Archipelago » qemu

/*

 * 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.

 */

/* Needed early for CONFIG_BSD etc. */

#include "config-host.h"

#include "monitor.h"

#include "sysemu.h"

#include "gdbstub.h"

#include "dma.h"

#include "kvm.h"

#include "exec-all.h"

#include "qemu-thread.h"

#include "cpus.h"

#include "compatfd.h"

#ifdef SIGRTMIN

#define SIG_IPI (SIGRTMIN+4)

#else

#define SIG_IPI SIGUSR1

#endif

#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 */

static CPUState *next_cpu;

/***********************************************************/

void hw_error(const char *fmt, ...)

{

    va_list ap;

    CPUState *env;

    va_start(ap, fmt);

    fprintf(stderr, "qemu: hardware error: ");

    vfprintf(stderr, fmt, ap);

    fprintf(stderr, "\n");

    for(env = first_cpu; env != NULL; env = env->next_cpu) {

        fprintf(stderr, "CPU #%d:\n", env->cpu_index);

#ifdef TARGET_I386

        cpu_dump_state(env, stderr, fprintf, X86_DUMP_FPU);

#else

        cpu_dump_state(env, stderr, fprintf, 0);

#endif

    }

    va_end(ap);

    abort();

}

void cpu_synchronize_all_states(void)

{

    CPUState *cpu;

    for (cpu = first_cpu; cpu; cpu = cpu->next_cpu) {

        cpu_synchronize_state(cpu);

    }

}

void cpu_synchronize_all_post_reset(void)

{

    CPUState *cpu;

    for (cpu = first_cpu; cpu; cpu = cpu->next_cpu) {

        cpu_synchronize_post_reset(cpu);

    }

}

void cpu_synchronize_all_post_init(void)

{

    CPUState *cpu;

    for (cpu = first_cpu; cpu; cpu = cpu->next_cpu) {

        cpu_synchronize_post_init(cpu);

    }

}

int cpu_is_stopped(CPUState *env)

{

    return !vm_running || env->stopped;

}

static void do_vm_stop(int reason)

{

    if (vm_running) {

        cpu_disable_ticks();

        vm_running = 0;

        pause_all_vcpus();

        vm_state_notify(0, reason);

        qemu_aio_flush();

        bdrv_flush_all();

        monitor_protocol_event(QEVENT_STOP, NULL);

    }

}

static int cpu_can_run(CPUState *env)

{

    if (env->stop) {

        return 0;

    }

    if (env->stopped || !vm_running) {

        return 0;

    }

    return 1;

}

static bool cpu_thread_is_idle(CPUState *env)

{

    if (env->stop || env->queued_work_first) {

        return false;

    }

    if (env->stopped || !vm_running) {

        return true;

    }

    if (!env->halted || qemu_cpu_has_work(env)) {

        return false;

    }

    return true;

}

static bool all_cpu_threads_idle(void)

{

    CPUState *env;

    for (env = first_cpu; env != NULL; env = env->next_cpu) {

        if (!cpu_thread_is_idle(env)) {

            return false;

        }

    }

    return true;

}

static CPUDebugExcpHandler *debug_excp_handler;

CPUDebugExcpHandler *cpu_set_debug_excp_handler(CPUDebugExcpHandler *handler)

{

    CPUDebugExcpHandler *old_handler = debug_excp_handler;

    debug_excp_handler = handler;

    return old_handler;

}

static void cpu_handle_debug_exception(CPUState *env)

{

    CPUWatchpoint *wp;

    if (!env->watchpoint_hit) {

        QTAILQ_FOREACH(wp, &env->watchpoints, entry) {

            wp->flags &= ~BP_WATCHPOINT_HIT;

        }

    }

    if (debug_excp_handler) {

        debug_excp_handler(env);

    }

    gdb_set_stop_cpu(env);

    qemu_system_debug_request();

#ifdef CONFIG_IOTHREAD

    env->stopped = 1;

#endif

}

#ifdef CONFIG_IOTHREAD

static void cpu_signal(int sig)

{

    if (cpu_single_env) {

        cpu_exit(cpu_single_env);

    }

    exit_request = 1;

}

#endif

#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);

        sigprocmask(SIG_UNBLOCK, &set, NULL);

    }

    perror("Failed to re-raise SIGBUS!\n");

    abort();

}

static void sigbus_handler(int n, struct qemu_signalfd_siginfo *siginfo,

                           void *ctx)

{

    if (kvm_on_sigbus(siginfo->ssi_code,

                      (void *)(intptr_t)siginfo->ssi_addr)) {

        sigbus_reraise();

    }

}

static void qemu_init_sigbus(void)

{

    struct sigaction action;

    memset(&action, 0, sizeof(action));

    action.sa_flags = SA_SIGINFO;

    action.sa_sigaction = (void (*)(int, siginfo_t*, void*))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 */

#ifndef _WIN32

static int io_thread_fd = -1;

static void qemu_event_increment(void)

{

    /* Write 8 bytes to be compatible with eventfd.  */

    static const uint64_t val = 1;

    ssize_t ret;

    if (io_thread_fd == -1) {

        return;

    }

    do {

        ret = write(io_thread_fd, &val, sizeof(val));

    } while (ret < 0 && errno == EINTR);

    /* EAGAIN is fine, a read must be pending.  */

    if (ret < 0 && errno != EAGAIN) {

        fprintf(stderr, "qemu_event_increment: write() filed: %s\n",

                strerror(errno));

        exit (1);

    }

}

static void qemu_event_read(void *opaque)

{

    int fd = (unsigned long)opaque;

    ssize_t len;

    char buffer[512];

    /* Drain the notify pipe.  For eventfd, only 8 bytes will be read.  */

    do {

        len = read(fd, buffer, sizeof(buffer));

    } while ((len == -1 && errno == EINTR) || len == sizeof(buffer));

}

static int qemu_event_init(void)

{

    int err;

    int fds[2];

    err = qemu_eventfd(fds);

    if (err == -1) {

        return -errno;

    }

    err = fcntl_setfl(fds[0], O_NONBLOCK);

    if (err < 0) {

        goto fail;

    }

    err = fcntl_setfl(fds[1], O_NONBLOCK);

    if (err < 0) {

        goto fail;

    }

    qemu_set_fd_handler2(fds[0], NULL, qemu_event_read, NULL,

                         (void *)(unsigned long)fds[0]);

    io_thread_fd = fds[1];

    return 0;

fail:

    close(fds[0]);

    close(fds[1]);

    return err;

}

static void dummy_signal(int sig)

{

}

/* If we have signalfd, we mask out the signals we want to handle and then

 * use signalfd to listen for them.  We rely on whatever the current signal

 * handler is to dispatch the signals when we receive them.

 */

static void sigfd_handler(void *opaque)

{

    int fd = (unsigned long) opaque;

    struct qemu_signalfd_siginfo info;

    struct sigaction action;

    ssize_t len;

    while (1) {

        do {

            len = read(fd, &info, sizeof(info));

        } while (len == -1 && errno == EINTR);

        if (len == -1 && errno == EAGAIN) {

            break;

        }

        if (len != sizeof(info)) {

            printf("read from sigfd returned %zd: %m\n", len);

            return;

        }

        sigaction(info.ssi_signo, NULL, &action);

        if ((action.sa_flags & SA_SIGINFO) && action.sa_sigaction) {

            action.sa_sigaction(info.ssi_signo,

                                (siginfo_t *)&info, NULL);

        } else if (action.sa_handler) {

            action.sa_handler(info.ssi_signo);

        }

    }

}

static int qemu_signal_init(void)

{

    int sigfd;

    sigset_t set;

#ifdef CONFIG_IOTHREAD

    /* SIGUSR2 used by posix-aio-compat.c */

    sigemptyset(&set);

    sigaddset(&set, SIGUSR2);

    pthread_sigmask(SIG_UNBLOCK, &set, NULL);

    sigemptyset(&set);

    sigaddset(&set, SIGIO);

    sigaddset(&set, SIGALRM);

    sigaddset(&set, SIG_IPI);

    sigaddset(&set, SIGBUS);

    pthread_sigmask(SIG_BLOCK, &set, NULL);

#else

    sigemptyset(&set);

    sigaddset(&set, SIGBUS);

    if (kvm_enabled()) {

        /*

         * We need to process timer signals synchronously to avoid a race

         * between exit_request check and KVM vcpu entry.

         */

        sigaddset(&set, SIGIO);

        sigaddset(&set, SIGALRM);

    }

#endif

    sigfd = qemu_signalfd(&set);

    if (sigfd == -1) {

        fprintf(stderr, "failed to create signalfd\n");

        return -errno;

    }

    fcntl_setfl(sigfd, O_NONBLOCK);

    qemu_set_fd_handler2(sigfd, NULL, sigfd_handler, NULL,

                         (void *)(unsigned long) sigfd);

    return 0;

}

static void qemu_kvm_init_cpu_signals(CPUState *env)

{

    int r;

    sigset_t set;

    struct sigaction sigact;

    memset(&sigact, 0, sizeof(sigact));

    sigact.sa_handler = dummy_signal;

    sigaction(SIG_IPI, &sigact, NULL);

#ifdef CONFIG_IOTHREAD

    pthread_sigmask(SIG_BLOCK, NULL, &set);

    sigdelset(&set, SIG_IPI);

    sigdelset(&set, SIGBUS);

    r = kvm_set_signal_mask(env, &set);

    if (r) {

        fprintf(stderr, "kvm_set_signal_mask: %s\n", strerror(-r));

        exit(1);

    }

#else

    sigemptyset(&set);

    sigaddset(&set, SIG_IPI);

    sigaddset(&set, SIGIO);

    sigaddset(&set, SIGALRM);

    pthread_sigmask(SIG_BLOCK, &set, NULL);

    pthread_sigmask(SIG_BLOCK, NULL, &set);

    sigdelset(&set, SIGIO);

    sigdelset(&set, SIGALRM);

#endif

    sigdelset(&set, SIG_IPI);

    sigdelset(&set, SIGBUS);

    r = kvm_set_signal_mask(env, &set);

    if (r) {

        fprintf(stderr, "kvm_set_signal_mask: %s\n", strerror(-r));

        exit(1);

    }

}

static void qemu_tcg_init_cpu_signals(void)

{

#ifdef CONFIG_IOTHREAD

    sigset_t set;

    struct sigaction sigact;

    memset(&sigact, 0, sizeof(sigact));

    sigact.sa_handler = cpu_signal;

    sigaction(SIG_IPI, &sigact, NULL);

    sigemptyset(&set);

    sigaddset(&set, SIG_IPI);

    pthread_sigmask(SIG_UNBLOCK, &set, NULL);

#endif

}

static void qemu_kvm_eat_signals(CPUState *env)

{

    struct timespec ts = { 0, 0 };

    siginfo_t siginfo;

    sigset_t waitset;

    sigset_t chkset;

    int r;

    sigemptyset(&waitset);

    sigaddset(&waitset, SIG_IPI);

    sigaddset(&waitset, SIGBUS);

    do {

        r = sigtimedwait(&waitset, &siginfo, &ts);

        if (r == -1 && !(errno == EAGAIN || errno == EINTR)) {

            perror("sigtimedwait");

            exit(1);

        }

        switch (r) {

        case SIGBUS:

            if (kvm_on_sigbus_vcpu(env, siginfo.si_code, siginfo.si_addr)) {

                sigbus_reraise();

            }

            break;

        default:

            break;

        }

        r = sigpending(&chkset);

        if (r == -1) {

            perror("sigpending");

            exit(1);

        }

    } while (sigismember(&chkset, SIG_IPI) || sigismember(&chkset, SIGBUS));

#ifndef CONFIG_IOTHREAD

    if (sigismember(&chkset, SIGIO) || sigismember(&chkset, SIGALRM)) {

        qemu_notify_event();

    }

#endif

}

#else /* _WIN32 */

HANDLE qemu_event_handle;

static void dummy_event_handler(void *opaque)

{

}

static int qemu_event_init(void)

{

    qemu_event_handle = CreateEvent(NULL, FALSE, FALSE, NULL);

    if (!qemu_event_handle) {

        fprintf(stderr, "Failed CreateEvent: %ld\n", GetLastError());

        return -1;

    }

    qemu_add_wait_object(qemu_event_handle, dummy_event_handler, NULL);

    return 0;

}

static void qemu_event_increment(void)

{

    if (!SetEvent(qemu_event_handle)) {

        fprintf(stderr, "qemu_event_increment: SetEvent failed: %ld\n",

                GetLastError());

        exit (1);

    }

}

static void qemu_kvm_eat_signals(CPUState *env)

{

}

static int qemu_signal_init(void)

{

    return 0;

}

static void qemu_kvm_init_cpu_signals(CPUState *env)

{

    abort();

}

static void qemu_tcg_init_cpu_signals(void)

{

}

#endif /* _WIN32 */

#ifndef CONFIG_IOTHREAD

int qemu_init_main_loop(void)

{

    int ret;

    ret = qemu_signal_init();

    if (ret) {

        return ret;

    }

    qemu_init_sigbus();

    return qemu_event_init();

}

void qemu_main_loop_start(void)

{

}

void qemu_init_vcpu(void *_env)

{

    CPUState *env = _env;

    int r;

    env->nr_cores = smp_cores;

    env->nr_threads = smp_threads;

    if (kvm_enabled()) {

        r = kvm_init_vcpu(env);

        if (r < 0) {

            fprintf(stderr, "kvm_init_vcpu failed: %s\n", strerror(-r));

            exit(1);

        }

        qemu_kvm_init_cpu_signals(env);

    } else {

        qemu_tcg_init_cpu_signals();

    }

}

int qemu_cpu_is_self(void *env)

{

    return 1;

}

void run_on_cpu(CPUState *env, void (*func)(void *data), void *data)

{

    func(data);

}

void resume_all_vcpus(void)

{

}

void pause_all_vcpus(void)

{

}

void qemu_cpu_kick(void *env)

{

}

void qemu_cpu_kick_self(void)

{

#ifndef _WIN32

    assert(cpu_single_env);

    raise(SIG_IPI);

#else

    abort();

#endif

}

void qemu_notify_event(void)

{

    CPUState *env = cpu_single_env;

    qemu_event_increment ();

    if (env) {

        cpu_exit(env);

    }

    if (next_cpu && env != next_cpu) {

        cpu_exit(next_cpu);

    }

    exit_request = 1;

}

void qemu_mutex_lock_iothread(void) {}

void qemu_mutex_unlock_iothread(void) {}

void cpu_stop_current(void)

{

}

void vm_stop(int reason)

{

    do_vm_stop(reason);

}

#else /* CONFIG_IOTHREAD */

QemuMutex qemu_global_mutex;

static QemuMutex qemu_fair_mutex;

static QemuThread io_thread;

static QemuThread *tcg_cpu_thread;

static QemuCond *tcg_halt_cond;

static int qemu_system_ready;

/* cpu creation */

static QemuCond qemu_cpu_cond;

/* system init */

static QemuCond qemu_system_cond;

static QemuCond qemu_pause_cond;

static QemuCond qemu_work_cond;

int qemu_init_main_loop(void)

{

    int ret;

    qemu_init_sigbus();

    ret = qemu_signal_init();

    if (ret) {

        return ret;

    }

    /* Note eventfd must be drained before signalfd handlers run */

    ret = qemu_event_init();

    if (ret) {

        return ret;

    }

    qemu_cond_init(&qemu_cpu_cond);

    qemu_cond_init(&qemu_system_cond);

    qemu_cond_init(&qemu_pause_cond);

    qemu_cond_init(&qemu_work_cond);

    qemu_mutex_init(&qemu_fair_mutex);

    qemu_mutex_init(&qemu_global_mutex);

    qemu_mutex_lock(&qemu_global_mutex);

    qemu_thread_get_self(&io_thread);

    return 0;

}

void qemu_main_loop_start(void)

{

    qemu_system_ready = 1;

    qemu_cond_broadcast(&qemu_system_cond);

}

void run_on_cpu(CPUState *env, void (*func)(void *data), void *data)

{

    struct qemu_work_item wi;

    if (qemu_cpu_is_self(env)) {

        func(data);

        return;

    }

    wi.func = func;

    wi.data = data;

    if (!env->queued_work_first) {

        env->queued_work_first = &wi;

    } else {

        env->queued_work_last->next = &wi;

    }

    env->queued_work_last = &wi;

    wi.next = NULL;

    wi.done = false;

    qemu_cpu_kick(env);

    while (!wi.done) {

        CPUState *self_env = cpu_single_env;

        qemu_cond_wait(&qemu_work_cond, &qemu_global_mutex);

        cpu_single_env = self_env;

    }

}

static void flush_queued_work(CPUState *env)

{

    struct qemu_work_item *wi;

    if (!env->queued_work_first) {

        return;

    }

    while ((wi = env->queued_work_first)) {

        env->queued_work_first = wi->next;

        wi->func(wi->data);

        wi->done = true;

    }

    env->queued_work_last = NULL;

    qemu_cond_broadcast(&qemu_work_cond);

}

static void qemu_wait_io_event_common(CPUState *env)

{

    if (env->stop) {

        env->stop = 0;

        env->stopped = 1;

        qemu_cond_signal(&qemu_pause_cond);

    }

    flush_queued_work(env);

    env->thread_kicked = false;

}

static void qemu_tcg_wait_io_event(void)

{

    CPUState *env;

    while (all_cpu_threads_idle()) {

        qemu_cond_wait(tcg_halt_cond, &qemu_global_mutex);

    }

    qemu_mutex_unlock(&qemu_global_mutex);

    /*

     * Users of qemu_global_mutex can be starved, having no chance

     * to acquire it since this path will get to it first.

     * So use another lock to provide fairness.

     */

    qemu_mutex_lock(&qemu_fair_mutex);

    qemu_mutex_unlock(&qemu_fair_mutex);

    qemu_mutex_lock(&qemu_global_mutex);

    for (env = first_cpu; env != NULL; env = env->next_cpu) {

        qemu_wait_io_event_common(env);

    }

}

static void qemu_kvm_wait_io_event(CPUState *env)

{

    while (cpu_thread_is_idle(env)) {

        qemu_cond_wait(env->halt_cond, &qemu_global_mutex);

    }

    qemu_kvm_eat_signals(env);

    qemu_wait_io_event_common(env);

}

static void *qemu_kvm_cpu_thread_fn(void *arg)

{

    CPUState *env = arg;

    int r;

    qemu_mutex_lock(&qemu_global_mutex);

    qemu_thread_get_self(env->thread);

    r = kvm_init_vcpu(env);

    if (r < 0) {

        fprintf(stderr, "kvm_init_vcpu failed: %s\n", strerror(-r));

        exit(1);

    }

    qemu_kvm_init_cpu_signals(env);

    /* signal CPU creation */

    env->created = 1;

    qemu_cond_signal(&qemu_cpu_cond);

    /* and wait for machine initialization */

    while (!qemu_system_ready) {

        qemu_cond_wait(&qemu_system_cond, &qemu_global_mutex);

    }

    while (1) {

        if (cpu_can_run(env)) {

            r = kvm_cpu_exec(env);

            if (r == EXCP_DEBUG) {

                cpu_handle_debug_exception(env);

            }

        }

        qemu_kvm_wait_io_event(env);

    }

    return NULL;

}

static void *qemu_tcg_cpu_thread_fn(void *arg)

{

    CPUState *env = arg;

    qemu_tcg_init_cpu_signals();

    qemu_thread_get_self(env->thread);

    /* signal CPU creation */

    qemu_mutex_lock(&qemu_global_mutex);

    for (env = first_cpu; env != NULL; env = env->next_cpu) {

        env->created = 1;

    }

    qemu_cond_signal(&qemu_cpu_cond);

    /* and wait for machine initialization */

    while (!qemu_system_ready) {

        qemu_cond_wait(&qemu_system_cond, &qemu_global_mutex);

    }

    while (1) {

        cpu_exec_all();

        qemu_tcg_wait_io_event();

    }

    return NULL;

}

static void qemu_cpu_kick_thread(CPUState *env)

{

#ifndef _WIN32

    int err;

    err = pthread_kill(env->thread->thread, SIG_IPI);

    if (err) {

        fprintf(stderr, "qemu:%s: %s", __func__, strerror(err));

        exit(1);

    }

#else /* _WIN32 */

    if (!qemu_cpu_is_self(env)) {

        SuspendThread(env->thread->thread);

        cpu_signal(0);

        ResumeThread(env->thread->thread);

    }

#endif

}

void qemu_cpu_kick(void *_env)

{

    CPUState *env = _env;

    qemu_cond_broadcast(env->halt_cond);

    if (!env->thread_kicked) {

        qemu_cpu_kick_thread(env);

        env->thread_kicked = true;

    }

}

void qemu_cpu_kick_self(void)

{

#ifndef _WIN32

    assert(cpu_single_env);

    if (!cpu_single_env->thread_kicked) {

        qemu_cpu_kick_thread(cpu_single_env);

        cpu_single_env->thread_kicked = true;

    }

#else

    abort();

#endif

}

int qemu_cpu_is_self(void *_env)

{

    CPUState *env = _env;

    return qemu_thread_is_self(env->thread);

}

void qemu_mutex_lock_iothread(void)

{

    if (kvm_enabled()) {

        qemu_mutex_lock(&qemu_global_mutex);