On 22/04/20 02:48, Wanpeng Li wrote:
> On Tue, 21 Apr 2020 at 19:37, Paolo Bonzini <pbonzini@xxxxxxxxxx> wrote:
>> On 21/04/20 13:20, Wanpeng Li wrote:
>>> + case MSR_IA32_TSCDEADLINE:
>>> + if (!kvm_x86_ops.event_needs_reinjection(vcpu)) {
>>> + data = kvm_read_edx_eax(vcpu);
>>> + if (!handle_fastpath_set_tscdeadline(vcpu, data))
>>> + ret = EXIT_FASTPATH_CONT_RUN;
>>> + }
>>> break;
>> Can you explain the event_needs_reinjection case? Also, does this break
> This is used to catch the case vmexit occurred while another event was
> being delivered to guest software, I move the
> vmx_exit_handlers_fastpath() call after vmx_complete_interrupts()
> which will decode such event and make kvm_event_needs_reinjection
> return true.
This doesn't need a callback, kvm_event_needs_reinjection should be enough.
You should also check other conditions such as
vcpu->mode == EXITING_GUEST_MODE || kvm_request_pending(vcpu)
|| need_resched() || signal_pending(current)
before doing CONT_RUN.
>> AMD which does not implement the callback?
> Now I add the tscdeadline msr emulation and vmx-preemption timer
> fastpath pair for Intel platform.
But this would cause a crash if you run on AMD.
Paolo
