Date: Tue, 4 Jul 2017 11:21:59 +0100
From: Mark Rutland <mark.rutland@arm.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Kyle Huey <me@kylehuey.com>, Vince Weaver <vincent.weaver@maine.edu>,
        "Jin, Yao" <yao.jin@linux.intel.com>, Ingo Molnar <mingo@kernel.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>, 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: [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)
Message-ID: <20170704102159.GB20062@leverpostej>
References: <CAP045Ao2=6A7GEhBfmY0gZ2g=urL5U4R5ywLsTo4Yb6Tk1M8Cw@mail.gmail.com>
 <2256f9b5-1277-c4b1-1472-61a10cd1db9a@linux.intel.com>
 <CAP045AryPCUTO92S3hmrkag3D7NqgJM-hK82a7iKm9s-rWdn1w@mail.gmail.com>
 <20170628101248.GB5981@leverpostej>
 <20170628105600.GC5981@leverpostej>
 <CAP045ApjOeng6M9kqwbNpv5OTN=_Gkk2MHREztzZV_CecqpmxQ@mail.gmail.com>
 <20170628174900.GG8252@leverpostej>
 <CAP045Apcdk6wHU9yt3m5x6L_GUoOqnU2DzKeSQj5nHRGQuNuRQ@mail.gmail.com>
 <20170704090313.xyb5lntyy55ga7dm@hirez.programming.kicks-ass.net>
 <20170704093345.GB19649@leverpostej>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20170704093345.GB19649@leverpostej>
User-Agent: Mutt/1.5.21 (2010-09-15)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1151
Lines: 42

On Tue, Jul 04, 2017 at 10:33:45AM +0100, Mark Rutland wrote:
> On Tue, Jul 04, 2017 at 11:03:13AM +0200, Peter Zijlstra wrote:
> > Faking data gets a wee bit tricky in how much data we need to clear
> > through, its not only IP, pretty much everything we get from the
> > interrupt context, like the branch stack and registers is also suspect.
> 
> Indeed. I'll take a run through __perf_event_output() and callees, and
> see what we need to drop.

Looking at perf_event_sample_format in uapi/linux/perf_event.h, there
are samples that are obviously sensitive, and should be dropped:

* PERF_SAMPLE_IP
* PERF_SAMPLE_CALLCHAIN
* PERF_SAMPLE_BRANCH_STACK
* PERF_SAMPLE_REGS_INTR

... samples that look benign:

* PERF_SAMPLE_TID
* PERF_SAMPLE_TIME
* PERF_SAMPLE_CPU
* PERF_SAMPLE_PERIOD
* PERF_SAMPLE_REGS_USER
* PERF_SAMPLE_STACK_USER
* PERF_SAMPLE_READ
* PERF_SAMPLE_ID
* PERF_SAMPLE_STREAM_ID
* PERF_SAMPLE_IDENTIFIER

.. and samples that I have no idea about:

* PERF_SAMPLE_ADDR
* PERF_SAMPLE_RAW
* PERF_SAMPLE_WEIGHT
* PERF_SAMPLE_DATA_SRC
* PERF_SAMPLE_TRANSACTION

Should any of those be moved into the "should be dropped" pile?

Thanks,
Mark.