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)

From	Ingo Molnar <mingo@kernel.org>
Newsgroups	linux.kernel
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)
Date	2017-07-12 10:00 +0200
Message-ID	<u2kIV-5nd-11@gated-at.bofh.it> (permalink)
References	(5 earlier) <tZtfI-6Ye-17@gated-at.bofh.it> <u07d8-8ih-7@gated-at.bofh.it> <u1SMG-4AC-11@gated-at.bofh.it> <u1Zl7-mF-1@gated-at.bofh.it> <u235n-2FI-11@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

* Jin, Yao <yao.jin@linux.intel.com> wrote:

> Could we provide 2 options in user space when enabling the event sampling?
> 
> One option is for the use case like rr debugger which only cares the PMI 
> interrupt but doesn't care the skid. The skid samples doesn't need to be 
> dropped.

Since it's an information leak, this is not something we want to expose as an 
interface. It's also a very ugly interface: why not just *clear* the sample, 
instead of dropping it?

The hardware messed up and gave us something we specifically did not permit 
user-space to collect. We have to fix the bad effects to the best extent we can, 
and not based on some knob.

Thanks,

	Ingo

Thread

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) Peter Zijlstra <peterz@infradead.org> - 2017-07-04 11:10 +0200
  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) Mark Rutland <mark.rutland@arm.com> - 2017-07-04 11:40 +0200
    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) Peter Zijlstra <peterz@infradead.org> - 2017-07-04 11:50 +0200
    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) Mark Rutland <mark.rutland@arm.com> - 2017-07-04 12:30 +0200
      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) "Robert O'Callahan" <robert@ocallahan.org> - 2017-07-06 07:10 +0200
        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) Kyle Huey <me@kylehuey.com> - 2017-07-11 04:10 +0200
          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) Ingo Molnar <mingo@kernel.org> - 2017-07-11 11:10 +0200
            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) "Jin, Yao" <yao.jin@linux.intel.com> - 2017-07-11 15:10 +0200
              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) Ingo Molnar <mingo@kernel.org> - 2017-07-12 10:00 +0200
            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) Mark Rutland <mark.rutland@arm.com> - 2017-07-11 16:30 +0200
            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) Kyle Huey <me@kylehuey.com> - 2017-07-11 17:40 +0200
              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) Kyle Huey <me@kylehuey.com> - 2017-07-18 02:10 +0200

csiph-web