diff options
Diffstat (limited to 'tcg/i386')
| -rw-r--r-- | tcg/i386/tcg-target-con-set.h | 2 | ||||
| -rw-r--r-- | tcg/i386/tcg-target-con-str.h | 1 | ||||
| -rw-r--r-- | tcg/i386/tcg-target.c.inc | 291 | ||||
| -rw-r--r-- | tcg/i386/tcg-target.h | 9 |
4 files changed, 190 insertions, 113 deletions
diff --git a/tcg/i386/tcg-target-con-set.h b/tcg/i386/tcg-target-con-set.h index 5ea3a292f0..7d00a7dde8 100644 --- a/tcg/i386/tcg-target-con-set.h +++ b/tcg/i386/tcg-target-con-set.h @@ -33,7 +33,7 @@ C_O1_I1(r, q) C_O1_I1(r, r) C_O1_I1(x, r) C_O1_I1(x, x) -C_O1_I2(Q, 0, Q) +C_O1_I2(q, 0, qi) C_O1_I2(q, r, re) C_O1_I2(r, 0, ci) C_O1_I2(r, 0, r) diff --git a/tcg/i386/tcg-target-con-str.h b/tcg/i386/tcg-target-con-str.h index 24e6bcb80d..95a30e58cd 100644 --- a/tcg/i386/tcg-target-con-str.h +++ b/tcg/i386/tcg-target-con-str.h @@ -19,7 +19,6 @@ REGS('D', 1u << TCG_REG_EDI) REGS('r', ALL_GENERAL_REGS) REGS('x', ALL_VECTOR_REGS) REGS('q', ALL_BYTEL_REGS) /* regs that can be used as a byte operand */ -REGS('Q', ALL_BYTEH_REGS) /* regs with a second byte (e.g. %ah) */ REGS('L', ALL_GENERAL_REGS & ~SOFTMMU_RESERVE_REGS) /* qemu_ld/st */ REGS('s', ALL_BYTEL_REGS & ~SOFTMMU_RESERVE_REGS) /* qemu_st8_i32 data */ diff --git a/tcg/i386/tcg-target.c.inc b/tcg/i386/tcg-target.c.inc index a6b2eae995..0c3d1e4cef 100644 --- a/tcg/i386/tcg-target.c.inc +++ b/tcg/i386/tcg-target.c.inc @@ -144,7 +144,6 @@ static TCGReg tcg_target_call_oarg_reg(TCGCallReturnKind kind, int slot) # define TCG_REG_L1 TCG_REG_EDX #endif -#define ALL_BYTEH_REGS 0x0000000fu #if TCG_TARGET_REG_BITS == 64 # define ALL_GENERAL_REGS 0x0000ffffu # define ALL_VECTOR_REGS 0xffff0000u @@ -152,7 +151,7 @@ static TCGReg tcg_target_call_oarg_reg(TCGCallReturnKind kind, int slot) #else # define ALL_GENERAL_REGS 0x000000ffu # define ALL_VECTOR_REGS 0x00ff0000u -# define ALL_BYTEL_REGS ALL_BYTEH_REGS +# define ALL_BYTEL_REGS 0x0000000fu #endif #ifdef CONFIG_SOFTMMU # define SOFTMMU_RESERVE_REGS ((1 << TCG_REG_L0) | (1 << TCG_REG_L1)) @@ -277,6 +276,7 @@ static bool tcg_target_const_match(int64_t val, TCGType type, int ct) #define OPC_MOVL_GvEv (0x8b) /* loads, more or less */ #define OPC_MOVB_EvIz (0xc6) #define OPC_MOVL_EvIz (0xc7) +#define OPC_MOVB_Ib (0xb0) #define OPC_MOVL_Iv (0xb8) #define OPC_MOVBE_GyMy (0xf0 | P_EXT38) #define OPC_MOVBE_MyGy (0xf1 | P_EXT38) @@ -1436,99 +1436,89 @@ static void tcg_out_cmp(TCGContext *s, TCGArg arg1, TCGArg arg2, } } -static void tcg_out_brcond32(TCGContext *s, TCGCond cond, - TCGArg arg1, TCGArg arg2, int const_arg2, - TCGLabel *label, int small) +static void tcg_out_brcond(TCGContext *s, int rexw, TCGCond cond, + TCGArg arg1, TCGArg arg2, int const_arg2, + TCGLabel *label, bool small) { - tcg_out_cmp(s, arg1, arg2, const_arg2, 0); + tcg_out_cmp(s, arg1, arg2, const_arg2, rexw); tcg_out_jxx(s, tcg_cond_to_jcc[cond], label, small); } -#if TCG_TARGET_REG_BITS == 64 -static void tcg_out_brcond64(TCGContext *s, TCGCond cond, - TCGArg arg1, TCGArg arg2, int const_arg2, - TCGLabel *label, int small) -{ - tcg_out_cmp(s, arg1, arg2, const_arg2, P_REXW); - tcg_out_jxx(s, tcg_cond_to_jcc[cond], label, small); -} -#else -/* XXX: we implement it at the target level to avoid having to - handle cross basic blocks temporaries */ +#if TCG_TARGET_REG_BITS == 32 static void tcg_out_brcond2(TCGContext *s, const TCGArg *args, - const int *const_args, int small) + const int *const_args, bool small) { TCGLabel *label_next = gen_new_label(); TCGLabel *label_this = arg_label(args[5]); switch(args[4]) { case TCG_COND_EQ: - 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], - label_this, small); + tcg_out_brcond(s, 0, TCG_COND_NE, args[0], args[2], const_args[2], + label_next, 1); + tcg_out_brcond(s, 0, TCG_COND_EQ, args[1], args[3], const_args[3], + label_this, small); break; case TCG_COND_NE: - tcg_out_brcond32(s, TCG_COND_NE, args[0], args[2], const_args[2], - label_this, small); - tcg_out_brcond32(s, TCG_COND_NE, args[1], args[3], const_args[3], - label_this, small); + tcg_out_brcond(s, 0, TCG_COND_NE, args[0], args[2], const_args[2], + label_this, small); + tcg_out_brcond(s, 0, TCG_COND_NE, args[1], args[3], const_args[3], + label_this, small); break; case TCG_COND_LT: - tcg_out_brcond32(s, TCG_COND_LT, args[1], args[3], const_args[3], - label_this, small); + tcg_out_brcond(s, 0, TCG_COND_LT, args[1], args[3], const_args[3], + label_this, small); tcg_out_jxx(s, JCC_JNE, label_next, 1); - tcg_out_brcond32(s, TCG_COND_LTU, args[0], args[2], const_args[2], - label_this, small); + tcg_out_brcond(s, 0, TCG_COND_LTU, args[0], args[2], const_args[2], + label_this, small); break; case TCG_COND_LE: - tcg_out_brcond32(s, TCG_COND_LT, args[1], args[3], const_args[3], - label_this, small); + tcg_out_brcond(s, 0, TCG_COND_LT, args[1], args[3], const_args[3], + label_this, small); tcg_out_jxx(s, JCC_JNE, label_next, 1); - tcg_out_brcond32(s, TCG_COND_LEU, args[0], args[2], const_args[2], - label_this, small); + tcg_out_brcond(s, 0, TCG_COND_LEU, args[0], args[2], const_args[2], + label_this, small); break; case TCG_COND_GT: - tcg_out_brcond32(s, TCG_COND_GT, args[1], args[3], const_args[3], - label_this, small); + tcg_out_brcond(s, 0, TCG_COND_GT, args[1], args[3], const_args[3], + label_this, small); tcg_out_jxx(s, JCC_JNE, label_next, 1); - tcg_out_brcond32(s, TCG_COND_GTU, args[0], args[2], const_args[2], - label_this, small); + tcg_out_brcond(s, 0, TCG_COND_GTU, args[0], args[2], const_args[2], + label_this, small); break; case TCG_COND_GE: - tcg_out_brcond32(s, TCG_COND_GT, args[1], args[3], const_args[3], - label_this, small); + tcg_out_brcond(s, 0, TCG_COND_GT, args[1], args[3], const_args[3], + label_this, small); tcg_out_jxx(s, JCC_JNE, label_next, 1); - tcg_out_brcond32(s, TCG_COND_GEU, args[0], args[2], const_args[2], - label_this, small); + tcg_out_brcond(s, 0, TCG_COND_GEU, args[0], args[2], const_args[2], + label_this, small); break; case TCG_COND_LTU: - tcg_out_brcond32(s, TCG_COND_LTU, args[1], args[3], const_args[3], - label_this, small); + tcg_out_brcond(s, 0, TCG_COND_LTU, args[1], args[3], const_args[3], + label_this, small); tcg_out_jxx(s, JCC_JNE, label_next, 1); - tcg_out_brcond32(s, TCG_COND_LTU, args[0], args[2], const_args[2], - label_this, small); + tcg_out_brcond(s, 0, TCG_COND_LTU, args[0], args[2], const_args[2], + label_this, small); break; case TCG_COND_LEU: - tcg_out_brcond32(s, TCG_COND_LTU, args[1], args[3], const_args[3], - label_this, small); + tcg_out_brcond(s, 0, TCG_COND_LTU, args[1], args[3], const_args[3], + label_this, small); tcg_out_jxx(s, JCC_JNE, label_next, 1); - tcg_out_brcond32(s, TCG_COND_LEU, args[0], args[2], const_args[2], - label_this, small); + tcg_out_brcond(s, 0, TCG_COND_LEU, args[0], args[2], const_args[2], + label_this, small); break; case TCG_COND_GTU: - tcg_out_brcond32(s, TCG_COND_GTU, args[1], args[3], const_args[3], - label_this, small); + tcg_out_brcond(s, 0, TCG_COND_GTU, args[1], args[3], const_args[3], + label_this, small); tcg_out_jxx(s, JCC_JNE, label_next, 1); - tcg_out_brcond32(s, TCG_COND_GTU, args[0], args[2], const_args[2], - label_this, small); + tcg_out_brcond(s, 0, TCG_COND_GTU, args[0], args[2], const_args[2], + label_this, small); break; case TCG_COND_GEU: - tcg_out_brcond32(s, TCG_COND_GTU, args[1], args[3], const_args[3], - label_this, small); + tcg_out_brcond(s, 0, TCG_COND_GTU, args[1], args[3], const_args[3], + label_this, small); tcg_out_jxx(s, JCC_JNE, label_next, 1); - tcg_out_brcond32(s, TCG_COND_GEU, args[0], args[2], const_args[2], - label_this, small); + tcg_out_brcond(s, 0, TCG_COND_GEU, args[0], args[2], const_args[2], + label_this, small); break; default: g_assert_not_reached(); @@ -1537,23 +1527,107 @@ static void tcg_out_brcond2(TCGContext *s, const TCGArg *args, } #endif -static void tcg_out_setcond32(TCGContext *s, TCGCond cond, TCGArg dest, - TCGArg arg1, TCGArg arg2, int const_arg2) +static void tcg_out_setcond(TCGContext *s, int rexw, TCGCond cond, + TCGArg dest, TCGArg arg1, TCGArg arg2, + int const_arg2, bool neg) { - 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); -} + bool inv = false; + bool cleared; -#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); + switch (cond) { + case TCG_COND_NE: + inv = true; + /* fall through */ + case TCG_COND_EQ: + /* If arg2 is 0, convert to LTU/GEU vs 1. */ + if (const_arg2 && arg2 == 0) { + arg2 = 1; + goto do_ltu; + } + break; + + case TCG_COND_LEU: + inv = true; + /* fall through */ + case TCG_COND_GTU: + /* If arg2 is a register, swap for LTU/GEU. */ + if (!const_arg2) { + TCGReg t = arg1; + arg1 = arg2; + arg2 = t; + goto do_ltu; + } + break; + + case TCG_COND_GEU: + inv = true; + /* fall through */ + case TCG_COND_LTU: + do_ltu: + /* + * Relying on the carry bit, use SBB to produce -1 if LTU, 0 if GEU. + * We can then use NEG or INC to produce the desired result. + * This is always smaller than the SETCC expansion. + */ + tcg_out_cmp(s, arg1, arg2, const_arg2, rexw); + + /* X - X - C = -C = (C ? -1 : 0) */ + tgen_arithr(s, ARITH_SBB + (neg ? rexw : 0), dest, dest); + if (inv && neg) { + /* ~(C ? -1 : 0) = (C ? 0 : -1) */ + tcg_out_modrm(s, OPC_GRP3_Ev + rexw, EXT3_NOT, dest); + } else if (inv) { + /* (C ? -1 : 0) + 1 = (C ? 0 : 1) */ + tgen_arithi(s, ARITH_ADD, dest, 1, 0); + } else if (!neg) { + /* -(C ? -1 : 0) = (C ? 1 : 0) */ + tcg_out_modrm(s, OPC_GRP3_Ev, EXT3_NEG, dest); + } + return; + + case TCG_COND_GE: + inv = true; + /* fall through */ + case TCG_COND_LT: + /* If arg2 is 0, extract the sign bit. */ + if (const_arg2 && arg2 == 0) { + tcg_out_mov(s, rexw ? TCG_TYPE_I64 : TCG_TYPE_I32, dest, arg1); + if (inv) { + tcg_out_modrm(s, OPC_GRP3_Ev + rexw, EXT3_NOT, dest); + } + tcg_out_shifti(s, (neg ? SHIFT_SAR : SHIFT_SHR) + rexw, + dest, rexw ? 63 : 31); + return; + } + break; + + default: + break; + } + + /* + * If dest does not overlap the inputs, clearing it first is preferred. + * The XOR breaks any false dependency for the low-byte write to dest, + * and is also one byte smaller than MOVZBL. + */ + cleared = false; + if (dest != arg1 && (const_arg2 || dest != arg2)) { + tgen_arithr(s, ARITH_XOR, dest, dest); + cleared = true; + } + + tcg_out_cmp(s, arg1, arg2, const_arg2, rexw); tcg_out_modrm(s, OPC_SETCC | tcg_cond_to_jcc[cond], 0, dest); - tcg_out_ext8u(s, dest, dest); + + if (!cleared) { + tcg_out_ext8u(s, dest, dest); + } + if (neg) { + tcg_out_modrm(s, OPC_GRP3_Ev + rexw, EXT3_NEG, dest); + } } -#else + +#if TCG_TARGET_REG_BITS == 32 static void tcg_out_setcond2(TCGContext *s, const TCGArg *args, const int *const_args) { @@ -1610,23 +1684,13 @@ static void tcg_out_cmov(TCGContext *s, TCGCond cond, int rexw, } } -static void tcg_out_movcond32(TCGContext *s, TCGCond cond, TCGReg dest, - TCGReg c1, TCGArg c2, int const_c2, - TCGReg v1) -{ - tcg_out_cmp(s, c1, c2, const_c2, 0); - tcg_out_cmov(s, cond, 0, dest, v1); -} - -#if TCG_TARGET_REG_BITS == 64 -static void tcg_out_movcond64(TCGContext *s, TCGCond cond, TCGReg dest, - TCGReg c1, TCGArg c2, int const_c2, - TCGReg v1) +static void tcg_out_movcond(TCGContext *s, int rexw, TCGCond cond, + TCGReg dest, TCGReg c1, TCGArg c2, int const_c2, + TCGReg v1) { - tcg_out_cmp(s, c1, c2, const_c2, P_REXW); - tcg_out_cmov(s, cond, P_REXW, dest, v1); + tcg_out_cmp(s, c1, c2, const_c2, rexw); + tcg_out_cmov(s, cond, rexw, dest, v1); } -#endif static void tcg_out_ctz(TCGContext *s, int rexw, TCGReg dest, TCGReg arg1, TCGArg arg2, bool const_a2) @@ -2574,14 +2638,18 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, tcg_out_modrm(s, OPC_POPCNT + rexw, a0, a1); break; - case INDEX_op_brcond_i32: - tcg_out_brcond32(s, a2, a0, a1, const_args[1], arg_label(args[3]), 0); + OP_32_64(brcond): + tcg_out_brcond(s, rexw, a2, a0, a1, const_args[1], + arg_label(args[3]), 0); break; - case INDEX_op_setcond_i32: - tcg_out_setcond32(s, args[3], a0, a1, a2, const_a2); + OP_32_64(setcond): + tcg_out_setcond(s, rexw, args[3], a0, a1, a2, const_a2, false); break; - case INDEX_op_movcond_i32: - tcg_out_movcond32(s, args[5], a0, a1, a2, const_a2, args[3]); + OP_32_64(negsetcond): + tcg_out_setcond(s, rexw, args[3], a0, a1, a2, const_a2, true); + break; + OP_32_64(movcond): + tcg_out_movcond(s, rexw, args[5], a0, a1, a2, const_a2, args[3]); break; OP_32_64(bswap16): @@ -2730,16 +2798,6 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, } break; - case INDEX_op_brcond_i64: - tcg_out_brcond64(s, a2, a0, a1, const_args[1], arg_label(args[3]), 0); - break; - case INDEX_op_setcond_i64: - tcg_out_setcond64(s, args[3], a0, a1, a2, const_a2); - break; - case INDEX_op_movcond_i64: - tcg_out_movcond64(s, args[5], a0, a1, a2, const_a2, args[3]); - break; - case INDEX_op_bswap64_i64: tcg_out_bswap64(s, a0); break; @@ -2751,13 +2809,30 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, OP_32_64(deposit): if (args[3] == 0 && args[4] == 8) { /* load bits 0..7 */ - tcg_out_modrm(s, OPC_MOVB_EvGv | P_REXB_R | P_REXB_RM, a2, a0); - } else if (args[3] == 8 && args[4] == 8) { + if (const_a2) { + tcg_out_opc(s, OPC_MOVB_Ib | P_REXB_RM | LOWREGMASK(a0), + 0, a0, 0); + tcg_out8(s, a2); + } else { + tcg_out_modrm(s, OPC_MOVB_EvGv | P_REXB_R | P_REXB_RM, a2, a0); + } + } else if (TCG_TARGET_REG_BITS == 32 && args[3] == 8 && args[4] == 8) { /* load bits 8..15 */ - tcg_out_modrm(s, OPC_MOVB_EvGv, a2, a0 + 4); + if (const_a2) { + tcg_out8(s, OPC_MOVB_Ib + a0 + 4); + tcg_out8(s, a2); + } else { + tcg_out_modrm(s, OPC_MOVB_EvGv, a2, a0 + 4); + } } else if (args[3] == 0 && args[4] == 16) { /* load bits 0..15 */ - tcg_out_modrm(s, OPC_MOVL_EvGv | P_DATA16, a2, a0); + if (const_a2) { + tcg_out_opc(s, OPC_MOVL_Iv | P_DATA16 | LOWREGMASK(a0), + 0, a0, 0); + tcg_out16(s, a2); + } else { + tcg_out_modrm(s, OPC_MOVL_EvGv | P_DATA16, a2, a0); + } } else { g_assert_not_reached(); } @@ -3312,10 +3387,12 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op) case INDEX_op_deposit_i32: case INDEX_op_deposit_i64: - return C_O1_I2(Q, 0, Q); + return C_O1_I2(q, 0, qi); case INDEX_op_setcond_i32: case INDEX_op_setcond_i64: + case INDEX_op_negsetcond_i32: + case INDEX_op_negsetcond_i64: return C_O1_I2(q, r, re); case INDEX_op_movcond_i32: diff --git a/tcg/i386/tcg-target.h b/tcg/i386/tcg-target.h index 2a2e3fffa8..8417ea4899 100644 --- a/tcg/i386/tcg-target.h +++ b/tcg/i386/tcg-target.h @@ -150,6 +150,7 @@ typedef enum { #define TCG_TARGET_HAS_sextract_i32 1 #define TCG_TARGET_HAS_extract2_i32 1 #define TCG_TARGET_HAS_movcond_i32 1 +#define TCG_TARGET_HAS_negsetcond_i32 1 #define TCG_TARGET_HAS_add2_i32 1 #define TCG_TARGET_HAS_sub2_i32 1 #define TCG_TARGET_HAS_mulu2_i32 1 @@ -159,8 +160,7 @@ typedef enum { #if TCG_TARGET_REG_BITS == 64 /* Keep 32-bit values zero-extended in a register. */ -#define TCG_TARGET_HAS_extrl_i64_i32 1 -#define TCG_TARGET_HAS_extrh_i64_i32 1 +#define TCG_TARGET_HAS_extr_i64_i32 1 #define TCG_TARGET_HAS_div2_i64 1 #define TCG_TARGET_HAS_rot_i64 1 #define TCG_TARGET_HAS_ext8s_i64 1 @@ -187,6 +187,7 @@ typedef enum { #define TCG_TARGET_HAS_sextract_i64 0 #define TCG_TARGET_HAS_extract2_i64 1 #define TCG_TARGET_HAS_movcond_i64 1 +#define TCG_TARGET_HAS_negsetcond_i64 1 #define TCG_TARGET_HAS_add2_i64 1 #define TCG_TARGET_HAS_sub2_i64 1 #define TCG_TARGET_HAS_mulu2_i64 1 @@ -227,8 +228,8 @@ typedef enum { #define TCG_TARGET_HAS_cmpsel_vec -1 #define TCG_TARGET_deposit_i32_valid(ofs, len) \ - (((ofs) == 0 && (len) == 8) || ((ofs) == 8 && (len) == 8) || \ - ((ofs) == 0 && (len) == 16)) + (((ofs) == 0 && ((len) == 8 || (len) == 16)) || \ + (TCG_TARGET_REG_BITS == 32 && (ofs) == 8 && (len) == 8)) #define TCG_TARGET_deposit_i64_valid TCG_TARGET_deposit_i32_valid /* Check for the possibility of high-byte extraction and, for 64-bit, |