#define TCG_CT_CONST_S32 0x400
#define TCG_CT_CONST_U32 0x800
#define TCG_CT_CONST_ZERO 0x1000
+#define TCG_CT_CONST_MONE 0x2000
static uint8_t *tb_ret_addr;
#define GUEST_BASE 0
#endif
+#ifdef CONFIG_GETAUXVAL
+#include <sys/auxv.h>
+static bool have_isa_2_06;
+#define HAVE_ISA_2_06 have_isa_2_06
+#define HAVE_ISEL have_isa_2_06
+#else
#define HAVE_ISA_2_06 0
+#define HAVE_ISEL 0
+#endif
#ifdef CONFIG_USE_GUEST_BASE
#define TCG_GUEST_BASE_REG 30
case 'J':
ct->ct |= TCG_CT_CONST_U16;
break;
+ case 'M':
+ ct->ct |= TCG_CT_CONST_MONE;
+ break;
case 'T':
ct->ct |= TCG_CT_CONST_S32;
break;
return 1;
} else if ((ct & TCG_CT_CONST_ZERO) && val == 0) {
return 1;
+ } else if ((ct & TCG_CT_CONST_MONE) && val == -1) {
+ return 1;
}
return 0;
}
#define OPCD(opc) ((opc)<<26)
#define XO19(opc) (OPCD(19)|((opc)<<1))
-#define XO30(opc) (OPCD(30)|((opc)<<2))
+#define MD30(opc) (OPCD(30)|((opc)<<2))
+#define MDS30(opc) (OPCD(30)|((opc)<<1))
#define XO31(opc) (OPCD(31)|((opc)<<1))
#define XO58(opc) (OPCD(58)|(opc))
#define XO62(opc) (OPCD(62)|(opc))
#define RLWINM OPCD( 21)
#define RLWNM OPCD( 23)
-#define RLDICL XO30( 0)
-#define RLDICR XO30( 1)
-#define RLDIMI XO30( 3)
-#define RLDCL XO30( 8)
+#define RLDICL MD30( 0)
+#define RLDICR MD30( 1)
+#define RLDIMI MD30( 3)
+#define RLDCL MDS30( 8)
#define BCLR XO19( 16)
#define BCCTR XO19(528)
#define EXTSW XO31(986)
#define ADD XO31(266)
#define ADDE XO31(138)
+#define ADDME XO31(234)
+#define ADDZE XO31(202)
#define ADDC XO31( 10)
#define AND XO31( 28)
#define SUBF XO31( 40)
#define SUBFC XO31( 8)
#define SUBFE XO31(136)
+#define SUBFME XO31(232)
+#define SUBFZE XO31(200)
#define OR XO31(444)
#define XOR XO31(316)
#define MULLW XO31(235)
#define SRAWI XO31(824)
#define NEG XO31(104)
#define MFCR XO31( 19)
+#define MFOCRF (MFCR | (1u << 20))
#define NOR XO31(124)
#define CNTLZW XO31( 26)
#define CNTLZD XO31( 58)
#define ORC XO31(412)
#define EQV XO31(284)
#define NAND XO31(476)
+#define ISEL XO31( 15)
#define MULLD XO31(233)
#define MULHD XO31( 73)
#define ME(e) ((e)<<1)
#define BO(o) ((o)<<21)
#define MB64(b) ((b)<<5)
+#define FXM(b) (1 << (19 - (b)))
#define LK 1
#define BT(n, c) (((c)+((n)*4))<<21)
#define BA(n, c) (((c)+((n)*4))<<16)
#define BB(n, c) (((c)+((n)*4))<<11)
+#define BC_(n, c) (((c)+((n)*4))<<6)
#define BO_COND_TRUE BO (12)
#define BO_COND_FALSE BO ( 4)
[TCG_COND_GTU] = BC | BI (7, CR_GT) | BO_COND_TRUE,
};
+/* The low bit here is set if the RA and RB fields must be inverted. */
+static const uint32_t tcg_to_isel[] = {
+ [TCG_COND_EQ] = ISEL | BC_(7, CR_EQ),
+ [TCG_COND_NE] = ISEL | BC_(7, CR_EQ) | 1,
+ [TCG_COND_LT] = ISEL | BC_(7, CR_LT),
+ [TCG_COND_GE] = ISEL | BC_(7, CR_LT) | 1,
+ [TCG_COND_LE] = ISEL | BC_(7, CR_GT) | 1,
+ [TCG_COND_GT] = ISEL | BC_(7, CR_GT),
+ [TCG_COND_LTU] = ISEL | BC_(7, CR_LT),
+ [TCG_COND_GEU] = ISEL | BC_(7, CR_LT) | 1,
+ [TCG_COND_LEU] = ISEL | BC_(7, CR_GT) | 1,
+ [TCG_COND_GTU] = ISEL | BC_(7, CR_GT),
+};
+
static inline void tcg_out_mov(TCGContext *s, TCGType type,
TCGReg ret, TCGReg arg)
{
int imm;
uint32_t op;
+ /* Simplify the comparisons below wrt CMPI. */
+ if (type == TCG_TYPE_I32) {
+ arg2 = (int32_t)arg2;
+ }
+
switch (cond) {
case TCG_COND_EQ:
case TCG_COND_NE:
}
}
-static void tcg_out_setcond (TCGContext *s, TCGType type, TCGCond cond,
- TCGArg arg0, TCGArg arg1, TCGArg arg2,
- int const_arg2)
+static void tcg_out_setcond_eq0(TCGContext *s, TCGType type,
+ TCGReg dst, TCGReg src)
{
- int crop, sh, arg;
+ tcg_out32(s, (type == TCG_TYPE_I64 ? CNTLZD : CNTLZW) | RS(src) | RA(dst));
+ tcg_out_shri64(s, dst, dst, type == TCG_TYPE_I64 ? 6 : 5);
+}
- switch (cond) {
- case TCG_COND_EQ:
- if (const_arg2) {
- if (!arg2) {
- arg = arg1;
- }
- else {
- arg = 0;
- if ((uint16_t) arg2 == arg2) {
- tcg_out32(s, XORI | SAI(arg1, 0, arg2));
- }
- else {
- tcg_out_movi (s, type, 0, arg2);
- tcg_out32 (s, XOR | SAB (arg1, 0, 0));
- }
- }
- }
- else {
- arg = 0;
- tcg_out32 (s, XOR | SAB (arg1, 0, arg2));
- }
+static void tcg_out_setcond_ne0(TCGContext *s, TCGReg dst, TCGReg src)
+{
+ /* X != 0 implies X + -1 generates a carry. Extra addition
+ trickery means: R = X-1 + ~X + C = X-1 + (-X+1) + C = C. */
+ if (dst != src) {
+ tcg_out32(s, ADDIC | TAI(dst, src, -1));
+ tcg_out32(s, SUBFE | TAB(dst, dst, src));
+ } else {
+ tcg_out32(s, ADDIC | TAI(0, src, -1));
+ tcg_out32(s, SUBFE | TAB(dst, 0, src));
+ }
+}
- if (type == TCG_TYPE_I64) {
- tcg_out32 (s, CNTLZD | RS (arg) | RA (0));
- tcg_out_rld (s, RLDICL, arg0, 0, 58, 6);
- }
- else {
- tcg_out32 (s, CNTLZW | RS (arg) | RA (0));
- tcg_out_rlw(s, RLWINM, arg0, 0, 27, 5, 31);
+static TCGReg tcg_gen_setcond_xor(TCGContext *s, TCGReg arg1, TCGArg arg2,
+ bool const_arg2)
+{
+ if (const_arg2) {
+ if ((uint32_t)arg2 == arg2) {
+ tcg_out_xori32(s, TCG_REG_R0, arg1, arg2);
+ } else {
+ tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_R0, arg2);
+ tcg_out32(s, XOR | SAB(arg1, TCG_REG_R0, TCG_REG_R0));
}
- break;
+ } else {
+ tcg_out32(s, XOR | SAB(arg1, TCG_REG_R0, arg2));
+ }
+ return TCG_REG_R0;
+}
- case TCG_COND_NE:
- if (const_arg2) {
- if (!arg2) {
- arg = arg1;
- }
- else {
- arg = 0;
- if ((uint16_t) arg2 == arg2) {
- tcg_out32(s, XORI | SAI(arg1, 0, arg2));
- } else {
- tcg_out_movi (s, type, 0, arg2);
- tcg_out32 (s, XOR | SAB (arg1, 0, 0));
- }
+static void tcg_out_setcond(TCGContext *s, TCGType type, TCGCond cond,
+ TCGArg arg0, TCGArg arg1, TCGArg arg2,
+ int const_arg2)
+{
+ int crop, sh;
+
+ /* Ignore high bits of a potential constant arg2. */
+ if (type == TCG_TYPE_I32) {
+ arg2 = (uint32_t)arg2;
+ }
+
+ /* Handle common and trivial cases before handling anything else. */
+ if (arg2 == 0) {
+ switch (cond) {
+ case TCG_COND_EQ:
+ tcg_out_setcond_eq0(s, type, arg0, arg1);
+ return;
+ case TCG_COND_NE:
+ if (type == TCG_TYPE_I32) {
+ tcg_out_ext32u(s, TCG_REG_R0, arg1);
+ arg1 = TCG_REG_R0;
}
+ tcg_out_setcond_ne0(s, arg0, arg1);
+ return;
+ case TCG_COND_GE:
+ tcg_out32(s, NOR | SAB(arg1, arg0, arg1));
+ arg1 = arg0;
+ /* FALLTHRU */
+ case TCG_COND_LT:
+ /* Extract the sign bit. */
+ tcg_out_rld(s, RLDICL, arg0, arg1,
+ type == TCG_TYPE_I64 ? 1 : 33, 63);
+ return;
+ default:
+ break;
}
- else {
- arg = 0;
- tcg_out32 (s, XOR | SAB (arg1, 0, arg2));
- }
+ }
- /* Make sure and discard the high 32-bits of the input. */
- if (type == TCG_TYPE_I32) {
- tcg_out32(s, EXTSW | RA(TCG_REG_R0) | RS(arg));
- arg = TCG_REG_R0;
- }
+ /* If we have ISEL, we can implement everything with 3 or 4 insns.
+ All other cases below are also at least 3 insns, so speed up the
+ code generator by not considering them and always using ISEL. */
+ if (HAVE_ISEL) {
+ int isel, tab;
+
+ tcg_out_cmp(s, cond, arg1, arg2, const_arg2, 7, type);
+
+ isel = tcg_to_isel[cond];
- if (arg == arg1 && arg1 == arg0) {
- tcg_out32(s, ADDIC | TAI(0, arg, -1));
- tcg_out32(s, SUBFE | TAB(arg0, 0, arg));
+ tcg_out_movi(s, type, arg0, 1);
+ if (isel & 1) {
+ /* arg0 = (bc ? 0 : 1) */
+ tab = TAB(arg0, 0, arg0);
+ isel &= ~1;
+ } else {
+ /* arg0 = (bc ? 1 : 0) */
+ tcg_out_movi(s, type, TCG_REG_R0, 0);
+ tab = TAB(arg0, arg0, TCG_REG_R0);
}
- else {
- tcg_out32(s, ADDIC | TAI(arg0, arg, -1));
- tcg_out32(s, SUBFE | TAB(arg0, arg0, arg));
+ tcg_out32(s, isel | tab);
+ return;
+ }
+
+ switch (cond) {
+ case TCG_COND_EQ:
+ arg1 = tcg_gen_setcond_xor(s, arg1, arg2, const_arg2);
+ tcg_out_setcond_eq0(s, type, arg0, arg1);
+ return;
+
+ case TCG_COND_NE:
+ arg1 = tcg_gen_setcond_xor(s, arg1, arg2, const_arg2);
+ /* Discard the high bits only once, rather than both inputs. */
+ if (type == TCG_TYPE_I32) {
+ tcg_out_ext32u(s, TCG_REG_R0, arg1);
+ arg1 = TCG_REG_R0;
}
- break;
+ tcg_out_setcond_ne0(s, arg0, arg1);
+ return;
case TCG_COND_GT:
case TCG_COND_GTU:
sh = 31;
crop = CRNOR | BT (7, CR_EQ) | BA (7, CR_GT) | BB (7, CR_GT);
crtest:
- tcg_out_cmp (s, cond, arg1, arg2, const_arg2, 7, type);
- if (crop) tcg_out32 (s, crop);
- tcg_out32 (s, MFCR | RT (0));
- tcg_out_rlw(s, RLWINM, arg0, 0, sh, 31, 31);
+ tcg_out_cmp(s, cond, arg1, arg2, const_arg2, 7, type);
+ if (crop) {
+ tcg_out32(s, crop);
+ }
+ tcg_out32(s, MFOCRF | RT(TCG_REG_R0) | FXM(7));
+ tcg_out_rlw(s, RLWINM, arg0, TCG_REG_R0, sh, 31, 31);
break;
default:
tcg_out_bc(s, tcg_to_bc[cond], label_index);
}
+static void tcg_out_movcond(TCGContext *s, TCGType type, TCGCond cond,
+ TCGArg dest, TCGArg c1, TCGArg c2, TCGArg v1,
+ TCGArg v2, bool const_c2)
+{
+ /* If for some reason both inputs are zero, don't produce bad code. */
+ if (v1 == 0 && v2 == 0) {
+ tcg_out_movi(s, type, dest, 0);
+ return;
+ }
+
+ tcg_out_cmp(s, cond, c1, c2, const_c2, 7, type);
+
+ if (HAVE_ISEL) {
+ int isel = tcg_to_isel[cond];
+
+ /* Swap the V operands if the operation indicates inversion. */
+ if (isel & 1) {
+ int t = v1;
+ v1 = v2;
+ v2 = t;
+ isel &= ~1;
+ }
+ /* V1 == 0 is handled by isel; V2 == 0 must be handled by hand. */
+ if (v2 == 0) {
+ tcg_out_movi(s, type, 0, 0);
+ }
+ tcg_out32(s, isel | TAB(dest, v1, v2));
+ } else {
+ if (dest == v2) {
+ cond = tcg_invert_cond(cond);
+ v2 = v1;
+ } else if (dest != v1) {
+ if (v1 == 0) {
+ tcg_out_movi(s, type, dest, 0);
+ } else {
+ tcg_out_mov(s, type, dest, v1);
+ }
+ }
+ /* Branch forward over one insn */
+ tcg_out32(s, tcg_to_bc[cond] | 8);
+ if (v2 == 0) {
+ tcg_out_movi(s, type, dest, 0);
+ } else {
+ tcg_out_mov(s, type, dest, v2);
+ }
+ }
+}
+
void ppc_tb_set_jmp_target (unsigned long jmp_addr, unsigned long addr)
{
TCGContext s;
tcg_out32 (s, DIVWU | TAB (args[0], args[1], args[2]));
break;
- case INDEX_op_rem_i32:
- tcg_out32 (s, DIVW | TAB (0, args[1], args[2]));
- tcg_out32 (s, MULLW | TAB (0, 0, args[2]));
- tcg_out32 (s, SUBF | TAB (args[0], 0, args[1]));
- break;
-
- case INDEX_op_remu_i32:
- tcg_out32 (s, DIVWU | TAB (0, args[1], args[2]));
- tcg_out32 (s, MULLW | TAB (0, 0, args[2]));
- tcg_out32 (s, SUBF | TAB (args[0], 0, args[1]));
- break;
-
case INDEX_op_shl_i32:
if (const_args[2]) {
tcg_out_rlw(s, RLWINM, args[0], args[1], args[2], 0, 31 - args[2]);
tcg_out_rlw(s, RLWINM, args[0], args[1], 32 - args[2], 0, 31);
} else {
tcg_out32(s, SUBFIC | TAI(0, args[2], 32));
- tcg_out32(s, RLWNM | SAB(args[1], args[0], args[2])
+ tcg_out32(s, RLWNM | SAB(args[1], args[0], 0)
| MB(0) | ME(31));
}
break;
case INDEX_op_divu_i64:
tcg_out32 (s, DIVDU | TAB (args[0], args[1], args[2]));
break;
- case INDEX_op_rem_i64:
- tcg_out32 (s, DIVD | TAB (0, args[1], args[2]));
- tcg_out32 (s, MULLD | TAB (0, 0, args[2]));
- tcg_out32 (s, SUBF | TAB (args[0], 0, args[1]));
- break;
- case INDEX_op_remu_i64:
- tcg_out32 (s, DIVDU | TAB (0, args[1], args[2]));
- tcg_out32 (s, MULLD | TAB (0, 0, args[2]));
- tcg_out32 (s, SUBF | TAB (args[0], 0, args[1]));
- break;
case INDEX_op_qemu_ld8u:
tcg_out_qemu_ld (s, args, 0);
if (a0 == 0) {
tcg_out_mov(s, TCG_TYPE_I64, args[0], a0);
- /* Revert the source rotate that we performed above. */
- tcg_out_rld(s, RLDICL, a1, a1, 32, 0);
}
break;
case INDEX_op_deposit_i32:
- tcg_out_rlw(s, RLWIMI, args[0], args[2], args[3],
- 32 - args[3] - args[4], 31 - args[3]);
+ if (const_args[2]) {
+ uint32_t mask = ((2u << (args[4] - 1)) - 1) << args[3];
+ tcg_out_andi32(s, args[0], args[0], ~mask);
+ } else {
+ tcg_out_rlw(s, RLWIMI, args[0], args[2], args[3],
+ 32 - args[3] - args[4], 31 - args[3]);
+ }
break;
case INDEX_op_deposit_i64:
- tcg_out_rld(s, RLDIMI, args[0], args[2], args[3],
- 64 - args[3] - args[4]);
+ if (const_args[2]) {
+ uint64_t mask = ((2ull << (args[4] - 1)) - 1) << args[3];
+ tcg_out_andi64(s, args[0], args[0], ~mask);
+ } else {
+ tcg_out_rld(s, RLDIMI, args[0], args[2], args[3],
+ 64 - args[3] - args[4]);
+ }
+ break;
+
+ case INDEX_op_movcond_i32:
+ tcg_out_movcond(s, TCG_TYPE_I32, args[5], args[0], args[1], args[2],
+ args[3], args[4], const_args[2]);
+ break;
+ case INDEX_op_movcond_i64:
+ tcg_out_movcond(s, TCG_TYPE_I64, args[5], args[0], args[1], args[2],
+ args[3], args[4], const_args[2]);
+ break;
+
+ case INDEX_op_add2_i64:
+ /* Note that the CA bit is defined based on the word size of the
+ environment. So in 64-bit mode it's always carry-out of bit 63.
+ The fallback code using deposit works just as well for 32-bit. */
+ a0 = args[0], a1 = args[1];
+ if (a0 == args[3] || (!const_args[5] && a0 == args[5])) {
+ a0 = TCG_REG_R0;
+ }
+ if (const_args[4]) {
+ tcg_out32(s, ADDIC | TAI(a0, args[2], args[4]));
+ } else {
+ tcg_out32(s, ADDC | TAB(a0, args[2], args[4]));
+ }
+ if (const_args[5]) {
+ tcg_out32(s, (args[5] ? ADDME : ADDZE) | RT(a1) | RA(args[3]));
+ } else {
+ tcg_out32(s, ADDE | TAB(a1, args[3], args[5]));
+ }
+ if (a0 != args[0]) {
+ tcg_out_mov(s, TCG_TYPE_I64, args[0], a0);
+ }
+ break;
+
+ case INDEX_op_sub2_i64:
+ a0 = args[0], a1 = args[1];
+ if (a0 == args[5] || (!const_args[4] && a0 == args[4])) {
+ a0 = TCG_REG_R0;
+ }
+ if (const_args[2]) {
+ tcg_out32(s, SUBFIC | TAI(a0, args[3], args[2]));
+ } else {
+ tcg_out32(s, SUBFC | TAB(a0, args[3], args[2]));
+ }
+ if (const_args[4]) {
+ tcg_out32(s, (args[4] ? SUBFME : SUBFZE) | RT(a1) | RA(args[5]));
+ } else {
+ tcg_out32(s, SUBFE | TAB(a1, args[5], args[4]));
+ }
+ if (a0 != args[0]) {
+ tcg_out_mov(s, TCG_TYPE_I64, args[0], a0);
+ }
+ break;
+
+ case INDEX_op_mulu2_i64:
+ case INDEX_op_muls2_i64:
+ {
+ int oph = (opc == INDEX_op_mulu2_i64 ? MULHDU : MULHD);
+ TCGReg outl = args[0], outh = args[1];
+ a0 = args[2], a1 = args[3];
+
+ if (outl == a0 || outl == a1) {
+ if (outh == a0 || outh == a1) {
+ outl = TCG_REG_R0;
+ } else {
+ tcg_out32(s, oph | TAB(outh, a0, a1));
+ oph = 0;
+ }
+ }
+ tcg_out32(s, MULLD | TAB(outl, a0, a1));
+ if (oph != 0) {
+ tcg_out32(s, oph | TAB(outh, a0, a1));
+ }
+ if (outl != args[0]) {
+ tcg_out_mov(s, TCG_TYPE_I64, args[0], outl);
+ }
+ }
break;
default:
{ INDEX_op_mul_i32, { "r", "r", "rI" } },
{ INDEX_op_div_i32, { "r", "r", "r" } },
{ INDEX_op_divu_i32, { "r", "r", "r" } },
- { INDEX_op_rem_i32, { "r", "r", "r" } },
- { INDEX_op_remu_i32, { "r", "r", "r" } },
{ INDEX_op_sub_i32, { "r", "rI", "ri" } },
{ INDEX_op_and_i32, { "r", "r", "ri" } },
{ INDEX_op_or_i32, { "r", "r", "ri" } },
{ INDEX_op_mul_i64, { "r", "r", "rI" } },
{ INDEX_op_div_i64, { "r", "r", "r" } },
{ INDEX_op_divu_i64, { "r", "r", "r" } },
- { INDEX_op_rem_i64, { "r", "r", "r" } },
- { INDEX_op_remu_i64, { "r", "r", "r" } },
{ INDEX_op_neg_i64, { "r", "r" } },
{ INDEX_op_not_i64, { "r", "r" } },
{ INDEX_op_setcond_i32, { "r", "r", "ri" } },
{ INDEX_op_setcond_i64, { "r", "r", "ri" } },
+ { INDEX_op_movcond_i32, { "r", "r", "ri", "rZ", "rZ" } },
+ { INDEX_op_movcond_i64, { "r", "r", "ri", "rZ", "rZ" } },
{ INDEX_op_bswap16_i32, { "r", "r" } },
{ INDEX_op_bswap16_i64, { "r", "r" } },
{ INDEX_op_bswap32_i64, { "r", "r" } },
{ INDEX_op_bswap64_i64, { "r", "r" } },
- { INDEX_op_deposit_i32, { "r", "0", "r" } },
- { INDEX_op_deposit_i64, { "r", "0", "r" } },
+ { INDEX_op_deposit_i32, { "r", "0", "rZ" } },
+ { INDEX_op_deposit_i64, { "r", "0", "rZ" } },
+
+ { INDEX_op_add2_i64, { "r", "r", "r", "r", "rI", "rZM" } },
+ { INDEX_op_sub2_i64, { "r", "r", "rI", "r", "rZM", "r" } },
+ { INDEX_op_muls2_i64, { "r", "r", "r", "r" } },
+ { INDEX_op_mulu2_i64, { "r", "r", "r", "r" } },
{ -1 },
};
static void tcg_target_init (TCGContext *s)
{
+#ifdef CONFIG_GETAUXVAL
+ unsigned long hwcap = getauxval(AT_HWCAP);
+ if (hwcap & PPC_FEATURE_ARCH_2_06) {
+ have_isa_2_06 = true;
+ }
+#endif
+
tcg_regset_set32 (tcg_target_available_regs[TCG_TYPE_I32], 0, 0xffffffff);
tcg_regset_set32 (tcg_target_available_regs[TCG_TYPE_I64], 0, 0xffffffff);
tcg_regset_set32 (tcg_target_call_clobber_regs, 0,