diff options
Diffstat (limited to 'tcg')
-rw-r--r-- | tcg/aarch64/tcg-target.inc.c | 7 | ||||
-rw-r--r-- | tcg/arm/tcg-target.inc.c | 78 | ||||
-rw-r--r-- | tcg/ppc/tcg-target.inc.c | 71 | ||||
-rw-r--r-- | tcg/tcg-runtime.c | 233 | ||||
-rw-r--r-- | tcg/tcg.c | 20 | ||||
-rw-r--r-- | tcg/tcg.h | 2 | ||||
-rw-r--r-- | tcg/tci.c | 1251 |
7 files changed, 1559 insertions, 103 deletions
diff --git a/tcg/aarch64/tcg-target.inc.c b/tcg/aarch64/tcg-target.inc.c index 5f18545..1fa3bcc 100644 --- a/tcg/aarch64/tcg-target.inc.c +++ b/tcg/aarch64/tcg-target.inc.c @@ -616,7 +616,12 @@ static void tcg_out_movi(TCGContext *s, TCGType type, TCGReg rd, /* Look for host pointer values within 4G of the PC. This happens often when loading pointers to QEMU's own data structures. */ if (type == TCG_TYPE_I64) { - tcg_target_long disp = (value >> 12) - ((intptr_t)s->code_ptr >> 12); + tcg_target_long disp = value - (intptr_t)s->code_ptr; + if (disp == sextract64(disp, 0, 21)) { + tcg_out_insn(s, 3406, ADR, rd, disp); + return; + } + disp = (value >> 12) - ((intptr_t)s->code_ptr >> 12); if (disp == sextract64(disp, 0, 21)) { tcg_out_insn(s, 3406, ADRP, rd, disp); if (value & 0xfff) { diff --git a/tcg/arm/tcg-target.inc.c b/tcg/arm/tcg-target.inc.c index 9f5cb66..d1793ec 100644 --- a/tcg/arm/tcg-target.inc.c +++ b/tcg/arm/tcg-target.inc.c @@ -418,23 +418,37 @@ static inline void tcg_out_dat_imm(TCGContext *s, static void tcg_out_movi32(TCGContext *s, int cond, int rd, uint32_t arg) { - int rot, opc, rn; - - /* For armv7, make sure not to use movw+movt when mov/mvn would do. - Speed things up by only checking when movt would be required. - Prior to armv7, have one go at fully rotated immediates before - doing the decomposition thing below. */ - if (!use_armv7_instructions || (arg & 0xffff0000)) { - rot = encode_imm(arg); + int rot, opc, rn, diff; + + /* Check a single MOV/MVN before anything else. */ + rot = encode_imm(arg); + if (rot >= 0) { + tcg_out_dat_imm(s, cond, ARITH_MOV, rd, 0, + rotl(arg, rot) | (rot << 7)); + return; + } + rot = encode_imm(~arg); + if (rot >= 0) { + tcg_out_dat_imm(s, cond, ARITH_MVN, rd, 0, + rotl(~arg, rot) | (rot << 7)); + return; + } + + /* Check for a pc-relative address. This will usually be the TB, + or within the TB, which is immediately before the code block. */ + diff = arg - ((intptr_t)s->code_ptr + 8); + if (diff >= 0) { + rot = encode_imm(diff); if (rot >= 0) { - tcg_out_dat_imm(s, cond, ARITH_MOV, rd, 0, - rotl(arg, rot) | (rot << 7)); + tcg_out_dat_imm(s, cond, ARITH_ADD, rd, TCG_REG_PC, + rotl(diff, rot) | (rot << 7)); return; } - rot = encode_imm(~arg); + } else { + rot = encode_imm(-diff); if (rot >= 0) { - tcg_out_dat_imm(s, cond, ARITH_MVN, rd, 0, - rotl(~arg, rot) | (rot << 7)); + tcg_out_dat_imm(s, cond, ARITH_SUB, rd, TCG_REG_PC, + rotl(-diff, rot) | (rot << 7)); return; } } @@ -1026,16 +1040,6 @@ static void tcg_out_call(TCGContext *s, tcg_insn_unit *addr) } } -void arm_tb_set_jmp_target(uintptr_t jmp_addr, uintptr_t addr) -{ - tcg_insn_unit *code_ptr = (tcg_insn_unit *)jmp_addr; - tcg_insn_unit *target = (tcg_insn_unit *)addr; - - /* we could use a ldr pc, [pc, #-4] kind of branch and avoid the flush */ - reloc_pc24_atomic(code_ptr, target); - flush_icache_range(jmp_addr, jmp_addr + 4); -} - static inline void tcg_out_goto_label(TCGContext *s, int cond, TCGLabel *l) { if (l->has_value) { @@ -1665,17 +1669,27 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, } break; case INDEX_op_goto_tb: - if (s->tb_jmp_insn_offset) { - /* Direct jump method */ - s->tb_jmp_insn_offset[args[0]] = tcg_current_code_size(s); - tcg_out_b_noaddr(s, COND_AL); - } else { + { /* Indirect jump method */ - intptr_t ptr = (intptr_t)(s->tb_jmp_target_addr + args[0]); - tcg_out_movi32(s, COND_AL, TCG_REG_R0, ptr & ~0xfff); - tcg_out_ld32_12(s, COND_AL, TCG_REG_PC, TCG_REG_R0, ptr & 0xfff); + intptr_t ptr, dif, dil; + TCGReg base = TCG_REG_PC; + + tcg_debug_assert(s->tb_jmp_insn_offset == 0); + ptr = (intptr_t)(s->tb_jmp_target_addr + args[0]); + dif = ptr - ((intptr_t)s->code_ptr + 8); + dil = sextract32(dif, 0, 12); + if (dif != dil) { + /* The TB is close, but outside the 12 bits addressable by + the load. We can extend this to 20 bits with a sub of a + shifted immediate from pc. In the vastly unlikely event + the code requires more than 1MB, we'll use 2 insns and + be no worse off. */ + base = TCG_REG_R0; + tcg_out_movi32(s, COND_AL, base, ptr - dil); + } + tcg_out_ld32_12(s, COND_AL, TCG_REG_PC, base, dil); + s->tb_jmp_reset_offset[args[0]] = tcg_current_code_size(s); } - s->tb_jmp_reset_offset[args[0]] = tcg_current_code_size(s); break; case INDEX_op_goto_ptr: tcg_out_bx(s, COND_AL, args[0]); diff --git a/tcg/ppc/tcg-target.inc.c b/tcg/ppc/tcg-target.inc.c index 8d50f18..1f690df 100644 --- a/tcg/ppc/tcg-target.inc.c +++ b/tcg/ppc/tcg-target.inc.c @@ -2820,14 +2820,11 @@ void tcg_register_jit(void *buf, size_t buf_size) } #endif /* __ELF__ */ -static size_t dcache_bsize = 16; -static size_t icache_bsize = 16; - void flush_icache_range(uintptr_t start, uintptr_t stop) { uintptr_t p, start1, stop1; - size_t dsize = dcache_bsize; - size_t isize = icache_bsize; + size_t dsize = qemu_dcache_linesize; + size_t isize = qemu_icache_linesize; start1 = start & ~(dsize - 1); stop1 = (stop + dsize - 1) & ~(dsize - 1); @@ -2844,67 +2841,3 @@ void flush_icache_range(uintptr_t start, uintptr_t stop) asm volatile ("sync" : : : "memory"); asm volatile ("isync" : : : "memory"); } - -#if defined _AIX -#include <sys/systemcfg.h> - -static void __attribute__((constructor)) tcg_cache_init(void) -{ - icache_bsize = _system_configuration.icache_line; - dcache_bsize = _system_configuration.dcache_line; -} - -#elif defined __linux__ -static void __attribute__((constructor)) tcg_cache_init(void) -{ - unsigned long dsize = qemu_getauxval(AT_DCACHEBSIZE); - unsigned long isize = qemu_getauxval(AT_ICACHEBSIZE); - - if (dsize == 0 || isize == 0) { - if (dsize == 0) { - fprintf(stderr, "getauxval AT_DCACHEBSIZE failed\n"); - } - if (isize == 0) { - fprintf(stderr, "getauxval AT_ICACHEBSIZE failed\n"); - } - exit(1); - } - dcache_bsize = dsize; - icache_bsize = isize; -} - -#elif defined __APPLE__ -#include <sys/sysctl.h> - -static void __attribute__((constructor)) tcg_cache_init(void) -{ - size_t len; - unsigned cacheline; - int name[2] = { CTL_HW, HW_CACHELINE }; - - len = sizeof(cacheline); - if (sysctl(name, 2, &cacheline, &len, NULL, 0)) { - perror("sysctl CTL_HW HW_CACHELINE failed"); - exit(1); - } - dcache_bsize = cacheline; - icache_bsize = cacheline; -} - -#elif defined(__FreeBSD__) || defined(__FreeBSD_kernel__) -#include <sys/sysctl.h> - -static void __attribute__((constructor)) tcg_cache_init(void) -{ - size_t len = 4; - unsigned cacheline; - - if (sysctlbyname ("machdep.cacheline_size", &cacheline, &len, NULL, 0)) { - fprintf(stderr, "sysctlbyname machdep.cacheline_size failed: %s\n", - strerror(errno)); - exit(1); - } - dcache_bsize = cacheline; - icache_bsize = cacheline; -} -#endif diff --git a/tcg/tcg-runtime.c b/tcg/tcg-runtime.c new file mode 100644 index 0000000..ec3a34e --- /dev/null +++ b/tcg/tcg-runtime.c @@ -0,0 +1,233 @@ +/* + * Tiny Code Generator for QEMU + * + * 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 "qemu/osdep.h" +#include "qemu/host-utils.h" +#include "cpu.h" +#include "exec/helper-proto.h" +#include "exec/cpu_ldst.h" +#include "exec/exec-all.h" +#include "exec/tb-hash.h" +#include "disas/disas.h" +#include "exec/log.h" + +/* 32-bit helpers */ + +int32_t HELPER(div_i32)(int32_t arg1, int32_t arg2) +{ + return arg1 / arg2; +} + +int32_t HELPER(rem_i32)(int32_t arg1, int32_t arg2) +{ + return arg1 % arg2; +} + +uint32_t HELPER(divu_i32)(uint32_t arg1, uint32_t arg2) +{ + return arg1 / arg2; +} + +uint32_t HELPER(remu_i32)(uint32_t arg1, uint32_t arg2) +{ + return arg1 % arg2; +} + +/* 64-bit helpers */ + +uint64_t HELPER(shl_i64)(uint64_t arg1, uint64_t arg2) +{ + return arg1 << arg2; +} + +uint64_t HELPER(shr_i64)(uint64_t arg1, uint64_t arg2) +{ + return arg1 >> arg2; +} + +int64_t HELPER(sar_i64)(int64_t arg1, int64_t arg2) +{ + return arg1 >> arg2; +} + +int64_t HELPER(div_i64)(int64_t arg1, int64_t arg2) +{ + return arg1 / arg2; +} + +int64_t HELPER(rem_i64)(int64_t arg1, int64_t arg2) +{ + return arg1 % arg2; +} + +uint64_t HELPER(divu_i64)(uint64_t arg1, uint64_t arg2) +{ + return arg1 / arg2; +} + +uint64_t HELPER(remu_i64)(uint64_t arg1, uint64_t arg2) +{ + return arg1 % arg2; +} + +uint64_t HELPER(muluh_i64)(uint64_t arg1, uint64_t arg2) +{ + uint64_t l, h; + mulu64(&l, &h, arg1, arg2); + return h; +} + +int64_t HELPER(mulsh_i64)(int64_t arg1, int64_t arg2) +{ + uint64_t l, h; + muls64(&l, &h, arg1, arg2); + return h; +} + +uint32_t HELPER(clz_i32)(uint32_t arg, uint32_t zero_val) +{ + return arg ? clz32(arg) : zero_val; +} + +uint32_t HELPER(ctz_i32)(uint32_t arg, uint32_t zero_val) +{ + return arg ? ctz32(arg) : zero_val; +} + +uint64_t HELPER(clz_i64)(uint64_t arg, uint64_t zero_val) +{ + return arg ? clz64(arg) : zero_val; +} + +uint64_t HELPER(ctz_i64)(uint64_t arg, uint64_t zero_val) +{ + return arg ? ctz64(arg) : zero_val; +} + +uint32_t HELPER(clrsb_i32)(uint32_t arg) +{ + return clrsb32(arg); +} + +uint64_t HELPER(clrsb_i64)(uint64_t arg) +{ + return clrsb64(arg); +} + +uint32_t HELPER(ctpop_i32)(uint32_t arg) +{ + return ctpop32(arg); +} + +uint64_t HELPER(ctpop_i64)(uint64_t arg) +{ + return ctpop64(arg); +} + +void *HELPER(lookup_tb_ptr)(CPUArchState *env, target_ulong addr) +{ + CPUState *cpu = ENV_GET_CPU(env); + TranslationBlock *tb; + target_ulong cs_base, pc; + uint32_t flags, addr_hash; + + addr_hash = tb_jmp_cache_hash_func(addr); + tb = atomic_rcu_read(&cpu->tb_jmp_cache[addr_hash]); + cpu_get_tb_cpu_state(env, &pc, &cs_base, &flags); + + if (unlikely(!(tb + && tb->pc == addr + && tb->cs_base == cs_base + && tb->flags == flags))) { + tb = tb_htable_lookup(cpu, addr, cs_base, flags); + if (!tb) { + return tcg_ctx.code_gen_epilogue; + } + atomic_set(&cpu->tb_jmp_cache[addr_hash], tb); + } + + qemu_log_mask_and_addr(CPU_LOG_EXEC, addr, + "Chain %p [%d: " TARGET_FMT_lx "] %s\n", + tb->tc_ptr, cpu->cpu_index, addr, + lookup_symbol(addr)); + return tb->tc_ptr; +} + +void HELPER(exit_atomic)(CPUArchState *env) +{ + cpu_loop_exit_atomic(ENV_GET_CPU(env), GETPC()); +} + +#ifndef CONFIG_SOFTMMU +/* The softmmu versions of these helpers are in cputlb.c. */ + +/* Do not allow unaligned operations to proceed. Return the host address. */ +static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr, + int size, uintptr_t retaddr) +{ + /* Enforce qemu required alignment. */ + if (unlikely(addr & (size - 1))) { + cpu_loop_exit_atomic(ENV_GET_CPU(env), retaddr); + } + return g2h(addr); +} + +/* Macro to call the above, with local variables from the use context. */ +#define ATOMIC_MMU_LOOKUP atomic_mmu_lookup(env, addr, DATA_SIZE, GETPC()) + +#define ATOMIC_NAME(X) HELPER(glue(glue(atomic_ ## X, SUFFIX), END)) +#define EXTRA_ARGS + +#define DATA_SIZE 1 +#include "atomic_template.h" + +#define DATA_SIZE 2 +#include "atomic_template.h" + +#define DATA_SIZE 4 +#include "atomic_template.h" + +#ifdef CONFIG_ATOMIC64 +#define DATA_SIZE 8 +#include "atomic_template.h" +#endif + +/* The following is only callable from other helpers, and matches up + with the softmmu version. */ + +#ifdef CONFIG_ATOMIC128 + +#undef EXTRA_ARGS +#undef ATOMIC_NAME +#undef ATOMIC_MMU_LOOKUP + +#define EXTRA_ARGS , TCGMemOpIdx oi, uintptr_t retaddr +#define ATOMIC_NAME(X) \ + HELPER(glue(glue(glue(atomic_ ## X, SUFFIX), END), _mmu)) +#define ATOMIC_MMU_LOOKUP atomic_mmu_lookup(env, addr, DATA_SIZE, retaddr) + +#define DATA_SIZE 16 +#include "atomic_template.h" +#endif /* CONFIG_ATOMIC128 */ + +#endif /* !CONFIG_SOFTMMU */ @@ -383,6 +383,26 @@ void tcg_context_init(TCGContext *s) } } +/* + * Allocate TBs right before their corresponding translated code, making + * sure that TBs and code are on different cache lines. + */ +TranslationBlock *tcg_tb_alloc(TCGContext *s) +{ + uintptr_t align = qemu_icache_linesize; + TranslationBlock *tb; + void *next; + + tb = (void *)ROUND_UP((uintptr_t)s->code_gen_ptr, align); + next = (void *)ROUND_UP((uintptr_t)(tb + 1), align); + + if (unlikely(next > s->code_gen_highwater)) { + return NULL; + } + s->code_gen_ptr = next; + return tb; +} + void tcg_prologue_init(TCGContext *s) { size_t prologue_size, total_size; @@ -697,7 +697,6 @@ struct TCGContext { here, because there's too much arithmetic throughout that relies on addition and subtraction working on bytes. Rely on the GCC extension that allows arithmetic on void*. */ - int code_gen_max_blocks; void *code_gen_prologue; void *code_gen_epilogue; void *code_gen_buffer; @@ -756,6 +755,7 @@ static inline bool tcg_op_buf_full(void) /* tb_lock must be held for tcg_malloc_internal. */ void *tcg_malloc_internal(TCGContext *s, int size); void tcg_pool_reset(TCGContext *s); +TranslationBlock *tcg_tb_alloc(TCGContext *s); void tb_lock(void); void tb_unlock(void); diff --git a/tcg/tci.c b/tcg/tci.c new file mode 100644 index 0000000..4bdc645 --- /dev/null +++ b/tcg/tci.c @@ -0,0 +1,1251 @@ +/* + * Tiny Code Interpreter for QEMU + * + * Copyright (c) 2009, 2011, 2016 Stefan Weil + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" + +/* Enable TCI assertions only when debugging TCG (and without NDEBUG defined). + * Without assertions, the interpreter runs much faster. */ +#if defined(CONFIG_DEBUG_TCG) +# define tci_assert(cond) assert(cond) +#else +# define tci_assert(cond) ((void)0) +#endif + +#include "qemu-common.h" +#include "tcg/tcg.h" /* MAX_OPC_PARAM_IARGS */ +#include "exec/cpu_ldst.h" +#include "tcg-op.h" + +/* Marker for missing code. */ +#define TODO() \ + do { \ + fprintf(stderr, "TODO %s:%u: %s()\n", \ + __FILE__, __LINE__, __func__); \ + tcg_abort(); \ + } while (0) + +#if MAX_OPC_PARAM_IARGS != 5 +# error Fix needed, number of supported input arguments changed! +#endif +#if TCG_TARGET_REG_BITS == 32 +typedef uint64_t (*helper_function)(tcg_target_ulong, tcg_target_ulong, + tcg_target_ulong, tcg_target_ulong, + tcg_target_ulong, tcg_target_ulong, + tcg_target_ulong, tcg_target_ulong, + tcg_target_ulong, tcg_target_ulong); +#else +typedef uint64_t (*helper_function)(tcg_target_ulong, tcg_target_ulong, + tcg_target_ulong, tcg_target_ulong, + tcg_target_ulong); +#endif + +static tcg_target_ulong tci_reg[TCG_TARGET_NB_REGS]; + +static tcg_target_ulong tci_read_reg(TCGReg index) +{ + tci_assert(index < ARRAY_SIZE(tci_reg)); + return tci_reg[index]; +} + +#if TCG_TARGET_HAS_ext8s_i32 || TCG_TARGET_HAS_ext8s_i64 +static int8_t tci_read_reg8s(TCGReg index) +{ + return (int8_t)tci_read_reg(index); +} +#endif + +#if TCG_TARGET_HAS_ext16s_i32 || TCG_TARGET_HAS_ext16s_i64 +static int16_t tci_read_reg16s(TCGReg index) +{ + return (int16_t)tci_read_reg(index); +} +#endif + +#if TCG_TARGET_REG_BITS == 64 +static int32_t tci_read_reg32s(TCGReg index) +{ + return (int32_t)tci_read_reg(index); +} +#endif + +static uint8_t tci_read_reg8(TCGReg index) +{ + return (uint8_t)tci_read_reg(index); +} + +static uint16_t tci_read_reg16(TCGReg index) +{ + return (uint16_t)tci_read_reg(index); +} + +static uint32_t tci_read_reg32(TCGReg index) +{ + return (uint32_t)tci_read_reg(index); +} + +#if TCG_TARGET_REG_BITS == 64 +static uint64_t tci_read_reg64(TCGReg index) +{ + return tci_read_reg(index); +} +#endif + +static void tci_write_reg(TCGReg index, tcg_target_ulong value) +{ + tci_assert(index < ARRAY_SIZE(tci_reg)); + tci_assert(index != TCG_AREG0); + tci_assert(index != TCG_REG_CALL_STACK); + tci_reg[index] = value; +} + +#if TCG_TARGET_REG_BITS == 64 +static void tci_write_reg32s(TCGReg index, int32_t value) +{ + tci_write_reg(index, value); +} +#endif + +static void tci_write_reg8(TCGReg index, uint8_t value) +{ + tci_write_reg(index, value); +} + +static void tci_write_reg32(TCGReg index, uint32_t value) +{ + tci_write_reg(index, value); +} + +#if TCG_TARGET_REG_BITS == 32 +static void tci_write_reg64(uint32_t high_index, uint32_t low_index, + uint64_t value) +{ + tci_write_reg(low_index, value); + tci_write_reg(high_index, value >> 32); +} +#elif TCG_TARGET_REG_BITS == 64 +static void tci_write_reg64(TCGReg index, uint64_t value) +{ + tci_write_reg(index, value); +} +#endif + +#if TCG_TARGET_REG_BITS == 32 +/* Create a 64 bit value from two 32 bit values. */ +static uint64_t tci_uint64(uint32_t high, uint32_t low) +{ + return ((uint64_t)high << 32) + low; +} +#endif + +/* Read constant (native size) from bytecode. */ +static tcg_target_ulong tci_read_i(uint8_t **tb_ptr) +{ + tcg_target_ulong value = *(tcg_target_ulong *)(*tb_ptr); + *tb_ptr += sizeof(value); + return value; +} + +/* Read unsigned constant (32 bit) from bytecode. */ +static uint32_t tci_read_i32(uint8_t **tb_ptr) +{ + uint32_t value = *(uint32_t *)(*tb_ptr); + *tb_ptr += sizeof(value); + return value; +} + +/* Read signed constant (32 bit) from bytecode. */ +static int32_t tci_read_s32(uint8_t **tb_ptr) +{ + int32_t value = *(int32_t *)(*tb_ptr); + *tb_ptr += sizeof(value); + return value; +} + +#if TCG_TARGET_REG_BITS == 64 +/* Read constant (64 bit) from bytecode. */ +static uint64_t tci_read_i64(uint8_t **tb_ptr) +{ + uint64_t value = *(uint64_t *)(*tb_ptr); + *tb_ptr += sizeof(value); + return value; +} +#endif + +/* Read indexed register (native size) from bytecode. */ +static tcg_target_ulong tci_read_r(uint8_t **tb_ptr) +{ + tcg_target_ulong value = tci_read_reg(**tb_ptr); + *tb_ptr += 1; + return value; +} + +/* Read indexed register (8 bit) from bytecode. */ +static uint8_t tci_read_r8(uint8_t **tb_ptr) +{ + uint8_t value = tci_read_reg8(**tb_ptr); + *tb_ptr += 1; + return value; +} + +#if TCG_TARGET_HAS_ext8s_i32 || TCG_TARGET_HAS_ext8s_i64 +/* Read indexed register (8 bit signed) from bytecode. */ +static int8_t tci_read_r8s(uint8_t **tb_ptr) +{ + int8_t value = tci_read_reg8s(**tb_ptr); + *tb_ptr += 1; + return value; +} +#endif + +/* Read indexed register (16 bit) from bytecode. */ +static uint16_t tci_read_r16(uint8_t **tb_ptr) +{ + uint16_t value = tci_read_reg16(**tb_ptr); + *tb_ptr += 1; + return value; +} + +#if TCG_TARGET_HAS_ext16s_i32 || TCG_TARGET_HAS_ext16s_i64 +/* Read indexed register (16 bit signed) from bytecode. */ +static int16_t tci_read_r16s(uint8_t **tb_ptr) +{ + int16_t value = tci_read_reg16s(**tb_ptr); + *tb_ptr += 1; + return value; +} +#endif + +/* Read indexed register (32 bit) from bytecode. */ +static uint32_t tci_read_r32(uint8_t **tb_ptr) +{ + uint32_t value = tci_read_reg32(**tb_ptr); + *tb_ptr += 1; + return value; +} + +#if TCG_TARGET_REG_BITS == 32 +/* Read two indexed registers (2 * 32 bit) from bytecode. */ +static uint64_t tci_read_r64(uint8_t **tb_ptr) +{ + uint32_t low = tci_read_r32(tb_ptr); + return tci_uint64(tci_read_r32(tb_ptr), low); +} +#elif TCG_TARGET_REG_BITS == 64 +/* Read indexed register (32 bit signed) from bytecode. */ +static int32_t tci_read_r32s(uint8_t **tb_ptr) +{ + int32_t value = tci_read_reg32s(**tb_ptr); + *tb_ptr += 1; + return value; +} + +/* Read indexed register (64 bit) from bytecode. */ +static uint64_t tci_read_r64(uint8_t **tb_ptr) +{ + uint64_t value = tci_read_reg64(**tb_ptr); + *tb_ptr += 1; + return value; +} +#endif + +/* Read indexed register(s) with target address from bytecode. */ +static target_ulong tci_read_ulong(uint8_t **tb_ptr) +{ + target_ulong taddr = tci_read_r(tb_ptr); +#if TARGET_LONG_BITS > TCG_TARGET_REG_BITS + taddr += (uint64_t)tci_read_r(tb_ptr) << 32; +#endif + return taddr; +} + +/* Read indexed register or constant (native size) from bytecode. */ +static tcg_target_ulong tci_read_ri(uint8_t **tb_ptr) +{ + tcg_target_ulong value; + TCGReg r = **tb_ptr; + *tb_ptr += 1; + if (r == TCG_CONST) { + value = tci_read_i(tb_ptr); + } else { + value = tci_read_reg(r); + } + return value; +} + +/* Read indexed register or constant (32 bit) from bytecode. */ +static uint32_t tci_read_ri32(uint8_t **tb_ptr) +{ + uint32_t value; + TCGReg r = **tb_ptr; + *tb_ptr += 1; + if (r == TCG_CONST) { + value = tci_read_i32(tb_ptr); + } else { + value = tci_read_reg32(r); + } + return value; +} + +#if TCG_TARGET_REG_BITS == 32 +/* Read two indexed registers or constants (2 * 32 bit) from bytecode. */ +static uint64_t tci_read_ri64(uint8_t **tb_ptr) +{ + uint32_t low = tci_read_ri32(tb_ptr); + return tci_uint64(tci_read_ri32(tb_ptr), low); +} +#elif TCG_TARGET_REG_BITS == 64 +/* Read indexed register or constant (64 bit) from bytecode. */ +static uint64_t tci_read_ri64(uint8_t **tb_ptr) +{ + uint64_t value; + TCGReg r = **tb_ptr; + *tb_ptr += 1; + if (r == TCG_CONST) { + value = tci_read_i64(tb_ptr); + } else { + value = tci_read_reg64(r); + } + return value; +} +#endif + +static tcg_target_ulong tci_read_label(uint8_t **tb_ptr) +{ + tcg_target_ulong label = tci_read_i(tb_ptr); + tci_assert(label != 0); + return label; +} + +static bool tci_compare32(uint32_t u0, uint32_t u1, TCGCond condition) +{ + bool result = false; + int32_t i0 = u0; + int32_t i1 = u1; + switch (condition) { + case TCG_COND_EQ: + result = (u0 == u1); + break; + case TCG_COND_NE: + result = (u0 != u1); + break; + case TCG_COND_LT: + result = (i0 < i1); + break; + case TCG_COND_GE: + result = (i0 >= i1); + break; + case TCG_COND_LE: + result = (i0 <= i1); + break; + case TCG_COND_GT: + result = (i0 > i1); + break; + case TCG_COND_LTU: + result = (u0 < u1); + break; + case TCG_COND_GEU: + result = (u0 >= u1); + break; + case TCG_COND_LEU: + result = (u0 <= u1); + break; + case TCG_COND_GTU: + result = (u0 > u1); + break; + default: + TODO(); + } + return result; +} + +static bool tci_compare64(uint64_t u0, uint64_t u1, TCGCond condition) +{ + bool result = false; + int64_t i0 = u0; + int64_t i1 = u1; + switch (condition) { + case TCG_COND_EQ: + result = (u0 == u1); + break; + case TCG_COND_NE: + result = (u0 != u1); + break; + case TCG_COND_LT: + result = (i0 < i1); + break; + case TCG_COND_GE: + result = (i0 >= i1); + break; + case TCG_COND_LE: + result = (i0 <= i1); + break; + case TCG_COND_GT: + result = (i0 > i1); + break; + case TCG_COND_LTU: + result = (u0 < u1); + break; + case TCG_COND_GEU: + result = (u0 >= u1); + break; + case TCG_COND_LEU: + result = (u0 <= u1); + break; + case TCG_COND_GTU: + result = (u0 > u1); + break; + default: + TODO(); + } + return result; +} + +#ifdef CONFIG_SOFTMMU +# define qemu_ld_ub \ + helper_ret_ldub_mmu(env, taddr, oi, (uintptr_t)tb_ptr) +# define qemu_ld_leuw \ + helper_le_lduw_mmu(env, taddr, oi, (uintptr_t)tb_ptr) +# define qemu_ld_leul \ + helper_le_ldul_mmu(env, taddr, oi, (uintptr_t)tb_ptr) +# define qemu_ld_leq \ + helper_le_ldq_mmu(env, taddr, oi, (uintptr_t)tb_ptr) +# define qemu_ld_beuw \ + helper_be_lduw_mmu(env, taddr, oi, (uintptr_t)tb_ptr) +# define qemu_ld_beul \ + helper_be_ldul_mmu(env, taddr, oi, (uintptr_t)tb_ptr) +# define qemu_ld_beq \ + helper_be_ldq_mmu(env, taddr, oi, (uintptr_t)tb_ptr) +# define qemu_st_b(X) \ + helper_ret_stb_mmu(env, taddr, X, oi, (uintptr_t)tb_ptr) +# define qemu_st_lew(X) \ + helper_le_stw_mmu(env, taddr, X, oi, (uintptr_t)tb_ptr) +# define qemu_st_lel(X) \ + helper_le_stl_mmu(env, taddr, X, oi, (uintptr_t)tb_ptr) +# define qemu_st_leq(X) \ + helper_le_stq_mmu(env, taddr, X, oi, (uintptr_t)tb_ptr) +# define qemu_st_bew(X) \ + helper_be_stw_mmu(env, taddr, X, oi, (uintptr_t)tb_ptr) +# define qemu_st_bel(X) \ + helper_be_stl_mmu(env, taddr, X, oi, (uintptr_t)tb_ptr) +# define qemu_st_beq(X) \ + helper_be_stq_mmu(env, taddr, X, oi, (uintptr_t)tb_ptr) +#else +# define qemu_ld_ub ldub_p(g2h(taddr)) +# define qemu_ld_leuw lduw_le_p(g2h(taddr)) +# define qemu_ld_leul (uint32_t)ldl_le_p(g2h(taddr)) +# define qemu_ld_leq ldq_le_p(g2h(taddr)) +# define qemu_ld_beuw lduw_be_p(g2h(taddr)) +# define qemu_ld_beul (uint32_t)ldl_be_p(g2h(taddr)) +# define qemu_ld_beq ldq_be_p(g2h(taddr)) +# define qemu_st_b(X) stb_p(g2h(taddr), X) +# define qemu_st_lew(X) stw_le_p(g2h(taddr), X) +# define qemu_st_lel(X) stl_le_p(g2h(taddr), X) +# define qemu_st_leq(X) stq_le_p(g2h(taddr), X) +# define qemu_st_bew(X) stw_be_p(g2h(taddr), X) +# define qemu_st_bel(X) stl_be_p(g2h(taddr), X) +# define qemu_st_beq(X) stq_be_p(g2h(taddr), X) +#endif + +/* Interpret pseudo code in tb. */ +uintptr_t tcg_qemu_tb_exec(CPUArchState *env, uint8_t *tb_ptr) +{ + long tcg_temps[CPU_TEMP_BUF_NLONGS]; + uintptr_t sp_value = (uintptr_t)(tcg_temps + CPU_TEMP_BUF_NLONGS); + uintptr_t ret = 0; + + tci_reg[TCG_AREG0] = (tcg_target_ulong)env; + tci_reg[TCG_REG_CALL_STACK] = sp_value; + tci_assert(tb_ptr); + + for (;;) { + TCGOpcode opc = tb_ptr[0]; +#if defined(CONFIG_DEBUG_TCG) && !defined(NDEBUG) + uint8_t op_size = tb_ptr[1]; + uint8_t *old_code_ptr = tb_ptr; +#endif + tcg_target_ulong t0; + tcg_target_ulong t1; + tcg_target_ulong t2; + tcg_target_ulong label; + TCGCond condition; + target_ulong taddr; + uint8_t tmp8; + uint16_t tmp16; + uint32_t tmp32; + uint64_t tmp64; +#if TCG_TARGET_REG_BITS == 32 + uint64_t v64; +#endif + TCGMemOpIdx oi; + +#if defined(GETPC) + tci_tb_ptr = (uintptr_t)tb_ptr; +#endif + + /* Skip opcode and size entry. */ + tb_ptr += 2; + + switch (opc) { + case INDEX_op_call: + t0 = tci_read_ri(&tb_ptr); +#if TCG_TARGET_REG_BITS == 32 + tmp64 = ((helper_function)t0)(tci_read_reg(TCG_REG_R0), + tci_read_reg(TCG_REG_R1), + tci_read_reg(TCG_REG_R2), + tci_read_reg(TCG_REG_R3), + tci_read_reg(TCG_REG_R5), + tci_read_reg(TCG_REG_R6), + tci_read_reg(TCG_REG_R7), + tci_read_reg(TCG_REG_R8), + tci_read_reg(TCG_REG_R9), + tci_read_reg(TCG_REG_R10)); + tci_write_reg(TCG_REG_R0, tmp64); + tci_write_reg(TCG_REG_R1, tmp64 >> 32); +#else + tmp64 = ((helper_function)t0)(tci_read_reg(TCG_REG_R0), + tci_read_reg(TCG_REG_R1), + tci_read_reg(TCG_REG_R2), + tci_read_reg(TCG_REG_R3), + tci_read_reg(TCG_REG_R5)); + tci_write_reg(TCG_REG_R0, tmp64); +#endif + break; + case INDEX_op_br: + label = tci_read_label(&tb_ptr); + tci_assert(tb_ptr == old_code_ptr + op_size); + tb_ptr = (uint8_t *)label; + continue; + case INDEX_op_setcond_i32: + t0 = *tb_ptr++; + t1 = tci_read_r32(&tb_ptr); + t2 = tci_read_ri32(&tb_ptr); + condition = *tb_ptr++; + tci_write_reg32(t0, tci_compare32(t1, t2, condition)); + break; +#if TCG_TARGET_REG_BITS == 32 + case INDEX_op_setcond2_i32: + t0 = *tb_ptr++; + tmp64 = tci_read_r64(&tb_ptr); + v64 = tci_read_ri64(&tb_ptr); + condition = *tb_ptr++; + tci_write_reg32(t0, tci_compare64(tmp64, v64, condition)); + break; +#elif TCG_TARGET_REG_BITS == 64 + case INDEX_op_setcond_i64: + t0 = *tb_ptr++; + t1 = tci_read_r64(&tb_ptr); + t2 = tci_read_ri64(&tb_ptr); + condition = *tb_ptr++; + tci_write_reg64(t0, tci_compare64(t1, t2, condition)); + break; +#endif + case INDEX_op_mov_i32: + t0 = *tb_ptr++; + t1 = tci_read_r32(&tb_ptr); + tci_write_reg32(t0, t1); + break; + case INDEX_op_movi_i32: + t0 = *tb_ptr++; + t1 = tci_read_i32(&tb_ptr); + tci_write_reg32(t0, t1); + break; + + /* Load/store operations (32 bit). */ + + case INDEX_op_ld8u_i32: + t0 = *tb_ptr++; + t1 = tci_read_r(&tb_ptr); + t2 = tci_read_s32(&tb_ptr); + tci_write_reg8(t0, *(uint8_t *)(t1 + t2)); + break; + case INDEX_op_ld8s_i32: + case INDEX_op_ld16u_i32: + TODO(); + break; + case INDEX_op_ld16s_i32: + TODO(); + break; + case INDEX_op_ld_i32: + t0 = *tb_ptr++; + t1 = tci_read_r(&tb_ptr); + t2 = tci_read_s32(&tb_ptr); + tci_write_reg32(t0, *(uint32_t *)(t1 + t2)); + break; + case INDEX_op_st8_i32: + t0 = tci_read_r8(&tb_ptr); + t1 = tci_read_r(&tb_ptr); + t2 = tci_read_s32(&tb_ptr); + *(uint8_t *)(t1 + t2) = t0; + break; + case INDEX_op_st16_i32: + t0 = tci_read_r16(&tb_ptr); + t1 = tci_read_r(&tb_ptr); + t2 = tci_read_s32(&tb_ptr); + *(uint16_t *)(t1 + t2) = t0; + break; + case INDEX_op_st_i32: + t0 = tci_read_r32(&tb_ptr); + t1 = tci_read_r(&tb_ptr); + t2 = tci_read_s32(&tb_ptr); + tci_assert(t1 != sp_value || (int32_t)t2 < 0); + *(uint32_t *)(t1 + t2) = t0; + break; + + /* Arithmetic operations (32 bit). */ + + case INDEX_op_add_i32: + t0 = *tb_ptr++; + t1 = tci_read_ri32(&tb_ptr); + t2 = tci_read_ri32(&tb_ptr); + tci_write_reg32(t0, t1 + t2); + break; + case INDEX_op_sub_i32: + t0 = *tb_ptr++; + t1 = tci_read_ri32(&tb_ptr); + t2 = tci_read_ri32(&tb_ptr); + tci_write_reg32(t0, t1 - t2); + break; + case INDEX_op_mul_i32: + t0 = *tb_ptr++; + t1 = tci_read_ri32(&tb_ptr); + t2 = tci_read_ri32(&tb_ptr); + tci_write_reg32(t0, t1 * t2); + break; +#if TCG_TARGET_HAS_div_i32 + case INDEX_op_div_i32: + t0 = *tb_ptr++; + t1 = tci_read_ri32(&tb_ptr); + t2 = tci_read_ri32(&tb_ptr); + tci_write_reg32(t0, (int32_t)t1 / (int32_t)t2); + break; + case INDEX_op_divu_i32: + t0 = *tb_ptr++; + t1 = tci_read_ri32(&tb_ptr); + t2 = tci_read_ri32(&tb_ptr); + tci_write_reg32(t0, t1 / t2); + break; + case INDEX_op_rem_i32: + t0 = *tb_ptr++; + t1 = tci_read_ri32(&tb_ptr); + t2 = tci_read_ri32(&tb_ptr); + tci_write_reg32(t0, (int32_t)t1 % (int32_t)t2); + break; + case INDEX_op_remu_i32: + t0 = *tb_ptr++; + t1 = tci_read_ri32(&tb_ptr); + t2 = tci_read_ri32(&tb_ptr); + tci_write_reg32(t0, t1 % t2); + break; +#elif TCG_TARGET_HAS_div2_i32 + case INDEX_op_div2_i32: + case INDEX_op_divu2_i32: + TODO(); + break; +#endif + case INDEX_op_and_i32: + t0 = *tb_ptr++; + t1 = tci_read_ri32(&tb_ptr); + t2 = tci_read_ri32(&tb_ptr); + tci_write_reg32(t0, t1 & t2); + break; + case INDEX_op_or_i32: + t0 = *tb_ptr++; + t1 = tci_read_ri32(&tb_ptr); + t2 = tci_read_ri32(&tb_ptr); + tci_write_reg32(t0, t1 | t2); + break; + case INDEX_op_xor_i32: + t0 = *tb_ptr++; + t1 = tci_read_ri32(&tb_ptr); + t2 = tci_read_ri32(&tb_ptr); + tci_write_reg32(t0, t1 ^ t2); + break; + + /* Shift/rotate operations (32 bit). */ + + case INDEX_op_shl_i32: + t0 = *tb_ptr++; + t1 = tci_read_ri32(&tb_ptr); + t2 = tci_read_ri32(&tb_ptr); + tci_write_reg32(t0, t1 << (t2 & 31)); + break; + case INDEX_op_shr_i32: + t0 = *tb_ptr++; + t1 = tci_read_ri32(&tb_ptr); + t2 = tci_read_ri32(&tb_ptr); + tci_write_reg32(t0, t1 >> (t2 & 31)); + break; + case INDEX_op_sar_i32: + t0 = *tb_ptr++; + t1 = tci_read_ri32(&tb_ptr); + t2 = tci_read_ri32(&tb_ptr); + tci_write_reg32(t0, ((int32_t)t1 >> (t2 & 31))); + break; +#if TCG_TARGET_HAS_rot_i32 + case INDEX_op_rotl_i32: + t0 = *tb_ptr++; + t1 = tci_read_ri32(&tb_ptr); + t2 = tci_read_ri32(&tb_ptr); + tci_write_reg32(t0, rol32(t1, t2 & 31)); + break; + case INDEX_op_rotr_i32: + t0 = *tb_ptr++; + t1 = tci_read_ri32(&tb_ptr); + t2 = tci_read_ri32(&tb_ptr); + tci_write_reg32(t0, ror32(t1, t2 & 31)); + break; +#endif +#if TCG_TARGET_HAS_deposit_i32 + case INDEX_op_deposit_i32: + t0 = *tb_ptr++; + t1 = tci_read_r32(&tb_ptr); + t2 = tci_read_r32(&tb_ptr); + tmp16 = *tb_ptr++; + tmp8 = *tb_ptr++; + tmp32 = (((1 << tmp8) - 1) << tmp16); + tci_write_reg32(t0, (t1 & ~tmp32) | ((t2 << tmp16) & tmp32)); + break; +#endif + case INDEX_op_brcond_i32: + t0 = tci_read_r32(&tb_ptr); + t1 = tci_read_ri32(&tb_ptr); + condition = *tb_ptr++; + label = tci_read_label(&tb_ptr); + if (tci_compare32(t0, t1, condition)) { + tci_assert(tb_ptr == old_code_ptr + op_size); + tb_ptr = (uint8_t *)label; + continue; + } + break; +#if TCG_TARGET_REG_BITS == 32 + case INDEX_op_add2_i32: + t0 = *tb_ptr++; + t1 = *tb_ptr++; + tmp64 = tci_read_r64(&tb_ptr); + tmp64 += tci_read_r64(&tb_ptr); + tci_write_reg64(t1, t0, tmp64); + break; + case INDEX_op_sub2_i32: + t0 = *tb_ptr++; + t1 = *tb_ptr++; + tmp64 = tci_read_r64(&tb_ptr); + tmp64 -= tci_read_r64(&tb_ptr); + tci_write_reg64(t1, t0, tmp64); + break; + case INDEX_op_brcond2_i32: + tmp64 = tci_read_r64(&tb_ptr); + v64 = tci_read_ri64(&tb_ptr); + condition = *tb_ptr++; + label = tci_read_label(&tb_ptr); + if (tci_compare64(tmp64, v64, condition)) { + tci_assert(tb_ptr == old_code_ptr + op_size); + tb_ptr = (uint8_t *)label; + continue; + } + break; + case INDEX_op_mulu2_i32: + t0 = *tb_ptr++; + t1 = *tb_ptr++; + t2 = tci_read_r32(&tb_ptr); + tmp64 = tci_read_r32(&tb_ptr); + tci_write_reg64(t1, t0, t2 * tmp64); + break; +#endif /* TCG_TARGET_REG_BITS == 32 */ +#if TCG_TARGET_HAS_ext8s_i32 + case INDEX_op_ext8s_i32: + t0 = *tb_ptr++; + t1 = tci_read_r8s(&tb_ptr); + tci_write_reg32(t0, t1); + break; +#endif +#if TCG_TARGET_HAS_ext16s_i32 + case INDEX_op_ext16s_i32: + t0 = *tb_ptr++; + t1 = tci_read_r16s(&tb_ptr); + tci_write_reg32(t0, t1); + break; +#endif +#if TCG_TARGET_HAS_ext8u_i32 + case INDEX_op_ext8u_i32: + t0 = *tb_ptr++; + t1 = tci_read_r8(&tb_ptr); + tci_write_reg32(t0, t1); + break; +#endif +#if TCG_TARGET_HAS_ext16u_i32 + case INDEX_op_ext16u_i32: + t0 = *tb_ptr++; + t1 = tci_read_r16(&tb_ptr); + tci_write_reg32(t0, t1); + break; +#endif +#if TCG_TARGET_HAS_bswap16_i32 + case INDEX_op_bswap16_i32: + t0 = *tb_ptr++; + t1 = tci_read_r16(&tb_ptr); + tci_write_reg32(t0, bswap16(t1)); + break; +#endif +#if TCG_TARGET_HAS_bswap32_i32 + case INDEX_op_bswap32_i32: + t0 = *tb_ptr++; + t1 = tci_read_r32(&tb_ptr); + tci_write_reg32(t0, bswap32(t1)); + break; +#endif +#if TCG_TARGET_HAS_not_i32 + case INDEX_op_not_i32: + t0 = *tb_ptr++; + t1 = tci_read_r32(&tb_ptr); + tci_write_reg32(t0, ~t1); + break; +#endif +#if TCG_TARGET_HAS_neg_i32 + case INDEX_op_neg_i32: + t0 = *tb_ptr++; + t1 = tci_read_r32(&tb_ptr); + tci_write_reg32(t0, -t1); + break; +#endif +#if TCG_TARGET_REG_BITS == 64 + case INDEX_op_mov_i64: + t0 = *tb_ptr++; + t1 = tci_read_r64(&tb_ptr); + tci_write_reg64(t0, t1); + break; + case INDEX_op_movi_i64: + t0 = *tb_ptr++; + t1 = tci_read_i64(&tb_ptr); + tci_write_reg64(t0, t1); + break; + + /* Load/store operations (64 bit). */ + + case INDEX_op_ld8u_i64: + t0 = *tb_ptr++; + t1 = tci_read_r(&tb_ptr); + t2 = tci_read_s32(&tb_ptr); + tci_write_reg8(t0, *(uint8_t *)(t1 + t2)); + break; + case INDEX_op_ld8s_i64: + case INDEX_op_ld16u_i64: + case INDEX_op_ld16s_i64: + TODO(); + break; + case INDEX_op_ld32u_i64: + t0 = *tb_ptr++; + t1 = tci_read_r(&tb_ptr); + t2 = tci_read_s32(&tb_ptr); + tci_write_reg32(t0, *(uint32_t *)(t1 + t2)); + break; + case INDEX_op_ld32s_i64: + t0 = *tb_ptr++; + t1 = tci_read_r(&tb_ptr); + t2 = tci_read_s32(&tb_ptr); + tci_write_reg32s(t0, *(int32_t *)(t1 + t2)); + break; + case INDEX_op_ld_i64: + t0 = *tb_ptr++; + t1 = tci_read_r(&tb_ptr); + t2 = tci_read_s32(&tb_ptr); + tci_write_reg64(t0, *(uint64_t *)(t1 + t2)); + break; + case INDEX_op_st8_i64: + t0 = tci_read_r8(&tb_ptr); + t1 = tci_read_r(&tb_ptr); + t2 = tci_read_s32(&tb_ptr); + *(uint8_t *)(t1 + t2) = t0; + break; + case INDEX_op_st16_i64: + t0 = tci_read_r16(&tb_ptr); + t1 = tci_read_r(&tb_ptr); + t2 = tci_read_s32(&tb_ptr); + *(uint16_t *)(t1 + t2) = t0; + break; + case INDEX_op_st32_i64: + t0 = tci_read_r32(&tb_ptr); + t1 = tci_read_r(&tb_ptr); + t2 = tci_read_s32(&tb_ptr); + *(uint32_t *)(t1 + t2) = t0; + break; + case INDEX_op_st_i64: + t0 = tci_read_r64(&tb_ptr); + t1 = tci_read_r(&tb_ptr); + t2 = tci_read_s32(&tb_ptr); + tci_assert(t1 != sp_value || (int32_t)t2 < 0); + *(uint64_t *)(t1 + t2) = t0; + break; + + /* Arithmetic operations (64 bit). */ + + case INDEX_op_add_i64: + t0 = *tb_ptr++; + t1 = tci_read_ri64(&tb_ptr); + t2 = tci_read_ri64(&tb_ptr); + tci_write_reg64(t0, t1 + t2); + break; + case INDEX_op_sub_i64: + t0 = *tb_ptr++; + t1 = tci_read_ri64(&tb_ptr); + t2 = tci_read_ri64(&tb_ptr); + tci_write_reg64(t0, t1 - t2); + break; + case INDEX_op_mul_i64: + t0 = *tb_ptr++; + t1 = tci_read_ri64(&tb_ptr); + t2 = tci_read_ri64(&tb_ptr); + tci_write_reg64(t0, t1 * t2); + break; +#if TCG_TARGET_HAS_div_i64 + case INDEX_op_div_i64: + case INDEX_op_divu_i64: + case INDEX_op_rem_i64: + case INDEX_op_remu_i64: + TODO(); + break; +#elif TCG_TARGET_HAS_div2_i64 + case INDEX_op_div2_i64: + case INDEX_op_divu2_i64: + TODO(); + break; +#endif + case INDEX_op_and_i64: + t0 = *tb_ptr++; + t1 = tci_read_ri64(&tb_ptr); + t2 = tci_read_ri64(&tb_ptr); + tci_write_reg64(t0, t1 & t2); + break; + case INDEX_op_or_i64: + t0 = *tb_ptr++; + t1 = tci_read_ri64(&tb_ptr); + t2 = tci_read_ri64(&tb_ptr); + tci_write_reg64(t0, t1 | t2); + break; + case INDEX_op_xor_i64: + t0 = *tb_ptr++; + t1 = tci_read_ri64(&tb_ptr); + t2 = tci_read_ri64(&tb_ptr); + tci_write_reg64(t0, t1 ^ t2); + break; + + /* Shift/rotate operations (64 bit). */ + + case INDEX_op_shl_i64: + t0 = *tb_ptr++; + t1 = tci_read_ri64(&tb_ptr); + t2 = tci_read_ri64(&tb_ptr); + tci_write_reg64(t0, t1 << (t2 & 63)); + break; + case INDEX_op_shr_i64: + t0 = *tb_ptr++; + t1 = tci_read_ri64(&tb_ptr); + t2 = tci_read_ri64(&tb_ptr); + tci_write_reg64(t0, t1 >> (t2 & 63)); + break; + case INDEX_op_sar_i64: + t0 = *tb_ptr++; + t1 = tci_read_ri64(&tb_ptr); + t2 = tci_read_ri64(&tb_ptr); + tci_write_reg64(t0, ((int64_t)t1 >> (t2 & 63))); + break; +#if TCG_TARGET_HAS_rot_i64 + case INDEX_op_rotl_i64: + t0 = *tb_ptr++; + t1 = tci_read_ri64(&tb_ptr); + t2 = tci_read_ri64(&tb_ptr); + tci_write_reg64(t0, rol64(t1, t2 & 63)); + break; + case INDEX_op_rotr_i64: + t0 = *tb_ptr++; + t1 = tci_read_ri64(&tb_ptr); + t2 = tci_read_ri64(&tb_ptr); + tci_write_reg64(t0, ror64(t1, t2 & 63)); + break; +#endif +#if TCG_TARGET_HAS_deposit_i64 + case INDEX_op_deposit_i64: + t0 = *tb_ptr++; + t1 = tci_read_r64(&tb_ptr); + t2 = tci_read_r64(&tb_ptr); + tmp16 = *tb_ptr++; + tmp8 = *tb_ptr++; + tmp64 = (((1ULL << tmp8) - 1) << tmp16); + tci_write_reg64(t0, (t1 & ~tmp64) | ((t2 << tmp16) & tmp64)); + break; +#endif + case INDEX_op_brcond_i64: + t0 = tci_read_r64(&tb_ptr); + t1 = tci_read_ri64(&tb_ptr); + condition = *tb_ptr++; + label = tci_read_label(&tb_ptr); + if (tci_compare64(t0, t1, condition)) { + tci_assert(tb_ptr == old_code_ptr + op_size); + tb_ptr = (uint8_t *)label; + continue; + } + break; +#if TCG_TARGET_HAS_ext8u_i64 + case INDEX_op_ext8u_i64: + t0 = *tb_ptr++; + t1 = tci_read_r8(&tb_ptr); + tci_write_reg64(t0, t1); + break; +#endif +#if TCG_TARGET_HAS_ext8s_i64 + case INDEX_op_ext8s_i64: + t0 = *tb_ptr++; + t1 = tci_read_r8s(&tb_ptr); + tci_write_reg64(t0, t1); + break; +#endif +#if TCG_TARGET_HAS_ext16s_i64 + case INDEX_op_ext16s_i64: + t0 = *tb_ptr++; + t1 = tci_read_r16s(&tb_ptr); + tci_write_reg64(t0, t1); + break; +#endif +#if TCG_TARGET_HAS_ext16u_i64 + case INDEX_op_ext16u_i64: + t0 = *tb_ptr++; + t1 = tci_read_r16(&tb_ptr); + tci_write_reg64(t0, t1); + break; +#endif +#if TCG_TARGET_HAS_ext32s_i64 + case INDEX_op_ext32s_i64: +#endif + case INDEX_op_ext_i32_i64: + t0 = *tb_ptr++; + t1 = tci_read_r32s(&tb_ptr); + tci_write_reg64(t0, t1); + break; +#if TCG_TARGET_HAS_ext32u_i64 + case INDEX_op_ext32u_i64: +#endif + case INDEX_op_extu_i32_i64: + t0 = *tb_ptr++; + t1 = tci_read_r32(&tb_ptr); + tci_write_reg64(t0, t1); + break; +#if TCG_TARGET_HAS_bswap16_i64 + case INDEX_op_bswap16_i64: + TODO(); + t0 = *tb_ptr++; + t1 = tci_read_r16(&tb_ptr); + tci_write_reg64(t0, bswap16(t1)); + break; +#endif +#if TCG_TARGET_HAS_bswap32_i64 + case INDEX_op_bswap32_i64: + t0 = *tb_ptr++; + t1 = tci_read_r32(&tb_ptr); + tci_write_reg64(t0, bswap32(t1)); + break; +#endif +#if TCG_TARGET_HAS_bswap64_i64 + case INDEX_op_bswap64_i64: + t0 = *tb_ptr++; + t1 = tci_read_r64(&tb_ptr); + tci_write_reg64(t0, bswap64(t1)); + break; +#endif +#if TCG_TARGET_HAS_not_i64 + case INDEX_op_not_i64: + t0 = *tb_ptr++; + t1 = tci_read_r64(&tb_ptr); + tci_write_reg64(t0, ~t1); + break; +#endif +#if TCG_TARGET_HAS_neg_i64 + case INDEX_op_neg_i64: + t0 = *tb_ptr++; + t1 = tci_read_r64(&tb_ptr); + tci_write_reg64(t0, -t1); + break; +#endif +#endif /* TCG_TARGET_REG_BITS == 64 */ + + /* QEMU specific operations. */ + + case INDEX_op_exit_tb: + ret = *(uint64_t *)tb_ptr; + goto exit; + break; + case INDEX_op_goto_tb: + /* Jump address is aligned */ + tb_ptr = QEMU_ALIGN_PTR_UP(tb_ptr, 4); + t0 = atomic_read((int32_t *)tb_ptr); + tb_ptr += sizeof(int32_t); + tci_assert(tb_ptr == old_code_ptr + op_size); + tb_ptr += (int32_t)t0; + continue; + case INDEX_op_qemu_ld_i32: + t0 = *tb_ptr++; + taddr = tci_read_ulong(&tb_ptr); + oi = tci_read_i(&tb_ptr); + switch (get_memop(oi) & (MO_BSWAP | MO_SSIZE)) { + case MO_UB: + tmp32 = qemu_ld_ub; + break; + case MO_SB: + tmp32 = (int8_t)qemu_ld_ub; + break; + case MO_LEUW: + tmp32 = qemu_ld_leuw; + break; + case MO_LESW: + tmp32 = (int16_t)qemu_ld_leuw; + break; + case MO_LEUL: + tmp32 = qemu_ld_leul; + break; + case MO_BEUW: + tmp32 = qemu_ld_beuw; + break; + case MO_BESW: + tmp32 = (int16_t)qemu_ld_beuw; + break; + case MO_BEUL: + tmp32 = qemu_ld_beul; + break; + default: + tcg_abort(); + } + tci_write_reg(t0, tmp32); + break; + case INDEX_op_qemu_ld_i64: + t0 = *tb_ptr++; + if (TCG_TARGET_REG_BITS == 32) { + t1 = *tb_ptr++; + } + taddr = tci_read_ulong(&tb_ptr); + oi = tci_read_i(&tb_ptr); + switch (get_memop(oi) & (MO_BSWAP | MO_SSIZE)) { + case MO_UB: + tmp64 = qemu_ld_ub; + break; + case MO_SB: + tmp64 = (int8_t)qemu_ld_ub; + break; + case MO_LEUW: + tmp64 = qemu_ld_leuw; + break; + case MO_LESW: + tmp64 = (int16_t)qemu_ld_leuw; + break; + case MO_LEUL: + tmp64 = qemu_ld_leul; + break; + case MO_LESL: + tmp64 = (int32_t)qemu_ld_leul; + break; + case MO_LEQ: + tmp64 = qemu_ld_leq; + break; + case MO_BEUW: + tmp64 = qemu_ld_beuw; + break; + case MO_BESW: + tmp64 = (int16_t)qemu_ld_beuw; + break; + case MO_BEUL: + tmp64 = qemu_ld_beul; + break; + case MO_BESL: + tmp64 = (int32_t)qemu_ld_beul; + break; + case MO_BEQ: + tmp64 = qemu_ld_beq; + break; + default: + tcg_abort(); + } + tci_write_reg(t0, tmp64); + if (TCG_TARGET_REG_BITS == 32) { + tci_write_reg(t1, tmp64 >> 32); + } + break; + case INDEX_op_qemu_st_i32: + t0 = tci_read_r(&tb_ptr); + taddr = tci_read_ulong(&tb_ptr); + oi = tci_read_i(&tb_ptr); + switch (get_memop(oi) & (MO_BSWAP | MO_SIZE)) { + case MO_UB: + qemu_st_b(t0); + break; + case MO_LEUW: + qemu_st_lew(t0); + break; + case MO_LEUL: + qemu_st_lel(t0); + break; + case MO_BEUW: + qemu_st_bew(t0); + break; + case MO_BEUL: + qemu_st_bel(t0); + break; + default: + tcg_abort(); + } + break; + case INDEX_op_qemu_st_i64: + tmp64 = tci_read_r64(&tb_ptr); + taddr = tci_read_ulong(&tb_ptr); + oi = tci_read_i(&tb_ptr); + switch (get_memop(oi) & (MO_BSWAP | MO_SIZE)) { + case MO_UB: + qemu_st_b(tmp64); + break; + case MO_LEUW: + qemu_st_lew(tmp64); + break; + case MO_LEUL: + qemu_st_lel(tmp64); + break; + case MO_LEQ: + qemu_st_leq(tmp64); + break; + case MO_BEUW: + qemu_st_bew(tmp64); + break; + case MO_BEUL: + qemu_st_bel(tmp64); + break; + case MO_BEQ: + qemu_st_beq(tmp64); + break; + default: + tcg_abort(); + } + break; + case INDEX_op_mb: + /* Ensure ordering for all kinds */ + smp_mb(); + break; + default: + TODO(); + break; + } + tci_assert(tb_ptr == old_code_ptr + op_size); + } +exit: + return ret; +} |