Hi Marc, On Mon, May 9, 2022 at 11:41 AM Marc Zyngier <maz@xxxxxxxxxx> wrote: > > On Mon, 09 May 2022 10:54:59 +0100, > Fuad Tabba <tabba@xxxxxxxxxx> wrote: > > > > Instead of the host accessing hyp data directly, pass the pmu > > events of the current cpu to hyp via the vcpu. > > > > This adds 64 bits (in two fields) to the vcpu that need to be > > synced before every vcpu run in nvhe and protected modes. > > However, it isolates the hypervisor from the host, which allows > > us to use pmu in protected mode in a subsequent patch. > > > > No functional change intended. > > BTW, there *are* plenty of functional changes, even if there was no > issue with the patch. The lifetime of the data structure changes, its > sharing changes, and its memory footprint is different. > > I guess what you are trying to say is that there shouldn't be any > visible side effect of this patch. But I don't think these are the > same things. Always thought that in this context functional == functionality. Will make it clearer in the next commit message that there should be no visible side effect changes instead. Thanks, /fuad > > Thanks, > > M. > > -- > Without deviation from the norm, progress is not possible. _______________________________________________ kvmarm mailing list kvmarm@xxxxxxxxxxxxxxxxxxxxx https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
