Hi Bjorn,
On Mon, Jul 27, 2015 at 05:54:53PM -0500, Bjorn Helgaas wrote:
> > Hmm, this is a place where the relaxed error handling in
> > pci_enable_ats() can get problematic.
>
> By "relaxed error handling," do you mean the fact that in v4.1,
> pci_enable_ats() has a BUG_ON(is_enabled), while n
Hi Joerg,
Thanks for all your help reviewing this!
On Mon, Jul 27, 2015 at 03:08:10PM +0200, Joerg Roedel wrote:
> On Mon, Jul 20, 2015 at 07:13:57PM -0500, Bjorn Helgaas wrote:
> > We check the ATS state (enabled/disabled) and fetch the PCI ATS Invalidate
> > Queue Depth in performance-sensitive
On Mon, Jul 20, 2015 at 07:13:57PM -0500, Bjorn Helgaas wrote:
> We check the ATS state (enabled/disabled) and fetch the PCI ATS Invalidate
> Queue Depth in performance-sensitive paths. It's easy to cache these,
> which removes dependencies on PCI.
>
> Remember the ATS enabled state. When enabli
We check the ATS state (enabled/disabled) and fetch the PCI ATS Invalidate
Queue Depth in performance-sensitive paths. It's easy to cache these,
which removes dependencies on PCI.
Remember the ATS enabled state. When enabling, read the queue depth once
and cache it in the device_domain_info stru
