[RFC PATCH] perf cs-etm: Handle valid-but-zero timestamps

[James Clark]

On 12/05/2021 05:08, Leo Yan wrote:
> On Tue, May 11, 2021 at 04:53:35PM +0300, James Clark wrote:
> 
> [...]
> 
>>         /* First get the packet queue for this traceID */
>>         packet_queue = cs_etm__etmq_get_packet_queue(etmq, trace_chan_id);
>> @@ -320,7 +323,20 @@ cs_etm_decoder__do_hard_timestamp(struct cs_etm_queue *etmq,
>>          * which instructions started by subtracting the number of instructions
>>          * executed to the timestamp.
>>          */
>> -       packet_queue->timestamp = elem->timestamp - packet_queue->instr_count;
>> +       if (!elem->timestamp) {
>> +               packet_queue->timestamp = 0;
>> +               if (!warned_timestamp_zero) {
>> +                       pr_err("Zero Coresight timestamp found at Idx:%" OCSD_TRC_IDX_STR
>> +                               ". Decoding may be improved with --itrace=Z...\n", indx);
>> +                       warned_timestamp_zero = true;
>> +               }
>> +       }
>> +       else if (packet_queue->instr_count >= elem->timestamp) {
> 
> Nitpick: I personally think should use the condition ">" rather than ">=".

Yes, good catch. I actually changed this because I realised that
if they are equal it shouldn't print an error.

> 
>> +               packet_queue->timestamp = 0;
>> +               pr_err("Timestamp calculation underflow at Idx:%" OCSD_TRC_IDX_STR "\n", indx);
>> +       }
>> +       else
>> +               packet_queue->timestamp = elem->timestamp - packet_queue->instr_count;
> 
> Nitpick for coding style, as described in
> Documentation/process/coding-style.rst, section "3) Placing Braces and
> Spaces", so here should use braces with the format:

Ok I will update and run it through checkpatch.pl before posting.

[...]