From: Andi Kleen <ak@linux.intel.com>
To: Stephane Eranian <eranian@google.com>
Cc: linux-kernel@vger.kernel.org, acme@redhat.com,
peterz@infradead.org, mingo@elte.hu, kan.liang@intel.com,
jolsa@redhat.com, namhyung@kernel.org, adrian.hunter@intel.com
Subject: Re: [PATCH 2/3] perf/x86/pebs: add workaround for broken OVFL status on HSW
Date: Thu, 3 Mar 2016 13:43:12 -0800 [thread overview]
Message-ID: <20160303214312.GI23621@tassilo.jf.intel.com> (raw)
In-Reply-To: <1457034642-21837-3-git-send-email-eranian@google.com>
> + /*
> + * There are cases where, even though, the PEBS ovfl bit is set in
> + * GLOBAL_OVF_STATUS, the PEBS events may also have their overflow bits
> + * set for their counters. We must clear them here because they have
> + * been processed as exact samples in the drain_pebs() routine. They
> + * must not be processed again in the for_each_bit_set() loop for
> + * regular samples below.
> + */
> + status &= ~cpuc->pebs_enabled;
> + status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI;
If you just clear the bits here they will not be acked and stay around
forever in GLOBAL_STATUS, which causes other problems.
You need a separate ack_status variable that contains all bits and is always
acked.
-Andi
--
ak@linux.intel.com -- Speaking for myself only
next prev parent reply other threads:[~2016-03-03 21:43 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-03-03 19:50 [PATCH 0/3] perf/x86/pebs: various important fixes for PEBS Stephane Eranian
2016-03-03 19:50 ` [PATCH 1/3] perf/x86/intel: add definition for PT PMI bit Stephane Eranian
2016-03-08 13:16 ` [tip:perf/core] perf/x86/intel: Add " tip-bot for Stephane Eranian
2016-03-03 19:50 ` [PATCH 2/3] perf/x86/pebs: add workaround for broken OVFL status on HSW Stephane Eranian
2016-03-03 21:43 ` Andi Kleen [this message]
2016-03-03 23:40 ` Stephane Eranian
2016-03-07 10:24 ` Peter Zijlstra
2016-03-07 12:18 ` Peter Zijlstra
2016-03-07 18:27 ` Jiri Olsa
2016-03-07 20:25 ` Peter Zijlstra
2016-03-08 20:59 ` Stephane Eranian
2016-03-08 21:07 ` Peter Zijlstra
2016-03-08 21:13 ` Stephane Eranian
2016-03-09 5:34 ` Stephane Eranian
2016-03-09 5:44 ` Stephane Eranian
2016-03-09 17:40 ` Stephane Eranian
2016-03-10 10:42 ` Peter Zijlstra
2016-12-14 17:55 ` Peter Zijlstra
2016-12-15 7:26 ` Stephane Eranian
2016-12-15 7:52 ` Jiri Olsa
2016-12-15 8:04 ` Stephane Eranian
2016-12-15 8:42 ` Peter Zijlstra
2016-12-15 16:59 ` Stephane Eranian
2016-12-15 17:10 ` Peter Zijlstra
2016-12-16 8:38 ` Stephane Eranian
2016-12-16 17:48 ` Stephane Eranian
2016-03-10 13:53 ` Peter Zijlstra
2016-03-10 16:10 ` Stephane Eranian
2016-03-08 13:16 ` [tip:perf/core] perf/x86/pebs: Add workaround for broken OVFL status on HSW+ tip-bot for Stephane Eranian
2016-03-03 19:50 ` [PATCH 3/3] perf/x86/pebs: add proper PEBS constraints for Broadwell Stephane Eranian
2016-03-08 13:16 ` [tip:perf/core] perf/x86/pebs: Add " tip-bot for Stephane Eranian
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20160303214312.GI23621@tassilo.jf.intel.com \
--to=ak@linux.intel.com \
--cc=acme@redhat.com \
--cc=adrian.hunter@intel.com \
--cc=eranian@google.com \
--cc=jolsa@redhat.com \
--cc=kan.liang@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.