/* Needed early for CONFIG_BSD etc. */
#include "qemu/osdep.h"
#include "qemu-common.h"
+#include "qemu/config-file.h"
#include "cpu.h"
#include "monitor/monitor.h"
#include "qapi/qmp/qerror.h"
#include "qemu/main-loop.h"
#include "qemu/bitmap.h"
#include "qemu/seqlock.h"
+#include "tcg.h"
#include "qapi-event.h"
#include "hw/nmi.h"
#include "sysemu/replay.h"
-#ifndef _WIN32
-#include "qemu/compatfd.h"
-#endif
-
#ifdef CONFIG_LINUX
#include <sys/prctl.h>
} TimersState;
static TimersState timers_state;
+bool mttcg_enabled;
+
+/*
+ * We default to false if we know other options have been enabled
+ * which are currently incompatible with MTTCG. Otherwise when each
+ * guest (target) has been updated to support:
+ * - atomic instructions
+ * - memory ordering primitives (barriers)
+ * they can set the appropriate CONFIG flags in ${target}-softmmu.mak
+ *
+ * Once a guest architecture has been converted to the new primitives
+ * there are two remaining limitations to check.
+ *
+ * - The guest can't be oversized (e.g. 64 bit guest on 32 bit host)
+ * - The host must have a stronger memory order than the guest
+ *
+ * It may be possible in future to support strong guests on weak hosts
+ * but that will require tagging all load/stores in a guest with their
+ * implicit memory order requirements which would likely slow things
+ * down a lot.
+ */
+
+static bool check_tcg_memory_orders_compatible(void)
+{
+#if defined(TCG_GUEST_DEFAULT_MO) && defined(TCG_TARGET_DEFAULT_MO)
+ return (TCG_GUEST_DEFAULT_MO & ~TCG_TARGET_DEFAULT_MO) == 0;
+#else
+ return false;
+#endif
+}
+
+static bool default_mttcg_enabled(void)
+{
+ QemuOpts *icount_opts = qemu_find_opts_singleton("icount");
+ const char *rr = qemu_opt_get(icount_opts, "rr");
+
+ if (rr || TCG_OVERSIZED_GUEST) {
+ return false;
+ } else {
+#ifdef TARGET_SUPPORTS_MTTCG
+ return check_tcg_memory_orders_compatible();
+#else
+ return false;
+#endif
+ }
+}
+
+void qemu_tcg_configure(QemuOpts *opts, Error **errp)
+{
+ const char *t = qemu_opt_get(opts, "thread");
+ if (t) {
+ if (strcmp(t, "multi") == 0) {
+ if (TCG_OVERSIZED_GUEST) {
+ error_setg(errp, "No MTTCG when guest word size > hosts");
+ } else {
+ if (!check_tcg_memory_orders_compatible()) {
+ error_report("Guest expects a stronger memory ordering "
+ "than the host provides");
+ error_printf("This may cause strange/hard to debug errors");
+ }
+ mttcg_enabled = true;
+ }
+ } else if (strcmp(t, "single") == 0) {
+ mttcg_enabled = false;
+ } else {
+ error_setg(errp, "Invalid 'thread' setting %s", t);
+ }
+ } else {
+ mttcg_enabled = default_mttcg_enabled();
+ }
+}
int64_t cpu_get_icount_raw(void)
{
NANOSECONDS_PER_SECOND / 10);
}
+/***********************************************************/
+/* TCG vCPU kick timer
+ *
+ * The kick timer is responsible for moving single threaded vCPU
+ * emulation on to the next vCPU. If more than one vCPU is running a
+ * timer event with force a cpu->exit so the next vCPU can get
+ * scheduled.
+ *
+ * The timer is removed if all vCPUs are idle and restarted again once
+ * idleness is complete.
+ */
+
+static QEMUTimer *tcg_kick_vcpu_timer;
+static CPUState *tcg_current_rr_cpu;
+
+#define TCG_KICK_PERIOD (NANOSECONDS_PER_SECOND / 10)
+
+static inline int64_t qemu_tcg_next_kick(void)
+{
+ return qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + TCG_KICK_PERIOD;
+}
+
+/* Kick the currently round-robin scheduled vCPU */
+static void qemu_cpu_kick_rr_cpu(void)
+{
+ CPUState *cpu;
+ do {
+ cpu = atomic_mb_read(&tcg_current_rr_cpu);
+ if (cpu) {
+ cpu_exit(cpu);
+ }
+ } while (cpu != atomic_mb_read(&tcg_current_rr_cpu));
+}
+
+static void kick_tcg_thread(void *opaque)
+{
+ timer_mod(tcg_kick_vcpu_timer, qemu_tcg_next_kick());
+ qemu_cpu_kick_rr_cpu();
+}
+
+static void start_tcg_kick_timer(void)
+{
+ if (!mttcg_enabled && !tcg_kick_vcpu_timer && CPU_NEXT(first_cpu)) {
+ tcg_kick_vcpu_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL,
+ kick_tcg_thread, NULL);
+ timer_mod(tcg_kick_vcpu_timer, qemu_tcg_next_kick());
+ }
+}
+
+static void stop_tcg_kick_timer(void)
+{
+ if (tcg_kick_vcpu_timer) {
+ timer_del(tcg_kick_vcpu_timer);
+ tcg_kick_vcpu_timer = NULL;
+ }
+}
+
/***********************************************************/
void hw_error(const char *fmt, ...)
{
abort();
}
-static void sigbus_handler(int n, struct qemu_signalfd_siginfo *siginfo,
- void *ctx)
+static void sigbus_handler(int n, siginfo_t *siginfo, void *ctx)
{
- if (kvm_on_sigbus(siginfo->ssi_code,
- (void *)(intptr_t)siginfo->ssi_addr)) {
+ 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)
memset(&action, 0, sizeof(action));
action.sa_flags = SA_SIGINFO;
- action.sa_sigaction = (void (*)(int, siginfo_t*, void*))sigbus_handler;
+ action.sa_sigaction = sigbus_handler;
sigaction(SIGBUS, &action, NULL);
prctl(PR_MCE_KILL, PR_MCE_KILL_SET, PR_MCE_KILL_EARLY, 0, 0);
}
-
-static void qemu_kvm_eat_signals(CPUState *cpu)
-{
- 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(cpu, 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));
-}
-
#else /* !CONFIG_LINUX */
-
static void qemu_init_sigbus(void)
{
}
-
-static void qemu_kvm_eat_signals(CPUState *cpu)
-{
-}
#endif /* !CONFIG_LINUX */
-#ifndef _WIN32
-static void dummy_signal(int sig)
-{
-}
-
-static void qemu_kvm_init_cpu_signals(CPUState *cpu)
-{
- int r;
- sigset_t set;
- struct sigaction sigact;
-
- memset(&sigact, 0, sizeof(sigact));
- sigact.sa_handler = dummy_signal;
- sigaction(SIG_IPI, &sigact, NULL);
-
- pthread_sigmask(SIG_BLOCK, NULL, &set);
- sigdelset(&set, SIG_IPI);
- sigdelset(&set, SIGBUS);
- r = kvm_set_signal_mask(cpu, &set);
- if (r) {
- fprintf(stderr, "kvm_set_signal_mask: %s\n", strerror(-r));
- exit(1);
- }
-}
-
-#else /* _WIN32 */
-static void qemu_kvm_init_cpu_signals(CPUState *cpu)
-{
- abort();
-}
-#endif /* _WIN32 */
-
static QemuMutex qemu_global_mutex;
-static QemuCond qemu_io_proceeded_cond;
-static unsigned iothread_requesting_mutex;
static QemuThread io_thread;
qemu_init_sigbus();
qemu_cond_init(&qemu_cpu_cond);
qemu_cond_init(&qemu_pause_cond);
- qemu_cond_init(&qemu_io_proceeded_cond);
qemu_mutex_init(&qemu_global_mutex);
qemu_thread_get_self(&io_thread);
static void qemu_wait_io_event_common(CPUState *cpu)
{
+ atomic_mb_set(&cpu->thread_kicked, false);
if (cpu->stop) {
cpu->stop = false;
cpu->stopped = true;
qemu_cond_broadcast(&qemu_pause_cond);
}
process_queued_cpu_work(cpu);
- cpu->thread_kicked = false;
+}
+
+static bool qemu_tcg_should_sleep(CPUState *cpu)
+{
+ if (mttcg_enabled) {
+ return cpu_thread_is_idle(cpu);
+ } else {
+ return all_cpu_threads_idle();
+ }
}
static void qemu_tcg_wait_io_event(CPUState *cpu)
{
- while (all_cpu_threads_idle()) {
+ while (qemu_tcg_should_sleep(cpu)) {
+ stop_tcg_kick_timer();
qemu_cond_wait(cpu->halt_cond, &qemu_global_mutex);
}
- while (iothread_requesting_mutex) {
- qemu_cond_wait(&qemu_io_proceeded_cond, &qemu_global_mutex);
- }
+ start_tcg_kick_timer();
- CPU_FOREACH(cpu) {
- qemu_wait_io_event_common(cpu);
- }
+ qemu_wait_io_event_common(cpu);
}
static void qemu_kvm_wait_io_event(CPUState *cpu)
qemu_cond_wait(cpu->halt_cond, &qemu_global_mutex);
}
- qemu_kvm_eat_signals(cpu);
qemu_wait_io_event_common(cpu);
}
exit(1);
}
- qemu_kvm_init_cpu_signals(cpu);
+ kvm_init_cpu_signals(cpu);
/* signal CPU creation */
cpu->created = true;
qemu_thread_get_self(cpu->thread);
cpu->thread_id = qemu_get_thread_id();
cpu->can_do_io = 1;
+ current_cpu = cpu;
sigemptyset(&waitset);
sigaddset(&waitset, SIG_IPI);
cpu->created = true;
qemu_cond_signal(&qemu_cpu_cond);
- current_cpu = cpu;
while (1) {
- current_cpu = NULL;
qemu_mutex_unlock_iothread();
do {
int sig;
exit(1);
}
qemu_mutex_lock_iothread();
- current_cpu = cpu;
qemu_wait_io_event_common(cpu);
}
cpu->icount_decr.u16.low = decr;
cpu->icount_extra = count;
}
+ qemu_mutex_unlock_iothread();
cpu_exec_start(cpu);
ret = cpu_exec(cpu);
cpu_exec_end(cpu);
+ qemu_mutex_lock_iothread();
#ifdef CONFIG_PROFILER
tcg_time += profile_getclock() - ti;
#endif
}
}
-static void *qemu_tcg_cpu_thread_fn(void *arg)
+/* Single-threaded TCG
+ *
+ * In the single-threaded case each vCPU is simulated in turn. If
+ * there is more than a single vCPU we create a simple timer to kick
+ * the vCPU and ensure we don't get stuck in a tight loop in one vCPU.
+ * This is done explicitly rather than relying on side-effects
+ * elsewhere.
+ */
+
+static void *qemu_tcg_rr_cpu_thread_fn(void *arg)
{
CPUState *cpu = arg;
/* process any pending work */
CPU_FOREACH(cpu) {
+ current_cpu = cpu;
qemu_wait_io_event_common(cpu);
}
}
- /* process any pending work */
- atomic_mb_set(&exit_request, 1);
+ start_tcg_kick_timer();
cpu = first_cpu;
+ /* process any pending work */
+ cpu->exit_request = 1;
+
while (1) {
/* Account partial waits to QEMU_CLOCK_VIRTUAL. */
qemu_account_warp_timer();
cpu = first_cpu;
}
- for (; cpu != NULL && !exit_request; cpu = CPU_NEXT(cpu)) {
+ while (cpu && !cpu->queued_work_first && !cpu->exit_request) {
+
+ atomic_mb_set(&tcg_current_rr_cpu, cpu);
+ current_cpu = cpu;
qemu_clock_enable(QEMU_CLOCK_VIRTUAL,
(cpu->singlestep_enabled & SSTEP_NOTIMER) == 0);
if (r == EXCP_DEBUG) {
cpu_handle_guest_debug(cpu);
break;
+ } else if (r == EXCP_ATOMIC) {
+ qemu_mutex_unlock_iothread();
+ cpu_exec_step_atomic(cpu);
+ qemu_mutex_lock_iothread();
+ break;
}
- } else if (cpu->stop || cpu->stopped) {
+ } else if (cpu->stop) {
if (cpu->unplug) {
cpu = CPU_NEXT(cpu);
}
break;
}
- } /* for cpu.. */
+ cpu = CPU_NEXT(cpu);
+ } /* while (cpu && !cpu->exit_request).. */
+
+ /* Does not need atomic_mb_set because a spurious wakeup is okay. */
+ atomic_set(&tcg_current_rr_cpu, NULL);
- /* Pairs with smp_wmb in qemu_cpu_kick. */
- atomic_mb_set(&exit_request, 0);
+ if (cpu && cpu->exit_request) {
+ atomic_mb_set(&cpu->exit_request, 0);
+ }
handle_icount_deadline();
- qemu_tcg_wait_io_event(QTAILQ_FIRST(&cpus));
+ qemu_tcg_wait_io_event(cpu ? cpu : QTAILQ_FIRST(&cpus));
deal_with_unplugged_cpus();
}
}
#endif
+/* Multi-threaded TCG
+ *
+ * In the multi-threaded case each vCPU has its own thread. The TLS
+ * variable current_cpu can be used deep in the code to find the
+ * current CPUState for a given thread.
+ */
+
+static void *qemu_tcg_cpu_thread_fn(void *arg)
+{
+ CPUState *cpu = arg;
+
+ rcu_register_thread();
+
+ qemu_mutex_lock_iothread();
+ qemu_thread_get_self(cpu->thread);
+
+ cpu->thread_id = qemu_get_thread_id();
+ cpu->created = true;
+ cpu->can_do_io = 1;
+ current_cpu = cpu;
+ qemu_cond_signal(&qemu_cpu_cond);
+
+ /* process any pending work */
+ cpu->exit_request = 1;
+
+ while (1) {
+ if (cpu_can_run(cpu)) {
+ int r;
+ r = tcg_cpu_exec(cpu);
+ switch (r) {
+ case EXCP_DEBUG:
+ cpu_handle_guest_debug(cpu);
+ break;
+ case EXCP_HALTED:
+ /* during start-up the vCPU is reset and the thread is
+ * kicked several times. If we don't ensure we go back
+ * to sleep in the halted state we won't cleanly
+ * start-up when the vCPU is enabled.
+ *
+ * cpu->halted should ensure we sleep in wait_io_event
+ */
+ g_assert(cpu->halted);
+ break;
+ case EXCP_ATOMIC:
+ qemu_mutex_unlock_iothread();
+ cpu_exec_step_atomic(cpu);
+ qemu_mutex_lock_iothread();
+ default:
+ /* Ignore everything else? */
+ break;
+ }
+ }
+
+ handle_icount_deadline();
+
+ atomic_mb_set(&cpu->exit_request, 0);
+ qemu_tcg_wait_io_event(cpu);
+ }
+
+ return NULL;
+}
+
static void qemu_cpu_kick_thread(CPUState *cpu)
{
#ifndef _WIN32
#endif
}
-static void qemu_cpu_kick_no_halt(void)
-{
- CPUState *cpu;
- /* Ensure whatever caused the exit has reached the CPU threads before
- * writing exit_request.
- */
- atomic_mb_set(&exit_request, 1);
- cpu = atomic_mb_read(&tcg_current_cpu);
- if (cpu) {
- cpu_exit(cpu);
- }
-}
-
void qemu_cpu_kick(CPUState *cpu)
{
qemu_cond_broadcast(cpu->halt_cond);
if (tcg_enabled()) {
- qemu_cpu_kick_no_halt();
+ cpu_exit(cpu);
+ /* NOP unless doing single-thread RR */
+ qemu_cpu_kick_rr_cpu();
} else {
if (hax_enabled()) {
/*
void qemu_mutex_lock_iothread(void)
{
- atomic_inc(&iothread_requesting_mutex);
- /* In the simple case there is no need to bump the VCPU thread out of
- * TCG code execution.
- */
- if (!tcg_enabled() || qemu_in_vcpu_thread() ||
- !first_cpu || !first_cpu->created) {
- qemu_mutex_lock(&qemu_global_mutex);
- atomic_dec(&iothread_requesting_mutex);
- } else {
- if (qemu_mutex_trylock(&qemu_global_mutex)) {
- qemu_cpu_kick_no_halt();
- qemu_mutex_lock(&qemu_global_mutex);
- }
- atomic_dec(&iothread_requesting_mutex);
- qemu_cond_broadcast(&qemu_io_proceeded_cond);
- }
+ g_assert(!qemu_mutex_iothread_locked());
+ qemu_mutex_lock(&qemu_global_mutex);
iothread_locked = true;
}
void qemu_mutex_unlock_iothread(void)
{
+ g_assert(qemu_mutex_iothread_locked());
iothread_locked = false;
qemu_mutex_unlock(&qemu_global_mutex);
}
if (qemu_in_vcpu_thread()) {
cpu_stop_current();
- if (!kvm_enabled()) {
- CPU_FOREACH(cpu) {
- cpu->stop = false;
- cpu->stopped = true;
- }
- return;
- }
}
while (!all_vcpus_paused()) {
static void qemu_tcg_init_vcpu(CPUState *cpu)
{
char thread_name[VCPU_THREAD_NAME_SIZE];
- static QemuCond *tcg_halt_cond;
- static QemuThread *tcg_cpu_thread;
+ static QemuCond *single_tcg_halt_cond;
+ static QemuThread *single_tcg_cpu_thread;
- /* share a single thread for all cpus with TCG */
- if (!tcg_cpu_thread) {
+ if (qemu_tcg_mttcg_enabled() || !single_tcg_cpu_thread) {
cpu->thread = g_malloc0(sizeof(QemuThread));
cpu->halt_cond = g_malloc0(sizeof(QemuCond));
qemu_cond_init(cpu->halt_cond);
- tcg_halt_cond = cpu->halt_cond;
- snprintf(thread_name, VCPU_THREAD_NAME_SIZE, "CPU %d/TCG",
+
+ if (qemu_tcg_mttcg_enabled()) {
+ /* create a thread per vCPU with TCG (MTTCG) */
+ parallel_cpus = true;
+ snprintf(thread_name, VCPU_THREAD_NAME_SIZE, "CPU %d/TCG",
cpu->cpu_index);
- qemu_thread_create(cpu->thread, thread_name, qemu_tcg_cpu_thread_fn,
- cpu, QEMU_THREAD_JOINABLE);
+
+ qemu_thread_create(cpu->thread, thread_name, qemu_tcg_cpu_thread_fn,
+ cpu, QEMU_THREAD_JOINABLE);
+
+ } else {
+ /* share a single thread for all cpus with TCG */
+ snprintf(thread_name, VCPU_THREAD_NAME_SIZE, "ALL CPUs/TCG");
+ qemu_thread_create(cpu->thread, thread_name,
+ qemu_tcg_rr_cpu_thread_fn,
+ cpu, QEMU_THREAD_JOINABLE);
+
+ single_tcg_halt_cond = cpu->halt_cond;
+ single_tcg_cpu_thread = cpu->thread;
+ }
#ifdef _WIN32
cpu->hThread = qemu_thread_get_handle(cpu->thread);
#endif
while (!cpu->created) {
qemu_cond_wait(&qemu_cpu_cond, &qemu_global_mutex);
}
- tcg_cpu_thread = cpu->thread;
} else {
- cpu->thread = tcg_cpu_thread;
- cpu->halt_cond = tcg_halt_cond;
+ /* For non-MTTCG cases we share the thread */
+ cpu->thread = single_tcg_cpu_thread;
+ cpu->halt_cond = single_tcg_halt_cond;
}
}
return do_vm_stop(state);
}
+/**
+ * Prepare for (re)starting the VM.
+ * Returns -1 if the vCPUs are not to be restarted (e.g. if they are already
+ * running or in case of an error condition), 0 otherwise.
+ */
+int vm_prepare_start(void)
+{
+ RunState requested;
+ int res = 0;
+
+ qemu_vmstop_requested(&requested);
+ if (runstate_is_running() && requested == RUN_STATE__MAX) {
+ return -1;
+ }
+
+ /* Ensure that a STOP/RESUME pair of events is emitted if a
+ * vmstop request was pending. The BLOCK_IO_ERROR event, for
+ * example, according to documentation is always followed by
+ * the STOP event.
+ */
+ if (runstate_is_running()) {
+ qapi_event_send_stop(&error_abort);
+ res = -1;
+ } else {
+ replay_enable_events();
+ cpu_enable_ticks();
+ runstate_set(RUN_STATE_RUNNING);
+ vm_state_notify(1, RUN_STATE_RUNNING);
+ }
+
+ /* We are sending this now, but the CPUs will be resumed shortly later */
+ qapi_event_send_resume(&error_abort);
+ return res;
+}
+
+void vm_start(void)
+{
+ if (!vm_prepare_start()) {
+ resume_all_vcpus();
+ }
+}
+
/* does a state transition even if the VM is already stopped,
current state is forgotten forever */
int vm_stop_force_state(RunState state)
projects / qemu.git / blobdiff