Re: [PATCH V6 6/6] kvm: add fast mmio capabilitiy

[Paolo Bonzini <pbonzini@redhat.com>]

On 15/09/2015 18:13, Cornelia Huck wrote:
> On Tue, 15 Sep 2015 17:07:55 +0200
> Paolo Bonzini <pbonzini@redhat.com> wrote:
> 
>> On 15/09/2015 08:41, Jason Wang wrote:
>>> +With KVM_CAP_FAST_MMIO, a zero length mmio eventfd is allowed for
>>> +kernel to ignore the length of guest write and get a possible faster
>>> +response. Note the speedup may only work on some specific
>>> +architectures and setups. Otherwise, it's as fast as wildcard mmio
>>> +eventfd.
>>
>> I don't really like tying the capability to MMIO, especially since
>> zero length ioeventfd is already accepted for virtio-ccw.
> 
> Actually, zero length ioeventfd does not make sense for virtio-ccw;

Can you explain why?  If there is any non-zero valid length, "wildcard
length" (represented by zero) would also make sense.

Paolo

> we just don't check it (although we probably should).
> 
>>
>> What about the following?
>>
>> diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
>> index 7a3cb48a644d..247944071cc8 100644
>> --- a/Documentation/virtual/kvm/api.txt
>> +++ b/Documentation/virtual/kvm/api.txt
>> @@ -1627,11 +1627,10 @@ to the registered address is equal to datamatch in struct kvm_ioeventfd.
>>  For virtio-ccw devices, addr contains the subchannel id and datamatch the
>>  virtqueue index.
>>
>> -With KVM_CAP_FAST_MMIO, a zero length mmio eventfd is allowed for
>> -kernel to ignore the length of guest write and get a possible faster
>> -response. Note the speedup may only work on some specific
>> -architectures and setups. Otherwise, it's as fast as wildcard mmio
>> -eventfd.
>> +With KVM_CAP_IOEVENTFD_ANY_LENGTH, a zero length ioeventfd is allowed, and
>> +the kernel will ignore the length of guest write and get a faster vmexit.
> 
> s/get/may get/ ?
> 
>> +The speedup may only apply to specific architectures, but the ioeventfd will
>> +work anyway.
>