Re: [PATCH 2/2] KVM MMU: fix race in invlpg code

[Avi Kivity <avi@redhat.com>]

On 05/05/2010 03:45 PM, Xiao Guangrong wrote:
>
> Avi Kivity wrote:
>
>    
>>>        spin_lock(&vcpu->kvm->mmu_lock);
>>> +    index = kvm_page_table_hashfn(gfn);
>>> +    bucket =&vcpu->kvm->arch.mmu_page_hash[index];
>>> +    hlist_for_each_entry_safe(s, node, tmp, bucket, hash_link)
>>> +        if (s == sp) {
>>> +            if (s->gfn == gfn&&   s->role.word == role.word)
>>> +                live = true;
>>> +            break;
>>> +        }
>>> +
>>> +    if (!live)
>>> +        goto unlock_exit;
>>> +
>>>
>>>        
>> Did you try the root_count method?  I think it's cleaner.
>>      
> Avi, Thanks for your idea.
>
> I have considered this method, but i'm not sure when it's the good time
> to real free this page, and i think we also need a way to synchronize the
> real free path and this path. Do you have any comment for it :-(
>    

Same as mmu_free_roots():

         --sp->root_count;
         if (!sp->root_count && sp->role.invalid) {
                 kvm_mmu_zap_page(vcpu->kvm, sp);
                 goto unlock_exit;
         }


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