SYS-OSS/FRET-qemu
4
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
FRET-qemu/tcg/mips/tcg-target.c.inc
Richard Henderson d0a9bb5ecb tcg: Add tlb_fast_offset to TCGContext 
Disconnect the layout of ArchCPU from TCG compilation.
Pass the relative offset of 'env' and 'neg.tlb.f' as a parameter.

Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2023-06-05 12:04:28 -07:00

2716 lines
82 KiB
C++
Raw Blame History

/*
* Tiny Code Generator for QEMU
*
* Copyright (c) 2008-2009 Arnaud Patard <arnaud.patard@rtp-net.org>
* Copyright (c) 2009 Aurelien Jarno <aurelien@aurel32.net>
* Based on i386/tcg-target.c - Copyright (c) 2008 Fabrice Bellard
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "../tcg-ldst.c.inc"
#include "../tcg-pool.c.inc"
#if TCG_TARGET_REG_BITS == 32
# define LO_OFF (HOST_BIG_ENDIAN * 4)
# define HI_OFF (4 - LO_OFF)
#else
/* Assert at compile-time that these values are never used for 64-bit. */
# define LO_OFF ({ qemu_build_not_reached(); 0; })
# define HI_OFF ({ qemu_build_not_reached(); 0; })
#endif
#ifdef CONFIG_DEBUG_TCG
static const char * const tcg_target_reg_names[TCG_TARGET_NB_REGS] = {
"zero",
"at",
"v0",
"v1",
"a0",
"a1",
"a2",
"a3",
"t0",
"t1",
"t2",
"t3",
"t4",
"t5",
"t6",
"t7",
"s0",
"s1",
"s2",
"s3",
"s4",
"s5",
"s6",
"s7",
"t8",
"t9",
"k0",
"k1",
"gp",
"sp",
"s8",
"ra",
};
#endif
#define TCG_TMP0 TCG_REG_AT
#define TCG_TMP1 TCG_REG_T9
#define TCG_TMP2 TCG_REG_T8
#define TCG_TMP3 TCG_REG_T7
#ifndef CONFIG_SOFTMMU
#define TCG_GUEST_BASE_REG TCG_REG_S7
#endif
#if TCG_TARGET_REG_BITS == 64
#define TCG_REG_TB TCG_REG_S6
#else
#define TCG_REG_TB (qemu_build_not_reached(), TCG_REG_ZERO)
#endif
/* check if we really need so many registers :P */
static const int tcg_target_reg_alloc_order[] = {
/* Call saved registers. */
TCG_REG_S0,
TCG_REG_S1,
TCG_REG_S2,
TCG_REG_S3,
TCG_REG_S4,
TCG_REG_S5,
TCG_REG_S6,
TCG_REG_S7,
TCG_REG_S8,
/* Call clobbered registers. */
TCG_REG_T4,
TCG_REG_T5,
TCG_REG_T6,
TCG_REG_T7,
TCG_REG_T8,
TCG_REG_T9,
TCG_REG_V1,
TCG_REG_V0,
/* Argument registers, opposite order of allocation. */
TCG_REG_T3,
TCG_REG_T2,
TCG_REG_T1,
TCG_REG_T0,
TCG_REG_A3,
TCG_REG_A2,
TCG_REG_A1,
TCG_REG_A0,
};
static const TCGReg tcg_target_call_iarg_regs[] = {
TCG_REG_A0,
TCG_REG_A1,
TCG_REG_A2,
TCG_REG_A3,
#if _MIPS_SIM == _ABIN32 || _MIPS_SIM == _ABI64
TCG_REG_T0,
TCG_REG_T1,
TCG_REG_T2,
TCG_REG_T3,
#endif
};
static TCGReg tcg_target_call_oarg_reg(TCGCallReturnKind kind, int slot)
{
tcg_debug_assert(kind == TCG_CALL_RET_NORMAL);
tcg_debug_assert(slot >= 0 && slot <= 1);
return TCG_REG_V0 + slot;
}
static const tcg_insn_unit *tb_ret_addr;
static const tcg_insn_unit *bswap32_addr;
static const tcg_insn_unit *bswap32u_addr;
static const tcg_insn_unit *bswap64_addr;
static bool reloc_pc16(tcg_insn_unit *src_rw, const tcg_insn_unit *target)
{
/* Let the compiler perform the right-shift as part of the arithmetic. */
const tcg_insn_unit *src_rx = tcg_splitwx_to_rx(src_rw);
ptrdiff_t disp = target - (src_rx + 1);
if (disp == (int16_t)disp) {
*src_rw = deposit32(*src_rw, 0, 16, disp);
return true;
}
return false;
}
static bool patch_reloc(tcg_insn_unit *code_ptr, int type,
intptr_t value, intptr_t addend)
{
value += addend;
switch (type) {
case R_MIPS_PC16:
return reloc_pc16(code_ptr, (const tcg_insn_unit *)value);
case R_MIPS_16:
if (value != (int16_t)value) {
return false;
}
*code_ptr = deposit32(*code_ptr, 0, 16, value);
return true;
}
g_assert_not_reached();
}
#define TCG_CT_CONST_ZERO 0x100
#define TCG_CT_CONST_U16 0x200 /* Unsigned 16-bit: 0 - 0xffff. */
#define TCG_CT_CONST_S16 0x400 /* Signed 16-bit: -32768 - 32767 */
#define TCG_CT_CONST_P2M1 0x800 /* Power of 2 minus 1. */
#define TCG_CT_CONST_N16 0x1000 /* "Negatable" 16-bit: -32767 - 32767 */
#define TCG_CT_CONST_WSZ 0x2000 /* word size */
#define ALL_GENERAL_REGS 0xffffffffu
static bool is_p2m1(tcg_target_long val)
{
return val && ((val + 1) & val) == 0;
}
/* test if a constant matches the constraint */
static bool tcg_target_const_match(int64_t val, TCGType type, int ct)
{
if (ct & TCG_CT_CONST) {
return 1;
} else if ((ct & TCG_CT_CONST_ZERO) && val == 0) {
return 1;
} else if ((ct & TCG_CT_CONST_U16) && val == (uint16_t)val) {
return 1;
} else if ((ct & TCG_CT_CONST_S16) && val == (int16_t)val) {
return 1;
} else if ((ct & TCG_CT_CONST_N16) && val >= -32767 && val <= 32767) {
return 1;
} else if ((ct & TCG_CT_CONST_P2M1)
&& use_mips32r2_instructions && is_p2m1(val)) {
return 1;
} else if ((ct & TCG_CT_CONST_WSZ)
&& val == (type == TCG_TYPE_I32 ? 32 : 64)) {
return 1;
}
return 0;
}
/* instruction opcodes */
typedef enum {
OPC_J = 002 << 26,
OPC_JAL = 003 << 26,
OPC_BEQ = 004 << 26,
OPC_BNE = 005 << 26,
OPC_BLEZ = 006 << 26,
OPC_BGTZ = 007 << 26,
OPC_ADDIU = 011 << 26,
OPC_SLTI = 012 << 26,
OPC_SLTIU = 013 << 26,
OPC_ANDI = 014 << 26,
OPC_ORI = 015 << 26,
OPC_XORI = 016 << 26,
OPC_LUI = 017 << 26,
OPC_BNEL = 025 << 26,
OPC_BNEZALC_R6 = 030 << 26,
OPC_DADDIU = 031 << 26,
OPC_LDL = 032 << 26,
OPC_LDR = 033 << 26,
OPC_LB = 040 << 26,
OPC_LH = 041 << 26,
OPC_LWL = 042 << 26,
OPC_LW = 043 << 26,
OPC_LBU = 044 << 26,
OPC_LHU = 045 << 26,
OPC_LWR = 046 << 26,
OPC_LWU = 047 << 26,
OPC_SB = 050 << 26,
OPC_SH = 051 << 26,
OPC_SWL = 052 << 26,
OPC_SW = 053 << 26,
OPC_SDL = 054 << 26,
OPC_SDR = 055 << 26,
OPC_SWR = 056 << 26,
OPC_LD = 067 << 26,
OPC_SD = 077 << 26,
OPC_SPECIAL = 000 << 26,
OPC_SLL = OPC_SPECIAL | 000,
OPC_SRL = OPC_SPECIAL | 002,
OPC_ROTR = OPC_SPECIAL | 002 | (1 << 21),
OPC_SRA = OPC_SPECIAL | 003,
OPC_SLLV = OPC_SPECIAL | 004,
OPC_SRLV = OPC_SPECIAL | 006,
OPC_ROTRV = OPC_SPECIAL | 006 | 0100,
OPC_SRAV = OPC_SPECIAL | 007,
OPC_JR_R5 = OPC_SPECIAL | 010,
OPC_JALR = OPC_SPECIAL | 011,
OPC_MOVZ = OPC_SPECIAL | 012,
OPC_MOVN = OPC_SPECIAL | 013,
OPC_SYNC = OPC_SPECIAL | 017,
OPC_MFHI = OPC_SPECIAL | 020,
OPC_MFLO = OPC_SPECIAL | 022,
OPC_DSLLV = OPC_SPECIAL | 024,
OPC_DSRLV = OPC_SPECIAL | 026,
OPC_DROTRV = OPC_SPECIAL | 026 | 0100,
OPC_DSRAV = OPC_SPECIAL | 027,
OPC_MULT = OPC_SPECIAL | 030,
OPC_MUL_R6 = OPC_SPECIAL | 030 | 0200,
OPC_MUH = OPC_SPECIAL | 030 | 0300,
OPC_MULTU = OPC_SPECIAL | 031,
OPC_MULU = OPC_SPECIAL | 031 | 0200,
OPC_MUHU = OPC_SPECIAL | 031 | 0300,
OPC_DIV = OPC_SPECIAL | 032,
OPC_DIV_R6 = OPC_SPECIAL | 032 | 0200,
OPC_MOD = OPC_SPECIAL | 032 | 0300,
OPC_DIVU = OPC_SPECIAL | 033,
OPC_DIVU_R6 = OPC_SPECIAL | 033 | 0200,
OPC_MODU = OPC_SPECIAL | 033 | 0300,
OPC_DMULT = OPC_SPECIAL | 034,
OPC_DMUL = OPC_SPECIAL | 034 | 0200,
OPC_DMUH = OPC_SPECIAL | 034 | 0300,
OPC_DMULTU = OPC_SPECIAL | 035,
OPC_DMULU = OPC_SPECIAL | 035 | 0200,
OPC_DMUHU = OPC_SPECIAL | 035 | 0300,
OPC_DDIV = OPC_SPECIAL | 036,
OPC_DDIV_R6 = OPC_SPECIAL | 036 | 0200,
OPC_DMOD = OPC_SPECIAL | 036 | 0300,
OPC_DDIVU = OPC_SPECIAL | 037,
OPC_DDIVU_R6 = OPC_SPECIAL | 037 | 0200,
OPC_DMODU = OPC_SPECIAL | 037 | 0300,
OPC_ADDU = OPC_SPECIAL | 041,
OPC_SUBU = OPC_SPECIAL | 043,
OPC_AND = OPC_SPECIAL | 044,
OPC_OR = OPC_SPECIAL | 045,
OPC_XOR = OPC_SPECIAL | 046,
OPC_NOR = OPC_SPECIAL | 047,
OPC_SLT = OPC_SPECIAL | 052,
OPC_SLTU = OPC_SPECIAL | 053,
OPC_DADDU = OPC_SPECIAL | 055,
OPC_DSUBU = OPC_SPECIAL | 057,
OPC_SELEQZ = OPC_SPECIAL | 065,
OPC_SELNEZ = OPC_SPECIAL | 067,
OPC_DSLL = OPC_SPECIAL | 070,
OPC_DSRL = OPC_SPECIAL | 072,
OPC_DROTR = OPC_SPECIAL | 072 | (1 << 21),
OPC_DSRA = OPC_SPECIAL | 073,
OPC_DSLL32 = OPC_SPECIAL | 074,
OPC_DSRL32 = OPC_SPECIAL | 076,
OPC_DROTR32 = OPC_SPECIAL | 076 | (1 << 21),
OPC_DSRA32 = OPC_SPECIAL | 077,
OPC_CLZ_R6 = OPC_SPECIAL | 0120,
OPC_DCLZ_R6 = OPC_SPECIAL | 0122,
OPC_REGIMM = 001 << 26,
OPC_BLTZ = OPC_REGIMM | (000 << 16),
OPC_BGEZ = OPC_REGIMM | (001 << 16),
OPC_SPECIAL2 = 034 << 26,
OPC_MUL_R5 = OPC_SPECIAL2 | 002,
OPC_CLZ = OPC_SPECIAL2 | 040,
OPC_DCLZ = OPC_SPECIAL2 | 044,
OPC_SPECIAL3 = 037 << 26,
OPC_EXT = OPC_SPECIAL3 | 000,
OPC_DEXTM = OPC_SPECIAL3 | 001,
OPC_DEXTU = OPC_SPECIAL3 | 002,
OPC_DEXT = OPC_SPECIAL3 | 003,
OPC_INS = OPC_SPECIAL3 | 004,
OPC_DINSM = OPC_SPECIAL3 | 005,
OPC_DINSU = OPC_SPECIAL3 | 006,
OPC_DINS = OPC_SPECIAL3 | 007,
OPC_WSBH = OPC_SPECIAL3 | 00240,
OPC_DSBH = OPC_SPECIAL3 | 00244,
OPC_DSHD = OPC_SPECIAL3 | 00544,
OPC_SEB = OPC_SPECIAL3 | 02040,
OPC_SEH = OPC_SPECIAL3 | 03040,
/* MIPS r6 doesn't have JR, JALR should be used instead */
OPC_JR = use_mips32r6_instructions ? OPC_JALR : OPC_JR_R5,
/*
* MIPS r6 replaces MUL with an alternative encoding which is
* backwards-compatible at the assembly level.
*/
OPC_MUL = use_mips32r6_instructions ? OPC_MUL_R6 : OPC_MUL_R5,
/* MIPS r6 introduced names for weaker variants of SYNC. These are
backward compatible to previous architecture revisions. */
OPC_SYNC_WMB = OPC_SYNC | 0x04 << 6,
OPC_SYNC_MB = OPC_SYNC | 0x10 << 6,
OPC_SYNC_ACQUIRE = OPC_SYNC | 0x11 << 6,
OPC_SYNC_RELEASE = OPC_SYNC | 0x12 << 6,
OPC_SYNC_RMB = OPC_SYNC | 0x13 << 6,
/* Aliases for convenience. */
ALIAS_PADD = sizeof(void *) == 4 ? OPC_ADDU : OPC_DADDU,
ALIAS_PADDI = sizeof(void *) == 4 ? OPC_ADDIU : OPC_DADDIU,
} MIPSInsn;
/*
* Type reg
*/
static void tcg_out_opc_reg(TCGContext *s, MIPSInsn opc,
TCGReg rd, TCGReg rs, TCGReg rt)
{
int32_t inst;
inst = opc;
inst |= (rs & 0x1F) << 21;
inst |= (rt & 0x1F) << 16;
inst |= (rd & 0x1F) << 11;
tcg_out32(s, inst);
}
/*
* Type immediate
*/
static void tcg_out_opc_imm(TCGContext *s, MIPSInsn opc,
TCGReg rt, TCGReg rs, TCGArg imm)
{
int32_t inst;
inst = opc;
inst |= (rs & 0x1F) << 21;
inst |= (rt & 0x1F) << 16;
inst |= (imm & 0xffff);
tcg_out32(s, inst);
}
/*
* Type bitfield
*/
static void tcg_out_opc_bf(TCGContext *s, MIPSInsn opc, TCGReg rt,
TCGReg rs, int msb, int lsb)
{
int32_t inst;
inst = opc;
inst |= (rs & 0x1F) << 21;
inst |= (rt & 0x1F) << 16;
inst |= (msb & 0x1F) << 11;
inst |= (lsb & 0x1F) << 6;
tcg_out32(s, inst);
}
static void tcg_out_opc_bf64(TCGContext *s, MIPSInsn opc, MIPSInsn opm,
MIPSInsn oph, TCGReg rt, TCGReg rs,
int msb, int lsb)
{
if (lsb >= 32) {
opc = oph;
msb -= 32;
lsb -= 32;
} else if (msb >= 32) {
opc = opm;
msb -= 32;
}
tcg_out_opc_bf(s, opc, rt, rs, msb, lsb);
}
/*
* Type branch
*/
static void tcg_out_opc_br(TCGContext *s, MIPSInsn opc, TCGReg rt, TCGReg rs)
{
tcg_out_opc_imm(s, opc, rt, rs, 0);
}
/*
* Type sa
*/
static void tcg_out_opc_sa(TCGContext *s, MIPSInsn opc,
TCGReg rd, TCGReg rt, TCGArg sa)
{
int32_t inst;
inst = opc;
inst |= (rt & 0x1F) << 16;
inst |= (rd & 0x1F) << 11;
inst |= (sa & 0x1F) << 6;
tcg_out32(s, inst);
}
static void tcg_out_opc_sa64(TCGContext *s, MIPSInsn opc1, MIPSInsn opc2,
TCGReg rd, TCGReg rt, TCGArg sa)
{
int32_t inst;
inst = (sa & 32 ? opc2 : opc1);
inst |= (rt & 0x1F) << 16;
inst |= (rd & 0x1F) << 11;
inst |= (sa & 0x1F) << 6;
tcg_out32(s, inst);
}
/*
* Type jump.
* Returns true if the branch was in range and the insn was emitted.
*/
static bool tcg_out_opc_jmp(TCGContext *s, MIPSInsn opc, const void *target)
{
uintptr_t dest = (uintptr_t)target;
uintptr_t from = (uintptr_t)tcg_splitwx_to_rx(s->code_ptr) + 4;
int32_t inst;
/* The pc-region branch happens within the 256MB region of
the delay slot (thus the +4). */
if ((from ^ dest) & -(1 << 28)) {
return false;
}
tcg_debug_assert((dest & 3) == 0);
inst = opc;
inst |= (dest >> 2) & 0x3ffffff;
tcg_out32(s, inst);
return true;
}
static void tcg_out_nop(TCGContext *s)
{
tcg_out32(s, 0);
}
static void tcg_out_nop_fill(tcg_insn_unit *p, int count)
{
memset(p, 0, count * sizeof(tcg_insn_unit));
}
static void tcg_out_dsll(TCGContext *s, TCGReg rd, TCGReg rt, TCGArg sa)
{
tcg_out_opc_sa64(s, OPC_DSLL, OPC_DSLL32, rd, rt, sa);
}
static void tcg_out_dsrl(TCGContext *s, TCGReg rd, TCGReg rt, TCGArg sa)
{
tcg_out_opc_sa64(s, OPC_DSRL, OPC_DSRL32, rd, rt, sa);
}
static void tcg_out_dsra(TCGContext *s, TCGReg rd, TCGReg rt, TCGArg sa)
{
tcg_out_opc_sa64(s, OPC_DSRA, OPC_DSRA32, rd, rt, sa);
}
static bool tcg_out_mov(TCGContext *s, TCGType type, TCGReg ret, TCGReg arg)
{
/* Simple reg-reg move, optimising out the 'do nothing' case */
if (ret != arg) {
tcg_out_opc_reg(s, OPC_OR, ret, arg, TCG_REG_ZERO);
}
return true;
}
static bool tcg_out_movi_one(TCGContext *s, TCGReg ret, tcg_target_long arg)
{
if (arg == (int16_t)arg) {
tcg_out_opc_imm(s, OPC_ADDIU, ret, TCG_REG_ZERO, arg);
return true;
}
if (arg == (uint16_t)arg) {
tcg_out_opc_imm(s, OPC_ORI, ret, TCG_REG_ZERO, arg);
return true;
}
if (arg == (int32_t)arg && (arg & 0xffff) == 0) {
tcg_out_opc_imm(s, OPC_LUI, ret, TCG_REG_ZERO, arg >> 16);
return true;
}
return false;
}
static bool tcg_out_movi_two(TCGContext *s, TCGReg ret, tcg_target_long arg)
{
/*
* All signed 32-bit constants are loadable with two immediates,
* and everything else requires more work.
*/
if (arg == (int32_t)arg) {
if (!tcg_out_movi_one(s, ret, arg)) {
tcg_out_opc_imm(s, OPC_LUI, ret, TCG_REG_ZERO, arg >> 16);
tcg_out_opc_imm(s, OPC_ORI, ret, ret, arg & 0xffff);
}
return true;
}
return false;
}
static void tcg_out_movi_pool(TCGContext *s, TCGReg ret,
tcg_target_long arg, TCGReg tbreg)
{
new_pool_label(s, arg, R_MIPS_16, s->code_ptr, tcg_tbrel_diff(s, NULL));
tcg_out_opc_imm(s, OPC_LD, ret, tbreg, 0);
}
static void tcg_out_movi_int(TCGContext *s, TCGType type, TCGReg ret,
tcg_target_long arg, TCGReg tbreg)
{
tcg_target_long tmp;
int sh, lo;
if (TCG_TARGET_REG_BITS == 64 && type == TCG_TYPE_I32) {
arg = (int32_t)arg;
}
/* Load all 32-bit constants. */
if (tcg_out_movi_two(s, ret, arg)) {
return;
}
assert(TCG_TARGET_REG_BITS == 64);
/* Load addresses within 2GB of TB with 1 or 3 insns. */
tmp = tcg_tbrel_diff(s, (void *)arg);
if (tmp == (int16_t)tmp) {
tcg_out_opc_imm(s, OPC_DADDIU, ret, tbreg, tmp);
return;
}
if (tcg_out_movi_two(s, ret, tmp)) {
tcg_out_opc_reg(s, OPC_DADDU, ret, ret, tbreg);
return;
}
/*
* Load bitmasks with a right-shift. This is good for things
* like 0x0fff_ffff_ffff_fff0: ADDUI r,0,0xff00 + DSRL r,r,4.
* or similarly using LUI. For this to work, bit 31 must be set.
*/
if (arg > 0 && (int32_t)arg < 0) {
sh = clz64(arg);
if (tcg_out_movi_one(s, ret, arg << sh)) {
tcg_out_dsrl(s, ret, ret, sh);
return;
}
}
/*
* Load slightly larger constants using left-shift.
* Limit this sequence to 3 insns to avoid too much expansion.
*/
sh = ctz64(arg);
if (sh && tcg_out_movi_two(s, ret, arg >> sh)) {
tcg_out_dsll(s, ret, ret, sh);
return;
}
/*
* Load slightly larger constants using left-shift and add/or.
* Prefer addi with a negative immediate when that would produce
* a larger shift. For this to work, bits 15 and 16 must be set.
*/
lo = arg & 0xffff;
if (lo) {
if ((arg & 0x18000) == 0x18000) {
lo = (int16_t)arg;
}
tmp = arg - lo;
sh = ctz64(tmp);
tmp >>= sh;
if (tcg_out_movi_one(s, ret, tmp)) {
tcg_out_dsll(s, ret, ret, sh);
tcg_out_opc_imm(s, lo < 0 ? OPC_DADDIU : OPC_ORI, ret, ret, lo);
return;
}
}
/* Otherwise, put 64-bit constants into the constant pool. */
tcg_out_movi_pool(s, ret, arg, tbreg);
}
static void tcg_out_movi(TCGContext *s, TCGType type,
TCGReg ret, tcg_target_long arg)
{
TCGReg tbreg = TCG_TARGET_REG_BITS == 64 ? TCG_REG_TB : 0;
tcg_out_movi_int(s, type, ret, arg, tbreg);
}
static void tcg_out_ext8s(TCGContext *s, TCGType type, TCGReg rd, TCGReg rs)
{
tcg_debug_assert(TCG_TARGET_HAS_ext8s_i32);
tcg_out_opc_reg(s, OPC_SEB, rd, TCG_REG_ZERO, rs);
}
static void tcg_out_ext8u(TCGContext *s, TCGReg rd, TCGReg rs)
{
tcg_out_opc_imm(s, OPC_ANDI, rd, rs, 0xff);
}
static void tcg_out_ext16s(TCGContext *s, TCGType type, TCGReg rd, TCGReg rs)
{
tcg_debug_assert(TCG_TARGET_HAS_ext16s_i32);
tcg_out_opc_reg(s, OPC_SEH, rd, TCG_REG_ZERO, rs);
}
static void tcg_out_ext16u(TCGContext *s, TCGReg rd, TCGReg rs)
{
tcg_out_opc_imm(s, OPC_ANDI, rd, rs, 0xffff);
}
static void tcg_out_ext32s(TCGContext *s, TCGReg rd, TCGReg rs)
{
tcg_debug_assert(TCG_TARGET_REG_BITS == 64);
tcg_out_opc_sa(s, OPC_SLL, rd, rs, 0);
}
static void tcg_out_exts_i32_i64(TCGContext *s, TCGReg rd, TCGReg rs)
{
if (rd != rs) {
tcg_out_ext32s(s, rd, rs);
}
}
static void tcg_out_extu_i32_i64(TCGContext *s, TCGReg rd, TCGReg rs)
{
tcg_out_ext32u(s, rd, rs);
}
static void tcg_out_extrl_i64_i32(TCGContext *s, TCGReg rd, TCGReg rs)
{
tcg_out_ext32s(s, rd, rs);
}
static bool tcg_out_xchg(TCGContext *s, TCGType type, TCGReg r1, TCGReg r2)
{
return false;
}
static void tcg_out_addi_ptr(TCGContext *s, TCGReg rd, TCGReg rs,
tcg_target_long imm)
{
/* This function is only used for passing structs by reference. */
g_assert_not_reached();
}
static void tcg_out_bswap16(TCGContext *s, TCGReg ret, TCGReg arg, int flags)
{
/* ret and arg can't be register tmp0 */
tcg_debug_assert(ret != TCG_TMP0);
tcg_debug_assert(arg != TCG_TMP0);
/* With arg = abcd: */
if (use_mips32r2_instructions) {
tcg_out_opc_reg(s, OPC_WSBH, ret, 0, arg); /* badc */
if (flags & TCG_BSWAP_OS) {
tcg_out_opc_reg(s, OPC_SEH, ret, 0, ret); /* ssdc */
} else if ((flags & (TCG_BSWAP_IZ | TCG_BSWAP_OZ)) == TCG_BSWAP_OZ) {
tcg_out_opc_imm(s, OPC_ANDI, ret, ret, 0xffff); /* 00dc */
}
return;
}
tcg_out_opc_sa(s, OPC_SRL, TCG_TMP0, arg, 8); /* 0abc */
if (!(flags & TCG_BSWAP_IZ)) {
tcg_out_opc_imm(s, OPC_ANDI, TCG_TMP0, TCG_TMP0, 0x00ff); /* 000c */
}
if (flags & TCG_BSWAP_OS) {
tcg_out_opc_sa(s, OPC_SLL, ret, arg, 24); /* d000 */
tcg_out_opc_sa(s, OPC_SRA, ret, ret, 16); /* ssd0 */
} else {
tcg_out_opc_sa(s, OPC_SLL, ret, arg, 8); /* bcd0 */
if (flags & TCG_BSWAP_OZ) {
tcg_out_opc_imm(s, OPC_ANDI, ret, ret, 0xff00); /* 00d0 */
}
}
tcg_out_opc_reg(s, OPC_OR, ret, ret, TCG_TMP0); /* ssdc */
}
static void tcg_out_bswap_subr(TCGContext *s, const tcg_insn_unit *sub)
{
if (!tcg_out_opc_jmp(s, OPC_JAL, sub)) {
tcg_out_movi(s, TCG_TYPE_PTR, TCG_TMP1, (uintptr_t)sub);
tcg_out_opc_reg(s, OPC_JALR, TCG_REG_RA, TCG_TMP1, 0);
}
}
static void tcg_out_bswap32(TCGContext *s, TCGReg ret, TCGReg arg, int flags)
{
if (use_mips32r2_instructions) {
tcg_out_opc_reg(s, OPC_WSBH, ret, 0, arg);
tcg_out_opc_sa(s, OPC_ROTR, ret, ret, 16);
if (flags & TCG_BSWAP_OZ) {
tcg_out_opc_bf(s, OPC_DEXT, ret, ret, 31, 0);
}
} else {
if (flags & TCG_BSWAP_OZ) {
tcg_out_bswap_subr(s, bswap32u_addr);
} else {
tcg_out_bswap_subr(s, bswap32_addr);
}
/* delay slot -- never omit the insn, like tcg_out_mov might. */
tcg_out_opc_reg(s, OPC_OR, TCG_TMP0, arg, TCG_REG_ZERO);
tcg_out_mov(s, TCG_TYPE_I32, ret, TCG_TMP3);
}
}
static void tcg_out_bswap64(TCGContext *s, TCGReg ret, TCGReg arg)
{
if (use_mips32r2_instructions) {
tcg_out_opc_reg(s, OPC_DSBH, ret, 0, arg);
tcg_out_opc_reg(s, OPC_DSHD, ret, 0, ret);
} else {
tcg_out_bswap_subr(s, bswap64_addr);
/* delay slot -- never omit the insn, like tcg_out_mov might. */
tcg_out_opc_reg(s, OPC_OR, TCG_TMP0, arg, TCG_REG_ZERO);
tcg_out_mov(s, TCG_TYPE_I32, ret, TCG_TMP3);
}
}
static void tcg_out_ext32u(TCGContext *s, TCGReg ret, TCGReg arg)
{
tcg_debug_assert(TCG_TARGET_REG_BITS == 64);
if (use_mips32r2_instructions) {
tcg_out_opc_bf(s, OPC_DEXT, ret, arg, 31, 0);
} else {
tcg_out_dsll(s, ret, arg, 32);
tcg_out_dsrl(s, ret, ret, 32);
}
}
static void tcg_out_ldst(TCGContext *s, MIPSInsn opc, TCGReg data,
TCGReg addr, intptr_t ofs)
{
int16_t lo = ofs;
if (ofs != lo) {
tcg_out_movi(s, TCG_TYPE_PTR, TCG_TMP0, ofs - lo);
if (addr != TCG_REG_ZERO) {
tcg_out_opc_reg(s, ALIAS_PADD, TCG_TMP0, TCG_TMP0, addr);
}
addr = TCG_TMP0;
}
tcg_out_opc_imm(s, opc, data, addr, lo);
}
static void tcg_out_ld(TCGContext *s, TCGType type, TCGReg arg,
TCGReg arg1, intptr_t arg2)
{
MIPSInsn opc = OPC_LD;
if (TCG_TARGET_REG_BITS == 32 || type == TCG_TYPE_I32) {
opc = OPC_LW;
}
tcg_out_ldst(s, opc, arg, arg1, arg2);
}
static void tcg_out_st(TCGContext *s, TCGType type, TCGReg arg,
TCGReg arg1, intptr_t arg2)
{
MIPSInsn opc = OPC_SD;
if (TCG_TARGET_REG_BITS == 32 || type == TCG_TYPE_I32) {
opc = OPC_SW;
}
tcg_out_ldst(s, opc, arg, arg1, arg2);
}
static bool tcg_out_sti(TCGContext *s, TCGType type, TCGArg val,
TCGReg base, intptr_t ofs)
{
if (val == 0) {
tcg_out_st(s, type, TCG_REG_ZERO, base, ofs);
return true;
}
return false;
}
static void tcg_out_addsub2(TCGContext *s, TCGReg rl, TCGReg rh, TCGReg al,
TCGReg ah, TCGArg bl, TCGArg bh, bool cbl,
bool cbh, bool is_sub)
{
TCGReg th = TCG_TMP1;
/* If we have a negative constant such that negating it would
make the high part zero, we can (usually) eliminate one insn. */
if (cbl && cbh && bh == -1 && bl != 0) {
bl = -bl;
bh = 0;
is_sub = !is_sub;
}
/* By operating on the high part first, we get to use the final
carry operation to move back from the temporary. */
if (!cbh) {
tcg_out_opc_reg(s, (is_sub ? OPC_SUBU : OPC_ADDU), th, ah, bh);
} else if (bh != 0 || ah == rl) {
tcg_out_opc_imm(s, OPC_ADDIU, th, ah, (is_sub ? -bh : bh));
} else {
th = ah;
}
/* Note that tcg optimization should eliminate the bl == 0 case. */
if (is_sub) {
if (cbl) {
tcg_out_opc_imm(s, OPC_SLTIU, TCG_TMP0, al, bl);
tcg_out_opc_imm(s, OPC_ADDIU, rl, al, -bl);
} else {
tcg_out_opc_reg(s, OPC_SLTU, TCG_TMP0, al, bl);
tcg_out_opc_reg(s, OPC_SUBU, rl, al, bl);
}
tcg_out_opc_reg(s, OPC_SUBU, rh, th, TCG_TMP0);
} else {
if (cbl) {
tcg_out_opc_imm(s, OPC_ADDIU, rl, al, bl);
tcg_out_opc_imm(s, OPC_SLTIU, TCG_TMP0, rl, bl);
} else if (rl == al && rl == bl) {
tcg_out_opc_sa(s, OPC_SRL, TCG_TMP0, al, TCG_TARGET_REG_BITS - 1);
tcg_out_opc_reg(s, OPC_ADDU, rl, al, bl);
} else {
tcg_out_opc_reg(s, OPC_ADDU, rl, al, bl);
tcg_out_opc_reg(s, OPC_SLTU, TCG_TMP0, rl, (rl == bl ? al : bl));
}
tcg_out_opc_reg(s, OPC_ADDU, rh, th, TCG_TMP0);
}
}
/* Bit 0 set if inversion required; bit 1 set if swapping required. */
#define MIPS_CMP_INV 1
#define MIPS_CMP_SWAP 2
static const uint8_t mips_cmp_map[16] = {
[TCG_COND_LT] = 0,
[TCG_COND_LTU] = 0,
[TCG_COND_GE] = MIPS_CMP_INV,
[TCG_COND_GEU] = MIPS_CMP_INV,
[TCG_COND_LE] = MIPS_CMP_INV | MIPS_CMP_SWAP,
[TCG_COND_LEU] = MIPS_CMP_INV | MIPS_CMP_SWAP,
[TCG_COND_GT] = MIPS_CMP_SWAP,
[TCG_COND_GTU] = MIPS_CMP_SWAP,
};
static void tcg_out_setcond(TCGContext *s, TCGCond cond, TCGReg ret,
TCGReg arg1, TCGReg arg2)
{
MIPSInsn s_opc = OPC_SLTU;
int cmp_map;
switch (cond) {
case TCG_COND_EQ:
if (arg2 != 0) {
tcg_out_opc_reg(s, OPC_XOR, ret, arg1, arg2);
arg1 = ret;
}
tcg_out_opc_imm(s, OPC_SLTIU, ret, arg1, 1);
break;
case TCG_COND_NE:
if (arg2 != 0) {
tcg_out_opc_reg(s, OPC_XOR, ret, arg1, arg2);
arg1 = ret;
}
tcg_out_opc_reg(s, OPC_SLTU, ret, TCG_REG_ZERO, arg1);
break;
case TCG_COND_LT:
case TCG_COND_GE:
case TCG_COND_LE:
case TCG_COND_GT:
s_opc = OPC_SLT;
/* FALLTHRU */
case TCG_COND_LTU:
case TCG_COND_GEU:
case TCG_COND_LEU:
case TCG_COND_GTU:
cmp_map = mips_cmp_map[cond];
if (cmp_map & MIPS_CMP_SWAP) {
TCGReg t = arg1;
arg1 = arg2;
arg2 = t;
}
tcg_out_opc_reg(s, s_opc, ret, arg1, arg2);
if (cmp_map & MIPS_CMP_INV) {
tcg_out_opc_imm(s, OPC_XORI, ret, ret, 1);
}
break;
default:
g_assert_not_reached();
break;
}
}
static void tcg_out_brcond(TCGContext *s, TCGCond cond, TCGReg arg1,
TCGReg arg2, TCGLabel *l)
{
static const MIPSInsn b_zero[16] = {
[TCG_COND_LT] = OPC_BLTZ,
[TCG_COND_GT] = OPC_BGTZ,
[TCG_COND_LE] = OPC_BLEZ,
[TCG_COND_GE] = OPC_BGEZ,
};
MIPSInsn s_opc = OPC_SLTU;
MIPSInsn b_opc;
int cmp_map;
switch (cond) {
case TCG_COND_EQ:
b_opc = OPC_BEQ;
break;
case TCG_COND_NE:
b_opc = OPC_BNE;
break;
case TCG_COND_LT:
case TCG_COND_GT:
case TCG_COND_LE:
case TCG_COND_GE:
if (arg2 == 0) {
b_opc = b_zero[cond];
arg2 = arg1;
arg1 = 0;
break;
}
s_opc = OPC_SLT;
/* FALLTHRU */
case TCG_COND_LTU:
case TCG_COND_GTU:
case TCG_COND_LEU:
case TCG_COND_GEU:
cmp_map = mips_cmp_map[cond];
if (cmp_map & MIPS_CMP_SWAP) {
TCGReg t = arg1;
arg1 = arg2;
arg2 = t;
}
tcg_out_opc_reg(s, s_opc, TCG_TMP0, arg1, arg2);
b_opc = (cmp_map & MIPS_CMP_INV ? OPC_BEQ : OPC_BNE);
arg1 = TCG_TMP0;
arg2 = TCG_REG_ZERO;
break;
default:
g_assert_not_reached();
break;
}
tcg_out_opc_br(s, b_opc, arg1, arg2);
tcg_out_reloc(s, s->code_ptr - 1, R_MIPS_PC16, l, 0);
tcg_out_nop(s);
}
static TCGReg tcg_out_reduce_eq2(TCGContext *s, TCGReg tmp0, TCGReg tmp1,
TCGReg al, TCGReg ah,
TCGReg bl, TCGReg bh)
{
/* Merge highpart comparison into AH. */
if (bh != 0) {
if (ah != 0) {
tcg_out_opc_reg(s, OPC_XOR, tmp0, ah, bh);
ah = tmp0;
} else {
ah = bh;
}
}
/* Merge lowpart comparison into AL. */
if (bl != 0) {
if (al != 0) {
tcg_out_opc_reg(s, OPC_XOR, tmp1, al, bl);
al = tmp1;
} else {
al = bl;
}
}
/* Merge high and low part comparisons into AL. */
if (ah != 0) {
if (al != 0) {
tcg_out_opc_reg(s, OPC_OR, tmp0, ah, al);
al = tmp0;
} else {
al = ah;
}
}
return al;
}
static void tcg_out_setcond2(TCGContext *s, TCGCond cond, TCGReg ret,
TCGReg al, TCGReg ah, TCGReg bl, TCGReg bh)
{
TCGReg tmp0 = TCG_TMP0;
TCGReg tmp1 = ret;
tcg_debug_assert(ret != TCG_TMP0);
if (ret == ah || ret == bh) {
tcg_debug_assert(ret != TCG_TMP1);
tmp1 = TCG_TMP1;
}
switch (cond) {
case TCG_COND_EQ:
case TCG_COND_NE:
tmp1 = tcg_out_reduce_eq2(s, tmp0, tmp1, al, ah, bl, bh);
tcg_out_setcond(s, cond, ret, tmp1, TCG_REG_ZERO);
break;
default:
tcg_out_setcond(s, TCG_COND_EQ, tmp0, ah, bh);
tcg_out_setcond(s, tcg_unsigned_cond(cond), tmp1, al, bl);
tcg_out_opc_reg(s, OPC_AND, tmp1, tmp1, tmp0);
tcg_out_setcond(s, tcg_high_cond(cond), tmp0, ah, bh);
tcg_out_opc_reg(s, OPC_OR, ret, tmp1, tmp0);
break;
}
}
static void tcg_out_brcond2(TCGContext *s, TCGCond cond, TCGReg al, TCGReg ah,
TCGReg bl, TCGReg bh, TCGLabel *l)
{
TCGCond b_cond = TCG_COND_NE;
TCGReg tmp = TCG_TMP1;
/* With branches, we emit between 4 and 9 insns with 2 or 3 branches.
With setcond, we emit between 3 and 10 insns and only 1 branch,
which ought to get better branch prediction. */
switch (cond) {
case TCG_COND_EQ:
case TCG_COND_NE:
b_cond = cond;
tmp = tcg_out_reduce_eq2(s, TCG_TMP0, TCG_TMP1, al, ah, bl, bh);
break;
default:
/* Minimize code size by preferring a compare not requiring INV. */
if (mips_cmp_map[cond] & MIPS_CMP_INV) {
cond = tcg_invert_cond(cond);
b_cond = TCG_COND_EQ;
}
tcg_out_setcond2(s, cond, tmp, al, ah, bl, bh);
break;
}
tcg_out_brcond(s, b_cond, tmp, TCG_REG_ZERO, l);
}
static void tcg_out_movcond(TCGContext *s, TCGCond cond, TCGReg ret,
TCGReg c1, TCGReg c2, TCGReg v1, TCGReg v2)
{
bool eqz = false;
/* If one of the values is zero, put it last to match SEL*Z instructions */
if (use_mips32r6_instructions && v1 == 0) {
v1 = v2;
v2 = 0;
cond = tcg_invert_cond(cond);
}
switch (cond) {
case TCG_COND_EQ:
eqz = true;
/* FALLTHRU */
case TCG_COND_NE:
if (c2 != 0) {
tcg_out_opc_reg(s, OPC_XOR, TCG_TMP0, c1, c2);
c1 = TCG_TMP0;
}
break;
default:
/* Minimize code size by preferring a compare not requiring INV. */
if (mips_cmp_map[cond] & MIPS_CMP_INV) {
cond = tcg_invert_cond(cond);
eqz = true;
}
tcg_out_setcond(s, cond, TCG_TMP0, c1, c2);
c1 = TCG_TMP0;
break;
}
if (use_mips32r6_instructions) {
MIPSInsn m_opc_t = eqz ? OPC_SELEQZ : OPC_SELNEZ;
MIPSInsn m_opc_f = eqz ? OPC_SELNEZ : OPC_SELEQZ;
if (v2 != 0) {
tcg_out_opc_reg(s, m_opc_f, TCG_TMP1, v2, c1);
}
tcg_out_opc_reg(s, m_opc_t, ret, v1, c1);
if (v2 != 0) {
tcg_out_opc_reg(s, OPC_OR, ret, ret, TCG_TMP1);
}
} else {
MIPSInsn m_opc = eqz ? OPC_MOVZ : OPC_MOVN;
tcg_out_opc_reg(s, m_opc, ret, v1, c1);
/* This should be guaranteed via constraints */
tcg_debug_assert(v2 == ret);
}
}
static void tcg_out_call_int(TCGContext *s, const tcg_insn_unit *arg, bool tail)
{
/*
* Note that __mips_abicalls requires the called function's address
* to be loaded into $25 (t9), even if a direct branch is in range.
*
* For n64, always drop the pointer into the constant pool.
* We can re-use helper addresses often and do not want any
* of the longer sequences tcg_out_movi may try.
*/
if (sizeof(uintptr_t) == 8) {
tcg_out_movi_pool(s, TCG_REG_T9, (uintptr_t)arg, TCG_REG_TB);
} else {
tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_T9, (uintptr_t)arg);
}
/* But do try a direct branch, allowing the cpu better insn prefetch. */
if (tail) {
if (!tcg_out_opc_jmp(s, OPC_J, arg)) {
tcg_out_opc_reg(s, OPC_JR, 0, TCG_REG_T9, 0);
}
} else {
if (!tcg_out_opc_jmp(s, OPC_JAL, arg)) {
tcg_out_opc_reg(s, OPC_JALR, TCG_REG_RA, TCG_REG_T9, 0);
}
}
}
static void tcg_out_call(TCGContext *s, const tcg_insn_unit *arg,
const TCGHelperInfo *info)
{
tcg_out_call_int(s, arg, false);
tcg_out_nop(s);
}
/* We have four temps, we might as well expose three of them. */
static const TCGLdstHelperParam ldst_helper_param = {
.ntmp = 3, .tmp = { TCG_TMP0, TCG_TMP1, TCG_TMP2 }
};
static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l)
{
const tcg_insn_unit *tgt_rx = tcg_splitwx_to_rx(s->code_ptr);
MemOp opc = get_memop(l->oi);
/* resolve label address */
if (!reloc_pc16(l->label_ptr[0], tgt_rx)
|| (l->label_ptr[1] && !reloc_pc16(l->label_ptr[1], tgt_rx))) {
return false;
}
tcg_out_ld_helper_args(s, l, &ldst_helper_param);
tcg_out_call_int(s, qemu_ld_helpers[opc & MO_SSIZE], false);
/* delay slot */
tcg_out_nop(s);
tcg_out_ld_helper_ret(s, l, true, &ldst_helper_param);
tcg_out_opc_br(s, OPC_BEQ, TCG_REG_ZERO, TCG_REG_ZERO);
if (!reloc_pc16(s->code_ptr - 1, l->raddr)) {
return false;
}
/* delay slot */
tcg_out_nop(s);
return true;
}
static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l)
{
const tcg_insn_unit *tgt_rx = tcg_splitwx_to_rx(s->code_ptr);
MemOp opc = get_memop(l->oi);
/* resolve label address */
if (!reloc_pc16(l->label_ptr[0], tgt_rx)
|| (l->label_ptr[1] && !reloc_pc16(l->label_ptr[1], tgt_rx))) {
return false;
}
tcg_out_st_helper_args(s, l, &ldst_helper_param);
tcg_out_call_int(s, qemu_st_helpers[opc & MO_SIZE], false);
/* delay slot */
tcg_out_nop(s);
tcg_out_opc_br(s, OPC_BEQ, TCG_REG_ZERO, TCG_REG_ZERO);
if (!reloc_pc16(s->code_ptr - 1, l->raddr)) {
return false;
}
/* delay slot */
tcg_out_nop(s);
return true;
}
typedef struct {
TCGReg base;
TCGAtomAlign aa;
} HostAddress;
bool tcg_target_has_memory_bswap(MemOp memop)
{
return false;
}
/* We expect to use a 16-bit negative offset from ENV. */
#define MIN_TLB_MASK_TABLE_OFS -32768
/*
* For softmmu, perform the TLB load and compare.
* For useronly, perform any required alignment tests.
* In both cases, return a TCGLabelQemuLdst structure if the slow path
* is required and fill in @h with the host address for the fast path.
*/
static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h,
TCGReg addrlo, TCGReg addrhi,
MemOpIdx oi, bool is_ld)
{
TCGType addr_type = s->addr_type;
TCGLabelQemuLdst *ldst = NULL;
MemOp opc = get_memop(oi);
MemOp a_bits;
unsigned s_bits = opc & MO_SIZE;
unsigned a_mask;
TCGReg base;
h->aa = atom_and_align_for_opc(s, opc, MO_ATOM_IFALIGN, false);
a_bits = h->aa.align;
a_mask = (1 << a_bits) - 1;
#ifdef CONFIG_SOFTMMU
unsigned s_mask = (1 << s_bits) - 1;
int mem_index = get_mmuidx(oi);
int fast_off = tlb_mask_table_ofs(s, mem_index);
int mask_off = fast_off + offsetof(CPUTLBDescFast, mask);
int table_off = fast_off + offsetof(CPUTLBDescFast, table);
int add_off = offsetof(CPUTLBEntry, addend);
int cmp_off = is_ld ? offsetof(CPUTLBEntry, addr_read)
: offsetof(CPUTLBEntry, addr_write);
ldst = new_ldst_label(s);
ldst->is_ld = is_ld;
ldst->oi = oi;
ldst->addrlo_reg = addrlo;
ldst->addrhi_reg = addrhi;
/* Load tlb_mask[mmu_idx] and tlb_table[mmu_idx]. */
tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP0, TCG_AREG0, mask_off);
tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP1, TCG_AREG0, table_off);
/* Extract the TLB index from the address into TMP3. */
if (TCG_TARGET_REG_BITS == 32 || addr_type == TCG_TYPE_I32) {
tcg_out_opc_sa(s, OPC_SRL, TCG_TMP3, addrlo,
s->page_bits - CPU_TLB_ENTRY_BITS);
} else {
tcg_out_dsrl(s, TCG_TMP3, addrlo,
s->page_bits - CPU_TLB_ENTRY_BITS);
}
tcg_out_opc_reg(s, OPC_AND, TCG_TMP3, TCG_TMP3, TCG_TMP0);
/* Add the tlb_table pointer, creating the CPUTLBEntry address in TMP3. */
tcg_out_opc_reg(s, ALIAS_PADD, TCG_TMP3, TCG_TMP3, TCG_TMP1);
if (TCG_TARGET_REG_BITS == 32 || addr_type == TCG_TYPE_I32) {
/* Load the (low half) tlb comparator. */
tcg_out_ld(s, TCG_TYPE_I32, TCG_TMP0, TCG_TMP3,
cmp_off + HOST_BIG_ENDIAN * 4);
} else {
tcg_out_ld(s, TCG_TYPE_I64, TCG_TMP0, TCG_TMP3, cmp_off);
}
if (TCG_TARGET_REG_BITS == 64 || addr_type == TCG_TYPE_I32) {
/* Load the tlb addend for the fast path. */
tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP3, TCG_TMP3, add_off);
}
/*
* Mask the page bits, keeping the alignment bits to compare against.
* For unaligned accesses, compare against the end of the access to
* verify that it does not cross a page boundary.
*/
tcg_out_movi(s, addr_type, TCG_TMP1, s->page_mask | a_mask);
if (a_mask < s_mask) {
if (TCG_TARGET_REG_BITS == 32 || addr_type == TCG_TYPE_I32) {
tcg_out_opc_imm(s, OPC_ADDIU, TCG_TMP2, addrlo, s_mask - a_mask);
} else {
tcg_out_opc_imm(s, OPC_DADDIU, TCG_TMP2, addrlo, s_mask - a_mask);
}
tcg_out_opc_reg(s, OPC_AND, TCG_TMP1, TCG_TMP1, TCG_TMP2);
} else {
tcg_out_opc_reg(s, OPC_AND, TCG_TMP1, TCG_TMP1, addrlo);
}
/* Zero extend a 32-bit guest address for a 64-bit host. */
if (TCG_TARGET_REG_BITS == 64 && addr_type == TCG_TYPE_I32) {
tcg_out_ext32u(s, TCG_TMP2, addrlo);
addrlo = TCG_TMP2;
}
ldst->label_ptr[0] = s->code_ptr;
tcg_out_opc_br(s, OPC_BNE, TCG_TMP1, TCG_TMP0);
/* Load and test the high half tlb comparator. */
if (TCG_TARGET_REG_BITS == 32 && addr_type != TCG_TYPE_I32) {
/* delay slot */
tcg_out_ldst(s, OPC_LW, TCG_TMP0, TCG_TMP3, cmp_off + HI_OFF);
/* Load the tlb addend for the fast path. */
tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP3, TCG_TMP3, add_off);
ldst->label_ptr[1] = s->code_ptr;
tcg_out_opc_br(s, OPC_BNE, addrhi, TCG_TMP0);
}
/* delay slot */
base = TCG_TMP3;
tcg_out_opc_reg(s, ALIAS_PADD, base, TCG_TMP3, addrlo);
#else
if (a_mask && (use_mips32r6_instructions || a_bits != s_bits)) {
ldst = new_ldst_label(s);
ldst->is_ld = is_ld;
ldst->oi = oi;
ldst->addrlo_reg = addrlo;
ldst->addrhi_reg = addrhi;
/* We are expecting a_bits to max out at 7, much lower than ANDI. */
tcg_debug_assert(a_bits < 16);
tcg_out_opc_imm(s, OPC_ANDI, TCG_TMP0, addrlo, a_mask);
ldst->label_ptr[0] = s->code_ptr;
if (use_mips32r6_instructions) {
tcg_out_opc_br(s, OPC_BNEZALC_R6, TCG_REG_ZERO, TCG_TMP0);
} else {
tcg_out_opc_br(s, OPC_BNEL, TCG_TMP0, TCG_REG_ZERO);
tcg_out_nop(s);
}
}
base = addrlo;
if (TCG_TARGET_REG_BITS == 64 && addr_type == TCG_TYPE_I32) {
tcg_out_ext32u(s, TCG_REG_A0, base);
base = TCG_REG_A0;
}
if (guest_base) {
if (guest_base == (int16_t)guest_base) {
tcg_out_opc_imm(s, ALIAS_PADDI, TCG_REG_A0, base, guest_base);
} else {
tcg_out_opc_reg(s, ALIAS_PADD, TCG_REG_A0, base,
TCG_GUEST_BASE_REG);
}
base = TCG_REG_A0;
}
#endif
h->base = base;
return ldst;
}
static void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg lo, TCGReg hi,
TCGReg base, MemOp opc, TCGType type)
{
switch (opc & MO_SSIZE) {
case MO_UB:
tcg_out_opc_imm(s, OPC_LBU, lo, base, 0);
break;
case MO_SB:
tcg_out_opc_imm(s, OPC_LB, lo, base, 0);
break;
case MO_UW:
tcg_out_opc_imm(s, OPC_LHU, lo, base, 0);
break;
case MO_SW:
tcg_out_opc_imm(s, OPC_LH, lo, base, 0);
break;
case MO_UL:
if (TCG_TARGET_REG_BITS == 64 && type == TCG_TYPE_I64) {
tcg_out_opc_imm(s, OPC_LWU, lo, base, 0);
break;
}
/* FALLTHRU */
case MO_SL:
tcg_out_opc_imm(s, OPC_LW, lo, base, 0);
break;
case MO_UQ:
/* Prefer to load from offset 0 first, but allow for overlap. */
if (TCG_TARGET_REG_BITS == 64) {
tcg_out_opc_imm(s, OPC_LD, lo, base, 0);
} else if (HOST_BIG_ENDIAN ? hi != base : lo == base) {
tcg_out_opc_imm(s, OPC_LW, hi, base, HI_OFF);
tcg_out_opc_imm(s, OPC_LW, lo, base, LO_OFF);
} else {
tcg_out_opc_imm(s, OPC_LW, lo, base, LO_OFF);
tcg_out_opc_imm(s, OPC_LW, hi, base, HI_OFF);
}
break;
default:
g_assert_not_reached();
}
}
static void tcg_out_qemu_ld_unalign(TCGContext *s, TCGReg lo, TCGReg hi,
TCGReg base, MemOp opc, TCGType type)
{
const MIPSInsn lw1 = HOST_BIG_ENDIAN ? OPC_LWL : OPC_LWR;
const MIPSInsn lw2 = HOST_BIG_ENDIAN ? OPC_LWR : OPC_LWL;
const MIPSInsn ld1 = HOST_BIG_ENDIAN ? OPC_LDL : OPC_LDR;
const MIPSInsn ld2 = HOST_BIG_ENDIAN ? OPC_LDR : OPC_LDL;
bool sgn = opc & MO_SIGN;
switch (opc & MO_SIZE) {
case MO_16:
if (HOST_BIG_ENDIAN) {
tcg_out_opc_imm(s, sgn ? OPC_LB : OPC_LBU, TCG_TMP0, base, 0);
tcg_out_opc_imm(s, OPC_LBU, lo, base, 1);
if (use_mips32r2_instructions) {
tcg_out_opc_bf(s, OPC_INS, lo, TCG_TMP0, 31, 8);
} else {
tcg_out_opc_sa(s, OPC_SLL, TCG_TMP0, TCG_TMP0, 8);
tcg_out_opc_reg(s, OPC_OR, lo, lo, TCG_TMP0);
}
} else if (use_mips32r2_instructions && lo != base) {
tcg_out_opc_imm(s, OPC_LBU, lo, base, 0);
tcg_out_opc_imm(s, sgn ? OPC_LB : OPC_LBU, TCG_TMP0, base, 1);
tcg_out_opc_bf(s, OPC_INS, lo, TCG_TMP0, 31, 8);
} else {
tcg_out_opc_imm(s, OPC_LBU, TCG_TMP0, base, 0);
tcg_out_opc_imm(s, sgn ? OPC_LB : OPC_LBU, TCG_TMP1, base, 1);
tcg_out_opc_sa(s, OPC_SLL, TCG_TMP1, TCG_TMP1, 8);
tcg_out_opc_reg(s, OPC_OR, lo, TCG_TMP0, TCG_TMP1);
}
break;
case MO_32:
tcg_out_opc_imm(s, lw1, lo, base, 0);
tcg_out_opc_imm(s, lw2, lo, base, 3);
if (TCG_TARGET_REG_BITS == 64 && type == TCG_TYPE_I64 && !sgn) {
tcg_out_ext32u(s, lo, lo);
}
break;
case MO_64:
if (TCG_TARGET_REG_BITS == 64) {
tcg_out_opc_imm(s, ld1, lo, base, 0);
tcg_out_opc_imm(s, ld2, lo, base, 7);
} else {
tcg_out_opc_imm(s, lw1, HOST_BIG_ENDIAN ? hi : lo, base, 0 + 0);
tcg_out_opc_imm(s, lw2, HOST_BIG_ENDIAN ? hi : lo, base, 0 + 3);
tcg_out_opc_imm(s, lw1, HOST_BIG_ENDIAN ? lo : hi, base, 4 + 0);
tcg_out_opc_imm(s, lw2, HOST_BIG_ENDIAN ? lo : hi, base, 4 + 3);
}
break;
default:
g_assert_not_reached();
}
}
static void tcg_out_qemu_ld(TCGContext *s, TCGReg datalo, TCGReg datahi,
TCGReg addrlo, TCGReg addrhi,
MemOpIdx oi, TCGType data_type)
{
MemOp opc = get_memop(oi);
TCGLabelQemuLdst *ldst;
HostAddress h;
ldst = prepare_host_addr(s, &h, addrlo, addrhi, oi, true);
if (use_mips32r6_instructions || h.aa.align >= (opc & MO_SIZE)) {
tcg_out_qemu_ld_direct(s, datalo, datahi, h.base, opc, data_type);
} else {
tcg_out_qemu_ld_unalign(s, datalo, datahi, h.base, opc, data_type);
}
if (ldst) {
ldst->type = data_type;
ldst->datalo_reg = datalo;
ldst->datahi_reg = datahi;
ldst->raddr = tcg_splitwx_to_rx(s->code_ptr);
}
}
static void tcg_out_qemu_st_direct(TCGContext *s, TCGReg lo, TCGReg hi,
TCGReg base, MemOp opc)
{
switch (opc & MO_SIZE) {
case MO_8:
tcg_out_opc_imm(s, OPC_SB, lo, base, 0);
break;
case MO_16:
tcg_out_opc_imm(s, OPC_SH, lo, base, 0);
break;
case MO_32:
tcg_out_opc_imm(s, OPC_SW, lo, base, 0);
break;
case MO_64:
if (TCG_TARGET_REG_BITS == 64) {
tcg_out_opc_imm(s, OPC_SD, lo, base, 0);
} else {
tcg_out_opc_imm(s, OPC_SW, HOST_BIG_ENDIAN ? hi : lo, base, 0);
tcg_out_opc_imm(s, OPC_SW, HOST_BIG_ENDIAN ? lo : hi, base, 4);
}
break;
default:
g_assert_not_reached();
}
}
static void tcg_out_qemu_st_unalign(TCGContext *s, TCGReg lo, TCGReg hi,
TCGReg base, MemOp opc)
{
const MIPSInsn sw1 = HOST_BIG_ENDIAN ? OPC_SWL : OPC_SWR;
const MIPSInsn sw2 = HOST_BIG_ENDIAN ? OPC_SWR : OPC_SWL;
const MIPSInsn sd1 = HOST_BIG_ENDIAN ? OPC_SDL : OPC_SDR;
const MIPSInsn sd2 = HOST_BIG_ENDIAN ? OPC_SDR : OPC_SDL;
switch (opc & MO_SIZE) {
case MO_16:
tcg_out_opc_sa(s, OPC_SRL, TCG_TMP0, lo, 8);
tcg_out_opc_imm(s, OPC_SB, HOST_BIG_ENDIAN ? TCG_TMP0 : lo, base, 0);
tcg_out_opc_imm(s, OPC_SB, HOST_BIG_ENDIAN ? lo : TCG_TMP0, base, 1);
break;
case MO_32:
tcg_out_opc_imm(s, sw1, lo, base, 0);
tcg_out_opc_imm(s, sw2, lo, base, 3);
break;
case MO_64:
if (TCG_TARGET_REG_BITS == 64) {
tcg_out_opc_imm(s, sd1, lo, base, 0);
tcg_out_opc_imm(s, sd2, lo, base, 7);
} else {
tcg_out_opc_imm(s, sw1, HOST_BIG_ENDIAN ? hi : lo, base, 0 + 0);
tcg_out_opc_imm(s, sw2, HOST_BIG_ENDIAN ? hi : lo, base, 0 + 3);
tcg_out_opc_imm(s, sw1, HOST_BIG_ENDIAN ? lo : hi, base, 4 + 0);
tcg_out_opc_imm(s, sw2, HOST_BIG_ENDIAN ? lo : hi, base, 4 + 3);
}
break;
default:
g_assert_not_reached();
}
}
static void tcg_out_qemu_st(TCGContext *s, TCGReg datalo, TCGReg datahi,
TCGReg addrlo, TCGReg addrhi,
MemOpIdx oi, TCGType data_type)
{
MemOp opc = get_memop(oi);
TCGLabelQemuLdst *ldst;
HostAddress h;
ldst = prepare_host_addr(s, &h, addrlo, addrhi, oi, false);
if (use_mips32r6_instructions || h.aa.align >= (opc & MO_SIZE)) {
tcg_out_qemu_st_direct(s, datalo, datahi, h.base, opc);
} else {
tcg_out_qemu_st_unalign(s, datalo, datahi, h.base, opc);
}
if (ldst) {
ldst->type = data_type;
ldst->datalo_reg = datalo;
ldst->datahi_reg = datahi;
ldst->raddr = tcg_splitwx_to_rx(s->code_ptr);
}
}
static void tcg_out_mb(TCGContext *s, TCGArg a0)
{
static const MIPSInsn sync[] = {
/* Note that SYNC_MB is a slightly weaker than SYNC 0,
as the former is an ordering barrier and the latter
is a completion barrier. */
[0 ... TCG_MO_ALL] = OPC_SYNC_MB,
[TCG_MO_LD_LD] = OPC_SYNC_RMB,
[TCG_MO_ST_ST] = OPC_SYNC_WMB,
[TCG_MO_LD_ST] = OPC_SYNC_RELEASE,
[TCG_MO_LD_ST | TCG_MO_ST_ST] = OPC_SYNC_RELEASE,
[TCG_MO_LD_ST | TCG_MO_LD_LD] = OPC_SYNC_ACQUIRE,
};
tcg_out32(s, sync[a0 & TCG_MO_ALL]);
}
static void tcg_out_clz(TCGContext *s, MIPSInsn opcv2, MIPSInsn opcv6,
int width, TCGReg a0, TCGReg a1, TCGArg a2)
{
if (use_mips32r6_instructions) {
if (a2 == width) {
tcg_out_opc_reg(s, opcv6, a0, a1, 0);
} else {
tcg_out_opc_reg(s, opcv6, TCG_TMP0, a1, 0);
tcg_out_movcond(s, TCG_COND_EQ, a0, a1, 0, a2, TCG_TMP0);
}
} else {
if (a2 == width) {
tcg_out_opc_reg(s, opcv2, a0, a1, a1);
} else if (a0 == a2) {
tcg_out_opc_reg(s, opcv2, TCG_TMP0, a1, a1);
tcg_out_opc_reg(s, OPC_MOVN, a0, TCG_TMP0, a1);
} else if (a0 != a1) {
tcg_out_opc_reg(s, opcv2, a0, a1, a1);
tcg_out_opc_reg(s, OPC_MOVZ, a0, a2, a1);
} else {
tcg_out_opc_reg(s, opcv2, TCG_TMP0, a1, a1);
tcg_out_opc_reg(s, OPC_MOVZ, TCG_TMP0, a2, a1);
tcg_out_mov(s, TCG_TYPE_REG, a0, TCG_TMP0);
}
}
}
static void tcg_out_exit_tb(TCGContext *s, uintptr_t a0)
{
TCGReg base = TCG_REG_ZERO;
int16_t lo = 0;
if (a0) {
intptr_t ofs;
if (TCG_TARGET_REG_BITS == 64) {
ofs = tcg_tbrel_diff(s, (void *)a0);
lo = ofs;
if (ofs == lo) {
base = TCG_REG_TB;
} else {
base = TCG_REG_V0;
tcg_out_movi(s, TCG_TYPE_PTR, base, ofs - lo);
tcg_out_opc_reg(s, ALIAS_PADD, base, base, TCG_REG_TB);
}
} else {
ofs = a0;
lo = ofs;
base = TCG_REG_V0;
tcg_out_movi(s, TCG_TYPE_PTR, base, ofs - lo);
}
}
if (!tcg_out_opc_jmp(s, OPC_J, tb_ret_addr)) {
tcg_out_movi(s, TCG_TYPE_PTR, TCG_TMP0, (uintptr_t)tb_ret_addr);
tcg_out_opc_reg(s, OPC_JR, 0, TCG_TMP0, 0);
}
/* delay slot */
tcg_out_opc_imm(s, ALIAS_PADDI, TCG_REG_V0, base, lo);
}
static void tcg_out_goto_tb(TCGContext *s, int which)
{
intptr_t ofs = get_jmp_target_addr(s, which);
TCGReg base, dest;
/* indirect jump method */
if (TCG_TARGET_REG_BITS == 64) {
dest = TCG_REG_TB;
base = TCG_REG_TB;
ofs = tcg_tbrel_diff(s, (void *)ofs);
} else {
dest = TCG_TMP0;
base = TCG_REG_ZERO;
}
tcg_out_ld(s, TCG_TYPE_PTR, dest, base, ofs);
tcg_out_opc_reg(s, OPC_JR, 0, dest, 0);
/* delay slot */
tcg_out_nop(s);
set_jmp_reset_offset(s, which);
if (TCG_TARGET_REG_BITS == 64) {
/* For the unlinked case, need to reset TCG_REG_TB. */
tcg_out_ldst(s, ALIAS_PADDI, TCG_REG_TB, TCG_REG_TB,
-tcg_current_code_size(s));
}
}
void tb_target_set_jmp_target(const TranslationBlock *tb, int n,
uintptr_t jmp_rx, uintptr_t jmp_rw)
{
/* Always indirect, nothing to do */
}
static void tcg_out_op(TCGContext *s, TCGOpcode opc,
const TCGArg args[TCG_MAX_OP_ARGS],
const int const_args[TCG_MAX_OP_ARGS])
{
MIPSInsn i1, i2;
TCGArg a0, a1, a2;
int c2;
/*
* Note that many operands use the constraint set "rZ".
* We make use of the fact that 0 is the ZERO register,
* and hence such cases need not check for const_args.
*/
a0 = args[0];
a1 = args[1];
a2 = args[2];
c2 = const_args[2];
switch (opc) {
case INDEX_op_goto_ptr:
/* jmp to the given host address (could be epilogue) */
tcg_out_opc_reg(s, OPC_JR, 0, a0, 0);
if (TCG_TARGET_REG_BITS == 64) {
tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_TB, a0);
} else {
tcg_out_nop(s);
}
break;
case INDEX_op_br:
tcg_out_brcond(s, TCG_COND_EQ, TCG_REG_ZERO, TCG_REG_ZERO,
arg_label(a0));
break;
case INDEX_op_ld8u_i32:
case INDEX_op_ld8u_i64:
i1 = OPC_LBU;
goto do_ldst;
case INDEX_op_ld8s_i32:
case INDEX_op_ld8s_i64:
i1 = OPC_LB;
goto do_ldst;
case INDEX_op_ld16u_i32:
case INDEX_op_ld16u_i64:
i1 = OPC_LHU;
goto do_ldst;
case INDEX_op_ld16s_i32:
case INDEX_op_ld16s_i64:
i1 = OPC_LH;
goto do_ldst;
case INDEX_op_ld_i32:
case INDEX_op_ld32s_i64:
i1 = OPC_LW;
goto do_ldst;
case INDEX_op_ld32u_i64:
i1 = OPC_LWU;
goto do_ldst;
case INDEX_op_ld_i64:
i1 = OPC_LD;
goto do_ldst;
case INDEX_op_st8_i32:
case INDEX_op_st8_i64:
i1 = OPC_SB;
goto do_ldst;
case INDEX_op_st16_i32:
case INDEX_op_st16_i64:
i1 = OPC_SH;
goto do_ldst;
case INDEX_op_st_i32:
case INDEX_op_st32_i64:
i1 = OPC_SW;
goto do_ldst;
case INDEX_op_st_i64:
i1 = OPC_SD;
do_ldst:
tcg_out_ldst(s, i1, a0, a1, a2);
break;
case INDEX_op_add_i32:
i1 = OPC_ADDU, i2 = OPC_ADDIU;
goto do_binary;
case INDEX_op_add_i64:
i1 = OPC_DADDU, i2 = OPC_DADDIU;
goto do_binary;
case INDEX_op_or_i32:
case INDEX_op_or_i64:
i1 = OPC_OR, i2 = OPC_ORI;
goto do_binary;
case INDEX_op_xor_i32:
case INDEX_op_xor_i64:
i1 = OPC_XOR, i2 = OPC_XORI;
do_binary:
if (c2) {
tcg_out_opc_imm(s, i2, a0, a1, a2);
break;
}
do_binaryv:
tcg_out_opc_reg(s, i1, a0, a1, a2);
break;
case INDEX_op_sub_i32:
i1 = OPC_SUBU, i2 = OPC_ADDIU;
goto do_subtract;
case INDEX_op_sub_i64:
i1 = OPC_DSUBU, i2 = OPC_DADDIU;
do_subtract:
if (c2) {
tcg_out_opc_imm(s, i2, a0, a1, -a2);
break;
}
goto do_binaryv;
case INDEX_op_and_i32:
if (c2 && a2 != (uint16_t)a2) {
int msb = ctz32(~a2) - 1;
tcg_debug_assert(use_mips32r2_instructions);
tcg_debug_assert(is_p2m1(a2));
tcg_out_opc_bf(s, OPC_EXT, a0, a1, msb, 0);
break;
}
i1 = OPC_AND, i2 = OPC_ANDI;
goto do_binary;
case INDEX_op_and_i64:
if (c2 && a2 != (uint16_t)a2) {
int msb = ctz64(~a2) - 1;
tcg_debug_assert(use_mips32r2_instructions);
tcg_debug_assert(is_p2m1(a2));
tcg_out_opc_bf64(s, OPC_DEXT, OPC_DEXTM, OPC_DEXTU, a0, a1, msb, 0);
break;
}
i1 = OPC_AND, i2 = OPC_ANDI;
goto do_binary;
case INDEX_op_nor_i32:
case INDEX_op_nor_i64:
i1 = OPC_NOR;
goto do_binaryv;
case INDEX_op_mul_i32:
if (use_mips32_instructions) {
tcg_out_opc_reg(s, OPC_MUL, a0, a1, a2);
break;
}
i1 = OPC_MULT, i2 = OPC_MFLO;
goto do_hilo1;
case INDEX_op_mulsh_i32:
if (use_mips32r6_instructions) {
tcg_out_opc_reg(s, OPC_MUH, a0, a1, a2);
break;
}
i1 = OPC_MULT, i2 = OPC_MFHI;
goto do_hilo1;
case INDEX_op_muluh_i32:
if (use_mips32r6_instructions) {
tcg_out_opc_reg(s, OPC_MUHU, a0, a1, a2);
break;
}
i1 = OPC_MULTU, i2 = OPC_MFHI;
goto do_hilo1;
case INDEX_op_div_i32:
if (use_mips32r6_instructions) {
tcg_out_opc_reg(s, OPC_DIV_R6, a0, a1, a2);
break;
}
i1 = OPC_DIV, i2 = OPC_MFLO;
goto do_hilo1;
case INDEX_op_divu_i32:
if (use_mips32r6_instructions) {
tcg_out_opc_reg(s, OPC_DIVU_R6, a0, a1, a2);
break;
}
i1 = OPC_DIVU, i2 = OPC_MFLO;
goto do_hilo1;
case INDEX_op_rem_i32:
if (use_mips32r6_instructions) {
tcg_out_opc_reg(s, OPC_MOD, a0, a1, a2);
break;
}
i1 = OPC_DIV, i2 = OPC_MFHI;
goto do_hilo1;
case INDEX_op_remu_i32:
if (use_mips32r6_instructions) {
tcg_out_opc_reg(s, OPC_MODU, a0, a1, a2);
break;
}
i1 = OPC_DIVU, i2 = OPC_MFHI;
goto do_hilo1;
case INDEX_op_mul_i64:
if (use_mips32r6_instructions) {
tcg_out_opc_reg(s, OPC_DMUL, a0, a1, a2);
break;
}
i1 = OPC_DMULT, i2 = OPC_MFLO;
goto do_hilo1;
case INDEX_op_mulsh_i64:
if (use_mips32r6_instructions) {
tcg_out_opc_reg(s, OPC_DMUH, a0, a1, a2);
break;
}
i1 = OPC_DMULT, i2 = OPC_MFHI;
goto do_hilo1;
case INDEX_op_muluh_i64:
if (use_mips32r6_instructions) {
tcg_out_opc_reg(s, OPC_DMUHU, a0, a1, a2);
break;
}
i1 = OPC_DMULTU, i2 = OPC_MFHI;
goto do_hilo1;
case INDEX_op_div_i64:
if (use_mips32r6_instructions) {
tcg_out_opc_reg(s, OPC_DDIV_R6, a0, a1, a2);
break;
}
i1 = OPC_DDIV, i2 = OPC_MFLO;
goto do_hilo1;
case INDEX_op_divu_i64:
if (use_mips32r6_instructions) {
tcg_out_opc_reg(s, OPC_DDIVU_R6, a0, a1, a2);
break;
}
i1 = OPC_DDIVU, i2 = OPC_MFLO;
goto do_hilo1;
case INDEX_op_rem_i64:
if (use_mips32r6_instructions) {
tcg_out_opc_reg(s, OPC_DMOD, a0, a1, a2);
break;
}
i1 = OPC_DDIV, i2 = OPC_MFHI;
goto do_hilo1;
case INDEX_op_remu_i64:
if (use_mips32r6_instructions) {
tcg_out_opc_reg(s, OPC_DMODU, a0, a1, a2);
break;
}
i1 = OPC_DDIVU, i2 = OPC_MFHI;
do_hilo1:
tcg_out_opc_reg(s, i1, 0, a1, a2);
tcg_out_opc_reg(s, i2, a0, 0, 0);
break;
case INDEX_op_muls2_i32:
i1 = OPC_MULT;
goto do_hilo2;
case INDEX_op_mulu2_i32:
i1 = OPC_MULTU;
goto do_hilo2;
case INDEX_op_muls2_i64:
i1 = OPC_DMULT;
goto do_hilo2;
case INDEX_op_mulu2_i64:
i1 = OPC_DMULTU;
do_hilo2:
tcg_out_opc_reg(s, i1, 0, a2, args[3]);
tcg_out_opc_reg(s, OPC_MFLO, a0, 0, 0);
tcg_out_opc_reg(s, OPC_MFHI, a1, 0, 0);
break;
case INDEX_op_not_i32:
case INDEX_op_not_i64:
i1 = OPC_NOR;
goto do_unary;
do_unary:
tcg_out_opc_reg(s, i1, a0, TCG_REG_ZERO, a1);
break;
case INDEX_op_bswap16_i32:
case INDEX_op_bswap16_i64:
tcg_out_bswap16(s, a0, a1, a2);
break;
case INDEX_op_bswap32_i32:
tcg_out_bswap32(s, a0, a1, 0);
break;
case INDEX_op_bswap32_i64:
tcg_out_bswap32(s, a0, a1, a2);
break;
case INDEX_op_bswap64_i64:
tcg_out_bswap64(s, a0, a1);
break;
case INDEX_op_extrh_i64_i32:
tcg_out_dsra(s, a0, a1, 32);
break;
case INDEX_op_sar_i32:
i1 = OPC_SRAV, i2 = OPC_SRA;
goto do_shift;
case INDEX_op_shl_i32:
i1 = OPC_SLLV, i2 = OPC_SLL;
goto do_shift;
case INDEX_op_shr_i32:
i1 = OPC_SRLV, i2 = OPC_SRL;
goto do_shift;
case INDEX_op_rotr_i32:
i1 = OPC_ROTRV, i2 = OPC_ROTR;
do_shift:
if (c2) {
tcg_out_opc_sa(s, i2, a0, a1, a2);
break;
}
do_shiftv:
tcg_out_opc_reg(s, i1, a0, a2, a1);
break;
case INDEX_op_rotl_i32:
if (c2) {
tcg_out_opc_sa(s, OPC_ROTR, a0, a1, 32 - a2);
} else {
tcg_out_opc_reg(s, OPC_SUBU, TCG_TMP0, TCG_REG_ZERO, a2);
tcg_out_opc_reg(s, OPC_ROTRV, a0, TCG_TMP0, a1);
}
break;
case INDEX_op_sar_i64:
if (c2) {
tcg_out_dsra(s, a0, a1, a2);
break;
}
i1 = OPC_DSRAV;
goto do_shiftv;
case INDEX_op_shl_i64:
if (c2) {
tcg_out_dsll(s, a0, a1, a2);
break;
}
i1 = OPC_DSLLV;
goto do_shiftv;
case INDEX_op_shr_i64:
if (c2) {
tcg_out_dsrl(s, a0, a1, a2);
break;
}
i1 = OPC_DSRLV;
goto do_shiftv;
case INDEX_op_rotr_i64:
if (c2) {
tcg_out_opc_sa64(s, OPC_DROTR, OPC_DROTR32, a0, a1, a2);
break;
}
i1 = OPC_DROTRV;
goto do_shiftv;
case INDEX_op_rotl_i64:
if (c2) {
tcg_out_opc_sa64(s, OPC_DROTR, OPC_DROTR32, a0, a1, 64 - a2);
} else {
tcg_out_opc_reg(s, OPC_DSUBU, TCG_TMP0, TCG_REG_ZERO, a2);
tcg_out_opc_reg(s, OPC_DROTRV, a0, TCG_TMP0, a1);
}
break;
case INDEX_op_clz_i32:
tcg_out_clz(s, OPC_CLZ, OPC_CLZ_R6, 32, a0, a1, a2);
break;
case INDEX_op_clz_i64:
tcg_out_clz(s, OPC_DCLZ, OPC_DCLZ_R6, 64, a0, a1, a2);
break;
case INDEX_op_deposit_i32:
tcg_out_opc_bf(s, OPC_INS, a0, a2, args[3] + args[4] - 1, args[3]);
break;
case INDEX_op_deposit_i64:
tcg_out_opc_bf64(s, OPC_DINS, OPC_DINSM, OPC_DINSU, a0, a2,
args[3] + args[4] - 1, args[3]);
break;
case INDEX_op_extract_i32:
tcg_out_opc_bf(s, OPC_EXT, a0, a1, args[3] - 1, a2);
break;
case INDEX_op_extract_i64:
tcg_out_opc_bf64(s, OPC_DEXT, OPC_DEXTM, OPC_DEXTU, a0, a1,
args[3] - 1, a2);
break;
case INDEX_op_brcond_i32:
case INDEX_op_brcond_i64:
tcg_out_brcond(s, a2, a0, a1, arg_label(args[3]));
break;
case INDEX_op_brcond2_i32:
tcg_out_brcond2(s, args[4], a0, a1, a2, args[3], arg_label(args[5]));
break;
case INDEX_op_movcond_i32:
case INDEX_op_movcond_i64:
tcg_out_movcond(s, args[5], a0, a1, a2, args[3], args[4]);
break;
case INDEX_op_setcond_i32:
case INDEX_op_setcond_i64:
tcg_out_setcond(s, args[3], a0, a1, a2);
break;
case INDEX_op_setcond2_i32:
tcg_out_setcond2(s, args[5], a0, a1, a2, args[3], args[4]);
break;
case INDEX_op_qemu_ld_a64_i32:
if (TCG_TARGET_REG_BITS == 32) {
tcg_out_qemu_ld(s, a0, 0, a1, a2, args[3], TCG_TYPE_I32);
break;
}
/* fall through */
case INDEX_op_qemu_ld_a32_i32:
tcg_out_qemu_ld(s, a0, 0, a1, 0, a2, TCG_TYPE_I32);
break;
case INDEX_op_qemu_ld_a32_i64:
if (TCG_TARGET_REG_BITS == 64) {
tcg_out_qemu_ld(s, a0, 0, a1, 0, a2, TCG_TYPE_I64);
} else {
tcg_out_qemu_ld(s, a0, a1, a2, 0, args[3], TCG_TYPE_I64);
}
break;
case INDEX_op_qemu_ld_a64_i64:
if (TCG_TARGET_REG_BITS == 64) {
tcg_out_qemu_ld(s, a0, 0, a1, 0, a2, TCG_TYPE_I64);
} else {
tcg_out_qemu_ld(s, a0, a1, a2, args[3], args[4], TCG_TYPE_I64);
}
break;
case INDEX_op_qemu_st_a64_i32:
if (TCG_TARGET_REG_BITS == 32) {
tcg_out_qemu_st(s, a0, 0, a1, a2, args[3], TCG_TYPE_I32);
break;
}
/* fall through */
case INDEX_op_qemu_st_a32_i32:
tcg_out_qemu_st(s, a0, 0, a1, 0, a2, TCG_TYPE_I32);
break;
case INDEX_op_qemu_st_a32_i64:
if (TCG_TARGET_REG_BITS == 64) {
tcg_out_qemu_st(s, a0, 0, a1, 0, a2, TCG_TYPE_I64);
} else {
tcg_out_qemu_st(s, a0, a1, a2, 0, args[3], TCG_TYPE_I64);
}
break;
case INDEX_op_qemu_st_a64_i64:
if (TCG_TARGET_REG_BITS == 64) {
tcg_out_qemu_st(s, a0, 0, a1, 0, a2, TCG_TYPE_I64);
} else {
tcg_out_qemu_st(s, a0, a1, a2, args[3], args[4], TCG_TYPE_I64);
}
break;
case INDEX_op_add2_i32:
tcg_out_addsub2(s, a0, a1, a2, args[3], args[4], args[5],
const_args[4], const_args[5], false);
break;
case INDEX_op_sub2_i32:
tcg_out_addsub2(s, a0, a1, a2, args[3], args[4], args[5],
const_args[4], const_args[5], true);
break;
case INDEX_op_mb:
tcg_out_mb(s, a0);
break;
case INDEX_op_mov_i32: /* Always emitted via tcg_out_mov. */
case INDEX_op_mov_i64:
case INDEX_op_call: /* Always emitted via tcg_out_call. */
case INDEX_op_exit_tb: /* Always emitted via tcg_out_exit_tb. */
case INDEX_op_goto_tb: /* Always emitted via tcg_out_goto_tb. */
case INDEX_op_ext8s_i32: /* Always emitted via tcg_reg_alloc_op. */
case INDEX_op_ext8s_i64:
case INDEX_op_ext8u_i32:
case INDEX_op_ext8u_i64:
case INDEX_op_ext16s_i32:
case INDEX_op_ext16s_i64:
case INDEX_op_ext32s_i64:
case INDEX_op_ext32u_i64:
case INDEX_op_ext_i32_i64:
case INDEX_op_extu_i32_i64:
case INDEX_op_extrl_i64_i32:
default:
g_assert_not_reached();
}
}
static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
{
switch (op) {
case INDEX_op_goto_ptr:
return C_O0_I1(r);
case INDEX_op_ld8u_i32:
case INDEX_op_ld8s_i32:
case INDEX_op_ld16u_i32:
case INDEX_op_ld16s_i32:
case INDEX_op_ld_i32:
case INDEX_op_not_i32:
case INDEX_op_bswap16_i32:
case INDEX_op_bswap32_i32:
case INDEX_op_ext8s_i32:
case INDEX_op_ext16s_i32:
case INDEX_op_extract_i32:
case INDEX_op_ld8u_i64:
case INDEX_op_ld8s_i64:
case INDEX_op_ld16u_i64:
case INDEX_op_ld16s_i64:
case INDEX_op_ld32s_i64:
case INDEX_op_ld32u_i64:
case INDEX_op_ld_i64:
case INDEX_op_not_i64:
case INDEX_op_bswap16_i64:
case INDEX_op_bswap32_i64:
case INDEX_op_bswap64_i64:
case INDEX_op_ext8s_i64:
case INDEX_op_ext16s_i64:
case INDEX_op_ext32s_i64:
case INDEX_op_ext32u_i64:
case INDEX_op_ext_i32_i64:
case INDEX_op_extu_i32_i64:
case INDEX_op_extrl_i64_i32:
case INDEX_op_extrh_i64_i32:
case INDEX_op_extract_i64:
return C_O1_I1(r, r);
case INDEX_op_st8_i32:
case INDEX_op_st16_i32:
case INDEX_op_st_i32:
case INDEX_op_st8_i64:
case INDEX_op_st16_i64:
case INDEX_op_st32_i64:
case INDEX_op_st_i64:
return C_O0_I2(rZ, r);
case INDEX_op_add_i32:
case INDEX_op_add_i64:
return C_O1_I2(r, r, rJ);
case INDEX_op_sub_i32:
case INDEX_op_sub_i64:
return C_O1_I2(r, rZ, rN);
case INDEX_op_mul_i32:
case INDEX_op_mulsh_i32:
case INDEX_op_muluh_i32:
case INDEX_op_div_i32:
case INDEX_op_divu_i32:
case INDEX_op_rem_i32:
case INDEX_op_remu_i32:
case INDEX_op_nor_i32:
case INDEX_op_setcond_i32:
case INDEX_op_mul_i64:
case INDEX_op_mulsh_i64:
case INDEX_op_muluh_i64:
case INDEX_op_div_i64:
case INDEX_op_divu_i64:
case INDEX_op_rem_i64:
case INDEX_op_remu_i64:
case INDEX_op_nor_i64:
case INDEX_op_setcond_i64:
return C_O1_I2(r, rZ, rZ);
case INDEX_op_muls2_i32:
case INDEX_op_mulu2_i32:
case INDEX_op_muls2_i64:
case INDEX_op_mulu2_i64:
return C_O2_I2(r, r, r, r);
case INDEX_op_and_i32:
case INDEX_op_and_i64:
return C_O1_I2(r, r, rIK);
case INDEX_op_or_i32:
case INDEX_op_xor_i32:
case INDEX_op_or_i64:
case INDEX_op_xor_i64:
return C_O1_I2(r, r, rI);
case INDEX_op_shl_i32:
case INDEX_op_shr_i32:
case INDEX_op_sar_i32:
case INDEX_op_rotr_i32:
case INDEX_op_rotl_i32:
case INDEX_op_shl_i64:
case INDEX_op_shr_i64:
case INDEX_op_sar_i64:
case INDEX_op_rotr_i64:
case INDEX_op_rotl_i64:
return C_O1_I2(r, r, ri);
case INDEX_op_clz_i32:
case INDEX_op_clz_i64:
return C_O1_I2(r, r, rWZ);
case INDEX_op_deposit_i32:
case INDEX_op_deposit_i64:
return C_O1_I2(r, 0, rZ);
case INDEX_op_brcond_i32:
case INDEX_op_brcond_i64:
return C_O0_I2(rZ, rZ);
case INDEX_op_movcond_i32:
case INDEX_op_movcond_i64:
return (use_mips32r6_instructions
? C_O1_I4(r, rZ, rZ, rZ, rZ)
: C_O1_I4(r, rZ, rZ, rZ, 0));
case INDEX_op_add2_i32:
case INDEX_op_sub2_i32:
return C_O2_I4(r, r, rZ, rZ, rN, rN);
case INDEX_op_setcond2_i32:
return C_O1_I4(r, rZ, rZ, rZ, rZ);
case INDEX_op_brcond2_i32:
return C_O0_I4(rZ, rZ, rZ, rZ);
case INDEX_op_qemu_ld_a32_i32:
return C_O1_I1(r, r);
case INDEX_op_qemu_ld_a64_i32:
return TCG_TARGET_REG_BITS == 64 ? C_O1_I1(r, r) : C_O1_I2(r, r, r);
case INDEX_op_qemu_st_a32_i32:
return C_O0_I2(rZ, r);
case INDEX_op_qemu_st_a64_i32:
return TCG_TARGET_REG_BITS == 64 ? C_O0_I2(rZ, r) : C_O0_I3(rZ, r, r);
case INDEX_op_qemu_ld_a32_i64:
return TCG_TARGET_REG_BITS == 64 ? C_O1_I1(r, r) : C_O2_I1(r, r, r);
case INDEX_op_qemu_ld_a64_i64:
return TCG_TARGET_REG_BITS == 64 ? C_O1_I1(r, r) : C_O2_I2(r, r, r, r);
case INDEX_op_qemu_st_a32_i64:
return TCG_TARGET_REG_BITS == 64 ? C_O0_I2(rZ, r) : C_O0_I3(rZ, rZ, r);
case INDEX_op_qemu_st_a64_i64:
return (TCG_TARGET_REG_BITS == 64 ? C_O0_I2(rZ, r)
: C_O0_I4(rZ, rZ, r, r));
default:
g_assert_not_reached();
}
}
static const int tcg_target_callee_save_regs[] = {
TCG_REG_S0,
TCG_REG_S1,
TCG_REG_S2,
TCG_REG_S3,
TCG_REG_S4,
TCG_REG_S5,
TCG_REG_S6, /* used for the tb base (TCG_REG_TB) */
TCG_REG_S7, /* used for guest_base */
TCG_REG_S8, /* used for the global env (TCG_AREG0) */
TCG_REG_RA, /* should be last for ABI compliance */
};
/* The Linux kernel doesn't provide any information about the available
instruction set. Probe it using a signal handler. */
#ifndef use_movnz_instructions
bool use_movnz_instructions = false;
#endif
#ifndef use_mips32_instructions
bool use_mips32_instructions = false;
#endif
#ifndef use_mips32r2_instructions
bool use_mips32r2_instructions = false;
#endif
static volatile sig_atomic_t got_sigill;
static void sigill_handler(int signo, siginfo_t *si, void *data)
{
/* Skip the faulty instruction */
ucontext_t *uc = (ucontext_t *)data;
uc->uc_mcontext.pc += 4;
got_sigill = 1;
}
static void tcg_target_detect_isa(void)
{
struct sigaction sa_old, sa_new;
memset(&sa_new, 0, sizeof(sa_new));
sa_new.sa_flags = SA_SIGINFO;
sa_new.sa_sigaction = sigill_handler;
sigaction(SIGILL, &sa_new, &sa_old);
/* Probe for movn/movz, necessary to implement movcond. */
#ifndef use_movnz_instructions
got_sigill = 0;
asm volatile(".set push\n"
".set mips32\n"
"movn $zero, $zero, $zero\n"
"movz $zero, $zero, $zero\n"
".set pop\n"
: : : );
use_movnz_instructions = !got_sigill;
#endif
/* Probe for MIPS32 instructions. As no subsetting is allowed
by the specification, it is only necessary to probe for one
of the instructions. */
#ifndef use_mips32_instructions
got_sigill = 0;
asm volatile(".set push\n"
".set mips32\n"
"mul $zero, $zero\n"
".set pop\n"
: : : );
use_mips32_instructions = !got_sigill;
#endif
/* Probe for MIPS32r2 instructions if MIPS32 instructions are
available. As no subsetting is allowed by the specification,
it is only necessary to probe for one of the instructions. */
#ifndef use_mips32r2_instructions
if (use_mips32_instructions) {
got_sigill = 0;
asm volatile(".set push\n"
".set mips32r2\n"
"seb $zero, $zero\n"
".set pop\n"
: : : );
use_mips32r2_instructions = !got_sigill;
}
#endif
sigaction(SIGILL, &sa_old, NULL);
}
static tcg_insn_unit *align_code_ptr(TCGContext *s)
{
uintptr_t p = (uintptr_t)s->code_ptr;
if (p & 15) {
p = (p + 15) & -16;
s->code_ptr = (void *)p;
}
return s->code_ptr;
}
/* Stack frame parameters. */
#define REG_SIZE (TCG_TARGET_REG_BITS / 8)
#define SAVE_SIZE ((int)ARRAY_SIZE(tcg_target_callee_save_regs) * REG_SIZE)
#define TEMP_SIZE (CPU_TEMP_BUF_NLONGS * (int)sizeof(long))
#define FRAME_SIZE ((TCG_STATIC_CALL_ARGS_SIZE + TEMP_SIZE + SAVE_SIZE \
+ TCG_TARGET_STACK_ALIGN - 1) \
& -TCG_TARGET_STACK_ALIGN)
#define SAVE_OFS (TCG_STATIC_CALL_ARGS_SIZE + TEMP_SIZE)
/* We're expecting to be able to use an immediate for frame allocation. */
QEMU_BUILD_BUG_ON(FRAME_SIZE > 0x7fff);
/* Generate global QEMU prologue and epilogue code */
static void tcg_target_qemu_prologue(TCGContext *s)
{
int i;
tcg_set_frame(s, TCG_REG_SP, TCG_STATIC_CALL_ARGS_SIZE, TEMP_SIZE);
/* TB prologue */
tcg_out_opc_imm(s, ALIAS_PADDI, TCG_REG_SP, TCG_REG_SP, -FRAME_SIZE);
for (i = 0; i < ARRAY_SIZE(tcg_target_callee_save_regs); i++) {
tcg_out_st(s, TCG_TYPE_REG, tcg_target_callee_save_regs[i],
TCG_REG_SP, SAVE_OFS + i * REG_SIZE);
}
#ifndef CONFIG_SOFTMMU
if (guest_base != (int16_t)guest_base) {
/*
* The function call abi for n32 and n64 will have loaded $25 (t9)
* with the address of the prologue, so we can use that instead
* of TCG_REG_TB.
*/
#if TCG_TARGET_REG_BITS == 64 && !defined(__mips_abicalls)
# error "Unknown mips abi"
#endif
tcg_out_movi_int(s, TCG_TYPE_PTR, TCG_GUEST_BASE_REG, guest_base,
TCG_TARGET_REG_BITS == 64 ? TCG_REG_T9 : 0);
tcg_regset_set_reg(s->reserved_regs, TCG_GUEST_BASE_REG);
}
#endif
if (TCG_TARGET_REG_BITS == 64) {
tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_TB, tcg_target_call_iarg_regs[1]);
}
/* Call generated code */
tcg_out_opc_reg(s, OPC_JR, 0, tcg_target_call_iarg_regs[1], 0);
/* delay slot */
tcg_out_mov(s, TCG_TYPE_PTR, TCG_AREG0, tcg_target_call_iarg_regs[0]);
/*
* Return path for goto_ptr. Set return value to 0, a-la exit_tb,
* and fall through to the rest of the epilogue.
*/
tcg_code_gen_epilogue = tcg_splitwx_to_rx(s->code_ptr);
tcg_out_mov(s, TCG_TYPE_REG, TCG_REG_V0, TCG_REG_ZERO);
/* TB epilogue */
tb_ret_addr = tcg_splitwx_to_rx(s->code_ptr);
for (i = 0; i < ARRAY_SIZE(tcg_target_callee_save_regs); i++) {
tcg_out_ld(s, TCG_TYPE_REG, tcg_target_callee_save_regs[i],
TCG_REG_SP, SAVE_OFS + i * REG_SIZE);
}
tcg_out_opc_reg(s, OPC_JR, 0, TCG_REG_RA, 0);
/* delay slot */
tcg_out_opc_imm(s, ALIAS_PADDI, TCG_REG_SP, TCG_REG_SP, FRAME_SIZE);
if (use_mips32r2_instructions) {
return;
}
/* Bswap subroutines: Input in TCG_TMP0, output in TCG_TMP3;
clobbers TCG_TMP1, TCG_TMP2. */
/*
* bswap32 -- 32-bit swap (signed result for mips64). a0 = abcd.
*/
bswap32_addr = tcg_splitwx_to_rx(align_code_ptr(s));
/* t3 = (ssss)d000 */
tcg_out_opc_sa(s, OPC_SLL, TCG_TMP3, TCG_TMP0, 24);
/* t1 = 000a */
tcg_out_opc_sa(s, OPC_SRL, TCG_TMP1, TCG_TMP0, 24);
/* t2 = 00c0 */
tcg_out_opc_imm(s, OPC_ANDI, TCG_TMP2, TCG_TMP0, 0xff00);
/* t3 = d00a */
tcg_out_opc_reg(s, OPC_OR, TCG_TMP3, TCG_TMP3, TCG_TMP1);
/* t1 = 0abc */
tcg_out_opc_sa(s, OPC_SRL, TCG_TMP1, TCG_TMP0, 8);
/* t2 = 0c00 */
tcg_out_opc_sa(s, OPC_SLL, TCG_TMP2, TCG_TMP2, 8);
/* t1 = 00b0 */
tcg_out_opc_imm(s, OPC_ANDI, TCG_TMP1, TCG_TMP1, 0xff00);
/* t3 = dc0a */
tcg_out_opc_reg(s, OPC_OR, TCG_TMP3, TCG_TMP3, TCG_TMP2);
tcg_out_opc_reg(s, OPC_JR, 0, TCG_REG_RA, 0);
/* t3 = dcba -- delay slot */
tcg_out_opc_reg(s, OPC_OR, TCG_TMP3, TCG_TMP3, TCG_TMP1);
if (TCG_TARGET_REG_BITS == 32) {
return;
}
/*
* bswap32u -- unsigned 32-bit swap. a0 = ....abcd.
*/
bswap32u_addr = tcg_splitwx_to_rx(align_code_ptr(s));
/* t1 = (0000)000d */
tcg_out_opc_imm(s, OPC_ANDI, TCG_TMP1, TCG_TMP0, 0xff);
/* t3 = 000a */
tcg_out_opc_sa(s, OPC_SRL, TCG_TMP3, TCG_TMP0, 24);
/* t1 = (0000)d000 */
tcg_out_dsll(s, TCG_TMP1, TCG_TMP1, 24);
/* t2 = 00c0 */
tcg_out_opc_imm(s, OPC_ANDI, TCG_TMP2, TCG_TMP0, 0xff00);
/* t3 = d00a */
tcg_out_opc_reg(s, OPC_OR, TCG_TMP3, TCG_TMP3, TCG_TMP1);
/* t1 = 0abc */
tcg_out_opc_sa(s, OPC_SRL, TCG_TMP1, TCG_TMP0, 8);
/* t2 = 0c00 */
tcg_out_opc_sa(s, OPC_SLL, TCG_TMP2, TCG_TMP2, 8);
/* t1 = 00b0 */
tcg_out_opc_imm(s, OPC_ANDI, TCG_TMP1, TCG_TMP1, 0xff00);
/* t3 = dc0a */
tcg_out_opc_reg(s, OPC_OR, TCG_TMP3, TCG_TMP3, TCG_TMP2);
tcg_out_opc_reg(s, OPC_JR, 0, TCG_REG_RA, 0);
/* t3 = dcba -- delay slot */
tcg_out_opc_reg(s, OPC_OR, TCG_TMP3, TCG_TMP3, TCG_TMP1);
/*
* bswap64 -- 64-bit swap. a0 = abcdefgh
*/
bswap64_addr = tcg_splitwx_to_rx(align_code_ptr(s));
/* t3 = h0000000 */
tcg_out_dsll(s, TCG_TMP3, TCG_TMP0, 56);
/* t1 = 0000000a */
tcg_out_dsrl(s, TCG_TMP1, TCG_TMP0, 56);
/* t2 = 000000g0 */
tcg_out_opc_imm(s, OPC_ANDI, TCG_TMP2, TCG_TMP0, 0xff00);
/* t3 = h000000a */
tcg_out_opc_reg(s, OPC_OR, TCG_TMP3, TCG_TMP3, TCG_TMP1);
/* t1 = 00000abc */
tcg_out_dsrl(s, TCG_TMP1, TCG_TMP0, 40);
/* t2 = 0g000000 */
tcg_out_dsll(s, TCG_TMP2, TCG_TMP2, 40);
/* t1 = 000000b0 */
tcg_out_opc_imm(s, OPC_ANDI, TCG_TMP1, TCG_TMP1, 0xff00);
/* t3 = hg00000a */
tcg_out_opc_reg(s, OPC_OR, TCG_TMP3, TCG_TMP3, TCG_TMP2);
/* t2 = 0000abcd */
tcg_out_dsrl(s, TCG_TMP2, TCG_TMP0, 32);
/* t3 = hg0000ba */
tcg_out_opc_reg(s, OPC_OR, TCG_TMP3, TCG_TMP3, TCG_TMP1);
/* t1 = 000000c0 */
tcg_out_opc_imm(s, OPC_ANDI, TCG_TMP1, TCG_TMP2, 0xff00);
/* t2 = 0000000d */
tcg_out_opc_imm(s, OPC_ANDI, TCG_TMP2, TCG_TMP2, 0x00ff);
/* t1 = 00000c00 */
tcg_out_dsll(s, TCG_TMP1, TCG_TMP1, 8);
/* t2 = 0000d000 */
tcg_out_dsll(s, TCG_TMP2, TCG_TMP2, 24);
/* t3 = hg000cba */
tcg_out_opc_reg(s, OPC_OR, TCG_TMP3, TCG_TMP3, TCG_TMP1);
/* t1 = 00abcdef */
tcg_out_dsrl(s, TCG_TMP1, TCG_TMP0, 16);
/* t3 = hg00dcba */
tcg_out_opc_reg(s, OPC_OR, TCG_TMP3, TCG_TMP3, TCG_TMP2);
/* t2 = 0000000f */
tcg_out_opc_imm(s, OPC_ANDI, TCG_TMP2, TCG_TMP1, 0x00ff);
/* t1 = 000000e0 */
tcg_out_opc_imm(s, OPC_ANDI, TCG_TMP1, TCG_TMP1, 0xff00);
/* t2 = 00f00000 */
tcg_out_dsll(s, TCG_TMP2, TCG_TMP2, 40);
/* t1 = 000e0000 */
tcg_out_dsll(s, TCG_TMP1, TCG_TMP1, 24);
/* t3 = hgf0dcba */
tcg_out_opc_reg(s, OPC_OR, TCG_TMP3, TCG_TMP3, TCG_TMP2);
tcg_out_opc_reg(s, OPC_JR, 0, TCG_REG_RA, 0);
/* t3 = hgfedcba -- delay slot */
tcg_out_opc_reg(s, OPC_OR, TCG_TMP3, TCG_TMP3, TCG_TMP1);
}
static void tcg_target_init(TCGContext *s)
{
tcg_target_detect_isa();
tcg_target_available_regs[TCG_TYPE_I32] = 0xffffffff;
if (TCG_TARGET_REG_BITS == 64) {
tcg_target_available_regs[TCG_TYPE_I64] = 0xffffffff;
}
tcg_target_call_clobber_regs = 0;
tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V0);
tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V1);
tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_A0);
tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_A1);
tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_A2);
tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_A3);
tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_T0);
tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_T1);
tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_T2);
tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_T3);
tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_T4);
tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_T5);
tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_T6);
tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_T7);
tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_T8);
tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_T9);
s->reserved_regs = 0;
tcg_regset_set_reg(s->reserved_regs, TCG_REG_ZERO); /* zero register */
tcg_regset_set_reg(s->reserved_regs, TCG_REG_K0); /* kernel use only */
tcg_regset_set_reg(s->reserved_regs, TCG_REG_K1); /* kernel use only */
tcg_regset_set_reg(s->reserved_regs, TCG_TMP0); /* internal use */
tcg_regset_set_reg(s->reserved_regs, TCG_TMP1); /* internal use */
tcg_regset_set_reg(s->reserved_regs, TCG_TMP2); /* internal use */
tcg_regset_set_reg(s->reserved_regs, TCG_TMP3); /* internal use */
tcg_regset_set_reg(s->reserved_regs, TCG_REG_RA); /* return address */
tcg_regset_set_reg(s->reserved_regs, TCG_REG_SP); /* stack pointer */
tcg_regset_set_reg(s->reserved_regs, TCG_REG_GP); /* global pointer */
if (TCG_TARGET_REG_BITS == 64) {
tcg_regset_set_reg(s->reserved_regs, TCG_REG_TB); /* tc->tc_ptr */
}
}
typedef struct {
DebugFrameHeader h;
uint8_t fde_def_cfa[4];
uint8_t fde_reg_ofs[ARRAY_SIZE(tcg_target_callee_save_regs) * 2];
} DebugFrame;
#define ELF_HOST_MACHINE EM_MIPS
/* GDB doesn't appear to require proper setting of ELF_HOST_FLAGS,
which is good because they're really quite complicated for MIPS. */
static const DebugFrame debug_frame = {
.h.cie.len = sizeof(DebugFrameCIE) - 4, /* length after .len member */
.h.cie.id = -1,
.h.cie.version = 1,
.h.cie.code_align = 1,
.h.cie.data_align = -(TCG_TARGET_REG_BITS / 8) & 0x7f, /* sleb128 */
.h.cie.return_column = TCG_REG_RA,
/* Total FDE size does not include the "len" member. */
.h.fde.len = sizeof(DebugFrame) - offsetof(DebugFrame, h.fde.cie_offset),
.fde_def_cfa = {
12, TCG_REG_SP, /* DW_CFA_def_cfa sp, ... */
(FRAME_SIZE & 0x7f) | 0x80, /* ... uleb128 FRAME_SIZE */
(FRAME_SIZE >> 7)
},
.fde_reg_ofs = {
0x80 + 16, 9, /* DW_CFA_offset, s0, -72 */
0x80 + 17, 8, /* DW_CFA_offset, s2, -64 */
0x80 + 18, 7, /* DW_CFA_offset, s3, -56 */
0x80 + 19, 6, /* DW_CFA_offset, s4, -48 */
0x80 + 20, 5, /* DW_CFA_offset, s5, -40 */
0x80 + 21, 4, /* DW_CFA_offset, s6, -32 */
0x80 + 22, 3, /* DW_CFA_offset, s7, -24 */
0x80 + 30, 2, /* DW_CFA_offset, s8, -16 */
0x80 + 31, 1, /* DW_CFA_offset, ra, -8 */
}
};
void tcg_register_jit(const void *buf, size_t buf_size)
{
tcg_register_jit_int(buf, buf_size, &debug_frame, sizeof(debug_frame));
}
Reference in New Issue View Git Blame Copy Permalink