system/cpus.c

/*
 * QEMU System Emulator
 *
 * Copyright (c) 2003-2008 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/coroutine-tls.h"
#include "qapi/error.h"
#include "exec/gdbstub.h"
#include "accel/accel-cpu-ops.h"
#include "system/hw_accel.h"
#include "exec/cpu-common.h"
#include "qemu/thread.h"
#include "qemu/main-loop.h"
#include "qemu/plugin.h"
#include "system/cpus.h"
#include "qemu/guest-random.h"
#include "system/physmem.h"
#include "system/replay.h"
#include "system/runstate.h"
#include "system/cpu-timers.h"
#include "system/whpx.h"
#include "hw/core/boards.h"
#include "hw/core/hw-error.h"
#include "trace.h"

#ifdef CONFIG_LINUX

#include <sys/prctl.h>

#ifndef PR_MCE_KILL
#define PR_MCE_KILL 33
#endif

#ifndef PR_MCE_KILL_SET
#define PR_MCE_KILL_SET 1
#endif

#ifndef PR_MCE_KILL_EARLY
#define PR_MCE_KILL_EARLY 1
#endif

#endif /* CONFIG_LINUX */

/* The Big QEMU Lock (BQL) */
static QemuMutex bql;

/*
 * The chosen accelerator is supposed to register this.
 */
static const AccelOpsClass *cpus_accel;

bool cpu_is_stopped(const CPUState *cpu)
{
    return cpu->stopped || !runstate_is_running();
}

bool cpu_work_list_empty(const CPUState *cpu)
{
    return QSIMPLEQ_EMPTY_ATOMIC(&cpu->work_list);
}

bool cpu_thread_is_idle(CPUState *cpu)
{
    if (cpu->stop || !cpu_work_list_empty(cpu)) {
        return false;
    }
    if (cpu_is_stopped(cpu)) {
        return true;
    }
    if (!cpu->halted || cpu_has_work(cpu)) {
        return false;
    }
    if (cpus_accel->cpu_thread_is_idle) {
        return cpus_accel->cpu_thread_is_idle(cpu);
    }
    return true;
}

bool all_cpu_threads_idle(void)
{
    CPUState *cpu;

    CPU_FOREACH(cpu) {
        if (!cpu_thread_is_idle(cpu)) {
            return false;
        }
    }
    return true;
}

/***********************************************************/
void hw_error(const char *fmt, ...)
{
    va_list ap;
    CPUState *cpu;

    va_start(ap, fmt);
    fprintf(stderr, "qemu: hardware error: ");
    vfprintf(stderr, fmt, ap);
    fprintf(stderr, "\n");
    CPU_FOREACH(cpu) {
        fprintf(stderr, "CPU #%d:\n", cpu->cpu_index);
        cpu_dump_state(cpu, stderr, CPU_DUMP_FPU);
    }
    va_end(ap);
    abort();
}

void cpu_synchronize_all_states(void)
{
    CPUState *cpu;

    CPU_FOREACH(cpu) {
        cpu_synchronize_state(cpu);
    }
}

void cpu_synchronize_all_post_reset(void)
{
    CPUState *cpu;

    CPU_FOREACH(cpu) {
        cpu_synchronize_post_reset(cpu);
    }
}

void cpu_synchronize_all_post_init(void)
{
    CPUState *cpu;

    CPU_FOREACH(cpu) {
        cpu_synchronize_post_init(cpu);
    }
}

void cpu_synchronize_all_pre_loadvm(void)
{
    CPUState *cpu;

    CPU_FOREACH(cpu) {
        cpu_synchronize_pre_loadvm(cpu);
    }
}

void cpu_synchronize_state(CPUState *cpu)
{
    if (cpus_accel->synchronize_state) {
        cpus_accel->synchronize_state(cpu);
    }
}

void cpu_synchronize_post_reset(CPUState *cpu)
{
    if (cpus_accel->synchronize_post_reset) {
        cpus_accel->synchronize_post_reset(cpu);
    }
}

void cpu_synchronize_post_init(CPUState *cpu)
{
    if (cpus_accel->synchronize_post_init) {
        cpus_accel->synchronize_post_init(cpu);
    }
}

void cpu_synchronize_pre_loadvm(CPUState *cpu)
{
    if (cpus_accel->synchronize_pre_loadvm) {
        cpus_accel->synchronize_pre_loadvm(cpu);
    }
}

bool cpus_are_resettable(void)
{
    if (cpus_accel->cpus_are_resettable) {
        return cpus_accel->cpus_are_resettable();
    }
    return true;
}

void cpu_exec_reset_hold(CPUState *cpu)
{
    if (cpus_accel->cpu_reset_hold) {
        cpus_accel->cpu_reset_hold(cpu);
    }
}

int64_t cpus_get_virtual_clock(void)
{
    /*
     * XXX
     *
     * need to check that cpus_accel is not NULL, because qcow2 calls
     * qemu_get_clock_ns(CLOCK_VIRTUAL) without any accel initialized and
     * with ticks disabled in some io-tests:
     * 030 040 041 060 099 120 127 140 156 161 172 181 191 192 195 203 229 249 256 267
     *
     * is this expected?
     *
     * XXX
     */
    if (cpus_accel && cpus_accel->get_virtual_clock) {
        return cpus_accel->get_virtual_clock();
    }
    return cpu_get_clock();
}

/*
 * Signal the new virtual time to the accelerator. This is only needed
 * by accelerators that need to track the changes as we warp time.
 */
void cpus_set_virtual_clock(int64_t new_time)
{
    if (cpus_accel && cpus_accel->set_virtual_clock) {
        cpus_accel->set_virtual_clock(new_time);
    }
}

/*
 * return the time elapsed in VM between vm_start and vm_stop.  Unless
 * icount is active, cpus_get_elapsed_ticks() uses units of the host CPU cycle
 * counter.
 */
int64_t cpus_get_elapsed_ticks(void)
{
    if (cpus_accel->get_elapsed_ticks) {
        return cpus_accel->get_elapsed_ticks();
    }
    return cpu_get_ticks();
}

void cpu_set_interrupt(CPUState *cpu, int mask)
{
    /* Pairs with cpu_test_interrupt(). */
    qatomic_or(&cpu->interrupt_request, mask);
}

void generic_handle_interrupt(CPUState *cpu, int mask)
{
    cpu_set_interrupt(cpu, mask);

    if (!qemu_cpu_is_self(cpu)) {
        qemu_cpu_kick(cpu);
    }
}

void cpu_interrupt(CPUState *cpu, int mask)
{
    g_assert(bql_locked());

    cpus_accel->handle_interrupt(cpu, mask);
}

bool cpu_can_run(const CPUState *cpu)
{
    if (cpu->stop) {
        return false;
    }
    if (cpu_is_stopped(cpu)) {
        return false;
    }
    return true;
}

void cpu_handle_guest_debug(CPUState *cpu)
{
    if (replay_running_debug()) {
        if (!cpu_single_stepping(cpu)) {
            /*
             * Report about the breakpoint and
             * make a single step to skip it
             */
            replay_breakpoint();
            cpu_single_step(cpu, SSTEP_ENABLE);
        } else {
            cpu_single_step(cpu, 0);
        }
    } else {
        gdb_set_stop_cpu(cpu);
        qemu_system_debug_request();
        cpu->stopped = true;
    }
}

#ifdef CONFIG_LINUX
static void sigbus_reraise(void)
{
    sigset_t set;
    struct sigaction action;

    memset(&action, 0, sizeof(action));
    action.sa_handler = SIG_DFL;
    if (!sigaction(SIGBUS, &action, NULL)) {
        raise(SIGBUS);
        sigemptyset(&set);
        sigaddset(&set, SIGBUS);
        pthread_sigmask(SIG_UNBLOCK, &set, NULL);
    }
    perror("Failed to re-raise SIGBUS!");
    abort();
}

static void sigbus_handler(int n, siginfo_t *siginfo, void *ctx)
{
    if (siginfo->si_code != BUS_MCEERR_AO && siginfo->si_code != BUS_MCEERR_AR) {
        sigbus_reraise();
    }

    if (current_cpu) {
        /* Called asynchronously in VCPU thread.  */
        if (kvm_on_sigbus_vcpu(current_cpu, siginfo->si_code, siginfo->si_addr)) {
            sigbus_reraise();
        }
    } else {
        /* Called synchronously (via signalfd) in main thread.  */
        if (kvm_on_sigbus(siginfo->si_code, siginfo->si_addr)) {
            sigbus_reraise();
        }
    }
}

static void qemu_init_sigbus(void)
{
    struct sigaction action;

    /*
     * ALERT: when modifying this, take care that SIGBUS forwarding in
     * qemu_prealloc_mem() will continue working as expected.
     */
    memset(&action, 0, sizeof(action));
    action.sa_flags = SA_SIGINFO;
    action.sa_sigaction = sigbus_handler;
    sigaction(SIGBUS, &action, NULL);

    prctl(PR_MCE_KILL, PR_MCE_KILL_SET, PR_MCE_KILL_EARLY, 0, 0);
}
#else /* !CONFIG_LINUX */
static void qemu_init_sigbus(void)
{
}
#endif /* !CONFIG_LINUX */

static QemuThread io_thread;

/* cpu creation */
static QemuCond qemu_cpu_cond;
/* system init */
static QemuCond qemu_pause_cond;

void qemu_init_cpu_loop(void)
{
    qemu_init_sigbus();
    qemu_cond_init(&qemu_cpu_cond);
    qemu_cond_init(&qemu_pause_cond);
    qemu_mutex_init(&bql);

    qemu_thread_get_self(&io_thread);
}

void run_on_cpu(CPUState *cpu, run_on_cpu_func func, run_on_cpu_data data)
{
    do_run_on_cpu(cpu, func, data, &bql);
}

static void qemu_cpu_stop(CPUState *cpu, bool exit)
{
    g_assert(qemu_cpu_is_self(cpu));
    cpu->stop = false;
    cpu->stopped = true;
    if (exit) {
        cpu_exit(cpu);
    }
    qemu_cond_broadcast(&qemu_pause_cond);
}

void qemu_process_cpu_events_common(CPUState *cpu)
{
    qatomic_set_mb(&cpu->thread_kicked, false);
    if (cpu->stop) {
        qemu_cpu_stop(cpu, false);
    }
    process_queued_cpu_work(cpu);
}

void qemu_process_cpu_events(CPUState *cpu)
{
    bool slept = false;

    qatomic_set(&cpu->exit_request, false);
    while (cpu_thread_is_idle(cpu)) {
        if (!slept) {
            slept = true;
            qemu_plugin_vcpu_idle_cb(cpu);
        }
        qemu_cond_wait(cpu->halt_cond, &bql);
    }
    if (slept) {
        qemu_plugin_vcpu_resume_cb(cpu);
    }

    qemu_process_cpu_events_common(cpu);
}

void cpus_kick_thread(CPUState *cpu)
{
    if (qatomic_read(&cpu->thread_kicked)) {
        return;
    }
    qatomic_set(&cpu->thread_kicked, true);

#ifndef _WIN32
    int err = pthread_kill(cpu->thread->thread, SIG_IPI);
    if (err && err != ESRCH) {
        fprintf(stderr, "qemu:%s: %s", __func__, strerror(err));
        exit(1);
    }
#else
    qemu_sem_post(&cpu->sem);
#endif
}

void qemu_cpu_kick(CPUState *cpu)
{
    qemu_cond_broadcast(cpu->halt_cond);
    if (cpus_accel->kick_vcpu_thread) {
        cpus_accel->kick_vcpu_thread(cpu);
    } else { /* default */
        cpus_kick_thread(cpu);
    }
}

void qemu_cpu_kick_self(void)
{
    assert(current_cpu);
    cpus_kick_thread(current_cpu);
}

bool qemu_cpu_is_self(CPUState *cpu)
{
    return qemu_thread_is_self(cpu->thread);
}

bool qemu_in_vcpu_thread(void)
{
    return current_cpu && qemu_cpu_is_self(current_cpu);
}

QEMU_DEFINE_STATIC_CO_TLS(bool, bql_locked)

bool mutex_is_bql(QemuMutex *mutex)
{
    return mutex == &bql;
}

void bql_update_status(bool locked)
{
    /* This function should only be used when an update happened.. */
    assert(bql_locked() != locked);
    set_bql_locked(locked);
}

static uint32_t bql_unlock_blocked;

void bql_block_unlock(bool increase)
{
    uint32_t new_value;

    assert(bql_locked());

    /* check for overflow! */
    new_value = bql_unlock_blocked + increase - !increase;
    assert((new_value > bql_unlock_blocked) == increase);
    bql_unlock_blocked = new_value;
}

bool bql_locked(void)
{
    return get_bql_locked();
}

bool qemu_in_main_thread(void)
{
    return bql_locked();
}

void rust_bql_mock_lock(void)
{
    error_report("This function should be used only from tests");
    abort();
}

/*
 * The BQL is taken from so many places that it is worth profiling the
 * callers directly, instead of funneling them all through a single function.
 */
void bql_lock_impl(const char *file, int line)
{
    QemuMutexLockFunc bql_lock_fn = qatomic_read(&bql_mutex_lock_func);

    g_assert(!bql_locked());
    bql_lock_fn(&bql, file, line);
}

void bql_unlock(void)
{
    g_assert(bql_locked());
    g_assert(!bql_unlock_blocked);
    qemu_mutex_unlock(&bql);
}

void qemu_cond_wait_bql(QemuCond *cond)
{
    qemu_cond_wait(cond, &bql);
}

void qemu_cond_timedwait_bql(QemuCond *cond, int ms)
{
    qemu_cond_timedwait(cond, &bql, ms);
}

/* signal CPU creation */
void cpu_thread_signal_created(CPUState *cpu)
{
    cpu->created = true;
    qemu_cond_signal(&qemu_cpu_cond);
}

/* signal CPU destruction */
void cpu_thread_signal_destroyed(CPUState *cpu)
{
    cpu->created = false;
    qemu_cond_signal(&qemu_cpu_cond);
}

void cpu_pause(CPUState *cpu)
{
    if (qemu_cpu_is_self(cpu)) {
        qemu_cpu_stop(cpu, true);
    } else {
        cpu->stop = true;
        cpu_exit(cpu);
    }
}

void cpu_resume(CPUState *cpu)
{
    cpu->exception_index = -1;
    cpu->stop = false;
    cpu->stopped = false;
    qemu_cpu_kick(cpu);
}

static bool all_vcpus_paused(void)
{
    CPUState *cpu;

    CPU_FOREACH(cpu) {
        if (!cpu->stopped) {
            return false;
        }
    }

    return true;
}

void pause_all_vcpus(void)
{
    CPUState *cpu;

    qemu_clock_enable(QEMU_CLOCK_VIRTUAL, false);
    CPU_FOREACH(cpu) {
        cpu_pause(cpu);
    }

    /* We need to drop the replay_lock so any vCPU threads woken up
     * can finish their replay tasks
     */
    replay_mutex_unlock();

    while (!all_vcpus_paused()) {
        qemu_cond_wait(&qemu_pause_cond, &bql);
        /* FIXME: is this needed? */
        CPU_FOREACH(cpu) {
            qemu_cpu_kick(cpu);
        }
    }

    bql_unlock();
    replay_mutex_lock();
    bql_lock();
}

void resume_all_vcpus(void)
{
    CPUState *cpu;

    if (!runstate_is_running()) {
        return;
    }

    qemu_clock_enable(QEMU_CLOCK_VIRTUAL, true);
    CPU_FOREACH(cpu) {
        cpu_resume(cpu);
    }
}

void cpu_remove_sync(CPUState *cpu)
{
    cpu->stop = true;
    cpu->unplug = true;
    cpu_exit(cpu);
    bql_unlock();
    qemu_thread_join(cpu->thread);
    bql_lock();
}

void cpus_register_accel(const AccelOpsClass *ops)
{
    assert(ops != NULL);
    assert(ops->create_vcpu_thread != NULL); /* mandatory */
    assert(ops->handle_interrupt);

    cpus_accel = ops;
}

const AccelOpsClass *cpus_get_accel(void)
{
    /* broken if we call this early */
    assert(cpus_accel);
    return cpus_accel;
}

void qemu_init_vcpu(CPUState *cpu)
{
    MachineState *ms = MACHINE(qdev_get_machine());

    cpu->nr_threads =  ms->smp.threads;
    cpu->stopped = true;
    cpu->random_seed = qemu_guest_random_seed_thread_part1();

    if (!cpu->as) {
        /* If the target cpu hasn't set up any address spaces itself,
         * give it the default one.
         */
        cpu_address_space_init(cpu, 0, "cpu-memory", cpu->memory);
    }

    /* accelerators all implement the AccelOpsClass */
    g_assert(cpus_accel != NULL && cpus_accel->create_vcpu_thread != NULL);
    cpus_accel->create_vcpu_thread(cpu);

    while (!cpu->created) {
        qemu_cond_wait(&qemu_cpu_cond, &bql);
    }
}

void cpu_stop_current(void)
{
    if (current_cpu) {
        current_cpu->stop = true;
        cpu_exit(current_cpu);
    }
}