On 2012-06-21 16:49, Liu Ping Fan wrote: > In order to break the big lock, using per-cpu_lock in kvm_cpu_exec() > to protect the race from other cpu's access to env->apic_state & related > field in env. > Also, we need to protect agaist run_on_cpu(). > > Race condition can be like this: > 1. vcpu-1 IPI vcpu-2 > vcpu-3 IPI vcpu-2 > Open window exists for accessing to vcpu-2's apic_state & env > > 2. run_on_cpu() write env->queued_work_last, while flush_queued_work() > read >
How much of this is still relevant with the (nowadays default-on) in-kernel irqchips? Jan -- Siemens AG, Corporate Technology, CT T DE IT 1 Corporate Competence Center Embedded Linux