Re: [PATCH 2/2] uio: new driver to support PCI MSI-X

[Thomas Monjalon <thomas.monjalon@6wind.com>]

To sum it up,
We want to remove the need of the out-of-tree module igb_uio.
3 possible implementations were discussed so far:
- new UIO driver
- extend uio_pci_generic
- VFIO without IOMMU

It is preferred to avoid creating yet another module to support.
That's why the uio_pci_generic extension would be nice.
In my understanding, there are currently 2 issues with the patches
from Vlad and Stephen:
- IRQ must be mapped to a fd without using a new ioctl
- MSI-X handling in userspace breaks the memory protection

I'm confident the first issue can be fixed with something like sysfs.
About the "security" concern, mainly expressed by MST, I think the idea
of Avi (below) deserves to be discussed.

2015-10-06 15:15, Avi Kivity:
> On 10/06/2015 10:33 AM, Stephen Hemminger wrote:
> > Other than implementation objections, so far the two main arguments
> > against this reduce to:
> >    1. If you allow UIO ioctl then it opens an API hook for all the crap out
> >       of tree UIO drivers to do what they want.
> >    2. If you allow UIO MSI-X then you are expanding the usage of userspace
> >       device access in an insecure manner.
[...]
> btw, (2) doesn't really add any insecurity.  The user could already poke 
> at the msix tables (as well as perform DMA); they just couldn't get a 
> useful interrupt out of them.
> 
> Maybe a module parameter "allow_insecure_dma" can be added to 
> uio_pci_generic.  Without the parameter, bus mastering and msix is 
> disabled, with the parameter it is allowed.  This requires the sysadmin 
> to take a positive step in order to make use of their hardware.

Giving the control of the memory protection level to the distribution or
the administrator looks a good idea.
When allowing insecure DMA, a log will make clear how it is supported
-or not- by the system provider.

>From another thread:
2015-10-01 14:09, Michael S. Tsirkin:
> If Linux keeps enabling hacks, no one will bother doing the right thing.
> Upstream inclusion is the only carrot Linux has to make people do the
> right thing.

The "right thing" should be guided by the users needs at a given time.
The "carrot" for a better solution will be to have a well protected system.