This vastly reduces the size of code generated for 64-bit addresses. The code for exit_tb, for instance, where we load a (tagged) pointer to the current TB, goes from
0x400aa9725c: li v0,64 0x400aa97260: dsll v0,v0,0x10 0x400aa97264: ori v0,v0,0xaa9 0x400aa97268: dsll v0,v0,0x10 0x400aa9726c: j 0x400aa9703c 0x400aa97270: ori v0,v0,0x7083 to 0x400aa97240: j 0x400aa97040 0x400aa97244: daddiu v0,s6,-189 Signed-off-by: Richard Henderson <richard.hender...@linaro.org> --- tcg/mips/tcg-target.c.inc | 75 ++++++++++++++++++++++++++++++++------- 1 file changed, 62 insertions(+), 13 deletions(-) diff --git a/tcg/mips/tcg-target.c.inc b/tcg/mips/tcg-target.c.inc index 46616784f8..76fb1dada0 100644 --- a/tcg/mips/tcg-target.c.inc +++ b/tcg/mips/tcg-target.c.inc @@ -88,6 +88,11 @@ static const char * const tcg_target_reg_names[TCG_TARGET_NB_REGS] = { #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[] = { @@ -1971,34 +1976,72 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc, switch (opc) { case INDEX_op_exit_tb: { - TCGReg b0 = TCG_REG_ZERO; + TCGReg base = TCG_REG_ZERO; + int16_t lo = 0; - a0 = (intptr_t)a0; - if (a0 & ~0xffff) { - tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_V0, a0 & ~0xffff); - b0 = TCG_REG_V0; + 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); } - tcg_out_opc_imm(s, OPC_ORI, TCG_REG_V0, b0, a0 & 0xffff); + tcg_out_opc_imm(s, ALIAS_PADDI, TCG_REG_V0, base, lo); } break; case INDEX_op_goto_tb: /* indirect jump method */ tcg_debug_assert(s->tb_jmp_insn_offset == 0); - tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP0, TCG_REG_ZERO, - (uintptr_t)(s->tb_jmp_target_addr + a0)); - tcg_out_opc_reg(s, OPC_JR, 0, TCG_TMP0, 0); - tcg_out_nop(s); - set_jmp_reset_offset(s, a0); + { + TCGReg base, dest; + intptr_t ofs; + + if (TCG_TARGET_REG_BITS == 64) { + dest = base = TCG_REG_TB; + ofs = tcg_tbrel_diff(s, s->tb_jmp_target_addr + a0); + } else { + dest = TCG_TMP0; + base = TCG_REG_ZERO; + ofs = (intptr_t)(s->tb_jmp_target_addr + a0); + } + 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, args[0]); + 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)); + } + } 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); + 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, @@ -2554,7 +2597,7 @@ static const int tcg_target_callee_save_regs[] = { TCG_REG_S3, TCG_REG_S4, TCG_REG_S5, - TCG_REG_S6, + 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 */ @@ -2682,6 +2725,9 @@ static void tcg_target_qemu_prologue(TCGContext *s) 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); @@ -2863,6 +2909,9 @@ static void tcg_target_init(TCGContext *s) 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 { -- 2.25.1