[PATCH v6 4/8] perf cs-etm: Flush thread stacks after decoder reset

[James Clark]

On 26/05/2026 5:59 pm, Leo Yan wrote:
> Perf resets the CoreSight decoder when moving to a new AUX trace buffer,
> this causes trace discontinunity globally.
> 
> For callchain synthesis, keeping thread-stack state after decoder reset
> can leave stale call/return history attached to threads that are decoded
> later, producing incorrect synthesized callchains.
> 
> Flush all host thread stacks after a decoder reset. When virtualization
> is present, flush the guest thread stacks as well.
> 
> Signed-off-by: Leo Yan <leo.yan at arm.com>
> ---
>   tools/perf/util/cs-etm.c | 37 +++++++++++++++++++++++++++++++++++++
>   1 file changed, 37 insertions(+)
> 
> diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
> index 398ab3b7a429d402cc8e5f6cccb35c0b7c253732..ea2424175558ddc0a6f20a9de6c30f377facdc52 100644
> --- a/tools/perf/util/cs-etm.c
> +++ b/tools/perf/util/cs-etm.c
> @@ -1956,6 +1956,37 @@ static int cs_etm__end_block(struct cs_etm_queue *etmq,
>   
>   	return 0;
>   }
> +
> +static int cs_etm__flush_stack_cb(struct thread *thread,
> +				  void *data __maybe_unused)
> +{
> +	thread_stack__flush(thread);
> +	return 0;
> +}
> +
> +static void cs_etm__flush_machine_stack(struct cs_etm_queue *etmq, pid_t pid)
> +{
> +	struct machine *machine;
> +
> +	machine = machines__find(&etmq->etm->session->machines, pid);
> +	if (machine)
> +		machine__for_each_thread(machine, cs_etm__flush_stack_cb, NULL);
> +}
> +
> +static void cs_etm__flush_all_stack(struct cs_etm_queue *etmq)
> +{
> +	enum cs_etm_pid_fmt pid_fmt = cs_etm__get_pid_fmt(etmq);
> +
> +	if (!etmq->etm->synth_opts.last_branch)
> +		return;
> +
> +	cs_etm__flush_machine_stack(etmq, HOST_KERNEL_ID);
> +
> +	/* Clear the guest stack if virtualization is supported */
> +	if (pid_fmt == CS_ETM_PIDFMT_CTXTID2)
> +		cs_etm__flush_machine_stack(etmq, DEFAULT_GUEST_KERNEL_ID);
> +}
> +
>   /*
>    * cs_etm__get_data_block: Fetch a block from the auxtrace_buffer queue
>    *			   if need be.
> @@ -1978,6 +2009,12 @@ static int cs_etm__get_data_block(struct cs_etm_queue *etmq)
>   		ret = cs_etm_decoder__reset(etmq->decoder);
>   		if (ret)
>   			return ret;
> +
> +		/*
> +		 * Since the decoder is reset, this causes a global trace
> +		 * discontinuity. Flush all thread stacks.
> +		 */
> +		cs_etm__flush_all_stack(etmq);
>   	}
>   
>   	return etmq->buf_len;
> 

Reviewed-by: James Clark <james.clark at linaro.org>