From: Kyle Huey <me@kylehuey.com>
To: Mark Rutland <mark.rutland@arm.com>
Cc: "Jin, Yao" <yao.jin@linux.intel.com>,
Ingo Molnar <mingo@kernel.org>,
"Peter Zijlstra (Intel)" <peterz@infradead.org>,
stable@vger.kernel.org,
Alexander Shishkin <alexander.shishkin@linux.intel.com>,
Arnaldo Carvalho de Melo <acme@redhat.com>,
Jiri Olsa <jolsa@redhat.com>,
Linus Torvalds <torvalds@linux-foundation.org>,
Namhyung Kim <namhyung@kernel.org>,
Stephane Eranian <eranian@google.com>,
Thomas Gleixner <tglx@linutronix.de>,
Vince Weaver <vincent.weaver@maine.edu>,
acme@kernel.org, jolsa@kernel.org, kan.liang@intel.com,
Will Deacon <will.deacon@arm.com>,
gregkh@linuxfoundation.org,
"Robert O'Callahan" <robert@ocallahan.org>,
open list <linux-kernel@vger.kernel.org>
Subject: Re: [REGRESSION] perf/core: PMU interrupts dropped if we entered the kernel in the "skid" region
Date: Wed, 28 Jun 2017 09:46:43 -0700 [thread overview]
Message-ID: <CAP045AqMGwHKCiTTUQauX1ZivpnW-QW355rzCVLgdGn7HgOo3Q@mail.gmail.com> (raw)
In-Reply-To: <20170628101248.GB5981@leverpostej>
On Wed, Jun 28, 2017 at 3:12 AM, Mark Rutland <mark.rutland@arm.com> wrote:
> On Tue, Jun 27, 2017 at 09:51:00PM -0700, Kyle Huey wrote:
>> On Tue, Jun 27, 2017 at 7:09 PM, Jin, Yao <yao.jin@linux.intel.com> wrote:
>> > Hi,
>> >
>> > In theory, the PMI interrupts in skid region should be dropped, right?
>>
>> No, why would they be dropped?
>>
>> My understanding of the situation is as follows:
>>
>> There is some time, call it t_0, where the hardware counter overflows.
>> The PMU triggers an interrupt, but this is not instantaneous. Call
>> the time when the interrupt is actually delivered t_1. Then t_1 - t_0
>> is the "skid".
>>
>> Note that if the counter is `exclude_kernel`, then at t_0 the CPU
>> *must* be running a userspace program. But by t_1, the CPU may be
>> doing something else. Your patch changed things so that if at t_1 the
>> CPU is in the kernel, then the interrupt is discarded. But rr has
>> programmed the counter to deliver a signal on overflow (via F_SETSIG
>> on the fd returned by perf_event_open). This change results in the
>> signal never being delivered, because the interrupt was ignored.
>> (More accurately, the signal is delivered the *next* time the counter
>> overflows, which is far past where we wanted to inject our
>> asynchronous event into our tracee.
>
> Yes, this is a bug.
>
> As we're trying to avoid smapling state, I think we can move the check
> into perf_prepare_sample() or __perf_event_output(), where that state is
> actually sampled. I'll take a look at that momentarily.
>
> Just to clarify, you don't care about the sample state at all? i.e. you
> don't need the user program counter?
Right. `sample_regs_user`, `sample_star_user`, `branch_sample_type`,
etc are all 0.
https://github.com/mozilla/rr/blob/cf594dd01f07d96a61409e9f41a29f78c8c51693/src/PerfCounters.cc#L194
is what we do use.
> Is that signal delivered to the tracee, or to a different process that
> traces it? If the latter, what ensures that the task is stopped
> sufficiently quickly?
It's delivered to the tracee (via an F_SETOWN_EX with the tracee tid).
In practice we've found that on modern Intel hardware that the
interrupt and resulting signal delivery delay is bounded by a
relatively small number of counter events.
>> It seems to me that it might be reasonable to ignore the interrupt if
>> the purpose of the interrupt is to trigger sampling of the CPUs
>> register state. But if the interrupt will trigger some other
>> operation, such as a signal on an fd, then there's no reason to drop
>> it.
>
> Agreed. I'll try to have a patch for this soon.
>
> I just need to figure out exactly where that overflow signal is
> generated by the perf core.
>
> Thanks,
> Mark.
- Kyle
next prev parent reply other threads:[~2017-06-28 16:46 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <CAP045Ap8cMx6mzSgcQ3n3bnh_8GJuCp7_KZe_5ZTCR_K6cPTLw@mail.gmail.com>
2017-06-28 1:01 ` [REGRESSION] perf/core: PMU interrupts dropped if we entered the kernel in the "skid" region Kyle Huey
2017-06-28 2:09 ` Jin, Yao
2017-06-28 4:51 ` Kyle Huey
2017-06-28 5:35 ` Jin, Yao
2017-06-28 7:30 ` Kyle Huey
2017-06-28 10:12 ` Mark Rutland
2017-06-28 10:56 ` [PATCH] perf/core: generate overflow signal when samples are dropped (WAS: Re: [REGRESSION] perf/core: PMU interrupts dropped if we entered the kernel in the "skid" region) Mark Rutland
2017-06-28 12:40 ` Vince Weaver
2017-06-28 13:07 ` Mark Rutland
2017-06-29 8:13 ` Alexey Budankov
2017-06-29 8:25 ` Alexey Budankov
2017-06-28 16:48 ` Kyle Huey
2017-06-28 17:49 ` Mark Rutland
2017-06-28 22:55 ` Kyle Huey
2017-06-29 0:27 ` Jin, Yao
2017-06-30 17:44 ` Kyle Huey
2017-07-04 9:03 ` Peter Zijlstra
2017-07-04 9:33 ` Mark Rutland
2017-07-04 9:46 ` Peter Zijlstra
2017-07-04 10:21 ` Mark Rutland
2017-07-06 5:07 ` Robert O'Callahan
2017-07-11 2:03 ` Kyle Huey
2017-07-11 9:03 ` Ingo Molnar
2017-07-11 13:07 ` Jin, Yao
2017-07-12 7:57 ` Ingo Molnar
2017-07-11 14:26 ` Mark Rutland
2017-07-11 15:32 ` Kyle Huey
2017-07-18 0:07 ` Kyle Huey
2017-06-29 8:12 ` Ingo Molnar
2017-07-04 9:06 ` Peter Zijlstra
2017-07-04 10:04 ` Ingo Molnar
2017-07-11 9:03 ` [tip:perf/urgent] Revert "perf/core: Drop kernel samples even though :u is specified" tip-bot for Ingo Molnar
2017-06-28 16:46 ` Kyle Huey [this message]
2017-06-28 17:19 ` [REGRESSION] perf/core: PMU interrupts dropped if we entered the kernel in the "skid" region Mark Rutland
2017-06-28 17:36 ` Kyle Huey
2017-06-28 17:52 ` Mark Rutland
2017-06-28 17:48 ` Robert O'Callahan
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=CAP045AqMGwHKCiTTUQauX1ZivpnW-QW355rzCVLgdGn7HgOo3Q@mail.gmail.com \
--to=me@kylehuey.com \
--cc=acme@kernel.org \
--cc=acme@redhat.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=eranian@google.com \
--cc=gregkh@linuxfoundation.org \
--cc=jolsa@kernel.org \
--cc=jolsa@redhat.com \
--cc=kan.liang@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mark.rutland@arm.com \
--cc=mingo@kernel.org \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
--cc=robert@ocallahan.org \
--cc=stable@vger.kernel.org \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
--cc=vincent.weaver@maine.edu \
--cc=will.deacon@arm.com \
--cc=yao.jin@linux.intel.com \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).