[v6,04/21] target/loongarch: Add fixed point arithmetic instruction translation

Message ID	1631866380-31017-5-git-send-email-gaosong@loongson.cn (mailing list archive)
State	New, archived
Headers	show Return-Path: <SRS0=w8MV=OH=nongnu.org=qemu-devel-bounces+qemu-devel=archiver.kernel.org@kernel.org> DMARC-Filter: OpenDMARC Filter v1.4.1 mail.kernel.org DE3F960EE2 From: Song Gao <gaosong@loongson.cn> To: qemu-devel@nongnu.org Subject: [PATCH v6 04/21] target/loongarch: Add fixed point arithmetic instruction translation Date: Fri, 17 Sep 2021 16:12:43 +0800 Message-Id: <1631866380-31017-5-git-send-email-gaosong@loongson.cn> In-Reply-To: <1631866380-31017-1-git-send-email-gaosong@loongson.cn> References: <1631866380-31017-1-git-send-email-gaosong@loongson.cn> Received-SPF: pass client-ip=114.242.206.163; envelope-from=gaosong@loongson.cn; helo=loongson.cn X-Spam_score_int: 0 X-Spam_score: -0.0 X-Spam_bar: / X-Spam_report: (-0.0 / 5.0 requ) SPF_HELO_PASS=-0.001, SPF_PASS=-0.001 autolearn=ham autolearn_force=no X-Spam_action: no action Precedence: list Cc: peter.maydell@linaro.org, thuth@redhat.com, chenhuacai@loongson.cn, philmd@redhat.com, richard.henderson@linaro.org, laurent@vivier.eu, peterx@redhat.com, f4bug@amsat.org, yangxiaojuan@loongson.cn, alistair.francis@wdc.com, maobibo@loongson.cn, pbonzini@redhat.com, bmeng.cn@gmail.com, alex.bennee@linaro.org, gaosong@loongson.cn Errors-To: qemu-devel-bounces+qemu-devel=archiver.kernel.org@nongnu.org Sender: "Qemu-devel" <qemu-devel-bounces+qemu-devel=archiver.kernel.org@nongnu.org>
Series	Add LoongArch linux-user emulation support \| expand [v6,00/21] Add LoongArch linux-user emulation support [v6,01/21] target/loongarch: Add README [v6,02/21] target/loongarch: Add core definition [v6,03/21] target/loongarch: Add main translation routines [v6,04/21] target/loongarch: Add fixed point arithmetic instruction translation [v6,05/21] target/loongarch: Add fixed point shift instruction translation [v6,06/21] target/loongarch: Add fixed point bit instruction translation [v6,07/21] target/loongarch: Add fixed point load/store instruction translation [v6,08/21] target/loongarch: Add fixed point atomic instruction translation [v6,09/21] target/loongarch: Add fixed point extra instruction translation [v6,10/21] target/loongarch: Add floating point arithmetic instruction translation [v6,11/21] target/loongarch: Add floating point comparison instruction translation [v6,12/21] target/loongarch: Add floating point conversion instruction translation [v6,13/21] target/loongarch: Add floating point move instruction translation [v6,14/21] target/loongarch: Add floating point load/store instruction translation [v6,15/21] target/loongarch: Add branch instruction translation [v6,16/21] target/loongarch: Add disassembler [v6,17/21] LoongArch Linux User Emulation [v6,18/21] default-configs: Add loongarch linux-user support [v6,19/21] target/loongarch: Add target build suport [v6,20/21] target/loongarch: 'make check-tcg' support [v6,21/21] scripts: add loongarch64 binfmt config

diff --git a/target/loongarch/insn_trans/trans_arith.c b/target/loongarch/insn_trans/trans_arith.c new file mode 100644 index 0000000..4e8b9dd --- /dev/null +++ b/target/loongarch/insn_trans/trans_arith.c @@ -0,0 +1,322 @@ +/* + * LoongArch translate functions + * + * Copyright (c) 2021 Loongson Technology Corporation Limited + * + * SPDX-License-Identifier: LGPL-2.1+ + */ + +static bool gen_r3(DisasContext *ctx, arg_fmt_rdrjrk *a, + DisasExtend src1_ext, DisasExtend src2_ext, + DisasExtend dst_ext, void (*func)(TCGv, TCGv, TCGv)) +{ + TCGv dest = gpr_dst(ctx, a->rd, dst_ext); + TCGv src1 = gpr_src(ctx, a->rj, src1_ext); + TCGv src2 = gpr_src(ctx, a->rk, src2_ext); + + func(dest, src1, src2); + + /* dst_ext is EXT_NONE and input is dest, We don't run gen_set_gpr. */ + if (dst_ext) { + gen_set_gpr(a->rd, dest, dst_ext); + } + return true; +} + +static bool gen_r2_si12(DisasContext *ctx, arg_fmt_rdrjsi12 *a, + DisasExtend src_ext, DisasExtend dst_ext, + void (*func)(TCGv, TCGv, TCGv)) +{ + TCGv dest = gpr_dst(ctx, a->rd, dst_ext); + TCGv src1 = gpr_src(ctx, a->rj, src_ext); + TCGv src2 = tcg_constant_tl(a->si12); + + func(dest, src1, src2); + + if (dst_ext) { + gen_set_gpr(a->rd, dest, dst_ext); + } + return true; +} + +static bool gen_r3_sa2(DisasContext *ctx, arg_fmt_rdrjrksa2 *a, + DisasExtend src_ext, DisasExtend dst_ext, + void (*func)(TCGv, TCGv, TCGv, TCGv, target_long)) +{ + TCGv dest = gpr_dst(ctx, a->rd, dst_ext); + TCGv src1 = gpr_src(ctx, a->rj, src_ext); + TCGv src2 = gpr_src(ctx, a->rk, src_ext); + TCGv temp = tcg_temp_new(); + + func(dest, src1, src2, temp, a->sa2); + + if (dst_ext) { + gen_set_gpr(a->rd, dest, dst_ext); + } + tcg_temp_free(temp); + return true; +} + +static bool trans_lu12i_w(DisasContext *ctx, arg_lu12i_w *a) +{ + TCGv dest = gpr_dst(ctx, a->rd, EXT_NONE); + + tcg_gen_movi_tl(dest, a->si20 << 12); + return true; +} + +static bool gen_pc(DisasContext *ctx, arg_fmt_rdsi20 *a, + target_ulong (*func)(target_ulong, int)) +{ + TCGv dest = gpr_dst(ctx, a->rd, EXT_NONE); + target_ulong addr = func(ctx->base.pc_next, a->si20); + + tcg_gen_movi_tl(dest, addr); + return true; +} + +static bool gen_r2_ui12(DisasContext *ctx, arg_fmt_rdrjui12 *a, + void (*func)(TCGv, TCGv, target_long)) +{ + TCGv dest = gpr_dst(ctx, a->rd, EXT_NONE); + TCGv src1 = gpr_src(ctx, a->rj, EXT_NONE); + + func(dest, src1, a->ui12); + return true; +} + +static void gen_slt(TCGv dest, TCGv src1, TCGv src2) +{ + tcg_gen_setcond_tl(TCG_COND_LT, dest, src1, src2); +} + +static void gen_sltu(TCGv dest, TCGv src1, TCGv src2) +{ + tcg_gen_setcond_tl(TCG_COND_LTU, dest, src1, src2); +} + +static void gen_mulh_w(TCGv dest, TCGv src1, TCGv src2) +{ + tcg_gen_mul_i64(dest, src1, src2); + tcg_gen_sari_i64(dest, dest, 32); +} + +static void gen_mulh_wu(TCGv dest, TCGv src1, TCGv src2) +{ + tcg_gen_mul_i64(dest, src1, src2); + tcg_gen_sari_i64(dest, dest, 32); +} + +static void gen_mulh_d(TCGv dest, TCGv src1, TCGv src2) +{ + TCGv discard = tcg_temp_new(); + tcg_gen_muls2_tl(discard, dest, src1, src2); + tcg_temp_free(discard); +} + +static void gen_mulh_du(TCGv dest, TCGv src1, TCGv src2) +{ + TCGv discard = tcg_temp_new(); + tcg_gen_mulu2_tl(discard, dest, src1, src2); + tcg_temp_free(discard); +} + +static void prep_divisor_d(TCGv ret, TCGv src1, TCGv src2) +{ + TCGv t0 = tcg_temp_new(); + TCGv t1 = tcg_temp_new(); + TCGv zero = tcg_constant_tl(0); + + /* + * If min / -1, set the divisor to 1. + * This avoids potential host overflow trap and produces min. + * If x / 0, set the divisor to 1. + * This avoids potential host overflow trap; + * the required result is undefined. + */ + tcg_gen_setcondi_tl(TCG_COND_EQ, ret, src1, INT64_MIN); + tcg_gen_setcondi_tl(TCG_COND_EQ, t0, src2, -1); + tcg_gen_setcondi_tl(TCG_COND_EQ, t1, src2, 0); + tcg_gen_and_tl(ret, ret, t0); + tcg_gen_or_tl(ret, ret, t1); + tcg_gen_movcond_tl(TCG_COND_NE, ret, ret, zero, ret, src2); + + tcg_temp_free(t0); + tcg_temp_free(t1); +} + +static void prep_divisor_du(TCGv ret, TCGv src2) +{ + TCGv zero = tcg_constant_tl(0); + TCGv one = tcg_constant_tl(1); + + /* + * If x / 0, set the divisor to 1. + * This avoids potential host overflow trap; + * the required result is undefined. + */ + tcg_gen_movcond_tl(TCG_COND_EQ, ret, src2, zero, one, src2); +} + +static void gen_div_d(TCGv dest, TCGv src1, TCGv src2) +{ + TCGv t0 = tcg_temp_new(); + prep_divisor_d(t0, src1, src2); + tcg_gen_div_tl(dest, src1, t0); + tcg_temp_free(t0); +} + +static void gen_rem_d(TCGv dest, TCGv src1, TCGv src2) +{ + TCGv t0 = tcg_temp_new(); + prep_divisor_d(t0, src1, src2); + tcg_gen_rem_tl(dest, src1, t0); + tcg_temp_free(t0); +} + +static void gen_div_du(TCGv dest, TCGv src1, TCGv src2) +{ + TCGv t0 = tcg_temp_new(); + prep_divisor_du(t0, src2); + tcg_gen_divu_tl(dest, src1, t0); + tcg_temp_free(t0); +} + +static void gen_rem_du(TCGv dest, TCGv src1, TCGv src2) +{ + TCGv t0 = tcg_temp_new(); + prep_divisor_du(t0, src2); + tcg_gen_remu_tl(dest, src1, t0); + tcg_temp_free(t0); +} + +static void gen_div_w(TCGv dest, TCGv src1, TCGv src2) +{ + TCGv t0 = tcg_temp_new(); + /* We need not check for integer overflow for div_w. */ + prep_divisor_du(t0, src2); + tcg_gen_div_tl(dest, src1, t0); + tcg_temp_free(t0); +} + +static void gen_rem_w(TCGv dest, TCGv src1, TCGv src2) +{ + TCGv t0 = tcg_temp_new(); + /* We need not check for integer overflow for rem_w. */ + prep_divisor_du(t0, src2); + tcg_gen_rem_tl(dest, src1, t0); + tcg_temp_free(t0); +} + +static void gen_alsl_w(TCGv dest, TCGv src1, TCGv src2, + TCGv temp, target_long sa2) +{ + tcg_gen_shli_tl(temp, src1, sa2 + 1); + tcg_gen_add_tl(dest, temp, src2); +} + +static void gen_alsl_wu(TCGv dest, TCGv src1, TCGv src2, + TCGv temp, target_long sa2) +{ + tcg_gen_shli_tl(temp, src1, sa2 + 1); + tcg_gen_add_tl(dest, temp, src2); +} + +static void gen_alsl_d(TCGv dest, TCGv src1, TCGv src2, + TCGv temp, target_long sa2) +{ + tcg_gen_shli_tl(temp, src1, sa2 + 1); + tcg_gen_add_tl(dest, temp, src2); +} + +static bool trans_lu32i_d(DisasContext *ctx, arg_lu32i_d *a) +{ + TCGv dest = gpr_dst(ctx, a->rd, EXT_NONE); + TCGv src1 = gpr_src(ctx, a->rd, EXT_NONE); + TCGv src2 = tcg_constant_tl(a->si20); + + tcg_gen_deposit_tl(dest, src1, src2, 32, 32); + return true; +} + +static bool trans_lu52i_d(DisasContext *ctx, arg_lu52i_d *a) +{ + TCGv dest = gpr_dst(ctx, a->rd, EXT_NONE); + TCGv src1 = gpr_src(ctx, a->rj, EXT_NONE); + TCGv src2 = tcg_constant_tl(a->si12); + + tcg_gen_deposit_tl(dest, src1, src2, 52, 12); + return true; +} + +static target_ulong gen_pcaddi(target_ulong pc, int si20) +{ + return pc + (si20 << 2); +} + +static target_ulong gen_pcalau12i(target_ulong pc, int si20) +{ + return (pc + (si20 << 12)) & ~0xfff; +} + +static target_ulong gen_pcaddu12i(target_ulong pc, int si20) +{ + return pc + (si20 << 12); +} + +static target_ulong gen_pcaddu18i(target_ulong pc, int si20) +{ + return pc + ((target_ulong)(si20) << 18); +} + +static bool trans_addu16i_d(DisasContext *ctx, arg_addu16i_d *a) +{ + TCGv dest = gpr_dst(ctx, a->rd, EXT_NONE); + TCGv src1 = gpr_src(ctx, a->rj, EXT_NONE); + + tcg_gen_addi_tl(dest, src1, a->si16 << 16); + return true; +} + +TRANS(add_w, gen_r3, EXT_NONE, EXT_NONE, EXT_SIGN, tcg_gen_add_tl) +TRANS(add_d, gen_r3, EXT_NONE, EXT_NONE, EXT_NONE, tcg_gen_add_tl) +TRANS(sub_w, gen_r3, EXT_NONE, EXT_NONE, EXT_SIGN, tcg_gen_sub_tl) +TRANS(sub_d, gen_r3, EXT_NONE, EXT_NONE, EXT_NONE, tcg_gen_sub_tl) +TRANS(and, gen_r3, EXT_NONE, EXT_NONE, EXT_NONE, tcg_gen_and_tl) +TRANS(or, gen_r3, EXT_NONE, EXT_NONE, EXT_NONE, tcg_gen_or_tl) +TRANS(xor, gen_r3, EXT_NONE, EXT_NONE, EXT_NONE, tcg_gen_xor_tl) +TRANS(nor, gen_r3, EXT_NONE, EXT_NONE, EXT_NONE, tcg_gen_nor_tl) +TRANS(andn, gen_r3, EXT_NONE, EXT_NONE, EXT_NONE, tcg_gen_andc_tl) +TRANS(orn, gen_r3, EXT_NONE, EXT_NONE, EXT_NONE, tcg_gen_orc_tl) +TRANS(slt, gen_r3, EXT_NONE, EXT_NONE, EXT_NONE, gen_slt) +TRANS(sltu, gen_r3, EXT_NONE, EXT_NONE, EXT_NONE, gen_sltu) +TRANS(mul_w, gen_r3, EXT_SIGN, EXT_SIGN, EXT_SIGN, tcg_gen_mul_tl) +TRANS(mul_d, gen_r3, EXT_NONE, EXT_NONE, EXT_NONE, tcg_gen_mul_tl) +TRANS(mulh_w, gen_r3, EXT_SIGN, EXT_SIGN, EXT_NONE, gen_mulh_w) +TRANS(mulh_wu, gen_r3, EXT_ZERO, EXT_ZERO, EXT_NONE, gen_mulh_wu) +TRANS(mulh_d, gen_r3, EXT_NONE, EXT_NONE, EXT_NONE, gen_mulh_d) +TRANS(mulh_du, gen_r3, EXT_NONE, EXT_NONE, EXT_NONE, gen_mulh_du) +TRANS(mulw_d_w, gen_r3, EXT_SIGN, EXT_SIGN, EXT_NONE, tcg_gen_mul_tl) +TRANS(mulw_d_wu, gen_r3, EXT_ZERO, EXT_ZERO, EXT_NONE, tcg_gen_mul_tl) +TRANS(div_w, gen_r3, EXT_SIGN, EXT_SIGN, EXT_SIGN, gen_div_w) +TRANS(mod_w, gen_r3, EXT_SIGN, EXT_SIGN, EXT_SIGN, gen_rem_w) +TRANS(div_wu, gen_r3, EXT_ZERO, EXT_ZERO, EXT_SIGN, gen_div_du) +TRANS(mod_wu, gen_r3, EXT_ZERO, EXT_ZERO, EXT_SIGN, gen_rem_du) +TRANS(div_d, gen_r3, EXT_NONE, EXT_NONE, EXT_NONE, gen_div_d) +TRANS(mod_d, gen_r3, EXT_NONE, EXT_NONE, EXT_NONE, gen_rem_d) +TRANS(div_du, gen_r3, EXT_NONE, EXT_NONE, EXT_NONE, gen_div_du) +TRANS(mod_du, gen_r3, EXT_NONE, EXT_NONE, EXT_NONE, gen_rem_du) +TRANS(slti, gen_r2_si12, EXT_NONE, EXT_NONE, gen_slt) +TRANS(sltui, gen_r2_si12, EXT_NONE, EXT_NONE, gen_sltu) +TRANS(addi_w, gen_r2_si12, EXT_NONE, EXT_SIGN, tcg_gen_add_tl) +TRANS(addi_d, gen_r2_si12, EXT_NONE, EXT_NONE, tcg_gen_add_tl) +TRANS(alsl_w, gen_r3_sa2, EXT_NONE, EXT_SIGN, gen_alsl_w) +TRANS(alsl_wu, gen_r3_sa2, EXT_NONE, EXT_ZERO, gen_alsl_wu) +TRANS(alsl_d, gen_r3_sa2, EXT_NONE, EXT_NONE, gen_alsl_d) +TRANS(pcaddi, gen_pc, gen_pcaddi) +TRANS(pcalau12i, gen_pc, gen_pcalau12i) +TRANS(pcaddu12i, gen_pc, gen_pcaddu12i) +TRANS(pcaddu18i, gen_pc, gen_pcaddu18i) +TRANS(andi, gen_r2_ui12, tcg_gen_andi_tl) +TRANS(ori, gen_r2_ui12, tcg_gen_ori_tl) +TRANS(xori, gen_r2_ui12, tcg_gen_xori_tl) diff --git a/target/loongarch/insns.decode b/target/loongarch/insns.decode new file mode 100644 index 0000000..1e0b755 --- /dev/null +++ b/target/loongarch/insns.decode @@ -0,0 +1,89 @@ +# +# LoongArch instruction decode definitions. +# +# Copyright (c) 2021 Loongson Technology Corporation Limited +# +# SPDX-License-Identifier: LGPL-2.1+ +# + +# +# Fields +# +%rd 0:5 +%rj 5:5 +%rk 10:5 +%sa2 15:2 +%si12 10:s12 +%ui12 10:12 +%si16 10:s16 +%si20 5:s20 + +# +# Argument sets +# +&fmt_rdrjrk rd rj rk +&fmt_rdrjsi12 rd rj si12 +&fmt_rdrjrksa2 rd rj rk sa2 +&fmt_rdrjsi16 rd rj si16 +&fmt_rdrjui12 rd rj ui12 +&fmt_rdsi20 rd si20 + +# +# Formats +# +@fmt_rdrjrk .... ........ ..... ..... ..... ..... &fmt_rdrjrk %rd %rj %rk +@fmt_rdrjsi12 .... ...... ............ ..... ..... &fmt_rdrjsi12 %rd %rj %si12 +@fmt_rdrjui12 .... ...... ............ ..... ..... &fmt_rdrjui12 %rd %rj %ui12 +@fmt_rdrjrksa2 .... ........ ... .. ..... ..... ..... &fmt_rdrjrksa2 %rd %rj %rk %sa2 +@fmt_rdrjsi16 .... .. ................ ..... ..... &fmt_rdrjsi16 %rd %rj %si16 +@fmt_rdsi20 .... ... .................... ..... &fmt_rdsi20 %rd %si20 + +# +# Fixed point arithmetic operation instruction +# +add_w 0000 00000001 00000 ..... ..... ..... @fmt_rdrjrk +add_d 0000 00000001 00001 ..... ..... ..... @fmt_rdrjrk +sub_w 0000 00000001 00010 ..... ..... ..... @fmt_rdrjrk +sub_d 0000 00000001 00011 ..... ..... ..... @fmt_rdrjrk +slt 0000 00000001 00100 ..... ..... ..... @fmt_rdrjrk +sltu 0000 00000001 00101 ..... ..... ..... @fmt_rdrjrk +slti 0000 001000 ............ ..... ..... @fmt_rdrjsi12 +sltui 0000 001001 ............ ..... ..... @fmt_rdrjsi12 +nor 0000 00000001 01000 ..... ..... ..... @fmt_rdrjrk +and 0000 00000001 01001 ..... ..... ..... @fmt_rdrjrk +or 0000 00000001 01010 ..... ..... ..... @fmt_rdrjrk +xor 0000 00000001 01011 ..... ..... ..... @fmt_rdrjrk +orn 0000 00000001 01100 ..... ..... ..... @fmt_rdrjrk +andn 0000 00000001 01101 ..... ..... ..... @fmt_rdrjrk +mul_w 0000 00000001 11000 ..... ..... ..... @fmt_rdrjrk +mulh_w 0000 00000001 11001 ..... ..... ..... @fmt_rdrjrk +mulh_wu 0000 00000001 11010 ..... ..... ..... @fmt_rdrjrk +mul_d 0000 00000001 11011 ..... ..... ..... @fmt_rdrjrk +mulh_d 0000 00000001 11100 ..... ..... ..... @fmt_rdrjrk +mulh_du 0000 00000001 11101 ..... ..... ..... @fmt_rdrjrk +mulw_d_w 0000 00000001 11110 ..... ..... ..... @fmt_rdrjrk +mulw_d_wu 0000 00000001 11111 ..... ..... ..... @fmt_rdrjrk +div_w 0000 00000010 00000 ..... ..... ..... @fmt_rdrjrk +mod_w 0000 00000010 00001 ..... ..... ..... @fmt_rdrjrk +div_wu 0000 00000010 00010 ..... ..... ..... @fmt_rdrjrk +mod_wu 0000 00000010 00011 ..... ..... ..... @fmt_rdrjrk +div_d 0000 00000010 00100 ..... ..... ..... @fmt_rdrjrk +mod_d 0000 00000010 00101 ..... ..... ..... @fmt_rdrjrk +div_du 0000 00000010 00110 ..... ..... ..... @fmt_rdrjrk +mod_du 0000 00000010 00111 ..... ..... ..... @fmt_rdrjrk +alsl_w 0000 00000000 010 .. ..... ..... ..... @fmt_rdrjrksa2 +alsl_wu 0000 00000000 011 .. ..... ..... ..... @fmt_rdrjrksa2 +alsl_d 0000 00000010 110 .. ..... ..... ..... @fmt_rdrjrksa2 +lu12i_w 0001 010 .................... ..... @fmt_rdsi20 +lu32i_d 0001 011 .................... ..... @fmt_rdsi20 +lu52i_d 0000 001100 ............ ..... ..... @fmt_rdrjsi12 +pcaddi 0001 100 .................... ..... @fmt_rdsi20 +pcalau12i 0001 101 .................... ..... @fmt_rdsi20 +pcaddu12i 0001 110 .................... ..... @fmt_rdsi20 +pcaddu18i 0001 111 .................... ..... @fmt_rdsi20 +addi_w 0000 001010 ............ ..... ..... @fmt_rdrjsi12 +addi_d 0000 001011 ............ ..... ..... @fmt_rdrjsi12 +addu16i_d 0001 00 ................ ..... ..... @fmt_rdrjsi16 +andi 0000 001101 ............ ..... ..... @fmt_rdrjui12 +ori 0000 001110 ............ ..... ..... @fmt_rdrjui12 +xori 0000 001111 ............ ..... ..... @fmt_rdrjui12 diff --git a/target/loongarch/translate.c b/target/loongarch/translate.c index 2399b1a..69207f1 100644 --- a/target/loongarch/translate.c +++ b/target/loongarch/translate.c @@ -58,6 +58,11 @@ static void loongarch_tr_init_disas_context(DisasContextBase *dcbase, /* Bound the number of insns to execute to those left on the page. */ bound = -(ctx->base.pc_first | TARGET_PAGE_MASK) / 4; ctx->base.max_insns = MIN(ctx->base.max_insns, bound); + + ctx->ntemp = 0; + memset(ctx->temp, 0, sizeof(ctx->temp)); + + ctx->zero = tcg_constant_tl(0); } static void loongarch_tr_tb_start(DisasContextBase *dcbase, CPUState *cs) @@ -71,6 +76,73 @@ static void loongarch_tr_insn_start(DisasContextBase *dcbase, CPUState *cs) tcg_gen_insn_start(ctx->base.pc_next); } +/* + * Wrappers for getting reg values. + * + * The $zero register does not have cpu_gpr[0] allocated -- we supply the + * constant zero as a source, and an uninitialized sink as destination. + * + * Further, we may provide an extension for word operations. + */ +static TCGv temp_new(DisasContext *ctx) +{ + assert(ctx->ntemp < ARRAY_SIZE(ctx->temp)); + return ctx->temp[ctx->ntemp++] = tcg_temp_new(); +} + +static TCGv gpr_src(DisasContext *ctx, int reg_num, DisasExtend src_ext) +{ + TCGv t; + + if (reg_num == 0) { + return ctx->zero; + } + + switch (src_ext) { + 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 TCGv gpr_dst(DisasContext *ctx, int reg_num, DisasExtend dst_ext) +{ + if (reg_num == 0 || dst_ext) { + return temp_new(ctx); + } + return cpu_gpr[reg_num]; +} + +static void gen_set_gpr(int reg_num, TCGv t, DisasExtend dst_ext) +{ + if (reg_num != 0) { + switch (dst_ext) { + case EXT_NONE: + tcg_gen_mov_tl(cpu_gpr[reg_num], t); + break; + case EXT_SIGN: + tcg_gen_ext32s_tl(cpu_gpr[reg_num], t); + break; + case EXT_ZERO: + tcg_gen_ext32u_tl(cpu_gpr[reg_num], t); + break; + default: + g_assert_not_reached(); + } + } +} + +#include "decode-insns.c.inc" +#include "insn_trans/trans_arith.c" + static void loongarch_tr_translate_insn(DisasContextBase *dcbase, CPUState *cs) { CPULoongArchState *env = cs->env_ptr; @@ -84,6 +156,12 @@ static void loongarch_tr_translate_insn(DisasContextBase *dcbase, CPUState *cs) generate_exception(ctx, EXCP_INE); } + for (int i = ctx->ntemp - 1; i >= 0; --i) { + tcg_temp_free(ctx->temp[i]); + ctx->temp[i] = NULL; + } + ctx->ntemp = 0; + ctx->base.pc_next += 4; } diff --git a/target/loongarch/translate.h b/target/loongarch/translate.h index dff7d79..832434c 100644 --- a/target/loongarch/translate.h +++ b/target/loongarch/translate.h @@ -11,11 +11,30 @@ #include "exec/translator.h" +#define TRANS(NAME, FUNC, ...) \ + static bool trans_##NAME(DisasContext *ctx, arg_##NAME * a) \ + { return FUNC(ctx, a, __VA_ARGS__); } + +/* + * 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; target_ulong page_start; uint32_t opcode; int mem_idx; + TCGv zero; + /* Space for 3 operands plus 1 extra for address computation. */ + TCGv temp[4]; + uint8_t ntemp; } DisasContext; void generate_exception(DisasContext *ctx, int excp);

[v6,04/21] target/loongarch: Add fixed point arithmetic instruction translation

Commit Message

Patch