Re: [RFC PATCH 0/5] perf: Intel uncore pmu counting support

From: Peter Zijlstra
Date: Wed Mar 28 2012 - 06:58:25 EST

On Wed, 2012-03-28 at 10:57 +0200, Andi Kleen wrote:
> The main problem is that we don't know currently what events are
> really useful. People need to play around with the raw events
> first to find that out. But to do that really already need some
> in tree support because out of tree is too painful to use: it's
> a chicken and egg problem.

So you're saying Intel just made the hardware without any idea if it was
useful or not?

Somehow that seems rather unlikely. It seems to me they had at least one
but very likely several strong use-cases before they designed the

What Ingo is asking is to implement these, so that everybody can enjoy
them instead of being a conduit for Intel proprietary tools.

A minimal driver with no users except $$ tools is not acceptable.
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at
Please read the FAQ at