Messages in this thread | | | Date | Tue, 5 Jun 2012 12:38:31 +0200 | Subject | Re: [PATCH] perf: Fix intel shared extra msr allocation | From | Stephane Eranian <> |
| |
On Tue, Jun 5, 2012 at 12:27 PM, Peter Zijlstra <a.p.zijlstra@chello.nl> wrote: > On Tue, 2012-06-05 at 12:21 +0200, Stephane Eranian wrote: >> I agree with the first part of the patch in intel_try_alt_er(), we >> should not touch >> the actual event struct. But I am still unclear about the reg->alloc part. > > reg->alloc is part of the actual event. > Ok, I missed that (despite writing some of that code ;-<)
> Thing is, the patch is horridly ugly.. while I agree that changing event > state isn't good, special casing all that code isn't good either.
Yeah, not pretty.
> > I was looking at cloning the events for validate_group() as well, but so > far that's not turning out too pretty either.
How about we add a field or flag to cpuc to tell it's fake, and then in try_alt_er() and __intel_shared_reg_get_constraints() we avoid touching live struct (like reg->alloc) if fake==1. I think he was trying to do the same with the core_id == -1 test.
| |