内核进行进程切换时，先调用了__schedule，在关抢占后调用context_switch：
static void __sched __schedule(void)
{
struct task_struct *prev, *next;
unsigned long *switch_count;
struct rq *rq;
int cpu;
need_resched:
preempt_disable();
cpu = smp_processor_id();
rq = cpu_rq(cpu);
...
raw_spin_lock_irq(&rq->lock);
...
context_switch(rq, prev, next);
...
sched_preempt_enable_no_resched();
static inline void
context_switch(struct rq *rq, struct task_struct *prev,
struct task_struct *next)
{
struct mm_struct *mm, *oldmm;
prepare_task_switch(rq, prev, next);
mm = next->mm;
oldmm = prev->active_mm;
…
finish_task_switch(this_rq(), prev);
prepare_task_switch里面调用fire_sched_out_preempt_notifiers，进而调用prev进程注册的sched_out操作，
static inline void
prepare_task_switch(struct rq *rq, struct task_struct *prev,
struct task_struct *next)
{
trace_sched_switch(prev, next);
sched_info_switch(prev, next);
perf_event_task_sched_out(prev, next);
fire_sched_out_preempt_notifiers(prev, next);
prepare_lock_switch(rq, next);
prepare_arch_switch(next);
}
这里是分支：如果是新创建的进程被调度了，要调用schedule_tail：
/**
* schedule_tail - first thing a freshly forked thread must call.
* @prev: the thread we just switched away from.
*/
asmlinkage void schedule_tail(struct task_struct *prev)
__releases(rq->lock)
{
struct rq *rq = this_rq();
finish_task_switch(rq, prev);
/*
* FIXME: do we need to worry about rq being invalidated by the
* task_switch?
*/
post_schedule(rq);
#ifdef __ARCH_WANT_UNLOCKED_CTXSW
/* In this case, finish_task_switch does not reenable preemption */
preempt_enable();
#endif
if (current->set_child_tid)
put_user(task_pid_vnr(current), current->set_child_tid);
}
回到主题：finish_task_switch这里会调用fire_sched_in_preempt_notifiers:
static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
{
struct preempt_notifier *notifier;
hlist_for_each_entry(notifier, &curr->preempt_notifiers, link)
notifier->ops->sched_in(notifier, raw_smp_processor_id());
}
preempt_notifiers在哪里注册的呢，对kvm来说是这里：
static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
{
int r;
struct kvm_vcpu *vcpu, *v;
if (id >= KVM_MAX_VCPUS)
return -EINVAL;
vcpu = kvm_arch_vcpu_create(kvm, id);
if (IS_ERR(vcpu))
return PTR_ERR(vcpu);
preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops);
r = kvm_arch_vcpu_setup(vcpu);
kvm模块加载的时候vmx_init->kvm_init里面初始化了kvm_preempt_ops
kvm_preempt_ops.sched_in = kvm_sched_in; kvm_preempt_ops.sched_out = kvm_sched_out;
所以kvm_sched_in和kvm_sched_out被调用时的上下文是关抢占的