diff options
Diffstat (limited to 'tcg/i386/tcg-target.c')
| -rw-r--r-- | tcg/i386/tcg-target.c | 709 |
1 files changed, 415 insertions, 294 deletions
diff --git a/tcg/i386/tcg-target.c b/tcg/i386/tcg-target.c index 4e33b25ef8..396a2f1d53 100644 --- a/tcg/i386/tcg-target.c +++ b/tcg/i386/tcg-target.c @@ -50,7 +50,7 @@ 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; @@ -156,6 +156,50 @@ static inline int tcg_target_const_match(tcg_target_long val, return 0; } +#define P_EXT 0x100 /* 0x0f opcode prefix */ + +#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_Iv (0xb8) +#define OPC_MOVSBL (0xbe | P_EXT) +#define OPC_MOVSWL (0xbf | P_EXT) +#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) /* ... plus condition code */ +#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 @@ -165,12 +209,26 @@ 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_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 @@ -189,8 +247,6 @@ 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, @@ -217,91 +273,192 @@ static inline void tcg_out_modrm(TCGContext *s, int opc, int r, int rm) tcg_out8(s, 0xc0 | (r << 3) | 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 -1 value. */ + +static void tcg_out_modrm_sib_offset(TCGContext *s, int opc, int r, int rm, + int index, int shift, int32_t offset) { + int mod, len; + + if (index == -1 && rm == -1) { + /* Absolute address. */ + tcg_out_opc(s, opc); + tcg_out8(s, (r << 3) | 5); + tcg_out32(s, offset); + return; + } + tcg_out_opc(s, opc); + + /* Find the length of the immediate addend. Note that the encoding + that would be used for (%ebp) indicates absolute addressing. */ if (rm == -1) { - tcg_out8(s, 0x05 | (r << 3)); - tcg_out32(s, offset); + mod = 0, len = 4, rm = 5; } 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); - } else { - tcg_out8(s, 0x40 | (r << 3) | rm); - } - tcg_out8(s, offset); + mod = 0, len = 0; + } else if (offset == (int8_t)offset) { + mod = 0x40, len = 1; } else { - if (rm == TCG_REG_ESP) { - tcg_out8(s, 0x84 | (r << 3)); - tcg_out8(s, 0x24); + 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 == -1 && rm != TCG_REG_ESP) { + /* Single byte MODRM format. */ + tcg_out8(s, mod | (r << 3) | rm); + } else { + /* Two byte MODRM+SIB format. */ + + /* Note that the encoding that would place %esp into the index + field indicates no index register. */ + if (index == -1) { + index = 4; } else { - tcg_out8(s, 0x80 | (r << 3) | rm); + assert(index != TCG_REG_ESP); } + + tcg_out8(s, mod | (r << 3) | 4); + tcg_out8(s, (shift << 6) | (index << 3) | rm); + } + + if (len == 1) { + tcg_out8(s, offset); + } else if (len == 4) { tcg_out32(s, offset); } } +/* rm == -1 means no register index */ +static inline void tcg_out_modrm_offset(TCGContext *s, int opc, int r, int rm, + int32_t 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) +{ + tcg_out_modrm(s, OPC_ARITH_GvEv + (subop << 3), dest, src); +} + static inline void tcg_out_mov(TCGContext *s, int ret, int arg) { - if (arg != ret) - tcg_out_modrm(s, 0x8b, ret, arg); + if (arg != ret) { + tcg_out_modrm(s, OPC_MOVL_GvEv, ret, arg); + } } static inline void tcg_out_movi(TCGContext *s, TCGType type, int ret, int32_t arg) { if (arg == 0) { - /* xor r0,r0 */ - tcg_out_modrm(s, 0x01 | (ARITH_XOR << 3), ret, ret); + tgen_arithr(s, ARITH_XOR, ret, ret); } else { - tcg_out8(s, 0xb8 + ret); + tcg_out8(s, OPC_MOVL_Iv + ret); tcg_out32(s, arg); } } +static inline void tcg_out_pushi(TCGContext *s, tcg_target_long val) +{ + if (val == (int8_t)val) { + tcg_out_opc(s, OPC_PUSH_Ib); + tcg_out8(s, val); + } else { + tcg_out_opc(s, OPC_PUSH_Iv); + tcg_out32(s, val); + } +} + +static inline void tcg_out_push(TCGContext *s, int reg) +{ + tcg_out_opc(s, OPC_PUSH_r32 + reg); +} + +static inline void tcg_out_pop(TCGContext *s, int reg) +{ + tcg_out_opc(s, OPC_POP_r32 + reg); +} + 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); + tcg_out_modrm_offset(s, OPC_MOVL_GvEv, 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); + tcg_out_modrm_offset(s, OPC_MOVL_EvGv, arg, arg1, arg2); +} + +static void tcg_out_shifti(TCGContext *s, int subopc, int reg, int count) +{ + if (count == 1) { + tcg_out_modrm(s, OPC_SHIFT_1, subopc, reg); + } else { + tcg_out_modrm(s, OPC_SHIFT_Ib, subopc, reg); + tcg_out8(s, count); + } +} + +static inline void tcg_out_bswap32(TCGContext *s, int reg) +{ + tcg_out_opc(s, OPC_BSWAP + reg); +} + +static inline void tcg_out_rolw_8(TCGContext *s, int reg) +{ + tcg_out8(s, 0x66); + tcg_out_shifti(s, SHIFT_ROL, reg, 8); +} + +static inline void tcg_out_ext8u(TCGContext *s, int dest, int src) +{ + /* movzbl */ + assert(src < 4); + tcg_out_modrm(s, OPC_MOVZBL, dest, src); +} + +static void tcg_out_ext8s(TCGContext *s, int dest, int src) +{ + /* movsbl */ + assert(src < 4); + tcg_out_modrm(s, OPC_MOVSBL, dest, src); } -static inline void tgen_arithi(TCGContext *s, int c, int r0, int32_t val, int cf) +static inline void tcg_out_ext16u(TCGContext *s, int dest, int src) { - 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); + /* movzwl */ + tcg_out_modrm(s, OPC_MOVZWL, dest, src); +} + +static inline void tcg_out_ext16s(TCGContext *s, int dest, int src) +{ + /* movswl */ + tcg_out_modrm(s, OPC_MOVSWL, dest, src); +} + +static inline void tgen_arithi(TCGContext *s, int c, int r0, + int32_t val, int cf) +{ + /* ??? 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 opc = ((c == ARITH_ADD) ^ (val < 0) ? OPC_INC_r32 : OPC_DEC_r32); + tcg_out_opc(s, opc + r0); } else if (val == (int8_t)val) { - tcg_out_modrm(s, 0x83, c, r0); + tcg_out_modrm(s, OPC_ARITH_EvIb, 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); + tcg_out_ext8u(s, r0, r0); } else if (c == ARITH_AND && val == 0xffffu) { - /* movzwl */ - tcg_out_modrm(s, 0xb7 | P_EXT, r0, r0); + tcg_out_ext16u(s, r0, r0); } else { - tcg_out_modrm(s, 0x81, c, r0); + tcg_out_modrm(s, OPC_ARITH_EvIz, c, r0); tcg_out32(s, val); } } @@ -317,15 +474,15 @@ 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); + tcg_out8(s, OPC_JMP_short); } else { - tcg_out8(s, 0x70 + opc); + tcg_out8(s, OPC_JCC_short + opc); } tcg_out8(s, val1); } else { @@ -333,28 +490,26 @@ static void tcg_out_jxx(TCGContext *s, int opc, int label_index, int 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); tcg_out32(s, val - 6); } } } else if (small) { if (opc == -1) { - tcg_out8(s, 0xeb); + tcg_out8(s, OPC_JMP_short); } else { - tcg_out8(s, 0x70 + opc); + 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); } tcg_out_reloc(s, s->code_ptr, R_386_PC32, label_index, -4); s->code_ptr += 4; @@ -367,12 +522,12 @@ static void tcg_out_cmp(TCGContext *s, TCGArg arg1, TCGArg arg2, if (const_arg2) { if (arg2 == 0) { /* test r, r */ - tcg_out_modrm(s, 0x85, arg1, arg1); + tcg_out_modrm(s, OPC_TESTL, arg1, arg1); } else { tgen_arithi(s, ARITH_CMP, arg1, arg2, 0); } } else { - tcg_out_modrm(s, 0x01 | (ARITH_CMP << 3), arg2, arg1); + tgen_arithr(s, ARITH_CMP, arg1, arg2); } } @@ -470,9 +625,8 @@ static void tcg_out_setcond(TCGContext *s, TCGCond cond, TCGArg dest, TCGArg arg1, TCGArg arg2, int const_arg2) { tcg_out_cmp(s, arg1, arg2, const_arg2); - /* setcc */ - tcg_out_modrm(s, 0x90 | tcg_cond_to_jcc[cond] | P_EXT, 0, dest); - tgen_arithi(s, ARITH_AND, dest, 0xff, 0); + tcg_out_modrm(s, OPC_SETCC | tcg_cond_to_jcc[cond], 0, dest); + tcg_out_ext8u(s, dest, dest); } static void tcg_out_setcond2(TCGContext *s, const TCGArg *args, @@ -517,6 +671,12 @@ static void tcg_out_setcond2(TCGContext *s, const TCGArg *args, } } +static void tcg_out_calli(TCGContext *s, tcg_target_long dest) +{ + tcg_out_opc(s, OPC_CALL_Jz); + tcg_out32(s, dest - (tcg_target_long)s->code_ptr - 4); +} + #if defined(CONFIG_SOFTMMU) #include "../../softmmu_defs.h" @@ -573,48 +733,42 @@ static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, r1 = TCG_REG_EDX; #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)); + tcg_out_mov(s, r1, addr_reg); + tcg_out_mov(s, r0, addr_reg); + + tcg_out_shifti(s, SHIFT_SHR, r1, TARGET_PAGE_BITS - CPU_TLB_ENTRY_BITS); + + tgen_arithi(s, ARITH_AND, r0, TARGET_PAGE_MASK | ((1 << s_bits) - 1), 0); + tgen_arithi(s, ARITH_AND, r1, (CPU_TLB_SIZE - 1) << CPU_TLB_ENTRY_BITS, 0); + + tcg_out_modrm_sib_offset(s, OPC_LEA, r1, TCG_AREG0, r1, 0, + offsetof(CPUState, + tlb_table[mem_index][0].addr_read)); /* cmp 0(r1), r0 */ - tcg_out_modrm_offset(s, 0x3b, r0, r1, 0); - + tcg_out_modrm_offset(s, OPC_CMP_GvEv, r0, r1, 0); + tcg_out_mov(s, r0, addr_reg); - + #if TARGET_LONG_BITS == 32 /* je label1 */ - tcg_out8(s, 0x70 + JCC_JE); + tcg_out8(s, OPC_JCC_short + JCC_JE); label1_ptr = s->code_ptr; s->code_ptr++; #else /* jne label3 */ - tcg_out8(s, 0x70 + JCC_JNE); + tcg_out8(s, OPC_JCC_short + 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, addr_reg2, r1, 4); /* je label1 */ - tcg_out8(s, 0x70 + JCC_JE); + tcg_out8(s, OPC_JCC_short + JCC_JE); label1_ptr = s->code_ptr; s->code_ptr++; - + /* label3: */ *label3_ptr = s->code_ptr - label3_ptr - 1; #endif @@ -626,26 +780,20 @@ static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, 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); + tcg_out_calli(s, (tcg_target_long)qemu_ld_helpers[s_bits]); switch(opc) { case 0 | 4: - /* movsbl */ - tcg_out_modrm(s, 0xbe | P_EXT, data_reg, TCG_REG_EAX); + tcg_out_ext8s(s, data_reg, TCG_REG_EAX); break; case 1 | 4: - /* movswl */ - tcg_out_modrm(s, 0xbf | P_EXT, data_reg, TCG_REG_EAX); + tcg_out_ext16s(s, data_reg, TCG_REG_EAX); break; case 0: - /* movzbl */ - tcg_out_modrm(s, 0xb6 | P_EXT, data_reg, TCG_REG_EAX); + tcg_out_ext8u(s, data_reg, TCG_REG_EAX); break; case 1: - /* movzwl */ - tcg_out_modrm(s, 0xb7 | P_EXT, data_reg, TCG_REG_EAX); + tcg_out_ext16u(s, data_reg, TCG_REG_EAX); break; case 2: default: @@ -653,7 +801,8 @@ static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, break; case 3: if (data_reg == TCG_REG_EDX) { - tcg_out_opc(s, 0x90 + TCG_REG_EDX); /* xchg %edx, %eax */ + /* xchg %edx, %eax */ + tcg_out_opc(s, OPC_XCHG_ax_r32 + TCG_REG_EDX); tcg_out_mov(s, data_reg2, TCG_REG_EAX); } else { tcg_out_mov(s, data_reg, TCG_REG_EAX); @@ -663,15 +812,16 @@ static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, } /* jmp label2 */ - tcg_out8(s, 0xeb); + tcg_out8(s, OPC_JMP_short); 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) - + tcg_out_modrm_offset(s, OPC_ADD_GvEv, r0, r1, + offsetof(CPUTLBEntry, addend) - offsetof(CPUTLBEntry, addr_read)); #else r0 = addr_reg; @@ -685,62 +835,51 @@ static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, switch(opc) { case 0: /* movzbl */ - tcg_out_modrm_offset(s, 0xb6 | P_EXT, data_reg, r0, GUEST_BASE); + tcg_out_modrm_offset(s, OPC_MOVZBL, data_reg, r0, GUEST_BASE); 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, data_reg, r0, GUEST_BASE); break; case 1: /* movzwl */ - tcg_out_modrm_offset(s, 0xb7 | P_EXT, data_reg, r0, GUEST_BASE); + tcg_out_modrm_offset(s, OPC_MOVZWL, 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); + tcg_out_rolw_8(s, data_reg); } break; case 1 | 4: /* movswl */ - tcg_out_modrm_offset(s, 0xbf | P_EXT, data_reg, r0, GUEST_BASE); + tcg_out_modrm_offset(s, OPC_MOVSWL, 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); + tcg_out_rolw_8(s, data_reg); /* movswl data_reg, data_reg */ - tcg_out_modrm(s, 0xbf | P_EXT, data_reg, data_reg); + tcg_out_modrm(s, OPC_MOVSWL, data_reg, data_reg); } 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, data_reg, r0, GUEST_BASE); if (bswap) { - /* bswap */ - tcg_out_opc(s, (0xc8 + data_reg) | P_EXT); + tcg_out_bswap32(s, data_reg); } 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 (bswap) { + int t = data_reg; + data_reg = data_reg2; + data_reg2 = t; } - 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); + if (r0 != data_reg) { + tcg_out_ld(s, TCG_TYPE_I32, data_reg, r0, GUEST_BASE); + tcg_out_ld(s, TCG_TYPE_I32, data_reg2, r0, GUEST_BASE + 4); } 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); + tcg_out_ld(s, TCG_TYPE_I32, data_reg2, r0, GUEST_BASE + 4); + tcg_out_ld(s, TCG_TYPE_I32, data_reg, r0, GUEST_BASE); + } + if (bswap) { + tcg_out_bswap32(s, data_reg); + tcg_out_bswap32(s, data_reg2); } break; default: @@ -759,6 +898,7 @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, { int addr_reg, data_reg, data_reg2, r0, r1, mem_index, s_bits, bswap; #if defined(CONFIG_SOFTMMU) + int stack_adjust; uint8_t *label1_ptr, *label2_ptr; #endif #if TARGET_LONG_BITS == 64 @@ -785,48 +925,42 @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, r1 = TCG_REG_EDX; #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)); + tcg_out_mov(s, r1, addr_reg); + tcg_out_mov(s, r0, addr_reg); + + tcg_out_shifti(s, SHIFT_SHR, r1, TARGET_PAGE_BITS - CPU_TLB_ENTRY_BITS); + + tgen_arithi(s, ARITH_AND, r0, TARGET_PAGE_MASK | ((1 << s_bits) - 1), 0); + tgen_arithi(s, ARITH_AND, r1, (CPU_TLB_SIZE - 1) << CPU_TLB_ENTRY_BITS, 0); + + tcg_out_modrm_sib_offset(s, OPC_LEA, r1, TCG_AREG0, r1, 0, + offsetof(CPUState, + tlb_table[mem_index][0].addr_write)); /* cmp 0(r1), r0 */ - tcg_out_modrm_offset(s, 0x3b, r0, r1, 0); - + tcg_out_modrm_offset(s, OPC_CMP_GvEv, r0, r1, 0); + tcg_out_mov(s, r0, addr_reg); - + #if TARGET_LONG_BITS == 32 /* je label1 */ - tcg_out8(s, 0x70 + JCC_JE); + tcg_out8(s, OPC_JCC_short + JCC_JE); label1_ptr = s->code_ptr; s->code_ptr++; #else /* jne label3 */ - tcg_out8(s, 0x70 + JCC_JNE); + tcg_out8(s, OPC_JCC_short + 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, addr_reg2, r1, 4); /* je label1 */ - tcg_out8(s, 0x70 + JCC_JE); + tcg_out8(s, OPC_JCC_short + JCC_JE); label1_ptr = s->code_ptr; s->code_ptr++; - + /* label3: */ *label3_ptr = s->code_ptr - label3_ptr - 1; #endif @@ -836,76 +970,68 @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, 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); + tcg_out_pushi(s, mem_index); + stack_adjust = 4; } else { switch(opc) { case 0: - /* movzbl */ - tcg_out_modrm(s, 0xb6 | P_EXT, TCG_REG_EDX, data_reg); + tcg_out_ext8u(s, TCG_REG_EDX, data_reg); break; case 1: - /* movzwl */ - tcg_out_modrm(s, 0xb7 | P_EXT, TCG_REG_EDX, data_reg); + tcg_out_ext16u(s, 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); + stack_adjust = 0; } #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); + 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_REG_EDX, addr_reg2); switch(opc) { case 0: - /* movzbl */ - tcg_out_modrm(s, 0xb6 | P_EXT, TCG_REG_ECX, data_reg); + tcg_out_ext8u(s, TCG_REG_ECX, data_reg); break; case 1: - /* movzwl */ - tcg_out_modrm(s, 0xb7 | P_EXT, TCG_REG_ECX, data_reg); + tcg_out_ext16u(s, TCG_REG_ECX, data_reg); break; case 2: tcg_out_mov(s, TCG_REG_ECX, data_reg); break; } - 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); + tcg_out_pushi(s, mem_index); + stack_adjust = 4; } #endif - + + tcg_out_calli(s, (tcg_target_long)qemu_st_helpers[s_bits]); + + if (stack_adjust == 4) { + /* 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); + } + /* jmp label2 */ - tcg_out8(s, 0xeb); + tcg_out8(s, OPC_JMP_short); 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) - + tcg_out_modrm_offset(s, OPC_ADD_GvEv, r0, r1, + offsetof(CPUTLBEntry, addend) - offsetof(CPUTLBEntry, addr_write)); #else r0 = addr_reg; @@ -918,44 +1044,37 @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, #endif switch(opc) { case 0: - /* movb */ - tcg_out_modrm_offset(s, 0x88, data_reg, r0, GUEST_BASE); + tcg_out_modrm_offset(s, OPC_MOVB_EvGv, data_reg, r0, GUEST_BASE); 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); + tcg_out_rolw_8(s, r1); data_reg = r1; } /* movw */ tcg_out8(s, 0x66); - tcg_out_modrm_offset(s, 0x89, data_reg, r0, GUEST_BASE); + tcg_out_modrm_offset(s, OPC_MOVL_EvGv, data_reg, r0, GUEST_BASE); break; case 2: if (bswap) { tcg_out_mov(s, r1, data_reg); - /* bswap data_reg */ - tcg_out_opc(s, (0xc8 + r1) | P_EXT); + tcg_out_bswap32(s, r1); data_reg = r1; } - /* movl */ - tcg_out_modrm_offset(s, 0x89, data_reg, r0, GUEST_BASE); + tcg_out_st(s, TCG_TYPE_I32, data_reg, r0, GUEST_BASE); 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_bswap32(s, r1); + tcg_out_st(s, TCG_TYPE_I32, 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); + tcg_out_bswap32(s, r1); + tcg_out_st(s, TCG_TYPE_I32, r1, r0, GUEST_BASE + 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, data_reg, r0, GUEST_BASE); + tcg_out_st(s, TCG_TYPE_I32, data_reg2, r0, GUEST_BASE + 4); } break; default: @@ -972,41 +1091,41 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, const TCGArg *args, const int *const_args) { int c; - + 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_out8(s, OPC_JMP_long); /* jmp tb_ret_addr */ tcg_out32(s, tb_ret_addr - s->code_ptr - 4); 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_out8(s, OPC_JMP_long); tcg_out32(s, args[0] - (tcg_target_long)s->code_ptr - 4); } 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: @@ -1017,37 +1136,54 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, break; case INDEX_op_ld8u_i32: /* movzbl */ - tcg_out_modrm_offset(s, 0xb6 | P_EXT, args[0], args[1], args[2]); + 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]); + tcg_out_modrm_offset(s, OPC_MOVSBL, 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]); + 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]); + tcg_out_modrm_offset(s, OPC_MOVSWL, args[0], args[1], args[2]); break; 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]); + tcg_out_modrm_offset(s, OPC_MOVB_EvGv, 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]); + tcg_out_modrm_offset(s, OPC_MOVL_EvGv, args[0], args[1], args[2]); break; 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_add_i32: + /* 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, a0, a1); + break; + } + + tcg_out_modrm_sib_offset(s, OPC_LEA, a0, a1, a2, 0, c3); + break; + } + c = ARITH_ADD; + goto gen_arith; case INDEX_op_sub_i32: c = ARITH_SUB; goto gen_arith; @@ -1060,13 +1196,11 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, case INDEX_op_xor_i32: 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); } else { - tcg_out_modrm(s, 0x01 | (c << 3), args[2], args[0]); + tgen_arithr(s, c, args[0], args[2]); } break; case INDEX_op_mul_i32: @@ -1074,37 +1208,32 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, 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, 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, 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, args[0], args[2]); } break; case INDEX_op_mulu2_i32: - tcg_out_modrm(s, 0xf7, 4, args[3]); + tcg_out_modrm(s, OPC_GRP3_Ev, EXT3_MUL, args[3]); break; case INDEX_op_div2_i32: - tcg_out_modrm(s, 0xf7, 7, args[4]); + tcg_out_modrm(s, OPC_GRP3_Ev, EXT3_IDIV, args[4]); break; case INDEX_op_divu2_i32: - tcg_out_modrm(s, 0xf7, 6, args[4]); + tcg_out_modrm(s, OPC_GRP3_Ev, EXT3_DIV, args[4]); break; case INDEX_op_shl_i32: 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]); - } + tcg_out_shifti(s, c, args[0], args[2]); } else { - tcg_out_modrm(s, 0xd3, c, args[0]); + tcg_out_modrm(s, OPC_SHIFT_cl, c, args[0]); } break; case INDEX_op_shr_i32: @@ -1121,24 +1250,28 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, goto gen_shift32; case INDEX_op_add2_i32: - if (const_args[4]) + 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]) + } 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 - tcg_out_modrm(s, 0x01 | (ARITH_ADC << 3), args[5], args[1]); + } else { + tgen_arithr(s, ARITH_ADC, args[1], args[5]); + } break; case INDEX_op_sub2_i32: - if (const_args[4]) + 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]) + } 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 - tcg_out_modrm(s, 0x01 | (ARITH_SBB << 3), args[5], args[1]); + } else { + tgen_arithr(s, ARITH_SBB, args[1], args[5]); + } break; case INDEX_op_brcond_i32: tcg_out_brcond(s, args[2], args[0], args[1], const_args[1], @@ -1149,33 +1282,31 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, break; case INDEX_op_bswap16_i32: - tcg_out8(s, 0x66); - tcg_out_modrm(s, 0xc1, SHIFT_ROL, args[0]); - tcg_out8(s, 8); + tcg_out_rolw_8(s, args[0]); break; case INDEX_op_bswap32_i32: - tcg_out_opc(s, (0xc8 + args[0]) | P_EXT); + tcg_out_bswap32(s, args[0]); break; case INDEX_op_neg_i32: - tcg_out_modrm(s, 0xf7, 3, args[0]); + tcg_out_modrm(s, OPC_GRP3_Ev, EXT3_NEG, args[0]); break; case INDEX_op_not_i32: - tcg_out_modrm(s, 0xf7, 2, args[0]); + tcg_out_modrm(s, OPC_GRP3_Ev, EXT3_NOT, args[0]); break; case INDEX_op_ext8s_i32: - tcg_out_modrm(s, 0xbe | P_EXT, args[0], args[1]); + tcg_out_ext8s(s, args[0], args[1]); break; case INDEX_op_ext16s_i32: - tcg_out_modrm(s, 0xbf | P_EXT, args[0], args[1]); + tcg_out_ext16s(s, args[0], args[1]); break; case INDEX_op_ext8u_i32: - tcg_out_modrm(s, 0xb6 | P_EXT, args[0], args[1]); + 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]); + tcg_out_ext16u(s, args[0], args[1]); break; case INDEX_op_setcond_i32: @@ -1203,7 +1334,7 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, 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; @@ -1239,7 +1370,7 @@ 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" } }, @@ -1270,8 +1401,8 @@ 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" } }, { INDEX_op_setcond2_i32, { "r", "r", "r", "ri", "ri" } }, @@ -1312,21 +1443,11 @@ static int tcg_target_callee_save_regs[] = { TCG_REG_EDI, }; -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) { 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++) { @@ -1335,20 +1456,20 @@ void tcg_target_qemu_prologue(TCGContext *s) /* reserve some stack space */ push_size = 4 + ARRAY_SIZE(tcg_target_callee_save_regs) * 4; 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 */ - + tcg_out_modrm(s, OPC_GRP5, EXT5_JMPN_Ev, TCG_REG_EAX); /* jmp *%eax */ + /* 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--) { tcg_out_pop(s, tcg_target_callee_save_regs[i]); } - tcg_out8(s, 0xc3); /* ret */ + tcg_out_opc(s, OPC_RET); } void tcg_target_init(TCGContext *s) |