Re: [PATCH v2 19/22] KVM: MMU: lockless walking shadow page table

[Avi Kivity <avi@redhat.com>]

On 06/29/2011 02:16 PM, Xiao Guangrong wrote:
> >>  @@ -1767,6 +1874,14 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm,
> >>
> >>        kvm_flush_remote_tlbs(kvm);
> >>
> >>  +    if (atomic_read(&kvm->arch.reader_counter)) {
> >>  +        kvm_mmu_isolate_pages(invalid_list);
> >>  +        sp = list_first_entry(invalid_list, struct kvm_mmu_page, link);
> >>  +        list_del_init(invalid_list);
> >>  +        call_rcu(&sp->rcu, free_pages_rcu);
> >>  +        return;
> >>  +    }
> >>  +
> >
> >  I think we should do this unconditionally.  The cost of ping-ponging the shared cache line containing reader_counter will increase with large smp counts.  On the other hand, zap_page is very rare, so it can be a little slower.  Also, less code paths = easier to understand.
> >
>
> On soft mmu, zap_page is very frequently, it can cause performance regression in my test.

Any idea what the cause of the regression is?  It seems to me that 
simply deferring freeing shouldn't have a large impact.

-- 
error compiling committee.c: too many arguments to function