[PATCH v6 3/8] perf cs-etm: Use thread-stack for last branch entries
James Clark
james.clark at linaro.org
Thu Jun 4 07:09:26 PDT 2026
On 26/05/2026 5:59 pm, Leo Yan wrote:
> CS ETM maintains its own circular array for last branch entries, with
> local helpers to update, copy and reset the branch stack. This duplicates
> logic already provided by the common code.
>
> Record branch with thread_stack__event() and synthesize branch stack
> with thread_stack__br_sample(). This removes the local last_branch_rb
> buffer and position tracking. Keep the buffer number updated via
> thread_stack__set_trace_nr(), which is used when exporting samples to
> Python scripts.
>
> The output should remain same, except that be->flags.predicted is no
> longer set. Since CoreSight trace does not provide branch prediction
> information, clearing the flag avoids confusion.
>
> Signed-off-by: Leo Yan <leo.yan at arm.com>
> ---
> tools/perf/util/cs-etm.c | 152 +++++++++++++----------------------------------
> 1 file changed, 41 insertions(+), 111 deletions(-)
>
> diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
> index 5bff8811d61e423463b7bd4e20d599d5b5307a1a..398ab3b7a429d402cc8e5f6cccb35c0b7c253732 100644
> --- a/tools/perf/util/cs-etm.c
> +++ b/tools/perf/util/cs-etm.c
> @@ -83,14 +83,13 @@ struct cs_etm_auxtrace {
> struct cs_etm_traceid_queue {
> u8 trace_chan_id;
> u64 period_instructions;
> - size_t last_branch_pos;
> union perf_event *event_buf;
> struct thread *thread;
> struct thread *prev_packet_thread;
> ocsd_ex_level prev_packet_el;
> ocsd_ex_level el;
> + unsigned int br_stack_sz;
> struct branch_stack *last_branch;
> - struct branch_stack *last_branch_rb;
> struct cs_etm_packet *prev_packet;
> struct cs_etm_packet *packet;
> struct cs_etm_packet_queue packet_queue;
> @@ -635,9 +634,8 @@ static int cs_etm__init_traceid_queue(struct cs_etm_queue *etmq,
> tidq->last_branch = zalloc(sz);
> if (!tidq->last_branch)
> goto out_free;
> - tidq->last_branch_rb = zalloc(sz);
> - if (!tidq->last_branch_rb)
> - goto out_free;
> +
> + tidq->br_stack_sz = etm->synth_opts.last_branch_sz;
> }
>
> tidq->event_buf = malloc(PERF_SAMPLE_MAX_SIZE);
> @@ -647,7 +645,6 @@ static int cs_etm__init_traceid_queue(struct cs_etm_queue *etmq,
> return 0;
>
> out_free:
> - zfree(&tidq->last_branch_rb);
> zfree(&tidq->last_branch);
> zfree(&tidq->prev_packet);
> zfree(&tidq->packet);
> @@ -941,7 +938,6 @@ static void cs_etm__free_traceid_queues(struct cs_etm_queue *etmq)
> thread__zput(tidq->prev_packet_thread);
> zfree(&tidq->event_buf);
> zfree(&tidq->last_branch);
> - zfree(&tidq->last_branch_rb);
> zfree(&tidq->prev_packet);
> zfree(&tidq->packet);
> zfree(&tidq);
> @@ -1281,57 +1277,6 @@ static int cs_etm__queue_first_cs_timestamp(struct cs_etm_auxtrace *etm,
> return ret;
> }
>
> -static inline
> -void cs_etm__copy_last_branch_rb(struct cs_etm_queue *etmq,
> - struct cs_etm_traceid_queue *tidq)
> -{
> - struct branch_stack *bs_src = tidq->last_branch_rb;
> - struct branch_stack *bs_dst = tidq->last_branch;
> - size_t nr = 0;
> -
> - /*
> - * Set the number of records before early exit: ->nr is used to
> - * determine how many branches to copy from ->entries.
> - */
> - bs_dst->nr = bs_src->nr;
> -
> - /*
> - * Early exit when there is nothing to copy.
> - */
> - if (!bs_src->nr)
> - return;
> -
> - /*
> - * As bs_src->entries is a circular buffer, we need to copy from it in
> - * two steps. First, copy the branches from the most recently inserted
> - * branch ->last_branch_pos until the end of bs_src->entries buffer.
> - */
> - nr = etmq->etm->synth_opts.last_branch_sz - tidq->last_branch_pos;
> - memcpy(&bs_dst->entries[0],
> - &bs_src->entries[tidq->last_branch_pos],
> - sizeof(struct branch_entry) * nr);
> -
> - /*
> - * If we wrapped around at least once, the branches from the beginning
> - * of the bs_src->entries buffer and until the ->last_branch_pos element
> - * are older valid branches: copy them over. The total number of
> - * branches copied over will be equal to the number of branches asked by
> - * the user in last_branch_sz.
> - */
> - if (bs_src->nr >= etmq->etm->synth_opts.last_branch_sz) {
> - memcpy(&bs_dst->entries[nr],
> - &bs_src->entries[0],
> - sizeof(struct branch_entry) * tidq->last_branch_pos);
> - }
> -}
> -
> -static inline
> -void cs_etm__reset_last_branch_rb(struct cs_etm_traceid_queue *tidq)
> -{
> - tidq->last_branch_pos = 0;
> - tidq->last_branch_rb->nr = 0;
> -}
> -
> static inline int cs_etm__t32_instr_size(struct cs_etm_queue *etmq,
> u8 trace_chan_id, u64 addr)
> {
> @@ -1400,38 +1345,6 @@ static inline u64 cs_etm__instr_addr(struct cs_etm_queue *etmq,
> return addr;
> }
>
> -static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq,
> - struct cs_etm_traceid_queue *tidq)
> -{
> - struct branch_stack *bs = tidq->last_branch_rb;
> - struct branch_entry *be;
> -
> - /*
> - * The branches are recorded in a circular buffer in reverse
> - * chronological order: we start recording from the last element of the
> - * buffer down. After writing the first element of the stack, move the
> - * insert position back to the end of the buffer.
> - */
> - if (!tidq->last_branch_pos)
> - tidq->last_branch_pos = etmq->etm->synth_opts.last_branch_sz;
> -
> - tidq->last_branch_pos -= 1;
> -
> - be = &bs->entries[tidq->last_branch_pos];
> - be->from = cs_etm__last_executed_instr(tidq->prev_packet);
> - be->to = cs_etm__first_executed_instr(tidq->packet);
> - /* No support for mispredict */
> - be->flags.mispred = 0;
> - be->flags.predicted = 1;
> -
> - /*
> - * Increment bs->nr until reaching the number of last branches asked by
> - * the user on the command line.
> - */
> - if (bs->nr < etmq->etm->synth_opts.last_branch_sz)
> - bs->nr += 1;
> -}
> -
> static int cs_etm__inject_event(struct cs_etm_auxtrace *etm, union perf_event *event,
> struct perf_sample *sample, u64 type)
> {
> @@ -1579,6 +1492,37 @@ static inline u64 cs_etm__resolve_sample_time(struct cs_etm_queue *etmq,
> return etm->latest_kernel_timestamp;
> }
>
> +static void cs_etm__add_stack_event(struct cs_etm_queue *etmq,
> + struct cs_etm_traceid_queue *tidq)
> +{
> + u64 from, to;
> + int size;
> +
> + if (!tidq->prev_packet->last_instr_taken_branch)
> + return;
> +
> + if (tidq->prev_packet->sample_type != CS_ETM_RANGE ||
> + tidq->packet->sample_type != CS_ETM_RANGE)
> + return;
> +
> + if (etmq->etm->synth_opts.last_branch) {
> + from = cs_etm__last_executed_instr(tidq->prev_packet);
> + to = cs_etm__first_executed_instr(tidq->packet);
> +
> + size = cs_etm__instr_size(etmq, tidq->trace_chan_id,
> + tidq->prev_packet->isa, from);
> +
> + /* Enable callchain so thread stack entry can be allocated */
> + thread_stack__event(tidq->thread, tidq->prev_packet->cpu,
> + tidq->prev_packet->flags, from, to, size,
> + etmq->buffer->buffer_nr + 1, true,
> + tidq->br_stack_sz, 0);
> + } else {
> + thread_stack__set_trace_nr(tidq->thread, tidq->prev_packet->cpu,
> + etmq->buffer->buffer_nr + 1);
> + }
> +}
> +
> static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
> struct cs_etm_traceid_queue *tidq,
> u64 addr, u64 period)
> @@ -1608,8 +1552,12 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
>
> cs_etm__copy_insn(etmq, tidq->trace_chan_id, tidq->packet, &sample);
>
> - if (etm->synth_opts.last_branch)
> + if (etm->synth_opts.last_branch) {
> + thread_stack__br_sample(tidq->thread, tidq->packet->cpu,
> + tidq->last_branch,
> + tidq->br_stack_sz);
> sample.branch_stack = tidq->last_branch;
> + }
>
> if (etm->synth_opts.inject) {
> ret = cs_etm__inject_event(etm, event, &sample,
> @@ -1798,14 +1746,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
>
> tidq->period_instructions += tidq->packet->instr_count;
>
> - /*
> - * Record a branch when the last instruction in
> - * PREV_PACKET is a branch.
> - */
> - if (etm->synth_opts.last_branch &&
> - tidq->prev_packet->sample_type == CS_ETM_RANGE &&
> - tidq->prev_packet->last_instr_taken_branch)
> - cs_etm__update_last_branch_rb(etmq, tidq);
> + cs_etm__add_stack_event(etmq, tidq);
Would it be cleaner to call this whenever a branch sample is generated?
Seems like the conditions for calling thread_stack__event() and
cs_etm__synth_branch_sample() are slightly different (ignoring the fact
that branches are only generated when the user asks for them).
Maybe the conditions should be different, but maybe a comment why or if
they're the same, a shared function for the conditions would help.
For example, we don't push a branch to the stack for
CS_ETM_DISCONTINUITY, but we do generate a branch sample from 0.
>
> if (etm->synth_opts.instructions &&
> tidq->period_instructions >= etm->instructions_sample_period) {
> @@ -1864,10 +1805,6 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
> u64 offset = etm->instructions_sample_period - instrs_prev;
> u64 addr;
>
> - /* Prepare last branches for instruction sample */
> - if (etm->synth_opts.last_branch)
> - cs_etm__copy_last_branch_rb(etmq, tidq);
> -
> while (tidq->period_instructions >=
> etm->instructions_sample_period) {
> /*
> @@ -1947,10 +1884,6 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
> etmq->etm->synth_opts.instructions &&
> tidq->prev_packet->sample_type == CS_ETM_RANGE) {
> u64 addr;
> -
> - /* Prepare last branches for instruction sample */
> - cs_etm__copy_last_branch_rb(etmq, tidq);
> -
> /*
> * Generate a last branch event for the branches left in the
> * circular buffer at the end of the trace.
> @@ -1982,7 +1915,7 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
>
> /* Reset last branches after flush the trace */
> if (etm->synth_opts.last_branch)
> - cs_etm__reset_last_branch_rb(tidq);
> + thread_stack__flush(tidq->thread);
>
> return err;
> }
> @@ -2006,9 +1939,6 @@ static int cs_etm__end_block(struct cs_etm_queue *etmq,
> tidq->prev_packet->sample_type == CS_ETM_RANGE) {
> u64 addr;
>
> - /* Prepare last branches for instruction sample */
> - cs_etm__copy_last_branch_rb(etmq, tidq);
> -
> /*
> * Use the address of the end of the last reported execution
> * range.
>
More information about the linux-arm-kernel
mailing list