Re: [PATCH V5 11/16] perf, core: Pass perf_sample_data to perf_callchain()

2014-10-07 Thread Peter Zijlstra
On Tue, Oct 07, 2014 at 03:50:45PM +, Liang, Kan wrote: > The data is originally from br_stack which is LBR format. Right, its read from the LBR, therefore this must be. > What the patch did is to convert it to CALLCHAIN output format in kernel. I saw that. > So you'd like to let the kernel

RE: [PATCH V5 11/16] perf, core: Pass perf_sample_data to perf_callchain()

2014-10-07 Thread Liang, Kan
> > > So I don't like this. Why not use the regular > > > PERF_SAMPLE_BRANCH_STACK output to generate the stuff from? We > > > already have two different means, with different transport, for callchains > anyhow, so a third really won't matter. > > > > I'm not sure what you mean by using the regul

Re: [PATCH V5 11/16] perf, core: Pass perf_sample_data to perf_callchain()

2014-10-07 Thread Peter Zijlstra
I think you're going to have to stop using outlook or whatnot, this is horrible. On Tue, Oct 07, 2014 at 03:00:00AM +, Liang, Kan wrote: > > -Original Message- > > From: Peter Zijlstra [mailto:pet...@infradead.org] > > So I don't like this. Why not use the regular PERF_SAMPLE_BRANCH_S

RE: [PATCH V5 11/16] perf, core: Pass perf_sample_data to perf_callchain()

2014-10-06 Thread Liang, Kan
el.com; Yan, Zheng > Subject: Re: [PATCH V5 11/16] perf, core: Pass perf_sample_data to > perf_callchain() > > On Wed, Sep 10, 2014 at 10:09:08AM -0400, kan.li...@intel.com wrote: > > From: Kan Liang > > > > Haswell has a new feature that utilizes the existing Last Branch

Re: [PATCH V5 11/16] perf, core: Pass perf_sample_data to perf_callchain()

2014-09-24 Thread Peter Zijlstra
On Wed, Sep 10, 2014 at 10:09:08AM -0400, kan.li...@intel.com wrote: > From: Kan Liang > > Haswell has a new feature that utilizes the existing Last Branch Record > facility to record call chains. When the feature is enabled, function > call will be collected as normal, but as return instructions

[PATCH V5 11/16] perf, core: Pass perf_sample_data to perf_callchain()

2014-09-10 Thread kan . liang
From: Kan Liang Haswell has a new feature that utilizes the existing Last Branch Record facility to record call chains. When the feature is enabled, function call will be collected as normal, but as return instructions are executed the last captured branch record is popped from the on-chip LBR re

[PATCH V5 11/16] perf, core: Pass perf_sample_data to perf_callchain()

2014-09-09 Thread kan . liang
From: Kan Liang Haswell has a new feature that utilizes the existing Last Branch Record facility to record call chains. When the feature is enabled, function call will be collected as normal, but as return instructions are executed the last captured branch record is popped from the on-chip LBR re

[PATCH v5 11/16] perf, core: Pass perf_sample_data to perf_callchain()

2014-07-06 Thread Yan, Zheng
Haswell has a new feature that utilizes the existing Last Branch Record facility to record call chains. When the feature is enabled, function call will be collected as normal, but as return instructions are executed the last captured branch record is popped from the on-chip LBR registers. The LBR c