[BUG] perf: No samples found when using kcore + coresight

[James Clark]

On 30/03/2023 00:25, Yang Shi wrote:
> On Wed, Mar 29, 2023 at 9:08 AM James Clark <james.clark at arm.com> wrote:
>>
>>
>>
>> On 14/03/2023 00:36, Leo Yan wrote:
>>> On Mon, Mar 13, 2023 at 11:15:44AM -0700, Yang Shi wrote:
>>>
>>> [...]
>>>
>>>>> Just a quick summary, here we have two issues:
>>>>>
>>>>> - With command:
>>>>>   perf record -e cs_etm/@tmc_etf63/k --kcore --per-thread \
>>>>>   -- taskset --cpu-list 1 uname",
>>>>>
>>>>>   perf doesn't enable "text poke" attribution.
>>>>
>>>> No, it enables "text poke" and perf fails to decode coresight trace
>>>> data too. It doesn't matter whether "--kcore" is after or before "-e
>>>> cs/etm/@tmc_etf63/k".
>>>
>>> Understand now.  Thanks for correction, if so we can ignore this one.
>>>
>>> Leo
>>
>> To me it looks like it's only --per-thread and --kcore together that
>> cause the issue. I can't see if that was mentioned previously in this
>> thread.
> 
> If "--pre-thread" is not passed in, perf record failed with "failed to
> mmap with 12 (Cannot allocate memory)". Sorry for not mentioning this
> in the first place. I was quite focused on --kcore and didn't realize
> they may be related.

That's unrelated. That's because you have specified a sink and without
--per-thread it tries to open the event on all cores. If the sink can't
be reached from all cores it will fail to open. You can make it work
without --per-thread if you limit it to a valid core like this, although
I don't know which ones exactly would be valid for your system:


  perf record -e cs_etm/@tmc_etf63/k --kcore -C 0 \
     -- taskset --cpu-list 1 uname

> 
>>
>> If it is --per-thread that's causing the issue then I think I have an
>> idea why it might be. There are some assumptions and different paths
>> taken in decoding in that mode that aren't correct. It causes some other
>> issues to do with ordering and timestamps as well and I wanted to fix it
>> previously. I wouldn't say that the text-poke change has caused a
>> regression, as decoding in this mode was always a bit buggy.
>>
>> Maybe this is another reason to fix it properly.