On Fri, May 18, 2018 at 11:41:23AM +0200, Paolo Bonzini wrote: > On 17/05/2018 20:46, Eduardo Habkost wrote: > > My understanding of the original patch is that the intention is > > to tell the guest that it is very unlikely to be preempted, so it > > can choose a more appropriate spinlock implementation. This > > description implies that the guest will never be preempted, which > > is much stronger guarantee. > > > > Isn't this new description incompatible with existing usage of > > the hint, which might include people who just use vCPU pinning > > but no mlock? > > If you use hugetlbfs and vhost-user you don't really need mlock for the > QEMU process, do you? The QEMU process is not doing much in that case > and hugetlbfs gives you pinned memory automatically. > > Paolo
Same with PCI device passthrough: VFIO pins all guest memory right now. -- MST
