Re: [RFC PATCH] dpci: Put the dpci back on the list if running on another CPU.

From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
To: Jan Beulich <JBeulich@suse.com>
Cc: andrew.cooper3@citrix.com, malcolm.crossley@citrix.com,
	xen-devel@lists.xenproject.org, linux@eikelenboom.it
Subject: Re: [RFC PATCH] dpci: Put the dpci back on the list if running on another CPU.
Date: Wed, 18 Mar 2015 10:06:35 -0400	[thread overview]
Message-ID: <20150318140635.GD13965@x230.dumpdata.com> (raw)
In-Reply-To: <55093A53020000780006B1D8@mail.emea.novell.com>

On Wed, Mar 18, 2015 at 07:41:55AM +0000, Jan Beulich wrote:
> >>> On 17.03.15 at 18:44, <konrad.wilk@oracle.com> wrote:
> > As you can see to preserve the existing functionality such as
> > being able to schedule N amount of interrupt injections
> > for the N interrupts we might get - I modified '->masked'
> > to be an atomic counter.
> 
> Why would that be? When an earlier interrupt wasn't fully handled,
> real hardware wouldn't latch more than one further instance either.

We acknowledge the interrupt in the hypervisor - as in we call
->ack on the handler (which for MSI is an nop anyhow).

If the device is misconfigured and keeps on sending burst of
interrupts every 10 msec for 1msec we can dead-lock.

Either way we should tell the guest about those interrupts.
> 
> > The end result is that we can still live-lock. Unless we:
> >  - Drop on the floor the injection of N interrupts and
> >    just deliever at max one per VMX_EXIT (and not bother
> >    with interrupts arriving when we are in the VMX handler).
> 
> I'm afraid I again don't see the point here.

I am basing all of this on the assumption that we have
many interrupts for the same device coming it - and we have
not been able to tell the guest about it (the guest could
be descheduled, too slow, etc) so that it can do what it
needs to silence the device.

It might be very well an busted device - and if that is
the case be that - but we must not dead-lock due to it.
> 
> >  - Alter the softirq code slightly - to have an variant
> >    which will only iterate once over the pending softirq
> >    bits per call. (so save an copy of the bitmap on the
> >    stack when entering the softirq handler - and use that.
> >    We could also xor it against the current to catch any
> >    non-duplicate bits being set that we should deal with).
> 
> That's clearly not an option: The solution should be isolated
> to DPCI code, i.e. without altering existing behavior in other
> (more generic) components.
> 
> Jan
> 