Hi Paolo: Thanks for your review. Sorry for later response due to holiday. On Mon, Oct 1, 2018 at 11:26 PM Paolo Bonzini <pbonzini@xxxxxxxxxx> wrote: > > On 27/09/2018 05:48, Tianyu Lan wrote: > > + > > + if (range && kvm_x86_ops->tlb_remote_flush_with_range) { > > + /* > > + * Read tlbs_dirty before flushing tlbs in order > > + * to track dirty tlbs during flushing. > > + */ > > + long dirty_count = smp_load_acquire(&kvm->tlbs_dirty); > > + > > + ret = kvm_x86_ops->tlb_remote_flush_with_range(kvm, range); > > + cmpxchg(&kvm->tlbs_dirty, dirty_count, 0); > > This is wrong, because it's not the entire TLB that is flushed. So you > cannot do the cmpxchg here. Yes, nice catch. Will update in the next version. -- Best regards Tianyu Lan _______________________________________________ devel mailing list devel@xxxxxxxxxxxxxxxxxxxxxx http://driverdev.linuxdriverproject.org/mailman/listinfo/driverdev-devel