* THE SOFTWARE.
*/
-#include "tcg-be-ldst.h"
-
#ifdef HOST_WORDS_BIGENDIAN
# define MIPS_BE 1
#else
# define MIPS_BE 0
#endif
-#define LO_OFF (MIPS_BE * 4)
-#define HI_OFF (4 - LO_OFF)
+#if TCG_TARGET_REG_BITS == 32
+# define LO_OFF (MIPS_BE * 4)
+# define HI_OFF (4 - LO_OFF)
+#else
+/* To assert at compile-time that these values are never used
+ for TCG_TARGET_REG_BITS == 64. */
+int link_error(void);
+# define LO_OFF link_error()
+# define HI_OFF link_error()
+#endif
#ifdef CONFIG_DEBUG_TCG
static const char * const tcg_target_reg_names[TCG_TARGET_NB_REGS] = {
#define TCG_TMP2 TCG_REG_T8
#define TCG_TMP3 TCG_REG_T7
+#ifndef CONFIG_SOFTMMU
+#define TCG_GUEST_BASE_REG TCG_REG_S1
+#endif
+
/* check if we really need so many registers :P */
static const int tcg_target_reg_alloc_order[] = {
/* Call saved registers. */
TCG_REG_S8,
/* Call clobbered registers. */
- TCG_REG_T0,
- TCG_REG_T1,
- TCG_REG_T2,
- TCG_REG_T3,
TCG_REG_T4,
TCG_REG_T5,
TCG_REG_T6,
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[4] = {
+static const TCGReg tcg_target_call_iarg_regs[] = {
TCG_REG_A0,
TCG_REG_A1,
TCG_REG_A2,
- TCG_REG_A3
+ TCG_REG_A3,
+#if _MIPS_SIM == _ABIN32 || _MIPS_SIM == _ABI64
+ TCG_REG_T0,
+ TCG_REG_T1,
+ TCG_REG_T2,
+ TCG_REG_T3,
+#endif
};
static const TCGReg tcg_target_call_oarg_regs[2] = {
*pc = deposit32(*pc, 0, 26, reloc_26_val(pc, target));
}
-static void patch_reloc(tcg_insn_unit *code_ptr, int type,
+static bool patch_reloc(tcg_insn_unit *code_ptr, int type,
intptr_t value, intptr_t addend)
{
tcg_debug_assert(type == R_MIPS_PC16);
tcg_debug_assert(addend == 0);
reloc_pc16(code_ptr, (tcg_insn_unit *)value);
+ return true;
}
#define TCG_CT_CONST_ZERO 0x100
#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 */
static inline bool is_p2m1(tcg_target_long val)
{
}
/* parse target specific constraints */
-static int target_parse_constraint(TCGArgConstraint *ct, const char **pct_str)
+static const char *target_parse_constraint(TCGArgConstraint *ct,
+ const char *ct_str, TCGType type)
{
- const char *ct_str;
-
- ct_str = *pct_str;
- switch(ct_str[0]) {
+ switch(*ct_str++) {
case 'r':
ct->ct |= TCG_CT_REG;
- tcg_regset_set(ct->u.regs, 0xffffffff);
+ ct->u.regs = 0xffffffff;
break;
case 'L': /* qemu_ld input arg constraint */
ct->ct |= TCG_CT_REG;
- tcg_regset_set(ct->u.regs, 0xffffffff);
+ ct->u.regs = 0xffffffff;
tcg_regset_reset_reg(ct->u.regs, TCG_REG_A0);
#if defined(CONFIG_SOFTMMU)
- if (TARGET_LONG_BITS == 64) {
+ if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) {
tcg_regset_reset_reg(ct->u.regs, TCG_REG_A2);
}
#endif
break;
case 'S': /* qemu_st constraint */
ct->ct |= TCG_CT_REG;
- tcg_regset_set(ct->u.regs, 0xffffffff);
+ ct->u.regs = 0xffffffff;
tcg_regset_reset_reg(ct->u.regs, TCG_REG_A0);
#if defined(CONFIG_SOFTMMU)
- if (TARGET_LONG_BITS == 32) {
- tcg_regset_reset_reg(ct->u.regs, TCG_REG_A1);
- } else {
+ if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) {
tcg_regset_reset_reg(ct->u.regs, TCG_REG_A2);
tcg_regset_reset_reg(ct->u.regs, TCG_REG_A3);
+ } else {
+ tcg_regset_reset_reg(ct->u.regs, TCG_REG_A1);
}
#endif
break;
case 'N':
ct->ct |= TCG_CT_CONST_N16;
break;
+ case 'W':
+ ct->ct |= TCG_CT_CONST_WSZ;
+ break;
case 'Z':
/* We are cheating a bit here, using the fact that the register
ZERO is also the register number 0. Hence there is no need
ct->ct |= TCG_CT_CONST_ZERO;
break;
default:
- return -1;
+ return NULL;
}
- ct_str++;
- *pct_str = ct_str;
- return 0;
+ return ct_str;
}
/* test if a constant matches the constraint */
} 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;
}
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_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,
static inline void tcg_out_opc_br(TCGContext *s, MIPSInsn opc,
TCGReg rt, TCGReg rs)
{
- /* We pay attention here to not modify the branch target by reading
- the existing value and using it again. This ensure that caches and
- memory are kept coherent during retranslation. */
- uint16_t offset = (uint16_t)*s->code_ptr;
-
- tcg_out_opc_imm(s, opc, rt, rs, offset);
+ tcg_out_opc_imm(s, opc, rt, rs, 0);
}
/*
return false;
}
-static inline void tcg_out_addi(TCGContext *s, TCGReg reg, TCGArg val)
-{
- if (val == (int16_t)val) {
- tcg_out_opc_imm(s, OPC_ADDIU, reg, reg, val);
- } else {
- tcg_out_movi(s, TCG_TYPE_PTR, TCG_TMP0, val);
- tcg_out_opc_reg(s, OPC_ADDU, reg, reg, TCG_TMP0);
- }
-}
-
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)
}
#if defined(CONFIG_SOFTMMU)
+#include "tcg-ldst.inc.c"
+
static void * const qemu_ld_helpers[16] = {
[MO_UB] = helper_ret_ldub_mmu,
[MO_SB] = helper_ret_ldsb_mmu,
[MO_BESW] = helper_be_ldsw_mmu,
[MO_BEUL] = helper_be_ldul_mmu,
[MO_BEQ] = helper_be_ldq_mmu,
+#if TCG_TARGET_REG_BITS == 64
+ [MO_LESL] = helper_le_ldsl_mmu,
+ [MO_BESL] = helper_be_ldsl_mmu,
+#endif
};
static void * const qemu_st_helpers[16] = {
if (i < ARRAY_SIZE(tcg_target_call_iarg_regs)) {
tcg_out_mov(s, TCG_TYPE_REG, tcg_target_call_iarg_regs[i], arg);
} else {
+ /* For N32 and N64, the initial offset is different. But there
+ we also have 8 argument register so we don't run out here. */
+ tcg_debug_assert(TCG_TARGET_REG_BITS == 32);
tcg_out_st(s, TCG_TYPE_REG, arg, TCG_REG_SP, 4 * i);
}
return i + 1;
static int tcg_out_call_iarg_reg2(TCGContext *s, int i, TCGReg al, TCGReg ah)
{
+ tcg_debug_assert(TCG_TARGET_REG_BITS == 32);
i = (i + 1) & ~1;
i = tcg_out_call_iarg_reg(s, i, (MIPS_BE ? ah : al));
i = tcg_out_call_iarg_reg(s, i, (MIPS_BE ? al : ah));
}
/* Perform the tlb comparison operation. The complete host address is
- placed in BASE. Clobbers TMP0, TMP1, A0. */
+ placed in BASE. Clobbers TMP0, TMP1, TMP2, A0. */
static void tcg_out_tlb_load(TCGContext *s, TCGReg base, TCGReg addrl,
TCGReg addrh, TCGMemOpIdx oi,
tcg_insn_unit *label_ptr[2], bool is_load)
TCGMemOp opc = get_memop(oi);
unsigned s_bits = opc & MO_SIZE;
unsigned a_bits = get_alignment_bits(opc);
+ target_ulong mask;
int mem_index = get_mmuidx(oi);
int cmp_off
= (is_load
: offsetof(CPUArchState, tlb_table[mem_index][0].addr_write));
int add_off = offsetof(CPUArchState, tlb_table[mem_index][0].addend);
- tcg_out_opc_sa(s, OPC_SRL, TCG_REG_A0, addrl,
+ tcg_out_opc_sa(s, ALIAS_TSRL, TCG_REG_A0, addrl,
TARGET_PAGE_BITS - CPU_TLB_ENTRY_BITS);
tcg_out_opc_imm(s, OPC_ANDI, TCG_REG_A0, TCG_REG_A0,
(CPU_TLB_SIZE - 1) << CPU_TLB_ENTRY_BITS);
- tcg_out_opc_reg(s, OPC_ADDU, TCG_REG_A0, TCG_REG_A0, TCG_AREG0);
+ tcg_out_opc_reg(s, ALIAS_PADD, TCG_REG_A0, TCG_REG_A0, TCG_AREG0);
/* Compensate for very large offsets. */
- if (add_off >= 0x8000) {
- /* Most target env are smaller than 32k; none are larger than 64k.
- Simplify the logic here merely to offset by 0x7ff0, giving us a
- range just shy of 64k. Check this assumption. */
- QEMU_BUILD_BUG_ON(offsetof(CPUArchState,
- tlb_table[NB_MMU_MODES - 1][1])
- > 0x7ff0 + 0x7fff);
- tcg_out_opc_imm(s, OPC_ADDIU, TCG_REG_A0, TCG_REG_A0, 0x7ff0);
+ while (add_off >= 0x8000) {
+ /* Most target env are smaller than 32k, but a few are larger than 64k,
+ * so handle an arbitrarily large offset.
+ */
+ tcg_out_opc_imm(s, ALIAS_PADDI, TCG_REG_A0, TCG_REG_A0, 0x7ff0);
cmp_off -= 0x7ff0;
add_off -= 0x7ff0;
}
- /* Load the (low half) tlb comparator. */
- tcg_out_opc_imm(s, OPC_LW, TCG_TMP0, TCG_REG_A0,
- cmp_off + (TARGET_LONG_BITS == 64 ? LO_OFF : 0));
-
/* We don't currently support unaligned accesses.
We could do so with mips32r6. */
if (a_bits < s_bits) {
a_bits = s_bits;
}
- /* Mask the page bits, keeping the alignment bits to compare against.
- In between on 32-bit targets, load the tlb addend for the fast path. */
- tcg_out_movi(s, TCG_TYPE_I32, TCG_TMP1,
- TARGET_PAGE_MASK | ((1 << a_bits) - 1));
- if (TARGET_LONG_BITS == 32) {
- tcg_out_opc_imm(s, OPC_LW, TCG_REG_A0, TCG_REG_A0, add_off);
+
+ mask = (target_ulong)TARGET_PAGE_MASK | ((1 << a_bits) - 1);
+
+ /* Load the (low half) tlb comparator. Mask the page bits, keeping the
+ alignment bits to compare against. */
+ if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) {
+ tcg_out_ld(s, TCG_TYPE_I32, TCG_TMP0, TCG_REG_A0, cmp_off + LO_OFF);
+ tcg_out_movi(s, TCG_TYPE_I32, TCG_TMP1, mask);
+ } else {
+ tcg_out_ldst(s,
+ (TARGET_LONG_BITS == 64 ? OPC_LD
+ : TCG_TARGET_REG_BITS == 64 ? OPC_LWU : OPC_LW),
+ TCG_TMP0, TCG_REG_A0, cmp_off);
+ tcg_out_movi(s, TCG_TYPE_TL, TCG_TMP1, mask);
+ /* No second compare is required here;
+ load the tlb addend for the fast path. */
+ tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP2, TCG_REG_A0, add_off);
}
tcg_out_opc_reg(s, OPC_AND, TCG_TMP1, TCG_TMP1, addrl);
+ /* Zero extend a 32-bit guest address for a 64-bit host. */
+ if (TCG_TARGET_REG_BITS > TARGET_LONG_BITS) {
+ tcg_out_ext32u(s, base, addrl);
+ addrl = base;
+ }
+
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 (TARGET_LONG_BITS == 64) {
+ if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) {
/* delay slot */
- tcg_out_opc_imm(s, OPC_LW, TCG_TMP0, TCG_REG_A0, cmp_off + HI_OFF);
+ tcg_out_ld(s, TCG_TYPE_I32, TCG_TMP0, TCG_REG_A0, cmp_off + HI_OFF);
- /* Load the tlb addend for the fast path. We can't do it earlier with
- 64-bit targets or we'll clobber a0 before reading the high half tlb
- comparator. */
- tcg_out_opc_imm(s, OPC_LW, TCG_REG_A0, TCG_REG_A0, add_off);
+ /* Load the tlb addend for the fast path. */
+ tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP2, TCG_REG_A0, add_off);
label_ptr[1] = s->code_ptr;
tcg_out_opc_br(s, OPC_BNE, addrh, TCG_TMP0);
}
/* delay slot */
- tcg_out_opc_reg(s, OPC_ADDU, base, TCG_REG_A0, addrl);
+ tcg_out_opc_reg(s, ALIAS_PADD, base, TCG_TMP2, addrl);
}
static void add_qemu_ldst_label(TCGContext *s, int is_ld, TCGMemOpIdx oi,
+ TCGType ext,
TCGReg datalo, TCGReg datahi,
TCGReg addrlo, TCGReg addrhi,
void *raddr, tcg_insn_unit *label_ptr[2])
label->is_ld = is_ld;
label->oi = oi;
+ label->type = ext;
label->datalo_reg = datalo;
label->datahi_reg = datahi;
label->addrlo_reg = addrlo;
label->addrhi_reg = addrhi;
label->raddr = raddr;
label->label_ptr[0] = label_ptr[0];
- if (TARGET_LONG_BITS == 64) {
+ if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) {
label->label_ptr[1] = label_ptr[1];
}
}
/* resolve label address */
reloc_pc16(l->label_ptr[0], s->code_ptr);
- if (TARGET_LONG_BITS == 64) {
+ if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) {
reloc_pc16(l->label_ptr[1], s->code_ptr);
}
i = 1;
- if (TARGET_LONG_BITS == 64) {
+ if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) {
i = tcg_out_call_iarg_reg2(s, i, l->addrlo_reg, l->addrhi_reg);
} else {
i = tcg_out_call_iarg_reg(s, i, l->addrlo_reg);
tcg_out_mov(s, TCG_TYPE_PTR, tcg_target_call_iarg_regs[0], TCG_AREG0);
v0 = l->datalo_reg;
- if ((opc & MO_SIZE) == MO_64) {
+ if (TCG_TARGET_REG_BITS == 32 && (opc & MO_SIZE) == MO_64) {
/* We eliminated V0 from the possible output registers, so it
cannot be clobbered here. So we must move V1 first. */
if (MIPS_BE) {
reloc_pc16(s->code_ptr, l->raddr);
tcg_out_opc_br(s, OPC_BEQ, TCG_REG_ZERO, TCG_REG_ZERO);
/* delay slot */
- tcg_out_mov(s, TCG_TYPE_REG, v0, TCG_REG_V0);
+ if (TCG_TARGET_REG_BITS == 64 && l->type == TCG_TYPE_I32) {
+ /* we always sign-extend 32-bit loads */
+ tcg_out_opc_sa(s, OPC_SLL, v0, TCG_REG_V0, 0);
+ } else {
+ tcg_out_opc_reg(s, OPC_OR, v0, TCG_REG_V0, TCG_REG_ZERO);
+ }
}
static void tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l)
/* resolve label address */
reloc_pc16(l->label_ptr[0], s->code_ptr);
- if (TARGET_LONG_BITS == 64) {
+ if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) {
reloc_pc16(l->label_ptr[1], s->code_ptr);
}
i = 1;
- if (TARGET_LONG_BITS == 64) {
+ if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) {
i = tcg_out_call_iarg_reg2(s, i, l->addrlo_reg, l->addrhi_reg);
} else {
i = tcg_out_call_iarg_reg(s, i, l->addrlo_reg);
i = tcg_out_call_iarg_reg(s, i, l->datalo_reg);
break;
case MO_64:
- i = tcg_out_call_iarg_reg2(s, i, l->datalo_reg, l->datahi_reg);
+ if (TCG_TARGET_REG_BITS == 32) {
+ i = tcg_out_call_iarg_reg2(s, i, l->datalo_reg, l->datahi_reg);
+ } else {
+ i = tcg_out_call_iarg_reg(s, i, l->datalo_reg);
+ }
break;
default:
tcg_abort();
#endif
static void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg lo, TCGReg hi,
- TCGReg base, TCGMemOp opc)
+ TCGReg base, TCGMemOp opc, bool is_64)
{
switch (opc & (MO_SSIZE | MO_BSWAP)) {
case MO_UB:
tcg_out_opc_imm(s, OPC_LH, lo, base, 0);
break;
case MO_UL | MO_BSWAP:
+ if (TCG_TARGET_REG_BITS == 64 && is_64) {
+ if (use_mips32r2_instructions) {
+ tcg_out_opc_imm(s, OPC_LWU, lo, base, 0);
+ tcg_out_bswap32u(s, lo, lo);
+ } else {
+ tcg_out_bswap_subr(s, bswap32u_addr);
+ /* delay slot */
+ tcg_out_opc_imm(s, OPC_LWU, TCG_TMP0, base, 0);
+ tcg_out_mov(s, TCG_TYPE_I64, lo, TCG_TMP3);
+ }
+ break;
+ }
+ /* FALLTHRU */
+ case MO_SL | MO_BSWAP:
if (use_mips32r2_instructions) {
tcg_out_opc_imm(s, OPC_LW, lo, base, 0);
tcg_out_bswap32(s, lo, lo);
}
break;
case MO_UL:
+ if (TCG_TARGET_REG_BITS == 64 && is_64) {
+ 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_Q | MO_BSWAP:
- if (use_mips32r2_instructions) {
+ if (TCG_TARGET_REG_BITS == 64) {
+ if (use_mips32r2_instructions) {
+ tcg_out_opc_imm(s, OPC_LD, lo, base, 0);
+ tcg_out_bswap64(s, lo, lo);
+ } else {
+ tcg_out_bswap_subr(s, bswap64_addr);
+ /* delay slot */
+ tcg_out_opc_imm(s, OPC_LD, TCG_TMP0, base, 0);
+ tcg_out_mov(s, TCG_TYPE_I64, lo, TCG_TMP3);
+ }
+ } else if (use_mips32r2_instructions) {
tcg_out_opc_imm(s, OPC_LW, TCG_TMP0, base, 0);
tcg_out_opc_imm(s, OPC_LW, TCG_TMP1, base, 4);
tcg_out_opc_reg(s, OPC_WSBH, TCG_TMP0, 0, TCG_TMP0);
break;
case MO_Q:
/* Prefer to load from offset 0 first, but allow for overlap. */
- if (MIPS_BE ? hi != base : lo == base) {
+ if (TCG_TARGET_REG_BITS == 64) {
+ tcg_out_opc_imm(s, OPC_LD, lo, base, 0);
+ } else if (MIPS_BE ? 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 {
TCGReg base = TCG_REG_A0;
data_regl = *args++;
- data_regh = (is_64 ? *args++ : 0);
+ data_regh = (TCG_TARGET_REG_BITS == 32 && is_64 ? *args++ : 0);
addr_regl = *args++;
- addr_regh = (TARGET_LONG_BITS == 64 ? *args++ : 0);
+ addr_regh = (TCG_TARGET_REG_BITS < TARGET_LONG_BITS ? *args++ : 0);
oi = *args++;
opc = get_memop(oi);
#if defined(CONFIG_SOFTMMU)
tcg_out_tlb_load(s, base, addr_regl, addr_regh, oi, label_ptr, 1);
- tcg_out_qemu_ld_direct(s, data_regl, data_regh, base, opc);
- add_qemu_ldst_label(s, 1, oi, data_regl, data_regh, addr_regl, addr_regh,
+ tcg_out_qemu_ld_direct(s, data_regl, data_regh, base, opc, is_64);
+ add_qemu_ldst_label(s, 1, oi,
+ (is_64 ? TCG_TYPE_I64 : TCG_TYPE_I32),
+ data_regl, data_regh, addr_regl, addr_regh,
s->code_ptr, label_ptr);
#else
+ if (TCG_TARGET_REG_BITS > TARGET_LONG_BITS) {
+ tcg_out_ext32u(s, base, addr_regl);
+ addr_regl = base;
+ }
if (guest_base == 0 && data_regl != addr_regl) {
base = addr_regl;
} else if (guest_base == (int16_t)guest_base) {
- tcg_out_opc_imm(s, OPC_ADDIU, base, addr_regl, guest_base);
+ tcg_out_opc_imm(s, ALIAS_PADDI, base, addr_regl, guest_base);
} else {
- tcg_out_movi(s, TCG_TYPE_PTR, base, guest_base);
- tcg_out_opc_reg(s, OPC_ADDU, base, base, addr_regl);
+ tcg_out_opc_reg(s, ALIAS_PADD, base, TCG_GUEST_BASE_REG, addr_regl);
}
- tcg_out_qemu_ld_direct(s, data_regl, data_regh, base, opc);
+ tcg_out_qemu_ld_direct(s, data_regl, data_regh, base, opc, is_64);
#endif
}
break;
case MO_64 | MO_BSWAP:
- if (use_mips32r2_instructions) {
+ if (TCG_TARGET_REG_BITS == 64) {
+ tcg_out_bswap64(s, TCG_TMP3, lo);
+ tcg_out_opc_imm(s, OPC_SD, TCG_TMP3, base, 0);
+ } else if (use_mips32r2_instructions) {
tcg_out_opc_reg(s, OPC_WSBH, TCG_TMP0, 0, MIPS_BE ? lo : hi);
tcg_out_opc_reg(s, OPC_WSBH, TCG_TMP1, 0, MIPS_BE ? hi : lo);
tcg_out_opc_sa(s, OPC_ROTR, TCG_TMP0, TCG_TMP0, 16);
}
break;
case MO_64:
- tcg_out_opc_imm(s, OPC_SW, MIPS_BE ? hi : lo, base, 0);
- tcg_out_opc_imm(s, OPC_SW, MIPS_BE ? lo : hi, base, 4);
+ if (TCG_TARGET_REG_BITS == 64) {
+ tcg_out_opc_imm(s, OPC_SD, lo, base, 0);
+ } else {
+ tcg_out_opc_imm(s, OPC_SW, MIPS_BE ? hi : lo, base, 0);
+ tcg_out_opc_imm(s, OPC_SW, MIPS_BE ? lo : hi, base, 4);
+ }
break;
default:
TCGReg base = TCG_REG_A0;
data_regl = *args++;
- data_regh = (is_64 ? *args++ : 0);
+ data_regh = (TCG_TARGET_REG_BITS == 32 && is_64 ? *args++ : 0);
addr_regl = *args++;
- addr_regh = (TARGET_LONG_BITS == 64 ? *args++ : 0);
+ addr_regh = (TCG_TARGET_REG_BITS < TARGET_LONG_BITS ? *args++ : 0);
oi = *args++;
opc = get_memop(oi);
#if defined(CONFIG_SOFTMMU)
tcg_out_tlb_load(s, base, addr_regl, addr_regh, oi, label_ptr, 0);
tcg_out_qemu_st_direct(s, data_regl, data_regh, base, opc);
- add_qemu_ldst_label(s, 0, oi, data_regl, data_regh, addr_regl, addr_regh,
+ add_qemu_ldst_label(s, 0, oi,
+ (is_64 ? TCG_TYPE_I64 : TCG_TYPE_I32),
+ data_regl, data_regh, addr_regl, addr_regh,
s->code_ptr, label_ptr);
#else
+ base = TCG_REG_A0;
+ if (TCG_TARGET_REG_BITS > TARGET_LONG_BITS) {
+ tcg_out_ext32u(s, base, addr_regl);
+ addr_regl = base;
+ }
if (guest_base == 0) {
base = addr_regl;
+ } else if (guest_base == (int16_t)guest_base) {
+ tcg_out_opc_imm(s, ALIAS_PADDI, base, addr_regl, guest_base);
} else {
- if (guest_base == (int16_t)guest_base) {
- tcg_out_opc_imm(s, OPC_ADDIU, base, addr_regl, guest_base);
- } else {
- tcg_out_movi(s, TCG_TYPE_PTR, base, guest_base);
- tcg_out_opc_reg(s, OPC_ADDU, base, base, addr_regl);
- }
+ tcg_out_opc_reg(s, ALIAS_PADD, base, TCG_GUEST_BASE_REG, addr_regl);
}
tcg_out_qemu_st_direct(s, data_regl, data_regh, base, opc);
#endif
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 inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
const TCGArg *args, const int *const_args)
{
tcg_out_opc_reg(s, OPC_JR, 0, TCG_TMP0, 0);
}
tcg_out_nop(s);
- s->tb_jmp_reset_offset[a0] = tcg_current_code_size(s);
+ set_jmp_reset_offset(s, a0);
+ break;
+ case INDEX_op_goto_ptr:
+ /* jmp to the given host address (could be epilogue) */
+ tcg_out_opc_reg(s, OPC_JR, 0, a0, 0);
+ tcg_out_nop(s);
break;
case INDEX_op_br:
tcg_out_brcond(s, TCG_COND_EQ, TCG_REG_ZERO, TCG_REG_ZERO,
}
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;
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:
}
}
-static const TCGTargetOpDef mips_op_defs[] = {
- { INDEX_op_exit_tb, { } },
- { INDEX_op_goto_tb, { } },
- { INDEX_op_br, { } },
+static const TCGTargetOpDef *tcg_target_op_def(TCGOpcode op)
+{
+ static const TCGTargetOpDef r = { .args_ct_str = { "r" } };
+ static const TCGTargetOpDef r_r = { .args_ct_str = { "r", "r" } };
+ static const TCGTargetOpDef r_L = { .args_ct_str = { "r", "L" } };
+ static const TCGTargetOpDef rZ_r = { .args_ct_str = { "rZ", "r" } };
+ static const TCGTargetOpDef SZ_S = { .args_ct_str = { "SZ", "S" } };
+ static const TCGTargetOpDef rZ_rZ = { .args_ct_str = { "rZ", "rZ" } };
+ static const TCGTargetOpDef r_r_L = { .args_ct_str = { "r", "r", "L" } };
+ static const TCGTargetOpDef r_L_L = { .args_ct_str = { "r", "L", "L" } };
+ static const TCGTargetOpDef r_r_ri = { .args_ct_str = { "r", "r", "ri" } };
+ static const TCGTargetOpDef r_r_rI = { .args_ct_str = { "r", "r", "rI" } };
+ static const TCGTargetOpDef r_r_rJ = { .args_ct_str = { "r", "r", "rJ" } };
+ static const TCGTargetOpDef SZ_S_S = { .args_ct_str = { "SZ", "S", "S" } };
+ static const TCGTargetOpDef SZ_SZ_S
+ = { .args_ct_str = { "SZ", "SZ", "S" } };
+ static const TCGTargetOpDef SZ_SZ_S_S
+ = { .args_ct_str = { "SZ", "SZ", "S", "S" } };
+ static const TCGTargetOpDef r_rZ_rN
+ = { .args_ct_str = { "r", "rZ", "rN" } };
+ static const TCGTargetOpDef r_rZ_rZ
+ = { .args_ct_str = { "r", "rZ", "rZ" } };
+ static const TCGTargetOpDef r_r_rIK
+ = { .args_ct_str = { "r", "r", "rIK" } };
+ static const TCGTargetOpDef r_r_rWZ
+ = { .args_ct_str = { "r", "r", "rWZ" } };
+ static const TCGTargetOpDef r_r_r_r
+ = { .args_ct_str = { "r", "r", "r", "r" } };
+ static const TCGTargetOpDef r_r_L_L
+ = { .args_ct_str = { "r", "r", "L", "L" } };
+ static const TCGTargetOpDef dep
+ = { .args_ct_str = { "r", "0", "rZ" } };
+ static const TCGTargetOpDef movc
+ = { .args_ct_str = { "r", "rZ", "rZ", "rZ", "0" } };
+ static const TCGTargetOpDef movc_r6
+ = { .args_ct_str = { "r", "rZ", "rZ", "rZ", "rZ" } };
+ static const TCGTargetOpDef add2
+ = { .args_ct_str = { "r", "r", "rZ", "rZ", "rN", "rN" } };
+ static const TCGTargetOpDef br2
+ = { .args_ct_str = { "rZ", "rZ", "rZ", "rZ" } };
+ static const TCGTargetOpDef setc2
+ = { .args_ct_str = { "r", "rZ", "rZ", "rZ", "rZ" } };
+
+ switch (op) {
+ case INDEX_op_goto_ptr:
+ return &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 &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 &rZ_r;
- { INDEX_op_ld8u_i32, { "r", "r" } },
- { INDEX_op_ld8s_i32, { "r", "r" } },
- { INDEX_op_ld16u_i32, { "r", "r" } },
- { INDEX_op_ld16s_i32, { "r", "r" } },
- { INDEX_op_ld_i32, { "r", "r" } },
- { INDEX_op_st8_i32, { "rZ", "r" } },
- { INDEX_op_st16_i32, { "rZ", "r" } },
- { INDEX_op_st_i32, { "rZ", "r" } },
+ case INDEX_op_add_i32:
+ case INDEX_op_add_i64:
+ return &r_r_rJ;
+ case INDEX_op_sub_i32:
+ case INDEX_op_sub_i64:
+ return &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 &r_rZ_rZ;
+ case INDEX_op_muls2_i32:
+ case INDEX_op_mulu2_i32:
+ case INDEX_op_muls2_i64:
+ case INDEX_op_mulu2_i64:
+ return &r_r_r_r;
+ case INDEX_op_and_i32:
+ case INDEX_op_and_i64:
+ return &r_r_rIK;
+ case INDEX_op_or_i32:
+ case INDEX_op_xor_i32:
+ case INDEX_op_or_i64:
+ case INDEX_op_xor_i64:
+ return &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 &r_r_ri;
+ case INDEX_op_clz_i32:
+ case INDEX_op_clz_i64:
+ return &r_r_rWZ;
- { INDEX_op_add_i32, { "r", "rZ", "rJ" } },
- { INDEX_op_mul_i32, { "r", "rZ", "rZ" } },
-#if !use_mips32r6_instructions
- { INDEX_op_muls2_i32, { "r", "r", "rZ", "rZ" } },
- { INDEX_op_mulu2_i32, { "r", "r", "rZ", "rZ" } },
-#endif
- { INDEX_op_mulsh_i32, { "r", "rZ", "rZ" } },
- { INDEX_op_muluh_i32, { "r", "rZ", "rZ" } },
- { INDEX_op_div_i32, { "r", "rZ", "rZ" } },
- { INDEX_op_divu_i32, { "r", "rZ", "rZ" } },
- { INDEX_op_rem_i32, { "r", "rZ", "rZ" } },
- { INDEX_op_remu_i32, { "r", "rZ", "rZ" } },
- { INDEX_op_sub_i32, { "r", "rZ", "rN" } },
-
- { INDEX_op_and_i32, { "r", "rZ", "rIK" } },
- { INDEX_op_nor_i32, { "r", "rZ", "rZ" } },
- { INDEX_op_not_i32, { "r", "rZ" } },
- { INDEX_op_or_i32, { "r", "rZ", "rIZ" } },
- { INDEX_op_xor_i32, { "r", "rZ", "rIZ" } },
-
- { INDEX_op_shl_i32, { "r", "rZ", "ri" } },
- { INDEX_op_shr_i32, { "r", "rZ", "ri" } },
- { INDEX_op_sar_i32, { "r", "rZ", "ri" } },
- { INDEX_op_rotr_i32, { "r", "rZ", "ri" } },
- { INDEX_op_rotl_i32, { "r", "rZ", "ri" } },
-
- { INDEX_op_bswap16_i32, { "r", "r" } },
- { INDEX_op_bswap32_i32, { "r", "r" } },
-
- { INDEX_op_ext8s_i32, { "r", "rZ" } },
- { INDEX_op_ext16s_i32, { "r", "rZ" } },
-
- { INDEX_op_deposit_i32, { "r", "0", "rZ" } },
-
- { INDEX_op_brcond_i32, { "rZ", "rZ" } },
-#if use_mips32r6_instructions
- { INDEX_op_movcond_i32, { "r", "rZ", "rZ", "rZ", "rZ" } },
-#else
- { INDEX_op_movcond_i32, { "r", "rZ", "rZ", "rZ", "0" } },
-#endif
- { INDEX_op_setcond_i32, { "r", "rZ", "rZ" } },
+ case INDEX_op_deposit_i32:
+ case INDEX_op_deposit_i64:
+ return &dep;
+ case INDEX_op_brcond_i32:
+ case INDEX_op_brcond_i64:
+ return &rZ_rZ;
+ case INDEX_op_movcond_i32:
+ case INDEX_op_movcond_i64:
+ return use_mips32r6_instructions ? &movc_r6 : &movc;
-#if TCG_TARGET_REG_BITS == 32
- { INDEX_op_add2_i32, { "r", "r", "rZ", "rZ", "rN", "rN" } },
- { INDEX_op_sub2_i32, { "r", "r", "rZ", "rZ", "rN", "rN" } },
- { INDEX_op_setcond2_i32, { "r", "rZ", "rZ", "rZ", "rZ" } },
- { INDEX_op_brcond2_i32, { "rZ", "rZ", "rZ", "rZ" } },
-#endif
+ case INDEX_op_add2_i32:
+ case INDEX_op_sub2_i32:
+ return &add2;
+ case INDEX_op_setcond2_i32:
+ return &setc2;
+ case INDEX_op_brcond2_i32:
+ return &br2;
-#if TCG_TARGET_REG_BITS == 64
- { INDEX_op_ld8u_i64, { "r", "r" } },
- { INDEX_op_ld8s_i64, { "r", "r" } },
- { INDEX_op_ld16u_i64, { "r", "r" } },
- { INDEX_op_ld16s_i64, { "r", "r" } },
- { INDEX_op_ld32s_i64, { "r", "r" } },
- { INDEX_op_ld32u_i64, { "r", "r" } },
- { INDEX_op_ld_i64, { "r", "r" } },
- { INDEX_op_st8_i64, { "rZ", "r" } },
- { INDEX_op_st16_i64, { "rZ", "r" } },
- { INDEX_op_st32_i64, { "rZ", "r" } },
- { INDEX_op_st_i64, { "rZ", "r" } },
-
- { INDEX_op_add_i64, { "r", "rZ", "rJ" } },
- { INDEX_op_mul_i64, { "r", "rZ", "rZ" } },
-#if !use_mips32r6_instructions
- { INDEX_op_muls2_i64, { "r", "r", "rZ", "rZ" } },
- { INDEX_op_mulu2_i64, { "r", "r", "rZ", "rZ" } },
-#endif
- { INDEX_op_mulsh_i64, { "r", "rZ", "rZ" } },
- { INDEX_op_muluh_i64, { "r", "rZ", "rZ" } },
- { INDEX_op_div_i64, { "r", "rZ", "rZ" } },
- { INDEX_op_divu_i64, { "r", "rZ", "rZ" } },
- { INDEX_op_rem_i64, { "r", "rZ", "rZ" } },
- { INDEX_op_remu_i64, { "r", "rZ", "rZ" } },
- { INDEX_op_sub_i64, { "r", "rZ", "rN" } },
-
- { INDEX_op_and_i64, { "r", "rZ", "rIK" } },
- { INDEX_op_nor_i64, { "r", "rZ", "rZ" } },
- { INDEX_op_not_i64, { "r", "rZ" } },
- { INDEX_op_or_i64, { "r", "rZ", "rI" } },
- { INDEX_op_xor_i64, { "r", "rZ", "rI" } },
-
- { INDEX_op_shl_i64, { "r", "rZ", "ri" } },
- { INDEX_op_shr_i64, { "r", "rZ", "ri" } },
- { INDEX_op_sar_i64, { "r", "rZ", "ri" } },
- { INDEX_op_rotr_i64, { "r", "rZ", "ri" } },
- { INDEX_op_rotl_i64, { "r", "rZ", "ri" } },
-
- { INDEX_op_bswap16_i64, { "r", "r" } },
- { INDEX_op_bswap32_i64, { "r", "r" } },
- { INDEX_op_bswap64_i64, { "r", "r" } },
-
- { INDEX_op_ext8s_i64, { "r", "rZ" } },
- { INDEX_op_ext16s_i64, { "r", "rZ" } },
- { INDEX_op_ext32s_i64, { "r", "rZ" } },
- { INDEX_op_ext32u_i64, { "r", "rZ" } },
- { INDEX_op_ext_i32_i64, { "r", "rZ" } },
- { INDEX_op_extu_i32_i64, { "r", "rZ" } },
- { INDEX_op_extrl_i64_i32, { "r", "rZ" } },
- { INDEX_op_extrh_i64_i32, { "r", "rZ" } },
-
- { INDEX_op_deposit_i64, { "r", "0", "rZ" } },
-
- { INDEX_op_brcond_i64, { "rZ", "rZ" } },
-#if use_mips32r6_instructions
- { INDEX_op_movcond_i64, { "r", "rZ", "rZ", "rZ", "rZ" } },
-#else
- { INDEX_op_movcond_i64, { "r", "rZ", "rZ", "rZ", "0" } },
-#endif
- { INDEX_op_setcond_i64, { "r", "rZ", "rZ" } },
-
- { INDEX_op_qemu_ld_i32, { "r", "LZ" } },
- { INDEX_op_qemu_st_i32, { "SZ", "SZ" } },
- { INDEX_op_qemu_ld_i64, { "r", "LZ" } },
- { INDEX_op_qemu_st_i64, { "SZ", "SZ" } },
-#elif TARGET_LONG_BITS == 32
- { INDEX_op_qemu_ld_i32, { "r", "LZ" } },
- { INDEX_op_qemu_st_i32, { "SZ", "SZ" } },
- { INDEX_op_qemu_ld_i64, { "r", "r", "LZ" } },
- { INDEX_op_qemu_st_i64, { "SZ", "SZ", "SZ" } },
-#else
- { INDEX_op_qemu_ld_i32, { "r", "LZ", "LZ" } },
- { INDEX_op_qemu_st_i32, { "SZ", "SZ", "SZ" } },
- { INDEX_op_qemu_ld_i64, { "r", "r", "LZ", "LZ" } },
- { INDEX_op_qemu_st_i64, { "SZ", "SZ", "SZ", "SZ" } },
-#endif
+ case INDEX_op_qemu_ld_i32:
+ return (TCG_TARGET_REG_BITS == 64 || TARGET_LONG_BITS == 32
+ ? &r_L : &r_L_L);
+ case INDEX_op_qemu_st_i32:
+ return (TCG_TARGET_REG_BITS == 64 || TARGET_LONG_BITS == 32
+ ? &SZ_S : &SZ_S_S);
+ case INDEX_op_qemu_ld_i64:
+ return (TCG_TARGET_REG_BITS == 64 ? &r_L
+ : TARGET_LONG_BITS == 32 ? &r_r_L : &r_r_L_L);
+ case INDEX_op_qemu_st_i64:
+ return (TCG_TARGET_REG_BITS == 64 ? &SZ_S
+ : TARGET_LONG_BITS == 32 ? &SZ_SZ_S : &SZ_SZ_S_S);
- { INDEX_op_mb, { } },
- { -1 },
-};
+ default:
+ return NULL;
+ }
+}
-static int tcg_target_callee_save_regs[] = {
+static const int tcg_target_callee_save_regs[] = {
TCG_REG_S0, /* used for the global env (TCG_AREG0) */
TCG_REG_S1,
TCG_REG_S2,
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, frame_size;
+ int i;
- /* reserve some stack space, also for TCG temps. */
- frame_size = ARRAY_SIZE(tcg_target_callee_save_regs) * 4
- + TCG_STATIC_CALL_ARGS_SIZE
- + CPU_TEMP_BUF_NLONGS * sizeof(long);
- frame_size = (frame_size + TCG_TARGET_STACK_ALIGN - 1) &
- ~(TCG_TARGET_STACK_ALIGN - 1);
- tcg_set_frame(s, TCG_REG_SP, ARRAY_SIZE(tcg_target_callee_save_regs) * 4
- + TCG_STATIC_CALL_ARGS_SIZE,
- CPU_TEMP_BUF_NLONGS * sizeof(long));
+ tcg_set_frame(s, TCG_REG_SP, TCG_STATIC_CALL_ARGS_SIZE, TEMP_SIZE);
/* TB prologue */
- tcg_out_addi(s, TCG_REG_SP, -frame_size);
- for(i = 0 ; i < ARRAY_SIZE(tcg_target_callee_save_regs) ; i++) {
- tcg_out_st(s, TCG_TYPE_I32, tcg_target_callee_save_regs[i],
- TCG_REG_SP, TCG_STATIC_CALL_ARGS_SIZE + i * 4);
+ 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) {
+ tcg_out_movi(s, TCG_TYPE_PTR, TCG_GUEST_BASE_REG, guest_base);
+ tcg_regset_set_reg(s->reserved_regs, TCG_GUEST_BASE_REG);
+ }
+#endif
+
/* 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]);
- tb_ret_addr = s->code_ptr;
+
+ /*
+ * Return path for goto_ptr. Set return value to 0, a-la exit_tb,
+ * and fall through to the rest of the epilogue.
+ */
+ s->code_gen_epilogue = s->code_ptr;
+ tcg_out_mov(s, TCG_TYPE_REG, TCG_REG_V0, TCG_REG_ZERO);
/* TB epilogue */
- for(i = 0 ; i < ARRAY_SIZE(tcg_target_callee_save_regs) ; i++) {
- tcg_out_ld(s, TCG_TYPE_I32, tcg_target_callee_save_regs[i],
- TCG_REG_SP, TCG_STATIC_CALL_ARGS_SIZE + i * 4);
+ tb_ret_addr = 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_addi(s, TCG_REG_SP, frame_size);
+ tcg_out_opc_imm(s, ALIAS_PADDI, TCG_REG_SP, TCG_REG_SP, FRAME_SIZE);
if (use_mips32r2_instructions) {
return;
static void tcg_target_init(TCGContext *s)
{
tcg_target_detect_isa();
- tcg_regset_set(tcg_target_available_regs[TCG_TYPE_I32], 0xffffffff);
- tcg_regset_set(tcg_target_call_clobber_regs,
- (1 << TCG_REG_V0) |
- (1 << TCG_REG_V1) |
- (1 << TCG_REG_A0) |
- (1 << TCG_REG_A1) |
- (1 << TCG_REG_A2) |
- (1 << TCG_REG_A3) |
- (1 << TCG_REG_T0) |
- (1 << TCG_REG_T1) |
- (1 << TCG_REG_T2) |
- (1 << TCG_REG_T3) |
- (1 << TCG_REG_T4) |
- (1 << TCG_REG_T5) |
- (1 << TCG_REG_T6) |
- (1 << TCG_REG_T7) |
- (1 << TCG_REG_T8) |
- (1 << TCG_REG_T9));
-
- tcg_regset_clear(s->reserved_regs);
+ 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_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 */
-
- tcg_add_target_add_op_defs(mips_op_defs);
}
-void tb_set_jmp_target1(uintptr_t jmp_addr, uintptr_t addr)
+void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_addr,
+ uintptr_t addr)
{
atomic_set((uint32_t *)jmp_addr, deposit32(OPC_J, 0, 26, addr >> 2));
flush_icache_range(jmp_addr, jmp_addr + 4);
}
+
+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(void *buf, size_t buf_size)
+{
+ tcg_register_jit_int(buf, buf_size, &debug_frame, sizeof(debug_frame));
+}
projects / mirror_qemu.git / blobdiff