qemu/target/riscv/translate.c

797 lines
22 KiB
C
Raw Normal View History

/*
* RISC-V emulation for qemu: main translation routines.
*
* Copyright (c) 2016-2017 Sagar Karandikar, sagark@eecs.berkeley.edu
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2 or later, as published by the Free Software Foundation.
*
* This program is distributed in the hope it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*
* You should have received a copy of the GNU General Public License along with
* this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include "qemu/osdep.h"
#include "qemu/log.h"
#include "cpu.h"
#include "tcg-op.h"
#include "disas/disas.h"
#include "exec/cpu_ldst.h"
#include "exec/exec-all.h"
#include "exec/helper-proto.h"
#include "exec/helper-gen.h"
#include "exec/translator.h"
#include "exec/log.h"
#include "instmap.h"
/* global register indices */
static TCGv cpu_gpr[32], cpu_pc;
static TCGv_i64 cpu_fpr[32]; /* assume F and D extensions */
static TCGv load_res;
static TCGv load_val;
#include "exec/gen-icount.h"
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;
uint32_t opcode;
uint32_t mstatus_fs;
uint32_t 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
no previous fp instruction. Note that we exit the TB when writing
to any system register, which includes CSR_FRM, so we do not have
to reset this known value. */
int frm;
} DisasContext;
#ifdef TARGET_RISCV64
/* convert riscv funct3 to qemu memop for load/store */
static const int tcg_memop_lookup[8] = {
[0 ... 7] = -1,
[0] = MO_SB,
[1] = MO_TESW,
[2] = MO_TESL,
[4] = MO_UB,
[5] = MO_TEUW,
#ifdef TARGET_RISCV64
[3] = MO_TEQ,
[6] = MO_TEUL,
#endif
};
#endif
#ifdef TARGET_RISCV64
#define CASE_OP_32_64(X) case X: case glue(X, W)
#else
#define CASE_OP_32_64(X) case X
#endif
static inline bool has_ext(DisasContext *ctx, uint32_t ext)
{
return ctx->misa & ext;
}
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);
ctx->base.is_jmp = DISAS_NORETURN;
}
static void generate_exception_mbadaddr(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);
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);
}
static void gen_exception_illegal(DisasContext *ctx)
{
generate_exception(ctx, RISCV_EXCP_ILLEGAL_INST);
}
static void gen_exception_inst_addr_mis(DisasContext *ctx)
{
generate_exception_mbadaddr(ctx, RISCV_EXCP_INST_ADDR_MIS);
}
static inline bool use_goto_tb(DisasContext *ctx, target_ulong dest)
{
if (unlikely(ctx->base.singlestep_enabled)) {
return false;
}
#ifndef CONFIG_USER_ONLY
return (ctx->base.tb->pc & TARGET_PAGE_MASK) == (dest & TARGET_PAGE_MASK);
#else
return true;
#endif
}
static void gen_goto_tb(DisasContext *ctx, int n, target_ulong dest)
{
if (use_goto_tb(ctx, dest)) {
/* chaining is only allowed when the jump is to the same page */
tcg_gen_goto_tb(n);
tcg_gen_movi_tl(cpu_pc, dest);
tcg_gen_exit_tb(ctx->base.tb, n);
} else {
tcg_gen_movi_tl(cpu_pc, dest);
if (ctx->base.singlestep_enabled) {
gen_exception_debug();
} else {
tcg_gen_lookup_and_goto_ptr();
}
}
}
/* Wrapper for getting reg values - need to check of reg is zero since
* cpu_gpr[0] is not actually allocated
*/
static inline void gen_get_gpr(TCGv t, int reg_num)
{
if (reg_num == 0) {
tcg_gen_movi_tl(t, 0);
} else {
tcg_gen_mov_tl(t, cpu_gpr[reg_num]);
}
}
/* 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);
}
}
static void gen_mulhsu(TCGv ret, TCGv arg1, TCGv arg2)
{
TCGv rl = tcg_temp_new();
TCGv rh = tcg_temp_new();
tcg_gen_mulu2_tl(rl, rh, arg1, arg2);
/* fix up for one negative */
tcg_gen_sari_tl(rl, arg1, TARGET_LONG_BITS - 1);
tcg_gen_and_tl(rl, rl, arg2);
tcg_gen_sub_tl(ret, rh, rl);
tcg_temp_free(rl);
tcg_temp_free(rh);
}
static void gen_div(TCGv ret, TCGv source1, TCGv source2)
{
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);
}
static void gen_jal(DisasContext *ctx, int rd, target_ulong imm)
{
target_ulong next_pc;
/* check misaligned: */
next_pc = ctx->base.pc_next + imm;
if (!has_ext(ctx, RVC)) {
if ((next_pc & 0x3) != 0) {
gen_exception_inst_addr_mis(ctx);
return;
}
}
if (rd != 0) {
tcg_gen_movi_tl(cpu_gpr[rd], ctx->pc_succ_insn);
}
gen_goto_tb(ctx, 0, ctx->base.pc_next + imm); /* must use this for safety */
ctx->base.is_jmp = DISAS_NORETURN;
}
#ifdef TARGET_RISCV64
static void gen_load_c(DisasContext *ctx, uint32_t opc, int rd, int rs1,
target_long imm)
{
TCGv t0 = tcg_temp_new();
TCGv t1 = tcg_temp_new();
gen_get_gpr(t0, rs1);
tcg_gen_addi_tl(t0, t0, imm);
int memop = tcg_memop_lookup[(opc >> 12) & 0x7];
if (memop < 0) {
gen_exception_illegal(ctx);
return;
}
tcg_gen_qemu_ld_tl(t1, t0, ctx->mem_idx, memop);
gen_set_gpr(rd, t1);
tcg_temp_free(t0);
tcg_temp_free(t1);
}
static void gen_store_c(DisasContext *ctx, uint32_t opc, int rs1, int rs2,
target_long imm)
{
TCGv t0 = tcg_temp_new();
TCGv dat = tcg_temp_new();
gen_get_gpr(t0, rs1);
tcg_gen_addi_tl(t0, t0, imm);
gen_get_gpr(dat, rs2);
int memop = tcg_memop_lookup[(opc >> 12) & 0x7];
if (memop < 0) {
gen_exception_illegal(ctx);
return;
}
tcg_gen_qemu_st_tl(dat, t0, ctx->mem_idx, memop);
tcg_temp_free(t0);
tcg_temp_free(dat);
}
#endif
#ifndef CONFIG_USER_ONLY
/* The states of mstatus_fs are:
* 0 = disabled, 1 = initial, 2 = clean, 3 = dirty
* We will have already diagnosed disabled state,
* and need to turn initial/clean into dirty.
*/
static void mark_fs_dirty(DisasContext *ctx)
{
TCGv tmp;
if (ctx->mstatus_fs == MSTATUS_FS) {
return;
}
/* Remember the state change for the rest of the TB. */
ctx->mstatus_fs = MSTATUS_FS;
tmp = tcg_temp_new();
tcg_gen_ld_tl(tmp, cpu_env, offsetof(CPURISCVState, mstatus));
tcg_gen_ori_tl(tmp, tmp, MSTATUS_FS);
tcg_gen_st_tl(tmp, cpu_env, offsetof(CPURISCVState, mstatus));
tcg_temp_free(tmp);
}
#else
static inline void mark_fs_dirty(DisasContext *ctx) { }
#endif
#if !defined(TARGET_RISCV64)
static void gen_fp_load(DisasContext *ctx, uint32_t opc, int rd,
int rs1, target_long imm)
{
TCGv t0;
if (ctx->mstatus_fs == 0) {
gen_exception_illegal(ctx);
return;
}
t0 = tcg_temp_new();
gen_get_gpr(t0, rs1);
tcg_gen_addi_tl(t0, t0, imm);
switch (opc) {
case OPC_RISC_FLW:
if (!has_ext(ctx, RVF)) {
goto do_illegal;
}
tcg_gen_qemu_ld_i64(cpu_fpr[rd], t0, ctx->mem_idx, MO_TEUL);
/* RISC-V requires NaN-boxing of narrower width floating point values */
tcg_gen_ori_i64(cpu_fpr[rd], cpu_fpr[rd], 0xffffffff00000000ULL);
break;
case OPC_RISC_FLD:
if (!has_ext(ctx, RVD)) {
goto do_illegal;
}
tcg_gen_qemu_ld_i64(cpu_fpr[rd], t0, ctx->mem_idx, MO_TEQ);
break;
do_illegal:
default:
gen_exception_illegal(ctx);
break;
}
tcg_temp_free(t0);
mark_fs_dirty(ctx);
}
static void gen_fp_store(DisasContext *ctx, uint32_t opc, int rs1,
int rs2, target_long imm)
{
TCGv t0;
if (ctx->mstatus_fs == 0) {
gen_exception_illegal(ctx);
return;
}
t0 = tcg_temp_new();
gen_get_gpr(t0, rs1);
tcg_gen_addi_tl(t0, t0, imm);
switch (opc) {
case OPC_RISC_FSW:
if (!has_ext(ctx, RVF)) {
goto do_illegal;
}
tcg_gen_qemu_st_i64(cpu_fpr[rs2], t0, ctx->mem_idx, MO_TEUL);
break;
case OPC_RISC_FSD:
if (!has_ext(ctx, RVD)) {
goto do_illegal;
}
tcg_gen_qemu_st_i64(cpu_fpr[rs2], t0, ctx->mem_idx, MO_TEQ);
break;
do_illegal:
default:
gen_exception_illegal(ctx);
break;
}
tcg_temp_free(t0);
}
#endif
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);
}
static void decode_RV32_64C0(DisasContext *ctx)
{
uint8_t funct3 = extract32(ctx->opcode, 13, 3);
uint8_t rd_rs2 = GET_C_RS2S(ctx->opcode);
uint8_t rs1s = GET_C_RS1S(ctx->opcode);
switch (funct3) {
case 3:
#if defined(TARGET_RISCV64)
/* C.LD(RV64/128) -> ld rd', offset[7:3](rs1')*/
gen_load_c(ctx, OPC_RISC_LD, rd_rs2, rs1s,
GET_C_LD_IMM(ctx->opcode));
#else
/* C.FLW (RV32) -> flw rd', offset[6:2](rs1')*/
gen_fp_load(ctx, OPC_RISC_FLW, rd_rs2, rs1s,
GET_C_LW_IMM(ctx->opcode));
#endif
break;
case 7:
#if defined(TARGET_RISCV64)
/* C.SD (RV64/128) -> sd rs2', offset[7:3](rs1')*/
gen_store_c(ctx, OPC_RISC_SD, rs1s, rd_rs2,
GET_C_LD_IMM(ctx->opcode));
#else
/* C.FSW (RV32) -> fsw rs2', offset[6:2](rs1')*/
gen_fp_store(ctx, OPC_RISC_FSW, rs1s, rd_rs2,
GET_C_LW_IMM(ctx->opcode));
#endif
break;
}
}
static void decode_RV32_64C(DisasContext *ctx)
{
uint8_t op = extract32(ctx->opcode, 0, 2);
switch (op) {
case 0:
decode_RV32_64C0(ctx);
break;
}
}
#define EX_SH(amount) \
static int ex_shift_##amount(int imm) \
{ \
return imm << amount; \
}
EX_SH(1)
EX_SH(2)
EX_SH(3)
EX_SH(4)
EX_SH(12)
#define REQUIRE_EXT(ctx, ext) do { \
if (!has_ext(ctx, ext)) { \
return false; \
} \
} while (0)
static int ex_rvc_register(int reg)
{
return 8 + reg;
}
bool decode_insn32(DisasContext *ctx, uint32_t insn);
/* Include the auto-generated decoder for 32 bit insn */
#include "decode_insn32.inc.c"
static bool gen_arith_imm(DisasContext *ctx, arg_i *a,
void(*func)(TCGv, TCGv, TCGv))
{
TCGv source1, source2;
source1 = tcg_temp_new();
source2 = tcg_temp_new();
gen_get_gpr(source1, a->rs1);
tcg_gen_movi_tl(source2, a->imm);
(*func)(source1, source1, source2);
gen_set_gpr(a->rd, source1);
tcg_temp_free(source1);
tcg_temp_free(source2);
return true;
}
#ifdef TARGET_RISCV64
static void gen_addw(TCGv ret, TCGv arg1, TCGv arg2)
{
tcg_gen_add_tl(ret, arg1, arg2);
tcg_gen_ext32s_tl(ret, ret);
}
static void gen_subw(TCGv ret, TCGv arg1, TCGv arg2)
{
tcg_gen_sub_tl(ret, arg1, arg2);
tcg_gen_ext32s_tl(ret, ret);
}
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);
return true;
}
#endif
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);
return true;
}
static bool gen_shift(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, TARGET_LONG_BITS - 1);
(*func)(source1, source1, source2);
gen_set_gpr(a->rd, source1);
tcg_temp_free(source1);
tcg_temp_free(source2);
return true;
}
/* Include insn module translation function */
#include "insn_trans/trans_rvi.inc.c"
#include "insn_trans/trans_rvm.inc.c"
#include "insn_trans/trans_rva.inc.c"
#include "insn_trans/trans_rvf.inc.c"
#include "insn_trans/trans_rvd.inc.c"
#include "insn_trans/trans_privileged.inc.c"
bool decode_insn16(DisasContext *ctx, uint16_t insn);
/* auto-generated decoder*/
#include "decode_insn16.inc.c"
#include "insn_trans/trans_rvc.inc.c"
static void decode_opc(DisasContext *ctx)
{
/* check for compressed insn */
if (extract32(ctx->opcode, 0, 2) != 3) {
if (!has_ext(ctx, RVC)) {
gen_exception_illegal(ctx);
} else {
ctx->pc_succ_insn = ctx->base.pc_next + 2;
if (!decode_insn16(ctx, ctx->opcode)) {
/* fall back to old decoder */
decode_RV32_64C(ctx);
}
}
} else {
ctx->pc_succ_insn = ctx->base.pc_next + 4;
if (!decode_insn32(ctx, ctx->opcode)) {
gen_exception_illegal(ctx);
}
}
}
static void riscv_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs)
{
DisasContext *ctx = container_of(dcbase, DisasContext, base);
CPURISCVState *env = cs->env_ptr;
ctx->pc_succ_insn = ctx->base.pc_first;
ctx->mem_idx = ctx->base.tb->flags & TB_FLAGS_MMU_MASK;
ctx->mstatus_fs = ctx->base.tb->flags & TB_FLAGS_MSTATUS_FS;
ctx->priv_ver = env->priv_ver;
ctx->misa = env->misa;
ctx->frm = -1; /* unknown rounding mode */
}
static void riscv_tr_tb_start(DisasContextBase *db, CPUState *cpu)
{
}
static void riscv_tr_insn_start(DisasContextBase *dcbase, CPUState *cpu)
{
DisasContext *ctx = container_of(dcbase, DisasContext, base);
tcg_gen_insn_start(ctx->base.pc_next);
}
static bool riscv_tr_breakpoint_check(DisasContextBase *dcbase, CPUState *cpu,
const CPUBreakpoint *bp)
{
DisasContext *ctx = container_of(dcbase, DisasContext, base);
tcg_gen_movi_tl(cpu_pc, ctx->base.pc_next);
ctx->base.is_jmp = DISAS_NORETURN;
gen_exception_debug();
/* The address covered by the breakpoint must be included in
[tb->pc, tb->pc + tb->size) in order to for it to be
properly cleared -- thus we increment the PC here so that
the logic setting tb->size below does the right thing. */
ctx->base.pc_next += 4;
return true;
}
static void riscv_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu)
{
DisasContext *ctx = container_of(dcbase, DisasContext, base);
CPURISCVState *env = cpu->env_ptr;
ctx->opcode = cpu_ldl_code(env, ctx->base.pc_next);
decode_opc(ctx);
ctx->base.pc_next = ctx->pc_succ_insn;
if (ctx->base.is_jmp == DISAS_NEXT) {
target_ulong page_start;
page_start = ctx->base.pc_first & TARGET_PAGE_MASK;
if (ctx->base.pc_next - page_start >= TARGET_PAGE_SIZE) {
ctx->base.is_jmp = DISAS_TOO_MANY;
}
}
}
static void riscv_tr_tb_stop(DisasContextBase *dcbase, CPUState *cpu)
{
DisasContext *ctx = container_of(dcbase, DisasContext, base);
switch (ctx->base.is_jmp) {
case DISAS_TOO_MANY:
target/riscv: call gen_goto_tb on DISAS_TOO_MANY Performance impact of this and the previous commits, measured with the very-easy-to-cross-compile rv8-bench: https://github.com/rv8-io/rv8-bench Host: Intel(R) Core(TM) i7-4790K CPU @ 4.00GHz - Key: before: master after1,2,3: the 3 commits in this series (i.e. 3 is this commit) - User-mode: bench before after1 after2 after3 final speedup --------------------------------------------------------- aes 1.12s 1.12s 1.10s 1.00s 1.12 bigint 0.78s 0.78s 0.78s 0.78s 1 dhrystone 0.96s 0.97s 0.49s 0.49s 1.9591837 miniz 1.94s 1.94s 1.88s 1.86s 1.0430108 norx 0.51s 0.51s 0.49s 0.48s 1.0625 primes 0.85s 0.85s 0.84s 0.84s 1.0119048 qsort 4.87s 4.88s 1.86s 1.86s 2.6182796 sha512 0.76s 0.77s 0.64s 0.64s 1.1875 (after1 only applies to softmmu, so no surprises here) - Full-system (fedora): bench before after1 after2 after3 final speedup --------------------------------------------------------- aes 2.68s 2.54s 2.60s 2.34s 1.1452991 bigint 1.61s 1.56s 1.55s 1.64s 0.98170732 dhrystone 1.78s 1.67s 1.25s 1.24s 1.4354839 miniz 3.53s 3.35s 3.28s 3.35s 1.0537313 norx 1.13s 1.09s 1.07s 1.06s 1.0660377 primes 15.37s 15.41s 15.20s 15.37s 1 qsort 7.20s 6.71s 3.85s 3.96s 1.8181818 sha512 1.07s 1.04s 0.90s 0.90s 1.1888889 SoftMMU slows things down, so the numbers are less sensitive. Cross-page jumps improve things a little bit, though. Note that I'm not showing here averages, just results from a single run, so with primes there isn't much to worry about. Signed-off-by: Emilio G. Cota <cota@braap.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
2018-07-29 05:14:34 +03:00
gen_goto_tb(ctx, 0, ctx->base.pc_next);
break;
case DISAS_NORETURN:
break;
default:
g_assert_not_reached();
}
}
static void riscv_tr_disas_log(const DisasContextBase *dcbase, CPUState *cpu)
{
qemu_log("IN: %s\n", lookup_symbol(dcbase->pc_first));
log_target_disas(cpu, dcbase->pc_first, dcbase->tb->size);
}
static const TranslatorOps riscv_tr_ops = {
.init_disas_context = riscv_tr_init_disas_context,
.tb_start = riscv_tr_tb_start,
.insn_start = riscv_tr_insn_start,
.breakpoint_check = riscv_tr_breakpoint_check,
.translate_insn = riscv_tr_translate_insn,
.tb_stop = riscv_tr_tb_stop,
.disas_log = riscv_tr_disas_log,
};
void gen_intermediate_code(CPUState *cs, TranslationBlock *tb)
{
DisasContext ctx;
translator_loop(&riscv_tr_ops, &ctx.base, cs, tb);
}
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] = NULL;
for (i = 1; i < 32; i++) {
cpu_gpr[i] = tcg_global_mem_new(cpu_env,
offsetof(CPURISCVState, gpr[i]), riscv_int_regnames[i]);
}
for (i = 0; i < 32; i++) {
cpu_fpr[i] = tcg_global_mem_new_i64(cpu_env,
offsetof(CPURISCVState, fpr[i]), riscv_fpr_regnames[i]);
}
cpu_pc = tcg_global_mem_new(cpu_env, offsetof(CPURISCVState, pc), "pc");
load_res = tcg_global_mem_new(cpu_env, offsetof(CPURISCVState, load_res),
"load_res");
load_val = tcg_global_mem_new(cpu_env, offsetof(CPURISCVState, load_val),
"load_val");
}