diff options
author | WANG Xuerui <git@xen0n.name> | 2021-12-21 13:40:57 +0800 |
---|---|---|
committer | Richard Henderson <richard.henderson@linaro.org> | 2021-12-21 13:17:06 -0800 |
commit | d3a1727c194edec6a8cd113eb23f83fc27663744 (patch) | |
tree | 57492c3b5d8d883334a8327a76dbca4d70aaf2e6 /tcg/loongarch64 | |
parent | 251ebcd8129d73b7099fbe5e9231aaaa96767cb5 (diff) | |
download | qemu-d3a1727c194edec6a8cd113eb23f83fc27663744.zip qemu-d3a1727c194edec6a8cd113eb23f83fc27663744.tar.gz qemu-d3a1727c194edec6a8cd113eb23f83fc27663744.tar.bz2 |
tcg/loongarch64: Add softmmu load/store helpers, implement qemu_ld/qemu_st ops
Signed-off-by: WANG Xuerui <git@xen0n.name>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20211221054105.178795-24-git@xen0n.name>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Diffstat (limited to 'tcg/loongarch64')
-rw-r--r-- | tcg/loongarch64/tcg-target-con-set.h | 2 | ||||
-rw-r--r-- | tcg/loongarch64/tcg-target.c.inc | 353 |
2 files changed, 355 insertions, 0 deletions
diff --git a/tcg/loongarch64/tcg-target-con-set.h b/tcg/loongarch64/tcg-target-con-set.h index e54ca9b..349c672 100644 --- a/tcg/loongarch64/tcg-target-con-set.h +++ b/tcg/loongarch64/tcg-target-con-set.h @@ -17,7 +17,9 @@ C_O0_I1(r) C_O0_I2(rZ, r) C_O0_I2(rZ, rZ) +C_O0_I2(LZ, L) C_O1_I1(r, r) +C_O1_I1(r, L) C_O1_I2(r, r, rC) C_O1_I2(r, r, ri) C_O1_I2(r, r, rI) diff --git a/tcg/loongarch64/tcg-target.c.inc b/tcg/loongarch64/tcg-target.c.inc index 3d1d7c3..f67d5fa 100644 --- a/tcg/loongarch64/tcg-target.c.inc +++ b/tcg/loongarch64/tcg-target.c.inc @@ -117,6 +117,11 @@ static const int tcg_target_call_oarg_regs[] = { TCG_REG_A1, }; +#ifndef CONFIG_SOFTMMU +#define USE_GUEST_BASE (guest_base != 0) +#define TCG_GUEST_BASE_REG TCG_REG_S1 +#endif + #define TCG_CT_CONST_ZERO 0x100 #define TCG_CT_CONST_S12 0x200 #define TCG_CT_CONST_N12 0x400 @@ -633,6 +638,333 @@ static bool tcg_out_sti(TCGContext *s, TCGType type, TCGArg val, } /* + * Load/store helpers for SoftMMU, and qemu_ld/st implementations + */ + +#if defined(CONFIG_SOFTMMU) +#include "../tcg-ldst.c.inc" + +/* + * helper signature: helper_ret_ld_mmu(CPUState *env, target_ulong addr, + * MemOpIdx oi, uintptr_t ra) + */ +static void * const qemu_ld_helpers[4] = { + [MO_8] = helper_ret_ldub_mmu, + [MO_16] = helper_le_lduw_mmu, + [MO_32] = helper_le_ldul_mmu, + [MO_64] = helper_le_ldq_mmu, +}; + +/* + * helper signature: helper_ret_st_mmu(CPUState *env, target_ulong addr, + * uintxx_t val, MemOpIdx oi, + * uintptr_t ra) + */ +static void * const qemu_st_helpers[4] = { + [MO_8] = helper_ret_stb_mmu, + [MO_16] = helper_le_stw_mmu, + [MO_32] = helper_le_stl_mmu, + [MO_64] = helper_le_stq_mmu, +}; + +/* We expect to use a 12-bit negative offset from ENV. */ +QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) > 0); +QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) < -(1 << 11)); + +static bool tcg_out_goto(TCGContext *s, const tcg_insn_unit *target) +{ + tcg_out_opc_b(s, 0); + return reloc_br_sd10k16(s->code_ptr - 1, target); +} + +/* + * Emits common code for TLB addend lookup, that eventually loads the + * addend in TCG_REG_TMP2. + */ +static void tcg_out_tlb_load(TCGContext *s, TCGReg addrl, MemOpIdx oi, + tcg_insn_unit **label_ptr, bool is_load) +{ + MemOp opc = get_memop(oi); + unsigned s_bits = opc & MO_SIZE; + unsigned a_bits = get_alignment_bits(opc); + tcg_target_long compare_mask; + int mem_index = get_mmuidx(oi); + int fast_ofs = TLB_MASK_TABLE_OFS(mem_index); + int mask_ofs = fast_ofs + offsetof(CPUTLBDescFast, mask); + int table_ofs = fast_ofs + offsetof(CPUTLBDescFast, table); + + tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP0, TCG_AREG0, mask_ofs); + tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP1, TCG_AREG0, table_ofs); + + tcg_out_opc_srli_d(s, TCG_REG_TMP2, addrl, + TARGET_PAGE_BITS - CPU_TLB_ENTRY_BITS); + tcg_out_opc_and(s, TCG_REG_TMP2, TCG_REG_TMP2, TCG_REG_TMP0); + tcg_out_opc_add_d(s, TCG_REG_TMP2, TCG_REG_TMP2, TCG_REG_TMP1); + + /* Load the tlb comparator and the addend. */ + tcg_out_ld(s, TCG_TYPE_TL, TCG_REG_TMP0, TCG_REG_TMP2, + is_load ? offsetof(CPUTLBEntry, addr_read) + : offsetof(CPUTLBEntry, addr_write)); + tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP2, TCG_REG_TMP2, + offsetof(CPUTLBEntry, addend)); + + /* We don't support unaligned accesses. */ + if (a_bits < s_bits) { + a_bits = s_bits; + } + /* Clear the non-page, non-alignment bits from the address. */ + compare_mask = (tcg_target_long)TARGET_PAGE_MASK | ((1 << a_bits) - 1); + tcg_out_movi(s, TCG_TYPE_TL, TCG_REG_TMP1, compare_mask); + tcg_out_opc_and(s, TCG_REG_TMP1, TCG_REG_TMP1, addrl); + + /* Compare masked address with the TLB entry. */ + label_ptr[0] = s->code_ptr; + tcg_out_opc_bne(s, TCG_REG_TMP0, TCG_REG_TMP1, 0); + + /* TLB Hit - addend in TCG_REG_TMP2, ready for use. */ +} + +static void add_qemu_ldst_label(TCGContext *s, int is_ld, MemOpIdx oi, + TCGType type, + TCGReg datalo, TCGReg addrlo, + void *raddr, tcg_insn_unit **label_ptr) +{ + TCGLabelQemuLdst *label = new_ldst_label(s); + + label->is_ld = is_ld; + label->oi = oi; + label->type = type; + label->datalo_reg = datalo; + label->datahi_reg = 0; /* unused */ + label->addrlo_reg = addrlo; + label->addrhi_reg = 0; /* unused */ + label->raddr = tcg_splitwx_to_rx(raddr); + label->label_ptr[0] = label_ptr[0]; +} + +static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l) +{ + MemOpIdx oi = l->oi; + MemOp opc = get_memop(oi); + MemOp size = opc & MO_SIZE; + TCGType type = l->type; + + /* resolve label address */ + if (!reloc_br_sk16(l->label_ptr[0], tcg_splitwx_to_rx(s->code_ptr))) { + return false; + } + + /* call load helper */ + tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_A0, TCG_AREG0); + tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_A1, l->addrlo_reg); + tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_A2, oi); + tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_A3, (tcg_target_long)l->raddr); + + tcg_out_call(s, qemu_ld_helpers[size]); + + switch (opc & MO_SSIZE) { + case MO_SB: + tcg_out_ext8s(s, l->datalo_reg, TCG_REG_A0); + break; + case MO_SW: + tcg_out_ext16s(s, l->datalo_reg, TCG_REG_A0); + break; + case MO_SL: + tcg_out_ext32s(s, l->datalo_reg, TCG_REG_A0); + break; + case MO_UL: + if (type == TCG_TYPE_I32) { + /* MO_UL loads of i32 should be sign-extended too */ + tcg_out_ext32s(s, l->datalo_reg, TCG_REG_A0); + break; + } + /* fallthrough */ + default: + tcg_out_mov(s, type, l->datalo_reg, TCG_REG_A0); + break; + } + + return tcg_out_goto(s, l->raddr); +} + +static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l) +{ + MemOpIdx oi = l->oi; + MemOp opc = get_memop(oi); + MemOp size = opc & MO_SIZE; + + /* resolve label address */ + if (!reloc_br_sk16(l->label_ptr[0], tcg_splitwx_to_rx(s->code_ptr))) { + return false; + } + + /* call store helper */ + tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_A0, TCG_AREG0); + tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_A1, l->addrlo_reg); + switch (size) { + case MO_8: + tcg_out_ext8u(s, TCG_REG_A2, l->datalo_reg); + break; + case MO_16: + tcg_out_ext16u(s, TCG_REG_A2, l->datalo_reg); + break; + case MO_32: + tcg_out_ext32u(s, TCG_REG_A2, l->datalo_reg); + break; + case MO_64: + tcg_out_mov(s, TCG_TYPE_I64, TCG_REG_A2, l->datalo_reg); + break; + default: + g_assert_not_reached(); + break; + } + tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_A3, oi); + tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_A4, (tcg_target_long)l->raddr); + + tcg_out_call(s, qemu_st_helpers[size]); + + return tcg_out_goto(s, l->raddr); +} +#endif /* CONFIG_SOFTMMU */ + +/* + * `ext32u` the address register into the temp register given, + * if target is 32-bit, no-op otherwise. + * + * Returns the address register ready for use with TLB addend. + */ +static TCGReg tcg_out_zext_addr_if_32_bit(TCGContext *s, + TCGReg addr, TCGReg tmp) +{ + if (TARGET_LONG_BITS == 32) { + tcg_out_ext32u(s, tmp, addr); + return tmp; + } + return addr; +} + +static void tcg_out_qemu_ld_indexed(TCGContext *s, TCGReg rd, TCGReg rj, + TCGReg rk, MemOp opc, TCGType type) +{ + /* Byte swapping is left to middle-end expansion. */ + tcg_debug_assert((opc & MO_BSWAP) == 0); + + switch (opc & MO_SSIZE) { + case MO_UB: + tcg_out_opc_ldx_bu(s, rd, rj, rk); + break; + case MO_SB: + tcg_out_opc_ldx_b(s, rd, rj, rk); + break; + case MO_UW: + tcg_out_opc_ldx_hu(s, rd, rj, rk); + break; + case MO_SW: + tcg_out_opc_ldx_h(s, rd, rj, rk); + break; + case MO_UL: + if (type == TCG_TYPE_I64) { + tcg_out_opc_ldx_wu(s, rd, rj, rk); + break; + } + /* fallthrough */ + case MO_SL: + tcg_out_opc_ldx_w(s, rd, rj, rk); + break; + case MO_Q: + tcg_out_opc_ldx_d(s, rd, rj, rk); + break; + default: + g_assert_not_reached(); + } +} + +static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, TCGType type) +{ + TCGReg addr_regl; + TCGReg data_regl; + MemOpIdx oi; + MemOp opc; +#if defined(CONFIG_SOFTMMU) + tcg_insn_unit *label_ptr[1]; +#endif + TCGReg base; + + data_regl = *args++; + addr_regl = *args++; + oi = *args++; + opc = get_memop(oi); + +#if defined(CONFIG_SOFTMMU) + tcg_out_tlb_load(s, addr_regl, oi, label_ptr, 1); + base = tcg_out_zext_addr_if_32_bit(s, addr_regl, TCG_REG_TMP0); + tcg_out_qemu_ld_indexed(s, data_regl, base, TCG_REG_TMP2, opc, type); + add_qemu_ldst_label(s, 1, oi, type, + data_regl, addr_regl, + s->code_ptr, label_ptr); +#else + base = tcg_out_zext_addr_if_32_bit(s, addr_regl, TCG_REG_TMP0); + TCGReg guest_base_reg = USE_GUEST_BASE ? TCG_GUEST_BASE_REG : TCG_REG_ZERO; + tcg_out_qemu_ld_indexed(s, data_regl, base, guest_base_reg, opc, type); +#endif +} + +static void tcg_out_qemu_st_indexed(TCGContext *s, TCGReg data, + TCGReg rj, TCGReg rk, MemOp opc) +{ + /* Byte swapping is left to middle-end expansion. */ + tcg_debug_assert((opc & MO_BSWAP) == 0); + + switch (opc & MO_SIZE) { + case MO_8: + tcg_out_opc_stx_b(s, data, rj, rk); + break; + case MO_16: + tcg_out_opc_stx_h(s, data, rj, rk); + break; + case MO_32: + tcg_out_opc_stx_w(s, data, rj, rk); + break; + case MO_64: + tcg_out_opc_stx_d(s, data, rj, rk); + break; + default: + g_assert_not_reached(); + } +} + +static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args) +{ + TCGReg addr_regl; + TCGReg data_regl; + MemOpIdx oi; + MemOp opc; +#if defined(CONFIG_SOFTMMU) + tcg_insn_unit *label_ptr[1]; +#endif + TCGReg base; + + data_regl = *args++; + addr_regl = *args++; + oi = *args++; + opc = get_memop(oi); + +#if defined(CONFIG_SOFTMMU) + tcg_out_tlb_load(s, addr_regl, oi, label_ptr, 0); + base = tcg_out_zext_addr_if_32_bit(s, addr_regl, TCG_REG_TMP0); + tcg_out_qemu_st_indexed(s, data_regl, base, TCG_REG_TMP2, opc); + add_qemu_ldst_label(s, 0, oi, + 0, /* type param is unused for stores */ + data_regl, addr_regl, + s->code_ptr, label_ptr); +#else + base = tcg_out_zext_addr_if_32_bit(s, addr_regl, TCG_REG_TMP0); + TCGReg guest_base_reg = USE_GUEST_BASE ? TCG_GUEST_BASE_REG : TCG_REG_ZERO; + tcg_out_qemu_st_indexed(s, data_regl, base, guest_base_reg, opc); +#endif +} + +/* * Entry-points */ @@ -1023,6 +1355,19 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc, tcg_out_ldst(s, OPC_ST_D, a0, a1, a2); break; + case INDEX_op_qemu_ld_i32: + tcg_out_qemu_ld(s, args, TCG_TYPE_I32); + break; + case INDEX_op_qemu_ld_i64: + tcg_out_qemu_ld(s, args, TCG_TYPE_I64); + break; + case INDEX_op_qemu_st_i32: + tcg_out_qemu_st(s, args); + break; + case INDEX_op_qemu_st_i64: + tcg_out_qemu_st(s, args); + 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. */ @@ -1050,6 +1395,10 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op) case INDEX_op_brcond_i64: return C_O0_I2(rZ, rZ); + case INDEX_op_qemu_st_i32: + case INDEX_op_qemu_st_i64: + return C_O0_I2(LZ, L); + case INDEX_op_ext8s_i32: case INDEX_op_ext8s_i64: case INDEX_op_ext8u_i32: @@ -1087,6 +1436,10 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op) case INDEX_op_ld_i64: return C_O1_I1(r, r); + case INDEX_op_qemu_ld_i32: + case INDEX_op_qemu_ld_i64: + return C_O1_I1(r, L); + case INDEX_op_andc_i32: case INDEX_op_andc_i64: case INDEX_op_orc_i32: |