[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20200117191220.GN302770@tassilo.jf.intel.com>
Date: Fri, 17 Jan 2020 11:12:20 -0800
From: Andi Kleen <ak@...ux.intel.com>
To: roman.sudarikov@...ux.intel.com
Cc: gregkh@...ux-foundation.org, roman.sudarikov@...ux.intel.com,
peterz@...radead.org, mingo@...hat.com, acme@...nel.org,
mark.rutland@....com, alexander.shishkin@...ux.intel.com,
jolsa@...hat.com, namhyung@...nel.org,
linux-kernel@...r.kernel.org, eranian@...gle.com,
bgregg@...flix.com, kan.liang@...ux.intel.com,
alexander.antonov@...el.com
Subject: Re: [PATCH v4 2/2] perf x86: Exposing an Uncore unit to PMON for Intel Xeon® server platform
> > pmon0-3: list of pci busses indexed by die
> >
> > To be honest the approach doesn't seem unreasonable to me. It's similar
> > e.g. how we express lists of cpus or nodes in sysfs today.
<snipped repeated form letter non answer to question>
Roman,
I suppose you'll need something like
/sys/device/system/dieXXX/pci-pmon<0-3>/bus
and bus could be a symlink to the pci bus directory.
The whole thing will be ugly and complicated and slow and difficult
to parse, but it will presumably follow Greg's rules.
-Andi
Powered by blists - more mailing lists