Messages in this thread | | | Subject | Re: [RESEND] ACPI / processor_idle: use dead loop instead of io port access for wait | From | "Yin, Fengwei" <> | Date | Tue, 15 Oct 2019 16:03:13 +0800 |
| |
On 10/14/2019 5:38 PM, Rafael J. Wysocki wrote: > On Friday, October 11, 2019 3:30:41 PM CEST Yin, Fengwei wrote: >> >> On 10/11/2019 5:05 PM, Rafael J. Wysocki wrote: >>> Sorry for the delay. >> No problem. >> >>> >>> On Monday, September 9, 2019 9:39:37 AM CEST Yin Fengwei wrote: >>>> In function acpi_idle_do_entry(), we do an io port access to guarantee >>>> hardware behavior. But it could trigger unnecessary vmexit for >>>> virtualization environemnt. >>> >>> Is this a theoretical problem, or do you actually see it? >>> >>> If you see it, I'd like to have a pointer to a bug report regarding it >>> or similar. >> We did see this issue when we run linux as guest with ACRN hypervisor >> instead of kvm or xen. In our case, we export all native C states to >> guest and let guest choose which C state it will enter. >> >> And we observed many pm timer port access when guest tried to enter >> deeper C state (Yes, we emulate pm timer so pm timer access will trigger >> vmexit). > > Can you please put this information into the changelog of your patch? I added this information to the patch commit message and sent out v2. Thanks a lot for reviewing and comments.
Regards Yin, Fengwei
> > It works very well as a rationale for me. :-) > > >
| |