On 12.08.2012, at 11:24, Avi Kivity wrote:
> On 08/09/2012 08:02 PM, Alexander Graf wrote:
>>
>>
>> On 09.08.2012, at 12:36, Avi Kivity <avi@xxxxxxxxxx> wrote:
>>
>>> On 08/09/2012 01:34 PM, Takuya Yoshikawa wrote:
>>>> On Tue, 7 Aug 2012 12:57:13 +0200
>>>> Alexander Graf <agraf@xxxxxxx> wrote:
>>>>
>>>>> +struct kvm_memory_slot *hva_to_memslot(struct kvm *kvm, hva_t hva)
>>>>> +{
>>>>> + struct kvm_memslots *slots = kvm_memslots(kvm);
>>>>> + struct kvm_memory_slot *memslot;
>>>>> +
>>>>> + kvm_for_each_memslot(memslot, slots)
>>>>> + if (hva >= memslot->userspace_addr &&
>>>>> + hva < memslot->userspace_addr + memslot->npages)
>>>>> + return memslot;
>>>>> +
>>>>> + return NULL;
>>>>> +}
>>>>
>>>> Can't we have two memory slots which contain that hva?
>>>> I thought that's why hva handler had to check all slots.
>>>
>>> We can and do. Good catch.
>>>
>>
>> Hrm. So I guess we can only do an hva_is_guest_memory() helper? That's all I really need anyways :)
>>
>
> How about kvm_for_each_memslot_hva_range()? That can useful in
> kvm_handle_hva_range(). For your use case, you just do you stuff and
> return immediately.
Well, for now I just dropped the whole thing. In general, chances are pretty good that an HVA we get notified on with mmu notifiers is representing guest memory. And flushing a few times too often shouldn't hurt.
Alex
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
