[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <c6468c4e-d704-d71a-6b00-e72977fbf68f@linux.vnet.ibm.com>
Date: Wed, 9 Aug 2017 07:13:36 +0530
From: Anshuman Khandual <khandual@...ux.vnet.ibm.com>
To: Laurent Dufour <ldufour@...ux.vnet.ibm.com>,
paulmck@...ux.vnet.ibm.com, peterz@...radead.org,
akpm@...ux-foundation.org, kirill@...temov.name,
ak@...ux.intel.com, mhocko@...nel.org, dave@...olabs.net,
jack@...e.cz, Matthew Wilcox <willy@...radead.org>,
benh@...nel.crashing.org, mpe@...erman.id.au, paulus@...ba.org,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>, hpa@...or.com,
Will Deacon <will.deacon@....com>
Cc: linux-kernel@...r.kernel.org, linux-mm@...ck.org,
haren@...ux.vnet.ibm.com, khandual@...ux.vnet.ibm.com,
npiggin@...il.com, bsingharora@...il.com,
Tim Chen <tim.c.chen@...ux.intel.com>,
linuxppc-dev@...ts.ozlabs.org, x86@...nel.org
Subject: Re: [PATCH 16/16] perf tools: Add support for SPF events
On 08/08/2017 08:05 PM, Laurent Dufour wrote:
> Add support for the new speculative faults events.
>
> Signed-off-by: Laurent Dufour <ldufour@...ux.vnet.ibm.com>
> ---
> tools/include/uapi/linux/perf_event.h | 2 ++
> tools/perf/util/evsel.c | 2 ++
> tools/perf/util/parse-events.c | 8 ++++++++
> tools/perf/util/parse-events.l | 2 ++
> tools/perf/util/python.c | 2 ++
> 5 files changed, 16 insertions(+)
>
> diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
> index b1c0b187acfe..fbfb03dff334 100644
> --- a/tools/include/uapi/linux/perf_event.h
> +++ b/tools/include/uapi/linux/perf_event.h
> @@ -111,6 +111,8 @@ enum perf_sw_ids {
> PERF_COUNT_SW_EMULATION_FAULTS = 8,
> PERF_COUNT_SW_DUMMY = 9,
> PERF_COUNT_SW_BPF_OUTPUT = 10,
> + PERF_COUNT_SW_SPF_DONE = 11,
> + PERF_COUNT_SW_SPF_FAILED = 12,
>
PERF_COUNT_SW_SPF_FAULTS makes sense but not the FAILED one. IIRC,
there are no error path counting in perf SW events at the moment.
SPF_FAULTS and SPF_FAILS are VM internal events like THP collapse
etc. IMHO it should be added as a VM statistics counter or as a
trace point event instead.
Powered by blists - more mailing lists