From nobody Sun Dec 29 19:32:48 2024 Delivered-To: importer2@patchew.org Authentication-Results: mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer2=patchew.org@nongnu.org; dmarc=pass(p=none dis=none) header.from=redhat.com ARC-Seal: i=1; a=rsa-sha256; t=1719037054; cv=none; d=zohomail.com; s=zohoarc; b=cd+EqdOqPg7dSrKKTOLngPNCSruV7VWp7OjcdmnfIyyQZoepoIy4EaGwUrAkM2CskIzjgg5MfpfOl6omRnwOmTHVZW9Iy0AnXljQIbjRtmu4vOiCycdiKBgTED+bRbZS9uU3wZoAJpLFSj6YcIMTbKXCYo7b8xCXc0gPv/zObPI= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1719037054; h=Content-Type:Content-Transfer-Encoding:Cc:Cc:Date:Date:From:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:Subject:To:To:Message-Id:Reply-To; bh=a21jRpbZ6uLFXei7m2mIb1JchhLz3QGPG9pcKkyftnc=; b=mLy/JFSjqEvmtomEsxPy33HJhYsoQBYfyTEh686UJbXX5QQQ4crk8fWR92TxMwE16op4MttI5rcez251PR+j6mF9TxyzwegY9AwCyA1x6SW+2pjdi01NRd+o5ra5IUyRWatWNFoxFNdbeYN0GdpcPvKV+1dEXztkkJDPBjaqHC0= ARC-Authentication-Results: i=1; mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer2=patchew.org@nongnu.org; dmarc=pass header.from= (p=none dis=none) Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1719037054951583.4979288540816; Fri, 21 Jun 2024 23:17:34 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sKu30-0000AR-U4; Sat, 22 Jun 2024 02:16:27 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sKu2w-00004u-3x for qemu-devel@nongnu.org; Sat, 22 Jun 2024 02:16:22 -0400 Received: from us-smtp-delivery-124.mimecast.com ([170.10.129.124]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sKu2t-0006OV-HF for qemu-devel@nongnu.org; Sat, 22 Jun 2024 02:16:21 -0400 Received: from mail-ed1-f69.google.com (mail-ed1-f69.google.com [209.85.208.69]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id us-mta-615-yh7BFSVIM3ejyfqwxxjy1g-1; Sat, 22 Jun 2024 02:16:13 -0400 Received: by mail-ed1-f69.google.com with SMTP id 4fb4d7f45d1cf-57cb86ffb3eso1114306a12.0 for ; Fri, 21 Jun 2024 23:16:13 -0700 (PDT) Received: from avogadro.local ([151.62.196.71]) by smtp.gmail.com with ESMTPSA id 4fb4d7f45d1cf-57d3042e407sm1893599a12.46.2024.06.21.23.16.08 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 21 Jun 2024 23:16:08 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1719036978; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=a21jRpbZ6uLFXei7m2mIb1JchhLz3QGPG9pcKkyftnc=; b=H9vtEfxBIz9BGakxc94bD47nRZ5F/1sPBv9HIw+BYRrE19EvPS2/se+0Yiqiuwbk/cjLzl HwbLgLSvYRTxPeGhLQ8RZE2CdUH+kSK8rpEH4/uWnBdtrbKDdntwJ0IuR4uaHhdPlcKLJ8 tghTCrblhXOn4xH85vzP5KIPCi9h7LU= X-MC-Unique: yh7BFSVIM3ejyfqwxxjy1g-1 X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1719036971; x=1719641771; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=a21jRpbZ6uLFXei7m2mIb1JchhLz3QGPG9pcKkyftnc=; b=MazbFW+BM+mw7yCAsHakW4ub69JRo5cxREFLt+cV54lMBeSMcqngM/n3olSkrByx7b Q4+lJJWDAMrm+JFp1YvAU6F2k6L2Mx9RfoOUNs+DyofgOz1S5TyUZd7TM6aD31SRsrR5 zXbOixClTLiX5TuOaqB3LPSqo1s5dv7rSO0bELdBqybF7lKQPDGMxWIZY404VG72NygF /F4v/l0veb1SQ+uzYWeO7TNtnVybJqRpJkdlFncnDJ2OX9FWs3ShrIEV18l87QNHYSGo WhtNm13bbVAYW6NkbeZGS9XEsLAOJDexbN8w6nzqYRFRffswI2EpYpIGAm7G+uP/3fpb 7Vwg== X-Gm-Message-State: AOJu0YwD2fb/rXhKzkENpSoB03ej1k6D4y1lxPI5GS1HrfOk1G+L4laf ziWFB4tlhFB5KllcuzbXfJBIlf78dbQKoLWdzg+L5OUco9GEuY+BAPwhVpV76g9DCLJcp0E6C3Z s+Vz5IwwgUndmg9QmR6EsAoGnJFPbEq6hwdjmPYCZkb8D56vjPCuYrZYe43bBHyw/oMd9Kxgarw HTXo2ZfuyRjlUMuzYzE6VYwIyKP6XvmsZpL+1p X-Received: by 2002:aa7:d0d1:0:b0:57d:2db9:15e7 with SMTP id 4fb4d7f45d1cf-57d2db91688mr3795746a12.12.1719036971409; Fri, 21 Jun 2024 23:16:11 -0700 (PDT) X-Google-Smtp-Source: AGHT+IH2LtvMKwVvX2ZkBK3MgK6kcWAa9tDywax20hREFUU99kw3PXolhQxfdD3QC8ilzglg3FLCwg== X-Received: by 2002:aa7:d0d1:0:b0:57d:2db9:15e7 with SMTP id 4fb4d7f45d1cf-57d2db91688mr3795728a12.12.1719036970842; Fri, 21 Jun 2024 23:16:10 -0700 (PDT) From: Paolo Bonzini To: qemu-devel@nongnu.org Cc: Richard Henderson Subject: [PULL 05/23] target/i386: convert bit test instructions to new decoder Date: Sat, 22 Jun 2024 08:15:39 +0200 Message-ID: <20240622061558.530543-6-pbonzini@redhat.com> X-Mailer: git-send-email 2.45.2 In-Reply-To: <20240622061558.530543-1-pbonzini@redhat.com> References: <20240622061558.530543-1-pbonzini@redhat.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer2=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=170.10.129.124; envelope-from=pbonzini@redhat.com; helo=us-smtp-delivery-124.mimecast.com X-Spam_score_int: -21 X-Spam_score: -2.2 X-Spam_bar: -- X-Spam_report: (-2.2 / 5.0 requ) BAYES_00=-1.9, DKIMWL_WL_HIGH=-0.145, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, RCVD_IN_MSPIKE_H4=0.001, RCVD_IN_MSPIKE_WL=0.001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer2=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer2=patchew.org@nongnu.org X-ZohoMail-DKIM: pass (identity @redhat.com) X-ZM-MESSAGEID: 1719037056043100005 Content-Type: text/plain; charset="utf-8" Reviewed-by: Richard Henderson Signed-off-by: Paolo Bonzini --- target/i386/tcg/decode-new.h | 3 + target/i386/tcg/translate.c | 147 +----------------------------- target/i386/tcg/decode-new.c.inc | 40 ++++++--- target/i386/tcg/emit.c.inc | 149 ++++++++++++++++++++++++++++++- 4 files changed, 181 insertions(+), 158 deletions(-) diff --git a/target/i386/tcg/decode-new.h b/target/i386/tcg/decode-new.h index f9bf9a60411..e4cdf5e3c4f 100644 --- a/target/i386/tcg/decode-new.h +++ b/target/i386/tcg/decode-new.h @@ -190,6 +190,9 @@ typedef enum X86InsnSpecial { /* Always locked if it has a memory operand (XCHG) */ X86_SPECIAL_Locked, =20 + /* Like HasLock, but also operand 2 provides bit displacement into mem= ory. */ + X86_SPECIAL_BitTest, + /* Do not load effective address in s->A0 */ X86_SPECIAL_NoLoadEA, =20 diff --git a/target/i386/tcg/translate.c b/target/i386/tcg/translate.c index 934c514e64f..257110ac703 100644 --- a/target/i386/tcg/translate.c +++ b/target/i386/tcg/translate.c @@ -708,11 +708,6 @@ static TCGv gen_ext_tl(TCGv dst, TCGv src, MemOp size,= bool sign) return dst; } =20 -static void gen_exts(MemOp ot, TCGv reg) -{ - gen_ext_tl(reg, reg, ot, true); -} - static void gen_op_j_ecx(DisasContext *s, TCGCond cond, TCGLabel *label1) { TCGv tmp =3D gen_ext_tl(NULL, cpu_regs[R_ECX], s->aflag, false); @@ -2985,7 +2980,7 @@ static void disas_insn_old(DisasContext *s, CPUState = *cpu, int b) int prefixes =3D s->prefix; MemOp dflag =3D s->dflag; MemOp ot; - int modrm, reg, rm, mod, op, val; + int modrm, reg, rm, mod, op; =20 /* now check op code */ switch (b) { @@ -3051,146 +3046,6 @@ static void disas_insn_old(DisasContext *s, CPUStat= e *cpu, int b) } break; =20 - /************************/ - /* bit operations */ - case 0x1ba: /* bt/bts/btr/btc Gv, im */ - ot =3D dflag; - modrm =3D x86_ldub_code(env, s); - op =3D (modrm >> 3) & 7; - mod =3D (modrm >> 6) & 3; - rm =3D (modrm & 7) | REX_B(s); - if (mod !=3D 3) { - s->rip_offset =3D 1; - gen_lea_modrm(env, s, modrm); - if (!(s->prefix & PREFIX_LOCK)) { - gen_op_ld_v(s, ot, s->T0, s->A0); - } - } else { - gen_op_mov_v_reg(s, ot, s->T0, rm); - } - /* load shift */ - val =3D x86_ldub_code(env, s); - tcg_gen_movi_tl(s->T1, val); - if (op < 4) - goto unknown_op; - op -=3D 4; - goto bt_op; - case 0x1a3: /* bt Gv, Ev */ - op =3D 0; - goto do_btx; - case 0x1ab: /* bts */ - op =3D 1; - goto do_btx; - case 0x1b3: /* btr */ - op =3D 2; - goto do_btx; - case 0x1bb: /* btc */ - op =3D 3; - do_btx: - ot =3D dflag; - modrm =3D x86_ldub_code(env, s); - reg =3D ((modrm >> 3) & 7) | REX_R(s); - mod =3D (modrm >> 6) & 3; - rm =3D (modrm & 7) | REX_B(s); - gen_op_mov_v_reg(s, MO_32, s->T1, reg); - if (mod !=3D 3) { - AddressParts a =3D gen_lea_modrm_0(env, s, modrm); - /* specific case: we need to add a displacement */ - gen_exts(ot, s->T1); - tcg_gen_sari_tl(s->tmp0, s->T1, 3 + ot); - tcg_gen_shli_tl(s->tmp0, s->tmp0, ot); - tcg_gen_add_tl(s->A0, gen_lea_modrm_1(s, a, false), s->tmp0); - gen_lea_v_seg(s, s->A0, a.def_seg, s->override); - if (!(s->prefix & PREFIX_LOCK)) { - gen_op_ld_v(s, ot, s->T0, s->A0); - } - } else { - gen_op_mov_v_reg(s, ot, s->T0, rm); - } - bt_op: - tcg_gen_andi_tl(s->T1, s->T1, (1 << (3 + ot)) - 1); - tcg_gen_movi_tl(s->tmp0, 1); - tcg_gen_shl_tl(s->tmp0, s->tmp0, s->T1); - if (s->prefix & PREFIX_LOCK) { - switch (op) { - case 0: /* bt */ - /* Needs no atomic ops; we suppressed the normal - memory load for LOCK above so do it now. */ - gen_op_ld_v(s, ot, s->T0, s->A0); - break; - case 1: /* bts */ - tcg_gen_atomic_fetch_or_tl(s->T0, s->A0, s->tmp0, - s->mem_index, ot | MO_LE); - break; - case 2: /* btr */ - tcg_gen_not_tl(s->tmp0, s->tmp0); - tcg_gen_atomic_fetch_and_tl(s->T0, s->A0, s->tmp0, - s->mem_index, ot | MO_LE); - break; - default: - case 3: /* btc */ - tcg_gen_atomic_fetch_xor_tl(s->T0, s->A0, s->tmp0, - s->mem_index, ot | MO_LE); - break; - } - tcg_gen_shr_tl(s->tmp4, s->T0, s->T1); - } else { - tcg_gen_shr_tl(s->tmp4, s->T0, s->T1); - switch (op) { - case 0: /* bt */ - /* Data already loaded; nothing to do. */ - break; - case 1: /* bts */ - tcg_gen_or_tl(s->T0, s->T0, s->tmp0); - break; - case 2: /* btr */ - tcg_gen_andc_tl(s->T0, s->T0, s->tmp0); - break; - default: - case 3: /* btc */ - tcg_gen_xor_tl(s->T0, s->T0, s->tmp0); - break; - } - if (op !=3D 0) { - if (mod !=3D 3) { - gen_op_st_v(s, ot, s->T0, s->A0); - } else { - gen_op_mov_reg_v(s, ot, rm, s->T0); - } - } - } - - /* Delay all CC updates until after the store above. Note that - C is the result of the test, Z is unchanged, and the others - are all undefined. */ - switch (s->cc_op) { - case CC_OP_MULB ... CC_OP_MULQ: - case CC_OP_ADDB ... CC_OP_ADDQ: - case CC_OP_ADCB ... CC_OP_ADCQ: - case CC_OP_SUBB ... CC_OP_SUBQ: - case CC_OP_SBBB ... CC_OP_SBBQ: - case CC_OP_LOGICB ... CC_OP_LOGICQ: - case CC_OP_INCB ... CC_OP_INCQ: - case CC_OP_DECB ... CC_OP_DECQ: - case CC_OP_SHLB ... CC_OP_SHLQ: - case CC_OP_SARB ... CC_OP_SARQ: - case CC_OP_BMILGB ... CC_OP_BMILGQ: - case CC_OP_POPCNT: - /* Z was going to be computed from the non-zero status of CC_D= ST. - We can get that same Z value (and the new C value) by leavi= ng - CC_DST alone, setting CC_SRC, and using a CC_OP_SAR of the - same width. */ - tcg_gen_mov_tl(cpu_cc_src, s->tmp4); - set_cc_op(s, ((s->cc_op - CC_OP_MULB) & 3) + CC_OP_SARB); - break; - default: - /* Otherwise, generate EFLAGS and replace the C bit. */ - gen_compute_eflags(s); - tcg_gen_deposit_tl(cpu_cc_src, cpu_cc_src, s->tmp4, - ctz32(CC_C), 1); - break; - } - break; case 0x100: modrm =3D x86_ldub_code(env, s); mod =3D (modrm >> 6) & 3; diff --git a/target/i386/tcg/decode-new.c.inc b/target/i386/tcg/decode-new.= c.inc index 0d846c32c22..33ffcf092ec 100644 --- a/target/i386/tcg/decode-new.c.inc +++ b/target/i386/tcg/decode-new.c.inc @@ -205,6 +205,7 @@ #define sextT0 .special =3D X86_SPECIAL_SExtT0, #define zextT0 .special =3D X86_SPECIAL_ZExtT0, #define op0_Mw .special =3D X86_SPECIAL_Op0_Mw, +#define btEvGv .special =3D X86_SPECIAL_BitTest, =20 #define vex1 .vex_class =3D 1, #define vex1_rep3 .vex_class =3D 1, .vex_special =3D X86_VEX_REPScalar, @@ -269,6 +270,24 @@ static inline const X86OpEntry *decode_by_prefix(Disas= Context *s, const X86OpEnt } } =20 +static void decode_group8(DisasContext *s, CPUX86State *env, X86OpEntry *e= ntry, uint8_t *b) +{ + static const X86GenFunc group8_gen[8] =3D { + NULL, NULL, NULL, NULL, + gen_BT, gen_BTS, gen_BTR, gen_BTC, + }; + int op =3D (get_modrm(s, env) >> 3) & 7; + entry->gen =3D group8_gen[op]; + if (op =3D=3D 4) { + /* prevent writeback and LOCK for BT */ + entry->op1 =3D entry->op0; + entry->op0 =3D X86_TYPE_None; + entry->s0 =3D X86_SIZE_None; + } else { + entry->special =3D X86_SPECIAL_HasLock; + } +} + static void decode_group15(DisasContext *s, CPUX86State *env, X86OpEntry *= entry, uint8_t *b) { static const X86OpEntry group15_reg[8] =3D { @@ -1162,12 +1181,14 @@ static const X86OpEntry opcodes_0F[256] =3D { [0xa0] =3D X86_OP_ENTRYr(PUSH, FS, w), [0xa1] =3D X86_OP_ENTRYw(POP, FS, w), [0xa2] =3D X86_OP_ENTRY0(CPUID), + [0xa3] =3D X86_OP_ENTRYrr(BT, E,v, G,v, btEvGv), [0xa4] =3D X86_OP_ENTRY4(SHLD, E,v, 2op,v, G,v), [0xa5] =3D X86_OP_ENTRY3(SHLD, E,v, 2op,v, G,v), =20 [0xb0] =3D X86_OP_ENTRY2(CMPXCHG,E,b, G,b, lock), [0xb1] =3D X86_OP_ENTRY2(CMPXCHG,E,v, G,v, lock), [0xb2] =3D X86_OP_ENTRY3(LSS, G,v, EM,p, None, None), + [0xb3] =3D X86_OP_ENTRY2(BTR, E,v, G,v, btEvGv), [0xb4] =3D X86_OP_ENTRY3(LFS, G,v, EM,p, None, None), [0xb5] =3D X86_OP_ENTRY3(LGS, G,v, EM,p, None, None), [0xb6] =3D X86_OP_ENTRY3(MOV, G,v, E,b, None, None, zextT0), /* MOV= ZX */ @@ -1294,6 +1315,7 @@ static const X86OpEntry opcodes_0F[256] =3D { [0xa8] =3D X86_OP_ENTRYr(PUSH, GS, w), [0xa9] =3D X86_OP_ENTRYw(POP, GS, w), [0xaa] =3D X86_OP_ENTRY0(RSM, chk(smm) svm(RSM)), + [0xab] =3D X86_OP_ENTRY2(BTS, E,v, G,v, btEvGv), [0xac] =3D X86_OP_ENTRY4(SHRD, E,v, 2op,v, G,v), [0xad] =3D X86_OP_ENTRY3(SHRD, E,v, 2op,v, G,v), [0xae] =3D X86_OP_GROUP0(group15), @@ -1306,6 +1328,8 @@ static const X86OpEntry opcodes_0F[256] =3D { [0xb8] =3D X86_OP_GROUP0(0FB8), /* decoded as modrm, which is visible as a difference between page fau= lt and #UD */ [0xb9] =3D X86_OP_ENTRYr(UD, nop,v), /* UD1= */ + [0xba] =3D X86_OP_GROUP2(group8, E,v, I,b), + [0xbb] =3D X86_OP_ENTRY2(BTC, E,v, G,v, btEvGv), [0xbc] =3D X86_OP_GROUP0(0FBC), [0xbd] =3D X86_OP_GROUP0(0FBD), [0xbe] =3D X86_OP_ENTRY3(MOV, G,v, E,b, None, None, sextT0), /* MOV= SX */ @@ -2424,6 +2448,7 @@ static void disas_insn(DisasContext *s, CPUState *cpu) CPUX86State *env =3D cpu_env(cpu); X86DecodedInsn decode; X86DecodeFunc decode_func =3D decode_root; + bool accept_lock =3D false; uint8_t cc_live, b; =20 s->pc =3D s->base.pc_next; @@ -2597,10 +2622,6 @@ static void disas_insn(DisasContext *s, CPUState *cp= u) switch (b) { case 0x00 ... 0x01: /* mostly privileged instructions */ case 0x1a ... 0x1b: /* MPX */ - case 0xa3: /* bt */ - case 0xab: /* bts */ - case 0xb3: /* btr */ - case 0xba ... 0xbb: /* grp8, btc */ case 0xc7: /* grp9 */ disas_insn_old(s, cpu, b + 0x100); return; @@ -2662,9 +2683,10 @@ static void disas_insn(DisasContext *s, CPUState *cp= u) if (decode.op[0].has_ea) { s->prefix |=3D PREFIX_LOCK; } - decode.e.special =3D X86_SPECIAL_HasLock; /* fallthrough */ case X86_SPECIAL_HasLock: + case X86_SPECIAL_BitTest: + accept_lock =3D decode.op[0].has_ea; break; =20 case X86_SPECIAL_Op0_Rd: @@ -2706,10 +2728,8 @@ static void disas_insn(DisasContext *s, CPUState *cp= u) break; } =20 - if (s->prefix & PREFIX_LOCK) { - if (decode.e.special !=3D X86_SPECIAL_HasLock || !decode.op[0].has= _ea) { - goto illegal_op; - } + if ((s->prefix & PREFIX_LOCK) && !accept_lock) { + goto illegal_op; } =20 if (!validate_vex(s, &decode)) { @@ -2755,7 +2775,7 @@ static void disas_insn(DisasContext *s, CPUState *cpu) =20 if (decode.e.special !=3D X86_SPECIAL_NoLoadEA && (decode.op[0].has_ea || decode.op[1].has_ea || decode.op[2].has_ea= )) { - gen_load_ea(s, &decode.mem, decode.e.vex_class =3D=3D 12); + gen_load_ea(s, &decode); } if (s->prefix & PREFIX_LOCK) { gen_load(s, &decode, 2, s->T1); diff --git a/target/i386/tcg/emit.c.inc b/target/i386/tcg/emit.c.inc index fc7477833bc..a25dff0570c 100644 --- a/target/i386/tcg/emit.c.inc +++ b/target/i386/tcg/emit.c.inc @@ -73,9 +73,25 @@ static void gen_NM_exception(DisasContext *s) gen_exception(s, EXCP07_PREX); } =20 -static void gen_load_ea(DisasContext *s, AddressParts *mem, bool is_vsib) +static void gen_load_ea(DisasContext *s, X86DecodedInsn *decode) { - TCGv ea =3D gen_lea_modrm_1(s, *mem, is_vsib); + AddressParts *mem =3D &decode->mem; + TCGv ea; + + ea =3D gen_lea_modrm_1(s, *mem, decode->e.vex_class =3D=3D 12); + if (decode->e.special =3D=3D X86_SPECIAL_BitTest) { + MemOp ot =3D decode->op[1].ot; + int poslen =3D 8 << ot; + TCGv ofs =3D tcg_temp_new(); + + /* Extract memory displacement from T1. */ + assert(decode->op[2].unit =3D=3D X86_OP_INT); + tcg_gen_sextract_tl(ofs, s->T1, 3, poslen - 3); + tcg_gen_andi_tl(ofs, ofs, -1 << ot); + tcg_gen_add_tl(s->A0, ea, ofs); + ea =3D s->A0; + } + gen_lea_v_seg(s, ea, mem->def_seg, s->override); } =20 @@ -407,6 +423,32 @@ static void prepare_update3_cc(X86DecodedInsn *decode,= DisasContext *s, CCOp op, decode->cc_op =3D op; } =20 +/* Set up decode->cc_* to modify CF while keeping other flags unchanged. = */ +static void prepare_update_cf(X86DecodedInsn *decode, DisasContext *s, TCG= v cf) +{ + switch (s->cc_op) { + case CC_OP_ADOX: + case CC_OP_ADCOX: + decode->cc_src2 =3D cpu_cc_src2; + decode->cc_src =3D cpu_cc_src; + decode->cc_op =3D CC_OP_ADCOX; + break; + + case CC_OP_EFLAGS: + case CC_OP_ADCX: + decode->cc_src =3D cpu_cc_src; + decode->cc_op =3D CC_OP_ADCX; + break; + + default: + decode->cc_src =3D tcg_temp_new(); + gen_mov_eflags(s, decode->cc_src); + decode->cc_op =3D CC_OP_ADCX; + break; + } + decode->cc_dst =3D cf; +} + static void gen_store_sse(DisasContext *s, X86DecodedInsn *decode, int src= _ofs) { MemOp ot =3D decode->op[0].ot; @@ -1385,6 +1427,109 @@ static void gen_BSWAP(DisasContext *s, X86DecodedIn= sn *decode) tcg_gen_bswap32_tl(s->T0, s->T0, TCG_BSWAP_OZ); } =20 +static TCGv gen_bt_mask(DisasContext *s, X86DecodedInsn *decode) +{ + MemOp ot =3D decode->op[1].ot; + TCGv mask =3D tcg_temp_new(); + + tcg_gen_andi_tl(s->T1, s->T1, (8 << ot) - 1); + tcg_gen_shl_tl(mask, tcg_constant_tl(1), s->T1); + return mask; +} + +/* Expects truncated bit index in s->T1, 1 << s->T1 in MASK. */ +static void gen_bt_flags(DisasContext *s, X86DecodedInsn *decode, TCGv src= , TCGv mask) +{ + TCGv cf; + + /* + * C is the result of the test, Z is unchanged, and the others + * are all undefined. + */ + switch (s->cc_op) { + case CC_OP_DYNAMIC: + case CC_OP_CLR: + case CC_OP_EFLAGS: + case CC_OP_ADCX: + case CC_OP_ADOX: + case CC_OP_ADCOX: + /* Generate EFLAGS and replace the C bit. */ + cf =3D tcg_temp_new(); + tcg_gen_setcond_tl(TCG_COND_TSTNE, cf, src, mask); + prepare_update_cf(decode, s, cf); + break; + default: + /* + * Z was going to be computed from the non-zero status of CC_DST. + * We can get that same Z value (and the new C value) by leaving + * CC_DST alone, setting CC_SRC, and using a CC_OP_SAR of the + * same width. + */ + decode->cc_src =3D tcg_temp_new(); + decode->cc_dst =3D cpu_cc_dst; + decode->cc_op =3D ((s->cc_op - CC_OP_MULB) & 3) + CC_OP_SARB; + tcg_gen_shr_tl(decode->cc_src, src, s->T1); + break; + } +} + +static void gen_BT(DisasContext *s, X86DecodedInsn *decode) +{ + TCGv mask =3D gen_bt_mask(s, decode); + + gen_bt_flags(s, decode, s->T0, mask); +} + +static void gen_BTC(DisasContext *s, X86DecodedInsn *decode) +{ + MemOp ot =3D decode->op[0].ot; + TCGv old =3D tcg_temp_new(); + TCGv mask =3D gen_bt_mask(s, decode); + + if (s->prefix & PREFIX_LOCK) { + tcg_gen_atomic_fetch_xor_tl(old, s->A0, mask, s->mem_index, ot | M= O_LE); + } else { + tcg_gen_mov_tl(old, s->T0); + tcg_gen_xor_tl(s->T0, s->T0, mask); + } + + gen_bt_flags(s, decode, old, mask); +} + +static void gen_BTR(DisasContext *s, X86DecodedInsn *decode) +{ + MemOp ot =3D decode->op[0].ot; + TCGv old =3D tcg_temp_new(); + TCGv mask =3D gen_bt_mask(s, decode); + + if (s->prefix & PREFIX_LOCK) { + TCGv maskc =3D tcg_temp_new(); + tcg_gen_not_tl(maskc, mask); + tcg_gen_atomic_fetch_and_tl(old, s->A0, maskc, s->mem_index, ot | = MO_LE); + } else { + tcg_gen_mov_tl(old, s->T0); + tcg_gen_andc_tl(s->T0, s->T0, mask); + } + + gen_bt_flags(s, decode, old, mask); +} + +static void gen_BTS(DisasContext *s, X86DecodedInsn *decode) +{ + MemOp ot =3D decode->op[0].ot; + TCGv old =3D tcg_temp_new(); + TCGv mask =3D gen_bt_mask(s, decode); + + if (s->prefix & PREFIX_LOCK) { + tcg_gen_atomic_fetch_or_tl(old, s->A0, mask, s->mem_index, ot | MO= _LE); + } else { + tcg_gen_mov_tl(old, s->T0); + tcg_gen_or_tl(s->T0, s->T0, mask); + } + + gen_bt_flags(s, decode, old, mask); +} + static void gen_BZHI(DisasContext *s, X86DecodedInsn *decode) { MemOp ot =3D decode->op[0].ot; --=20 2.45.2