diff --git a/hw/char/Kconfig b/hw/char/Kconfig index 2e4f620b13..6b6cf2fc1d 100644 --- a/hw/char/Kconfig +++ b/hw/char/Kconfig @@ -68,3 +68,6 @@ config SIFIVE_UART config GOLDFISH_TTY bool + +config SHAKTI_UART + bool diff --git a/hw/char/meson.build b/hw/char/meson.build index 8361d0ab28..7b594f51b8 100644 --- a/hw/char/meson.build +++ b/hw/char/meson.build @@ -16,7 +16,7 @@ softmmu_ss.add(when: 'CONFIG_SERIAL', if_true: files('serial.c')) softmmu_ss.add(when: 'CONFIG_SERIAL_ISA', if_true: files('serial-isa.c')) softmmu_ss.add(when: 'CONFIG_SERIAL_PCI', if_true: files('serial-pci.c')) softmmu_ss.add(when: 'CONFIG_SERIAL_PCI_MULTI', if_true: files('serial-pci-multi.c')) -softmmu_ss.add(when: 'CONFIG_SHAKTI', if_true: files('shakti_uart.c')) +softmmu_ss.add(when: 'CONFIG_SHAKTI_UART', if_true: files('shakti_uart.c')) softmmu_ss.add(when: 'CONFIG_VIRTIO_SERIAL', if_true: files('virtio-console.c')) softmmu_ss.add(when: 'CONFIG_XEN', if_true: files('xen_console.c')) softmmu_ss.add(when: 'CONFIG_XILINX', if_true: files('xilinx_uartlite.c')) diff --git a/hw/core/register.c b/hw/core/register.c index d6f8c20816..95b0150c0a 100644 --- a/hw/core/register.c +++ b/hw/core/register.c @@ -300,6 +300,18 @@ RegisterInfoArray *register_init_block32(DeviceState *owner, data, ops, debug_enabled, memory_size, 32); } +RegisterInfoArray *register_init_block64(DeviceState *owner, + const RegisterAccessInfo *rae, + int num, RegisterInfo *ri, + uint64_t *data, + const MemoryRegionOps *ops, + bool debug_enabled, + uint64_t memory_size) +{ + return register_init_block(owner, rae, num, ri, (void *) + data, ops, debug_enabled, memory_size, 64); +} + void register_finalize_block(RegisterInfoArray *r_array) { object_unparent(OBJECT(&r_array->mem)); diff --git a/hw/intc/sifive_clint.c b/hw/intc/sifive_clint.c index 0f41e5ea1c..99c870ced2 100644 --- a/hw/intc/sifive_clint.c +++ b/hw/intc/sifive_clint.c @@ -59,8 +59,29 @@ static void sifive_clint_write_timecmp(RISCVCPU *cpu, uint64_t value, riscv_cpu_update_mip(cpu, MIP_MTIP, BOOL_TO_MASK(0)); diff = cpu->env.timecmp - rtc_r; /* back to ns (note args switched in muldiv64) */ - next = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + - muldiv64(diff, NANOSECONDS_PER_SECOND, timebase_freq); + uint64_t ns_diff = muldiv64(diff, NANOSECONDS_PER_SECOND, timebase_freq); + + /* + * check if ns_diff overflowed and check if the addition would potentially + * overflow + */ + if ((NANOSECONDS_PER_SECOND > timebase_freq && ns_diff < diff) || + ns_diff > INT64_MAX) { + next = INT64_MAX; + } else { + /* + * as it is very unlikely qemu_clock_get_ns will return a value + * greater than INT64_MAX, no additional check is needed for an + * unsigned integer overflow. + */ + next = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + ns_diff; + /* + * if ns_diff is INT64_MAX next may still be outside the range + * of a signed integer. + */ + next = MIN(next, INT64_MAX); + } + timer_mod(cpu->env.timer, next); } diff --git a/hw/riscv/Kconfig b/hw/riscv/Kconfig index 0590f443fd..ff75add6f3 100644 --- a/hw/riscv/Kconfig +++ b/hw/riscv/Kconfig @@ -22,13 +22,10 @@ config OPENTITAN select IBEX select UNIMP -config SHAKTI - bool - config SHAKTI_C bool select UNIMP - select SHAKTI + select SHAKTI_UART select SIFIVE_CLINT select SIFIVE_PLIC diff --git a/hw/riscv/virt.c b/hw/riscv/virt.c index 0e55411045..5624adda58 100644 --- a/hw/riscv/virt.c +++ b/hw/riscv/virt.c @@ -454,7 +454,7 @@ static void create_fdt(RISCVVirtState *s, const MemMapEntry *memmap, qemu_fdt_setprop_cell(fdt, name, "interrupts", RTC_IRQ); g_free(name); - name = g_strdup_printf("/soc/flash@%" PRIx64, flashbase); + name = g_strdup_printf("/flash@%" PRIx64, flashbase); qemu_fdt_add_subnode(mc->fdt, name); qemu_fdt_setprop_string(mc->fdt, name, "compatible", "cfi-flash"); qemu_fdt_setprop_sized_cells(mc->fdt, name, "reg", @@ -540,6 +540,24 @@ static FWCfgState *create_fw_cfg(const MachineState *mc) return fw_cfg; } +/* + * Return the per-socket PLIC hart topology configuration string + * (caller must free with g_free()) + */ +static char *plic_hart_config_string(int hart_count) +{ + g_autofree const char **vals = g_new(const char *, hart_count + 1); + int i; + + for (i = 0; i < hart_count; i++) { + vals[i] = VIRT_PLIC_HART_CONFIG; + } + vals[i] = NULL; + + /* g_strjoinv() obliges us to cast away const here */ + return g_strjoinv(",", (char **)vals); +} + static void virt_machine_init(MachineState *machine) { const MemMapEntry *memmap = virt_memmap; @@ -548,13 +566,12 @@ static void virt_machine_init(MachineState *machine) MemoryRegion *main_mem = g_new(MemoryRegion, 1); MemoryRegion *mask_rom = g_new(MemoryRegion, 1); char *plic_hart_config, *soc_name; - size_t plic_hart_config_len; target_ulong start_addr = memmap[VIRT_DRAM].base; target_ulong firmware_end_addr, kernel_start_addr; uint32_t fdt_load_addr; uint64_t kernel_entry; DeviceState *mmio_plic, *virtio_plic, *pcie_plic; - int i, j, base_hartid, hart_count; + int i, base_hartid, hart_count; /* Check socket count limit */ if (VIRT_SOCKETS_MAX < riscv_socket_count(machine)) { @@ -603,17 +620,7 @@ static void virt_machine_init(MachineState *machine) SIFIVE_CLINT_TIMEBASE_FREQ, true); /* Per-socket PLIC hart topology configuration string */ - plic_hart_config_len = - (strlen(VIRT_PLIC_HART_CONFIG) + 1) * hart_count; - plic_hart_config = g_malloc0(plic_hart_config_len); - for (j = 0; j < hart_count; j++) { - if (j != 0) { - strncat(plic_hart_config, ",", plic_hart_config_len); - } - strncat(plic_hart_config, VIRT_PLIC_HART_CONFIG, - plic_hart_config_len); - plic_hart_config_len -= (strlen(VIRT_PLIC_HART_CONFIG) + 1); - } + plic_hart_config = plic_hart_config_string(hart_count); /* Per-socket PLIC */ s->plic[i] = sifive_plic_create( diff --git a/include/hw/register.h b/include/hw/register.h index b480e3882c..6a076cfcdf 100644 --- a/include/hw/register.h +++ b/include/hw/register.h @@ -204,6 +204,14 @@ RegisterInfoArray *register_init_block32(DeviceState *owner, bool debug_enabled, uint64_t memory_size); +RegisterInfoArray *register_init_block64(DeviceState *owner, + const RegisterAccessInfo *rae, + int num, RegisterInfo *ri, + uint64_t *data, + const MemoryRegionOps *ops, + bool debug_enabled, + uint64_t memory_size); + /** * This function should be called to cleanup the registers that were initialized * when calling register_init_block32(). This function should only be called diff --git a/include/hw/registerfields.h b/include/hw/registerfields.h index 93fa4a84c2..f2a3c9c41f 100644 --- a/include/hw/registerfields.h +++ b/include/hw/registerfields.h @@ -30,6 +30,10 @@ enum { A_ ## reg = (addr) }; \ enum { R_ ## reg = (addr) / 2 }; +#define REG64(reg, addr) \ + enum { A_ ## reg = (addr) }; \ + enum { R_ ## reg = (addr) / 8 }; + /* Define SHIFT, LENGTH and MASK constants for a field within a register */ /* This macro will define R_FOO_BAR_MASK, R_FOO_BAR_SHIFT and R_FOO_BAR_LENGTH @@ -58,6 +62,8 @@ /* Extract a field from an array of registers */ #define ARRAY_FIELD_EX32(regs, reg, field) \ FIELD_EX32((regs)[R_ ## reg], reg, field) +#define ARRAY_FIELD_EX64(regs, reg, field) \ + FIELD_EX64((regs)[R_ ## reg], reg, field) /* Deposit a register field. * Assigning values larger then the target field will result in @@ -89,7 +95,7 @@ _d; }) #define FIELD_DP64(storage, reg, field, val) ({ \ struct { \ - unsigned int v:R_ ## reg ## _ ## field ## _LENGTH; \ + uint64_t v:R_ ## reg ## _ ## field ## _LENGTH; \ } _v = { .v = val }; \ uint64_t _d; \ _d = deposit64((storage), R_ ## reg ## _ ## field ## _SHIFT, \ @@ -99,5 +105,7 @@ /* Deposit a field to array of registers. */ #define ARRAY_FIELD_DP32(regs, reg, field, val) \ (regs)[R_ ## reg] = FIELD_DP32((regs)[R_ ## reg], reg, field, val); +#define ARRAY_FIELD_DP64(regs, reg, field, val) \ + (regs)[R_ ## reg] = FIELD_DP64((regs)[R_ ## reg], reg, field, val); #endif diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c index 991a6bb760..1a2b03d579 100644 --- a/target/riscv/cpu.c +++ b/target/riscv/cpu.c @@ -392,9 +392,7 @@ static void riscv_cpu_realize(DeviceState *dev, Error **errp) RISCVCPU *cpu = RISCV_CPU(dev); CPURISCVState *env = &cpu->env; RISCVCPUClass *mcc = RISCV_CPU_GET_CLASS(dev); - int priv_version = PRIV_VERSION_1_11_0; - int bext_version = BEXT_VERSION_0_93_0; - int vext_version = VEXT_VERSION_0_07_1; + int priv_version = 0; target_ulong target_misa = env->misa; Error *local_err = NULL; @@ -417,9 +415,11 @@ static void riscv_cpu_realize(DeviceState *dev, Error **errp) } } - set_priv_version(env, priv_version); - set_bext_version(env, bext_version); - set_vext_version(env, vext_version); + 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); @@ -497,6 +497,7 @@ static void riscv_cpu_realize(DeviceState *dev, Error **errp) target_misa |= RVH; } if (cpu->cfg.ext_b) { + int bext_version = BEXT_VERSION_0_93_0; target_misa |= RVB; if (cpu->cfg.bext_spec) { @@ -515,6 +516,7 @@ static void riscv_cpu_realize(DeviceState *dev, Error **errp) set_bext_version(env, bext_version); } if (cpu->cfg.ext_v) { + int vext_version = VEXT_VERSION_0_07_1; target_misa |= RVV; if (!is_power_of_2(cpu->cfg.vlen)) { error_setg(errp, diff --git a/target/riscv/csr.c b/target/riscv/csr.c index 9a4ed18ac5..50a2c3a3b4 100644 --- a/target/riscv/csr.c +++ b/target/riscv/csr.c @@ -937,9 +937,12 @@ static RISCVException rmw_vsip(CPURISCVState *env, int csrno, /* 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); - *ret_value &= VS_MODE_INTERRUPTS; - /* Shift the VS bits to their S bit location in vsip */ - *ret_value >>= 1; + + if (ret_value) { + *ret_value &= VS_MODE_INTERRUPTS; + /* Shift the VS bits to their S bit location in vsip */ + *ret_value >>= 1; + } return ret; } @@ -956,7 +959,9 @@ static RISCVException rmw_sip(CPURISCVState *env, int csrno, write_mask & env->mideleg & sip_writable_mask); } - *ret_value &= env->mideleg; + if (ret_value) { + *ret_value &= env->mideleg; + } return ret; } @@ -1072,8 +1077,9 @@ static RISCVException rmw_hvip(CPURISCVState *env, int csrno, int ret = rmw_mip(env, 0, ret_value, new_value, write_mask & hvip_writable_mask); - *ret_value &= hvip_writable_mask; - + if (ret_value) { + *ret_value &= hvip_writable_mask; + } return ret; } @@ -1084,8 +1090,9 @@ static RISCVException rmw_hip(CPURISCVState *env, int csrno, int ret = rmw_mip(env, 0, ret_value, new_value, write_mask & hip_writable_mask); - *ret_value &= hip_writable_mask; - + if (ret_value) { + *ret_value &= hip_writable_mask; + } return ret; } @@ -1117,17 +1124,12 @@ static RISCVException write_hcounteren(CPURISCVState *env, int csrno, return RISCV_EXCP_NONE; } -static RISCVException read_hgeie(CPURISCVState *env, int csrno, - target_ulong *val) -{ - qemu_log_mask(LOG_UNIMP, "No support for a non-zero GEILEN."); - return RISCV_EXCP_NONE; -} - static RISCVException write_hgeie(CPURISCVState *env, int csrno, target_ulong val) { - qemu_log_mask(LOG_UNIMP, "No support for a non-zero GEILEN."); + if (val) { + qemu_log_mask(LOG_UNIMP, "No support for a non-zero GEILEN."); + } return RISCV_EXCP_NONE; } @@ -1158,17 +1160,12 @@ static RISCVException write_htinst(CPURISCVState *env, int csrno, return RISCV_EXCP_NONE; } -static RISCVException read_hgeip(CPURISCVState *env, int csrno, - target_ulong *val) -{ - qemu_log_mask(LOG_UNIMP, "No support for a non-zero GEILEN."); - return RISCV_EXCP_NONE; -} - static RISCVException write_hgeip(CPURISCVState *env, int csrno, target_ulong val) { - qemu_log_mask(LOG_UNIMP, "No support for a non-zero GEILEN."); + if (val) { + qemu_log_mask(LOG_UNIMP, "No support for a non-zero GEILEN."); + } return RISCV_EXCP_NONE; } @@ -1422,11 +1419,11 @@ RISCVException riscv_csrrw(CPURISCVState *env, int csrno, RISCVException ret; target_ulong old_value; RISCVCPU *cpu = env_archcpu(env); + int read_only = get_field(csrno, 0xC00) == 3; - /* check privileges and return -1 if check fails */ + /* check privileges and return RISCV_EXCP_ILLEGAL_INST if check fails */ #if !defined(CONFIG_USER_ONLY) int effective_priv = env->priv; - int read_only = get_field(csrno, 0xC00) == 3; if (riscv_has_ext(env, RVH) && env->priv == PRV_S && @@ -1439,11 +1436,13 @@ RISCVException riscv_csrrw(CPURISCVState *env, int csrno, effective_priv++; } - if ((write_mask && read_only) || - (!env->debugger && (effective_priv < get_field(csrno, 0x300)))) { + 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) { @@ -1592,10 +1591,10 @@ riscv_csr_operations csr_ops[CSR_TABLE_SIZE] = { [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_hgeie, write_hgeie }, + [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_hgeip, write_hgeip }, + [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 }, diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 415e37bc37..460eee9988 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -65,9 +65,9 @@ DEF_HELPER_FLAGS_2(gorc, TCG_CALL_NO_RWG_SE, tl, tl, tl) DEF_HELPER_FLAGS_2(gorcw, TCG_CALL_NO_RWG_SE, tl, tl, tl) /* Special functions */ -DEF_HELPER_3(csrrw, tl, env, tl, tl) -DEF_HELPER_4(csrrs, tl, env, tl, tl, tl) -DEF_HELPER_4(csrrc, tl, env, tl, tl, tl) +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) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index f09f8d5faf..2cd921d51c 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -42,6 +42,7 @@ &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 diff --git a/target/riscv/insn_trans/trans_rva.c.inc b/target/riscv/insn_trans/trans_rva.c.inc index ab2ec4f0a5..6ea07d89b0 100644 --- a/target/riscv/insn_trans/trans_rva.c.inc +++ b/target/riscv/insn_trans/trans_rva.c.inc @@ -18,11 +18,10 @@ * this program. If not, see . */ -static inline bool gen_lr(DisasContext *ctx, arg_atomic *a, MemOp mop) +static bool gen_lr(DisasContext *ctx, arg_atomic *a, MemOp mop) { - TCGv src1 = tcg_temp_new(); - /* Put addr in load_res, data in load_val. */ - gen_get_gpr(src1, a->rs1); + TCGv src1 = get_gpr(ctx, a->rs1, EXT_ZERO); + if (a->rl) { tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL); } @@ -30,33 +29,33 @@ static inline bool gen_lr(DisasContext *ctx, arg_atomic *a, MemOp mop) if (a->aq) { tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); } - tcg_gen_mov_tl(load_res, src1); - gen_set_gpr(a->rd, load_val); - tcg_temp_free(src1); + /* 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 inline bool gen_sc(DisasContext *ctx, arg_atomic *a, MemOp mop) +static bool gen_sc(DisasContext *ctx, arg_atomic *a, MemOp mop) { - TCGv src1 = tcg_temp_new(); - TCGv src2 = tcg_temp_new(); - TCGv dat = tcg_temp_new(); + TCGv dest, src1, src2; TCGLabel *l1 = gen_new_label(); TCGLabel *l2 = gen_new_label(); - gen_get_gpr(src1, a->rs1); + src1 = get_gpr(ctx, a->rs1, EXT_ZERO); tcg_gen_brcond_tl(TCG_COND_NE, load_res, src1, l1); - gen_get_gpr(src2, a->rs2); /* * Note that the TCG atomic primitives are SC, * so we can ignore AQ/RL along this path. */ - tcg_gen_atomic_cmpxchg_tl(src1, load_res, load_val, src2, + 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, dat, src1, load_val); - gen_set_gpr(a->rd, dat); + 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); @@ -65,8 +64,7 @@ static inline bool gen_sc(DisasContext *ctx, arg_atomic *a, MemOp mop) * provide the memory barrier implied by AQ/RL. */ tcg_gen_mb(TCG_MO_ALL + a->aq * TCG_BAR_LDAQ + a->rl * TCG_BAR_STRL); - tcg_gen_movi_tl(dat, 1); - gen_set_gpr(a->rd, dat); + gen_set_gpr(ctx, a->rd, tcg_constant_tl(1)); gen_set_label(l2); /* @@ -75,9 +73,6 @@ static inline bool gen_sc(DisasContext *ctx, arg_atomic *a, MemOp mop) */ tcg_gen_movi_tl(load_res, -1); - tcg_temp_free(dat); - tcg_temp_free(src1); - tcg_temp_free(src2); return true; } @@ -85,17 +80,13 @@ static bool gen_amo(DisasContext *ctx, arg_atomic *a, void(*func)(TCGv, TCGv, TCGv, TCGArg, MemOp), MemOp mop) { - TCGv src1 = tcg_temp_new(); - TCGv src2 = tcg_temp_new(); + 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); - gen_get_gpr(src1, a->rs1); - gen_get_gpr(src2, a->rs2); + func(dest, src1, src2, ctx->mem_idx, mop); - (*func)(src2, src1, src2, ctx->mem_idx, mop); - - gen_set_gpr(a->rd, src2); - tcg_temp_free(src1); - tcg_temp_free(src2); + gen_set_gpr(ctx, a->rd, dest); return true; } diff --git a/target/riscv/insn_trans/trans_rvb.c.inc b/target/riscv/insn_trans/trans_rvb.c.inc index 9e81f6e3de..b72e76255c 100644 --- a/target/riscv/insn_trans/trans_rvb.c.inc +++ b/target/riscv/insn_trans/trans_rvb.c.inc @@ -17,422 +17,632 @@ * this program. If not, see . */ + +static void gen_clz(TCGv ret, TCGv arg1) +{ + tcg_gen_clzi_tl(ret, arg1, TARGET_LONG_BITS); +} + static bool trans_clz(DisasContext *ctx, arg_clz *a) { REQUIRE_EXT(ctx, RVB); - return gen_unary(ctx, a, gen_clz); + return gen_unary(ctx, a, EXT_ZERO, gen_clz); +} + +static void gen_ctz(TCGv ret, TCGv arg1) +{ + tcg_gen_ctzi_tl(ret, arg1, TARGET_LONG_BITS); } static bool trans_ctz(DisasContext *ctx, arg_ctz *a) { REQUIRE_EXT(ctx, RVB); - return gen_unary(ctx, a, gen_ctz); + return gen_unary(ctx, a, EXT_ZERO, gen_ctz); } static bool trans_cpop(DisasContext *ctx, arg_cpop *a) { REQUIRE_EXT(ctx, RVB); - return gen_unary(ctx, a, tcg_gen_ctpop_tl); + return gen_unary(ctx, a, EXT_ZERO, tcg_gen_ctpop_tl); } static bool trans_andn(DisasContext *ctx, arg_andn *a) { REQUIRE_EXT(ctx, RVB); - return gen_arith(ctx, a, tcg_gen_andc_tl); + return gen_arith(ctx, a, EXT_NONE, tcg_gen_andc_tl); } static bool trans_orn(DisasContext *ctx, arg_orn *a) { REQUIRE_EXT(ctx, RVB); - return gen_arith(ctx, a, tcg_gen_orc_tl); + return gen_arith(ctx, a, EXT_NONE, tcg_gen_orc_tl); } static bool trans_xnor(DisasContext *ctx, arg_xnor *a) { REQUIRE_EXT(ctx, RVB); - return gen_arith(ctx, a, tcg_gen_eqv_tl); + return gen_arith(ctx, a, EXT_NONE, tcg_gen_eqv_tl); +} + +static void gen_pack(TCGv ret, TCGv arg1, TCGv arg2) +{ + tcg_gen_deposit_tl(ret, arg1, arg2, + TARGET_LONG_BITS / 2, + TARGET_LONG_BITS / 2); } static bool trans_pack(DisasContext *ctx, arg_pack *a) { REQUIRE_EXT(ctx, RVB); - return gen_arith(ctx, a, gen_pack); + return gen_arith(ctx, a, EXT_NONE, gen_pack); +} + +static void gen_packu(TCGv ret, TCGv arg1, TCGv arg2) +{ + TCGv t = tcg_temp_new(); + tcg_gen_shri_tl(t, arg1, TARGET_LONG_BITS / 2); + tcg_gen_deposit_tl(ret, arg2, t, 0, TARGET_LONG_BITS / 2); + tcg_temp_free(t); } static bool trans_packu(DisasContext *ctx, arg_packu *a) { REQUIRE_EXT(ctx, RVB); - return gen_arith(ctx, a, gen_packu); + return gen_arith(ctx, a, EXT_NONE, gen_packu); +} + +static void gen_packh(TCGv ret, TCGv arg1, TCGv arg2) +{ + TCGv t = tcg_temp_new(); + tcg_gen_ext8u_tl(t, arg2); + tcg_gen_deposit_tl(ret, arg1, t, 8, TARGET_LONG_BITS - 8); + tcg_temp_free(t); } static bool trans_packh(DisasContext *ctx, arg_packh *a) { REQUIRE_EXT(ctx, RVB); - return gen_arith(ctx, a, gen_packh); + return gen_arith(ctx, a, EXT_NONE, gen_packh); } static bool trans_min(DisasContext *ctx, arg_min *a) { REQUIRE_EXT(ctx, RVB); - return gen_arith(ctx, a, tcg_gen_smin_tl); + return gen_arith(ctx, a, EXT_SIGN, tcg_gen_smin_tl); } static bool trans_max(DisasContext *ctx, arg_max *a) { REQUIRE_EXT(ctx, RVB); - return gen_arith(ctx, a, tcg_gen_smax_tl); + return gen_arith(ctx, a, EXT_SIGN, tcg_gen_smax_tl); } static bool trans_minu(DisasContext *ctx, arg_minu *a) { REQUIRE_EXT(ctx, RVB); - return gen_arith(ctx, a, tcg_gen_umin_tl); + return gen_arith(ctx, a, EXT_SIGN, tcg_gen_umin_tl); } static bool trans_maxu(DisasContext *ctx, arg_maxu *a) { REQUIRE_EXT(ctx, RVB); - return gen_arith(ctx, a, tcg_gen_umax_tl); + return gen_arith(ctx, a, EXT_SIGN, tcg_gen_umax_tl); } static bool trans_sext_b(DisasContext *ctx, arg_sext_b *a) { REQUIRE_EXT(ctx, RVB); - return gen_unary(ctx, a, tcg_gen_ext8s_tl); + return gen_unary(ctx, a, EXT_NONE, tcg_gen_ext8s_tl); } static bool trans_sext_h(DisasContext *ctx, arg_sext_h *a) { REQUIRE_EXT(ctx, RVB); - return gen_unary(ctx, a, tcg_gen_ext16s_tl); + 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_EXT(ctx, RVB); - return gen_shift(ctx, a, gen_bset); + return gen_shift(ctx, a, EXT_NONE, gen_bset); } static bool trans_bseti(DisasContext *ctx, arg_bseti *a) { REQUIRE_EXT(ctx, RVB); - return gen_shifti(ctx, a, gen_bset); + 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_EXT(ctx, RVB); - return gen_shift(ctx, a, gen_bclr); + return gen_shift(ctx, a, EXT_NONE, gen_bclr); } static bool trans_bclri(DisasContext *ctx, arg_bclri *a) { REQUIRE_EXT(ctx, RVB); - return gen_shifti(ctx, a, gen_bclr); + 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_EXT(ctx, RVB); - return gen_shift(ctx, a, gen_binv); + return gen_shift(ctx, a, EXT_NONE, gen_binv); } static bool trans_binvi(DisasContext *ctx, arg_binvi *a) { REQUIRE_EXT(ctx, RVB); - return gen_shifti(ctx, a, gen_binv); + 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_EXT(ctx, RVB); - return gen_shift(ctx, a, gen_bext); + return gen_shift(ctx, a, EXT_NONE, gen_bext); } static bool trans_bexti(DisasContext *ctx, arg_bexti *a) { REQUIRE_EXT(ctx, RVB); - return gen_shifti(ctx, a, gen_bext); + return gen_shift_imm_tl(ctx, a, EXT_NONE, gen_bext); +} + +static void gen_slo(TCGv ret, TCGv arg1, TCGv arg2) +{ + tcg_gen_not_tl(ret, arg1); + tcg_gen_shl_tl(ret, ret, arg2); + tcg_gen_not_tl(ret, ret); } static bool trans_slo(DisasContext *ctx, arg_slo *a) { REQUIRE_EXT(ctx, RVB); - return gen_shift(ctx, a, gen_slo); + return gen_shift(ctx, a, EXT_NONE, gen_slo); } static bool trans_sloi(DisasContext *ctx, arg_sloi *a) { REQUIRE_EXT(ctx, RVB); - return gen_shifti(ctx, a, gen_slo); + return gen_shift_imm_tl(ctx, a, EXT_NONE, gen_slo); +} + +static void gen_sro(TCGv ret, TCGv arg1, TCGv arg2) +{ + tcg_gen_not_tl(ret, arg1); + tcg_gen_shr_tl(ret, ret, arg2); + tcg_gen_not_tl(ret, ret); } static bool trans_sro(DisasContext *ctx, arg_sro *a) { REQUIRE_EXT(ctx, RVB); - return gen_shift(ctx, a, gen_sro); + return gen_shift(ctx, a, EXT_ZERO, gen_sro); } static bool trans_sroi(DisasContext *ctx, arg_sroi *a) { REQUIRE_EXT(ctx, RVB); - return gen_shifti(ctx, a, gen_sro); + return gen_shift_imm_tl(ctx, a, EXT_ZERO, gen_sro); } static bool trans_ror(DisasContext *ctx, arg_ror *a) { REQUIRE_EXT(ctx, RVB); - return gen_shift(ctx, a, tcg_gen_rotr_tl); + return gen_shift(ctx, a, EXT_NONE, tcg_gen_rotr_tl); } static bool trans_rori(DisasContext *ctx, arg_rori *a) { REQUIRE_EXT(ctx, RVB); - return gen_shifti(ctx, a, tcg_gen_rotr_tl); + return gen_shift_imm_fn(ctx, a, EXT_NONE, tcg_gen_rotri_tl); } static bool trans_rol(DisasContext *ctx, arg_rol *a) { REQUIRE_EXT(ctx, RVB); - return gen_shift(ctx, a, tcg_gen_rotl_tl); + return gen_shift(ctx, a, EXT_NONE, tcg_gen_rotl_tl); } static bool trans_grev(DisasContext *ctx, arg_grev *a) { REQUIRE_EXT(ctx, RVB); - return gen_shift(ctx, a, gen_helper_grev); + return gen_shift(ctx, a, EXT_NONE, gen_helper_grev); +} + +static void gen_grevi(TCGv dest, TCGv src, target_long shamt) +{ + if (shamt == TARGET_LONG_BITS - 8) { + /* rev8, byte swaps */ + tcg_gen_bswap_tl(dest, src); + } else { + gen_helper_grev(dest, src, tcg_constant_tl(shamt)); + } } static bool trans_grevi(DisasContext *ctx, arg_grevi *a) { REQUIRE_EXT(ctx, RVB); - - if (a->shamt >= TARGET_LONG_BITS) { - return false; - } - - return gen_grevi(ctx, a); + return gen_shift_imm_fn(ctx, a, EXT_NONE, gen_grevi); } static bool trans_gorc(DisasContext *ctx, arg_gorc *a) { REQUIRE_EXT(ctx, RVB); - return gen_shift(ctx, a, gen_helper_gorc); + return gen_shift(ctx, a, EXT_ZERO, gen_helper_gorc); } static bool trans_gorci(DisasContext *ctx, arg_gorci *a) { REQUIRE_EXT(ctx, RVB); - return gen_shifti(ctx, a, gen_helper_gorc); + return gen_shift_imm_tl(ctx, a, EXT_ZERO, gen_helper_gorc); } +#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_EXT(ctx, RVB); \ - return gen_arith(ctx, a, gen_sh##SHAMT##add); \ + return gen_arith(ctx, a, EXT_NONE, gen_sh##SHAMT##add); \ } GEN_TRANS_SHADD(1) GEN_TRANS_SHADD(2) GEN_TRANS_SHADD(3) +static void gen_clzw(TCGv ret, TCGv arg1) +{ + tcg_gen_clzi_tl(ret, ret, 64); + tcg_gen_subi_tl(ret, ret, 32); +} + static bool trans_clzw(DisasContext *ctx, arg_clzw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_unary(ctx, a, gen_clzw); + return gen_unary(ctx, a, EXT_ZERO, gen_clzw); +} + +static void gen_ctzw(TCGv ret, TCGv arg1) +{ + tcg_gen_ori_tl(ret, arg1, (target_ulong)MAKE_64BIT_MASK(32, 32)); + tcg_gen_ctzi_tl(ret, ret, 64); } static bool trans_ctzw(DisasContext *ctx, arg_ctzw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_unary(ctx, a, gen_ctzw); + return gen_unary(ctx, a, EXT_NONE, gen_ctzw); } static bool trans_cpopw(DisasContext *ctx, arg_cpopw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_unary(ctx, a, gen_cpopw); + ctx->w = true; + return gen_unary(ctx, a, EXT_ZERO, tcg_gen_ctpop_tl); +} + +static void gen_packw(TCGv ret, TCGv arg1, TCGv arg2) +{ + TCGv t = tcg_temp_new(); + tcg_gen_ext16s_tl(t, arg2); + tcg_gen_deposit_tl(ret, arg1, t, 16, 48); + tcg_temp_free(t); } static bool trans_packw(DisasContext *ctx, arg_packw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_arith(ctx, a, gen_packw); + return gen_arith(ctx, a, EXT_NONE, gen_packw); +} + +static void gen_packuw(TCGv ret, TCGv arg1, TCGv arg2) +{ + TCGv t = tcg_temp_new(); + tcg_gen_shri_tl(t, arg1, 16); + tcg_gen_deposit_tl(ret, arg2, t, 0, 16); + tcg_gen_ext32s_tl(ret, ret); + tcg_temp_free(t); } static bool trans_packuw(DisasContext *ctx, arg_packuw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_arith(ctx, a, gen_packuw); + return gen_arith(ctx, a, EXT_NONE, gen_packuw); } static bool trans_bsetw(DisasContext *ctx, arg_bsetw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftw(ctx, a, gen_bset); + ctx->w = true; + return gen_shift(ctx, a, EXT_NONE, gen_bset); } static bool trans_bsetiw(DisasContext *ctx, arg_bsetiw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftiw(ctx, a, gen_bset); + ctx->w = true; + return gen_shift_imm_tl(ctx, a, EXT_NONE, gen_bset); } static bool trans_bclrw(DisasContext *ctx, arg_bclrw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftw(ctx, a, gen_bclr); + ctx->w = true; + return gen_shift(ctx, a, EXT_NONE, gen_bclr); } static bool trans_bclriw(DisasContext *ctx, arg_bclriw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftiw(ctx, a, gen_bclr); + ctx->w = true; + return gen_shift_imm_tl(ctx, a, EXT_NONE, gen_bclr); } static bool trans_binvw(DisasContext *ctx, arg_binvw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftw(ctx, a, gen_binv); + ctx->w = true; + return gen_shift(ctx, a, EXT_NONE, gen_binv); } static bool trans_binviw(DisasContext *ctx, arg_binviw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftiw(ctx, a, gen_binv); + ctx->w = true; + return gen_shift_imm_tl(ctx, a, EXT_NONE, gen_binv); } static bool trans_bextw(DisasContext *ctx, arg_bextw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftw(ctx, a, gen_bext); + ctx->w = true; + return gen_shift(ctx, a, EXT_NONE, gen_bext); } static bool trans_slow(DisasContext *ctx, arg_slow *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftw(ctx, a, gen_slo); + ctx->w = true; + return gen_shift(ctx, a, EXT_NONE, gen_slo); } static bool trans_sloiw(DisasContext *ctx, arg_sloiw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftiw(ctx, a, gen_slo); + ctx->w = true; + return gen_shift_imm_tl(ctx, a, EXT_NONE, gen_slo); } static bool trans_srow(DisasContext *ctx, arg_srow *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftw(ctx, a, gen_sro); + ctx->w = true; + return gen_shift(ctx, a, EXT_ZERO, gen_sro); } static bool trans_sroiw(DisasContext *ctx, arg_sroiw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftiw(ctx, a, gen_sro); + ctx->w = true; + return gen_shift_imm_tl(ctx, a, EXT_ZERO, gen_sro); +} + +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_rorw(DisasContext *ctx, arg_rorw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftw(ctx, a, gen_rorw); + ctx->w = true; + return gen_shift(ctx, a, EXT_NONE, gen_rorw); } static bool trans_roriw(DisasContext *ctx, arg_roriw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftiw(ctx, a, gen_rorw); + ctx->w = true; + return gen_shift_imm_tl(ctx, a, EXT_NONE, gen_rorw); +} + +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_rolw(DisasContext *ctx, arg_rolw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftw(ctx, a, gen_rolw); + ctx->w = true; + return gen_shift(ctx, a, EXT_NONE, gen_rolw); } static bool trans_grevw(DisasContext *ctx, arg_grevw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftw(ctx, a, gen_grevw); + ctx->w = true; + return gen_shift(ctx, a, EXT_ZERO, gen_helper_grev); } static bool trans_greviw(DisasContext *ctx, arg_greviw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftiw(ctx, a, gen_grevw); + ctx->w = true; + return gen_shift_imm_tl(ctx, a, EXT_ZERO, gen_helper_grev); } static bool trans_gorcw(DisasContext *ctx, arg_gorcw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftw(ctx, a, gen_gorcw); + ctx->w = true; + return gen_shift(ctx, a, EXT_ZERO, gen_helper_gorc); } static bool trans_gorciw(DisasContext *ctx, arg_gorciw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftiw(ctx, a, gen_gorcw); + ctx->w = true; + return gen_shift_imm_tl(ctx, a, EXT_ZERO, gen_helper_gorc); } +#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_EXT(ctx, RVB); \ - return gen_arith(ctx, a, gen_sh##SHAMT##add_uw); \ + 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) +{ + tcg_gen_ext32u_tl(arg1, arg1); + tcg_gen_add_tl(ret, arg1, arg2); +} + static bool trans_add_uw(DisasContext *ctx, arg_add_uw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_arith(ctx, a, gen_add_uw); + 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_EXT(ctx, RVB); - - TCGv source1 = tcg_temp_new(); - gen_get_gpr(source1, a->rs1); - - if (a->shamt < 32) { - tcg_gen_deposit_z_tl(source1, source1, a->shamt, 32); - } else { - tcg_gen_shli_tl(source1, source1, a->shamt); - } - - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - return true; + return gen_shift_imm_fn(ctx, a, EXT_NONE, gen_slli_uw); } diff --git a/target/riscv/insn_trans/trans_rvd.c.inc b/target/riscv/insn_trans/trans_rvd.c.inc index 7e45538ae0..db9ae15755 100644 --- a/target/riscv/insn_trans/trans_rvd.c.inc +++ b/target/riscv/insn_trans/trans_rvd.c.inc @@ -20,30 +20,40 @@ static bool trans_fld(DisasContext *ctx, arg_fld *a) { + TCGv addr; + REQUIRE_FPU; REQUIRE_EXT(ctx, RVD); - TCGv t0 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); - tcg_gen_addi_tl(t0, t0, a->imm); - tcg_gen_qemu_ld_i64(cpu_fpr[a->rd], t0, ctx->mem_idx, MO_TEQ); + 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; + } + + tcg_gen_qemu_ld_i64(cpu_fpr[a->rd], addr, ctx->mem_idx, MO_TEQ); mark_fs_dirty(ctx); - tcg_temp_free(t0); return true; } static bool trans_fsd(DisasContext *ctx, arg_fsd *a) { + TCGv addr; + REQUIRE_FPU; REQUIRE_EXT(ctx, RVD); - TCGv t0 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); - tcg_gen_addi_tl(t0, t0, a->imm); - tcg_gen_qemu_st_i64(cpu_fpr[a->rs2], t0, ctx->mem_idx, MO_TEQ); + 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; + } + + tcg_gen_qemu_st_i64(cpu_fpr[a->rs2], addr, ctx->mem_idx, MO_TEQ); - tcg_temp_free(t0); return true; } @@ -252,11 +262,10 @@ static bool trans_feq_d(DisasContext *ctx, arg_feq_d *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVD); - TCGv t0 = tcg_temp_new(); - gen_helper_feq_d(t0, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + 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; } @@ -265,11 +274,10 @@ static bool trans_flt_d(DisasContext *ctx, arg_flt_d *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVD); - TCGv t0 = tcg_temp_new(); - gen_helper_flt_d(t0, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + 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; } @@ -278,11 +286,10 @@ static bool trans_fle_d(DisasContext *ctx, arg_fle_d *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVD); - TCGv t0 = tcg_temp_new(); - gen_helper_fle_d(t0, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + 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; } @@ -291,10 +298,10 @@ static bool trans_fclass_d(DisasContext *ctx, arg_fclass_d *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVD); - TCGv t0 = tcg_temp_new(); - gen_helper_fclass_d(t0, cpu_fpr[a->rs1]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + 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; } @@ -303,12 +310,11 @@ static bool trans_fcvt_w_d(DisasContext *ctx, arg_fcvt_w_d *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVD); - TCGv t0 = tcg_temp_new(); - gen_set_rm(ctx, a->rm); - gen_helper_fcvt_w_d(t0, cpu_env, cpu_fpr[a->rs1]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + 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; } @@ -317,12 +323,11 @@ static bool trans_fcvt_wu_d(DisasContext *ctx, arg_fcvt_wu_d *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVD); - TCGv t0 = tcg_temp_new(); - gen_set_rm(ctx, a->rm); - gen_helper_fcvt_wu_d(t0, cpu_env, cpu_fpr[a->rs1]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + 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; } @@ -331,12 +336,10 @@ static bool trans_fcvt_d_w(DisasContext *ctx, arg_fcvt_d_w *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVD); - TCGv t0 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); + 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, t0); - tcg_temp_free(t0); + gen_helper_fcvt_d_w(cpu_fpr[a->rd], cpu_env, src); mark_fs_dirty(ctx); return true; @@ -347,12 +350,10 @@ static bool trans_fcvt_d_wu(DisasContext *ctx, arg_fcvt_d_wu *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVD); - TCGv t0 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); + 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, t0); - tcg_temp_free(t0); + gen_helper_fcvt_d_wu(cpu_fpr[a->rd], cpu_env, src); mark_fs_dirty(ctx); return true; @@ -364,11 +365,11 @@ static bool trans_fcvt_l_d(DisasContext *ctx, arg_fcvt_l_d *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVD); - TCGv t0 = tcg_temp_new(); + TCGv dest = dest_gpr(ctx, a->rd); + gen_set_rm(ctx, a->rm); - gen_helper_fcvt_l_d(t0, cpu_env, cpu_fpr[a->rs1]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + gen_helper_fcvt_l_d(dest, cpu_env, cpu_fpr[a->rs1]); + gen_set_gpr(ctx, a->rd, dest); return true; } @@ -378,11 +379,11 @@ static bool trans_fcvt_lu_d(DisasContext *ctx, arg_fcvt_lu_d *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVD); - TCGv t0 = tcg_temp_new(); + TCGv dest = dest_gpr(ctx, a->rd); + gen_set_rm(ctx, a->rm); - gen_helper_fcvt_lu_d(t0, cpu_env, cpu_fpr[a->rs1]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + gen_helper_fcvt_lu_d(dest, cpu_env, cpu_fpr[a->rs1]); + gen_set_gpr(ctx, a->rd, dest); return true; } @@ -393,7 +394,7 @@ static bool trans_fmv_x_d(DisasContext *ctx, arg_fmv_x_d *a) REQUIRE_EXT(ctx, RVD); #ifdef TARGET_RISCV64 - gen_set_gpr(a->rd, cpu_fpr[a->rs1]); + gen_set_gpr(ctx, a->rd, cpu_fpr[a->rs1]); return true; #else qemu_build_not_reached(); @@ -406,12 +407,11 @@ static bool trans_fcvt_d_l(DisasContext *ctx, arg_fcvt_d_l *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVD); - TCGv t0 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); + 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, t0); - tcg_temp_free(t0); + gen_helper_fcvt_d_l(cpu_fpr[a->rd], cpu_env, src); + mark_fs_dirty(ctx); return true; } @@ -422,12 +422,11 @@ static bool trans_fcvt_d_lu(DisasContext *ctx, arg_fcvt_d_lu *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVD); - TCGv t0 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); + 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, t0); - tcg_temp_free(t0); + gen_helper_fcvt_d_lu(cpu_fpr[a->rd], cpu_env, src); + mark_fs_dirty(ctx); return true; } @@ -439,11 +438,7 @@ static bool trans_fmv_d_x(DisasContext *ctx, arg_fmv_d_x *a) REQUIRE_EXT(ctx, RVD); #ifdef TARGET_RISCV64 - TCGv t0 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); - - tcg_gen_mov_tl(cpu_fpr[a->rd], t0); - tcg_temp_free(t0); + tcg_gen_mov_tl(cpu_fpr[a->rd], get_gpr(ctx, a->rs1, EXT_NONE)); mark_fs_dirty(ctx); return true; #else diff --git a/target/riscv/insn_trans/trans_rvf.c.inc b/target/riscv/insn_trans/trans_rvf.c.inc index db1c0c9974..bddbd418d9 100644 --- a/target/riscv/insn_trans/trans_rvf.c.inc +++ b/target/riscv/insn_trans/trans_rvf.c.inc @@ -25,32 +25,43 @@ static bool trans_flw(DisasContext *ctx, arg_flw *a) { + TCGv_i64 dest; + TCGv addr; + REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); - tcg_gen_addi_tl(t0, t0, a->imm); - tcg_gen_qemu_ld_i64(cpu_fpr[a->rd], t0, ctx->mem_idx, MO_TEUL); - gen_nanbox_s(cpu_fpr[a->rd], cpu_fpr[a->rd]); + 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; + } + + dest = cpu_fpr[a->rd]; + tcg_gen_qemu_ld_i64(dest, addr, ctx->mem_idx, MO_TEUL); + gen_nanbox_s(dest, dest); - tcg_temp_free(t0); mark_fs_dirty(ctx); return true; } static bool trans_fsw(DisasContext *ctx, arg_fsw *a) { + TCGv addr; + REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); - tcg_gen_addi_tl(t0, t0, a->imm); + 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; + } - tcg_gen_qemu_st_i64(cpu_fpr[a->rs2], t0, ctx->mem_idx, MO_TEUL); + tcg_gen_qemu_st_i64(cpu_fpr[a->rs2], addr, ctx->mem_idx, MO_TEUL); - tcg_temp_free(t0); return true; } @@ -200,12 +211,11 @@ static bool trans_fsgnjn_s(DisasContext *ctx, arg_fsgnjn_s *a) * Replace bit 31 in rs1 with inverse in rs2. * This formulation retains the nanboxing of rs1. */ - mask = tcg_const_i64(~MAKE_64BIT_MASK(31, 1)); + 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(mask); tcg_temp_free_i64(rs2); } tcg_temp_free_i64(rs1); @@ -272,12 +282,11 @@ static bool trans_fcvt_w_s(DisasContext *ctx, arg_fcvt_w_s *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); - gen_set_rm(ctx, a->rm); - gen_helper_fcvt_w_s(t0, cpu_env, cpu_fpr[a->rs1]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + 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; } @@ -286,12 +295,11 @@ static bool trans_fcvt_wu_s(DisasContext *ctx, arg_fcvt_wu_s *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); - gen_set_rm(ctx, a->rm); - gen_helper_fcvt_wu_s(t0, cpu_env, cpu_fpr[a->rs1]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + 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; } @@ -301,17 +309,15 @@ static bool trans_fmv_x_w(DisasContext *ctx, arg_fmv_x_w *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); + TCGv dest = dest_gpr(ctx, a->rd); #if defined(TARGET_RISCV64) - tcg_gen_ext32s_tl(t0, cpu_fpr[a->rs1]); + tcg_gen_ext32s_tl(dest, cpu_fpr[a->rs1]); #else - tcg_gen_extrl_i64_i32(t0, cpu_fpr[a->rs1]); + tcg_gen_extrl_i64_i32(dest, cpu_fpr[a->rs1]); #endif - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); - + gen_set_gpr(ctx, a->rd, dest); return true; } @@ -319,10 +325,11 @@ static bool trans_feq_s(DisasContext *ctx, arg_feq_s *a) { REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); - gen_helper_feq_s(t0, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + + 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; } @@ -330,10 +337,11 @@ static bool trans_flt_s(DisasContext *ctx, arg_flt_s *a) { REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); - gen_helper_flt_s(t0, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + + 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; } @@ -341,10 +349,11 @@ static bool trans_fle_s(DisasContext *ctx, arg_fle_s *a) { REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); - gen_helper_fle_s(t0, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + + 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; } @@ -353,13 +362,10 @@ static bool trans_fclass_s(DisasContext *ctx, arg_fclass_s *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); - - gen_helper_fclass_s(t0, cpu_fpr[a->rs1]); - - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + 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; } @@ -368,15 +374,12 @@ static bool trans_fcvt_s_w(DisasContext *ctx, arg_fcvt_s_w *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); + 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, t0); + gen_helper_fcvt_s_w(cpu_fpr[a->rd], cpu_env, src); mark_fs_dirty(ctx); - tcg_temp_free(t0); - return true; } @@ -385,15 +388,12 @@ static bool trans_fcvt_s_wu(DisasContext *ctx, arg_fcvt_s_wu *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); + 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, t0); + gen_helper_fcvt_s_wu(cpu_fpr[a->rd], cpu_env, src); mark_fs_dirty(ctx); - tcg_temp_free(t0); - return true; } @@ -403,15 +403,12 @@ static bool trans_fmv_w_x(DisasContext *ctx, arg_fmv_w_x *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); + TCGv src = get_gpr(ctx, a->rs1, EXT_ZERO); - tcg_gen_extu_tl_i64(cpu_fpr[a->rd], t0); + 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); - tcg_temp_free(t0); - return true; } @@ -421,11 +418,11 @@ static bool trans_fcvt_l_s(DisasContext *ctx, arg_fcvt_l_s *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); + TCGv dest = dest_gpr(ctx, a->rd); + gen_set_rm(ctx, a->rm); - gen_helper_fcvt_l_s(t0, cpu_env, cpu_fpr[a->rs1]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + gen_helper_fcvt_l_s(dest, cpu_env, cpu_fpr[a->rs1]); + gen_set_gpr(ctx, a->rd, dest); return true; } @@ -435,11 +432,11 @@ static bool trans_fcvt_lu_s(DisasContext *ctx, arg_fcvt_lu_s *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); + TCGv dest = dest_gpr(ctx, a->rd); + gen_set_rm(ctx, a->rm); - gen_helper_fcvt_lu_s(t0, cpu_env, cpu_fpr[a->rs1]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + gen_helper_fcvt_lu_s(dest, cpu_env, cpu_fpr[a->rs1]); + gen_set_gpr(ctx, a->rd, dest); return true; } @@ -449,14 +446,12 @@ static bool trans_fcvt_s_l(DisasContext *ctx, arg_fcvt_s_l *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); + 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, t0); + gen_helper_fcvt_s_l(cpu_fpr[a->rd], cpu_env, src); mark_fs_dirty(ctx); - tcg_temp_free(t0); return true; } @@ -466,13 +461,11 @@ static bool trans_fcvt_s_lu(DisasContext *ctx, arg_fcvt_s_lu *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); + 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, t0); + gen_helper_fcvt_s_lu(cpu_fpr[a->rd], cpu_env, src); mark_fs_dirty(ctx); - tcg_temp_free(t0); return true; } diff --git a/target/riscv/insn_trans/trans_rvh.c.inc b/target/riscv/insn_trans/trans_rvh.c.inc index 6b5edf82b7..ecbf77ff9c 100644 --- a/target/riscv/insn_trans/trans_rvh.c.inc +++ b/target/riscv/insn_trans/trans_rvh.c.inc @@ -17,281 +17,139 @@ */ #ifndef CONFIG_USER_ONLY -static void check_access(DisasContext *ctx) { +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); -#ifndef CONFIG_USER_ONLY - TCGv t0 = tcg_temp_new(); - TCGv t1 = tcg_temp_new(); - - check_access(ctx); - - gen_get_gpr(t0, a->rs1); - - tcg_gen_qemu_ld_tl(t1, t0, ctx->mem_idx | TB_FLAGS_PRIV_HYP_ACCESS_MASK, MO_SB); - gen_set_gpr(a->rd, t1); - - tcg_temp_free(t0); - tcg_temp_free(t1); - return true; -#else - return false; -#endif + return do_hlv(ctx, a, MO_SB); } static bool trans_hlv_h(DisasContext *ctx, arg_hlv_h *a) { REQUIRE_EXT(ctx, RVH); -#ifndef CONFIG_USER_ONLY - TCGv t0 = tcg_temp_new(); - TCGv t1 = tcg_temp_new(); - - check_access(ctx); - - gen_get_gpr(t0, a->rs1); - - tcg_gen_qemu_ld_tl(t1, t0, ctx->mem_idx | TB_FLAGS_PRIV_HYP_ACCESS_MASK, MO_TESW); - gen_set_gpr(a->rd, t1); - - tcg_temp_free(t0); - tcg_temp_free(t1); - return true; -#else - return false; -#endif + return do_hlv(ctx, a, MO_TESW); } static bool trans_hlv_w(DisasContext *ctx, arg_hlv_w *a) { REQUIRE_EXT(ctx, RVH); -#ifndef CONFIG_USER_ONLY - TCGv t0 = tcg_temp_new(); - TCGv t1 = tcg_temp_new(); - - check_access(ctx); - - gen_get_gpr(t0, a->rs1); - - tcg_gen_qemu_ld_tl(t1, t0, ctx->mem_idx | TB_FLAGS_PRIV_HYP_ACCESS_MASK, MO_TESL); - gen_set_gpr(a->rd, t1); - - tcg_temp_free(t0); - tcg_temp_free(t1); - return true; -#else - return false; -#endif + return do_hlv(ctx, a, MO_TESL); } static bool trans_hlv_bu(DisasContext *ctx, arg_hlv_bu *a) { REQUIRE_EXT(ctx, RVH); -#ifndef CONFIG_USER_ONLY - TCGv t0 = tcg_temp_new(); - TCGv t1 = tcg_temp_new(); - - check_access(ctx); - - gen_get_gpr(t0, a->rs1); - - tcg_gen_qemu_ld_tl(t1, t0, ctx->mem_idx | TB_FLAGS_PRIV_HYP_ACCESS_MASK, MO_UB); - gen_set_gpr(a->rd, t1); - - tcg_temp_free(t0); - tcg_temp_free(t1); - return true; -#else - return false; -#endif + return do_hlv(ctx, a, MO_UB); } static bool trans_hlv_hu(DisasContext *ctx, arg_hlv_hu *a) { REQUIRE_EXT(ctx, RVH); -#ifndef CONFIG_USER_ONLY - TCGv t0 = tcg_temp_new(); - TCGv t1 = tcg_temp_new(); + return do_hlv(ctx, a, MO_TEUW); +} - check_access(ctx); - - gen_get_gpr(t0, a->rs1); - tcg_gen_qemu_ld_tl(t1, t0, ctx->mem_idx | TB_FLAGS_PRIV_HYP_ACCESS_MASK, MO_TEUW); - gen_set_gpr(a->rd, t1); - - tcg_temp_free(t0); - tcg_temp_free(t1); - return true; -#else +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); -#ifndef CONFIG_USER_ONLY - TCGv t0 = tcg_temp_new(); - TCGv dat = tcg_temp_new(); - - check_access(ctx); - - gen_get_gpr(t0, a->rs1); - gen_get_gpr(dat, a->rs2); - - tcg_gen_qemu_st_tl(dat, t0, ctx->mem_idx | TB_FLAGS_PRIV_HYP_ACCESS_MASK, MO_SB); - - tcg_temp_free(t0); - tcg_temp_free(dat); - return true; -#else - return false; -#endif + return do_hsv(ctx, a, MO_SB); } static bool trans_hsv_h(DisasContext *ctx, arg_hsv_h *a) { REQUIRE_EXT(ctx, RVH); -#ifndef CONFIG_USER_ONLY - TCGv t0 = tcg_temp_new(); - TCGv dat = tcg_temp_new(); - - check_access(ctx); - - gen_get_gpr(t0, a->rs1); - gen_get_gpr(dat, a->rs2); - - tcg_gen_qemu_st_tl(dat, t0, ctx->mem_idx | TB_FLAGS_PRIV_HYP_ACCESS_MASK, MO_TESW); - - tcg_temp_free(t0); - tcg_temp_free(dat); - return true; -#else - return false; -#endif + return do_hsv(ctx, a, MO_TESW); } static bool trans_hsv_w(DisasContext *ctx, arg_hsv_w *a) { REQUIRE_EXT(ctx, RVH); -#ifndef CONFIG_USER_ONLY - TCGv t0 = tcg_temp_new(); - TCGv dat = tcg_temp_new(); - - check_access(ctx); - - gen_get_gpr(t0, a->rs1); - gen_get_gpr(dat, a->rs2); - - tcg_gen_qemu_st_tl(dat, t0, ctx->mem_idx | TB_FLAGS_PRIV_HYP_ACCESS_MASK, MO_TESL); - - tcg_temp_free(t0); - tcg_temp_free(dat); - return true; -#else - return false; -#endif + 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); - -#ifndef CONFIG_USER_ONLY - TCGv t0 = tcg_temp_new(); - TCGv t1 = tcg_temp_new(); - - check_access(ctx); - - gen_get_gpr(t0, a->rs1); - - tcg_gen_qemu_ld_tl(t1, t0, ctx->mem_idx | TB_FLAGS_PRIV_HYP_ACCESS_MASK, MO_TEUL); - gen_set_gpr(a->rd, t1); - - tcg_temp_free(t0); - tcg_temp_free(t1); - return true; -#else - return false; -#endif + 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); - -#ifndef CONFIG_USER_ONLY - TCGv t0 = tcg_temp_new(); - TCGv t1 = tcg_temp_new(); - - check_access(ctx); - - gen_get_gpr(t0, a->rs1); - - tcg_gen_qemu_ld_tl(t1, t0, ctx->mem_idx | TB_FLAGS_PRIV_HYP_ACCESS_MASK, MO_TEQ); - gen_set_gpr(a->rd, t1); - - tcg_temp_free(t0); - tcg_temp_free(t1); - return true; -#else - return false; -#endif + 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 - TCGv t0 = tcg_temp_new(); - TCGv dat = tcg_temp_new(); - - check_access(ctx); - - gen_get_gpr(t0, a->rs1); - gen_get_gpr(dat, a->rs2); - - tcg_gen_qemu_st_tl(dat, t0, ctx->mem_idx | TB_FLAGS_PRIV_HYP_ACCESS_MASK, MO_TEQ); - - tcg_temp_free(t0); - tcg_temp_free(dat); +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; -#else - return false; -#endif } +#endif static bool trans_hlvx_hu(DisasContext *ctx, arg_hlvx_hu *a) { REQUIRE_EXT(ctx, RVH); #ifndef CONFIG_USER_ONLY - TCGv t0 = tcg_temp_new(); - TCGv t1 = tcg_temp_new(); - - check_access(ctx); - - gen_get_gpr(t0, a->rs1); - - gen_helper_hyp_hlvx_hu(t1, cpu_env, t0); - gen_set_gpr(a->rd, t1); - - tcg_temp_free(t0); - tcg_temp_free(t1); - return true; + return do_hlvx(ctx, a, gen_helper_hyp_hlvx_hu); #else return false; #endif @@ -301,19 +159,7 @@ static bool trans_hlvx_wu(DisasContext *ctx, arg_hlvx_wu *a) { REQUIRE_EXT(ctx, RVH); #ifndef CONFIG_USER_ONLY - TCGv t0 = tcg_temp_new(); - TCGv t1 = tcg_temp_new(); - - check_access(ctx); - - gen_get_gpr(t0, a->rs1); - - gen_helper_hyp_hlvx_wu(t1, cpu_env, t0); - gen_set_gpr(a->rd, t1); - - tcg_temp_free(t0); - tcg_temp_free(t1); - return true; + return do_hlvx(ctx, a, gen_helper_hyp_hlvx_wu); #else return false; #endif diff --git a/target/riscv/insn_trans/trans_rvi.c.inc b/target/riscv/insn_trans/trans_rvi.c.inc index 6e736c9d0d..920ae0edb3 100644 --- a/target/riscv/insn_trans/trans_rvi.c.inc +++ b/target/riscv/insn_trans/trans_rvi.c.inc @@ -54,24 +54,25 @@ static bool trans_jal(DisasContext *ctx, arg_jal *a) static bool trans_jalr(DisasContext *ctx, arg_jalr *a) { - /* no chaining with JALR */ TCGLabel *misaligned = NULL; - TCGv t0 = tcg_temp_new(); - - gen_get_gpr(cpu_pc, a->rs1); - tcg_gen_addi_tl(cpu_pc, cpu_pc, a->imm); + 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); } + + /* No chaining with JALR. */ lookup_and_goto_ptr(ctx); if (misaligned) { @@ -80,21 +81,18 @@ static bool trans_jalr(DisasContext *ctx, arg_jalr *a) } ctx->base.is_jmp = DISAS_NORETURN; - tcg_temp_free(t0); return true; } static bool gen_branch(DisasContext *ctx, arg_b *a, TCGCond cond) { TCGLabel *l = gen_new_label(); - TCGv source1, source2; - source1 = tcg_temp_new(); - source2 = tcg_temp_new(); - gen_get_gpr(source1, a->rs1); - gen_get_gpr(source2, a->rs2); + TCGv src1 = get_gpr(ctx, a->rs1, EXT_SIGN); + TCGv src2 = get_gpr(ctx, a->rs2, EXT_SIGN); - tcg_gen_brcond_tl(cond, source1, source2, l); + 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)) { @@ -105,9 +103,6 @@ static bool gen_branch(DisasContext *ctx, arg_b *a, TCGCond cond) } ctx->base.is_jmp = DISAS_NORETURN; - tcg_temp_free(source1); - tcg_temp_free(source2); - return true; } @@ -143,15 +138,17 @@ static bool trans_bgeu(DisasContext *ctx, arg_bgeu *a) static bool gen_load(DisasContext *ctx, arg_lb *a, MemOp memop) { - TCGv t0 = tcg_temp_new(); - TCGv t1 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); - tcg_gen_addi_tl(t0, t0, a->imm); + TCGv dest = dest_gpr(ctx, a->rd); + TCGv addr = get_gpr(ctx, a->rs1, EXT_NONE); - tcg_gen_qemu_ld_tl(t1, t0, ctx->mem_idx, memop); - gen_set_gpr(a->rd, t1); - tcg_temp_free(t0); - tcg_temp_free(t1); + if (a->imm) { + TCGv temp = temp_new(ctx); + tcg_gen_addi_tl(temp, addr, a->imm); + addr = temp; + } + + tcg_gen_qemu_ld_tl(dest, addr, ctx->mem_idx, memop); + gen_set_gpr(ctx, a->rd, dest); return true; } @@ -182,19 +179,19 @@ static bool trans_lhu(DisasContext *ctx, arg_lhu *a) static bool gen_store(DisasContext *ctx, arg_sb *a, MemOp memop) { - TCGv t0 = tcg_temp_new(); - TCGv dat = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); - tcg_gen_addi_tl(t0, t0, a->imm); - gen_get_gpr(dat, a->rs2); + TCGv addr = get_gpr(ctx, a->rs1, EXT_NONE); + TCGv data = get_gpr(ctx, a->rs2, EXT_NONE); - tcg_gen_qemu_st_tl(dat, t0, ctx->mem_idx, memop); - tcg_temp_free(t0); - tcg_temp_free(dat); + if (a->imm) { + TCGv temp = temp_new(ctx); + tcg_gen_addi_tl(temp, addr, a->imm); + addr = temp; + } + + 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); @@ -230,7 +227,7 @@ static bool trans_sd(DisasContext *ctx, arg_sd *a) static bool trans_addi(DisasContext *ctx, arg_addi *a) { - return gen_arith_imm_fn(ctx, a, &tcg_gen_addi_tl); + return gen_arith_imm_fn(ctx, a, EXT_NONE, tcg_gen_addi_tl); } static void gen_slt(TCGv ret, TCGv s1, TCGv s2) @@ -243,204 +240,167 @@ 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, &gen_slt); + 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, &gen_sltu); + 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, &tcg_gen_xori_tl); + 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, &tcg_gen_ori_tl); + 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, &tcg_gen_andi_tl); + return gen_arith_imm_fn(ctx, a, EXT_NONE, tcg_gen_andi_tl); } + static bool trans_slli(DisasContext *ctx, arg_slli *a) { - return gen_shifti(ctx, a, tcg_gen_shl_tl); + return gen_shift_imm_fn(ctx, a, EXT_NONE, tcg_gen_shli_tl); } static bool trans_srli(DisasContext *ctx, arg_srli *a) { - return gen_shifti(ctx, a, tcg_gen_shr_tl); + return gen_shift_imm_fn(ctx, a, EXT_ZERO, tcg_gen_shri_tl); } static bool trans_srai(DisasContext *ctx, arg_srai *a) { - return gen_shifti(ctx, a, tcg_gen_sar_tl); + return gen_shift_imm_fn(ctx, a, EXT_SIGN, tcg_gen_sari_tl); } static bool trans_add(DisasContext *ctx, arg_add *a) { - return gen_arith(ctx, a, &tcg_gen_add_tl); + 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, &tcg_gen_sub_tl); + 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, &tcg_gen_shl_tl); + 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, &gen_slt); + return gen_arith(ctx, a, EXT_SIGN, gen_slt); } static bool trans_sltu(DisasContext *ctx, arg_sltu *a) { - return gen_arith(ctx, a, &gen_sltu); + return gen_arith(ctx, a, EXT_SIGN, gen_sltu); } static bool trans_xor(DisasContext *ctx, arg_xor *a) { - return gen_arith(ctx, a, &tcg_gen_xor_tl); + 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, &tcg_gen_shr_tl); + 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, &tcg_gen_sar_tl); + 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, &tcg_gen_or_tl); + 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, &tcg_gen_and_tl); + return gen_arith(ctx, a, EXT_NONE, tcg_gen_and_tl); } static bool trans_addiw(DisasContext *ctx, arg_addiw *a) { REQUIRE_64BIT(ctx); - return gen_arith_imm_tl(ctx, a, &gen_addw); + ctx->w = true; + 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); - return gen_shiftiw(ctx, a, tcg_gen_shl_tl); + ctx->w = true; + 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_srliw(DisasContext *ctx, arg_srliw *a) { REQUIRE_64BIT(ctx); - TCGv t = tcg_temp_new(); - gen_get_gpr(t, a->rs1); - tcg_gen_extract_tl(t, t, a->shamt, 32 - a->shamt); - /* sign-extend for W instructions */ - tcg_gen_ext32s_tl(t, t); - gen_set_gpr(a->rd, t); - tcg_temp_free(t); - return true; + ctx->w = true; + return gen_shift_imm_fn(ctx, a, EXT_NONE, 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_sraiw(DisasContext *ctx, arg_sraiw *a) { REQUIRE_64BIT(ctx); - TCGv t = tcg_temp_new(); - gen_get_gpr(t, a->rs1); - tcg_gen_sextract_tl(t, t, a->shamt, 32 - a->shamt); - gen_set_gpr(a->rd, t); - tcg_temp_free(t); - return true; + ctx->w = true; + return gen_shift_imm_fn(ctx, a, EXT_NONE, gen_sraiw); } static bool trans_addw(DisasContext *ctx, arg_addw *a) { REQUIRE_64BIT(ctx); - return gen_arith(ctx, a, &gen_addw); + ctx->w = true; + return gen_arith(ctx, a, EXT_NONE, tcg_gen_add_tl); } static bool trans_subw(DisasContext *ctx, arg_subw *a) { REQUIRE_64BIT(ctx); - return gen_arith(ctx, a, &gen_subw); + ctx->w = true; + return gen_arith(ctx, a, EXT_NONE, tcg_gen_sub_tl); } static bool trans_sllw(DisasContext *ctx, arg_sllw *a) { REQUIRE_64BIT(ctx); - TCGv source1 = tcg_temp_new(); - TCGv source2 = tcg_temp_new(); - - gen_get_gpr(source1, a->rs1); - gen_get_gpr(source2, a->rs2); - - tcg_gen_andi_tl(source2, source2, 0x1F); - tcg_gen_shl_tl(source1, source1, source2); - - tcg_gen_ext32s_tl(source1, source1); - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - tcg_temp_free(source2); - return true; + ctx->w = true; + return gen_shift(ctx, a, EXT_NONE, tcg_gen_shl_tl); } static bool trans_srlw(DisasContext *ctx, arg_srlw *a) { REQUIRE_64BIT(ctx); - TCGv source1 = tcg_temp_new(); - TCGv source2 = tcg_temp_new(); - - gen_get_gpr(source1, a->rs1); - gen_get_gpr(source2, a->rs2); - - /* clear upper 32 */ - tcg_gen_ext32u_tl(source1, source1); - tcg_gen_andi_tl(source2, source2, 0x1F); - tcg_gen_shr_tl(source1, source1, source2); - - tcg_gen_ext32s_tl(source1, source1); - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - tcg_temp_free(source2); - return true; + ctx->w = true; + return gen_shift(ctx, a, EXT_ZERO, tcg_gen_shr_tl); } static bool trans_sraw(DisasContext *ctx, arg_sraw *a) { REQUIRE_64BIT(ctx); - TCGv source1 = tcg_temp_new(); - TCGv source2 = tcg_temp_new(); - - gen_get_gpr(source1, a->rs1); - gen_get_gpr(source2, a->rs2); - - /* - * first, trick to get it to act like working on 32 bits (get rid of - * upper 32, sign extend to fill space) - */ - tcg_gen_ext32s_tl(source1, source1); - tcg_gen_andi_tl(source2, source2, 0x1F); - tcg_gen_sar_tl(source1, source1, source2); - - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - tcg_temp_free(source2); - - return true; + ctx->w = true; + return gen_shift(ctx, a, EXT_SIGN, tcg_gen_sar_tl); } static bool trans_fence(DisasContext *ctx, arg_fence *a) @@ -466,80 +426,150 @@ static bool trans_fence_i(DisasContext *ctx, arg_fence_i *a) return true; } -#define RISCV_OP_CSR_PRE do {\ - source1 = tcg_temp_new(); \ - csr_store = tcg_temp_new(); \ - dest = tcg_temp_new(); \ - rs1_pass = tcg_temp_new(); \ - gen_get_gpr(source1, a->rs1); \ - tcg_gen_movi_tl(cpu_pc, ctx->base.pc_next); \ - tcg_gen_movi_tl(rs1_pass, a->rs1); \ - tcg_gen_movi_tl(csr_store, a->csr); \ - gen_io_start();\ -} while (0) +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); + exit_tb(ctx); + ctx->base.is_jmp = DISAS_NORETURN; + return true; +} -#define RISCV_OP_CSR_POST do {\ - gen_set_gpr(a->rd, dest); \ - tcg_gen_movi_tl(cpu_pc, ctx->pc_succ_insn); \ - exit_tb(ctx); \ - ctx->base.is_jmp = DISAS_NORETURN; \ - tcg_temp_free(source1); \ - tcg_temp_free(csr_store); \ - tcg_temp_free(dest); \ - tcg_temp_free(rs1_pass); \ -} while (0) +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 source1, csr_store, dest, rs1_pass; - RISCV_OP_CSR_PRE; - gen_helper_csrrw(dest, cpu_env, source1, csr_store); - RISCV_OP_CSR_POST; - return true; + 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) { - TCGv source1, csr_store, dest, rs1_pass; - RISCV_OP_CSR_PRE; - gen_helper_csrrs(dest, cpu_env, source1, csr_store, rs1_pass); - RISCV_OP_CSR_POST; - return true; + /* + * 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) { - TCGv source1, csr_store, dest, rs1_pass; - RISCV_OP_CSR_PRE; - gen_helper_csrrc(dest, cpu_env, source1, csr_store, rs1_pass); - RISCV_OP_CSR_POST; - return true; + /* + * 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 source1, csr_store, dest, rs1_pass; - RISCV_OP_CSR_PRE; - gen_helper_csrrw(dest, cpu_env, rs1_pass, csr_store); - RISCV_OP_CSR_POST; - return true; + 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) { - TCGv source1, csr_store, dest, rs1_pass; - RISCV_OP_CSR_PRE; - gen_helper_csrrs(dest, cpu_env, rs1_pass, csr_store, rs1_pass); - RISCV_OP_CSR_POST; - return true; + /* + * 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) { - TCGv source1, csr_store, dest, rs1_pass; - RISCV_OP_CSR_PRE; - gen_helper_csrrc(dest, cpu_env, rs1_pass, csr_store, rs1_pass); - RISCV_OP_CSR_POST; - return true; + /* + * 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 index 10ecc456fc..b89a85ad3a 100644 --- a/target/riscv/insn_trans/trans_rvm.c.inc +++ b/target/riscv/insn_trans/trans_rvm.c.inc @@ -22,107 +22,230 @@ static bool trans_mul(DisasContext *ctx, arg_mul *a) { REQUIRE_EXT(ctx, RVM); - return gen_arith(ctx, a, &tcg_gen_mul_tl); + 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 bool trans_mulh(DisasContext *ctx, arg_mulh *a) { REQUIRE_EXT(ctx, RVM); - TCGv source1 = tcg_temp_new(); - TCGv source2 = tcg_temp_new(); - gen_get_gpr(source1, a->rs1); - gen_get_gpr(source2, a->rs2); + return gen_arith(ctx, a, EXT_NONE, gen_mulh); +} - tcg_gen_muls2_tl(source2, source1, source1, source2); +static void gen_mulhsu(TCGv ret, TCGv arg1, TCGv arg2) +{ + TCGv rl = tcg_temp_new(); + TCGv rh = tcg_temp_new(); - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - tcg_temp_free(source2); - return true; + 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 bool trans_mulhsu(DisasContext *ctx, arg_mulhsu *a) { REQUIRE_EXT(ctx, RVM); - return gen_arith(ctx, a, &gen_mulhsu); + return gen_arith(ctx, a, EXT_NONE, gen_mulhsu); +} + +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); - TCGv source1 = tcg_temp_new(); - TCGv source2 = tcg_temp_new(); - gen_get_gpr(source1, a->rs1); - gen_get_gpr(source2, a->rs2); + return gen_arith(ctx, a, EXT_NONE, gen_mulhu); +} - tcg_gen_mulu2_tl(source2, source1, source1, source2); +static void gen_div(TCGv ret, TCGv source1, TCGv source2) +{ + TCGv temp1, temp2, zero, one, mone, min; - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - tcg_temp_free(source2); - return true; + 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, &gen_div); + 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, &gen_divu); + 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, &gen_rem); + 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, &gen_remu); + 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); - - return gen_arith(ctx, a, &gen_mulw); + ctx->w = true; + 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); - - return gen_arith_div_w(ctx, a, &gen_div); + ctx->w = true; + 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); - - return gen_arith_div_uw(ctx, a, &gen_divu); + ctx->w = true; + 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); - - return gen_arith_div_w(ctx, a, &gen_rem); + ctx->w = true; + 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); - - return gen_arith_div_uw(ctx, a, &gen_remu); + ctx->w = true; + 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 index 83d9a285ba..fa451938f1 100644 --- a/target/riscv/insn_trans/trans_rvv.c.inc +++ b/target/riscv/insn_trans/trans_rvv.c.inc @@ -27,27 +27,22 @@ static bool trans_vsetvl(DisasContext *ctx, arg_vsetvl *a) return false; } - s2 = tcg_temp_new(); - dst = tcg_temp_new(); + 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_const_tl(RV_VLEN_MAX); + s1 = tcg_constant_tl(RV_VLEN_MAX); } else { - s1 = tcg_temp_new(); - gen_get_gpr(s1, a->rs1); + s1 = get_gpr(ctx, a->rs1, EXT_ZERO); } - gen_get_gpr(s2, a->rs2); gen_helper_vsetvl(dst, cpu_env, s1, s2); - gen_set_gpr(a->rd, dst); + gen_set_gpr(ctx, a->rd, dst); + tcg_gen_movi_tl(cpu_pc, ctx->pc_succ_insn); lookup_and_goto_ptr(ctx); ctx->base.is_jmp = DISAS_NORETURN; - - tcg_temp_free(s1); - tcg_temp_free(s2); - tcg_temp_free(dst); return true; } @@ -59,25 +54,21 @@ static bool trans_vsetvli(DisasContext *ctx, arg_vsetvli *a) return false; } - s2 = tcg_const_tl(a->zimm); - dst = tcg_temp_new(); + 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_const_tl(RV_VLEN_MAX); + s1 = tcg_constant_tl(RV_VLEN_MAX); } else { - s1 = tcg_temp_new(); - gen_get_gpr(s1, a->rs1); + s1 = get_gpr(ctx, a->rs1, EXT_ZERO); } gen_helper_vsetvl(dst, cpu_env, s1, s2); - gen_set_gpr(a->rd, dst); + gen_set_gpr(ctx, a->rd, dst); + gen_goto_tb(ctx, 0, ctx->pc_succ_insn); ctx->base.is_jmp = DISAS_NORETURN; - - tcg_temp_free(s1); - tcg_temp_free(s2); - tcg_temp_free(dst); return true; } @@ -174,7 +165,7 @@ static bool ldst_us_trans(uint32_t vd, uint32_t rs1, uint32_t data, dest = tcg_temp_new_ptr(); mask = tcg_temp_new_ptr(); - base = tcg_temp_new(); + base = get_gpr(s, rs1, EXT_NONE); /* * As simd_desc supports at most 256 bytes, and in this implementation, @@ -183,9 +174,8 @@ static bool ldst_us_trans(uint32_t vd, uint32_t rs1, uint32_t data, * 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_const_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); - gen_get_gpr(base, rs1); tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, vd)); tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0)); @@ -193,8 +183,6 @@ static bool ldst_us_trans(uint32_t vd, uint32_t rs1, uint32_t data, tcg_temp_free_ptr(dest); tcg_temp_free_ptr(mask); - tcg_temp_free(base); - tcg_temp_free_i32(desc); gen_set_label(over); return true; } @@ -332,12 +320,10 @@ static bool ldst_stride_trans(uint32_t vd, uint32_t rs1, uint32_t rs2, dest = tcg_temp_new_ptr(); mask = tcg_temp_new_ptr(); - base = tcg_temp_new(); - stride = tcg_temp_new(); - desc = tcg_const_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + 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)); - gen_get_gpr(base, rs1); - gen_get_gpr(stride, rs2); tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, vd)); tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0)); @@ -345,9 +331,6 @@ static bool ldst_stride_trans(uint32_t vd, uint32_t rs1, uint32_t rs2, tcg_temp_free_ptr(dest); tcg_temp_free_ptr(mask); - tcg_temp_free(base); - tcg_temp_free(stride); - tcg_temp_free_i32(desc); gen_set_label(over); return true; } @@ -461,10 +444,9 @@ static bool ldst_index_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, dest = tcg_temp_new_ptr(); mask = tcg_temp_new_ptr(); index = tcg_temp_new_ptr(); - base = tcg_temp_new(); - desc = tcg_const_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + base = get_gpr(s, rs1, EXT_NONE); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); - gen_get_gpr(base, rs1); 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)); @@ -474,8 +456,6 @@ static bool ldst_index_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, tcg_temp_free_ptr(dest); tcg_temp_free_ptr(mask); tcg_temp_free_ptr(index); - tcg_temp_free(base); - tcg_temp_free_i32(desc); gen_set_label(over); return true; } @@ -593,10 +573,9 @@ static bool ldff_trans(uint32_t vd, uint32_t rs1, uint32_t data, dest = tcg_temp_new_ptr(); mask = tcg_temp_new_ptr(); - base = tcg_temp_new(); - desc = tcg_const_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + base = get_gpr(s, rs1, EXT_NONE); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); - gen_get_gpr(base, rs1); tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, vd)); tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0)); @@ -604,8 +583,6 @@ static bool ldff_trans(uint32_t vd, uint32_t rs1, uint32_t data, tcg_temp_free_ptr(dest); tcg_temp_free_ptr(mask); - tcg_temp_free(base); - tcg_temp_free_i32(desc); gen_set_label(over); return true; } @@ -670,10 +647,9 @@ static bool amo_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, dest = tcg_temp_new_ptr(); mask = tcg_temp_new_ptr(); index = tcg_temp_new_ptr(); - base = tcg_temp_new(); - desc = tcg_const_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + base = get_gpr(s, rs1, EXT_NONE); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); - gen_get_gpr(base, rs1); 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)); @@ -683,8 +659,6 @@ static bool amo_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, tcg_temp_free_ptr(dest); tcg_temp_free_ptr(mask); tcg_temp_free_ptr(index); - tcg_temp_free(base); - tcg_temp_free_i32(desc); gen_set_label(over); return true; } @@ -868,13 +842,12 @@ static bool opivx_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, uint32_t vm, dest = tcg_temp_new_ptr(); mask = tcg_temp_new_ptr(); src2 = tcg_temp_new_ptr(); - src1 = tcg_temp_new(); - gen_get_gpr(src1, rs1); + 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_const_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + 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)); @@ -885,8 +858,6 @@ static bool opivx_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, uint32_t vm, tcg_temp_free_ptr(dest); tcg_temp_free_ptr(mask); tcg_temp_free_ptr(src2); - tcg_temp_free(src1); - tcg_temp_free_i32(desc); gen_set_label(over); return true; } @@ -912,15 +883,12 @@ do_opivx_gvec(DisasContext *s, arg_rmrr *a, GVecGen2sFn *gvec_fn, if (a->vm && s->vl_eq_vlmax) { TCGv_i64 src1 = tcg_temp_new_i64(); - TCGv tmp = tcg_temp_new(); - gen_get_gpr(tmp, a->rs1); - tcg_gen_ext_tl_i64(src1, tmp); + 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); - tcg_temp_free(tmp); return true; } return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fn, s); @@ -1014,14 +982,14 @@ static bool opivi_trans(uint32_t vd, uint32_t imm, uint32_t vs2, uint32_t vm, mask = tcg_temp_new_ptr(); src2 = tcg_temp_new_ptr(); if (zx) { - src1 = tcg_const_tl(imm); + src1 = tcg_constant_tl(imm); } else { - src1 = tcg_const_tl(sextract64(imm, 0, 5)); + 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_const_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + 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)); @@ -1032,8 +1000,6 @@ static bool opivi_trans(uint32_t vd, uint32_t imm, uint32_t vs2, uint32_t vm, tcg_temp_free_ptr(dest); tcg_temp_free_ptr(mask); tcg_temp_free_ptr(src2); - tcg_temp_free(src1); - tcg_temp_free_i32(desc); gen_set_label(over); return true; } @@ -1080,9 +1046,8 @@ 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_const_i64(c); + TCGv_i64 tmp = tcg_constant_i64(c); tcg_gen_gvec_rsubs(vece, dofs, aofs, tmp, oprsz, maxsz); - tcg_temp_free_i64(tmp); } GEN_OPIVI_GVEC_TRANS(vrsub_vi, 0, vrsub_vx, rsubi) @@ -1408,16 +1373,13 @@ do_opivx_gvec_shift(DisasContext *s, arg_rmrr *a, GVecGen2sFn32 *gvec_fn, if (a->vm && s->vl_eq_vlmax) { TCGv_i32 src1 = tcg_temp_new_i32(); - TCGv tmp = tcg_temp_new(); - gen_get_gpr(tmp, a->rs1); - tcg_gen_trunc_tl_i32(src1, tmp); + 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); - tcg_temp_free(tmp); return true; } return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fn, s); @@ -1675,14 +1637,13 @@ static bool trans_vmv_v_x(DisasContext *s, arg_vmv_v_x *a) TCGLabel *over = gen_new_label(); tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); - s1 = tcg_temp_new(); - gen_get_gpr(s1, a->rs1); + 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_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); @@ -1692,16 +1653,14 @@ static bool trans_vmv_v_x(DisasContext *s, arg_vmv_v_x *a) }; tcg_gen_ext_tl_i64(s1_i64, s1); - desc = tcg_const_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + 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_i32(desc); tcg_temp_free_i64(s1_i64); } - tcg_temp_free(s1); gen_set_label(over); return true; } @@ -1729,15 +1688,13 @@ static bool trans_vmv_v_i(DisasContext *s, arg_vmv_v_i *a) TCGLabel *over = gen_new_label(); tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); - s1 = tcg_const_i64(simm); + s1 = tcg_constant_i64(simm); dest = tcg_temp_new_ptr(); - desc = tcg_const_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + 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); - tcg_temp_free_i32(desc); - tcg_temp_free_i64(s1); gen_set_label(over); } return true; @@ -1866,7 +1823,7 @@ static bool opfvf_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, dest = tcg_temp_new_ptr(); mask = tcg_temp_new_ptr(); src2 = tcg_temp_new_ptr(); - desc = tcg_const_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + 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)); @@ -1877,7 +1834,6 @@ static bool opfvf_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, tcg_temp_free_ptr(dest); tcg_temp_free_ptr(mask); tcg_temp_free_ptr(src2); - tcg_temp_free_i32(desc); gen_set_label(over); return true; } @@ -2231,12 +2187,11 @@ static bool trans_vfmv_v_f(DisasContext *s, arg_vfmv_v_f *a) tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); dest = tcg_temp_new_ptr(); - desc = tcg_const_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + 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); - tcg_temp_free_i32(desc); gen_set_label(over); } return true; @@ -2427,19 +2382,17 @@ static bool trans_vmpopc_m(DisasContext *s, arg_rmr *a) mask = tcg_temp_new_ptr(); src2 = tcg_temp_new_ptr(); - dst = tcg_temp_new(); - desc = tcg_const_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + 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(a->rd, dst); + gen_set_gpr(s, a->rd, dst); tcg_temp_free_ptr(mask); tcg_temp_free_ptr(src2); - tcg_temp_free(dst); - tcg_temp_free_i32(desc); return true; } return false; @@ -2459,19 +2412,17 @@ static bool trans_vmfirst_m(DisasContext *s, arg_rmr *a) mask = tcg_temp_new_ptr(); src2 = tcg_temp_new_ptr(); - dst = tcg_temp_new(); - desc = tcg_const_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + 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(a->rd, dst); + gen_set_gpr(s, a->rd, dst); tcg_temp_free_ptr(mask); tcg_temp_free_ptr(src2); - tcg_temp_free(dst); - tcg_temp_free_i32(desc); return true; } return false; @@ -2636,15 +2587,13 @@ static void vec_element_loadx(DisasContext *s, TCGv_i64 dest, tcg_temp_free_i32(ofs); /* Flush out-of-range indexing to zero. */ - t_vlmax = tcg_const_i64(vlmax); - t_zero = tcg_const_i64(0); + 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_vlmax); - tcg_temp_free_i64(t_zero); tcg_temp_free_i64(t_idx); } @@ -2657,7 +2606,7 @@ static void vec_element_loadi(DisasContext *s, TCGv_i64 dest, static bool trans_vext_x_v(DisasContext *s, arg_r *a) { TCGv_i64 tmp = tcg_temp_new_i64(); - TCGv dest = tcg_temp_new(); + TCGv dest = dest_gpr(s, a->rd); if (a->rs1 == 0) { /* Special case vmv.x.s rd, vs2. */ @@ -2667,10 +2616,10 @@ static bool trans_vext_x_v(DisasContext *s, arg_r *a) 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(a->rd, dest); - tcg_temp_free(dest); + tcg_gen_trunc_i64_tl(dest, tmp); + gen_set_gpr(s, a->rd, dest); + tcg_temp_free_i64(tmp); return true; } diff --git a/target/riscv/op_helper.c b/target/riscv/op_helper.c index 3c48e739ac..ee7c24efe7 100644 --- a/target/riscv/op_helper.c +++ b/target/riscv/op_helper.c @@ -37,11 +37,10 @@ void helper_raise_exception(CPURISCVState *env, uint32_t exception) riscv_raise_exception(env, exception, 0); } -target_ulong helper_csrrw(CPURISCVState *env, target_ulong src, - target_ulong csr) +target_ulong helper_csrr(CPURISCVState *env, int csr) { target_ulong val = 0; - RISCVException ret = riscv_csrrw(env, csr, &val, src, -1); + RISCVException ret = riscv_csrrw(env, csr, &val, 0, 0); if (ret != RISCV_EXCP_NONE) { riscv_raise_exception(env, ret, GETPC()); @@ -49,23 +48,20 @@ target_ulong helper_csrrw(CPURISCVState *env, target_ulong src, return val; } -target_ulong helper_csrrs(CPURISCVState *env, target_ulong src, - target_ulong csr, target_ulong rs1_pass) +void helper_csrw(CPURISCVState *env, int csr, target_ulong src) { - target_ulong val = 0; - RISCVException ret = riscv_csrrw(env, csr, &val, -1, rs1_pass ? src : 0); + RISCVException ret = riscv_csrrw(env, csr, NULL, src, -1); if (ret != RISCV_EXCP_NONE) { riscv_raise_exception(env, ret, GETPC()); } - return val; } -target_ulong helper_csrrc(CPURISCVState *env, target_ulong src, - target_ulong csr, target_ulong rs1_pass) +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, 0, rs1_pass ? src : 0); + RISCVException ret = riscv_csrrw(env, csr, &val, src, write_mask); if (ret != RISCV_EXCP_NONE) { riscv_raise_exception(env, ret, GETPC()); diff --git a/target/riscv/translate.c b/target/riscv/translate.c index 6983be5723..e356fc6c46 100644 --- a/target/riscv/translate.c +++ b/target/riscv/translate.c @@ -39,15 +39,25 @@ static TCGv load_val; #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; - bool virt_enabled; + target_ulong misa; uint32_t opcode; uint32_t mstatus_fs; - target_ulong misa; 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 @@ -55,6 +65,8 @@ typedef struct DisasContext { to any system register, which includes CSR_FRM, so we do not have to reset this known value. */ int frm; + bool w; + bool virt_enabled; bool ext_ifencei; bool hlsx; /* vector extension */ @@ -64,7 +76,11 @@ typedef struct DisasContext { 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]; } DisasContext; static inline bool has_ext(DisasContext *ctx, uint32_t ext) @@ -83,6 +99,13 @@ static inline bool is_32bit(DisasContext *ctx) } #endif +/* The word size for this operation. */ +static inline int oper_len(DisasContext *ctx) +{ + return ctx->w ? 32 : TARGET_LONG_BITS; +} + + /* * 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. @@ -104,20 +127,16 @@ static void gen_nanbox_s(TCGv_i64 out, TCGv_i64 in) */ static void gen_check_nanbox_s(TCGv_i64 out, TCGv_i64 in) { - TCGv_i64 t_max = tcg_const_i64(0xffffffff00000000ull); - TCGv_i64 t_nan = tcg_const_i64(0xffffffff7fc00000ull); + 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); - tcg_temp_free_i64(t_max); - tcg_temp_free_i64(t_nan); } static void generate_exception(DisasContext *ctx, int excp) { tcg_gen_movi_tl(cpu_pc, ctx->base.pc_next); - TCGv_i32 helper_tmp = tcg_const_i32(excp); - gen_helper_raise_exception(cpu_env, helper_tmp); - tcg_temp_free_i32(helper_tmp); + gen_helper_raise_exception(cpu_env, tcg_constant_i32(excp)); ctx->base.is_jmp = DISAS_NORETURN; } @@ -125,17 +144,13 @@ 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)); - TCGv_i32 helper_tmp = tcg_const_i32(excp); - gen_helper_raise_exception(cpu_env, helper_tmp); - tcg_temp_free_i32(helper_tmp); + gen_helper_raise_exception(cpu_env, tcg_constant_i32(excp)); ctx->base.is_jmp = DISAS_NORETURN; } static void gen_exception_debug(void) { - TCGv_i32 helper_tmp = tcg_const_i32(EXCP_DEBUG); - gen_helper_raise_exception(cpu_env, helper_tmp); - tcg_temp_free_i32(helper_tmp); + gen_helper_raise_exception(cpu_env, tcg_constant_i32(EXCP_DEBUG)); } /* Wrapper around tcg_gen_exit_tb that handles single stepping */ @@ -180,151 +195,60 @@ static void gen_goto_tb(DisasContext *ctx, int n, target_ulong dest) } } -/* Wrapper for getting reg values - need to check of reg is zero since - * cpu_gpr[0] is not actually allocated +/* + * 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 inline void gen_get_gpr(TCGv t, int reg_num) +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) { - tcg_gen_movi_tl(t, 0); - } else { - tcg_gen_mov_tl(t, cpu_gpr[reg_num]); + return ctx->zero; } -} -/* Wrapper for setting reg values - need to check of reg is zero since - * cpu_gpr[0] is not actually allocated. this is more for safety purposes, - * since we usually avoid calling the OP_TYPE_gen function if we see a write to - * $zero - */ -static inline void gen_set_gpr(int reg_num_dst, TCGv t) -{ - if (reg_num_dst != 0) { - tcg_gen_mov_tl(cpu_gpr[reg_num_dst], t); + switch (ctx->w ? ext : EXT_NONE) { + case EXT_NONE: + return cpu_gpr[reg_num]; + 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; } + g_assert_not_reached(); } -static void gen_mulhsu(TCGv ret, TCGv arg1, TCGv arg2) +static TCGv dest_gpr(DisasContext *ctx, int reg_num) { - 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); + if (reg_num == 0 || ctx->w) { + return temp_new(ctx); + } + return cpu_gpr[reg_num]; } -static void gen_div(TCGv ret, TCGv source1, TCGv source2) +static void gen_set_gpr(DisasContext *ctx, int reg_num, TCGv t) { - TCGv cond1, cond2, zeroreg, resultopt1; - /* - * Handle by altering args to tcg_gen_div to produce req'd results: - * For overflow: want source1 in source1 and 1 in source2 - * For div by zero: want -1 in source1 and 1 in source2 -> -1 result - */ - cond1 = tcg_temp_new(); - cond2 = tcg_temp_new(); - zeroreg = tcg_const_tl(0); - resultopt1 = tcg_temp_new(); - - tcg_gen_movi_tl(resultopt1, (target_ulong)-1); - tcg_gen_setcondi_tl(TCG_COND_EQ, cond2, source2, (target_ulong)(~0L)); - tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source1, - ((target_ulong)1) << (TARGET_LONG_BITS - 1)); - tcg_gen_and_tl(cond1, cond1, cond2); /* cond1 = overflow */ - tcg_gen_setcondi_tl(TCG_COND_EQ, cond2, source2, 0); /* cond2 = div 0 */ - /* if div by zero, set source1 to -1, otherwise don't change */ - tcg_gen_movcond_tl(TCG_COND_EQ, source1, cond2, zeroreg, source1, - resultopt1); - /* if overflow or div by zero, set source2 to 1, else don't change */ - tcg_gen_or_tl(cond1, cond1, cond2); - tcg_gen_movi_tl(resultopt1, (target_ulong)1); - tcg_gen_movcond_tl(TCG_COND_EQ, source2, cond1, zeroreg, source2, - resultopt1); - tcg_gen_div_tl(ret, source1, source2); - - tcg_temp_free(cond1); - tcg_temp_free(cond2); - tcg_temp_free(zeroreg); - tcg_temp_free(resultopt1); -} - -static void gen_divu(TCGv ret, TCGv source1, TCGv source2) -{ - TCGv cond1, zeroreg, resultopt1; - cond1 = tcg_temp_new(); - - zeroreg = tcg_const_tl(0); - resultopt1 = tcg_temp_new(); - - tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source2, 0); - tcg_gen_movi_tl(resultopt1, (target_ulong)-1); - tcg_gen_movcond_tl(TCG_COND_EQ, source1, cond1, zeroreg, source1, - resultopt1); - tcg_gen_movi_tl(resultopt1, (target_ulong)1); - tcg_gen_movcond_tl(TCG_COND_EQ, source2, cond1, zeroreg, source2, - resultopt1); - tcg_gen_divu_tl(ret, source1, source2); - - tcg_temp_free(cond1); - tcg_temp_free(zeroreg); - tcg_temp_free(resultopt1); -} - -static void gen_rem(TCGv ret, TCGv source1, TCGv source2) -{ - TCGv cond1, cond2, zeroreg, resultopt1; - - cond1 = tcg_temp_new(); - cond2 = tcg_temp_new(); - zeroreg = tcg_const_tl(0); - resultopt1 = tcg_temp_new(); - - tcg_gen_movi_tl(resultopt1, 1L); - tcg_gen_setcondi_tl(TCG_COND_EQ, cond2, source2, (target_ulong)-1); - tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source1, - (target_ulong)1 << (TARGET_LONG_BITS - 1)); - tcg_gen_and_tl(cond2, cond1, cond2); /* cond1 = overflow */ - tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source2, 0); /* cond2 = div 0 */ - /* if overflow or div by zero, set source2 to 1, else don't change */ - tcg_gen_or_tl(cond2, cond1, cond2); - tcg_gen_movcond_tl(TCG_COND_EQ, source2, cond2, zeroreg, source2, - resultopt1); - tcg_gen_rem_tl(resultopt1, source1, source2); - /* if div by zero, just return the original dividend */ - tcg_gen_movcond_tl(TCG_COND_EQ, ret, cond1, zeroreg, resultopt1, - source1); - - tcg_temp_free(cond1); - tcg_temp_free(cond2); - tcg_temp_free(zeroreg); - tcg_temp_free(resultopt1); -} - -static void gen_remu(TCGv ret, TCGv source1, TCGv source2) -{ - TCGv cond1, zeroreg, resultopt1; - cond1 = tcg_temp_new(); - zeroreg = tcg_const_tl(0); - resultopt1 = tcg_temp_new(); - - tcg_gen_movi_tl(resultopt1, (target_ulong)1); - tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source2, 0); - tcg_gen_movcond_tl(TCG_COND_EQ, source2, cond1, zeroreg, source2, - resultopt1); - tcg_gen_remu_tl(resultopt1, source1, source2); - /* if div by zero, just return the original dividend */ - tcg_gen_movcond_tl(TCG_COND_EQ, ret, cond1, zeroreg, resultopt1, - source1); - - tcg_temp_free(cond1); - tcg_temp_free(zeroreg); - tcg_temp_free(resultopt1); + if (reg_num != 0) { + if (ctx->w) { + tcg_gen_ext32s_tl(cpu_gpr[reg_num], t); + } else { + tcg_gen_mov_tl(cpu_gpr[reg_num], t); + } + } } static void gen_jal(DisasContext *ctx, int rd, target_ulong imm) @@ -384,15 +308,11 @@ static inline void mark_fs_dirty(DisasContext *ctx) { } static void gen_set_rm(DisasContext *ctx, int rm) { - TCGv_i32 t0; - if (ctx->frm == rm) { return; } ctx->frm = rm; - t0 = tcg_const_i32(rm); - gen_helper_set_rounding_mode(cpu_env, t0); - tcg_temp_free_i32(t0); + gen_helper_set_rounding_mode(cpu_env, tcg_constant_i32(rm)); } static int ex_plus_1(DisasContext *ctx, int nf) @@ -437,355 +357,108 @@ static int ex_rvc_shifti(DisasContext *ctx, int imm) /* 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, +static bool gen_arith_imm_fn(DisasContext *ctx, arg_i *a, DisasExtend ext, void (*func)(TCGv, TCGv, target_long)) { - TCGv source1; - source1 = tcg_temp_new(); + TCGv dest = dest_gpr(ctx, a->rd); + TCGv src1 = get_gpr(ctx, a->rs1, ext); - gen_get_gpr(source1, a->rs1); + func(dest, src1, a->imm); - (*func)(source1, source1, a->imm); - - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); + gen_set_gpr(ctx, a->rd, dest); return true; } -static bool gen_arith_imm_tl(DisasContext *ctx, arg_i *a, +static bool gen_arith_imm_tl(DisasContext *ctx, arg_i *a, DisasExtend ext, void (*func)(TCGv, TCGv, TCGv)) { - TCGv source1, source2; - source1 = tcg_temp_new(); - source2 = tcg_temp_new(); + TCGv dest = dest_gpr(ctx, a->rd); + TCGv src1 = get_gpr(ctx, a->rs1, ext); + TCGv src2 = tcg_constant_tl(a->imm); - gen_get_gpr(source1, a->rs1); - tcg_gen_movi_tl(source2, a->imm); + func(dest, src1, src2); - (*func)(source1, source1, source2); - - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - tcg_temp_free(source2); + gen_set_gpr(ctx, a->rd, dest); return true; } -static void gen_addw(TCGv ret, TCGv arg1, TCGv arg2) +static bool gen_arith(DisasContext *ctx, arg_r *a, DisasExtend ext, + void (*func)(TCGv, TCGv, TCGv)) { - tcg_gen_add_tl(ret, arg1, arg2); - tcg_gen_ext32s_tl(ret, ret); -} + TCGv dest = dest_gpr(ctx, a->rd); + TCGv src1 = get_gpr(ctx, a->rs1, ext); + TCGv src2 = get_gpr(ctx, a->rs2, ext); -static void gen_subw(TCGv ret, TCGv arg1, TCGv arg2) -{ - tcg_gen_sub_tl(ret, arg1, arg2); - tcg_gen_ext32s_tl(ret, ret); -} + func(dest, src1, src2); -static void gen_mulw(TCGv ret, TCGv arg1, TCGv arg2) -{ - tcg_gen_mul_tl(ret, arg1, arg2); - tcg_gen_ext32s_tl(ret, ret); -} - -static bool gen_arith_div_w(DisasContext *ctx, arg_r *a, - void(*func)(TCGv, TCGv, TCGv)) -{ - TCGv source1, source2; - source1 = tcg_temp_new(); - source2 = tcg_temp_new(); - - gen_get_gpr(source1, a->rs1); - gen_get_gpr(source2, a->rs2); - tcg_gen_ext32s_tl(source1, source1); - tcg_gen_ext32s_tl(source2, source2); - - (*func)(source1, source1, source2); - - tcg_gen_ext32s_tl(source1, source1); - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - tcg_temp_free(source2); + gen_set_gpr(ctx, a->rd, dest); return true; } -static bool gen_arith_div_uw(DisasContext *ctx, arg_r *a, - void(*func)(TCGv, TCGv, TCGv)) +static bool gen_shift_imm_fn(DisasContext *ctx, arg_shift *a, DisasExtend ext, + void (*func)(TCGv, TCGv, target_long)) { - TCGv source1, source2; - source1 = tcg_temp_new(); - source2 = tcg_temp_new(); + TCGv dest, src1; + int max_len = oper_len(ctx); - gen_get_gpr(source1, a->rs1); - gen_get_gpr(source2, a->rs2); - tcg_gen_ext32u_tl(source1, source1); - tcg_gen_ext32u_tl(source2, source2); - - (*func)(source1, source1, source2); - - tcg_gen_ext32s_tl(source1, source1); - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - tcg_temp_free(source2); - return true; -} - -static void gen_pack(TCGv ret, TCGv arg1, TCGv arg2) -{ - tcg_gen_deposit_tl(ret, arg1, arg2, - TARGET_LONG_BITS / 2, - TARGET_LONG_BITS / 2); -} - -static void gen_packu(TCGv ret, TCGv arg1, TCGv arg2) -{ - TCGv t = tcg_temp_new(); - tcg_gen_shri_tl(t, arg1, TARGET_LONG_BITS / 2); - tcg_gen_deposit_tl(ret, arg2, t, 0, TARGET_LONG_BITS / 2); - tcg_temp_free(t); -} - -static void gen_packh(TCGv ret, TCGv arg1, TCGv arg2) -{ - TCGv t = tcg_temp_new(); - tcg_gen_ext8u_tl(t, arg2); - tcg_gen_deposit_tl(ret, arg1, t, 8, TARGET_LONG_BITS - 8); - tcg_temp_free(t); -} - -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 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 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 void gen_bext(TCGv ret, TCGv arg1, TCGv shamt) -{ - tcg_gen_shr_tl(ret, arg1, shamt); - tcg_gen_andi_tl(ret, ret, 1); -} - -static void gen_slo(TCGv ret, TCGv arg1, TCGv arg2) -{ - tcg_gen_not_tl(ret, arg1); - tcg_gen_shl_tl(ret, ret, arg2); - tcg_gen_not_tl(ret, ret); -} - -static void gen_sro(TCGv ret, TCGv arg1, TCGv arg2) -{ - tcg_gen_not_tl(ret, arg1); - tcg_gen_shr_tl(ret, ret, arg2); - tcg_gen_not_tl(ret, ret); -} - -static bool gen_grevi(DisasContext *ctx, arg_grevi *a) -{ - TCGv source1 = tcg_temp_new(); - TCGv source2; - - gen_get_gpr(source1, a->rs1); - - if (a->shamt == (TARGET_LONG_BITS - 8)) { - /* rev8, byte swaps */ - tcg_gen_bswap_tl(source1, source1); - } else { - source2 = tcg_temp_new(); - tcg_gen_movi_tl(source2, a->shamt); - gen_helper_grev(source1, source1, source2); - tcg_temp_free(source2); + if (a->shamt >= max_len) { + return false; } - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); + 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; } -#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) - -static void gen_ctzw(TCGv ret, TCGv arg1) +static bool gen_shift_imm_tl(DisasContext *ctx, arg_shift *a, DisasExtend ext, + void (*func)(TCGv, TCGv, TCGv)) { - tcg_gen_ori_tl(ret, arg1, (target_ulong)MAKE_64BIT_MASK(32, 32)); - tcg_gen_ctzi_tl(ret, ret, 64); -} + TCGv dest, src1, src2; + int max_len = oper_len(ctx); -static void gen_clzw(TCGv ret, TCGv arg1) -{ - tcg_gen_ext32u_tl(ret, arg1); - tcg_gen_clzi_tl(ret, ret, 64); - tcg_gen_subi_tl(ret, ret, 32); -} + if (a->shamt >= max_len) { + return false; + } -static void gen_cpopw(TCGv ret, TCGv arg1) -{ - tcg_gen_ext32u_tl(arg1, arg1); - tcg_gen_ctpop_tl(ret, arg1); -} + dest = dest_gpr(ctx, a->rd); + src1 = get_gpr(ctx, a->rs1, ext); + src2 = tcg_constant_tl(a->shamt); -static void gen_packw(TCGv ret, TCGv arg1, TCGv arg2) -{ - TCGv t = tcg_temp_new(); - tcg_gen_ext16s_tl(t, arg2); - tcg_gen_deposit_tl(ret, arg1, t, 16, 48); - tcg_temp_free(t); -} + func(dest, src1, src2); -static void gen_packuw(TCGv ret, TCGv arg1, TCGv arg2) -{ - TCGv t = tcg_temp_new(); - tcg_gen_shri_tl(t, arg1, 16); - tcg_gen_deposit_tl(ret, arg2, t, 0, 16); - tcg_gen_ext32s_tl(ret, ret); - tcg_temp_free(t); -} - -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 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 void gen_grevw(TCGv ret, TCGv arg1, TCGv arg2) -{ - tcg_gen_ext32u_tl(arg1, arg1); - gen_helper_grev(ret, arg1, arg2); -} - -static void gen_gorcw(TCGv ret, TCGv arg1, TCGv arg2) -{ - tcg_gen_ext32u_tl(arg1, arg1); - gen_helper_gorcw(ret, arg1, arg2); -} - -#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) - -static void gen_add_uw(TCGv ret, TCGv arg1, TCGv arg2) -{ - tcg_gen_ext32u_tl(arg1, arg1); - tcg_gen_add_tl(ret, arg1, arg2); -} - -static bool gen_arith(DisasContext *ctx, arg_r *a, - void(*func)(TCGv, TCGv, TCGv)) -{ - TCGv source1, source2; - source1 = tcg_temp_new(); - source2 = tcg_temp_new(); - - gen_get_gpr(source1, a->rs1); - gen_get_gpr(source2, a->rs2); - - (*func)(source1, source1, source2); - - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - tcg_temp_free(source2); + gen_set_gpr(ctx, a->rd, dest); return true; } -static bool gen_shift(DisasContext *ctx, arg_r *a, - void(*func)(TCGv, TCGv, TCGv)) +static bool gen_shift(DisasContext *ctx, arg_r *a, DisasExtend ext, + void (*func)(TCGv, TCGv, TCGv)) { - TCGv source1 = tcg_temp_new(); - TCGv source2 = tcg_temp_new(); + 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(); - gen_get_gpr(source1, a->rs1); - gen_get_gpr(source2, a->rs2); + tcg_gen_andi_tl(ext2, src2, oper_len(ctx) - 1); + func(dest, src1, ext2); - tcg_gen_andi_tl(source2, source2, TARGET_LONG_BITS - 1); - (*func)(source1, source1, source2); + gen_set_gpr(ctx, a->rd, dest); + tcg_temp_free(ext2); + return true; +} - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - tcg_temp_free(source2); +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; } @@ -798,88 +471,6 @@ static uint32_t opcode_at(DisasContextBase *dcbase, target_ulong pc) return cpu_ldl_code(env, pc); } -static bool gen_shifti(DisasContext *ctx, arg_shift *a, - void(*func)(TCGv, TCGv, TCGv)) -{ - if (a->shamt >= TARGET_LONG_BITS) { - return false; - } - - TCGv source1 = tcg_temp_new(); - TCGv source2 = tcg_temp_new(); - - gen_get_gpr(source1, a->rs1); - - tcg_gen_movi_tl(source2, a->shamt); - (*func)(source1, source1, source2); - - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - tcg_temp_free(source2); - return true; -} - -static bool gen_shiftw(DisasContext *ctx, arg_r *a, - void(*func)(TCGv, TCGv, TCGv)) -{ - TCGv source1 = tcg_temp_new(); - TCGv source2 = tcg_temp_new(); - - gen_get_gpr(source1, a->rs1); - gen_get_gpr(source2, a->rs2); - - tcg_gen_andi_tl(source2, source2, 31); - (*func)(source1, source1, source2); - tcg_gen_ext32s_tl(source1, source1); - - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - tcg_temp_free(source2); - return true; -} - -static bool gen_shiftiw(DisasContext *ctx, arg_shift *a, - void(*func)(TCGv, TCGv, TCGv)) -{ - TCGv source1 = tcg_temp_new(); - TCGv source2 = tcg_temp_new(); - - gen_get_gpr(source1, a->rs1); - tcg_gen_movi_tl(source2, a->shamt); - - (*func)(source1, source1, source2); - tcg_gen_ext32s_tl(source1, source1); - - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - tcg_temp_free(source2); - return true; -} - -static void gen_ctz(TCGv ret, TCGv arg1) -{ - tcg_gen_ctzi_tl(ret, arg1, TARGET_LONG_BITS); -} - -static void gen_clz(TCGv ret, TCGv arg1) -{ - tcg_gen_clzi_tl(ret, arg1, TARGET_LONG_BITS); -} - -static bool gen_unary(DisasContext *ctx, arg_r2 *a, - void(*func)(TCGv, TCGv)) -{ - TCGv source = tcg_temp_new(); - - gen_get_gpr(source, a->rs1); - - (*func)(source, source); - - gen_set_gpr(a->rd, source); - tcg_temp_free(source); - return true; -} - /* Include insn module translation function */ #include "insn_trans/trans_rvi.c.inc" #include "insn_trans/trans_rvm.c.inc" @@ -948,6 +539,11 @@ static void riscv_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) ctx->mlen = 1 << (ctx->sew + 3 - ctx->lmul); ctx->vl_eq_vlmax = FIELD_EX32(tb_flags, TB_FLAGS, VL_EQ_VLMAX); ctx->cs = cs; + ctx->w = false; + ctx->ntemp = 0; + memset(ctx->temp, 0, sizeof(ctx->temp)); + + ctx->zero = tcg_constant_tl(0); } static void riscv_tr_tb_start(DisasContextBase *db, CPUState *cpu) @@ -969,6 +565,13 @@ static void riscv_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) decode_opc(env, ctx, opcode16); ctx->base.pc_next = ctx->pc_succ_insn; + ctx->w = false; + + 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; @@ -1029,9 +632,11 @@ 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 gen_get_gpr helper functions when accessing */ - /* registers, unless you specifically block reads/writes to reg 0 */ + /* + * 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++) { diff --git a/tests/tcg/riscv64/Makefile.target b/tests/tcg/riscv64/Makefile.target new file mode 100644 index 0000000000..d41bf6d60d --- /dev/null +++ b/tests/tcg/riscv64/Makefile.target @@ -0,0 +1,5 @@ +# -*- Mode: makefile -*- +# RISC-V specific tweaks + +VPATH += $(SRC_PATH)/tests/tcg/riscv64 +TESTS += test-div diff --git a/tests/tcg/riscv64/test-div.c b/tests/tcg/riscv64/test-div.c new file mode 100644 index 0000000000..a90480be3f --- /dev/null +++ b/tests/tcg/riscv64/test-div.c @@ -0,0 +1,58 @@ +#include +#include + +struct TestS { + long x, y, q, r; +}; + +static struct TestS test_s[] = { + { 4, 2, 2, 0 }, /* normal cases */ + { 9, 7, 1, 2 }, + { 0, 0, -1, 0 }, /* div by zero cases */ + { 9, 0, -1, 9 }, + { LONG_MIN, -1, LONG_MIN, 0 }, /* overflow case */ +}; + +struct TestU { + unsigned long x, y, q, r; +}; + +static struct TestU test_u[] = { + { 4, 2, 2, 0 }, /* normal cases */ + { 9, 7, 1, 2 }, + { 0, 0, ULONG_MAX, 0 }, /* div by zero cases */ + { 9, 0, ULONG_MAX, 9 }, +}; + +#define ARRAY_SIZE(X) (sizeof(X) / sizeof(*(X))) + +int main (void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(test_s); i++) { + long q, r; + + asm("div %0, %2, %3\n\t" + "rem %1, %2, %3" + : "=&r" (q), "=r" (r) + : "r" (test_s[i].x), "r" (test_s[i].y)); + + assert(q == test_s[i].q); + assert(r == test_s[i].r); + } + + for (i = 0; i < ARRAY_SIZE(test_u); i++) { + unsigned long q, r; + + asm("divu %0, %2, %3\n\t" + "remu %1, %2, %3" + : "=&r" (q), "=r" (r) + : "r" (test_u[i].x), "r" (test_u[i].y)); + + assert(q == test_u[i].q); + assert(r == test_u[i].r); + } + + return 0; +}