Re: [RFC PATCH 01/17] shm-signal: shared-memory signals

[Gregory Haskins]

Avi Kivity wrote:
> Gregory Haskins wrote:
>>>> +struct shm_signal_irq {
>>>> +    __u8                  enabled;
>>>> +    __u8                  pending;
>>>> +    __u8                  dirty;
>>>> +};
>>>>         
>>> Some ABIs may choose to pad this, suggest explicit padding.
>>>     
>>
>> Yeah, good idea.  What is the official way to do this these days?  Are
>> GCC pragmas allowed?
>>
>>   
>
> I just add a __u8 pad[5] in such cases.

Oh, duh.  Dumb question.  I was getting confused with "pack", not pad.  :)

>
>>>> +
>>>> +struct shm_signal;
>>>> +
>>>> +struct shm_signal_ops {
>>>> +    int      (*inject)(struct shm_signal *s);
>>>> +    void     (*fault)(struct shm_signal *s, const char *fmt, ...);
>>>>         
>>> Eww.  Must we involve strings and printf formats?
>>>     
>>
>> This is still somewhat of a immature part of the design.  Its supposed
>> to be used so that by default, its a panic.  But on the host side, we
>> can do something like inject a machine-check.  That way malicious/broken
>> guests cannot (should not? ;) be able to take down the host.  Note today
>> I do not map this to anything other than the default panic, so this
>> needs some love.
>>
>> But given the asynchronous nature of the fault, I want to be sure we
>> have decent accounting to avoid bug reports like "silent MCE kills the
>> guest" ;)  At least this way, we can log the fault string somewhere to
>> get a clue.
>>   
>
> I see.
>
> This raises a point I've been thinking of - the symmetrical nature of
> the API vs the assymetrical nature of guest/host or user/kernel
> interfaces.  This is most pronounced in ->inject(); in the host->guest
> direction this is async (host can continue processing while the guest
> is handling the interrupt), whereas in the guest->host direction it is
> synchronous (the guest is blocked while the host is processing the
> call, unless the host explicitly hands off work to a different thread).

Note that this is exactly what I do (though it is device specific). 
venet-tap has a ioq_notifier registered on its "rx" ring (which is the
tx-ring for the guest) that simply calls ioq_notify_disable() (which
calls shm_signal_disable() under the covers) and it wakes its
rx-thread.  This all happens in the context of the hypercall, which then
returns and allows the vcpu to re-enter guest mode immediately.


>
>

Attachment: signature.asc
Description: OpenPGP digital signature