[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CABPqkBS320VrPL9CzDVMzQCkHb6sxC+d1d7f_J3Mp0UXmF=3XA@mail.gmail.com>
Date: Wed, 24 Oct 2012 10:49:08 +0200
From: Stephane Eranian <eranian@...gle.com>
To: "Yan, Zheng" <zheng.z.yan@...el.com>
Cc: LKML <linux-kernel@...r.kernel.org>,
Peter Zijlstra <a.p.zijlstra@...llo.nl>,
"ak@...ux.intel.com" <ak@...ux.intel.com>
Subject: Re: [PATCH V2 0/7] perf, x86: Haswell LBR call stack support
On Wed, Oct 24, 2012 at 7:59 AM, Yan, Zheng <zheng.z.yan@...el.com> wrote:
> From: "Yan, Zheng" <zheng.z.yan@...el.com>
>
> 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 call stack facility can help perf to get call chains of progam
> without frame pointer.
>
> The LBR call stack has following known limitations
> 1. Zero length calls are not filtered out by hardware
> 2. Exception handing such as setjmp/longjmp will have calls/returns not
> match
> 3. Pushing different return address onto the stack will have calls/returns
> not match
>
> The patch series depends on Andi's "perf PMU support for Haswel" patches
>
The part that is missing here is that you don't explain that you are now
fitting LBR cstack under PERF_SAMPLE_CALLCHAIN. It is dynamically
enabled based on users callstack request mode.
> ---
> Changes since v1
> - not expose PERF_SAMPLE_BRANCH_CALL_STACK to user space
> - save/restore LBR stack on context switch for all sampling branch modes
> - reduce lbr_sel_map size
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists