Re: [PATCH V2 7/8] vfio/pci: Support dynamic MSI-x

[Reinette Chatre]

Hi Alex,

On 4/4/2023 11:24 AM, Alex Williamson wrote:

> We're talking about the contexts that we now allocate in the xarray to
> store the eventfd linkage, right?  We need to pre-allocate some irqs
> both to satisfy the API and to support non-dynamic MSI-X devices, but
> we don't need to pre-allocate contexts.  The logic that I propose below
> supports lookup of the pre-allocated irqs for all cases and falls back
> to allocating a new irq only for cases that support it.  irqs and
> contexts aren't exactly 1:1 for the dynamic case due to the artifacts
> of the API, but the model supports only allocating contexts as they're
> used, or "active".

Now I understand. Thank you very much for your patience.

...

> Interrupts and contexts allocated together would be ideal, but I think
> given the API it's a reasonable and simple compromise given the
> non-dynamic support to draw from the initial allocation where we can.
> Actually, there could be a latency and reliability advantage to hang on
> to the irq when an eventfd is unset, maybe we should only free irqs on
> MSI-X teardown and otherwise use the allocated irqs as a cache.  Maybe
> worth thinking about.  Thanks,

I implemented this change and I think it looks good. Enabling of dynamic
MSI-X ended up consisting out of vfio_pci_alloc_irq() you suggested and
one more line that uses it. This is because I also made the change to
defer freeing irqs to MSI-X teardown and doing so is surely more efficient
in the scenario that Jing pointed out.

I did not transition the INTx code to "active" contexts - meaning that
the interrupt context continues to be allocated at the time INTx is
enabled. From what I understand the additional support for mask/unmask
requires a context but it does not need to be active.

Reinette