UUU_H, H4, H2, fwmsac16) +RVVCALL(OPFVF3, vfwmsac_vf_w, WOP_UUU_W, H8, H4, fwmsac32) +GEN_VEXT_VF(vfwmsac_vf_h, 2, 4, clearl) +GEN_VEXT_VF(vfwmsac_vf_w, 4, 8, clearq) + +static uint32_t fwnmsac16(uint16_t a, uint16_t b, uint32_t d, float_status *s) +{ + return float32_muladd(float16_to_float32(a, true, s), + float16_to_float32(b, true, s), d, + float_muladd_negate_product, s); +} + +static uint64_t fwnmsac32(uint32_t a, uint32_t b, uint64_t d, float_status *s) +{ + return float64_muladd(float32_to_float64(a, s), + float32_to_float64(b, s), d, + float_muladd_negate_product, s); +} + +RVVCALL(OPFVV3, vfwnmsac_vv_h, WOP_UUU_H, H4, H2, H2, fwnmsac16) +RVVCALL(OPFVV3, vfwnmsac_vv_w, WOP_UUU_W, H8, H4, H4, fwnmsac32) +GEN_VEXT_VV_ENV(vfwnmsac_vv_h, 2, 4, clearl) +GEN_VEXT_VV_ENV(vfwnmsac_vv_w, 4, 8, clearq) +RVVCALL(OPFVF3, vfwnmsac_vf_h, WOP_UUU_H, H4, H2, fwnmsac16) +RVVCALL(OPFVF3, vfwnmsac_vf_w, WOP_UUU_W, H8, H4, fwnmsac32) +GEN_VEXT_VF(vfwnmsac_vf_h, 2, 4, clearl) +GEN_VEXT_VF(vfwnmsac_vf_w, 4, 8, clearq) + +/* 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) \ +{ \ + TX2 s2 = *((T2 *)vs2 + HS2(i)); \ + *((TD *)vd + HD(i)) = OP(s2, &env->fp_status); \ +} + +#define GEN_VEXT_V_ENV(NAME, ESZ, DSZ, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, void *vs2, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t vlmax = vext_maxsz(desc) / ESZ; \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vm = vext_vm(desc); \ + uint32_t vl = env->vl; \ + uint32_t i; \ + \ + if (vl == 0) { \ + return; \ + } \ + for (i = 0; i < vl; i++) { \ + if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + continue; \ + } \ + do_##NAME(vd, vs2, i, env); \ + } \ + CLEAR_FN(vd, vl, vl * DSZ, vlmax * DSZ); \ +} + +RVVCALL(OPFVV1, vfsqrt_v_h, OP_UU_H, H2, H2, float16_sqrt) +RVVCALL(OPFVV1, vfsqrt_v_w, OP_UU_W, H4, H4, float32_sqrt) +RVVCALL(OPFVV1, vfsqrt_v_d, OP_UU_D, H8, H8, float64_sqrt) +GEN_VEXT_V_ENV(vfsqrt_v_h, 2, 2, clearh) +GEN_VEXT_V_ENV(vfsqrt_v_w, 4, 4, clearl) +GEN_VEXT_V_ENV(vfsqrt_v_d, 8, 8, clearq) + +/* Vector Floating-Point MIN/MAX Instructions */ +RVVCALL(OPFVV2, vfmin_vv_h, OP_UUU_H, H2, H2, H2, float16_minnum) +RVVCALL(OPFVV2, vfmin_vv_w, OP_UUU_W, H4, H4, H4, float32_minnum) +RVVCALL(OPFVV2, vfmin_vv_d, OP_UUU_D, H8, H8, H8, float64_minnum) +GEN_VEXT_VV_ENV(vfmin_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfmin_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfmin_vv_d, 8, 8, clearq) +RVVCALL(OPFVF2, vfmin_vf_h, OP_UUU_H, H2, H2, float16_minnum) +RVVCALL(OPFVF2, vfmin_vf_w, OP_UUU_W, H4, H4, float32_minnum) +RVVCALL(OPFVF2, vfmin_vf_d, OP_UUU_D, H8, H8, float64_minnum) +GEN_VEXT_VF(vfmin_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfmin_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfmin_vf_d, 8, 8, clearq) + +RVVCALL(OPFVV2, vfmax_vv_h, OP_UUU_H, H2, H2, H2, float16_maxnum) +RVVCALL(OPFVV2, vfmax_vv_w, OP_UUU_W, H4, H4, H4, float32_maxnum) +RVVCALL(OPFVV2, vfmax_vv_d, OP_UUU_D, H8, H8, H8, float64_maxnum) +GEN_VEXT_VV_ENV(vfmax_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfmax_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfmax_vv_d, 8, 8, clearq) +RVVCALL(OPFVF2, vfmax_vf_h, OP_UUU_H, H2, H2, float16_maxnum) +RVVCALL(OPFVF2, vfmax_vf_w, OP_UUU_W, H4, H4, float32_maxnum) +RVVCALL(OPFVF2, vfmax_vf_d, OP_UUU_D, H8, H8, float64_maxnum) +GEN_VEXT_VF(vfmax_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfmax_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfmax_vf_d, 8, 8, clearq) + +/* Vector Floating-Point Sign-Injection Instructions */ +static uint16_t fsgnj16(uint16_t a, uint16_t b, float_status *s) +{ + return deposit64(b, 0, 15, a); +} + +static uint32_t fsgnj32(uint32_t a, uint32_t b, float_status *s) +{ + return deposit64(b, 0, 31, a); +} + +static uint64_t fsgnj64(uint64_t a, uint64_t b, float_status *s) +{ + return deposit64(b, 0, 63, a); +} + +RVVCALL(OPFVV2, vfsgnj_vv_h, OP_UUU_H, H2, H2, H2, fsgnj16) +RVVCALL(OPFVV2, vfsgnj_vv_w, OP_UUU_W, H4, H4, H4, fsgnj32) +RVVCALL(OPFVV2, vfsgnj_vv_d, OP_UUU_D, H8, H8, H8, fsgnj64) +GEN_VEXT_VV_ENV(vfsgnj_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfsgnj_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfsgnj_vv_d, 8, 8, clearq) +RVVCALL(OPFVF2, vfsgnj_vf_h, OP_UUU_H, H2, H2, fsgnj16) +RVVCALL(OPFVF2, vfsgnj_vf_w, OP_UUU_W, H4, H4, fsgnj32) +RVVCALL(OPFVF2, vfsgnj_vf_d, OP_UUU_D, H8, H8, fsgnj64) +GEN_VEXT_VF(vfsgnj_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfsgnj_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfsgnj_vf_d, 8, 8, clearq) + +static uint16_t fsgnjn16(uint16_t a, uint16_t b, float_status *s) +{ + return deposit64(~b, 0, 15, a); +} + +static uint32_t fsgnjn32(uint32_t a, uint32_t b, float_status *s) +{ + return deposit64(~b, 0, 31, a); +} + +static uint64_t fsgnjn64(uint64_t a, uint64_t b, float_status *s) +{ + return deposit64(~b, 0, 63, a); +} + +RVVCALL(OPFVV2, vfsgnjn_vv_h, OP_UUU_H, H2, H2, H2, fsgnjn16) +RVVCALL(OPFVV2, vfsgnjn_vv_w, OP_UUU_W, H4, H4, H4, fsgnjn32) +RVVCALL(OPFVV2, vfsgnjn_vv_d, OP_UUU_D, H8, H8, H8, fsgnjn64) +GEN_VEXT_VV_ENV(vfsgnjn_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfsgnjn_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfsgnjn_vv_d, 8, 8, clearq) +RVVCALL(OPFVF2, vfsgnjn_vf_h, OP_UUU_H, H2, H2, fsgnjn16) +RVVCALL(OPFVF2, vfsgnjn_vf_w, OP_UUU_W, H4, H4, fsgnjn32) +RVVCALL(OPFVF2, vfsgnjn_vf_d, OP_UUU_D, H8, H8, fsgnjn64) +GEN_VEXT_VF(vfsgnjn_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfsgnjn_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfsgnjn_vf_d, 8, 8, clearq) + +static uint16_t fsgnjx16(uint16_t a, uint16_t b, float_status *s) +{ + return deposit64(b ^ a, 0, 15, a); +} + +static uint32_t fsgnjx32(uint32_t a, uint32_t b, float_status *s) +{ + return deposit64(b ^ a, 0, 31, a); +} + +static uint64_t fsgnjx64(uint64_t a, uint64_t b, float_status *s) +{ + return deposit64(b ^ a, 0, 63, a); +} + +RVVCALL(OPFVV2, vfsgnjx_vv_h, OP_UUU_H, H2, H2, H2, fsgnjx16) +RVVCALL(OPFVV2, vfsgnjx_vv_w, OP_UUU_W, H4, H4, H4, fsgnjx32) +RVVCALL(OPFVV2, vfsgnjx_vv_d, OP_UUU_D, H8, H8, H8, fsgnjx64) +GEN_VEXT_VV_ENV(vfsgnjx_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfsgnjx_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfsgnjx_vv_d, 8, 8, clearq) +RVVCALL(OPFVF2, vfsgnjx_vf_h, OP_UUU_H, H2, H2, fsgnjx16) +RVVCALL(OPFVF2, vfsgnjx_vf_w, OP_UUU_W, H4, H4, fsgnjx32) +RVVCALL(OPFVF2, vfsgnjx_vf_d, OP_UUU_D, H8, H8, fsgnjx64) +GEN_VEXT_VF(vfsgnjx_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfsgnjx_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfsgnjx_vf_d, 8, 8, clearq) + +/* Vector Floating-Point Compare Instructions */ +#define GEN_VEXT_CMP_VV_ENV(NAME, ETYPE, H, DO_OP) \ +void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vm = vext_vm(desc); \ + uint32_t vl = env->vl; \ + uint32_t vlmax = vext_maxsz(desc) / sizeof(ETYPE); \ + uint32_t i; \ + \ + for (i = 0; i < vl; i++) { \ + ETYPE s1 = *((ETYPE *)vs1 + H(i)); \ + ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ + if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + continue; \ + } \ + vext_set_elem_mask(vd, mlen, i, \ + DO_OP(s2, s1, &env->fp_status)); \ + } \ + for (; i < vlmax; i++) { \ + vext_set_elem_mask(vd, mlen, i, 0); \ + } \ +} + +GEN_VEXT_CMP_VV_ENV(vmfeq_vv_h, uint16_t, H2, float16_eq_quiet) +GEN_VEXT_CMP_VV_ENV(vmfeq_vv_w, uint32_t, H4, float32_eq_quiet) +GEN_VEXT_CMP_VV_ENV(vmfeq_vv_d, uint64_t, H8, float64_eq_quiet) + +#define GEN_VEXT_CMP_VF(NAME, ETYPE, H, DO_OP) \ +void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vm = vext_vm(desc); \ + uint32_t vl = env->vl; \ + uint32_t vlmax = vext_maxsz(desc) / sizeof(ETYPE); \ + uint32_t i; \ + \ + for (i = 0; i < vl; i++) { \ + ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ + if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + continue; \ + } \ + vext_set_elem_mask(vd, mlen, i, \ + DO_OP(s2, (ETYPE)s1, &env->fp_status)); \ + } \ + for (; i < vlmax; i++) { \ + vext_set_elem_mask(vd, mlen, i, 0); \ + } \ +} + +GEN_VEXT_CMP_VF(vmfeq_vf_h, uint16_t, H2, float16_eq_quiet) +GEN_VEXT_CMP_VF(vmfeq_vf_w, uint32_t, H4, float32_eq_quiet) +GEN_VEXT_CMP_VF(vmfeq_vf_d, uint64_t, H8, float64_eq_quiet) + +static bool vmfne16(uint16_t a, uint16_t b, float_status *s) +{ + FloatRelation compare = float16_compare_quiet(a, b, s); + return compare != float_relation_equal; +} + +static bool vmfne32(uint32_t a, uint32_t b, float_status *s) +{ + FloatRelation compare = float32_compare_quiet(a, b, s); + return compare != float_relation_equal; +} + +static bool vmfne64(uint64_t a, uint64_t b, float_status *s) +{ + FloatRelation compare = float64_compare_quiet(a, b, s); + return compare != float_relation_equal; +} + +GEN_VEXT_CMP_VV_ENV(vmfne_vv_h, uint16_t, H2, vmfne16) +GEN_VEXT_CMP_VV_ENV(vmfne_vv_w, uint32_t, H4, vmfne32) +GEN_VEXT_CMP_VV_ENV(vmfne_vv_d, uint64_t, H8, vmfne64) +GEN_VEXT_CMP_VF(vmfne_vf_h, uint16_t, H2, vmfne16) +GEN_VEXT_CMP_VF(vmfne_vf_w, uint32_t, H4, vmfne32) +GEN_VEXT_CMP_VF(vmfne_vf_d, uint64_t, H8, vmfne64) + +GEN_VEXT_CMP_VV_ENV(vmflt_vv_h, uint16_t, H2, float16_lt) +GEN_VEXT_CMP_VV_ENV(vmflt_vv_w, uint32_t, H4, float32_lt) +GEN_VEXT_CMP_VV_ENV(vmflt_vv_d, uint64_t, H8, float64_lt) +GEN_VEXT_CMP_VF(vmflt_vf_h, uint16_t, H2, float16_lt) +GEN_VEXT_CMP_VF(vmflt_vf_w, uint32_t, H4, float32_lt) +GEN_VEXT_CMP_VF(vmflt_vf_d, uint64_t, H8, float64_lt) + +GEN_VEXT_CMP_VV_ENV(vmfle_vv_h, uint16_t, H2, float16_le) +GEN_VEXT_CMP_VV_ENV(vmfle_vv_w, uint32_t, H4, float32_le) +GEN_VEXT_CMP_VV_ENV(vmfle_vv_d, uint64_t, H8, float64_le) +GEN_VEXT_CMP_VF(vmfle_vf_h, uint16_t, H2, float16_le) +GEN_VEXT_CMP_VF(vmfle_vf_w, uint32_t, H4, float32_le) +GEN_VEXT_CMP_VF(vmfle_vf_d, uint64_t, H8, float64_le) + +static bool vmfgt16(uint16_t a, uint16_t b, float_status *s) +{ + FloatRelation compare = float16_compare(a, b, s); + return compare == float_relation_greater; +} + +static bool vmfgt32(uint32_t a, uint32_t b, float_status *s) +{ + FloatRelation compare = float32_compare(a, b, s); + return compare == float_relation_greater; +} + +static bool vmfgt64(uint64_t a, uint64_t b, float_status *s) +{ + FloatRelation compare = float64_compare(a, b, s); + return compare == float_relation_greater; +} + +GEN_VEXT_CMP_VF(vmfgt_vf_h, uint16_t, H2, vmfgt16) +GEN_VEXT_CMP_VF(vmfgt_vf_w, uint32_t, H4, vmfgt32) +GEN_VEXT_CMP_VF(vmfgt_vf_d, uint64_t, H8, vmfgt64) + +static bool vmfge16(uint16_t a, uint16_t b, float_status *s) +{ + FloatRelation compare = float16_compare(a, b, s); + return compare == float_relation_greater || + compare == float_relation_equal; +} + +static bool vmfge32(uint32_t a, uint32_t b, float_status *s) +{ + FloatRelation compare = float32_compare(a, b, s); + return compare == float_relation_greater || + compare == float_relation_equal; +} + +static bool vmfge64(uint64_t a, uint64_t b, float_status *s) +{ + FloatRelation compare = float64_compare(a, b, s); + return compare == float_relation_greater || + compare == float_relation_equal; +} + +GEN_VEXT_CMP_VF(vmfge_vf_h, uint16_t, H2, vmfge16) +GEN_VEXT_CMP_VF(vmfge_vf_w, uint32_t, H4, vmfge32) +GEN_VEXT_CMP_VF(vmfge_vf_d, uint64_t, H8, vmfge64) + +GEN_VEXT_CMP_VV_ENV(vmford_vv_h, uint16_t, H2, !float16_unordered_quiet) +GEN_VEXT_CMP_VV_ENV(vmford_vv_w, uint32_t, H4, !float32_unordered_quiet) +GEN_VEXT_CMP_VV_ENV(vmford_vv_d, uint64_t, H8, !float64_unordered_quiet) +GEN_VEXT_CMP_VF(vmford_vf_h, uint16_t, H2, !float16_unordered_quiet) +GEN_VEXT_CMP_VF(vmford_vf_w, uint32_t, H4, !float32_unordered_quiet) +GEN_VEXT_CMP_VF(vmford_vf_d, uint64_t, H8, !float64_unordered_quiet) + +/* 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, DSZ, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, void *vs2, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t vlmax = vext_maxsz(desc) / ESZ; \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vm = vext_vm(desc); \ + uint32_t vl = env->vl; \ + uint32_t i; \ + \ + for (i = 0; i < vl; i++) { \ + if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + continue; \ + } \ + do_##NAME(vd, vs2, i); \ + } \ + CLEAR_FN(vd, vl, vl * DSZ, vlmax * DSZ); \ +} + +target_ulong fclass_h(uint64_t frs1) +{ + float16 f = frs1; + bool sign = float16_is_neg(f); + + if (float16_is_infinity(f)) { + return sign ? 1 << 0 : 1 << 7; + } else if (float16_is_zero(f)) { + return sign ? 1 << 3 : 1 << 4; + } else if (float16_is_zero_or_denormal(f)) { + return sign ? 1 << 2 : 1 << 5; + } else if (float16_is_any_nan(f)) { + float_status s = { }; /* for snan_bit_is_one */ + return float16_is_quiet_nan(f, &s) ? 1 << 9 : 1 << 8; + } else { + return sign ? 1 << 1 : 1 << 6; + } +} + +target_ulong fclass_s(uint64_t frs1) +{ + float32 f = frs1; + bool sign = float32_is_neg(f); + + if (float32_is_infinity(f)) { + return sign ? 1 << 0 : 1 << 7; + } else if (float32_is_zero(f)) { + return sign ? 1 << 3 : 1 << 4; + } else if (float32_is_zero_or_denormal(f)) { + return sign ? 1 << 2 : 1 << 5; + } else if (float32_is_any_nan(f)) { + float_status s = { }; /* for snan_bit_is_one */ + return float32_is_quiet_nan(f, &s) ? 1 << 9 : 1 << 8; + } else { + return sign ? 1 << 1 : 1 << 6; + } +} + +target_ulong fclass_d(uint64_t frs1) +{ + float64 f = frs1; + bool sign = float64_is_neg(f); + + if (float64_is_infinity(f)) { + return sign ? 1 << 0 : 1 << 7; + } else if (float64_is_zero(f)) { + return sign ? 1 << 3 : 1 << 4; + } else if (float64_is_zero_or_denormal(f)) { + return sign ? 1 << 2 : 1 << 5; + } else if (float64_is_any_nan(f)) { + float_status s = { }; /* for snan_bit_is_one */ + return float64_is_quiet_nan(f, &s) ? 1 << 9 : 1 << 8; + } else { + return sign ? 1 << 1 : 1 << 6; + } +} + +RVVCALL(OPIVV1, vfclass_v_h, OP_UU_H, H2, H2, fclass_h) +RVVCALL(OPIVV1, vfclass_v_w, OP_UU_W, H4, H4, fclass_s) +RVVCALL(OPIVV1, vfclass_v_d, OP_UU_D, H8, H8, fclass_d) +GEN_VEXT_V(vfclass_v_h, 2, 2, clearh) +GEN_VEXT_V(vfclass_v_w, 4, 4, clearl) +GEN_VEXT_V(vfclass_v_d, 8, 8, clearq) + +/* Vector Floating-Point Merge Instruction */ +#define GEN_VFMERGE_VF(NAME, ETYPE, H, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vm = vext_vm(desc); \ + uint32_t vl = env->vl; \ + uint32_t esz = sizeof(ETYPE); \ + uint32_t vlmax = vext_maxsz(desc) / esz; \ + uint32_t i; \ + \ + for (i = 0; i < vl; i++) { \ + ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ + *((ETYPE *)vd + H(i)) \ + = (!vm && !vext_elem_mask(v0, mlen, i) ? s2 : s1); \ + } \ + CLEAR_FN(vd, vl, vl * esz, vlmax * esz); \ +} + +GEN_VFMERGE_VF(vfmerge_vfm_h, int16_t, H2, clearh) +GEN_VFMERGE_VF(vfmerge_vfm_w, int32_t, H4, clearl) +GEN_VFMERGE_VF(vfmerge_vfm_d, int64_t, H8, clearq) + +/* Single-Width Floating-Point/Integer Type-Convert Instructions */ +/* vfcvt.xu.f.v vd, vs2, vm # Convert float to unsigned integer. */ +RVVCALL(OPFVV1, vfcvt_xu_f_v_h, OP_UU_H, H2, H2, float16_to_uint16) +RVVCALL(OPFVV1, vfcvt_xu_f_v_w, OP_UU_W, H4, H4, float32_to_uint32) +RVVCALL(OPFVV1, vfcvt_xu_f_v_d, OP_UU_D, H8, H8, float64_to_uint64) +GEN_VEXT_V_ENV(vfcvt_xu_f_v_h, 2, 2, clearh) +GEN_VEXT_V_ENV(vfcvt_xu_f_v_w, 4, 4, clearl) +GEN_VEXT_V_ENV(vfcvt_xu_f_v_d, 8, 8, clearq) + +/* vfcvt.x.f.v vd, vs2, vm # Convert float to signed integer. */ +RVVCALL(OPFVV1, vfcvt_x_f_v_h, OP_UU_H, H2, H2, float16_to_int16) +RVVCALL(OPFVV1, vfcvt_x_f_v_w, OP_UU_W, H4, H4, float32_to_int32) +RVVCALL(OPFVV1, vfcvt_x_f_v_d, OP_UU_D, H8, H8, float64_to_int64) +GEN_VEXT_V_ENV(vfcvt_x_f_v_h, 2, 2, clearh) +GEN_VEXT_V_ENV(vfcvt_x_f_v_w, 4, 4, clearl) +GEN_VEXT_V_ENV(vfcvt_x_f_v_d, 8, 8, clearq) + +/* vfcvt.f.xu.v vd, vs2, vm # Convert unsigned integer to float. */ +RVVCALL(OPFVV1, vfcvt_f_xu_v_h, OP_UU_H, H2, H2, uint16_to_float16) +RVVCALL(OPFVV1, vfcvt_f_xu_v_w, OP_UU_W, H4, H4, uint32_to_float32) +RVVCALL(OPFVV1, vfcvt_f_xu_v_d, OP_UU_D, H8, H8, uint64_to_float64) +GEN_VEXT_V_ENV(vfcvt_f_xu_v_h, 2, 2, clearh) +GEN_VEXT_V_ENV(vfcvt_f_xu_v_w, 4, 4, clearl) +GEN_VEXT_V_ENV(vfcvt_f_xu_v_d, 8, 8, clearq) + +/* vfcvt.f.x.v vd, vs2, vm # Convert integer to float. */ +RVVCALL(OPFVV1, vfcvt_f_x_v_h, OP_UU_H, H2, H2, int16_to_float16) +RVVCALL(OPFVV1, vfcvt_f_x_v_w, OP_UU_W, H4, H4, int32_to_float32) +RVVCALL(OPFVV1, vfcvt_f_x_v_d, OP_UU_D, H8, H8, int64_to_float64) +GEN_VEXT_V_ENV(vfcvt_f_x_v_h, 2, 2, clearh) +GEN_VEXT_V_ENV(vfcvt_f_x_v_w, 4, 4, clearl) +GEN_VEXT_V_ENV(vfcvt_f_x_v_d, 8, 8, clearq) + +/* Widening Floating-Point/Integer Type-Convert Instructions */ +/* (TD, T2, TX2) */ +#define WOP_UU_H uint32_t, uint16_t, uint16_t +#define WOP_UU_W uint64_t, uint32_t, uint32_t +/* vfwcvt.xu.f.v vd, vs2, vm # Convert float to double-width unsigned integer.*/ +RVVCALL(OPFVV1, vfwcvt_xu_f_v_h, WOP_UU_H, H4, H2, float16_to_uint32) +RVVCALL(OPFVV1, vfwcvt_xu_f_v_w, WOP_UU_W, H8, H4, float32_to_uint64) +GEN_VEXT_V_ENV(vfwcvt_xu_f_v_h, 2, 4, clearl) +GEN_VEXT_V_ENV(vfwcvt_xu_f_v_w, 4, 8, clearq) + +/* vfwcvt.x.f.v vd, vs2, vm # Convert float to double-width signed integer. */ +RVVCALL(OPFVV1, vfwcvt_x_f_v_h, WOP_UU_H, H4, H2, float16_to_int32) +RVVCALL(OPFVV1, vfwcvt_x_f_v_w, WOP_UU_W, H8, H4, float32_to_int64) +GEN_VEXT_V_ENV(vfwcvt_x_f_v_h, 2, 4, clearl) +GEN_VEXT_V_ENV(vfwcvt_x_f_v_w, 4, 8, clearq) + +/* vfwcvt.f.xu.v vd, vs2, vm # Convert unsigned integer to double-width float */ +RVVCALL(OPFVV1, vfwcvt_f_xu_v_h, WOP_UU_H, H4, H2, uint16_to_float32) +RVVCALL(OPFVV1, vfwcvt_f_xu_v_w, WOP_UU_W, H8, H4, uint32_to_float64) +GEN_VEXT_V_ENV(vfwcvt_f_xu_v_h, 2, 4, clearl) +GEN_VEXT_V_ENV(vfwcvt_f_xu_v_w, 4, 8, clearq) + +/* vfwcvt.f.x.v vd, vs2, vm # Convert integer to double-width float. */ +RVVCALL(OPFVV1, vfwcvt_f_x_v_h, WOP_UU_H, H4, H2, int16_to_float32) +RVVCALL(OPFVV1, vfwcvt_f_x_v_w, WOP_UU_W, H8, H4, int32_to_float64) +GEN_VEXT_V_ENV(vfwcvt_f_x_v_h, 2, 4, clearl) +GEN_VEXT_V_ENV(vfwcvt_f_x_v_w, 4, 8, clearq) + +/* + * vfwcvt.f.f.v vd, vs2, vm # + * Convert single-width float to double-width float. + */ +static uint32_t vfwcvtffv16(uint16_t a, float_status *s) +{ + return float16_to_float32(a, true, s); +} + +RVVCALL(OPFVV1, vfwcvt_f_f_v_h, WOP_UU_H, H4, H2, vfwcvtffv16) +RVVCALL(OPFVV1, vfwcvt_f_f_v_w, WOP_UU_W, H8, H4, float32_to_float64) +GEN_VEXT_V_ENV(vfwcvt_f_f_v_h, 2, 4, clearl) +GEN_VEXT_V_ENV(vfwcvt_f_f_v_w, 4, 8, clearq) + +/* Narrowing Floating-Point/Integer Type-Convert Instructions */ +/* (TD, T2, TX2) */ +#define NOP_UU_H uint16_t, uint32_t, uint32_t +#define NOP_UU_W uint32_t, uint64_t, uint64_t +/* vfncvt.xu.f.v vd, vs2, vm # Convert float to unsigned integer. */ +RVVCALL(OPFVV1, vfncvt_xu_f_v_h, NOP_UU_H, H2, H4, float32_to_uint16) +RVVCALL(OPFVV1, vfncvt_xu_f_v_w, NOP_UU_W, H4, H8, float64_to_uint32) +GEN_VEXT_V_ENV(vfncvt_xu_f_v_h, 2, 2, clearh) +GEN_VEXT_V_ENV(vfncvt_xu_f_v_w, 4, 4, clearl) + +/* vfncvt.x.f.v vd, vs2, vm # Convert double-width float to signed integer. */ +RVVCALL(OPFVV1, vfncvt_x_f_v_h, NOP_UU_H, H2, H4, float32_to_int16) +RVVCALL(OPFVV1, vfncvt_x_f_v_w, NOP_UU_W, H4, H8, float64_to_int32) +GEN_VEXT_V_ENV(vfncvt_x_f_v_h, 2, 2, clearh) +GEN_VEXT_V_ENV(vfncvt_x_f_v_w, 4, 4, clearl) + +/* vfncvt.f.xu.v vd, vs2, vm # Convert double-width unsigned integer to float */ +RVVCALL(OPFVV1, vfncvt_f_xu_v_h, NOP_UU_H, H2, H4, uint32_to_float16) +RVVCALL(OPFVV1, vfncvt_f_xu_v_w, NOP_UU_W, H4, H8, uint64_to_float32) +GEN_VEXT_V_ENV(vfncvt_f_xu_v_h, 2, 2, clearh) +GEN_VEXT_V_ENV(vfncvt_f_xu_v_w, 4, 4, clearl) + +/* vfncvt.f.x.v vd, vs2, vm # Convert double-width integer to float. */ +RVVCALL(OPFVV1, vfncvt_f_x_v_h, NOP_UU_H, H2, H4, int32_to_float16) +RVVCALL(OPFVV1, vfncvt_f_x_v_w, NOP_UU_W, H4, H8, int64_to_float32) +GEN_VEXT_V_ENV(vfncvt_f_x_v_h, 2, 2, clearh) +GEN_VEXT_V_ENV(vfncvt_f_x_v_w, 4, 4, clearl) + +/* vfncvt.f.f.v vd, vs2, vm # Convert double float to single-width float. */ +static uint16_t vfncvtffv16(uint32_t a, float_status *s) +{ + return float32_to_float16(a, true, s); +} + +RVVCALL(OPFVV1, vfncvt_f_f_v_h, NOP_UU_H, H2, H4, vfncvtffv16) +RVVCALL(OPFVV1, vfncvt_f_f_v_w, NOP_UU_W, H4, H8, float64_to_float32) +GEN_VEXT_V_ENV(vfncvt_f_f_v_h, 2, 2, clearh) +GEN_VEXT_V_ENV(vfncvt_f_f_v_w, 4, 4, clearl) + +/* + *** Vector Reduction Operations + */ +/* Vector Single-Width Integer Reduction Instructions */ +#define GEN_VEXT_RED(NAME, TD, TS2, HD, HS2, OP, CLEAR_FN)\ +void HELPER(NAME)(void *vd, void *v0, void *vs1, \ + void *vs2, CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vm = vext_vm(desc); \ + uint32_t vl = env->vl; \ + uint32_t i; \ + uint32_t tot = env_archcpu(env)->cfg.vlen / 8; \ + TD s1 = *((TD *)vs1 + HD(0)); \ + \ + for (i = 0; i < vl; i++) { \ + TS2 s2 = *((TS2 *)vs2 + HS2(i)); \ + if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + continue; \ + } \ + s1 = OP(s1, (TD)s2); \ + } \ + *((TD *)vd + HD(0)) = s1; \ + CLEAR_FN(vd, 1, sizeof(TD), tot); \ +} + +/* vd[0] = sum(vs1[0], vs2[*]) */ +GEN_VEXT_RED(vredsum_vs_b, int8_t, int8_t, H1, H1, DO_ADD, clearb) +GEN_VEXT_RED(vredsum_vs_h, int16_t, int16_t, H2, H2, DO_ADD, clearh) +GEN_VEXT_RED(vredsum_vs_w, int32_t, int32_t, H4, H4, DO_ADD, clearl) +GEN_VEXT_RED(vredsum_vs_d, int64_t, int64_t, H8, H8, DO_ADD, clearq) + +/* vd[0] = maxu(vs1[0], vs2[*]) */ +GEN_VEXT_RED(vredmaxu_vs_b, uint8_t, uint8_t, H1, H1, DO_MAX, clearb) +GEN_VEXT_RED(vredmaxu_vs_h, uint16_t, uint16_t, H2, H2, DO_MAX, clearh) +GEN_VEXT_RED(vredmaxu_vs_w, uint32_t, uint32_t, H4, H4, DO_MAX, clearl) +GEN_VEXT_RED(vredmaxu_vs_d, uint64_t, uint64_t, H8, H8, DO_MAX, clearq) + +/* vd[0] = max(vs1[0], vs2[*]) */ +GEN_VEXT_RED(vredmax_vs_b, int8_t, int8_t, H1, H1, DO_MAX, clearb) +GEN_VEXT_RED(vredmax_vs_h, int16_t, int16_t, H2, H2, DO_MAX, clearh) +GEN_VEXT_RED(vredmax_vs_w, int32_t, int32_t, H4, H4, DO_MAX, clearl) +GEN_VEXT_RED(vredmax_vs_d, int64_t, int64_t, H8, H8, DO_MAX, clearq) + +/* vd[0] = minu(vs1[0], vs2[*]) */ +GEN_VEXT_RED(vredminu_vs_b, uint8_t, uint8_t, H1, H1, DO_MIN, clearb) +GEN_VEXT_RED(vredminu_vs_h, uint16_t, uint16_t, H2, H2, DO_MIN, clearh) +GEN_VEXT_RED(vredminu_vs_w, uint32_t, uint32_t, H4, H4, DO_MIN, clearl) +GEN_VEXT_RED(vredminu_vs_d, uint64_t, uint64_t, H8, H8, DO_MIN, clearq) + +/* vd[0] = min(vs1[0], vs2[*]) */ +GEN_VEXT_RED(vredmin_vs_b, int8_t, int8_t, H1, H1, DO_MIN, clearb) +GEN_VEXT_RED(vredmin_vs_h, int16_t, int16_t, H2, H2, DO_MIN, clearh) +GEN_VEXT_RED(vredmin_vs_w, int32_t, int32_t, H4, H4, DO_MIN, clearl) +GEN_VEXT_RED(vredmin_vs_d, int64_t, int64_t, H8, H8, DO_MIN, clearq) + +/* vd[0] = and(vs1[0], vs2[*]) */ +GEN_VEXT_RED(vredand_vs_b, int8_t, int8_t, H1, H1, DO_AND, clearb) +GEN_VEXT_RED(vredand_vs_h, int16_t, int16_t, H2, H2, DO_AND, clearh) +GEN_VEXT_RED(vredand_vs_w, int32_t, int32_t, H4, H4, DO_AND, clearl) +GEN_VEXT_RED(vredand_vs_d, int64_t, int64_t, H8, H8, DO_AND, clearq) + +/* vd[0] = or(vs1[0], vs2[*]) */ +GEN_VEXT_RED(vredor_vs_b, int8_t, int8_t, H1, H1, DO_OR, clearb) +GEN_VEXT_RED(vredor_vs_h, int16_t, int16_t, H2, H2, DO_OR, clearh) +GEN_VEXT_RED(vredor_vs_w, int32_t, int32_t, H4, H4, DO_OR, clearl) +GEN_VEXT_RED(vredor_vs_d, int64_t, int64_t, H8, H8, DO_OR, clearq) + +/* vd[0] = xor(vs1[0], vs2[*]) */ +GEN_VEXT_RED(vredxor_vs_b, int8_t, int8_t, H1, H1, DO_XOR, clearb) +GEN_VEXT_RED(vredxor_vs_h, int16_t, int16_t, H2, H2, DO_XOR, clearh) +GEN_VEXT_RED(vredxor_vs_w, int32_t, int32_t, H4, H4, DO_XOR, clearl) +GEN_VEXT_RED(vredxor_vs_d, int64_t, int64_t, H8, H8, DO_XOR, clearq) + +/* Vector Widening Integer Reduction Instructions */ +/* signed sum reduction into double-width accumulator */ +GEN_VEXT_RED(vwredsum_vs_b, int16_t, int8_t, H2, H1, DO_ADD, clearh) +GEN_VEXT_RED(vwredsum_vs_h, int32_t, int16_t, H4, H2, DO_ADD, clearl) +GEN_VEXT_RED(vwredsum_vs_w, int64_t, int32_t, H8, H4, DO_ADD, clearq) + +/* Unsigned sum reduction into double-width accumulator */ +GEN_VEXT_RED(vwredsumu_vs_b, uint16_t, uint8_t, H2, H1, DO_ADD, clearh) +GEN_VEXT_RED(vwredsumu_vs_h, uint32_t, uint16_t, H4, H2, DO_ADD, clearl) +GEN_VEXT_RED(vwredsumu_vs_w, uint64_t, uint32_t, H8, H4, DO_ADD, clearq) + +/* Vector Single-Width Floating-Point Reduction Instructions */ +#define GEN_VEXT_FRED(NAME, TD, TS2, HD, HS2, OP, CLEAR_FN)\ +void HELPER(NAME)(void *vd, void *v0, void *vs1, \ + void *vs2, CPURISCVState *env, \ + uint32_t desc) \ +{ \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vm = vext_vm(desc); \ + uint32_t vl = env->vl; \ + uint32_t i; \ + uint32_t tot = env_archcpu(env)->cfg.vlen / 8; \ + TD s1 = *((TD *)vs1 + HD(0)); \ + \ + for (i = 0; i < vl; i++) { \ + TS2 s2 = *((TS2 *)vs2 + HS2(i)); \ + if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + continue; \ + } \ + s1 = OP(s1, (TD)s2, &env->fp_status); \ + } \ + *((TD *)vd + HD(0)) = s1; \ + CLEAR_FN(vd, 1, sizeof(TD), tot); \ +} + +/* Unordered sum */ +GEN_VEXT_FRED(vfredsum_vs_h, uint16_t, uint16_t, H2, H2, float16_add, clearh) +GEN_VEXT_FRED(vfredsum_vs_w, uint32_t, uint32_t, H4, H4, float32_add, clearl) +GEN_VEXT_FRED(vfredsum_vs_d, uint64_t, uint64_t, H8, H8, float64_add, clearq) + +/* Maximum value */ +GEN_VEXT_FRED(vfredmax_vs_h, uint16_t, uint16_t, H2, H2, float16_maxnum, clearh) +GEN_VEXT_FRED(vfredmax_vs_w, uint32_t, uint32_t, H4, H4, float32_maxnum, clearl) +GEN_VEXT_FRED(vfredmax_vs_d, uint64_t, uint64_t, H8, H8, float64_maxnum, clearq) + +/* Minimum value */ +GEN_VEXT_FRED(vfredmin_vs_h, uint16_t, uint16_t, H2, H2, float16_minnum, clearh) +GEN_VEXT_FRED(vfredmin_vs_w, uint32_t, uint32_t, H4, H4, float32_minnum, clearl) +GEN_VEXT_FRED(vfredmin_vs_d, uint64_t, uint64_t, H8, H8, float64_minnum, clearq) + +/* Vector Widening Floating-Point Reduction Instructions */ +/* Unordered reduce 2*SEW = 2*SEW + sum(promote(SEW)) */ +void HELPER(vfwredsum_vs_h)(void *vd, void *v0, void *vs1, + void *vs2, CPURISCVState *env, uint32_t desc) +{ + uint32_t mlen = vext_mlen(desc); + uint32_t vm = vext_vm(desc); + uint32_t vl = env->vl; + uint32_t i; + uint32_t tot = env_archcpu(env)->cfg.vlen / 8; + uint32_t s1 = *((uint32_t *)vs1 + H4(0)); + + for (i = 0; i < vl; i++) { + uint16_t s2 = *((uint16_t *)vs2 + H2(i)); + if (!vm && !vext_elem_mask(v0, mlen, i)) { + continue; + } + s1 = float32_add(s1, float16_to_float32(s2, true, &env->fp_status), + &env->fp_status); + } + *((uint32_t *)vd + H4(0)) = s1; + clearl(vd, 1, sizeof(uint32_t), tot); +} + +void HELPER(vfwredsum_vs_w)(void *vd, void *v0, void *vs1, + void *vs2, CPURISCVState *env, uint32_t desc) +{ + uint32_t mlen = vext_mlen(desc); + uint32_t vm = vext_vm(desc); + uint32_t vl = env->vl; + uint32_t i; + uint32_t tot = env_archcpu(env)->cfg.vlen / 8; + uint64_t s1 = *((uint64_t *)vs1); + + for (i = 0; i < vl; i++) { + uint32_t s2 = *((uint32_t *)vs2 + H4(i)); + if (!vm && !vext_elem_mask(v0, mlen, i)) { + continue; + } + s1 = float64_add(s1, float32_to_float64(s2, &env->fp_status), + &env->fp_status); + } + *((uint64_t *)vd) = s1; + clearq(vd, 1, sizeof(uint64_t), tot); +} + +/* + *** Vector Mask Operations + */ +/* Vector Mask-Register Logical Instructions */ +#define GEN_VEXT_MASK_VV(NAME, OP) \ +void HELPER(NAME)(void *vd, void *v0, void *vs1, \ + void *vs2, CPURISCVState *env, \ + uint32_t desc) \ +{ \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vl = env->vl; \ + uint32_t i; \ + int a, b; \ + \ + for (i = 0; i < vl; i++) { \ + a = vext_elem_mask(vs1, mlen, i); \ + b = vext_elem_mask(vs2, mlen, i); \ + vext_set_elem_mask(vd, mlen, i, OP(b, a)); \ + } \ + for (; i < vlmax; i++) { \ + vext_set_elem_mask(vd, mlen, i, 0); \ + } \ +} + +#define DO_NAND(N, M) (!(N & M)) +#define DO_ANDNOT(N, M) (N & !M) +#define DO_NOR(N, M) (!(N | M)) +#define DO_ORNOT(N, M) (N | !M) +#define DO_XNOR(N, M) (!(N ^ M)) + +GEN_VEXT_MASK_VV(vmand_mm, DO_AND) +GEN_VEXT_MASK_VV(vmnand_mm, DO_NAND) +GEN_VEXT_MASK_VV(vmandnot_mm, DO_ANDNOT) +GEN_VEXT_MASK_VV(vmxor_mm, DO_XOR) +GEN_VEXT_MASK_VV(vmor_mm, DO_OR) +GEN_VEXT_MASK_VV(vmnor_mm, DO_NOR) +GEN_VEXT_MASK_VV(vmornot_mm, DO_ORNOT) +GEN_VEXT_MASK_VV(vmxnor_mm, DO_XNOR) + +/* Vector mask population count vmpopc */ +target_ulong HELPER(vmpopc_m)(void *v0, void *vs2, CPURISCVState *env, + uint32_t desc) +{ + target_ulong cnt = 0; + uint32_t mlen = vext_mlen(desc); + uint32_t vm = vext_vm(desc); + uint32_t vl = env->vl; + int i; + + for (i = 0; i < vl; i++) { + if (vm || vext_elem_mask(v0, mlen, i)) { + if (vext_elem_mask(vs2, mlen, i)) { + cnt++; + } + } + } + return cnt; +} + +/* vmfirst find-first-set mask bit*/ +target_ulong HELPER(vmfirst_m)(void *v0, void *vs2, CPURISCVState *env, + uint32_t desc) +{ + uint32_t mlen = vext_mlen(desc); + uint32_t vm = vext_vm(desc); + uint32_t vl = env->vl; + int i; + + for (i = 0; i < vl; i++) { + if (vm || vext_elem_mask(v0, mlen, i)) { + if (vext_elem_mask(vs2, mlen, i)) { + return i; + } + } + } + return -1LL; +} + +enum set_mask_type { + ONLY_FIRST = 1, + INCLUDE_FIRST, + BEFORE_FIRST, +}; + +static void vmsetm(void *vd, void *v0, void *vs2, CPURISCVState *env, + uint32_t desc, enum set_mask_type type) +{ + uint32_t mlen = vext_mlen(desc); + uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; + uint32_t vm = vext_vm(desc); + uint32_t vl = env->vl; + int i; + bool first_mask_bit = false; + + for (i = 0; i < vl; i++) { + if (!vm && !vext_elem_mask(v0, mlen, i)) { + continue; + } + /* write a zero to all following active elements */ + if (first_mask_bit) { + vext_set_elem_mask(vd, mlen, i, 0); + continue; + } + if (vext_elem_mask(vs2, mlen, i)) { + first_mask_bit = true; + if (type == BEFORE_FIRST) { + vext_set_elem_mask(vd, mlen, i, 0); + } else { + vext_set_elem_mask(vd, mlen, i, 1); + } + } else { + if (type == ONLY_FIRST) { + vext_set_elem_mask(vd, mlen, i, 0); + } else { + vext_set_elem_mask(vd, mlen, i, 1); + } + } + } + for (; i < vlmax; i++) { + vext_set_elem_mask(vd, mlen, i, 0); + } +} + +void HELPER(vmsbf_m)(void *vd, void *v0, void *vs2, CPURISCVState *env, + uint32_t desc) +{ + vmsetm(vd, v0, vs2, env, desc, BEFORE_FIRST); +} + +void HELPER(vmsif_m)(void *vd, void *v0, void *vs2, CPURISCVState *env, + uint32_t desc) +{ + vmsetm(vd, v0, vs2, env, desc, INCLUDE_FIRST); +} + +void HELPER(vmsof_m)(void *vd, void *v0, void *vs2, CPURISCVState *env, + uint32_t desc) +{ + vmsetm(vd, v0, vs2, env, desc, ONLY_FIRST); +} + +/* Vector Iota Instruction */ +#define GEN_VEXT_VIOTA_M(NAME, ETYPE, H, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, void *vs2, CPURISCVState *env, \ + uint32_t desc) \ +{ \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vm = vext_vm(desc); \ + uint32_t vl = env->vl; \ + uint32_t sum = 0; \ + int i; \ + \ + for (i = 0; i < vl; i++) { \ + if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + continue; \ + } \ + *((ETYPE *)vd + H(i)) = sum; \ + if (vext_elem_mask(vs2, mlen, i)) { \ + sum++; \ + } \ + } \ + CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE)); \ +} + +GEN_VEXT_VIOTA_M(viota_m_b, uint8_t, H1, clearb) +GEN_VEXT_VIOTA_M(viota_m_h, uint16_t, H2, clearh) +GEN_VEXT_VIOTA_M(viota_m_w, uint32_t, H4, clearl) +GEN_VEXT_VIOTA_M(viota_m_d, uint64_t, H8, clearq) + +/* Vector Element Index Instruction */ +#define GEN_VEXT_VID_V(NAME, ETYPE, H, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vm = vext_vm(desc); \ + uint32_t vl = env->vl; \ + int i; \ + \ + for (i = 0; i < vl; i++) { \ + if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + continue; \ + } \ + *((ETYPE *)vd + H(i)) = i; \ + } \ + CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE)); \ +} + +GEN_VEXT_VID_V(vid_v_b, uint8_t, H1, clearb) +GEN_VEXT_VID_V(vid_v_h, uint16_t, H2, clearh) +GEN_VEXT_VID_V(vid_v_w, uint32_t, H4, clearl) +GEN_VEXT_VID_V(vid_v_d, uint64_t, H8, clearq) + +/* + *** Vector Permutation Instructions + */ + +/* Vector Slide Instructions */ +#define GEN_VEXT_VSLIDEUP_VX(NAME, ETYPE, H, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vm = vext_vm(desc); \ + uint32_t vl = env->vl; \ + target_ulong offset = s1, i; \ + \ + for (i = offset; i < vl; i++) { \ + if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + continue; \ + } \ + *((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(i - offset)); \ + } \ + CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE)); \ +} + +/* vslideup.vx vd, vs2, rs1, vm # vd[i+rs1] = vs2[i] */ +GEN_VEXT_VSLIDEUP_VX(vslideup_vx_b, uint8_t, H1, clearb) +GEN_VEXT_VSLIDEUP_VX(vslideup_vx_h, uint16_t, H2, clearh) +GEN_VEXT_VSLIDEUP_VX(vslideup_vx_w, uint32_t, H4, clearl) +GEN_VEXT_VSLIDEUP_VX(vslideup_vx_d, uint64_t, H8, clearq) + +#define GEN_VEXT_VSLIDEDOWN_VX(NAME, ETYPE, H, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vm = vext_vm(desc); \ + uint32_t vl = env->vl; \ + target_ulong offset = s1, i; \ + \ + for (i = 0; i < vl; ++i) { \ + target_ulong j = i + offset; \ + if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + continue; \ + } \ + *((ETYPE *)vd + H(i)) = j >= vlmax ? 0 : *((ETYPE *)vs2 + H(j)); \ + } \ + CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE)); \ +} + +/* vslidedown.vx vd, vs2, rs1, vm # vd[i] = vs2[i+rs1] */ +GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_b, uint8_t, H1, clearb) +GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_h, uint16_t, H2, clearh) +GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_w, uint32_t, H4, clearl) +GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_d, uint64_t, H8, clearq) + +#define GEN_VEXT_VSLIDE1UP_VX(NAME, ETYPE, H, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vm = vext_vm(desc); \ + uint32_t vl = env->vl; \ + uint32_t i; \ + \ + for (i = 0; i < vl; i++) { \ + if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + continue; \ + } \ + if (i == 0) { \ + *((ETYPE *)vd + H(i)) = s1; \ + } else { \ + *((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(i - 1)); \ + } \ + } \ + CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE)); \ +} + +/* vslide1up.vx vd, vs2, rs1, vm # vd[0]=x[rs1], vd[i+1] = vs2[i] */ +GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_b, uint8_t, H1, clearb) +GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_h, uint16_t, H2, clearh) +GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_w, uint32_t, H4, clearl) +GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_d, uint64_t, H8, clearq) + +#define GEN_VEXT_VSLIDE1DOWN_VX(NAME, ETYPE, H, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vm = vext_vm(desc); \ + uint32_t vl = env->vl; \ + uint32_t i; \ + \ + for (i = 0; i < vl; i++) { \ + if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + continue; \ + } \ + if (i == vl - 1) { \ + *((ETYPE *)vd + H(i)) = s1; \ + } else { \ + *((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(i + 1)); \ + } \ + } \ + CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE)); \ +} + +/* vslide1down.vx vd, vs2, rs1, vm # vd[i] = vs2[i+1], vd[vl-1]=x[rs1] */ +GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_b, uint8_t, H1, clearb) +GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_h, uint16_t, H2, clearh) +GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_w, uint32_t, H4, clearl) +GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_d, uint64_t, H8, clearq) + +/* Vector Register Gather Instruction */ +#define GEN_VEXT_VRGATHER_VV(NAME, ETYPE, H, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vm = vext_vm(desc); \ + uint32_t vl = env->vl; \ + uint64_t index; \ + uint32_t i; \ + \ + for (i = 0; i < vl; i++) { \ + if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + continue; \ + } \ + index = *((ETYPE *)vs1 + H(i)); \ + if (index >= vlmax) { \ + *((ETYPE *)vd + H(i)) = 0; \ + } else { \ + *((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(index)); \ + } \ + } \ + CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE)); \ +} + +/* vd[i] = (vs1[i] >= VLMAX) ? 0 : vs2[vs1[i]]; */ +GEN_VEXT_VRGATHER_VV(vrgather_vv_b, uint8_t, H1, clearb) +GEN_VEXT_VRGATHER_VV(vrgather_vv_h, uint16_t, H2, clearh) +GEN_VEXT_VRGATHER_VV(vrgather_vv_w, uint32_t, H4, clearl) +GEN_VEXT_VRGATHER_VV(vrgather_vv_d, uint64_t, H8, clearq) + +#define GEN_VEXT_VRGATHER_VX(NAME, ETYPE, H, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vm = vext_vm(desc); \ + uint32_t vl = env->vl; \ + uint64_t index = s1; \ + uint32_t i; \ + \ + for (i = 0; i < vl; i++) { \ + if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + continue; \ + } \ + if (index >= vlmax) { \ + *((ETYPE *)vd + H(i)) = 0; \ + } else { \ + *((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(index)); \ + } \ + } \ + CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE)); \ +} + +/* vd[i] = (x[rs1] >= VLMAX) ? 0 : vs2[rs1] */ +GEN_VEXT_VRGATHER_VX(vrgather_vx_b, uint8_t, H1, clearb) +GEN_VEXT_VRGATHER_VX(vrgather_vx_h, uint16_t, H2, clearh) +GEN_VEXT_VRGATHER_VX(vrgather_vx_w, uint32_t, H4, clearl) +GEN_VEXT_VRGATHER_VX(vrgather_vx_d, uint64_t, H8, clearq) + +/* Vector Compress Instruction */ +#define GEN_VEXT_VCOMPRESS_VM(NAME, ETYPE, H, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vl = env->vl; \ + uint32_t num = 0, i; \ + \ + for (i = 0; i < vl; i++) { \ + if (!vext_elem_mask(vs1, mlen, i)) { \ + continue; \ + } \ + *((ETYPE *)vd + H(num)) = *((ETYPE *)vs2 + H(i)); \ + num++; \ + } \ + CLEAR_FN(vd, num, num * sizeof(ETYPE), vlmax * sizeof(ETYPE)); \ +} + +/* Compress into vd elements of vs2 where vs1 is enabled */ +GEN_VEXT_VCOMPRESS_VM(vcompress_vm_b, uint8_t, H1, clearb) +GEN_VEXT_VCOMPRESS_VM(vcompress_vm_h, uint16_t, H2, clearh) +GEN_VEXT_VCOMPRESS_VM(vcompress_vm_w, uint32_t, H4, clearl) +GEN_VEXT_VCOMPRESS_VM(vcompress_vm_d, uint64_t, H8, clearq) |