Re: [PATCH v6 00/19] ARM64 PMU Partitioning

On Thu, 12 Feb 2026 21:08:36 +0000,
Colton Lewis [off-list ref] wrote:

Hey Marc, thanks for the review.

Marc Zyngier [off-list ref] writes:

quoted

On Mon, 09 Feb 2026 22:13:55 +0000,
Colton Lewis [off-list ref] wrote:

quoted

quoted

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.

quoted

quoted

An overview of what this series accomplishes was presented at KVM
Forum 2025. Slides [1] and video [2] are linked below.

quoted

quoted

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.

quoted

[...]

quoted

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.

quoted

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.