On Thu, 12 Feb 2026 21:08:36 +0000,
Colton Lewis <[email protected]> wrote:
>
> Hey Marc, thanks for the review.
>
> Marc Zyngier <[email protected]> writes:
>
> > On Mon, 09 Feb 2026 22:13:55 +0000,
> > Colton Lewis <[email protected]> wrote:
>
> >> This series creates a new PMU scheme on ARM, a partitioned PMU that
> >> allows reserving a subset of counters for more direct guest access,
> >> significantly reducing overhead. More details, including performance
> >> benchmarks, can be read in the v1 cover letter linked below.
>
> >> An overview of what this series accomplishes was presented at KVM
> >> Forum 2025. Slides [1] and video [2] are linked below.
>
> >> IMPORTANT: This iteration does not yet implement the dynamic counter
> >> reservation approach suggested by Will Deacon in January [3]. I am
> >> working on it, but wanted to send this version first to keep momentum
> >> going and ensure I've addressed all issues besides that.
>
> > [...]
>
> > As I have asked before, this is missing an example of how userspace is
> > going to use this. Without it, it is impossible to correctly review
> > this series.
>
> > Please consider this as a blocker.
>
> Understood. I remember you asking for a QEMU patch specifically.
No. *any* VMM. QEMU, kvmtool, crosvm, firecrackpoter, whichever you want.
> I had hoped that the use in the selftest was sufficient to show how to
> use the uAPI.
The selftests are absolutely pointless, like 99% of all selftests.
They don't demonstrate how the userspace API works, now how
configuring the PMU is ordered with the rest of the save/restore flow.
> If not, I can send out an example QEMU patch to the QEMU ARM mailing
> list.
Please do.
M.
--
Without deviation from the norm, progress is not possible.
