diff options
author | David 'Digit' Turner <digit@android.com> | 2011-05-11 18:19:41 +0200 |
---|---|---|
committer | David 'Digit' Turner <digit@android.com> | 2011-06-01 17:08:19 +0200 |
commit | f1d9bf153726533acf659efd796aa484dfd0b412 (patch) | |
tree | a3bcdccf0b81e1bc6e4ac6a21fb6b4777d4f0383 /tcg/i386 | |
parent | 280afa072a7b829e581d884c2b3276530a6014b7 (diff) | |
download | external_qemu-f1d9bf153726533acf659efd796aa484dfd0b412.zip external_qemu-f1d9bf153726533acf659efd796aa484dfd0b412.tar.gz external_qemu-f1d9bf153726533acf659efd796aa484dfd0b412.tar.bz2 |
tcg: integrate upstream version
Change-Id: Ifcdebc2e7179fbc64b46a9150e6dae62f86eba3c
Diffstat (limited to 'tcg/i386')
-rw-r--r-- | tcg/i386/tcg-target.c | 2002 | ||||
-rw-r--r-- | tcg/i386/tcg-target.h | 61 |
2 files changed, 1423 insertions, 640 deletions
diff --git a/tcg/i386/tcg-target.c b/tcg/i386/tcg-target.c index 972b102..09a5c55 100644 --- a/tcg/i386/tcg-target.c +++ b/tcg/i386/tcg-target.c @@ -24,18 +24,33 @@ #ifndef NDEBUG static const char * const tcg_target_reg_names[TCG_TARGET_NB_REGS] = { - "%eax", - "%ecx", - "%edx", - "%ebx", - "%esp", - "%ebp", - "%esi", - "%edi", +#if TCG_TARGET_REG_BITS == 64 + "%rax", "%rcx", "%rdx", "%rbx", "%rsp", "%rbp", "%rsi", "%rdi", + "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15", +#else + "%eax", "%ecx", "%edx", "%ebx", "%esp", "%ebp", "%esi", "%edi", +#endif }; #endif static const int tcg_target_reg_alloc_order[] = { +#if TCG_TARGET_REG_BITS == 64 + TCG_REG_RBP, + TCG_REG_RBX, + TCG_REG_R12, + TCG_REG_R13, + TCG_REG_R14, + TCG_REG_R15, + TCG_REG_R10, + TCG_REG_R11, + TCG_REG_R9, + TCG_REG_R8, + TCG_REG_RCX, + TCG_REG_RDX, + TCG_REG_RSI, + TCG_REG_RDI, + TCG_REG_RAX, +#else TCG_REG_EAX, TCG_REG_EDX, TCG_REG_ECX, @@ -43,23 +58,49 @@ static const int tcg_target_reg_alloc_order[] = { TCG_REG_ESI, TCG_REG_EDI, TCG_REG_EBP, +#endif +}; + +static const int tcg_target_call_iarg_regs[] = { +#if TCG_TARGET_REG_BITS == 64 + TCG_REG_RDI, + TCG_REG_RSI, + TCG_REG_RDX, + TCG_REG_RCX, + TCG_REG_R8, + TCG_REG_R9, +#else + TCG_REG_EAX, + TCG_REG_EDX, + TCG_REG_ECX +#endif }; -static const int tcg_target_call_iarg_regs[3] = { TCG_REG_EAX, TCG_REG_EDX, TCG_REG_ECX }; -static const int tcg_target_call_oarg_regs[2] = { TCG_REG_EAX, TCG_REG_EDX }; +static const int tcg_target_call_oarg_regs[2] = { + TCG_REG_EAX, + TCG_REG_EDX +}; static uint8_t *tb_ret_addr; -static void patch_reloc(uint8_t *code_ptr, int type, +static void patch_reloc(uint8_t *code_ptr, int type, tcg_target_long value, tcg_target_long addend) { value += addend; switch(type) { - case R_386_32: + case R_386_PC32: + value -= (uintptr_t)code_ptr; + if (value != (int32_t)value) { + tcg_abort(); + } *(uint32_t *)code_ptr = value; break; - case R_386_PC32: - *(uint32_t *)code_ptr = value - (long)code_ptr; + case R_386_PC8: + value -= (uintptr_t)code_ptr; + if (value != (int8_t)value) { + tcg_abort(); + } + *(uint8_t *)code_ptr = value; break; default: tcg_abort(); @@ -69,6 +110,10 @@ static void patch_reloc(uint8_t *code_ptr, int type, /* maximum number of register used for input function arguments */ static inline int tcg_target_get_call_iarg_regs_count(int flags) { + if (TCG_TARGET_REG_BITS == 64) { + return 6; + } + flags &= TCG_CALL_TYPE_MASK; switch(flags) { case TCG_CALL_TYPE_STD: @@ -115,20 +160,42 @@ static int target_parse_constraint(TCGArgConstraint *ct, const char **pct_str) break; case 'q': ct->ct |= TCG_CT_REG; - tcg_regset_set32(ct->u.regs, 0, 0xf); + if (TCG_TARGET_REG_BITS == 64) { + tcg_regset_set32(ct->u.regs, 0, 0xffff); + } else { + tcg_regset_set32(ct->u.regs, 0, 0xf); + } break; case 'r': ct->ct |= TCG_CT_REG; - tcg_regset_set32(ct->u.regs, 0, 0xff); + if (TCG_TARGET_REG_BITS == 64) { + tcg_regset_set32(ct->u.regs, 0, 0xffff); + } else { + tcg_regset_set32(ct->u.regs, 0, 0xff); + } break; /* qemu_ld/st address constraint */ case 'L': ct->ct |= TCG_CT_REG; - tcg_regset_set32(ct->u.regs, 0, 0xff); - tcg_regset_reset_reg(ct->u.regs, TCG_REG_EAX); - tcg_regset_reset_reg(ct->u.regs, TCG_REG_EDX); + if (TCG_TARGET_REG_BITS == 64) { + tcg_regset_set32(ct->u.regs, 0, 0xffff); + tcg_regset_reset_reg(ct->u.regs, TCG_REG_RSI); + tcg_regset_reset_reg(ct->u.regs, TCG_REG_RDI); + } else { + tcg_regset_set32(ct->u.regs, 0, 0xff); + tcg_regset_reset_reg(ct->u.regs, TCG_REG_EAX); + tcg_regset_reset_reg(ct->u.regs, TCG_REG_EDX); + } break; + + case 'e': + ct->ct |= TCG_CT_CONST_S32; + break; + case 'Z': + ct->ct |= TCG_CT_CONST_U32; + break; + default: return -1; } @@ -141,14 +208,83 @@ static int target_parse_constraint(TCGArgConstraint *ct, const char **pct_str) static inline int tcg_target_const_match(tcg_target_long val, const TCGArgConstraint *arg_ct) { - int ct; - ct = arg_ct->ct; - if (ct & TCG_CT_CONST) + int ct = arg_ct->ct; + if (ct & TCG_CT_CONST) { return 1; - else - return 0; + } + if ((ct & TCG_CT_CONST_S32) && val == (int32_t)val) { + return 1; + } + if ((ct & TCG_CT_CONST_U32) && val == (uint32_t)val) { + return 1; + } + return 0; } +#if TCG_TARGET_REG_BITS == 64 +# define LOWREGMASK(x) ((x) & 7) +#else +# define LOWREGMASK(x) (x) +#endif + +#define P_EXT 0x100 /* 0x0f opcode prefix */ +#define P_DATA16 0x200 /* 0x66 opcode prefix */ +#if TCG_TARGET_REG_BITS == 64 +# define P_ADDR32 0x400 /* 0x67 opcode prefix */ +# define P_REXW 0x800 /* Set REX.W = 1 */ +# define P_REXB_R 0x1000 /* REG field as byte register */ +# define P_REXB_RM 0x2000 /* R/M field as byte register */ +#else +# define P_ADDR32 0 +# define P_REXW 0 +# define P_REXB_R 0 +# define P_REXB_RM 0 +#endif + +#define OPC_ARITH_EvIz (0x81) +#define OPC_ARITH_EvIb (0x83) +#define OPC_ARITH_GvEv (0x03) /* ... plus (ARITH_FOO << 3) */ +#define OPC_ADD_GvEv (OPC_ARITH_GvEv | (ARITH_ADD << 3)) +#define OPC_BSWAP (0xc8 | P_EXT) +#define OPC_CALL_Jz (0xe8) +#define OPC_CMP_GvEv (OPC_ARITH_GvEv | (ARITH_CMP << 3)) +#define OPC_DEC_r32 (0x48) +#define OPC_IMUL_GvEv (0xaf | P_EXT) +#define OPC_IMUL_GvEvIb (0x6b) +#define OPC_IMUL_GvEvIz (0x69) +#define OPC_INC_r32 (0x40) +#define OPC_JCC_long (0x80 | P_EXT) /* ... plus condition code */ +#define OPC_JCC_short (0x70) /* ... plus condition code */ +#define OPC_JMP_long (0xe9) +#define OPC_JMP_short (0xeb) +#define OPC_LEA (0x8d) +#define OPC_MOVB_EvGv (0x88) /* stores, more or less */ +#define OPC_MOVL_EvGv (0x89) /* stores, more or less */ +#define OPC_MOVL_GvEv (0x8b) /* loads, more or less */ +#define OPC_MOVL_EvIz (0xc7) +#define OPC_MOVL_Iv (0xb8) +#define OPC_MOVSBL (0xbe | P_EXT) +#define OPC_MOVSWL (0xbf | P_EXT) +#define OPC_MOVSLQ (0x63 | P_REXW) +#define OPC_MOVZBL (0xb6 | P_EXT) +#define OPC_MOVZWL (0xb7 | P_EXT) +#define OPC_POP_r32 (0x58) +#define OPC_PUSH_r32 (0x50) +#define OPC_PUSH_Iv (0x68) +#define OPC_PUSH_Ib (0x6a) +#define OPC_RET (0xc3) +#define OPC_SETCC (0x90 | P_EXT | P_REXB_RM) /* ... plus cc */ +#define OPC_SHIFT_1 (0xd1) +#define OPC_SHIFT_Ib (0xc1) +#define OPC_SHIFT_cl (0xd3) +#define OPC_TESTL (0x85) +#define OPC_XCHG_ax_r32 (0x90) + +#define OPC_GRP3_Ev (0xf7) +#define OPC_GRP5 (0xff) + +/* Group 1 opcode extensions for 0x80-0x83. + These are also used as modifiers for OPC_ARITH. */ #define ARITH_ADD 0 #define ARITH_OR 1 #define ARITH_ADC 2 @@ -158,12 +294,28 @@ static inline int tcg_target_const_match(tcg_target_long val, #define ARITH_XOR 6 #define ARITH_CMP 7 +/* Group 2 opcode extensions for 0xc0, 0xc1, 0xd0-0xd3. */ #define SHIFT_ROL 0 #define SHIFT_ROR 1 #define SHIFT_SHL 4 #define SHIFT_SHR 5 #define SHIFT_SAR 7 +/* Group 3 opcode extensions for 0xf6, 0xf7. To be used with OPC_GRP3. */ +#define EXT3_NOT 2 +#define EXT3_NEG 3 +#define EXT3_MUL 4 +#define EXT3_IMUL 5 +#define EXT3_DIV 6 +#define EXT3_IDIV 7 + +/* Group 5 opcode extensions for 0xff. To be used with OPC_GRP5. */ +#define EXT5_INC_Ev 0 +#define EXT5_DEC_Ev 1 +#define EXT5_CALLN_Ev 2 +#define EXT5_JMPN_Ev 4 + +/* Condition codes to be added to OPC_JCC_{long,short}. */ #define JCC_JMP (-1) #define JCC_JO 0x0 #define JCC_JNO 0x1 @@ -182,8 +334,6 @@ static inline int tcg_target_const_match(tcg_target_long val, #define JCC_JLE 0xe #define JCC_JG 0xf -#define P_EXT 0x100 /* 0x0f opcode prefix */ - static const uint8_t tcg_cond_to_jcc[10] = { [TCG_COND_EQ] = JCC_JE, [TCG_COND_NE] = JCC_JNE, @@ -197,228 +347,616 @@ static const uint8_t tcg_cond_to_jcc[10] = { [TCG_COND_GTU] = JCC_JA, }; -static inline void tcg_out_opc(TCGContext *s, int opc) +#if TCG_TARGET_REG_BITS == 64 +static void tcg_out_opc(TCGContext *s, int opc, int r, int rm, int x) +{ + int rex; + + if (opc & P_DATA16) { + /* We should never be asking for both 16 and 64-bit operation. */ + assert((opc & P_REXW) == 0); + tcg_out8(s, 0x66); + } + if (opc & P_ADDR32) { + tcg_out8(s, 0x67); + } + + rex = 0; + rex |= (opc & P_REXW) >> 8; /* REX.W */ + rex |= (r & 8) >> 1; /* REX.R */ + rex |= (x & 8) >> 2; /* REX.X */ + rex |= (rm & 8) >> 3; /* REX.B */ + + /* P_REXB_{R,RM} indicates that the given register is the low byte. + For %[abcd]l we need no REX prefix, but for %{si,di,bp,sp}l we do, + as otherwise the encoding indicates %[abcd]h. Note that the values + that are ORed in merely indicate that the REX byte must be present; + those bits get discarded in output. */ + rex |= opc & (r >= 4 ? P_REXB_R : 0); + rex |= opc & (rm >= 4 ? P_REXB_RM : 0); + + if (rex) { + tcg_out8(s, (uint8_t)(rex | 0x40)); + } + + if (opc & P_EXT) { + tcg_out8(s, 0x0f); + } + tcg_out8(s, opc); +} +#else +static void tcg_out_opc(TCGContext *s, int opc) { - if (opc & P_EXT) + if (opc & P_DATA16) { + tcg_out8(s, 0x66); + } + if (opc & P_EXT) { tcg_out8(s, 0x0f); + } tcg_out8(s, opc); } +/* Discard the register arguments to tcg_out_opc early, so as not to penalize + the 32-bit compilation paths. This method works with all versions of gcc, + whereas relying on optimization may not be able to exclude them. */ +#define tcg_out_opc(s, opc, r, rm, x) (tcg_out_opc)(s, opc) +#endif -static inline void tcg_out_modrm(TCGContext *s, int opc, int r, int rm) +static void tcg_out_modrm(TCGContext *s, int opc, int r, int rm) { - tcg_out_opc(s, opc); - tcg_out8(s, 0xc0 | (r << 3) | rm); + tcg_out_opc(s, opc, r, rm, 0); + tcg_out8(s, 0xc0 | (LOWREGMASK(r) << 3) | LOWREGMASK(rm)); } -/* rm == -1 means no register index */ -static inline void tcg_out_modrm_offset(TCGContext *s, int opc, int r, int rm, - int32_t offset) +/* Output an opcode with a full "rm + (index<<shift) + offset" address mode. + We handle either RM and INDEX missing with a negative value. In 64-bit + mode for absolute addresses, ~RM is the size of the immediate operand + that will follow the instruction. */ + +static void tcg_out_modrm_sib_offset(TCGContext *s, int opc, int r, int rm, + int index, int shift, + tcg_target_long offset) { - tcg_out_opc(s, opc); - if (rm == -1) { - tcg_out8(s, 0x05 | (r << 3)); - tcg_out32(s, offset); - } else if (offset == 0 && rm != TCG_REG_EBP) { - if (rm == TCG_REG_ESP) { - tcg_out8(s, 0x04 | (r << 3)); - tcg_out8(s, 0x24); - } else { - tcg_out8(s, 0x00 | (r << 3) | rm); - } - } else if ((int8_t)offset == offset) { - if (rm == TCG_REG_ESP) { - tcg_out8(s, 0x44 | (r << 3)); - tcg_out8(s, 0x24); + int mod, len; + + if (index < 0 && rm < 0) { + if (TCG_TARGET_REG_BITS == 64) { + /* Try for a rip-relative addressing mode. This has replaced + the 32-bit-mode absolute addressing encoding. */ + tcg_target_long pc = (tcg_target_long)s->code_ptr + 5 + ~rm; + tcg_target_long disp = offset - pc; + if (disp == (int32_t)disp) { + tcg_out_opc(s, opc, r, 0, 0); + tcg_out8(s, (LOWREGMASK(r) << 3) | 5); + tcg_out32(s, disp); + return; + } + + /* Try for an absolute address encoding. This requires the + use of the MODRM+SIB encoding and is therefore larger than + rip-relative addressing. */ + if (offset == (int32_t)offset) { + tcg_out_opc(s, opc, r, 0, 0); + tcg_out8(s, (LOWREGMASK(r) << 3) | 4); + tcg_out8(s, (4 << 3) | 5); + tcg_out32(s, offset); + return; + } + + /* ??? The memory isn't directly addressable. */ + tcg_abort(); } else { - tcg_out8(s, 0x40 | (r << 3) | rm); + /* Absolute address. */ + tcg_out_opc(s, opc, r, 0, 0); + tcg_out8(s, (r << 3) | 5); + tcg_out32(s, offset); + return; } - tcg_out8(s, offset); + } + + /* Find the length of the immediate addend. Note that the encoding + that would be used for (%ebp) indicates absolute addressing. */ + if (rm < 0) { + mod = 0, len = 4, rm = 5; + } else if (offset == 0 && LOWREGMASK(rm) != TCG_REG_EBP) { + mod = 0, len = 0; + } else if (offset == (int8_t)offset) { + mod = 0x40, len = 1; + } else { + mod = 0x80, len = 4; + } + + /* Use a single byte MODRM format if possible. Note that the encoding + that would be used for %esp is the escape to the two byte form. */ + if (index < 0 && LOWREGMASK(rm) != TCG_REG_ESP) { + /* Single byte MODRM format. */ + tcg_out_opc(s, opc, r, rm, 0); + tcg_out8(s, mod | (LOWREGMASK(r) << 3) | LOWREGMASK(rm)); } else { - if (rm == TCG_REG_ESP) { - tcg_out8(s, 0x84 | (r << 3)); - tcg_out8(s, 0x24); + /* Two byte MODRM+SIB format. */ + + /* Note that the encoding that would place %esp into the index + field indicates no index register. In 64-bit mode, the REX.X + bit counts, so %r12 can be used as the index. */ + if (index < 0) { + index = 4; } else { - tcg_out8(s, 0x80 | (r << 3) | rm); + assert(index != TCG_REG_ESP); } + + tcg_out_opc(s, opc, r, rm, index); + tcg_out8(s, mod | (LOWREGMASK(r) << 3) | 4); + tcg_out8(s, (shift << 6) | (LOWREGMASK(index) << 3) | LOWREGMASK(rm)); + } + + if (len == 1) { + tcg_out8(s, offset); + } else if (len == 4) { tcg_out32(s, offset); } } -static inline void tcg_out_mov(TCGContext *s, int ret, int arg) +/* A simplification of the above with no index or shift. */ +static inline void tcg_out_modrm_offset(TCGContext *s, int opc, int r, + int rm, tcg_target_long offset) +{ + tcg_out_modrm_sib_offset(s, opc, r, rm, -1, 0, offset); +} + +/* Generate dest op= src. Uses the same ARITH_* codes as tgen_arithi. */ +static inline void tgen_arithr(TCGContext *s, int subop, int dest, int src) +{ + /* Propagate an opcode prefix, such as P_REXW. */ + int ext = subop & ~0x7; + subop &= 0x7; + + tcg_out_modrm(s, OPC_ARITH_GvEv + (subop << 3) + ext, dest, src); +} + +static inline void tcg_out_mov(TCGContext *s, TCGType type, int ret, int arg) { - if (arg != ret) - tcg_out_modrm(s, 0x8b, ret, arg); + if (arg != ret) { + int opc = OPC_MOVL_GvEv + (type == TCG_TYPE_I64 ? P_REXW : 0); + tcg_out_modrm(s, opc, ret, arg); + } } -static inline void tcg_out_movi(TCGContext *s, TCGType type, - int ret, int32_t arg) +static void tcg_out_movi(TCGContext *s, TCGType type, + int ret, tcg_target_long arg) { if (arg == 0) { - /* xor r0,r0 */ - tcg_out_modrm(s, 0x01 | (ARITH_XOR << 3), ret, ret); + tgen_arithr(s, ARITH_XOR, ret, ret); + return; + } else if (arg == (uint32_t)arg || type == TCG_TYPE_I32) { + tcg_out_opc(s, OPC_MOVL_Iv + LOWREGMASK(ret), 0, ret, 0); + tcg_out32(s, arg); + } else if (arg == (int32_t)arg) { + tcg_out_modrm(s, OPC_MOVL_EvIz + P_REXW, 0, ret); + tcg_out32(s, arg); } else { - tcg_out8(s, 0xb8 + ret); + tcg_out_opc(s, OPC_MOVL_Iv + P_REXW + LOWREGMASK(ret), 0, ret, 0); tcg_out32(s, arg); + tcg_out32(s, arg >> 31 >> 1); + } +} + +static inline void tcg_out_pushi(TCGContext *s, tcg_target_long val) +{ + if (val == (int8_t)val) { + tcg_out_opc(s, OPC_PUSH_Ib, 0, 0, 0); + tcg_out8(s, val); + } else if (val == (int32_t)val) { + tcg_out_opc(s, OPC_PUSH_Iv, 0, 0, 0); + tcg_out32(s, val); + } else { + tcg_abort(); } } +static inline void tcg_out_push(TCGContext *s, int reg) +{ + tcg_out_opc(s, OPC_PUSH_r32 + LOWREGMASK(reg), 0, reg, 0); +} + +static inline void tcg_out_pop(TCGContext *s, int reg) +{ + tcg_out_opc(s, OPC_POP_r32 + LOWREGMASK(reg), 0, reg, 0); +} + static inline void tcg_out_ld(TCGContext *s, TCGType type, int ret, int arg1, tcg_target_long arg2) { - /* movl */ - tcg_out_modrm_offset(s, 0x8b, ret, arg1, arg2); + int opc = OPC_MOVL_GvEv + (type == TCG_TYPE_I64 ? P_REXW : 0); + tcg_out_modrm_offset(s, opc, ret, arg1, arg2); } static inline void tcg_out_st(TCGContext *s, TCGType type, int arg, int arg1, tcg_target_long arg2) { - /* movl */ - tcg_out_modrm_offset(s, 0x89, arg, arg1, arg2); + int opc = OPC_MOVL_EvGv + (type == TCG_TYPE_I64 ? P_REXW : 0); + tcg_out_modrm_offset(s, opc, arg, arg1, arg2); } -static inline void tgen_arithi(TCGContext *s, int c, int r0, int32_t val, int cf) +static void tcg_out_shifti(TCGContext *s, int subopc, int reg, int count) { - if (!cf && ((c == ARITH_ADD && val == 1) || (c == ARITH_SUB && val == -1))) { - /* inc */ - tcg_out_opc(s, 0x40 + r0); - } else if (!cf && ((c == ARITH_ADD && val == -1) || (c == ARITH_SUB && val == 1))) { - /* dec */ - tcg_out_opc(s, 0x48 + r0); - } else if (val == (int8_t)val) { - tcg_out_modrm(s, 0x83, c, r0); - tcg_out8(s, val); - } else if (c == ARITH_AND && val == 0xffu && r0 < 4) { - /* movzbl */ - tcg_out_modrm(s, 0xb6 | P_EXT, r0, r0); - } else if (c == ARITH_AND && val == 0xffffu) { - /* movzwl */ - tcg_out_modrm(s, 0xb7 | P_EXT, r0, r0); + /* Propagate an opcode prefix, such as P_DATA16. */ + int ext = subopc & ~0x7; + subopc &= 0x7; + + if (count == 1) { + tcg_out_modrm(s, OPC_SHIFT_1 + ext, subopc, reg); } else { - tcg_out_modrm(s, 0x81, c, r0); + tcg_out_modrm(s, OPC_SHIFT_Ib + ext, subopc, reg); + tcg_out8(s, count); + } +} + +static inline void tcg_out_bswap32(TCGContext *s, int reg) +{ + tcg_out_opc(s, OPC_BSWAP + LOWREGMASK(reg), 0, reg, 0); +} + +static inline void tcg_out_rolw_8(TCGContext *s, int reg) +{ + tcg_out_shifti(s, SHIFT_ROL + P_DATA16, reg, 8); +} + +static inline void tcg_out_ext8u(TCGContext *s, int dest, int src) +{ + /* movzbl */ + assert(src < 4 || TCG_TARGET_REG_BITS == 64); + tcg_out_modrm(s, OPC_MOVZBL + P_REXB_RM, dest, src); +} + +static void tcg_out_ext8s(TCGContext *s, int dest, int src, int rexw) +{ + /* movsbl */ + assert(src < 4 || TCG_TARGET_REG_BITS == 64); + tcg_out_modrm(s, OPC_MOVSBL + P_REXB_RM + rexw, dest, src); +} + +static inline void tcg_out_ext16u(TCGContext *s, int dest, int src) +{ + /* movzwl */ + tcg_out_modrm(s, OPC_MOVZWL, dest, src); +} + +static inline void tcg_out_ext16s(TCGContext *s, int dest, int src, int rexw) +{ + /* movsw[lq] */ + tcg_out_modrm(s, OPC_MOVSWL + rexw, dest, src); +} + +static inline void tcg_out_ext32u(TCGContext *s, int dest, int src) +{ + /* 32-bit mov zero extends. */ + tcg_out_modrm(s, OPC_MOVL_GvEv, dest, src); +} + +static inline void tcg_out_ext32s(TCGContext *s, int dest, int src) +{ + tcg_out_modrm(s, OPC_MOVSLQ, dest, src); +} + +static inline void tcg_out_bswap64(TCGContext *s, int reg) +{ + tcg_out_opc(s, OPC_BSWAP + P_REXW + LOWREGMASK(reg), 0, reg, 0); +} + +static void tgen_arithi(TCGContext *s, int c, int r0, + tcg_target_long val, int cf) +{ + int rexw = 0; + + if (TCG_TARGET_REG_BITS == 64) { + rexw = c & -8; + c &= 7; + } + + /* ??? While INC is 2 bytes shorter than ADDL $1, they also induce + partial flags update stalls on Pentium4 and are not recommended + by current Intel optimization manuals. */ + if (!cf && (c == ARITH_ADD || c == ARITH_SUB) && (val == 1 || val == -1)) { + int is_inc = (c == ARITH_ADD) ^ (val < 0); + if (TCG_TARGET_REG_BITS == 64) { + /* The single-byte increment encodings are re-tasked as the + REX prefixes. Use the MODRM encoding. */ + tcg_out_modrm(s, OPC_GRP5 + rexw, + (is_inc ? EXT5_INC_Ev : EXT5_DEC_Ev), r0); + } else { + tcg_out8(s, (is_inc ? OPC_INC_r32 : OPC_DEC_r32) + r0); + } + return; + } + + if (c == ARITH_AND) { + if (TCG_TARGET_REG_BITS == 64) { + if (val == 0xffffffffu) { + tcg_out_ext32u(s, r0, r0); + return; + } + if (val == (uint32_t)val) { + /* AND with no high bits set can use a 32-bit operation. */ + rexw = 0; + } + } + if (val == 0xffu && (r0 < 4 || TCG_TARGET_REG_BITS == 64)) { + tcg_out_ext8u(s, r0, r0); + return; + } + if (val == 0xffffu) { + tcg_out_ext16u(s, r0, r0); + return; + } + } + + if (val == (int8_t)val) { + tcg_out_modrm(s, OPC_ARITH_EvIb + rexw, c, r0); + tcg_out8(s, val); + return; + } + if (rexw == 0 || val == (int32_t)val) { + tcg_out_modrm(s, OPC_ARITH_EvIz + rexw, c, r0); tcg_out32(s, val); + return; } + + tcg_abort(); } static void tcg_out_addi(TCGContext *s, int reg, tcg_target_long val) { - if (val != 0) - tgen_arithi(s, ARITH_ADD, reg, val, 0); + if (val != 0) { + tgen_arithi(s, ARITH_ADD + P_REXW, reg, val, 0); + } } -static void tcg_out_jxx(TCGContext *s, int opc, int label_index) +#undef small /* for mingw build */ + +/* Use SMALL != 0 to force a short forward branch. */ +static void tcg_out_jxx(TCGContext *s, int opc, int label_index, int small) { int32_t val, val1; TCGLabel *l = &s->labels[label_index]; - + if (l->has_value) { val = l->u.value - (tcg_target_long)s->code_ptr; val1 = val - 2; if ((int8_t)val1 == val1) { - if (opc == -1) - tcg_out8(s, 0xeb); - else - tcg_out8(s, 0x70 + opc); + if (opc == -1) { + tcg_out8(s, OPC_JMP_short); + } else { + tcg_out8(s, OPC_JCC_short + opc); + } tcg_out8(s, val1); } else { + if (small) { + tcg_abort(); + } if (opc == -1) { - tcg_out8(s, 0xe9); + tcg_out8(s, OPC_JMP_long); tcg_out32(s, val - 5); } else { - tcg_out8(s, 0x0f); - tcg_out8(s, 0x80 + opc); + tcg_out_opc(s, OPC_JCC_long + opc, 0, 0, 0); tcg_out32(s, val - 6); } } + } else if (small) { + if (opc == -1) { + tcg_out8(s, OPC_JMP_short); + } else { + tcg_out8(s, OPC_JCC_short + opc); + } + tcg_out_reloc(s, s->code_ptr, R_386_PC8, label_index, -1); + s->code_ptr += 1; } else { if (opc == -1) { - tcg_out8(s, 0xe9); + tcg_out8(s, OPC_JMP_long); } else { - tcg_out8(s, 0x0f); - tcg_out8(s, 0x80 + opc); + tcg_out_opc(s, OPC_JCC_long + opc, 0, 0, 0); } tcg_out_reloc(s, s->code_ptr, R_386_PC32, label_index, -4); s->code_ptr += 4; } } -static void tcg_out_brcond(TCGContext *s, int cond, - TCGArg arg1, TCGArg arg2, int const_arg2, - int label_index) +static void tcg_out_cmp(TCGContext *s, TCGArg arg1, TCGArg arg2, + int const_arg2, int rexw) { if (const_arg2) { if (arg2 == 0) { /* test r, r */ - tcg_out_modrm(s, 0x85, arg1, arg1); + tcg_out_modrm(s, OPC_TESTL + rexw, arg1, arg1); } else { - tgen_arithi(s, ARITH_CMP, arg1, arg2, 0); + tgen_arithi(s, ARITH_CMP + rexw, arg1, arg2, 0); } } else { - tcg_out_modrm(s, 0x01 | (ARITH_CMP << 3), arg2, arg1); + tgen_arithr(s, ARITH_CMP + rexw, arg1, arg2); } - tcg_out_jxx(s, tcg_cond_to_jcc[cond], label_index); } +static void tcg_out_brcond32(TCGContext *s, TCGCond cond, + TCGArg arg1, TCGArg arg2, int const_arg2, + int label_index, int small) +{ + tcg_out_cmp(s, arg1, arg2, const_arg2, 0); + tcg_out_jxx(s, tcg_cond_to_jcc[cond], label_index, small); +} + +#if TCG_TARGET_REG_BITS == 64 +static void tcg_out_brcond64(TCGContext *s, TCGCond cond, + TCGArg arg1, TCGArg arg2, int const_arg2, + int label_index, int small) +{ + tcg_out_cmp(s, arg1, arg2, const_arg2, P_REXW); + tcg_out_jxx(s, tcg_cond_to_jcc[cond], label_index, small); +} +#else /* XXX: we implement it at the target level to avoid having to handle cross basic blocks temporaries */ -static void tcg_out_brcond2(TCGContext *s, - const TCGArg *args, const int *const_args) +static void tcg_out_brcond2(TCGContext *s, const TCGArg *args, + const int *const_args, int small) { int label_next; label_next = gen_new_label(); switch(args[4]) { case TCG_COND_EQ: - tcg_out_brcond(s, TCG_COND_NE, args[0], args[2], const_args[2], label_next); - tcg_out_brcond(s, TCG_COND_EQ, args[1], args[3], const_args[3], args[5]); + tcg_out_brcond32(s, TCG_COND_NE, args[0], args[2], const_args[2], + label_next, 1); + tcg_out_brcond32(s, TCG_COND_EQ, args[1], args[3], const_args[3], + args[5], small); break; case TCG_COND_NE: - tcg_out_brcond(s, TCG_COND_NE, args[0], args[2], const_args[2], args[5]); - tcg_out_brcond(s, TCG_COND_NE, args[1], args[3], const_args[3], args[5]); + tcg_out_brcond32(s, TCG_COND_NE, args[0], args[2], const_args[2], + args[5], small); + tcg_out_brcond32(s, TCG_COND_NE, args[1], args[3], const_args[3], + args[5], small); break; case TCG_COND_LT: - tcg_out_brcond(s, TCG_COND_LT, args[1], args[3], const_args[3], args[5]); - tcg_out_jxx(s, JCC_JNE, label_next); - tcg_out_brcond(s, TCG_COND_LTU, args[0], args[2], const_args[2], args[5]); + tcg_out_brcond32(s, TCG_COND_LT, args[1], args[3], const_args[3], + args[5], small); + tcg_out_jxx(s, JCC_JNE, label_next, 1); + tcg_out_brcond32(s, TCG_COND_LTU, args[0], args[2], const_args[2], + args[5], small); break; case TCG_COND_LE: - tcg_out_brcond(s, TCG_COND_LT, args[1], args[3], const_args[3], args[5]); - tcg_out_jxx(s, JCC_JNE, label_next); - tcg_out_brcond(s, TCG_COND_LEU, args[0], args[2], const_args[2], args[5]); + tcg_out_brcond32(s, TCG_COND_LT, args[1], args[3], const_args[3], + args[5], small); + tcg_out_jxx(s, JCC_JNE, label_next, 1); + tcg_out_brcond32(s, TCG_COND_LEU, args[0], args[2], const_args[2], + args[5], small); break; case TCG_COND_GT: - tcg_out_brcond(s, TCG_COND_GT, args[1], args[3], const_args[3], args[5]); - tcg_out_jxx(s, JCC_JNE, label_next); - tcg_out_brcond(s, TCG_COND_GTU, args[0], args[2], const_args[2], args[5]); + tcg_out_brcond32(s, TCG_COND_GT, args[1], args[3], const_args[3], + args[5], small); + tcg_out_jxx(s, JCC_JNE, label_next, 1); + tcg_out_brcond32(s, TCG_COND_GTU, args[0], args[2], const_args[2], + args[5], small); break; case TCG_COND_GE: - tcg_out_brcond(s, TCG_COND_GT, args[1], args[3], const_args[3], args[5]); - tcg_out_jxx(s, JCC_JNE, label_next); - tcg_out_brcond(s, TCG_COND_GEU, args[0], args[2], const_args[2], args[5]); + tcg_out_brcond32(s, TCG_COND_GT, args[1], args[3], const_args[3], + args[5], small); + tcg_out_jxx(s, JCC_JNE, label_next, 1); + tcg_out_brcond32(s, TCG_COND_GEU, args[0], args[2], const_args[2], + args[5], small); break; case TCG_COND_LTU: - tcg_out_brcond(s, TCG_COND_LTU, args[1], args[3], const_args[3], args[5]); - tcg_out_jxx(s, JCC_JNE, label_next); - tcg_out_brcond(s, TCG_COND_LTU, args[0], args[2], const_args[2], args[5]); + tcg_out_brcond32(s, TCG_COND_LTU, args[1], args[3], const_args[3], + args[5], small); + tcg_out_jxx(s, JCC_JNE, label_next, 1); + tcg_out_brcond32(s, TCG_COND_LTU, args[0], args[2], const_args[2], + args[5], small); break; case TCG_COND_LEU: - tcg_out_brcond(s, TCG_COND_LTU, args[1], args[3], const_args[3], args[5]); - tcg_out_jxx(s, JCC_JNE, label_next); - tcg_out_brcond(s, TCG_COND_LEU, args[0], args[2], const_args[2], args[5]); + tcg_out_brcond32(s, TCG_COND_LTU, args[1], args[3], const_args[3], + args[5], small); + tcg_out_jxx(s, JCC_JNE, label_next, 1); + tcg_out_brcond32(s, TCG_COND_LEU, args[0], args[2], const_args[2], + args[5], small); break; case TCG_COND_GTU: - tcg_out_brcond(s, TCG_COND_GTU, args[1], args[3], const_args[3], args[5]); - tcg_out_jxx(s, JCC_JNE, label_next); - tcg_out_brcond(s, TCG_COND_GTU, args[0], args[2], const_args[2], args[5]); + tcg_out_brcond32(s, TCG_COND_GTU, args[1], args[3], const_args[3], + args[5], small); + tcg_out_jxx(s, JCC_JNE, label_next, 1); + tcg_out_brcond32(s, TCG_COND_GTU, args[0], args[2], const_args[2], + args[5], small); break; case TCG_COND_GEU: - tcg_out_brcond(s, TCG_COND_GTU, args[1], args[3], const_args[3], args[5]); - tcg_out_jxx(s, JCC_JNE, label_next); - tcg_out_brcond(s, TCG_COND_GEU, args[0], args[2], const_args[2], args[5]); + tcg_out_brcond32(s, TCG_COND_GTU, args[1], args[3], const_args[3], + args[5], small); + tcg_out_jxx(s, JCC_JNE, label_next, 1); + tcg_out_brcond32(s, TCG_COND_GEU, args[0], args[2], const_args[2], + args[5], small); break; default: tcg_abort(); } tcg_out_label(s, label_next, (tcg_target_long)s->code_ptr); } +#endif + +static void tcg_out_setcond32(TCGContext *s, TCGCond cond, TCGArg dest, + TCGArg arg1, TCGArg arg2, int const_arg2) +{ + tcg_out_cmp(s, arg1, arg2, const_arg2, 0); + tcg_out_modrm(s, OPC_SETCC | tcg_cond_to_jcc[cond], 0, dest); + tcg_out_ext8u(s, dest, dest); +} + +#if TCG_TARGET_REG_BITS == 64 +static void tcg_out_setcond64(TCGContext *s, TCGCond cond, TCGArg dest, + TCGArg arg1, TCGArg arg2, int const_arg2) +{ + tcg_out_cmp(s, arg1, arg2, const_arg2, P_REXW); + tcg_out_modrm(s, OPC_SETCC | tcg_cond_to_jcc[cond], 0, dest); + tcg_out_ext8u(s, dest, dest); +} +#else +static void tcg_out_setcond2(TCGContext *s, const TCGArg *args, + const int *const_args) +{ + TCGArg new_args[6]; + int label_true, label_over; + + memcpy(new_args, args+1, 5*sizeof(TCGArg)); + + if (args[0] == args[1] || args[0] == args[2] + || (!const_args[3] && args[0] == args[3]) + || (!const_args[4] && args[0] == args[4])) { + /* When the destination overlaps with one of the argument + registers, don't do anything tricky. */ + label_true = gen_new_label(); + label_over = gen_new_label(); + + new_args[5] = label_true; + tcg_out_brcond2(s, new_args, const_args+1, 1); + + tcg_out_movi(s, TCG_TYPE_I32, args[0], 0); + tcg_out_jxx(s, JCC_JMP, label_over, 1); + tcg_out_label(s, label_true, (tcg_target_long)s->code_ptr); + + tcg_out_movi(s, TCG_TYPE_I32, args[0], 1); + tcg_out_label(s, label_over, (tcg_target_long)s->code_ptr); + } else { + /* When the destination does not overlap one of the arguments, + clear the destination first, jump if cond false, and emit an + increment in the true case. This results in smaller code. */ + + tcg_out_movi(s, TCG_TYPE_I32, args[0], 0); + + label_over = gen_new_label(); + new_args[4] = tcg_invert_cond(new_args[4]); + new_args[5] = label_over; + tcg_out_brcond2(s, new_args, const_args+1, 1); + + tgen_arithi(s, ARITH_ADD, args[0], 1, 0); + tcg_out_label(s, label_over, (tcg_target_long)s->code_ptr); + } +} +#endif + +static void tcg_out_branch(TCGContext *s, int call, tcg_target_long dest) +{ + tcg_target_long disp = dest - (tcg_target_long)s->code_ptr - 5; + + if (disp == (int32_t)disp) { + tcg_out_opc(s, call ? OPC_CALL_Jz : OPC_JMP_long, 0, 0, 0); + tcg_out32(s, disp); + } else { + tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_R10, dest); + tcg_out_modrm(s, OPC_GRP5, + call ? EXT5_CALLN_Ev : EXT5_JMPN_Ev, TCG_REG_R10); + } +} + +static inline void tcg_out_calli(TCGContext *s, tcg_target_long dest) +{ + tcg_out_branch(s, 1, dest); +} + +static void tcg_out_jmp(TCGContext *s, tcg_target_long dest) +{ + tcg_out_branch(s, 0, dest); +} #if defined(CONFIG_SOFTMMU) @@ -437,647 +975,670 @@ static void *qemu_st_helpers[4] = { __stl_mmu, __stq_mmu, }; -#endif -#ifndef CONFIG_USER_ONLY -#define GUEST_BASE 0 -#endif +/* Perform the TLB load and compare. -/* XXX: qemu_ld and qemu_st could be modified to clobber only EDX and - EAX. It will be useful once fixed registers globals are less - common. */ -static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, - int opc) + Inputs: + ADDRLO_IDX contains the index into ARGS of the low part of the + address; the high part of the address is at ADDR_LOW_IDX+1. + + MEM_INDEX and S_BITS are the memory context and log2 size of the load. + + WHICH is the offset into the CPUTLBEntry structure of the slot to read. + This should be offsetof addr_read or addr_write. + + Outputs: + LABEL_PTRS is filled with 1 (32-bit addresses) or 2 (64-bit addresses) + positions of the displacements of forward jumps to the TLB miss case. + + First argument register is loaded with the low part of the address. + In the TLB hit case, it has been adjusted as indicated by the TLB + and so is a host address. In the TLB miss case, it continues to + hold a guest address. + + Second argument register is clobbered. */ + +static inline void tcg_out_tlb_load(TCGContext *s, int addrlo_idx, + int mem_index, int s_bits, + const TCGArg *args, + uint8_t **label_ptr, int which) { - int addr_reg, data_reg, data_reg2, r0, r1, mem_index, s_bits, bswap; -#if defined(CONFIG_SOFTMMU) - uint8_t *label1_ptr, *label2_ptr; -#endif -#if TARGET_LONG_BITS == 64 -#if defined(CONFIG_SOFTMMU) - uint8_t *label3_ptr; -#endif - int addr_reg2; -#endif + const int addrlo = args[addrlo_idx]; + const int r0 = tcg_target_call_iarg_regs[0]; + const int r1 = tcg_target_call_iarg_regs[1]; + TCGType type = TCG_TYPE_I32; + int rexw = 0; + + if (TCG_TARGET_REG_BITS == 64 && TARGET_LONG_BITS == 64) { + type = TCG_TYPE_I64; + rexw = P_REXW; + } - data_reg = *args++; - if (opc == 3) - data_reg2 = *args++; - else - data_reg2 = 0; - addr_reg = *args++; -#if TARGET_LONG_BITS == 64 - addr_reg2 = *args++; -#endif - mem_index = *args; - s_bits = opc & 3; + tcg_out_mov(s, type, r1, addrlo); + tcg_out_mov(s, type, r0, addrlo); - r0 = TCG_REG_EAX; - r1 = TCG_REG_EDX; + tcg_out_shifti(s, SHIFT_SHR + rexw, r1, + TARGET_PAGE_BITS - CPU_TLB_ENTRY_BITS); -#if defined(CONFIG_SOFTMMU) - tcg_out_mov(s, r1, addr_reg); - - tcg_out_mov(s, r0, addr_reg); - - tcg_out_modrm(s, 0xc1, 5, r1); /* shr $x, r1 */ - tcg_out8(s, TARGET_PAGE_BITS - CPU_TLB_ENTRY_BITS); - - tcg_out_modrm(s, 0x81, 4, r0); /* andl $x, r0 */ - tcg_out32(s, TARGET_PAGE_MASK | ((1 << s_bits) - 1)); - - tcg_out_modrm(s, 0x81, 4, r1); /* andl $x, r1 */ - tcg_out32(s, (CPU_TLB_SIZE - 1) << CPU_TLB_ENTRY_BITS); - - tcg_out_opc(s, 0x8d); /* lea offset(r1, %ebp), r1 */ - tcg_out8(s, 0x80 | (r1 << 3) | 0x04); - tcg_out8(s, (5 << 3) | r1); - tcg_out32(s, offsetof(CPUState, tlb_table[mem_index][0].addr_read)); + tgen_arithi(s, ARITH_AND + rexw, r0, + TARGET_PAGE_MASK | ((1 << s_bits) - 1), 0); + tgen_arithi(s, ARITH_AND + rexw, r1, + (CPU_TLB_SIZE - 1) << CPU_TLB_ENTRY_BITS, 0); + + tcg_out_modrm_sib_offset(s, OPC_LEA + P_REXW, r1, TCG_AREG0, r1, 0, + offsetof(CPUState, tlb_table[mem_index][0]) + + which); /* cmp 0(r1), r0 */ - tcg_out_modrm_offset(s, 0x3b, r0, r1, 0); - - tcg_out_mov(s, r0, addr_reg); - -#if TARGET_LONG_BITS == 32 - /* je label1 */ - tcg_out8(s, 0x70 + JCC_JE); - label1_ptr = s->code_ptr; - s->code_ptr++; -#else - /* jne label3 */ - tcg_out8(s, 0x70 + JCC_JNE); - label3_ptr = s->code_ptr; - s->code_ptr++; - - /* cmp 4(r1), addr_reg2 */ - tcg_out_modrm_offset(s, 0x3b, addr_reg2, r1, 4); + tcg_out_modrm_offset(s, OPC_CMP_GvEv + rexw, r0, r1, 0); + + tcg_out_mov(s, type, r0, addrlo); - /* je label1 */ - tcg_out8(s, 0x70 + JCC_JE); - label1_ptr = s->code_ptr; + /* jne label1 */ + tcg_out8(s, OPC_JCC_short + JCC_JNE); + label_ptr[0] = s->code_ptr; s->code_ptr++; - - /* label3: */ - *label3_ptr = s->code_ptr - label3_ptr - 1; -#endif - /* XXX: move that code at the end of the TB */ -#if TARGET_LONG_BITS == 32 - tcg_out_movi(s, TCG_TYPE_I32, TCG_REG_EDX, mem_index); -#else - tcg_out_mov(s, TCG_REG_EDX, addr_reg2); - tcg_out_movi(s, TCG_TYPE_I32, TCG_REG_ECX, mem_index); -#endif - tcg_out8(s, 0xe8); - tcg_out32(s, (tcg_target_long)qemu_ld_helpers[s_bits] - - (tcg_target_long)s->code_ptr - 4); + if (TARGET_LONG_BITS > TCG_TARGET_REG_BITS) { + /* cmp 4(r1), addrhi */ + tcg_out_modrm_offset(s, OPC_CMP_GvEv, args[addrlo_idx+1], r1, 4); - switch(opc) { - case 0 | 4: - /* movsbl */ - tcg_out_modrm(s, 0xbe | P_EXT, data_reg, TCG_REG_EAX); - break; - case 1 | 4: - /* movswl */ - tcg_out_modrm(s, 0xbf | P_EXT, data_reg, TCG_REG_EAX); - break; - case 0: - /* movzbl */ - tcg_out_modrm(s, 0xb6 | P_EXT, data_reg, TCG_REG_EAX); - break; - case 1: - /* movzwl */ - tcg_out_modrm(s, 0xb7 | P_EXT, data_reg, TCG_REG_EAX); - break; - case 2: - default: - tcg_out_mov(s, data_reg, TCG_REG_EAX); - break; - case 3: - if (data_reg == TCG_REG_EDX) { - tcg_out_opc(s, 0x90 + TCG_REG_EDX); /* xchg %edx, %eax */ - tcg_out_mov(s, data_reg2, TCG_REG_EAX); - } else { - tcg_out_mov(s, data_reg, TCG_REG_EAX); - tcg_out_mov(s, data_reg2, TCG_REG_EDX); - } - break; + /* jne label1 */ + tcg_out8(s, OPC_JCC_short + JCC_JNE); + label_ptr[1] = s->code_ptr; + s->code_ptr++; } - /* jmp label2 */ - tcg_out8(s, 0xeb); - label2_ptr = s->code_ptr; - s->code_ptr++; - - /* label1: */ - *label1_ptr = s->code_ptr - label1_ptr - 1; + /* TLB Hit. */ - /* add x(r1), r0 */ - tcg_out_modrm_offset(s, 0x03, r0, r1, offsetof(CPUTLBEntry, addend) - - offsetof(CPUTLBEntry, addr_read)); -#else - r0 = addr_reg; + /* add addend(r1), r0 */ + tcg_out_modrm_offset(s, OPC_ADD_GvEv + P_REXW, r0, r1, + offsetof(CPUTLBEntry, addend) - which); +} #endif +static void tcg_out_qemu_ld_direct(TCGContext *s, int datalo, int datahi, + int base, tcg_target_long ofs, int sizeop) +{ #ifdef TARGET_WORDS_BIGENDIAN - bswap = 1; + const int bswap = 1; #else - bswap = 0; + const int bswap = 0; #endif - switch(opc) { + switch (sizeop) { case 0: - /* movzbl */ - tcg_out_modrm_offset(s, 0xb6 | P_EXT, data_reg, r0, GUEST_BASE); + tcg_out_modrm_offset(s, OPC_MOVZBL, datalo, base, ofs); break; case 0 | 4: - /* movsbl */ - tcg_out_modrm_offset(s, 0xbe | P_EXT, data_reg, r0, GUEST_BASE); + tcg_out_modrm_offset(s, OPC_MOVSBL + P_REXW, datalo, base, ofs); break; case 1: - /* movzwl */ - tcg_out_modrm_offset(s, 0xb7 | P_EXT, data_reg, r0, GUEST_BASE); + tcg_out_modrm_offset(s, OPC_MOVZWL, datalo, base, ofs); if (bswap) { - /* rolw $8, data_reg */ - tcg_out8(s, 0x66); - tcg_out_modrm(s, 0xc1, 0, data_reg); - tcg_out8(s, 8); + tcg_out_rolw_8(s, datalo); } break; case 1 | 4: - /* movswl */ - tcg_out_modrm_offset(s, 0xbf | P_EXT, data_reg, r0, GUEST_BASE); if (bswap) { - /* rolw $8, data_reg */ - tcg_out8(s, 0x66); - tcg_out_modrm(s, 0xc1, 0, data_reg); - tcg_out8(s, 8); - - /* movswl data_reg, data_reg */ - tcg_out_modrm(s, 0xbf | P_EXT, data_reg, data_reg); + tcg_out_modrm_offset(s, OPC_MOVZWL, datalo, base, ofs); + tcg_out_rolw_8(s, datalo); + tcg_out_modrm(s, OPC_MOVSWL + P_REXW, datalo, datalo); + } else { + tcg_out_modrm_offset(s, OPC_MOVSWL + P_REXW, datalo, base, ofs); } break; case 2: - /* movl (r0), data_reg */ - tcg_out_modrm_offset(s, 0x8b, data_reg, r0, GUEST_BASE); + tcg_out_ld(s, TCG_TYPE_I32, datalo, base, ofs); if (bswap) { - /* bswap */ - tcg_out_opc(s, (0xc8 + data_reg) | P_EXT); + tcg_out_bswap32(s, datalo); } break; - case 3: - /* XXX: could be nicer */ - if (r0 == data_reg) { - r1 = TCG_REG_EDX; - if (r1 == data_reg) - r1 = TCG_REG_EAX; - tcg_out_mov(s, r1, r0); - r0 = r1; +#if TCG_TARGET_REG_BITS == 64 + case 2 | 4: + if (bswap) { + tcg_out_ld(s, TCG_TYPE_I32, datalo, base, ofs); + tcg_out_bswap32(s, datalo); + tcg_out_ext32s(s, datalo, datalo); + } else { + tcg_out_modrm_offset(s, OPC_MOVSLQ, datalo, base, ofs); } - if (!bswap) { - tcg_out_modrm_offset(s, 0x8b, data_reg, r0, GUEST_BASE); - tcg_out_modrm_offset(s, 0x8b, data_reg2, r0, GUEST_BASE + 4); + break; +#endif + case 3: + if (TCG_TARGET_REG_BITS == 64) { + tcg_out_ld(s, TCG_TYPE_I64, datalo, base, ofs); + if (bswap) { + tcg_out_bswap64(s, datalo); + } } else { - tcg_out_modrm_offset(s, 0x8b, data_reg, r0, GUEST_BASE + 4); - tcg_out_opc(s, (0xc8 + data_reg) | P_EXT); - - tcg_out_modrm_offset(s, 0x8b, data_reg2, r0, GUEST_BASE); - /* bswap */ - tcg_out_opc(s, (0xc8 + data_reg2) | P_EXT); + if (bswap) { + int t = datalo; + datalo = datahi; + datahi = t; + } + if (base != datalo) { + tcg_out_ld(s, TCG_TYPE_I32, datalo, base, ofs); + tcg_out_ld(s, TCG_TYPE_I32, datahi, base, ofs + 4); + } else { + tcg_out_ld(s, TCG_TYPE_I32, datahi, base, ofs + 4); + tcg_out_ld(s, TCG_TYPE_I32, datalo, base, ofs); + } + if (bswap) { + tcg_out_bswap32(s, datalo); + tcg_out_bswap32(s, datahi); + } } break; default: tcg_abort(); } - -#if defined(CONFIG_SOFTMMU) - /* label2: */ - *label2_ptr = s->code_ptr - label2_ptr - 1; -#endif } - -static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, +/* XXX: qemu_ld and qemu_st could be modified to clobber only EDX and + EAX. It will be useful once fixed registers globals are less + common. */ +static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, int opc) { - int addr_reg, data_reg, data_reg2, r0, r1, mem_index, s_bits, bswap; + int data_reg, data_reg2 = 0; + int addrlo_idx; #if defined(CONFIG_SOFTMMU) - uint8_t *label1_ptr, *label2_ptr; -#endif -#if TARGET_LONG_BITS == 64 -#if defined(CONFIG_SOFTMMU) - uint8_t *label3_ptr; -#endif - int addr_reg2; + int mem_index, s_bits, arg_idx; + uint8_t *label_ptr[3]; #endif - data_reg = *args++; - if (opc == 3) - data_reg2 = *args++; - else - data_reg2 = 0; - addr_reg = *args++; -#if TARGET_LONG_BITS == 64 - addr_reg2 = *args++; -#endif - mem_index = *args; + data_reg = args[0]; + addrlo_idx = 1; + if (TCG_TARGET_REG_BITS == 32 && opc == 3) { + data_reg2 = args[1]; + addrlo_idx = 2; + } - s_bits = opc; +#if defined(CONFIG_SOFTMMU) + mem_index = args[addrlo_idx + 1 + (TARGET_LONG_BITS > TCG_TARGET_REG_BITS)]; + s_bits = opc & 3; - r0 = TCG_REG_EAX; - r1 = TCG_REG_EDX; + tcg_out_tlb_load(s, addrlo_idx, mem_index, s_bits, args, + label_ptr, offsetof(CPUTLBEntry, addr_read)); -#if defined(CONFIG_SOFTMMU) - tcg_out_mov(s, r1, addr_reg); - - tcg_out_mov(s, r0, addr_reg); - - tcg_out_modrm(s, 0xc1, 5, r1); /* shr $x, r1 */ - tcg_out8(s, TARGET_PAGE_BITS - CPU_TLB_ENTRY_BITS); - - tcg_out_modrm(s, 0x81, 4, r0); /* andl $x, r0 */ - tcg_out32(s, TARGET_PAGE_MASK | ((1 << s_bits) - 1)); - - tcg_out_modrm(s, 0x81, 4, r1); /* andl $x, r1 */ - tcg_out32(s, (CPU_TLB_SIZE - 1) << CPU_TLB_ENTRY_BITS); - - tcg_out_opc(s, 0x8d); /* lea offset(r1, %ebp), r1 */ - tcg_out8(s, 0x80 | (r1 << 3) | 0x04); - tcg_out8(s, (5 << 3) | r1); - tcg_out32(s, offsetof(CPUState, tlb_table[mem_index][0].addr_write)); + /* TLB Hit. */ + tcg_out_qemu_ld_direct(s, data_reg, data_reg2, + tcg_target_call_iarg_regs[0], 0, opc); - /* cmp 0(r1), r0 */ - tcg_out_modrm_offset(s, 0x3b, r0, r1, 0); - - tcg_out_mov(s, r0, addr_reg); - -#if TARGET_LONG_BITS == 32 - /* je label1 */ - tcg_out8(s, 0x70 + JCC_JE); - label1_ptr = s->code_ptr; - s->code_ptr++; -#else - /* jne label3 */ - tcg_out8(s, 0x70 + JCC_JNE); - label3_ptr = s->code_ptr; + /* jmp label2 */ + tcg_out8(s, OPC_JMP_short); + label_ptr[2] = s->code_ptr; s->code_ptr++; - - /* cmp 4(r1), addr_reg2 */ - tcg_out_modrm_offset(s, 0x3b, addr_reg2, r1, 4); - /* je label1 */ - tcg_out8(s, 0x70 + JCC_JE); - label1_ptr = s->code_ptr; - s->code_ptr++; - - /* label3: */ - *label3_ptr = s->code_ptr - label3_ptr - 1; -#endif + /* TLB Miss. */ + + /* label1: */ + *label_ptr[0] = s->code_ptr - label_ptr[0] - 1; + if (TARGET_LONG_BITS > TCG_TARGET_REG_BITS) { + *label_ptr[1] = s->code_ptr - label_ptr[1] - 1; + } /* XXX: move that code at the end of the TB */ -#if TARGET_LONG_BITS == 32 - if (opc == 3) { - tcg_out_mov(s, TCG_REG_EDX, data_reg); - tcg_out_mov(s, TCG_REG_ECX, data_reg2); - tcg_out8(s, 0x6a); /* push Ib */ - tcg_out8(s, mem_index); - tcg_out8(s, 0xe8); - tcg_out32(s, (tcg_target_long)qemu_st_helpers[s_bits] - - (tcg_target_long)s->code_ptr - 4); - tcg_out_addi(s, TCG_REG_ESP, 4); - } else { - switch(opc) { - case 0: - /* movzbl */ - tcg_out_modrm(s, 0xb6 | P_EXT, TCG_REG_EDX, data_reg); - break; - case 1: - /* movzwl */ - tcg_out_modrm(s, 0xb7 | P_EXT, TCG_REG_EDX, data_reg); - break; - case 2: - tcg_out_mov(s, TCG_REG_EDX, data_reg); - break; - } - tcg_out_movi(s, TCG_TYPE_I32, TCG_REG_ECX, mem_index); - tcg_out8(s, 0xe8); - tcg_out32(s, (tcg_target_long)qemu_st_helpers[s_bits] - - (tcg_target_long)s->code_ptr - 4); + /* The first argument is already loaded with addrlo. */ + arg_idx = 1; + if (TCG_TARGET_REG_BITS == 32 && TARGET_LONG_BITS == 64) { + tcg_out_mov(s, TCG_TYPE_I32, tcg_target_call_iarg_regs[arg_idx++], + args[addrlo_idx + 1]); } -#else - if (opc == 3) { - tcg_out_mov(s, TCG_REG_EDX, addr_reg2); - tcg_out8(s, 0x6a); /* push Ib */ - tcg_out8(s, mem_index); - tcg_out_opc(s, 0x50 + data_reg2); /* push */ - tcg_out_opc(s, 0x50 + data_reg); /* push */ - tcg_out8(s, 0xe8); - tcg_out32(s, (tcg_target_long)qemu_st_helpers[s_bits] - - (tcg_target_long)s->code_ptr - 4); - tcg_out_addi(s, TCG_REG_ESP, 12); - } else { - tcg_out_mov(s, TCG_REG_EDX, addr_reg2); - switch(opc) { - case 0: - /* movzbl */ - tcg_out_modrm(s, 0xb6 | P_EXT, TCG_REG_ECX, data_reg); - break; - case 1: - /* movzwl */ - tcg_out_modrm(s, 0xb7 | P_EXT, TCG_REG_ECX, data_reg); - break; - case 2: - tcg_out_mov(s, TCG_REG_ECX, data_reg); - break; + tcg_out_movi(s, TCG_TYPE_I32, tcg_target_call_iarg_regs[arg_idx], + mem_index); + tcg_out_calli(s, (tcg_target_long)qemu_ld_helpers[s_bits]); + + switch(opc) { + case 0 | 4: + tcg_out_ext8s(s, data_reg, TCG_REG_EAX, P_REXW); + break; + case 1 | 4: + tcg_out_ext16s(s, data_reg, TCG_REG_EAX, P_REXW); + break; + case 0: + tcg_out_ext8u(s, data_reg, TCG_REG_EAX); + break; + case 1: + tcg_out_ext16u(s, data_reg, TCG_REG_EAX); + break; + case 2: + tcg_out_mov(s, TCG_TYPE_I32, data_reg, TCG_REG_EAX); + break; +#if TCG_TARGET_REG_BITS == 64 + case 2 | 4: + tcg_out_ext32s(s, data_reg, TCG_REG_EAX); + break; +#endif + case 3: + if (TCG_TARGET_REG_BITS == 64) { + tcg_out_mov(s, TCG_TYPE_I64, data_reg, TCG_REG_RAX); + } else if (data_reg == TCG_REG_EDX) { + /* xchg %edx, %eax */ + tcg_out_opc(s, OPC_XCHG_ax_r32 + TCG_REG_EDX, 0, 0, 0); + tcg_out_mov(s, TCG_TYPE_I32, data_reg2, TCG_REG_EAX); + } else { + tcg_out_mov(s, TCG_TYPE_I32, data_reg, TCG_REG_EAX); + tcg_out_mov(s, TCG_TYPE_I32, data_reg2, TCG_REG_EDX); } - tcg_out8(s, 0x6a); /* push Ib */ - tcg_out8(s, mem_index); - tcg_out8(s, 0xe8); - tcg_out32(s, (tcg_target_long)qemu_st_helpers[s_bits] - - (tcg_target_long)s->code_ptr - 4); - tcg_out_addi(s, TCG_REG_ESP, 4); + break; + default: + tcg_abort(); } -#endif - - /* jmp label2 */ - tcg_out8(s, 0xeb); - label2_ptr = s->code_ptr; - s->code_ptr++; - - /* label1: */ - *label1_ptr = s->code_ptr - label1_ptr - 1; - /* add x(r1), r0 */ - tcg_out_modrm_offset(s, 0x03, r0, r1, offsetof(CPUTLBEntry, addend) - - offsetof(CPUTLBEntry, addr_write)); + /* label2: */ + *label_ptr[2] = s->code_ptr - label_ptr[2] - 1; #else - r0 = addr_reg; + { + int32_t offset = GUEST_BASE; + int base = args[addrlo_idx]; + + if (TCG_TARGET_REG_BITS == 64) { + /* ??? We assume all operations have left us with register + contents that are zero extended. So far this appears to + be true. If we want to enforce this, we can either do + an explicit zero-extension here, or (if GUEST_BASE == 0) + use the ADDR32 prefix. For now, do nothing. */ + + if (offset != GUEST_BASE) { + tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_RDI, GUEST_BASE); + tgen_arithr(s, ARITH_ADD + P_REXW, TCG_REG_RDI, base); + base = TCG_REG_RDI, offset = 0; + } + } + + tcg_out_qemu_ld_direct(s, data_reg, data_reg2, base, offset, opc); + } #endif +} +static void tcg_out_qemu_st_direct(TCGContext *s, int datalo, int datahi, + int base, tcg_target_long ofs, int sizeop) +{ #ifdef TARGET_WORDS_BIGENDIAN - bswap = 1; + const int bswap = 1; #else - bswap = 0; + const int bswap = 0; #endif - switch(opc) { + /* ??? Ideally we wouldn't need a scratch register. For user-only, + we could perform the bswap twice to restore the original value + instead of moving to the scratch. But as it is, the L constraint + means that the second argument reg is definitely free here. */ + int scratch = tcg_target_call_iarg_regs[1]; + + switch (sizeop) { case 0: - /* movb */ - tcg_out_modrm_offset(s, 0x88, data_reg, r0, GUEST_BASE); + tcg_out_modrm_offset(s, OPC_MOVB_EvGv + P_REXB_R, datalo, base, ofs); break; case 1: if (bswap) { - tcg_out_mov(s, r1, data_reg); - tcg_out8(s, 0x66); /* rolw $8, %ecx */ - tcg_out_modrm(s, 0xc1, 0, r1); - tcg_out8(s, 8); - data_reg = r1; + tcg_out_mov(s, TCG_TYPE_I32, scratch, datalo); + tcg_out_rolw_8(s, scratch); + datalo = scratch; } - /* movw */ - tcg_out8(s, 0x66); - tcg_out_modrm_offset(s, 0x89, data_reg, r0, GUEST_BASE); + tcg_out_modrm_offset(s, OPC_MOVL_EvGv + P_DATA16, datalo, base, ofs); break; case 2: if (bswap) { - tcg_out_mov(s, r1, data_reg); - /* bswap data_reg */ - tcg_out_opc(s, (0xc8 + r1) | P_EXT); - data_reg = r1; + tcg_out_mov(s, TCG_TYPE_I32, scratch, datalo); + tcg_out_bswap32(s, scratch); + datalo = scratch; } - /* movl */ - tcg_out_modrm_offset(s, 0x89, data_reg, r0, GUEST_BASE); + tcg_out_st(s, TCG_TYPE_I32, datalo, base, ofs); break; case 3: - if (bswap) { - tcg_out_mov(s, r1, data_reg2); - /* bswap data_reg */ - tcg_out_opc(s, (0xc8 + r1) | P_EXT); - tcg_out_modrm_offset(s, 0x89, r1, r0, GUEST_BASE); - tcg_out_mov(s, r1, data_reg); - /* bswap data_reg */ - tcg_out_opc(s, (0xc8 + r1) | P_EXT); - tcg_out_modrm_offset(s, 0x89, r1, r0, GUEST_BASE + 4); + if (TCG_TARGET_REG_BITS == 64) { + if (bswap) { + tcg_out_mov(s, TCG_TYPE_I64, scratch, datalo); + tcg_out_bswap64(s, scratch); + datalo = scratch; + } + tcg_out_st(s, TCG_TYPE_I64, datalo, base, ofs); + } else if (bswap) { + tcg_out_mov(s, TCG_TYPE_I32, scratch, datahi); + tcg_out_bswap32(s, scratch); + tcg_out_st(s, TCG_TYPE_I32, scratch, base, ofs); + tcg_out_mov(s, TCG_TYPE_I32, scratch, datalo); + tcg_out_bswap32(s, scratch); + tcg_out_st(s, TCG_TYPE_I32, scratch, base, ofs + 4); } else { - tcg_out_modrm_offset(s, 0x89, data_reg, r0, GUEST_BASE); - tcg_out_modrm_offset(s, 0x89, data_reg2, r0, GUEST_BASE + 4); + tcg_out_st(s, TCG_TYPE_I32, datalo, base, ofs); + tcg_out_st(s, TCG_TYPE_I32, datahi, base, ofs + 4); } break; default: tcg_abort(); } +} +static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, + int opc) +{ + int data_reg, data_reg2 = 0; + int addrlo_idx; #if defined(CONFIG_SOFTMMU) + int mem_index, s_bits; + int stack_adjust; + uint8_t *label_ptr[3]; +#endif + + data_reg = args[0]; + addrlo_idx = 1; + if (TCG_TARGET_REG_BITS == 32 && opc == 3) { + data_reg2 = args[1]; + addrlo_idx = 2; + } + +#if defined(CONFIG_SOFTMMU) + mem_index = args[addrlo_idx + 1 + (TARGET_LONG_BITS > TCG_TARGET_REG_BITS)]; + s_bits = opc; + + tcg_out_tlb_load(s, addrlo_idx, mem_index, s_bits, args, + label_ptr, offsetof(CPUTLBEntry, addr_write)); + + /* TLB Hit. */ + tcg_out_qemu_st_direct(s, data_reg, data_reg2, + tcg_target_call_iarg_regs[0], 0, opc); + + /* jmp label2 */ + tcg_out8(s, OPC_JMP_short); + label_ptr[2] = s->code_ptr; + s->code_ptr++; + + /* TLB Miss. */ + + /* label1: */ + *label_ptr[0] = s->code_ptr - label_ptr[0] - 1; + if (TARGET_LONG_BITS > TCG_TARGET_REG_BITS) { + *label_ptr[1] = s->code_ptr - label_ptr[1] - 1; + } + + /* XXX: move that code at the end of the TB */ + if (TCG_TARGET_REG_BITS == 64) { + tcg_out_mov(s, (opc == 3 ? TCG_TYPE_I64 : TCG_TYPE_I32), + TCG_REG_RSI, data_reg); + tcg_out_movi(s, TCG_TYPE_I32, TCG_REG_RDX, mem_index); + stack_adjust = 0; + } else if (TARGET_LONG_BITS == 32) { + tcg_out_mov(s, TCG_TYPE_I32, TCG_REG_EDX, data_reg); + if (opc == 3) { + tcg_out_mov(s, TCG_TYPE_I32, TCG_REG_ECX, data_reg2); + tcg_out_pushi(s, mem_index); + stack_adjust = 4; + } else { + tcg_out_movi(s, TCG_TYPE_I32, TCG_REG_ECX, mem_index); + stack_adjust = 0; + } + } else { + if (opc == 3) { + tcg_out_mov(s, TCG_TYPE_I32, TCG_REG_EDX, args[addrlo_idx + 1]); + tcg_out_pushi(s, mem_index); + tcg_out_push(s, data_reg2); + tcg_out_push(s, data_reg); + stack_adjust = 12; + } else { + tcg_out_mov(s, TCG_TYPE_I32, TCG_REG_EDX, args[addrlo_idx + 1]); + switch(opc) { + case 0: + tcg_out_ext8u(s, TCG_REG_ECX, data_reg); + break; + case 1: + tcg_out_ext16u(s, TCG_REG_ECX, data_reg); + break; + case 2: + tcg_out_mov(s, TCG_TYPE_I32, TCG_REG_ECX, data_reg); + break; + } + tcg_out_pushi(s, mem_index); + stack_adjust = 4; + } + } + + tcg_out_calli(s, (tcg_target_long)qemu_st_helpers[s_bits]); + + if (stack_adjust == (TCG_TARGET_REG_BITS / 8)) { + /* Pop and discard. This is 2 bytes smaller than the add. */ + tcg_out_pop(s, TCG_REG_ECX); + } else if (stack_adjust != 0) { + tcg_out_addi(s, TCG_REG_ESP, stack_adjust); + } + /* label2: */ - *label2_ptr = s->code_ptr - label2_ptr - 1; + *label_ptr[2] = s->code_ptr - label_ptr[2] - 1; +#else + { + int32_t offset = GUEST_BASE; + int base = args[addrlo_idx]; + + if (TCG_TARGET_REG_BITS == 64) { + /* ??? We assume all operations have left us with register + contents that are zero extended. So far this appears to + be true. If we want to enforce this, we can either do + an explicit zero-extension here, or (if GUEST_BASE == 0) + use the ADDR32 prefix. For now, do nothing. */ + + if (offset != GUEST_BASE) { + tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_RDI, GUEST_BASE); + tgen_arithr(s, ARITH_ADD + P_REXW, TCG_REG_RDI, base); + base = TCG_REG_RDI, offset = 0; + } + } + + tcg_out_qemu_st_direct(s, data_reg, data_reg2, base, offset, opc); + } #endif } -static inline void tcg_out_op(TCGContext *s, int opc, +static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, const TCGArg *args, const int *const_args) { - int c; - + int c, rexw = 0; + +#if TCG_TARGET_REG_BITS == 64 +# define OP_32_64(x) \ + case glue(glue(INDEX_op_, x), _i64): \ + rexw = P_REXW; /* FALLTHRU */ \ + case glue(glue(INDEX_op_, x), _i32) +#else +# define OP_32_64(x) \ + case glue(glue(INDEX_op_, x), _i32) +#endif + switch(opc) { case INDEX_op_exit_tb: - tcg_out_movi(s, TCG_TYPE_I32, TCG_REG_EAX, args[0]); - tcg_out8(s, 0xe9); /* jmp tb_ret_addr */ - tcg_out32(s, tb_ret_addr - s->code_ptr - 4); + tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_EAX, args[0]); + tcg_out_jmp(s, (tcg_target_long) tb_ret_addr); break; case INDEX_op_goto_tb: if (s->tb_jmp_offset) { /* direct jump method */ - tcg_out8(s, 0xe9); /* jmp im */ + tcg_out8(s, OPC_JMP_long); /* jmp im */ s->tb_jmp_offset[args[0]] = s->code_ptr - s->code_buf; tcg_out32(s, 0); } else { /* indirect jump method */ - /* jmp Ev */ - tcg_out_modrm_offset(s, 0xff, 4, -1, + tcg_out_modrm_offset(s, OPC_GRP5, EXT5_JMPN_Ev, -1, (tcg_target_long)(s->tb_next + args[0])); } s->tb_next_offset[args[0]] = s->code_ptr - s->code_buf; break; case INDEX_op_call: if (const_args[0]) { - tcg_out8(s, 0xe8); - tcg_out32(s, args[0] - (tcg_target_long)s->code_ptr - 4); + tcg_out_calli(s, args[0]); } else { - tcg_out_modrm(s, 0xff, 2, args[0]); + /* call *reg */ + tcg_out_modrm(s, OPC_GRP5, EXT5_CALLN_Ev, args[0]); } break; case INDEX_op_jmp: if (const_args[0]) { - tcg_out8(s, 0xe9); - tcg_out32(s, args[0] - (tcg_target_long)s->code_ptr - 4); + tcg_out_jmp(s, args[0]); } else { - tcg_out_modrm(s, 0xff, 4, args[0]); + /* jmp *reg */ + tcg_out_modrm(s, OPC_GRP5, EXT5_JMPN_Ev, args[0]); } break; case INDEX_op_br: - tcg_out_jxx(s, JCC_JMP, args[0]); + tcg_out_jxx(s, JCC_JMP, args[0], 0); break; case INDEX_op_movi_i32: tcg_out_movi(s, TCG_TYPE_I32, args[0], args[1]); break; - case INDEX_op_ld8u_i32: - /* movzbl */ - tcg_out_modrm_offset(s, 0xb6 | P_EXT, args[0], args[1], args[2]); + OP_32_64(ld8u): + /* Note that we can ignore REXW for the zero-extend to 64-bit. */ + tcg_out_modrm_offset(s, OPC_MOVZBL, args[0], args[1], args[2]); break; - case INDEX_op_ld8s_i32: - /* movsbl */ - tcg_out_modrm_offset(s, 0xbe | P_EXT, args[0], args[1], args[2]); + OP_32_64(ld8s): + tcg_out_modrm_offset(s, OPC_MOVSBL + rexw, args[0], args[1], args[2]); break; - case INDEX_op_ld16u_i32: - /* movzwl */ - tcg_out_modrm_offset(s, 0xb7 | P_EXT, args[0], args[1], args[2]); + OP_32_64(ld16u): + /* Note that we can ignore REXW for the zero-extend to 64-bit. */ + tcg_out_modrm_offset(s, OPC_MOVZWL, args[0], args[1], args[2]); break; - case INDEX_op_ld16s_i32: - /* movswl */ - tcg_out_modrm_offset(s, 0xbf | P_EXT, args[0], args[1], args[2]); + OP_32_64(ld16s): + tcg_out_modrm_offset(s, OPC_MOVSWL + rexw, args[0], args[1], args[2]); break; +#if TCG_TARGET_REG_BITS == 64 + case INDEX_op_ld32u_i64: +#endif case INDEX_op_ld_i32: - /* movl */ - tcg_out_modrm_offset(s, 0x8b, args[0], args[1], args[2]); + tcg_out_ld(s, TCG_TYPE_I32, args[0], args[1], args[2]); break; - case INDEX_op_st8_i32: - /* movb */ - tcg_out_modrm_offset(s, 0x88, args[0], args[1], args[2]); + + OP_32_64(st8): + tcg_out_modrm_offset(s, OPC_MOVB_EvGv | P_REXB_R, + args[0], args[1], args[2]); break; - case INDEX_op_st16_i32: - /* movw */ - tcg_out8(s, 0x66); - tcg_out_modrm_offset(s, 0x89, args[0], args[1], args[2]); + OP_32_64(st16): + tcg_out_modrm_offset(s, OPC_MOVL_EvGv | P_DATA16, + args[0], args[1], args[2]); break; +#if TCG_TARGET_REG_BITS == 64 + case INDEX_op_st32_i64: +#endif case INDEX_op_st_i32: - /* movl */ - tcg_out_modrm_offset(s, 0x89, args[0], args[1], args[2]); + tcg_out_st(s, TCG_TYPE_I32, args[0], args[1], args[2]); break; - case INDEX_op_sub_i32: + + OP_32_64(add): + /* For 3-operand addition, use LEA. */ + if (args[0] != args[1]) { + TCGArg a0 = args[0], a1 = args[1], a2 = args[2], c3 = 0; + + if (const_args[2]) { + c3 = a2, a2 = -1; + } else if (a0 == a2) { + /* Watch out for dest = src + dest, since we've removed + the matching constraint on the add. */ + tgen_arithr(s, ARITH_ADD + rexw, a0, a1); + break; + } + + tcg_out_modrm_sib_offset(s, OPC_LEA + rexw, a0, a1, a2, 0, c3); + break; + } + c = ARITH_ADD; + goto gen_arith; + OP_32_64(sub): c = ARITH_SUB; goto gen_arith; - case INDEX_op_and_i32: + OP_32_64(and): c = ARITH_AND; goto gen_arith; - case INDEX_op_or_i32: + OP_32_64(or): c = ARITH_OR; goto gen_arith; - case INDEX_op_xor_i32: + OP_32_64(xor): c = ARITH_XOR; goto gen_arith; - case INDEX_op_add_i32: - c = ARITH_ADD; gen_arith: if (const_args[2]) { - tgen_arithi(s, c, args[0], args[2], 0); + tgen_arithi(s, c + rexw, args[0], args[2], 0); } else { - tcg_out_modrm(s, 0x01 | (c << 3), args[2], args[0]); + tgen_arithr(s, c + rexw, args[0], args[2]); } break; - case INDEX_op_mul_i32: + + OP_32_64(mul): if (const_args[2]) { int32_t val; val = args[2]; if (val == (int8_t)val) { - tcg_out_modrm(s, 0x6b, args[0], args[0]); + tcg_out_modrm(s, OPC_IMUL_GvEvIb + rexw, args[0], args[0]); tcg_out8(s, val); } else { - tcg_out_modrm(s, 0x69, args[0], args[0]); + tcg_out_modrm(s, OPC_IMUL_GvEvIz + rexw, args[0], args[0]); tcg_out32(s, val); } } else { - tcg_out_modrm(s, 0xaf | P_EXT, args[0], args[2]); + tcg_out_modrm(s, OPC_IMUL_GvEv + rexw, args[0], args[2]); } break; - case INDEX_op_mulu2_i32: - tcg_out_modrm(s, 0xf7, 4, args[3]); - break; - case INDEX_op_div2_i32: - tcg_out_modrm(s, 0xf7, 7, args[4]); + + OP_32_64(div2): + tcg_out_modrm(s, OPC_GRP3_Ev + rexw, EXT3_IDIV, args[4]); break; - case INDEX_op_divu2_i32: - tcg_out_modrm(s, 0xf7, 6, args[4]); + OP_32_64(divu2): + tcg_out_modrm(s, OPC_GRP3_Ev + rexw, EXT3_DIV, args[4]); break; - case INDEX_op_shl_i32: + + OP_32_64(shl): c = SHIFT_SHL; - gen_shift32: - if (const_args[2]) { - if (args[2] == 1) { - tcg_out_modrm(s, 0xd1, c, args[0]); - } else { - tcg_out_modrm(s, 0xc1, c, args[0]); - tcg_out8(s, args[2]); - } - } else { - tcg_out_modrm(s, 0xd3, c, args[0]); - } - break; - case INDEX_op_shr_i32: + goto gen_shift; + OP_32_64(shr): c = SHIFT_SHR; - goto gen_shift32; - case INDEX_op_sar_i32: + goto gen_shift; + OP_32_64(sar): c = SHIFT_SAR; - goto gen_shift32; - case INDEX_op_rotl_i32: + goto gen_shift; + OP_32_64(rotl): c = SHIFT_ROL; - goto gen_shift32; - case INDEX_op_rotr_i32: + goto gen_shift; + OP_32_64(rotr): c = SHIFT_ROR; - goto gen_shift32; - - case INDEX_op_add2_i32: - if (const_args[4]) - tgen_arithi(s, ARITH_ADD, args[0], args[4], 1); - else - tcg_out_modrm(s, 0x01 | (ARITH_ADD << 3), args[4], args[0]); - if (const_args[5]) - tgen_arithi(s, ARITH_ADC, args[1], args[5], 1); - else - tcg_out_modrm(s, 0x01 | (ARITH_ADC << 3), args[5], args[1]); - break; - case INDEX_op_sub2_i32: - if (const_args[4]) - tgen_arithi(s, ARITH_SUB, args[0], args[4], 1); - else - tcg_out_modrm(s, 0x01 | (ARITH_SUB << 3), args[4], args[0]); - if (const_args[5]) - tgen_arithi(s, ARITH_SBB, args[1], args[5], 1); - else - tcg_out_modrm(s, 0x01 | (ARITH_SBB << 3), args[5], args[1]); + goto gen_shift; + gen_shift: + if (const_args[2]) { + tcg_out_shifti(s, c + rexw, args[0], args[2]); + } else { + tcg_out_modrm(s, OPC_SHIFT_cl + rexw, c, args[0]); + } break; + case INDEX_op_brcond_i32: - tcg_out_brcond(s, args[2], args[0], args[1], const_args[1], args[3]); + tcg_out_brcond32(s, args[2], args[0], args[1], const_args[1], + args[3], 0); break; - case INDEX_op_brcond2_i32: - tcg_out_brcond2(s, args, const_args); + case INDEX_op_setcond_i32: + tcg_out_setcond32(s, args[3], args[0], args[1], + args[2], const_args[2]); break; - case INDEX_op_bswap16_i32: - tcg_out8(s, 0x66); - tcg_out_modrm(s, 0xc1, SHIFT_ROL, args[0]); - tcg_out8(s, 8); + OP_32_64(bswap16): + tcg_out_rolw_8(s, args[0]); break; - case INDEX_op_bswap32_i32: - tcg_out_opc(s, (0xc8 + args[0]) | P_EXT); + OP_32_64(bswap32): + tcg_out_bswap32(s, args[0]); break; - case INDEX_op_neg_i32: - tcg_out_modrm(s, 0xf7, 3, args[0]); + OP_32_64(neg): + tcg_out_modrm(s, OPC_GRP3_Ev + rexw, EXT3_NEG, args[0]); break; - - case INDEX_op_not_i32: - tcg_out_modrm(s, 0xf7, 2, args[0]); + OP_32_64(not): + tcg_out_modrm(s, OPC_GRP3_Ev + rexw, EXT3_NOT, args[0]); break; - case INDEX_op_ext8s_i32: - tcg_out_modrm(s, 0xbe | P_EXT, args[0], args[1]); + OP_32_64(ext8s): + tcg_out_ext8s(s, args[0], args[1], rexw); break; - case INDEX_op_ext16s_i32: - tcg_out_modrm(s, 0xbf | P_EXT, args[0], args[1]); + OP_32_64(ext16s): + tcg_out_ext16s(s, args[0], args[1], rexw); break; - case INDEX_op_ext8u_i32: - tcg_out_modrm(s, 0xb6 | P_EXT, args[0], args[1]); + OP_32_64(ext8u): + tcg_out_ext8u(s, args[0], args[1]); break; - case INDEX_op_ext16u_i32: - tcg_out_modrm(s, 0xb7 | P_EXT, args[0], args[1]); + OP_32_64(ext16u): + tcg_out_ext16u(s, args[0], args[1]); break; case INDEX_op_qemu_ld8u: @@ -1092,13 +1653,16 @@ static inline void tcg_out_op(TCGContext *s, int opc, case INDEX_op_qemu_ld16s: tcg_out_qemu_ld(s, args, 1 | 4); break; +#if TCG_TARGET_REG_BITS == 64 case INDEX_op_qemu_ld32u: +#endif + case INDEX_op_qemu_ld32: tcg_out_qemu_ld(s, args, 2); break; case INDEX_op_qemu_ld64: tcg_out_qemu_ld(s, args, 3); break; - + case INDEX_op_qemu_st8: tcg_out_qemu_st(s, args, 0); break; @@ -1112,9 +1676,82 @@ static inline void tcg_out_op(TCGContext *s, int opc, tcg_out_qemu_st(s, args, 3); break; +#if TCG_TARGET_REG_BITS == 32 + case INDEX_op_brcond2_i32: + tcg_out_brcond2(s, args, const_args, 0); + break; + case INDEX_op_setcond2_i32: + tcg_out_setcond2(s, args, const_args); + break; + case INDEX_op_mulu2_i32: + tcg_out_modrm(s, OPC_GRP3_Ev, EXT3_MUL, args[3]); + break; + case INDEX_op_add2_i32: + if (const_args[4]) { + tgen_arithi(s, ARITH_ADD, args[0], args[4], 1); + } else { + tgen_arithr(s, ARITH_ADD, args[0], args[4]); + } + if (const_args[5]) { + tgen_arithi(s, ARITH_ADC, args[1], args[5], 1); + } else { + tgen_arithr(s, ARITH_ADC, args[1], args[5]); + } + break; + case INDEX_op_sub2_i32: + if (const_args[4]) { + tgen_arithi(s, ARITH_SUB, args[0], args[4], 1); + } else { + tgen_arithr(s, ARITH_SUB, args[0], args[4]); + } + if (const_args[5]) { + tgen_arithi(s, ARITH_SBB, args[1], args[5], 1); + } else { + tgen_arithr(s, ARITH_SBB, args[1], args[5]); + } + break; +#else /* TCG_TARGET_REG_BITS == 64 */ + case INDEX_op_movi_i64: + tcg_out_movi(s, TCG_TYPE_I64, args[0], args[1]); + break; + case INDEX_op_ld32s_i64: + tcg_out_modrm_offset(s, OPC_MOVSLQ, args[0], args[1], args[2]); + break; + case INDEX_op_ld_i64: + tcg_out_ld(s, TCG_TYPE_I64, args[0], args[1], args[2]); + break; + case INDEX_op_st_i64: + tcg_out_st(s, TCG_TYPE_I64, args[0], args[1], args[2]); + break; + case INDEX_op_qemu_ld32s: + tcg_out_qemu_ld(s, args, 2 | 4); + break; + + case INDEX_op_brcond_i64: + tcg_out_brcond64(s, args[2], args[0], args[1], const_args[1], + args[3], 0); + break; + case INDEX_op_setcond_i64: + tcg_out_setcond64(s, args[3], args[0], args[1], + args[2], const_args[2]); + break; + + case INDEX_op_bswap64_i64: + tcg_out_bswap64(s, args[0]); + break; + case INDEX_op_ext32u_i64: + tcg_out_ext32u(s, args[0], args[1]); + break; + case INDEX_op_ext32s_i64: + tcg_out_ext32s(s, args[0], args[1]); + break; +#endif + default: tcg_abort(); } + +#undef OP_32_64 } static const TCGTargetOpDef x86_op_defs[] = { @@ -1134,10 +1771,9 @@ static const TCGTargetOpDef x86_op_defs[] = { { INDEX_op_st16_i32, { "r", "r" } }, { INDEX_op_st_i32, { "r", "r" } }, - { INDEX_op_add_i32, { "r", "0", "ri" } }, + { INDEX_op_add_i32, { "r", "r", "ri" } }, { INDEX_op_sub_i32, { "r", "0", "ri" } }, { INDEX_op_mul_i32, { "r", "0", "ri" } }, - { INDEX_op_mulu2_i32, { "a", "d", "a", "r" } }, { INDEX_op_div2_i32, { "a", "d", "0", "1", "r" } }, { INDEX_op_divu2_i32, { "a", "d", "0", "1", "r" } }, { INDEX_op_and_i32, { "r", "0", "ri" } }, @@ -1152,10 +1788,6 @@ static const TCGTargetOpDef x86_op_defs[] = { { INDEX_op_brcond_i32, { "r", "ri" } }, - { INDEX_op_add2_i32, { "r", "r", "0", "1", "ri", "ri" } }, - { INDEX_op_sub2_i32, { "r", "r", "0", "1", "ri", "ri" } }, - { INDEX_op_brcond2_i32, { "r", "r", "ri", "ri" } }, - { INDEX_op_bswap16_i32, { "r", "0" } }, { INDEX_op_bswap32_i32, { "r", "0" } }, @@ -1165,15 +1797,84 @@ static const TCGTargetOpDef x86_op_defs[] = { { INDEX_op_ext8s_i32, { "r", "q" } }, { INDEX_op_ext16s_i32, { "r", "r" } }, - { INDEX_op_ext8u_i32, { "r", "q"} }, - { INDEX_op_ext16u_i32, { "r", "r"} }, + { INDEX_op_ext8u_i32, { "r", "q" } }, + { INDEX_op_ext16u_i32, { "r", "r" } }, + + { INDEX_op_setcond_i32, { "q", "r", "ri" } }, -#if TARGET_LONG_BITS == 32 +#if TCG_TARGET_REG_BITS == 32 + { INDEX_op_mulu2_i32, { "a", "d", "a", "r" } }, + { INDEX_op_add2_i32, { "r", "r", "0", "1", "ri", "ri" } }, + { INDEX_op_sub2_i32, { "r", "r", "0", "1", "ri", "ri" } }, + { INDEX_op_brcond2_i32, { "r", "r", "ri", "ri" } }, + { INDEX_op_setcond2_i32, { "r", "r", "r", "ri", "ri" } }, +#else + { INDEX_op_mov_i64, { "r", "r" } }, + { INDEX_op_movi_i64, { "r" } }, + { INDEX_op_ld8u_i64, { "r", "r" } }, + { INDEX_op_ld8s_i64, { "r", "r" } }, + { INDEX_op_ld16u_i64, { "r", "r" } }, + { INDEX_op_ld16s_i64, { "r", "r" } }, + { INDEX_op_ld32u_i64, { "r", "r" } }, + { INDEX_op_ld32s_i64, { "r", "r" } }, + { INDEX_op_ld_i64, { "r", "r" } }, + { INDEX_op_st8_i64, { "r", "r" } }, + { INDEX_op_st16_i64, { "r", "r" } }, + { INDEX_op_st32_i64, { "r", "r" } }, + { INDEX_op_st_i64, { "r", "r" } }, + + { INDEX_op_add_i64, { "r", "0", "re" } }, + { INDEX_op_mul_i64, { "r", "0", "re" } }, + { INDEX_op_div2_i64, { "a", "d", "0", "1", "r" } }, + { INDEX_op_divu2_i64, { "a", "d", "0", "1", "r" } }, + { INDEX_op_sub_i64, { "r", "0", "re" } }, + { INDEX_op_and_i64, { "r", "0", "reZ" } }, + { INDEX_op_or_i64, { "r", "0", "re" } }, + { INDEX_op_xor_i64, { "r", "0", "re" } }, + + { INDEX_op_shl_i64, { "r", "0", "ci" } }, + { INDEX_op_shr_i64, { "r", "0", "ci" } }, + { INDEX_op_sar_i64, { "r", "0", "ci" } }, + { INDEX_op_rotl_i64, { "r", "0", "ci" } }, + { INDEX_op_rotr_i64, { "r", "0", "ci" } }, + + { INDEX_op_brcond_i64, { "r", "re" } }, + { INDEX_op_setcond_i64, { "r", "r", "re" } }, + + { INDEX_op_bswap16_i64, { "r", "0" } }, + { INDEX_op_bswap32_i64, { "r", "0" } }, + { INDEX_op_bswap64_i64, { "r", "0" } }, + { INDEX_op_neg_i64, { "r", "0" } }, + { INDEX_op_not_i64, { "r", "0" } }, + + { INDEX_op_ext8s_i64, { "r", "r" } }, + { INDEX_op_ext16s_i64, { "r", "r" } }, + { INDEX_op_ext32s_i64, { "r", "r" } }, + { INDEX_op_ext8u_i64, { "r", "r" } }, + { INDEX_op_ext16u_i64, { "r", "r" } }, + { INDEX_op_ext32u_i64, { "r", "r" } }, +#endif + +#if TCG_TARGET_REG_BITS == 64 { INDEX_op_qemu_ld8u, { "r", "L" } }, { INDEX_op_qemu_ld8s, { "r", "L" } }, { INDEX_op_qemu_ld16u, { "r", "L" } }, { INDEX_op_qemu_ld16s, { "r", "L" } }, + { INDEX_op_qemu_ld32, { "r", "L" } }, { INDEX_op_qemu_ld32u, { "r", "L" } }, + { INDEX_op_qemu_ld32s, { "r", "L" } }, + { INDEX_op_qemu_ld64, { "r", "L" } }, + + { INDEX_op_qemu_st8, { "L", "L" } }, + { INDEX_op_qemu_st16, { "L", "L" } }, + { INDEX_op_qemu_st32, { "L", "L" } }, + { INDEX_op_qemu_st64, { "L", "L" } }, +#elif TARGET_LONG_BITS <= TCG_TARGET_REG_BITS + { INDEX_op_qemu_ld8u, { "r", "L" } }, + { INDEX_op_qemu_ld8s, { "r", "L" } }, + { INDEX_op_qemu_ld16u, { "r", "L" } }, + { INDEX_op_qemu_ld16s, { "r", "L" } }, + { INDEX_op_qemu_ld32, { "r", "L" } }, { INDEX_op_qemu_ld64, { "r", "r", "L" } }, { INDEX_op_qemu_st8, { "cb", "L" } }, @@ -1185,7 +1886,7 @@ static const TCGTargetOpDef x86_op_defs[] = { { INDEX_op_qemu_ld8s, { "r", "L", "L" } }, { INDEX_op_qemu_ld16u, { "r", "L", "L" } }, { INDEX_op_qemu_ld16s, { "r", "L", "L" } }, - { INDEX_op_qemu_ld32u, { "r", "L", "L" } }, + { INDEX_op_qemu_ld32, { "r", "L", "L" } }, { INDEX_op_qemu_ld64, { "r", "r", "L", "L" } }, { INDEX_op_qemu_st8, { "cb", "L", "L" } }, @@ -1197,64 +1898,85 @@ static const TCGTargetOpDef x86_op_defs[] = { }; static int tcg_target_callee_save_regs[] = { - /* TCG_REG_EBP, */ /* currently used for the global env, so no - need to save */ +#if TCG_TARGET_REG_BITS == 64 + TCG_REG_RBP, + TCG_REG_RBX, + TCG_REG_R12, + TCG_REG_R13, + /* TCG_REG_R14, */ /* Currently used for the global env. */ + TCG_REG_R15, +#else + /* TCG_REG_EBP, */ /* Currently used for the global env. */ TCG_REG_EBX, TCG_REG_ESI, TCG_REG_EDI, +#endif }; -static inline void tcg_out_push(TCGContext *s, int reg) -{ - tcg_out_opc(s, 0x50 + reg); -} - -static inline void tcg_out_pop(TCGContext *s, int reg) -{ - tcg_out_opc(s, 0x58 + reg); -} - /* Generate global QEMU prologue and epilogue code */ -void tcg_target_qemu_prologue(TCGContext *s) +static void tcg_target_qemu_prologue(TCGContext *s) { int i, frame_size, push_size, stack_addend; - + /* TB prologue */ - /* save all callee saved registers */ - for(i = 0; i < ARRAY_SIZE(tcg_target_callee_save_regs); i++) { + + /* Save all callee saved registers. */ + for (i = 0; i < ARRAY_SIZE(tcg_target_callee_save_regs); i++) { tcg_out_push(s, tcg_target_callee_save_regs[i]); } - /* reserve some stack space */ - push_size = 4 + ARRAY_SIZE(tcg_target_callee_save_regs) * 4; + + /* Reserve some stack space. */ + push_size = 1 + ARRAY_SIZE(tcg_target_callee_save_regs); + push_size *= TCG_TARGET_REG_BITS / 8; + frame_size = push_size + TCG_STATIC_CALL_ARGS_SIZE; - frame_size = (frame_size + TCG_TARGET_STACK_ALIGN - 1) & + frame_size = (frame_size + TCG_TARGET_STACK_ALIGN - 1) & ~(TCG_TARGET_STACK_ALIGN - 1); stack_addend = frame_size - push_size; tcg_out_addi(s, TCG_REG_ESP, -stack_addend); - tcg_out_modrm(s, 0xff, 4, TCG_REG_EAX); /* jmp *%eax */ - + /* jmp *tb. */ + tcg_out_modrm(s, OPC_GRP5, EXT5_JMPN_Ev, tcg_target_call_iarg_regs[0]); + /* TB epilogue */ tb_ret_addr = s->code_ptr; + tcg_out_addi(s, TCG_REG_ESP, stack_addend); - for(i = ARRAY_SIZE(tcg_target_callee_save_regs) - 1; i >= 0; i--) { + + for (i = ARRAY_SIZE(tcg_target_callee_save_regs) - 1; i >= 0; i--) { tcg_out_pop(s, tcg_target_callee_save_regs[i]); } - tcg_out8(s, 0xc3); /* ret */ + tcg_out_opc(s, OPC_RET, 0, 0, 0); } -void tcg_target_init(TCGContext *s) +static void tcg_target_init(TCGContext *s) { +#if !defined(CONFIG_USER_ONLY) /* fail safe */ if ((1 << CPU_TLB_ENTRY_BITS) != sizeof(CPUTLBEntry)) tcg_abort(); +#endif + + if (TCG_TARGET_REG_BITS == 64) { + tcg_regset_set32(tcg_target_available_regs[TCG_TYPE_I32], 0, 0xffff); + tcg_regset_set32(tcg_target_available_regs[TCG_TYPE_I64], 0, 0xffff); + } else { + tcg_regset_set32(tcg_target_available_regs[TCG_TYPE_I32], 0, 0xff); + } + + tcg_regset_clear(tcg_target_call_clobber_regs); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_EAX); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_EDX); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_ECX); + if (TCG_TARGET_REG_BITS == 64) { + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_RDI); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_RSI); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R8); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R9); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R10); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R11); + } - tcg_regset_set32(tcg_target_available_regs[TCG_TYPE_I32], 0, 0xff); - tcg_regset_set32(tcg_target_call_clobber_regs, 0, - (1 << TCG_REG_EAX) | - (1 << TCG_REG_EDX) | - (1 << TCG_REG_ECX)); - tcg_regset_clear(s->reserved_regs); tcg_regset_set_reg(s->reserved_regs, TCG_REG_ESP); diff --git a/tcg/i386/tcg-target.h b/tcg/i386/tcg-target.h index f97034c..a869cf5 100644 --- a/tcg/i386/tcg-target.h +++ b/tcg/i386/tcg-target.h @@ -23,10 +23,18 @@ */ #define TCG_TARGET_I386 1 +#if defined(__x86_64__) +# define TCG_TARGET_REG_BITS 64 +#else #define TCG_TARGET_REG_BITS 32 +#endif //#define TCG_TARGET_WORDS_BIGENDIAN +#if TCG_TARGET_REG_BITS == 64 +# define TCG_TARGET_NB_REGS 16 +#else #define TCG_TARGET_NB_REGS 8 +#endif enum { TCG_REG_EAX = 0, @@ -37,14 +45,37 @@ enum { TCG_REG_EBP, TCG_REG_ESI, TCG_REG_EDI, + + /* 64-bit registers; always define the symbols to avoid + too much if-deffing. */ + TCG_REG_R8, + TCG_REG_R9, + TCG_REG_R10, + TCG_REG_R11, + TCG_REG_R12, + TCG_REG_R13, + TCG_REG_R14, + TCG_REG_R15, + TCG_REG_RAX = TCG_REG_EAX, + TCG_REG_RCX = TCG_REG_ECX, + TCG_REG_RDX = TCG_REG_EDX, + TCG_REG_RBX = TCG_REG_EBX, + TCG_REG_RSP = TCG_REG_ESP, + TCG_REG_RBP = TCG_REG_EBP, + TCG_REG_RSI = TCG_REG_ESI, + TCG_REG_RDI = TCG_REG_EDI, }; +#define TCG_CT_CONST_S32 0x100 +#define TCG_CT_CONST_U32 0x200 + /* used for function call generation */ #define TCG_REG_CALL_STACK TCG_REG_ESP #define TCG_TARGET_STACK_ALIGN 16 #define TCG_TARGET_CALL_STACK_OFFSET 0 /* optional instructions */ +#define TCG_TARGET_HAS_div2_i32 #define TCG_TARGET_HAS_rot_i32 #define TCG_TARGET_HAS_ext8s_i32 #define TCG_TARGET_HAS_ext16s_i32 @@ -56,13 +87,43 @@ enum { #define TCG_TARGET_HAS_not_i32 // #define TCG_TARGET_HAS_andc_i32 // #define TCG_TARGET_HAS_orc_i32 +// #define TCG_TARGET_HAS_eqv_i32 +// #define TCG_TARGET_HAS_nand_i32 +// #define TCG_TARGET_HAS_nor_i32 + +#if TCG_TARGET_REG_BITS == 64 +#define TCG_TARGET_HAS_div2_i64 +#define TCG_TARGET_HAS_rot_i64 +#define TCG_TARGET_HAS_ext8s_i64 +#define TCG_TARGET_HAS_ext16s_i64 +#define TCG_TARGET_HAS_ext32s_i64 +#define TCG_TARGET_HAS_ext8u_i64 +#define TCG_TARGET_HAS_ext16u_i64 +#define TCG_TARGET_HAS_ext32u_i64 +#define TCG_TARGET_HAS_bswap16_i64 +#define TCG_TARGET_HAS_bswap32_i64 +#define TCG_TARGET_HAS_bswap64_i64 +#define TCG_TARGET_HAS_neg_i64 +#define TCG_TARGET_HAS_not_i64 +// #define TCG_TARGET_HAS_andc_i64 +// #define TCG_TARGET_HAS_orc_i64 +// #define TCG_TARGET_HAS_eqv_i64 +// #define TCG_TARGET_HAS_nand_i64 +// #define TCG_TARGET_HAS_nor_i64 +#endif #define TCG_TARGET_HAS_GUEST_BASE /* Note: must be synced with dyngen-exec.h */ +#if TCG_TARGET_REG_BITS == 64 +#define TCG_AREG0 TCG_REG_R14 +#define TCG_AREG1 TCG_REG_R15 +#define TCG_AREG2 TCG_REG_R12 +#else #define TCG_AREG0 TCG_REG_EBP #define TCG_AREG1 TCG_REG_EBX #define TCG_AREG2 TCG_REG_ESI +#endif static inline void flush_icache_range(unsigned long start, unsigned long stop) { |