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

From: Leo Yan
Date: Tue May 11 2021 - 22:08:38 EST


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 ">=".

> + 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:

if (!elem->timestamp) {
/* print warning */
} else if {packet_queue->instr_count >= elem->timestamp) {
/* print warning */
} else {
packet_queue->timestamp = elem->timestamp - packet_queue->instr_count;
}

Thanks,
Leo

> packet_queue->next_timestamp = elem->timestamp;
> packet_queue->instr_count = 0;
>
> @@ -542,7 +558,7 @@ cs_etm_decoder__set_tid(struct cs_etm_queue *etmq,
>
> static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer(
> const void *context,
> - const ocsd_trc_index_t indx __maybe_unused,
> + const ocsd_trc_index_t indx,
> const u8 trace_chan_id __maybe_unused,
> const ocsd_generic_trace_elem *elem)
> {
> @@ -579,7 +595,8 @@ static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer(
> break;
> case OCSD_GEN_TRC_ELEM_TIMESTAMP:
> resp = cs_etm_decoder__do_hard_timestamp(etmq, elem,
> - trace_chan_id);
> + trace_chan_id,
> + indx);
> break;
> case OCSD_GEN_TRC_ELEM_PE_CONTEXT:
> resp = cs_etm_decoder__set_tid(etmq, packet_queue,
>
>
> James
>
> >
> > Thanks,
> > Leo
> >