On Mon, 17 May 2010, Stephane Eranian wrote:
> In case the sampling buffer has no "payload" pages, nr_pages is 0.
> The problem is that the error path in perf_output_begin() skips to
> a label which assumes perf_output_lock() has been issued which is
> not the case. That triggers a WARN_
In case the sampling buffer has no "payload" pages, nr_pages is 0.
The problem is that the error path in perf_output_begin() skips to
a label which assumes perf_output_lock() has been issued which is
not the case. That triggers a WARN_ON() in perf_output_unlock().
This patch fixes the problem by s
On Mon, May 17, 2010 at 2:09 PM, Peter Zijlstra wrote:
> On Mon, 2010-05-17 at 14:04 +0200, Stephane Eranian wrote:
>>
>> > So you want to preserve this state for when you munmap() and mmap()
>> > again? The only user of data->lost is writing the PERF_RECORD_LOST
>> > event, which only ever happen
On Mon, 2010-05-17 at 14:04 +0200, Stephane Eranian wrote:
>
> > So you want to preserve this state for when you munmap() and mmap()
> > again? The only user of data->lost is writing the PERF_RECORD_LOST
> > event, which only ever happens when you have pages, so counting it when
> > there's no pag
On Mon, May 17, 2010 at 2:03 PM, Peter Zijlstra wrote:
> On Mon, 2010-05-17 at 13:56 +0200, Stephane Eranian wrote:
>> >> + if (!data->nr_pages) {
>> >> + atomic_inc(&data->lost);
>> >> + goto out;
>> >> + }
>
>
>> Well, nr_pages = 0 means all you have is the sampli
In case the sampling buffer has no "payload" pages, nr_pages is 0.
The problem is that the error path in perf_output_begin() skips to
a label which assumes perf_output_lock() has been issued which is
not the case. That triggers a WARN_ON() is perf_output_unlock().
This patch fixes the problem by s
On Mon, 2010-05-17 at 13:56 +0200, Stephane Eranian wrote:
> >> + if (!data->nr_pages) {
> >> + atomic_inc(&data->lost);
> >> + goto out;
> >> + }
> Well, nr_pages = 0 means all you have is the sampling buffer
> header page. You cannot save any sample, so you actu
On Mon, May 17, 2010 at 1:04 PM, John Kacur wrote:
>
>
> On Mon, 17 May 2010, Stephane Eranian wrote:
>
>> In case the sampling buffer has no "payload" pages, nr_pages is 0.
>> The problem is that the error path in perf_output_begin() skips to
>> a label which assumes perf_output_lock() has
On Mon, May 17, 2010 at 1:46 PM, Frederic Weisbecker wrote:
> On Mon, May 17, 2010 at 12:46:01PM +0200, Stephane Eranian wrote:
>> In case the sampling buffer has no "payload" pages, nr_pages is 0.
>> The problem is that the error path in perf_output_begin() skips to
>> a label which assumes
On Mon, May 17, 2010 at 12:46:01PM +0200, Stephane Eranian wrote:
> In case the sampling buffer has no "payload" pages, nr_pages is 0.
> The problem is that the error path in perf_output_begin() skips to
> a label which assumes perf_output_lock() has been issued which is
> not the case. Tha
In case the sampling buffer has no "payload" pages, nr_pages is 0.
The problem is that the error path in perf_output_begin() skips to
a label which assumes perf_output_lock() has been issued which is
not the case. That triggers a WARN_ON() is perf_output_unlock().
This patch fixes the pr
11 matches
Mail list logo
