diff --git a/tcg/ppc/tcg-target.c.inc b/tcg/ppc/tcg-target.c.inc index c31da4da9d..856c3b18f5 100644 --- a/tcg/ppc/tcg-target.c.inc +++ b/tcg/ppc/tcg-target.c.inc @@ -107,9 +107,7 @@ #define have_isel (cpuinfo & CPUINFO_ISEL) -#ifndef CONFIG_SOFTMMU -#define TCG_GUEST_BASE_REG 30 -#endif +#define TCG_GUEST_BASE_REG TCG_REG_R30 #ifdef CONFIG_DEBUG_TCG static const char tcg_target_reg_names[TCG_TARGET_NB_REGS][4] = { @@ -2317,151 +2315,157 @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h, s_bits == MO_128); a_bits = h->aa.align; -#ifdef CONFIG_SOFTMMU - int mem_index = get_mmuidx(oi); - int cmp_off = is_ld ? offsetof(CPUTLBEntry, addr_read) - : offsetof(CPUTLBEntry, addr_write); - 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); + if (tcg_use_softmmu) { + int mem_index = get_mmuidx(oi); + int cmp_off = is_ld ? offsetof(CPUTLBEntry, addr_read) + : offsetof(CPUTLBEntry, addr_write); + 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); - 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_REG_TMP1, TCG_AREG0, mask_off); - tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP2, TCG_AREG0, table_off); - - /* Extract the page index, shifted into place for tlb index. */ - if (TCG_TARGET_REG_BITS == 32) { - tcg_out_shri32(s, TCG_REG_R0, addrlo, - s->page_bits - CPU_TLB_ENTRY_BITS); - } else { - tcg_out_shri64(s, TCG_REG_R0, addrlo, - s->page_bits - CPU_TLB_ENTRY_BITS); - } - tcg_out32(s, AND | SAB(TCG_REG_TMP1, TCG_REG_TMP1, TCG_REG_R0)); - - /* - * Load the (low part) TLB comparator into TMP2. - * For 64-bit host, always load the entire 64-bit slot for simplicity. - * We will ignore the high bits with tcg_out_cmp(..., addr_type). - */ - if (TCG_TARGET_REG_BITS == 64) { - if (cmp_off == 0) { - tcg_out32(s, LDUX | TAB(TCG_REG_TMP2, TCG_REG_TMP1, TCG_REG_TMP2)); - } else { - tcg_out32(s, ADD | TAB(TCG_REG_TMP1, TCG_REG_TMP1, TCG_REG_TMP2)); - tcg_out_ld(s, TCG_TYPE_I64, TCG_REG_TMP2, TCG_REG_TMP1, cmp_off); - } - } else if (cmp_off == 0 && !HOST_BIG_ENDIAN) { - tcg_out32(s, LWZUX | TAB(TCG_REG_TMP2, TCG_REG_TMP1, TCG_REG_TMP2)); - } else { - tcg_out32(s, ADD | TAB(TCG_REG_TMP1, TCG_REG_TMP1, TCG_REG_TMP2)); - tcg_out_ld(s, TCG_TYPE_I32, TCG_REG_TMP2, TCG_REG_TMP1, - cmp_off + 4 * HOST_BIG_ENDIAN); - } - - /* - * Load the TLB addend for use on the fast path. - * Do this asap to minimize any load use delay. - */ - if (TCG_TARGET_REG_BITS == 64 || addr_type == TCG_TYPE_I32) { - tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP1, TCG_REG_TMP1, - offsetof(CPUTLBEntry, addend)); - } - - /* Clear the non-page, non-alignment bits from the address in R0. */ - if (TCG_TARGET_REG_BITS == 32) { - /* - * We don't support unaligned accesses on 32-bits. - * Preserve the bottom bits and thus trigger a comparison - * failure on unaligned accesses. - */ - if (a_bits < s_bits) { - a_bits = s_bits; - } - tcg_out_rlw(s, RLWINM, TCG_REG_R0, addrlo, 0, - (32 - a_bits) & 31, 31 - s->page_bits); - } else { - TCGReg t = addrlo; - - /* - * If the access is unaligned, we need to make sure we fail if we - * cross a page boundary. The trick is to add the access size-1 - * to the address before masking the low bits. That will make the - * address overflow to the next page if we cross a page boundary, - * which will then force a mismatch of the TLB compare. - */ - if (a_bits < s_bits) { - unsigned a_mask = (1 << a_bits) - 1; - unsigned s_mask = (1 << s_bits) - 1; - tcg_out32(s, ADDI | TAI(TCG_REG_R0, t, s_mask - a_mask)); - t = TCG_REG_R0; - } - - /* Mask the address for the requested alignment. */ - if (addr_type == TCG_TYPE_I32) { - tcg_out_rlw(s, RLWINM, TCG_REG_R0, t, 0, - (32 - a_bits) & 31, 31 - s->page_bits); - } else if (a_bits == 0) { - tcg_out_rld(s, RLDICR, TCG_REG_R0, t, 0, 63 - s->page_bits); - } else { - tcg_out_rld(s, RLDICL, TCG_REG_R0, t, - 64 - s->page_bits, s->page_bits - a_bits); - tcg_out_rld(s, RLDICL, TCG_REG_R0, TCG_REG_R0, s->page_bits, 0); - } - } - - if (TCG_TARGET_REG_BITS == 32 && addr_type != TCG_TYPE_I32) { - /* Low part comparison into cr7. */ - tcg_out_cmp(s, TCG_COND_EQ, TCG_REG_R0, TCG_REG_TMP2, - 0, 7, TCG_TYPE_I32); - - /* Load the high part TLB comparator into TMP2. */ - tcg_out_ld(s, TCG_TYPE_I32, TCG_REG_TMP2, TCG_REG_TMP1, - cmp_off + 4 * !HOST_BIG_ENDIAN); - - /* Load addend, deferred for this case. */ - tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP1, TCG_REG_TMP1, - offsetof(CPUTLBEntry, addend)); - - /* High part comparison into cr6. */ - tcg_out_cmp(s, TCG_COND_EQ, addrhi, TCG_REG_TMP2, 0, 6, TCG_TYPE_I32); - - /* Combine comparisons into cr7. */ - tcg_out32(s, CRAND | BT(7, CR_EQ) | BA(6, CR_EQ) | BB(7, CR_EQ)); - } else { - /* Full comparison into cr7. */ - tcg_out_cmp(s, TCG_COND_EQ, TCG_REG_R0, TCG_REG_TMP2, 0, 7, addr_type); - } - - /* Load a pointer into the current opcode w/conditional branch-link. */ - ldst->label_ptr[0] = s->code_ptr; - tcg_out32(s, BC | BI(7, CR_EQ) | BO_COND_FALSE | LK); - - h->base = TCG_REG_TMP1; -#else - if (a_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_out32(s, ANDI | SAI(addrlo, TCG_REG_R0, (1 << a_bits) - 1)); + /* Load tlb_mask[mmu_idx] and tlb_table[mmu_idx]. */ + tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP1, TCG_AREG0, mask_off); + tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP2, TCG_AREG0, table_off); + /* Extract the page index, shifted into place for tlb index. */ + if (TCG_TARGET_REG_BITS == 32) { + tcg_out_shri32(s, TCG_REG_R0, addrlo, + s->page_bits - CPU_TLB_ENTRY_BITS); + } else { + tcg_out_shri64(s, TCG_REG_R0, addrlo, + s->page_bits - CPU_TLB_ENTRY_BITS); + } + tcg_out32(s, AND | SAB(TCG_REG_TMP1, TCG_REG_TMP1, TCG_REG_R0)); + + /* + * Load the (low part) TLB comparator into TMP2. + * For 64-bit host, always load the entire 64-bit slot for simplicity. + * We will ignore the high bits with tcg_out_cmp(..., addr_type). + */ + if (TCG_TARGET_REG_BITS == 64) { + if (cmp_off == 0) { + tcg_out32(s, LDUX | TAB(TCG_REG_TMP2, + TCG_REG_TMP1, TCG_REG_TMP2)); + } else { + tcg_out32(s, ADD | TAB(TCG_REG_TMP1, + TCG_REG_TMP1, TCG_REG_TMP2)); + tcg_out_ld(s, TCG_TYPE_I64, TCG_REG_TMP2, + TCG_REG_TMP1, cmp_off); + } + } else if (cmp_off == 0 && !HOST_BIG_ENDIAN) { + tcg_out32(s, LWZUX | TAB(TCG_REG_TMP2, + TCG_REG_TMP1, TCG_REG_TMP2)); + } else { + tcg_out32(s, ADD | TAB(TCG_REG_TMP1, TCG_REG_TMP1, TCG_REG_TMP2)); + tcg_out_ld(s, TCG_TYPE_I32, TCG_REG_TMP2, TCG_REG_TMP1, + cmp_off + 4 * HOST_BIG_ENDIAN); + } + + /* + * Load the TLB addend for use on the fast path. + * Do this asap to minimize any load use delay. + */ + if (TCG_TARGET_REG_BITS == 64 || addr_type == TCG_TYPE_I32) { + tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP1, TCG_REG_TMP1, + offsetof(CPUTLBEntry, addend)); + } + + /* Clear the non-page, non-alignment bits from the address in R0. */ + if (TCG_TARGET_REG_BITS == 32) { + /* + * We don't support unaligned accesses on 32-bits. + * Preserve the bottom bits and thus trigger a comparison + * failure on unaligned accesses. + */ + if (a_bits < s_bits) { + a_bits = s_bits; + } + tcg_out_rlw(s, RLWINM, TCG_REG_R0, addrlo, 0, + (32 - a_bits) & 31, 31 - s->page_bits); + } else { + TCGReg t = addrlo; + + /* + * If the access is unaligned, we need to make sure we fail if we + * cross a page boundary. The trick is to add the access size-1 + * to the address before masking the low bits. That will make the + * address overflow to the next page if we cross a page boundary, + * which will then force a mismatch of the TLB compare. + */ + if (a_bits < s_bits) { + unsigned a_mask = (1 << a_bits) - 1; + unsigned s_mask = (1 << s_bits) - 1; + tcg_out32(s, ADDI | TAI(TCG_REG_R0, t, s_mask - a_mask)); + t = TCG_REG_R0; + } + + /* Mask the address for the requested alignment. */ + if (addr_type == TCG_TYPE_I32) { + tcg_out_rlw(s, RLWINM, TCG_REG_R0, t, 0, + (32 - a_bits) & 31, 31 - s->page_bits); + } else if (a_bits == 0) { + tcg_out_rld(s, RLDICR, TCG_REG_R0, t, 0, 63 - s->page_bits); + } else { + tcg_out_rld(s, RLDICL, TCG_REG_R0, t, + 64 - s->page_bits, s->page_bits - a_bits); + tcg_out_rld(s, RLDICL, TCG_REG_R0, TCG_REG_R0, s->page_bits, 0); + } + } + + if (TCG_TARGET_REG_BITS == 32 && addr_type != TCG_TYPE_I32) { + /* Low part comparison into cr7. */ + tcg_out_cmp(s, TCG_COND_EQ, TCG_REG_R0, TCG_REG_TMP2, + 0, 7, TCG_TYPE_I32); + + /* Load the high part TLB comparator into TMP2. */ + tcg_out_ld(s, TCG_TYPE_I32, TCG_REG_TMP2, TCG_REG_TMP1, + cmp_off + 4 * !HOST_BIG_ENDIAN); + + /* Load addend, deferred for this case. */ + tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP1, TCG_REG_TMP1, + offsetof(CPUTLBEntry, addend)); + + /* High part comparison into cr6. */ + tcg_out_cmp(s, TCG_COND_EQ, addrhi, TCG_REG_TMP2, + 0, 6, TCG_TYPE_I32); + + /* Combine comparisons into cr7. */ + tcg_out32(s, CRAND | BT(7, CR_EQ) | BA(6, CR_EQ) | BB(7, CR_EQ)); + } else { + /* Full comparison into cr7. */ + tcg_out_cmp(s, TCG_COND_EQ, TCG_REG_R0, TCG_REG_TMP2, + 0, 7, addr_type); + } + + /* Load a pointer into the current opcode w/conditional branch-link. */ ldst->label_ptr[0] = s->code_ptr; - tcg_out32(s, BC | BI(0, CR_EQ) | BO_COND_FALSE | LK); - } + tcg_out32(s, BC | BI(7, CR_EQ) | BO_COND_FALSE | LK); - h->base = guest_base ? TCG_GUEST_BASE_REG : 0; -#endif + h->base = TCG_REG_TMP1; + } else { + if (a_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_out32(s, ANDI | SAI(addrlo, TCG_REG_R0, (1 << a_bits) - 1)); + + ldst->label_ptr[0] = s->code_ptr; + tcg_out32(s, BC | BI(0, CR_EQ) | BO_COND_FALSE | LK); + } + + h->base = guest_base ? TCG_GUEST_BASE_REG : 0; + } if (TCG_TARGET_REG_BITS == 64 && addr_type == TCG_TYPE_I32) { /* Zero-extend the guest address for use in the host address. */ @@ -2695,12 +2699,10 @@ static void tcg_target_qemu_prologue(TCGContext *s) } tcg_out_st(s, TCG_TYPE_PTR, TCG_REG_R0, TCG_REG_R1, FRAME_SIZE+LR_OFFSET); -#ifndef CONFIG_SOFTMMU - if (guest_base) { + if (!tcg_use_softmmu && guest_base) { tcg_out_movi_int(s, TCG_TYPE_PTR, TCG_GUEST_BASE_REG, guest_base, true); tcg_regset_set_reg(s->reserved_regs, TCG_GUEST_BASE_REG); } -#endif tcg_out_mov(s, TCG_TYPE_PTR, TCG_AREG0, tcg_target_call_iarg_regs[0]); tcg_out32(s, MTSPR | RS(tcg_target_call_iarg_regs[1]) | CTR);