/*
 *  emulator main execution loop
 *
 *  Copyright (c) 2003-2005 Fabrice Bellard
 *
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2 of the License, or (at your option) any later version.
 *
 * This library 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
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this library; if not, see <http://www.gnu.org/licenses/>.
 */
#include "qemu/osdep.h"
#include "cpu.h"
#include "trace.h"
#include "disas/disas.h"
#include "exec/exec-all.h"
#include "tcg.h"
#include "qemu/atomic.h"
#include "sysemu/qtest.h"
#include "qemu/timer.h"
#include "exec/address-spaces.h"
#include "qemu/rcu.h"
#include "exec/tb-hash.h"
#include "exec/tb-lookup.h"
#include "exec/log.h"
#include "qemu/main-loop.h"
#if defined(TARGET_I386) && !defined(CONFIG_USER_ONLY)
#include "hw/i386/apic.h"
#endif
#include "sysemu/cpus.h"
#include "sysemu/replay.h"
#include "qemu/etrace.h"

/* -icount align implementation. */

typedef struct SyncClocks {
    int64_t diff_clk;
    int64_t last_cpu_icount;
    int64_t realtime_clock;
} SyncClocks;

#if !defined(CONFIG_USER_ONLY)
/* Allow the guest to have a max 3ms advance.
 * The difference between the 2 clocks could therefore
 * oscillate around 0.
 */
#define VM_CLOCK_ADVANCE 3000000
#define THRESHOLD_REDUCE 1.5
#define MAX_DELAY_PRINT_RATE 2000000000LL
#define MAX_NB_PRINTS 100

static void align_clocks(SyncClocks *sc, const CPUState *cpu)
{
    int64_t cpu_icount;

    if (!icount_align_option) {
        return;
    }

    cpu_icount = cpu->icount_extra + cpu->icount_decr.u16.low;
    sc->diff_clk += cpu_icount_to_ns(sc->last_cpu_icount - cpu_icount);
    sc->last_cpu_icount = cpu_icount;

    if (sc->diff_clk > VM_CLOCK_ADVANCE) {
#ifndef _WIN32
        struct timespec sleep_delay, rem_delay;
        sleep_delay.tv_sec = sc->diff_clk / 1000000000LL;
        sleep_delay.tv_nsec = sc->diff_clk % 1000000000LL;
        if (nanosleep(&sleep_delay, &rem_delay) < 0) {
            sc->diff_clk = rem_delay.tv_sec * 1000000000LL + rem_delay.tv_nsec;
        } else {
            sc->diff_clk = 0;
        }
#else
        Sleep(sc->diff_clk / SCALE_MS);
        sc->diff_clk = 0;
#endif
    }
}

static void print_delay(const SyncClocks *sc)
{
    static float threshold_delay;
    static int64_t last_realtime_clock;
    static int nb_prints;

    if (icount_align_option &&
        sc->realtime_clock - last_realtime_clock >= MAX_DELAY_PRINT_RATE &&
        nb_prints < MAX_NB_PRINTS) {
        if ((-sc->diff_clk / (float)1000000000LL > threshold_delay) ||
            (-sc->diff_clk / (float)1000000000LL <
             (threshold_delay - THRESHOLD_REDUCE))) {
            threshold_delay = (-sc->diff_clk / 1000000000LL) + 1;
            printf("Warning: The guest is now late by %.1f to %.1f seconds\n",
                   threshold_delay - 1,
                   threshold_delay);
            nb_prints++;
            last_realtime_clock = sc->realtime_clock;
        }
    }
}

static void init_delay_params(SyncClocks *sc,
                              const CPUState *cpu)
{
    if (!icount_align_option) {
        return;
    }
    sc->realtime_clock = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL_RT);
    sc->diff_clk = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) - sc->realtime_clock;
    sc->last_cpu_icount = cpu->icount_extra + cpu->icount_decr.u16.low;
    if (sc->diff_clk < max_delay) {
        max_delay = sc->diff_clk;
    }
    if (sc->diff_clk > max_advance) {
        max_advance = sc->diff_clk;
    }

    /* Print every 2s max if the guest is late. We limit the number
       of printed messages to NB_PRINT_MAX(currently 100) */
    print_delay(sc);
}
#else
static void align_clocks(SyncClocks *sc, const CPUState *cpu)
{
}

static void init_delay_params(SyncClocks *sc, const CPUState *cpu)
{
}
#endif /* CONFIG USER ONLY */

/* Execute a TB, and fix up the CPU state afterwards if necessary */
static inline tcg_target_ulong cpu_tb_exec(CPUState *cpu, TranslationBlock *itb)
{
    CPUArchState *env = cpu->env_ptr;
    uintptr_t ret;
    TranslationBlock *last_tb;
    int tb_exit;
    uint8_t *tb_ptr = itb->tc.ptr;

    qemu_log_mask_and_addr(CPU_LOG_EXEC, itb->pc,
                           "Trace %p [%d: " TARGET_FMT_lx "] %s\n",
                           itb->tc.ptr, cpu->cpu_index, itb->pc,
                           lookup_symbol(itb->pc));

    if (qemu_etrace_mask(ETRACE_F_CPU)) {
        /* FIXME: Create a binary representation.
                  printf is too slow!!  */
        qemu_etracer.current_unit_id = cpu->cpu_index;
        cpu_dump_state(cpu, (void *) &qemu_etracer,
                       etrace_note_fprintf, 0);
    }
    if (qemu_etrace_mask(ETRACE_F_EXEC)) {
        etrace_dump_exec_start(&qemu_etracer, cpu->cpu_index,
                               itb->pc);
    }


#if defined(DEBUG_DISAS)
    if (qemu_loglevel_mask(CPU_LOG_TB_CPU)
        && qemu_log_in_addr_range(itb->pc)) {
        qemu_log_lock();
#if defined(TARGET_I386)
        log_cpu_state(cpu, CPU_DUMP_CCOP);
#else
        log_cpu_state(cpu, 0);
#endif
        qemu_log_unlock();
    }
#endif /* DEBUG_DISAS */

    cpu->can_do_io = !use_icount;
    ret = tcg_qemu_tb_exec(env, tb_ptr);
    cpu->can_do_io = 1;
    last_tb = (TranslationBlock *)(ret & ~TB_EXIT_MASK);
    tb_exit = ret & TB_EXIT_MASK;
    trace_exec_tb_exit(last_tb, tb_exit);

    if (tb_exit > TB_EXIT_IDX1) {
        /* We didn't start executing this TB (eg because the instruction
         * counter hit zero); we must restore the guest PC to the address
         * of the start of the TB.
         */
        CPUClass *cc = CPU_GET_CLASS(cpu);
        qemu_log_mask_and_addr(CPU_LOG_EXEC, last_tb->pc,
                               "Stopped execution of TB chain before %p ["
                               TARGET_FMT_lx "] %s\n",
                               last_tb->tc.ptr, last_tb->pc,
                               lookup_symbol(last_tb->pc));
        if (cc->synchronize_from_tb) {
            cc->synchronize_from_tb(cpu, last_tb);
        } else {
            assert(cc->set_pc);
            cc->set_pc(cpu, last_tb->pc);
        }
    }
    return ret;
}

#ifndef CONFIG_USER_ONLY
/* Execute the code without caching the generated code. An interpreter
   could be used if available. */
static void cpu_exec_nocache(CPUState *cpu, int max_cycles,
                             TranslationBlock *orig_tb, bool ignore_icount)
{
    TranslationBlock *tb;
    uint32_t cflags = curr_cflags() | CF_NOCACHE;

    if (ignore_icount) {
        cflags &= ~CF_USE_ICOUNT;
    }

    /* Should never happen.
       We only end up here when an existing TB is too long.  */
    cflags |= MIN(max_cycles, CF_COUNT_MASK);

    tb_lock();
    tb = tb_gen_code(cpu, orig_tb->pc, orig_tb->cs_base,
                     orig_tb->flags, cflags);
    tb->orig_tb = orig_tb;
    tb_unlock();

    /* execute the generated code */
    trace_exec_tb_nocache(tb, tb->pc);
    cpu_tb_exec(cpu, tb);

    tb_lock();
    tb_phys_invalidate(tb, -1);
    tb_remove(tb);
    tb_unlock();
}
#endif

void cpu_exec_step_atomic(CPUState *cpu)
{
    CPUClass *cc = CPU_GET_CLASS(cpu);
    TranslationBlock *tb;
    target_ulong cs_base, pc;
    uint32_t flags;
    uint32_t cflags = 1;
    uint32_t cf_mask = cflags & CF_HASH_MASK;
    /* volatile because we modify it between setjmp and longjmp */
    volatile bool in_exclusive_region = false;

    if (sigsetjmp(cpu->jmp_env, 0) == 0) {
        tb = tb_lookup__cpu_state(cpu, &pc, &cs_base, &flags, cf_mask);
        if (tb == NULL) {
            mmap_lock();
            tb_lock();
            tb = tb_htable_lookup(cpu, pc, cs_base, flags, cf_mask);
            if (likely(tb == NULL)) {
                tb = tb_gen_code(cpu, pc, cs_base, flags, cflags);
            }
            tb_unlock();
            mmap_unlock();
        }

        start_exclusive();

        /* Since we got here, we know that parallel_cpus must be true.  */
        parallel_cpus = false;
        in_exclusive_region = true;
        cc->cpu_exec_enter(cpu);
        /* execute the generated code */
        trace_exec_tb(tb, pc);
        cpu_tb_exec(cpu, tb);
        cc->cpu_exec_exit(cpu);
    } else {
        /* We may have exited due to another problem here, so we need
         * to reset any tb_locks we may have taken but didn't release.
         * The mmap_lock is dropped by tb_gen_code if it runs out of
         * memory.
         */
#ifndef CONFIG_SOFTMMU
        tcg_debug_assert(!have_mmap_lock());
#endif
        tb_lock_reset();
    }

    if (in_exclusive_region) {
        /* We might longjump out of either the codegen or the
         * execution, so must make sure we only end the exclusive
         * region if we started it.
         */
        parallel_cpus = true;
        end_exclusive();
    }
}

struct tb_desc {
    target_ulong pc;
    target_ulong cs_base;
    CPUArchState *env;
    tb_page_addr_t phys_page1;
    uint32_t flags;
    uint32_t cf_mask;
    uint32_t trace_vcpu_dstate;
};

static bool tb_cmp(const void *p, const void *d)
{
    const TranslationBlock *tb = p;
    const struct tb_desc *desc = d;

    if (tb->pc == desc->pc &&
        tb->page_addr[0] == desc->phys_page1 &&
        tb->cs_base == desc->cs_base &&
        tb->flags == desc->flags &&
        tb->trace_vcpu_dstate == desc->trace_vcpu_dstate &&
        (tb_cflags(tb) & (CF_HASH_MASK | CF_INVALID)) == desc->cf_mask) {
        /* check next page if needed */
        if (tb->page_addr[1] == -1) {
            return true;
        } else {
            tb_page_addr_t phys_page2;
            target_ulong virt_page2;

            virt_page2 = (desc->pc & TARGET_PAGE_MASK) + TARGET_PAGE_SIZE;
            phys_page2 = get_page_addr_code(desc->env, virt_page2);
            if (tb->page_addr[1] == phys_page2) {
                return true;
            }
        }
    }
    return false;
}

TranslationBlock *tb_htable_lookup(CPUState *cpu, target_ulong pc,
                                   target_ulong cs_base, uint32_t flags,
                                   uint32_t cf_mask)
{
    tb_page_addr_t phys_pc;
    struct tb_desc desc;
    uint32_t h;

    desc.env = (CPUArchState *)cpu->env_ptr;
    desc.cs_base = cs_base;
    desc.flags = flags;
    desc.cf_mask = cf_mask;
    desc.trace_vcpu_dstate = *cpu->trace_dstate;
    desc.pc = pc;
    phys_pc = get_page_addr_code(desc.env, pc);
    desc.phys_page1 = phys_pc & TARGET_PAGE_MASK;
    h = tb_hash_func(phys_pc, pc, flags, cf_mask, *cpu->trace_dstate);
    return qht_lookup(&tb_ctx.htable, tb_cmp, &desc, h);
}

void tb_set_jmp_target(TranslationBlock *tb, int n, uintptr_t addr)
{
    if (TCG_TARGET_HAS_direct_jump) {
        uintptr_t offset = tb->jmp_target_arg[n];
        uintptr_t tc_ptr = (uintptr_t)tb->tc.ptr;
        tb_target_set_jmp_target(tc_ptr, tc_ptr + offset, addr);
    } else {
        tb->jmp_target_arg[n] = addr;
    }
}

/* Called with tb_lock held.  */
static inline void tb_add_jump(TranslationBlock *tb, int n,
                               TranslationBlock *tb_next)
{
    assert(n < ARRAY_SIZE(tb->jmp_list_next));
    if (tb->jmp_list_next[n]) {
        /* Another thread has already done this while we were
         * outside of the lock; nothing to do in this case */
        return;
    }
    qemu_log_mask_and_addr(CPU_LOG_EXEC, tb->pc,
                           "Linking TBs %p [" TARGET_FMT_lx
                           "] index %d -> %p [" TARGET_FMT_lx "]\n",
                           tb->tc.ptr, tb->pc, n,
                           tb_next->tc.ptr, tb_next->pc);

    /* patch the native jump address */
    tb_set_jmp_target(tb, n, (uintptr_t)tb_next->tc.ptr);

    /* add in TB jmp circular list */
    tb->jmp_list_next[n] = tb_next->jmp_list_first;
    tb_next->jmp_list_first = (uintptr_t)tb | n;
}

static inline TranslationBlock *tb_find(CPUState *cpu,
                                        TranslationBlock *last_tb,
                                        int tb_exit, uint32_t cf_mask)
{
    TranslationBlock *tb;
    target_ulong cs_base, pc;
    uint32_t flags;
    bool acquired_tb_lock = false;

    tb = tb_lookup__cpu_state(cpu, &pc, &cs_base, &flags, cf_mask);
    if (tb == NULL) {
        /* mmap_lock is needed by tb_gen_code, and mmap_lock must be
         * taken outside tb_lock. As system emulation is currently
         * single threaded the locks are NOPs.
         */
        mmap_lock();
        tb_lock();
        acquired_tb_lock = true;

        /* There's a chance that our desired tb has been translated while
         * taking the locks so we check again inside the lock.
         */
        tb = tb_htable_lookup(cpu, pc, cs_base, flags, cf_mask);
        if (likely(tb == NULL)) {
            /* if no translated code available, then translate it now */
            tb = tb_gen_code(cpu, pc, cs_base, flags, cf_mask);
        }

        mmap_unlock();
        /* We add the TB in the virtual pc hash table for the fast lookup */
        atomic_set(&cpu->tb_jmp_cache[tb_jmp_cache_hash_func(pc)], tb);
    }
#ifndef CONFIG_USER_ONLY
    /* We don't take care of direct jumps when address mapping changes in
     * system emulation. So it's not safe to make a direct jump to a TB
     * spanning two pages because the mapping for the second page can change.
     */
    if (tb->page_addr[1] != -1) {
        last_tb = NULL;
    }
#endif
    /* See if we can patch the calling TB. */
    if (last_tb && !qemu_loglevel_mask(CPU_LOG_TB_NOCHAIN)) {
        if (!acquired_tb_lock) {
            tb_lock();
            acquired_tb_lock = true;
        }
        if (!(tb->cflags & CF_INVALID)) {
            tb_add_jump(last_tb, tb_exit, tb);
        }
    }
    if (acquired_tb_lock) {
        tb_unlock();
    }
    return tb;
}

static inline bool cpu_handle_halt(CPUState *cpu)
{
    if (cpu->halted) {
#if defined(TARGET_I386) && !defined(CONFIG_USER_ONLY)
        if ((cpu->interrupt_request & CPU_INTERRUPT_POLL)
            && replay_interrupt()) {
            X86CPU *x86_cpu = X86_CPU(cpu);
            qemu_mutex_lock_iothread();
            apic_poll_irq(x86_cpu->apic_state);
            cpu_reset_interrupt(cpu, CPU_INTERRUPT_POLL);
            qemu_mutex_unlock_iothread();
        }
#endif

        if (qemu_etrace_mask(ETRACE_F_EXEC)) {
            const char *dev_name = object_get_canonical_path(OBJECT(cpu));
            etrace_event_u64(&qemu_etracer, cpu->cpu_index,
                             ETRACE_EVU64_F_PREV_VAL,
                             dev_name, "sleep", 0, 1);
        }

        if (!cpu_has_work(cpu)) {
            return true;
        }

        cpu->halted = 0;
    }

    return false;
}

static inline void cpu_handle_debug_exception(CPUState *cpu)
{
    CPUClass *cc = CPU_GET_CLASS(cpu);
    CPUWatchpoint *wp;

    if (!cpu->watchpoint_hit) {
        QTAILQ_FOREACH(wp, &cpu->watchpoints, entry) {
            wp->flags &= ~BP_WATCHPOINT_HIT;
        }
    }

    cc->debug_excp_handler(cpu);
}

static inline bool cpu_handle_exception(CPUState *cpu, int *ret)
{
    if (cpu->exception_index < 0) {
#ifndef CONFIG_USER_ONLY
        if (replay_has_exception()
               && cpu->icount_decr.u16.low + cpu->icount_extra == 0) {
            /* try to cause an exception pending in the log */
            cpu_exec_nocache(cpu, 1, tb_find(cpu, NULL, 0, curr_cflags()), true);
        }
#endif
        if (cpu->exception_index < 0) {
            return false;
        }
    }

    if (cpu->exception_index >= EXCP_INTERRUPT) {
        /* exit request from the cpu execution loop */
        *ret = cpu->exception_index;
        if (*ret == EXCP_DEBUG) {
            cpu_handle_debug_exception(cpu);
        }
        cpu->exception_index = -1;
        return true;
    } else {
#if defined(CONFIG_USER_ONLY)
        /* if user mode only, we simulate a fake exception
           which will be handled outside the cpu execution
           loop */
#if defined(TARGET_I386)
        CPUClass *cc = CPU_GET_CLASS(cpu);
        cc->do_interrupt(cpu);
#endif
        *ret = cpu->exception_index;
        cpu->exception_index = -1;
        return true;
#else
        if (replay_exception()) {
            CPUClass *cc = CPU_GET_CLASS(cpu);
            qemu_mutex_lock_iothread();
            cc->do_interrupt(cpu);
            qemu_mutex_unlock_iothread();
            cpu->exception_index = -1;
        } else if (!replay_has_interrupt()) {
            /* give a chance to iothread in replay mode */
            *ret = EXCP_INTERRUPT;
            return true;
        }
#endif
    }

    return false;
}

static inline bool cpu_handle_interrupt(CPUState *cpu,
                                        TranslationBlock **last_tb)
{
    CPUClass *cc = CPU_GET_CLASS(cpu);
    int32_t insns_left;

    /* Clear the interrupt flag now since we're processing
     * cpu->interrupt_request and cpu->exit_request.
     */
    insns_left = atomic_read(&cpu->icount_decr.u32);
    atomic_set(&cpu->icount_decr.u16.high, 0);
    if (unlikely(insns_left < 0)) {
        /* Ensure the zeroing of icount_decr comes before the next read
         * of cpu->exit_request or cpu->interrupt_request.
         */
        smp_mb();
    }

    if (unlikely(atomic_read(&cpu->interrupt_request))) {
        int interrupt_request;
        qemu_mutex_lock_iothread();
        interrupt_request = cpu->interrupt_request;
        if (unlikely(cpu->singlestep_enabled & SSTEP_NOIRQ)) {
            /* Mask out external interrupts for this step. */
            interrupt_request &= ~CPU_INTERRUPT_SSTEP_MASK;
        }
        if (interrupt_request & CPU_INTERRUPT_DEBUG) {
            cpu->interrupt_request &= ~CPU_INTERRUPT_DEBUG;
            cpu->exception_index = EXCP_DEBUG;
            qemu_mutex_unlock_iothread();
            return true;
        }
        if (replay_mode == REPLAY_MODE_PLAY && !replay_has_interrupt()) {
            /* Do nothing */
        } else if (interrupt_request & CPU_INTERRUPT_HALT) {
            replay_interrupt();
            cpu->interrupt_request &= ~CPU_INTERRUPT_HALT;
            cpu->halted = 1;
            cpu->exception_index = EXCP_HLT;
            qemu_mutex_unlock_iothread();
            return true;
        }
#if defined(TARGET_I386)
        else if (interrupt_request & CPU_INTERRUPT_INIT) {
            X86CPU *x86_cpu = X86_CPU(cpu);
            CPUArchState *env = &x86_cpu->env;
            replay_interrupt();
            cpu_svm_check_intercept_param(env, SVM_EXIT_INIT, 0, 0);
            do_cpu_init(x86_cpu);
            cpu->exception_index = EXCP_HALTED;
            qemu_mutex_unlock_iothread();
            return true;
        }
#else
        else if (interrupt_request & CPU_INTERRUPT_RESET) {
            replay_interrupt();
            cpu_reset(cpu);
            qemu_mutex_unlock_iothread();
            return true;
        }
#endif
        /* The target hook has 3 exit conditions:
           False when the interrupt isn't processed,
           True when it is, and we should restart on a new TB,
           and via longjmp via cpu_loop_exit.  */
        else {
            if (cc->cpu_exec_interrupt(cpu, interrupt_request)) {
                replay_interrupt();
                *last_tb = NULL;
            }
            /* The target hook may have updated the 'cpu->interrupt_request';
             * reload the 'interrupt_request' value */
            interrupt_request = cpu->interrupt_request;
        }
        if (interrupt_request & CPU_INTERRUPT_EXITTB) {
            cpu->interrupt_request &= ~CPU_INTERRUPT_EXITTB;
            /* ensure that no TB jump will be modified as
               the program flow was changed */
            *last_tb = NULL;
        }

        /* If we exit via cpu_loop_exit/longjmp it is reset in cpu_exec */
        qemu_mutex_unlock_iothread();
    }

    /* Finally, check if we need to exit to the main loop.  */
    if (unlikely(atomic_read(&cpu->exit_request)
        || (use_icount && cpu->icount_decr.u16.low + cpu->icount_extra == 0))) {
        atomic_set(&cpu->exit_request, 0);
        cpu->exception_index = EXCP_INTERRUPT;
        return true;
    }

    return false;
}

static inline void cpu_loop_exec_tb(CPUState *cpu, TranslationBlock *tb,
                                    TranslationBlock **last_tb, int *tb_exit)
{
    uintptr_t ret;
    int32_t insns_left;

    trace_exec_tb(tb, tb->pc);
    ret = cpu_tb_exec(cpu, tb);
    tb = (TranslationBlock *)(ret & ~TB_EXIT_MASK);
    *tb_exit = ret & TB_EXIT_MASK;
    if (*tb_exit != TB_EXIT_REQUESTED) {
        *last_tb = tb;
        return;
    }

    *last_tb = NULL;
    insns_left = atomic_read(&cpu->icount_decr.u32);
    if (insns_left < 0) {
        /* Something asked us to stop executing chained TBs; just
         * continue round the main loop. Whatever requested the exit
         * will also have set something else (eg exit_request or
         * interrupt_request) which will be handled by
         * cpu_handle_interrupt.  cpu_handle_interrupt will also
         * clear cpu->icount_decr.u16.high.
         */
        return;
    }

    /* Instruction counter expired.  */
    assert(use_icount);
#ifndef CONFIG_USER_ONLY
    /* Ensure global icount has gone forward */
    cpu_update_icount(cpu);
    /* Refill decrementer and continue execution.  */
    insns_left = MIN(0xffff, cpu->icount_budget);
    cpu->icount_decr.u16.low = insns_left;
    cpu->icount_extra = cpu->icount_budget - insns_left;
    if (!cpu->icount_extra) {
        /* Execute any remaining instructions, then let the main loop
         * handle the next event.
         */
        if (insns_left > 0) {
            cpu_exec_nocache(cpu, insns_left, tb, false);
        }
    }
#endif
}

/* main execution loop */

int cpu_exec(CPUState *cpu)
{
    CPUClass *cc = CPU_GET_CLASS(cpu);
    int ret;
    CPUArchState *env = (CPUArchState *)cpu->env_ptr;
    SyncClocks sc = { 0 };

    /* replay_interrupt may need current_cpu */
    current_cpu = cpu;

    if (cpu_handle_halt(cpu)) {
        return EXCP_HALTED;
    }

    rcu_read_lock();

    cc->cpu_exec_enter(cpu);

    /* Calculate difference between guest clock and host clock.
     * This delay includes the delay of the last cycle, so
     * what we have to do is sleep until it is 0. As for the
     * advance/delay we gain here, we try to fix it next time.
     */
    init_delay_params(&sc, cpu);

    /* prepare setjmp context for exception handling */
    if (sigsetjmp(cpu->jmp_env, 0) != 0) {
#if defined(__clang__) || !QEMU_GNUC_PREREQ(4, 6)
        /* Some compilers wrongly smash all local variables after
         * siglongjmp. There were bug reports for gcc 4.5.0 and clang.
         * Reload essential local variables here for those compilers.
         * Newer versions of gcc would complain about this code (-Wclobbered). */
        cpu = current_cpu;
        cc = CPU_GET_CLASS(cpu);
#else /* buggy compiler */
        /* Assert that the compiler does not smash local variables. */
        g_assert(cpu == current_cpu);
        g_assert(cc == CPU_GET_CLASS(cpu));
#endif /* buggy compiler */
        cpu->can_do_io = 1;
        tb_lock_reset();
        if (qemu_mutex_iothread_locked()) {
            qemu_mutex_unlock_iothread();
        }

        if (qemu_etrace_mask(ETRACE_F_EXEC)
            && qemu_etracer.exec_start_valid) {
            target_ulong cs_base, pc;
            uint32_t flags;

            cpu_get_tb_cpu_state(env, &pc, &cs_base, &flags);
            etrace_dump_exec_end(&qemu_etracer, cpu->cpu_index, pc);
        }
    }

    /* if an exception is pending, we execute it here */
    while (!cpu_handle_exception(cpu, &ret)) {
        TranslationBlock *last_tb = NULL;
        int tb_exit = 0;

        while (!cpu_handle_interrupt(cpu, &last_tb)) {
            uint32_t cflags = cpu->cflags_next_tb;
            TranslationBlock *tb;

            /* When requested, use an exact setting for cflags for the next
               execution.  This is used for icount, precise smc, and stop-
               after-access watchpoints.  Since this request should never
               have CF_INVALID set, -1 is a convenient invalid value that
               does not require tcg headers for cpu_common_reset.  */
            if (cflags == -1) {
                cflags = curr_cflags();
            } else {
                cpu->cflags_next_tb = -1;
            }

            tb = tb_find(cpu, last_tb, tb_exit, cflags);
            cpu_loop_exec_tb(cpu, tb, &last_tb, &tb_exit);

            if (qemu_etrace_mask(ETRACE_F_EXEC)) {
                target_ulong cs_base, pc;
                uint32_t flags;

                if (tb_exit) {
                    /* TB early exit, ask for CPU state.  */
                    cpu_get_tb_cpu_state(env, &pc, &cs_base, &flags);
                } else {
                    /* TB didn't exit, assume we ran all of it.  */
                    pc = tb->pc + tb->size;
                }
                etrace_dump_exec_end(&qemu_etracer,
                                     cpu->cpu_index, pc);
            }

            qemu_etracer.exec_start_valid = false;

            /* Try to align the host and virtual clocks
               if the guest is in advance */
            align_clocks(&sc, cpu);
        }
    }

    cc->cpu_exec_exit(cpu);
    rcu_read_unlock();

    return ret;
}