Refactor CPUState handling out of vl.c

Signed-off-by: Blue Swirl <blauwirbel@gmail.com>

4 files changed, 795 insertions, 747 deletions

diff --git a/Makefile.target b/Makefile.target
index 16ea4431fa..a89158ae60 100644
--- a/Makefile.target
+++ b/Makefile.target
@@ -161,7 +161,7 @@ endif #CONFIG_BSD_USER
 # System emulator target
 ifdef CONFIG_SOFTMMU
 
-obj-y = vl.o monitor.o machine.o gdbstub.o
+obj-y = vl.o cpus.o monitor.o machine.o gdbstub.o
 obj-y += qemu-timer.o
 # virtio has to be here due to weird dependency between PCI and virtio-net.
 # need to fix this properly
diff --git a/cpus.c b/cpus.c
new file mode 100644
index 0000000000..9a8c2f7aec
--- /dev/null
+++ b/cpus.c
@@ -0,0 +1,773 @@
+/*
+ * 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 "cpus.h"
+
+static CPUState *cur_cpu;
+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);
+    }
+}
+
+static void do_vm_stop(int reason)
+{
+    if (vm_running) {
+        cpu_disable_ticks();
+        vm_running = 0;
+        pause_all_vcpus();
+        vm_state_notify(0, reason);
+        monitor_protocol_event(QEVENT_STOP, NULL);
+    }
+}
+
+static int cpu_can_run(CPUState *env)
+{
+    if (env->stop)
+        return 0;
+    if (env->stopped)
+        return 0;
+    if (!vm_running)
+        return 0;
+    return 1;
+}
+
+static int cpu_has_work(CPUState *env)
+{
+    if (env->stop)
+        return 1;
+    if (env->stopped)
+        return 0;
+    if (!env->halted)
+        return 1;
+    if (qemu_cpu_has_work(env))
+        return 1;
+    return 0;
+}
+
+static int tcg_has_work(void)
+{
+    CPUState *env;
+
+    for (env = first_cpu; env != NULL; env = env->next_cpu)
+        if (cpu_has_work(env))
+            return 1;
+    return 0;
+}
+
+#ifndef _WIN32
+static int io_thread_fd = -1;
+
+static void qemu_event_increment(void)
+{
+    /* Write 8 bytes to be compatible with eventfd.  */
+    static 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;
+}
+#else
+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);
+    }
+}
+#endif
+
+#ifndef CONFIG_IOTHREAD
+int qemu_init_main_loop(void)
+{
+    return qemu_event_init();
+}
+
+void qemu_init_vcpu(void *_env)
+{
+    CPUState *env = _env;
+
+    env->nr_cores = smp_cores;
+    env->nr_threads = smp_threads;
+    if (kvm_enabled())
+        kvm_init_vcpu(env);
+    return;
+}
+
+int qemu_cpu_self(void *env)
+{
+    return 1;
+}
+
+void resume_all_vcpus(void)
+{
+}
+
+void pause_all_vcpus(void)
+{
+}
+
+void qemu_cpu_kick(void *env)
+{
+    return;
+}
+
+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);
+    }
+}
+
+void qemu_mutex_lock_iothread(void) {}
+void qemu_mutex_unlock_iothread(void) {}
+
+void vm_stop(int reason)
+{
+    do_vm_stop(reason);
+}
+
+#else /* CONFIG_IOTHREAD */
+
+#include "qemu-thread.h"
+
+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 void tcg_block_io_signals(void);
+static void kvm_block_io_signals(CPUState *env);
+static void unblock_io_signals(void);
+
+int qemu_init_main_loop(void)
+{
+    int ret;
+
+    ret = qemu_event_init();
+    if (ret)
+        return ret;
+
+    qemu_cond_init(&qemu_pause_cond);
+    qemu_mutex_init(&qemu_fair_mutex);
+    qemu_mutex_init(&qemu_global_mutex);
+    qemu_mutex_lock(&qemu_global_mutex);
+
+    unblock_io_signals();
+    qemu_thread_self(&io_thread);
+
+    return 0;
+}
+
+static void qemu_wait_io_event_common(CPUState *env)
+{
+    if (env->stop) {
+        env->stop = 0;
+        env->stopped = 1;
+        qemu_cond_signal(&qemu_pause_cond);
+    }
+}
+
+static void qemu_wait_io_event(CPUState *env)
+{
+    while (!tcg_has_work())
+        qemu_cond_timedwait(env->halt_cond, &qemu_global_mutex, 1000);
+
+    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);
+    qemu_wait_io_event_common(env);
+}
+
+static void qemu_kvm_eat_signal(CPUState *env, int timeout)
+{
+    struct timespec ts;
+    int r, e;
+    siginfo_t siginfo;
+    sigset_t waitset;
+
+    ts.tv_sec = timeout / 1000;
+    ts.tv_nsec = (timeout % 1000) * 1000000;
+
+    sigemptyset(&waitset);
+    sigaddset(&waitset, SIG_IPI);
+
+    qemu_mutex_unlock(&qemu_global_mutex);
+    r = sigtimedwait(&waitset, &siginfo, &ts);
+    e = errno;
+    qemu_mutex_lock(&qemu_global_mutex);
+
+    if (r == -1 && !(e == EAGAIN || e == EINTR)) {
+        fprintf(stderr, "sigtimedwait: %s\n", strerror(e));
+        exit(1);
+    }
+}
+
+static void qemu_kvm_wait_io_event(CPUState *env)
+{
+    while (!cpu_has_work(env))
+        qemu_cond_timedwait(env->halt_cond, &qemu_global_mutex, 1000);
+
+    qemu_kvm_eat_signal(env, 0);
+    qemu_wait_io_event_common(env);
+}
+
+static int qemu_cpu_exec(CPUState *env);
+
+static void *kvm_cpu_thread_fn(void *arg)
+{
+    CPUState *env = arg;
+
+    qemu_thread_self(env->thread);
+    if (kvm_enabled())
+        kvm_init_vcpu(env);
+
+    kvm_block_io_signals(env);
+
+    /* signal CPU creation */
+    qemu_mutex_lock(&qemu_global_mutex);
+    env->created = 1;
+    qemu_cond_signal(&qemu_cpu_cond);
+
+    /* and wait for machine initialization */
+    while (!qemu_system_ready)
+        qemu_cond_timedwait(&qemu_system_cond, &qemu_global_mutex, 100);
+
+    while (1) {
+        if (cpu_can_run(env))
+            qemu_cpu_exec(env);
+        qemu_kvm_wait_io_event(env);
+    }
+
+    return NULL;
+}
+
+static void *tcg_cpu_thread_fn(void *arg)
+{
+    CPUState *env = arg;
+
+    tcg_block_io_signals();
+    qemu_thread_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_timedwait(&qemu_system_cond, &qemu_global_mutex, 100);
+
+    while (1) {
+        tcg_cpu_exec();
+        qemu_wait_io_event(cur_cpu);
+    }
+
+    return NULL;
+}
+
+void qemu_cpu_kick(void *_env)
+{
+    CPUState *env = _env;
+    qemu_cond_broadcast(env->halt_cond);
+    if (kvm_enabled())
+        qemu_thread_signal(env->thread, SIG_IPI);
+}
+
+int qemu_cpu_self(void *_env)
+{
+    CPUState *env = _env;
+    QemuThread this;
+
+    qemu_thread_self(&this);
+
+    return qemu_thread_equal(&this, env->thread);
+}
+
+static void cpu_signal(int sig)
+{
+    if (cpu_single_env)
+        cpu_exit(cpu_single_env);
+}
+
+static void tcg_block_io_signals(void)
+{
+    sigset_t set;
+    struct sigaction sigact;
+
+    sigemptyset(&set);
+    sigaddset(&set, SIGUSR2);
+    sigaddset(&set, SIGIO);
+    sigaddset(&set, SIGALRM);
+    sigaddset(&set, SIGCHLD);
+    pthread_sigmask(SIG_BLOCK, &set, NULL);
+
+    sigemptyset(&set);
+    sigaddset(&set, SIG_IPI);
+    pthread_sigmask(SIG_UNBLOCK, &set, NULL);
+
+    memset(&sigact, 0, sizeof(sigact));
+    sigact.sa_handler = cpu_signal;
+    sigaction(SIG_IPI, &sigact, NULL);
+}
+
+static void dummy_signal(int sig)
+{
+}
+
+static void kvm_block_io_signals(CPUState *env)
+{
+    int r;
+    sigset_t set;
+    struct sigaction sigact;
+
+    sigemptyset(&set);
+    sigaddset(&set, SIGUSR2);
+    sigaddset(&set, SIGIO);
+    sigaddset(&set, SIGALRM);
+    sigaddset(&set, SIGCHLD);
+    sigaddset(&set, SIG_IPI);
+    pthread_sigmask(SIG_BLOCK, &set, NULL);
+
+    pthread_sigmask(SIG_BLOCK, NULL, &set);
+    sigdelset(&set, SIG_IPI);
+
+    memset(&sigact, 0, sizeof(sigact));
+    sigact.sa_handler = dummy_signal;
+    sigaction(SIG_IPI, &sigact, NULL);
+
+    r = kvm_set_signal_mask(env, &set);
+    if (r) {
+        fprintf(stderr, "kvm_set_signal_mask: %s\n", strerror(r));
+        exit(1);
+    }
+}
+
+static void unblock_io_signals(void)
+{
+    sigset_t set;
+
+    sigemptyset(&set);
+    sigaddset(&set, SIGUSR2);
+    sigaddset(&set, SIGIO);
+    sigaddset(&set, SIGALRM);
+    pthread_sigmask(SIG_UNBLOCK, &set, NULL);
+
+    sigemptyset(&set);
+    sigaddset(&set, SIG_IPI);
+    pthread_sigmask(SIG_BLOCK, &set, NULL);
+}
+
+static void qemu_signal_lock(unsigned int msecs)
+{
+    qemu_mutex_lock(&qemu_fair_mutex);
+
+    while (qemu_mutex_trylock(&qemu_global_mutex)) {
+        qemu_thread_signal(tcg_cpu_thread, SIG_IPI);
+        if (!qemu_mutex_timedlock(&qemu_global_mutex, msecs))
+            break;
+    }
+    qemu_mutex_unlock(&qemu_fair_mutex);
+}
+
+void qemu_mutex_lock_iothread(void)
+{
+    if (kvm_enabled()) {
+        qemu_mutex_lock(&qemu_fair_mutex);
+        qemu_mutex_lock(&qemu_global_mutex);
+        qemu_mutex_unlock(&qemu_fair_mutex);
+    } else
+        qemu_signal_lock(100);
+}
+
+void qemu_mutex_unlock_iothread(void)
+{
+    qemu_mutex_unlock(&qemu_global_mutex);
+}
+
+static int all_vcpus_paused(void)
+{
+    CPUState *penv = first_cpu;
+
+    while (penv) {
+        if (!penv->stopped)
+            return 0;
+        penv = (CPUState *)penv->next_cpu;
+    }
+
+    return 1;
+}
+
+void pause_all_vcpus(void)
+{
+    CPUState *penv = first_cpu;
+
+    while (penv) {
+        penv->stop = 1;
+        qemu_thread_signal(penv->thread, SIG_IPI);
+        qemu_cpu_kick(penv);
+        penv = (CPUState *)penv->next_cpu;
+    }
+
+    while (!all_vcpus_paused()) {
+        qemu_cond_timedwait(&qemu_pause_cond, &qemu_global_mutex, 100);
+        penv = first_cpu;
+        while (penv) {
+            qemu_thread_signal(penv->thread, SIG_IPI);
+            penv = (CPUState *)penv->next_cpu;
+        }
+    }
+}
+
+void resume_all_vcpus(void)
+{
+    CPUState *penv = first_cpu;
+
+    while (penv) {
+        penv->stop = 0;
+        penv->stopped = 0;
+        qemu_thread_signal(penv->thread, SIG_IPI);
+        qemu_cpu_kick(penv);
+        penv = (CPUState *)penv->next_cpu;
+    }
+}
+
+static void tcg_init_vcpu(void *_env)
+{
+    CPUState *env = _env;
+    /* share a single thread for all cpus with TCG */
+    if (!tcg_cpu_thread) {
+        env->thread = qemu_mallocz(sizeof(QemuThread));
+        env->halt_cond = qemu_mallocz(sizeof(QemuCond));
+        qemu_cond_init(env->halt_cond);
+        qemu_thread_create(env->thread, tcg_cpu_thread_fn, env);
+        while (env->created == 0)
+            qemu_cond_timedwait(&qemu_cpu_cond, &qemu_global_mutex, 100);
+        tcg_cpu_thread = env->thread;
+        tcg_halt_cond = env->halt_cond;
+    } else {
+        env->thread = tcg_cpu_thread;
+        env->halt_cond = tcg_halt_cond;
+    }
+}
+
+static void kvm_start_vcpu(CPUState *env)
+{
+    env->thread = qemu_mallocz(sizeof(QemuThread));
+    env->halt_cond = qemu_mallocz(sizeof(QemuCond));
+    qemu_cond_init(env->halt_cond);
+    qemu_thread_create(env->thread, kvm_cpu_thread_fn, env);
+    while (env->created == 0)
+        qemu_cond_timedwait(&qemu_cpu_cond, &qemu_global_mutex, 100);
+}
+
+void qemu_init_vcpu(void *_env)
+{
+    CPUState *env = _env;
+
+    env->nr_cores = smp_cores;
+    env->nr_threads = smp_threads;
+    if (kvm_enabled())
+        kvm_start_vcpu(env);
+    else
+        tcg_init_vcpu(env);
+}
+
+void qemu_notify_event(void)
+{
+    qemu_event_increment();
+}
+
+static void qemu_system_vmstop_request(int reason)
+{
+    vmstop_requested = reason;
+    qemu_notify_event();
+}
+
+void vm_stop(int reason)
+{
+    QemuThread me;
+    qemu_thread_self(&me);
+
+    if (!qemu_thread_equal(&me, &io_thread)) {
+        qemu_system_vmstop_request(reason);
+        /*
+         * FIXME: should not return to device code in case
+         * vm_stop() has been requested.
+         */
+        if (cpu_single_env) {
+            cpu_exit(cpu_single_env);
+            cpu_single_env->stop = 1;
+        }
+        return;
+    }
+    do_vm_stop(reason);
+}
+
+#endif
+
+static int qemu_cpu_exec(CPUState *env)
+{
+    int ret;
+#ifdef CONFIG_PROFILER
+    int64_t ti;
+#endif
+
+#ifdef CONFIG_PROFILER
+    ti = profile_getclock();
+#endif
+    if (use_icount) {
+        int64_t count;
+        int decr;
+        qemu_icount -= (env->icount_decr.u16.low + env->icount_extra);
+        env->icount_decr.u16.low = 0;
+        env->icount_extra = 0;
+        count = qemu_icount_round (qemu_next_deadline());
+        qemu_icount += count;
+        decr = (count > 0xffff) ? 0xffff : count;
+        count -= decr;
+        env->icount_decr.u16.low = decr;
+        env->icount_extra = count;
+    }
+    ret = cpu_exec(env);
+#ifdef CONFIG_PROFILER
+    qemu_time += profile_getclock() - ti;
+#endif
+    if (use_icount) {
+        /* Fold pending instructions back into the
+           instruction counter, and clear the interrupt flag.  */
+        qemu_icount -= (env->icount_decr.u16.low
+                        + env->icount_extra);
+        env->icount_decr.u32 = 0;
+        env->icount_extra = 0;
+    }
+    return ret;
+}
+
+bool tcg_cpu_exec(void)
+{
+    int ret = 0;
+
+    if (next_cpu == NULL)
+        next_cpu = first_cpu;
+    for (; next_cpu != NULL; next_cpu = next_cpu->next_cpu) {
+        CPUState *env = cur_cpu = next_cpu;
+
+        qemu_clock_enable(vm_clock,
+                          (cur_cpu->singlestep_enabled & SSTEP_NOTIMER) == 0);
+
+        if (qemu_alarm_pending())
+            break;
+        if (cpu_can_run(env))
+            ret = qemu_cpu_exec(env);
+        else if (env->stop)
+            break;
+
+        if (ret == EXCP_DEBUG) {
+            gdb_set_stop_cpu(env);
+            debug_requested = EXCP_DEBUG;
+            break;
+        }
+    }
+    return tcg_has_work();
+}
+
+void set_numa_modes(void)
+{
+    CPUState *env;
+    int i;
+
+    for (env = first_cpu; env != NULL; env = env->next_cpu) {
+        for (i = 0; i < nb_numa_nodes; i++) {
+            if (node_cpumask[i] & (1 << env->cpu_index)) {
+                env->numa_node = i;
+            }
+        }
+    }
+}
+
+void set_cpu_log(const char *optarg)
+{
+    int mask;
+    const CPULogItem *item;
+
+    mask = cpu_str_to_log_mask(optarg);
+    if (!mask) {
+        printf("Log items (comma separated):\n");
+        for (item = cpu_log_items; item->mask != 0; item++) {
+            printf("%-10s %s\n", item->name, item->help);
+        }
+        exit(1);
+    }
+    cpu_set_log(mask);
+}
diff --git a/cpus.h b/cpus.h
new file mode 100644
index 0000000000..67c9a3b45e
--- /dev/null
+++ b/cpus.h
@@ -0,0 +1,18 @@
+#ifndef QEMU_CPUS_H
+#define QEMU_CPUS_H
+
+/* cpu-common.c */
+int qemu_init_main_loop(void);
+void resume_all_vcpus(void);
+void pause_all_vcpus(void);
+
+/* vl.c */
+extern int smp_cores;
+extern int smp_threads;
+extern int debug_requested;
+void vm_state_notify(int running, int reason);
+bool tcg_cpu_exec(void);
+void set_numa_modes(void);
+void set_cpu_log(const char *optarg);
+
+#endif
diff --git a/vl.c b/vl.c
index a1bb6e1959..15ab44c624 100644
--- a/vl.c
+++ b/vl.c
@@ -160,6 +160,7 @@ int main(int argc, char **argv)
 #include "slirp/libslirp.h"
 
 #include "qemu-queue.h"
+#include "cpus.h"
 
 //#define DEBUG_NET
 //#define DEBUG_SLIRP
@@ -249,8 +250,6 @@ int nb_numa_nodes;
 uint64_t node_mem[MAX_NODES];
 uint64_t node_cpumask[MAX_NODES];
 
-static CPUState *cur_cpu;
-static CPUState *next_cpu;
 static QEMUTimer *nographic_timer;
 
 uint8_t qemu_uuid[16];
@@ -314,28 +313,6 @@ static int default_driver_check(QemuOpts *opts, void *opaque)
 target_phys_addr_t isa_mem_base = 0;
 PicState2 *isa_pic;
 
-/***********************************************************/
-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();
-}
-
 static void set_proc_name(const char *s)
 {
 #if defined(__linux__) && defined(PR_SET_NAME)
@@ -1962,33 +1939,6 @@ static void nographic_update(void *opaque)
     qemu_mod_timer(nographic_timer, interval + qemu_get_clock(rt_clock));
 }
 
-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);
-    }
-}
-
 struct vm_change_state_entry {
     VMChangeStateHandler *cb;
     void *opaque;
@@ -2016,7 +1966,7 @@ void qemu_del_vm_change_state_handler(VMChangeStateEntry *e)
     qemu_free (e);
 }
 
-static void vm_state_notify(int running, int reason)
+void vm_state_notify(int running, int reason)
 {
     VMChangeStateEntry *e;
 
@@ -2025,9 +1975,6 @@ static void vm_state_notify(int running, int reason)
     }
 }
 
-static void resume_all_vcpus(void);
-static void pause_all_vcpus(void);
-
 void vm_start(void)
 {
     if (!vm_running) {
@@ -2051,7 +1998,7 @@ static QTAILQ_HEAD(reset_handlers, QEMUResetEntry) reset_handlers =
 static int reset_requested;
 static int shutdown_requested;
 static int powerdown_requested;
-static int debug_requested;
+int debug_requested;
 static int vmstop_requested;
 
 int qemu_shutdown_requested(void)
@@ -2089,17 +2036,6 @@ static int qemu_vmstop_requested(void)
     return r;
 }
 
-static void do_vm_stop(int reason)
-{
-    if (vm_running) {
-        cpu_disable_ticks();
-        vm_running = 0;
-        pause_all_vcpus();
-        vm_state_notify(0, reason);
-        monitor_protocol_event(QEVENT_STOP, NULL);
-    }
-}
-
 void qemu_register_reset(QEMUResetHandler *func, void *opaque)
 {
     QEMUResetEntry *re = qemu_mallocz(sizeof(QEMUResetEntry));
@@ -2156,589 +2092,6 @@ void qemu_system_powerdown_request(void)
     qemu_notify_event();
 }
 
-static int cpu_can_run(CPUState *env)
-{
-    if (env->stop)
-        return 0;
-    if (env->stopped)
-        return 0;
-    if (!vm_running)
-        return 0;
-    return 1;
-}
-
-static int cpu_has_work(CPUState *env)
-{
-    if (env->stop)
-        return 1;
-    if (env->stopped)
-        return 0;
-    if (!env->halted)
-        return 1;
-    if (qemu_cpu_has_work(env))
-        return 1;
-    return 0;
-}
-
-static int tcg_has_work(void)
-{
-    CPUState *env;
-
-    for (env = first_cpu; env != NULL; env = env->next_cpu)
-        if (cpu_has_work(env))
-            return 1;
-    return 0;
-}
-
-#ifndef _WIN32
-static int io_thread_fd = -1;
-
-static void qemu_event_increment(void)
-{
-    /* Write 8 bytes to be compatible with eventfd.  */
-    static 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;
-}
-#else
-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);
-    }
-}
-#endif
-
-#ifndef CONFIG_IOTHREAD
-static int qemu_init_main_loop(void)
-{
-    return qemu_event_init();
-}
-
-void qemu_init_vcpu(void *_env)
-{
-    CPUState *env = _env;
-
-    env->nr_cores = smp_cores;
-    env->nr_threads = smp_threads;
-    if (kvm_enabled())
-        kvm_init_vcpu(env);
-    return;
-}
-
-int qemu_cpu_self(void *env)
-{
-    return 1;
-}
-
-static void resume_all_vcpus(void)
-{
-}
-
-static void pause_all_vcpus(void)
-{
-}
-
-void qemu_cpu_kick(void *env)
-{
-    return;
-}
-
-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);
-    }
-}
-
-void qemu_mutex_lock_iothread(void) {}
-void qemu_mutex_unlock_iothread(void) {}
-
-void vm_stop(int reason)
-{
-    do_vm_stop(reason);
-}
-
-#else /* CONFIG_IOTHREAD */
-
-#include "qemu-thread.h"
-
-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 void tcg_block_io_signals(void);
-static void kvm_block_io_signals(CPUState *env);
-static void unblock_io_signals(void);
-
-static int qemu_init_main_loop(void)
-{
-    int ret;
-
-    ret = qemu_event_init();
-    if (ret)
-        return ret;
-
-    qemu_cond_init(&qemu_pause_cond);
-    qemu_mutex_init(&qemu_fair_mutex);
-    qemu_mutex_init(&qemu_global_mutex);
-    qemu_mutex_lock(&qemu_global_mutex);
-
-    unblock_io_signals();
-    qemu_thread_self(&io_thread);
-
-    return 0;
-}
-
-static void qemu_wait_io_event_common(CPUState *env)
-{
-    if (env->stop) {
-        env->stop = 0;
-        env->stopped = 1;
-        qemu_cond_signal(&qemu_pause_cond);
-    }
-}
-
-static void qemu_wait_io_event(CPUState *env)
-{
-    while (!tcg_has_work())
-        qemu_cond_timedwait(env->halt_cond, &qemu_global_mutex, 1000);
-
-    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);
-    qemu_wait_io_event_common(env);
-}
-
-static void qemu_kvm_eat_signal(CPUState *env, int timeout)
-{
-    struct timespec ts;
-    int r, e;
-    siginfo_t siginfo;
-    sigset_t waitset;
-
-    ts.tv_sec = timeout / 1000;
-    ts.tv_nsec = (timeout % 1000) * 1000000;
-
-    sigemptyset(&waitset);
-    sigaddset(&waitset, SIG_IPI);
-
-    qemu_mutex_unlock(&qemu_global_mutex);
-    r = sigtimedwait(&waitset, &siginfo, &ts);
-    e = errno;
-    qemu_mutex_lock(&qemu_global_mutex);
-
-    if (r == -1 && !(e == EAGAIN || e == EINTR)) {
-        fprintf(stderr, "sigtimedwait: %s\n", strerror(e));
-        exit(1);
-    }
-}
-
-static void qemu_kvm_wait_io_event(CPUState *env)
-{
-    while (!cpu_has_work(env))
-        qemu_cond_timedwait(env->halt_cond, &qemu_global_mutex, 1000);
-
-    qemu_kvm_eat_signal(env, 0);
-    qemu_wait_io_event_common(env);
-}
-
-static int qemu_cpu_exec(CPUState *env);
-
-static void *kvm_cpu_thread_fn(void *arg)
-{
-    CPUState *env = arg;
-
-    qemu_thread_self(env->thread);
-    if (kvm_enabled())
-        kvm_init_vcpu(env);
-
-    kvm_block_io_signals(env);
-
-    /* signal CPU creation */
-    qemu_mutex_lock(&qemu_global_mutex);
-    env->created = 1;
-    qemu_cond_signal(&qemu_cpu_cond);
-
-    /* and wait for machine initialization */
-    while (!qemu_system_ready)
-        qemu_cond_timedwait(&qemu_system_cond, &qemu_global_mutex, 100);
-
-    while (1) {
-        if (cpu_can_run(env))
-            qemu_cpu_exec(env);
-        qemu_kvm_wait_io_event(env);
-    }
-
-    return NULL;
-}
-
-static bool tcg_cpu_exec(void);
-
-static void *tcg_cpu_thread_fn(void *arg)
-{
-    CPUState *env = arg;
-
-    tcg_block_io_signals();
-    qemu_thread_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_timedwait(&qemu_system_cond, &qemu_global_mutex, 100);
-
-    while (1) {
-        tcg_cpu_exec();
-        qemu_wait_io_event(cur_cpu);
-    }
-
-    return NULL;
-}
-
-void qemu_cpu_kick(void *_env)
-{
-    CPUState *env = _env;
-    qemu_cond_broadcast(env->halt_cond);
-    if (kvm_enabled())
-        qemu_thread_signal(env->thread, SIG_IPI);
-}
-
-int qemu_cpu_self(void *_env)
-{
-    CPUState *env = _env;
-    QemuThread this;
- 
-    qemu_thread_self(&this);
- 
-    return qemu_thread_equal(&this, env->thread);
-}
-
-static void cpu_signal(int sig)
-{
-    if (cpu_single_env)
-        cpu_exit(cpu_single_env);
-}
-
-static void tcg_block_io_signals(void)
-{
-    sigset_t set;
-    struct sigaction sigact;
-
-    sigemptyset(&set);
-    sigaddset(&set, SIGUSR2);
-    sigaddset(&set, SIGIO);
-    sigaddset(&set, SIGALRM);
-    sigaddset(&set, SIGCHLD);
-    pthread_sigmask(SIG_BLOCK, &set, NULL);
-
-    sigemptyset(&set);
-    sigaddset(&set, SIG_IPI);
-    pthread_sigmask(SIG_UNBLOCK, &set, NULL);
-
-    memset(&sigact, 0, sizeof(sigact));
-    sigact.sa_handler = cpu_signal;
-    sigaction(SIG_IPI, &sigact, NULL);
-}
-
-static void dummy_signal(int sig)
-{
-}
-
-static void kvm_block_io_signals(CPUState *env)
-{
-    int r;
-    sigset_t set;
-    struct sigaction sigact;
-
-    sigemptyset(&set);
-    sigaddset(&set, SIGUSR2);
-    sigaddset(&set, SIGIO);
-    sigaddset(&set, SIGALRM);
-    sigaddset(&set, SIGCHLD);
-    sigaddset(&set, SIG_IPI);
-    pthread_sigmask(SIG_BLOCK, &set, NULL);
-
-    pthread_sigmask(SIG_BLOCK, NULL, &set);
-    sigdelset(&set, SIG_IPI);
-
-    memset(&sigact, 0, sizeof(sigact));
-    sigact.sa_handler = dummy_signal;
-    sigaction(SIG_IPI, &sigact, NULL);
-
-    r = kvm_set_signal_mask(env, &set);
-    if (r) {
-        fprintf(stderr, "kvm_set_signal_mask: %s\n", strerror(r));
-        exit(1);
-    }
-}
-
-static void unblock_io_signals(void)
-{
-    sigset_t set;
-
-    sigemptyset(&set);
-    sigaddset(&set, SIGUSR2);
-    sigaddset(&set, SIGIO);
-    sigaddset(&set, SIGALRM);
-    pthread_sigmask(SIG_UNBLOCK, &set, NULL);
-
-    sigemptyset(&set);
-    sigaddset(&set, SIG_IPI);
-    pthread_sigmask(SIG_BLOCK, &set, NULL);
-}
-
-static void qemu_signal_lock(unsigned int msecs)
-{
-    qemu_mutex_lock(&qemu_fair_mutex);
-
-    while (qemu_mutex_trylock(&qemu_global_mutex)) {
-        qemu_thread_signal(tcg_cpu_thread, SIG_IPI);
-        if (!qemu_mutex_timedlock(&qemu_global_mutex, msecs))
-            break;
-    }
-    qemu_mutex_unlock(&qemu_fair_mutex);
-}
-
-void qemu_mutex_lock_iothread(void)
-{
-    if (kvm_enabled()) {
-        qemu_mutex_lock(&qemu_fair_mutex);
-        qemu_mutex_lock(&qemu_global_mutex);
-        qemu_mutex_unlock(&qemu_fair_mutex);
-    } else
-        qemu_signal_lock(100);
-}
-
-void qemu_mutex_unlock_iothread(void)
-{
-    qemu_mutex_unlock(&qemu_global_mutex);
-}
-
-static int all_vcpus_paused(void)
-{
-    CPUState *penv = first_cpu;
-
-    while (penv) {
-        if (!penv->stopped)
-            return 0;
-        penv = (CPUState *)penv->next_cpu;
-    }
-
-    return 1;
-}
-
-static void pause_all_vcpus(void)
-{
-    CPUState *penv = first_cpu;
-
-    while (penv) {
-        penv->stop = 1;
-        qemu_thread_signal(penv->thread, SIG_IPI);
-        qemu_cpu_kick(penv);
-        penv = (CPUState *)penv->next_cpu;
-    }
-
-    while (!all_vcpus_paused()) {
-        qemu_cond_timedwait(&qemu_pause_cond, &qemu_global_mutex, 100);
-        penv = first_cpu;
-        while (penv) {
-            qemu_thread_signal(penv->thread, SIG_IPI);
-            penv = (CPUState *)penv->next_cpu;
-        }
-    }
-}
-
-static void resume_all_vcpus(void)
-{
-    CPUState *penv = first_cpu;
-
-    while (penv) {
-        penv->stop = 0;
-        penv->stopped = 0;
-        qemu_thread_signal(penv->thread, SIG_IPI);
-        qemu_cpu_kick(penv);
-        penv = (CPUState *)penv->next_cpu;
-    }
-}
-
-static void tcg_init_vcpu(void *_env)
-{
-    CPUState *env = _env;
-    /* share a single thread for all cpus with TCG */
-    if (!tcg_cpu_thread) {
-        env->thread = qemu_mallocz(sizeof(QemuThread));
-        env->halt_cond = qemu_mallocz(sizeof(QemuCond));
-        qemu_cond_init(env->halt_cond);
-        qemu_thread_create(env->thread, tcg_cpu_thread_fn, env);
-        while (env->created == 0)
-            qemu_cond_timedwait(&qemu_cpu_cond, &qemu_global_mutex, 100);
-        tcg_cpu_thread = env->thread;
-        tcg_halt_cond = env->halt_cond;
-    } else {
-        env->thread = tcg_cpu_thread;
-        env->halt_cond = tcg_halt_cond;
-    }
-}
-
-static void kvm_start_vcpu(CPUState *env)
-{
-    env->thread = qemu_mallocz(sizeof(QemuThread));
-    env->halt_cond = qemu_mallocz(sizeof(QemuCond));
-    qemu_cond_init(env->halt_cond);
-    qemu_thread_create(env->thread, kvm_cpu_thread_fn, env);
-    while (env->created == 0)
-        qemu_cond_timedwait(&qemu_cpu_cond, &qemu_global_mutex, 100);
-}
-
-void qemu_init_vcpu(void *_env)
-{
-    CPUState *env = _env;
-
-    env->nr_cores = smp_cores;
-    env->nr_threads = smp_threads;
-    if (kvm_enabled())
-        kvm_start_vcpu(env);
-    else
-        tcg_init_vcpu(env);
-}
-
-void qemu_notify_event(void)
-{
-    qemu_event_increment();
-}
-
-static void qemu_system_vmstop_request(int reason)
-{
-    vmstop_requested = reason;
-    qemu_notify_event();
-}
-
-void vm_stop(int reason)
-{
-    QemuThread me;
-    qemu_thread_self(&me);
-
-    if (!qemu_thread_equal(&me, &io_thread)) {
-        qemu_system_vmstop_request(reason);
-        /*
-         * FIXME: should not return to device code in case
-         * vm_stop() has been requested.
-         */
-        if (cpu_single_env) {
-            cpu_exit(cpu_single_env);
-            cpu_single_env->stop = 1;
-        }
-        return;
-    }
-    do_vm_stop(reason);
-}
-
-#endif
-
-
 #ifdef _WIN32
 static void host_main_loop_wait(int *timeout)
 {
@@ -2865,102 +2218,6 @@ void main_loop_wait(int nonblocking)
 
 }
 
-static int qemu_cpu_exec(CPUState *env)
-{
-    int ret;
-#ifdef CONFIG_PROFILER
-    int64_t ti;
-#endif
-
-#ifdef CONFIG_PROFILER
-    ti = profile_getclock();
-#endif
-    if (use_icount) {
-        int64_t count;
-        int decr;
-        qemu_icount -= (env->icount_decr.u16.low + env->icount_extra);
-        env->icount_decr.u16.low = 0;
-        env->icount_extra = 0;
-        count = qemu_icount_round (qemu_next_deadline());
-        qemu_icount += count;
-        decr = (count > 0xffff) ? 0xffff : count;
-        count -= decr;
-        env->icount_decr.u16.low = decr;
-        env->icount_extra = count;
-    }
-    ret = cpu_exec(env);
-#ifdef CONFIG_PROFILER
-    qemu_time += profile_getclock() - ti;
-#endif
-    if (use_icount) {
-        /* Fold pending instructions back into the
-           instruction counter, and clear the interrupt flag.  */
-        qemu_icount -= (env->icount_decr.u16.low
-                        + env->icount_extra);
-        env->icount_decr.u32 = 0;
-        env->icount_extra = 0;
-    }
-    return ret;
-}
-
-static bool tcg_cpu_exec(void)
-{
-    int ret = 0;
-
-    if (next_cpu == NULL)
-        next_cpu = first_cpu;
-    for (; next_cpu != NULL; next_cpu = next_cpu->next_cpu) {
-        CPUState *env = cur_cpu = next_cpu;
-
-        qemu_clock_enable(vm_clock,
-                          (cur_cpu->singlestep_enabled & SSTEP_NOTIMER) == 0);
-
-        if (qemu_alarm_pending())
-            break;
-        if (cpu_can_run(env))
-            ret = qemu_cpu_exec(env);
-        else if (env->stop)
-            break;
-
-        if (ret == EXCP_DEBUG) {
-            gdb_set_stop_cpu(env);
-            debug_requested = EXCP_DEBUG;
-            break;
-        }
-    }
-    return tcg_has_work();
-}
-
-static void set_numa_modes(void)
-{
-    CPUState *env;
-    int i;
-
-    for (env = first_cpu; env != NULL; env = env->next_cpu) {
-        for (i = 0; i < nb_numa_nodes; i++) {
-            if (node_cpumask[i] & (1 << env->cpu_index)) {
-                env->numa_node = i;
-            }
-        }
-    }
-}
-
-static void set_cpu_log(const char *optarg)
-{
-    int mask;
-    const CPULogItem *item;
-
-    mask = cpu_str_to_log_mask(optarg);
-    if (!mask) {
-        printf("Log items (comma separated):\n");
-        for (item = cpu_log_items; item->mask != 0; item++) {
-            printf("%-10s %s\n", item->name, item->help);
-        }
-        exit(1);
-    }
-    cpu_set_log(mask);
-}
-
 static int vm_can_run(void)
 {
     if (powerdown_requested)