[PATCH] perf, tool: Fix the array pointer to follow event data properly

[PATCH] perf, tool: Fix the array pointer to follow event data properly

[Jiri Olsa]

Currently we dont update the 'array' pointer properly after
processing the RAW data. This way perf might report wrong data
for branch stack if it is used along with tracepoint sample.

I'm not sure tracepoint could be connected with branch stack,
but I think the array pointer should have correct value after
each sample processing.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
 tools/perf/util/evsel.c |    1 +
 1 files changed, 1 insertions(+), 0 deletions(-)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index d9da62a..56a96896 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -580,6 +580,7 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 			return -EFAULT;
 
 		data->raw_data = (void *) pdata;
+		array = (u64 *)(((char *)array) + data->raw_size + sizeof(u32));
 	}
 
 	if (type & PERF_SAMPLE_BRANCH_STACK) {
-- 
1.7.7.6

Re: [PATCH] perf, tool: Fix the array pointer to follow event data properly

[David Ahern]

Stephane submitted a similar patch a week ago:
https://lkml.org/lkml/2012/3/17/91

David


On 3/24/12 8:19 AM, Jiri Olsa wrote:
> Currently we dont update the 'array' pointer properly after
> processing the RAW data. This way perf might report wrong data
> for branch stack if it is used along with tracepoint sample.
>
> I'm not sure tracepoint could be connected with branch stack,
> but I think the array pointer should have correct value after
> each sample processing.
>
> Signed-off-by: Jiri Olsa<jolsa@redhat.com>
> ---
>   tools/perf/util/evsel.c |    1 +
>   1 files changed, 1 insertions(+), 0 deletions(-)
>
> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> index d9da62a..56a96896 100644
> --- a/tools/perf/util/evsel.c
> +++ b/tools/perf/util/evsel.c
> @@ -580,6 +580,7 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
>   			return -EFAULT;
>
>   		data->raw_data = (void *) pdata;
> +		array = (u64 *)(((char *)array) + data->raw_size + sizeof(u32));
>   	}
>
>   	if (type&  PERF_SAMPLE_BRANCH_STACK) {

Re: [PATCH] perf, tool: Fix the array pointer to follow event data properly

[Stephane Eranian]

Yes, and I haven't heard back since then

On Sat, Mar 24, 2012 at 5:00 PM, David Ahern <dsahern@gmail.com> wrote:
> Stephane submitted a similar patch a week ago:
> https://lkml.org/lkml/2012/3/17/91
>
> David
>
>
> On 3/24/12 8:19 AM, Jiri Olsa wrote:
>>
>> Currently we dont update the 'array' pointer properly after
>> processing the RAW data. This way perf might report wrong data
>> for branch stack if it is used along with tracepoint sample.
>>
>> I'm not sure tracepoint could be connected with branch stack,
>> but I think the array pointer should have correct value after
>> each sample processing.
>>
>> Signed-off-by: Jiri Olsa<jolsa@redhat.com>
>> ---
>>  tools/perf/util/evsel.c |    1 +
>>  1 files changed, 1 insertions(+), 0 deletions(-)
>>
>> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
>> index d9da62a..56a96896 100644
>> --- a/tools/perf/util/evsel.c
>> +++ b/tools/perf/util/evsel.c
>> @@ -580,6 +580,7 @@ int perf_event__parse_sample(const union perf_event
>> *event, u64 type,
>>                        return -EFAULT;
>>
>>                data->raw_data = (void *) pdata;
>> +               array = (u64 *)(((char *)array) + data->raw_size +
>> sizeof(u32));
>>        }
>>
>>        if (type&  PERF_SAMPLE_BRANCH_STACK) {
>
>

Re: [PATCH] perf, tool: Fix the array pointer to follow event data properly

[Arnaldo Carvalho de Melo]

Em Sat, Mar 24, 2012 at 06:21:05PM +0100, Stephane Eranian escreveu:
> Yes, and I haven't heard back since then
> 
> On Sat, Mar 24, 2012 at 5:00 PM, David Ahern <dsahern@gmail.com> wrote:
> > Stephane submitted a similar patch a week ago:
> > https://lkml.org/lkml/2012/3/17/91


Gack, I updated one of my machines and the postfix setup had some issues
with SELinux.

Yeah, I noticed its the same fix Stephane submitted last week and that I
should have already sent Ingo's way.

Ingo, please apply the one from Stephane, next time I process it if you
haven't yet I'll make sure it gets pushed.

- Arnaldo

> > David
> >
> >
> > On 3/24/12 8:19 AM, Jiri Olsa wrote:
> >>
> >> Currently we dont update the 'array' pointer properly after
> >> processing the RAW data. This way perf might report wrong data
> >> for branch stack if it is used along with tracepoint sample.
> >>
> >> I'm not sure tracepoint could be connected with branch stack,
> >> but I think the array pointer should have correct value after
> >> each sample processing.
> >>
> >> Signed-off-by: Jiri Olsa<jolsa@redhat.com>
> >> ---
> >>  tools/perf/util/evsel.c |    1 +
> >>  1 files changed, 1 insertions(+), 0 deletions(-)
> >>
> >> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> >> index d9da62a..56a96896 100644
> >> --- a/tools/perf/util/evsel.c
> >> +++ b/tools/perf/util/evsel.c
> >> @@ -580,6 +580,7 @@ int perf_event__parse_sample(const union perf_event
> >> *event, u64 type,
> >>                        return -EFAULT;
> >>
> >>                data->raw_data = (void *) pdata;
> >> +               array = (u64 *)(((char *)array) + data->raw_size +
> >> sizeof(u32));
> >>        }
> >>
> >>        if (type&  PERF_SAMPLE_BRANCH_STACK) {
> >
> >
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/