#include "monitor/monitor.h"
#include "qapi/qmp/qerror.h"
+#include "qemu/error-report.h"
#include "sysemu/sysemu.h"
#include "exec/gdbstub.h"
#include "sysemu/dma.h"
/* Protected by TimersState seqlock */
+static bool icount_sleep = true;
static int64_t vm_clock_warp_start = -1;
/* Conversion factor from emulated instructions to virtual clock ticks. */
static int icount_time_shift;
icount = timers_state.qemu_icount;
if (cpu) {
- if (!cpu_can_do_io(cpu)) {
+ if (!cpu->can_do_io) {
fprintf(stderr, "Bad icount read\n");
exit(1);
}
return;
}
- /*
- * If the CPUs have been sleeping, advance QEMU_CLOCK_VIRTUAL timer now.
- * This ensures that the deadline for the timer is computed correctly below.
- * This also makes sure that the insn counter is synchronized before the
- * CPU starts running, in case the CPU is woken by an event other than
- * the earliest QEMU_CLOCK_VIRTUAL timer.
- */
- icount_warp_rt(NULL);
- timer_del(icount_warp_timer);
+ if (icount_sleep) {
+ /*
+ * If the CPUs have been sleeping, advance QEMU_CLOCK_VIRTUAL timer now.
+ * This ensures that the deadline for the timer is computed correctly
+ * below.
+ * This also makes sure that the insn counter is synchronized before
+ * the CPU starts running, in case the CPU is woken by an event other
+ * than the earliest QEMU_CLOCK_VIRTUAL timer.
+ */
+ icount_warp_rt(NULL);
+ timer_del(icount_warp_timer);
+ }
if (!all_cpu_threads_idle()) {
return;
}
clock = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL_RT);
deadline = qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL);
if (deadline < 0) {
+ static bool notified;
+ if (!icount_sleep && !notified) {
+ error_report("WARNING: icount sleep disabled and no active timers");
+ notified = true;
+ }
return;
}
* interrupt to wake it up, but the interrupt never comes because
* the vCPU isn't running any insns and thus doesn't advance the
* QEMU_CLOCK_VIRTUAL.
- *
- * An extreme solution for this problem would be to never let VCPUs
- * sleep in icount mode if there is a pending QEMU_CLOCK_VIRTUAL
- * timer; rather time could just advance to the next QEMU_CLOCK_VIRTUAL
- * event. Instead, we do stop VCPUs and only advance QEMU_CLOCK_VIRTUAL
- * after some "real" time, (related to the time left until the next
- * event) has passed. The QEMU_CLOCK_VIRTUAL_RT clock will do this.
- * This avoids that the warps are visible externally; for example,
- * you will not be sending network packets continuously instead of
- * every 100ms.
*/
- seqlock_write_lock(&timers_state.vm_clock_seqlock);
- if (vm_clock_warp_start == -1 || vm_clock_warp_start > clock) {
- vm_clock_warp_start = clock;
+ if (!icount_sleep) {
+ /*
+ * We never let VCPUs sleep in no sleep icount mode.
+ * If there is a pending QEMU_CLOCK_VIRTUAL timer we just advance
+ * to the next QEMU_CLOCK_VIRTUAL event and notify it.
+ * It is useful when we want a deterministic execution time,
+ * isolated from host latencies.
+ */
+ seqlock_write_lock(&timers_state.vm_clock_seqlock);
+ timers_state.qemu_icount_bias += deadline;
+ seqlock_write_unlock(&timers_state.vm_clock_seqlock);
+ qemu_clock_notify(QEMU_CLOCK_VIRTUAL);
+ } else {
+ /*
+ * We do stop VCPUs and only advance QEMU_CLOCK_VIRTUAL after some
+ * "real" time, (related to the time left until the next event) has
+ * passed. The QEMU_CLOCK_VIRTUAL_RT clock will do this.
+ * This avoids that the warps are visible externally; for example,
+ * you will not be sending network packets continuously instead of
+ * every 100ms.
+ */
+ seqlock_write_lock(&timers_state.vm_clock_seqlock);
+ if (vm_clock_warp_start == -1 || vm_clock_warp_start > clock) {
+ vm_clock_warp_start = clock;
+ }
+ seqlock_write_unlock(&timers_state.vm_clock_seqlock);
+ timer_mod_anticipate(icount_warp_timer, clock + deadline);
}
- seqlock_write_unlock(&timers_state.vm_clock_seqlock);
- timer_mod_anticipate(icount_warp_timer, clock + deadline);
} else if (deadline == 0) {
qemu_clock_notify(QEMU_CLOCK_VIRTUAL);
}
.name = "timer/icount",
.version_id = 1,
.minimum_version_id = 1,
+ .needed = icount_state_needed,
.fields = (VMStateField[]) {
VMSTATE_INT64(qemu_icount_bias, TimersState),
VMSTATE_INT64(qemu_icount, TimersState),
VMSTATE_INT64_V(cpu_clock_offset, TimersState, 2),
VMSTATE_END_OF_LIST()
},
- .subsections = (VMStateSubsection[]) {
- {
- .vmsd = &icount_vmstate_timers,
- .needed = icount_state_needed,
- }, {
- /* empty */
- }
+ .subsections = (const VMStateDescription*[]) {
+ &icount_vmstate_timers,
+ NULL
}
};
}
return;
}
+
+ icount_sleep = qemu_opt_get_bool(opts, "sleep", true);
+ if (icount_sleep) {
+ icount_warp_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL_RT,
+ icount_warp_rt, NULL);
+ }
+
icount_align_option = qemu_opt_get_bool(opts, "align", false);
- icount_warp_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL_RT,
- icount_warp_rt, NULL);
+
+ if (icount_align_option && !icount_sleep) {
+ error_setg(errp, "align=on and sleep=no are incompatible");
+ }
if (strcmp(option, "auto") != 0) {
errno = 0;
icount_time_shift = strtol(option, &rem_str, 0);
return;
} else if (icount_align_option) {
error_setg(errp, "shift=auto and align=on are incompatible");
+ } else if (!icount_sleep) {
+ error_setg(errp, "shift=auto and sleep=no are incompatible");
}
use_icount = 2;
cpu->stopped = true;
}
-static void cpu_signal(int sig)
-{
- if (current_cpu) {
- cpu_exit(current_cpu);
- }
- exit_request = 1;
-}
-
#ifdef CONFIG_LINUX
static void sigbus_reraise(void)
{
}
}
-static void qemu_tcg_init_cpu_signals(void)
-{
- 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);
-}
-
#else /* _WIN32 */
static void qemu_kvm_init_cpu_signals(CPUState *cpu)
{
abort();
}
-
-static void qemu_tcg_init_cpu_signals(void)
-{
-}
#endif /* _WIN32 */
static QemuMutex qemu_global_mutex;
static QemuThread io_thread;
-static QemuThread *tcg_cpu_thread;
-static QemuCond *tcg_halt_cond;
-
/* cpu creation */
static QemuCond qemu_cpu_cond;
/* system init */
wi.func = func;
wi.data = data;
wi.free = false;
+
+ qemu_mutex_lock(&cpu->work_mutex);
if (cpu->queued_work_first == NULL) {
cpu->queued_work_first = &wi;
} else {
cpu->queued_work_last = &wi;
wi.next = NULL;
wi.done = false;
+ qemu_mutex_unlock(&cpu->work_mutex);
qemu_cpu_kick(cpu);
- while (!wi.done) {
+ while (!atomic_mb_read(&wi.done)) {
CPUState *self_cpu = current_cpu;
qemu_cond_wait(&qemu_work_cond, &qemu_global_mutex);
wi->func = func;
wi->data = data;
wi->free = true;
+
+ qemu_mutex_lock(&cpu->work_mutex);
if (cpu->queued_work_first == NULL) {
cpu->queued_work_first = wi;
} else {
cpu->queued_work_last = wi;
wi->next = NULL;
wi->done = false;
+ qemu_mutex_unlock(&cpu->work_mutex);
qemu_cpu_kick(cpu);
}
return;
}
- while ((wi = cpu->queued_work_first)) {
+ qemu_mutex_lock(&cpu->work_mutex);
+ while (cpu->queued_work_first != NULL) {
+ wi = cpu->queued_work_first;
cpu->queued_work_first = wi->next;
+ if (!cpu->queued_work_first) {
+ cpu->queued_work_last = NULL;
+ }
+ qemu_mutex_unlock(&cpu->work_mutex);
wi->func(wi->data);
- wi->done = true;
+ qemu_mutex_lock(&cpu->work_mutex);
if (wi->free) {
g_free(wi);
+ } else {
+ atomic_mb_set(&wi->done, true);
}
}
- cpu->queued_work_last = NULL;
+ qemu_mutex_unlock(&cpu->work_mutex);
qemu_cond_broadcast(&qemu_work_cond);
}
cpu->thread_kicked = false;
}
-static void qemu_tcg_wait_io_event(void)
+static void qemu_tcg_wait_io_event(CPUState *cpu)
{
- CPUState *cpu;
-
while (all_cpu_threads_idle()) {
/* Start accounting real time to the virtual clock if the CPUs
are idle. */
qemu_clock_warp(QEMU_CLOCK_VIRTUAL);
- qemu_cond_wait(tcg_halt_cond, &qemu_global_mutex);
+ qemu_cond_wait(cpu->halt_cond, &qemu_global_mutex);
}
while (iothread_requesting_mutex) {
CPUState *cpu = arg;
int r;
- qemu_mutex_lock(&qemu_global_mutex);
+ rcu_register_thread();
+
+ qemu_mutex_lock_iothread();
qemu_thread_get_self(cpu->thread);
cpu->thread_id = qemu_get_thread_id();
cpu->can_do_io = 1;
sigset_t waitset;
int r;
+ rcu_register_thread();
+
qemu_mutex_lock_iothread();
qemu_thread_get_self(cpu->thread);
cpu->thread_id = qemu_get_thread_id();
{
CPUState *cpu = arg;
- qemu_tcg_init_cpu_signals();
+ rcu_register_thread();
+
+ qemu_mutex_lock_iothread();
qemu_thread_get_self(cpu->thread);
- qemu_mutex_lock(&qemu_global_mutex);
CPU_FOREACH(cpu) {
cpu->thread_id = qemu_get_thread_id();
cpu->created = true;
qemu_cond_signal(&qemu_cpu_cond);
/* wait for initial kick-off after machine start */
- while (QTAILQ_FIRST(&cpus)->stopped) {
- qemu_cond_wait(tcg_halt_cond, &qemu_global_mutex);
+ while (first_cpu->stopped) {
+ qemu_cond_wait(first_cpu->halt_cond, &qemu_global_mutex);
/* process any pending work */
CPU_FOREACH(cpu) {
}
/* process any pending work */
- exit_request = 1;
+ atomic_mb_set(&exit_request, 1);
while (1) {
tcg_exec_all();
qemu_clock_notify(QEMU_CLOCK_VIRTUAL);
}
}
- qemu_tcg_wait_io_event();
+ qemu_tcg_wait_io_event(QTAILQ_FIRST(&cpus));
}
return NULL;
#ifndef _WIN32
int err;
+ if (cpu->thread_kicked) {
+ return;
+ }
+ cpu->thread_kicked = true;
err = pthread_kill(cpu->thread->thread, SIG_IPI);
if (err) {
fprintf(stderr, "qemu:%s: %s", __func__, strerror(err));
exit(1);
}
#else /* _WIN32 */
- if (!qemu_cpu_is_self(cpu)) {
- CONTEXT tcgContext;
-
- if (SuspendThread(cpu->hThread) == (DWORD)-1) {
- fprintf(stderr, "qemu:%s: GetLastError:%lu\n", __func__,
- GetLastError());
- exit(1);
- }
-
- /* On multi-core systems, we are not sure that the thread is actually
- * suspended until we can get the context.
- */
- tcgContext.ContextFlags = CONTEXT_CONTROL;
- while (GetThreadContext(cpu->hThread, &tcgContext) != 0) {
- continue;
- }
-
- cpu_signal(0);
+ abort();
+#endif
+}
- if (ResumeThread(cpu->hThread) == (DWORD)-1) {
- fprintf(stderr, "qemu:%s: GetLastError:%lu\n", __func__,
- GetLastError());
- exit(1);
- }
+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);
}
-#endif
}
void qemu_cpu_kick(CPUState *cpu)
{
qemu_cond_broadcast(cpu->halt_cond);
- if (!tcg_enabled() && !cpu->thread_kicked) {
+ if (tcg_enabled()) {
+ qemu_cpu_kick_no_halt();
+ } else {
qemu_cpu_kick_thread(cpu);
- cpu->thread_kicked = true;
}
}
void qemu_cpu_kick_self(void)
{
-#ifndef _WIN32
assert(current_cpu);
-
- if (!current_cpu->thread_kicked) {
- qemu_cpu_kick_thread(current_cpu);
- current_cpu->thread_kicked = true;
- }
-#else
- abort();
-#endif
+ qemu_cpu_kick_thread(current_cpu);
}
bool qemu_cpu_is_self(CPUState *cpu)
return current_cpu && qemu_cpu_is_self(current_cpu);
}
+static __thread bool iothread_locked = false;
+
+bool qemu_mutex_iothread_locked(void)
+{
+ return iothread_locked;
+}
+
void qemu_mutex_lock_iothread(void)
{
atomic_inc(&iothread_requesting_mutex);
- if (!tcg_enabled() || !first_cpu) {
+ /* 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_thread(first_cpu);
+ qemu_cpu_kick_no_halt();
qemu_mutex_lock(&qemu_global_mutex);
}
atomic_dec(&iothread_requesting_mutex);
qemu_cond_broadcast(&qemu_io_proceeded_cond);
}
+ iothread_locked = true;
}
void qemu_mutex_unlock_iothread(void)
{
+ iothread_locked = false;
qemu_mutex_unlock(&qemu_global_mutex);
}
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;
tcg_cpu_address_space_init(cpu, cpu->as);
}
}
-static int tcg_cpu_exec(CPUArchState *env)
+static int tcg_cpu_exec(CPUState *cpu)
{
- CPUState *cpu = ENV_GET_CPU(env);
int ret;
#ifdef CONFIG_PROFILER
int64_t ti;
cpu->icount_decr.u16.low = decr;
cpu->icount_extra = count;
}
- ret = cpu_exec(env);
+ ret = cpu_exec(cpu);
#ifdef CONFIG_PROFILER
tcg_time += profile_getclock() - ti;
#endif
}
for (; next_cpu != NULL && !exit_request; next_cpu = CPU_NEXT(next_cpu)) {
CPUState *cpu = next_cpu;
- CPUArchState *env = cpu->env_ptr;
qemu_clock_enable(QEMU_CLOCK_VIRTUAL,
(cpu->singlestep_enabled & SSTEP_NOTIMER) == 0);
if (cpu_can_run(cpu)) {
- r = tcg_cpu_exec(env);
+ r = tcg_cpu_exec(cpu);
if (r == EXCP_DEBUG) {
cpu_handle_guest_debug(cpu);
break;
break;
}
}
- exit_request = 0;
+
+ /* Pairs with smp_wmb in qemu_cpu_kick. */
+ atomic_mb_set(&exit_request, 0);
}
void list_cpus(FILE *f, fprintf_function cpu_fprintf, const char *optarg)
info->value->CPU = cpu->cpu_index;
info->value->current = (cpu == first_cpu);
info->value->halted = cpu->halted;
+ info->value->qom_path = object_get_canonical_path(OBJECT(cpu));
info->value->thread_id = cpu->thread_id;
#if defined(TARGET_I386)
info->value->has_pc = true;
cpu = qemu_get_cpu(cpu_index);
if (cpu == NULL) {
- error_set(errp, QERR_INVALID_PARAMETER_VALUE, "cpu-index",
- "a CPU number");
+ error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "cpu-index",
+ "a CPU number");
return;
}
goto exit;
}
if (fwrite(buf, 1, l, f) != l) {
- error_set(errp, QERR_IO_ERROR);
+ error_setg(errp, QERR_IO_ERROR);
goto exit;
}
addr += l;
l = size;
cpu_physical_memory_read(addr, buf, l);
if (fwrite(buf, 1, l, f) != l) {
- error_set(errp, QERR_IO_ERROR);
+ error_setg(errp, QERR_IO_ERROR);
goto exit;
}
addr += l;