Re: [PATCH 7/9] perf test cs-etm: Test branch history on existing samples

On 12/08/2026 15:13, James Clark wrote:
> 
> 
> On 03/08/2026 10:06, Amir Ayupov wrote:
>> Add a CoreSight shell test for --itrace=L. Record timestamped ETM trace
>> with explicit -T sample timestamps and AUX pause/resume events, then
>> check that the pause samples carry both a multi-frame callchain and a
>> non-empty branch stack for each of the workload's two processes.
>>
>> Decode the same recording with L4 and L64 and reject any branch stack
>> deeper than the requested depth.
>>
>> The test skips when cs_etm is absent, when not run as root, or when the
>> recording turns out to lack virtual timestamps. It exercises the
>> timestamp-gated path and the requested-depth bound; it does not attempt
>> to verify that the attached history is correlated to the sample.
>>
>> Signed-off-by: Amir Ayupov <[email protected]>
>> ---
>>   .../tests/shell/coresight/add_last_branch.sh  | 175 ++++++++++++++++++
>>   1 file changed, 175 insertions(+)
>>   create mode 100755 tools/perf/tests/shell/coresight/add_last_branch.sh
>>
>> diff --git a/tools/perf/tests/shell/coresight/add_last_branch.sh b/ 
>> tools/perf/tests/shell/coresight/add_last_branch.sh
>> new file mode 100755
>> index 0000000000000..4654069ad651f
>> --- /dev/null
>> +++ b/tools/perf/tests/shell/coresight/add_last_branch.sh
>> @@ -0,0 +1,175 @@
>> +#!/bin/bash -e
>> +# SPDX-License-Identifier: GPL-2.0
>> +# CoreSight branch history on existing samples (exclusive)
>> +
>> +perf list pmu | grep -q 'cs_etm//' || exit 2
>> +
>> +if [ "$(id -u)" != 0 ]; then
>> +    echo "[Skip] No root permission"
>> +    exit 2
>> +fi
> 
> Is this so you can use -C 0? It's not completely obvious what that has 
> to do with the test. Can you not drop the -C option or use --per-thread 
> mode with a simpler non-forking workload?
> 
> I don't mind keeping it for some variety in the tests, but it should be 
> documented.
> 
>> +
>> +tmpdir=$(mktemp -d /tmp/perf-cs-add-last-branch.XXXXX)
>> +
>> +cleanup()
>> +{
>> +    rm -rf "$tmpdir"
>> +    trap - EXIT TERM INT
>> +}
>> +
>> +# shellcheck disable=SC2317 # Called through trap.
>> +trap_cleanup()
>> +{
>> +    cleanup
>> +    exit 1
>> +}
>> +trap trap_cleanup EXIT TERM INT
>> +
>> +record_data()
>> +{
>> +    if perf record -T -o "$tmpdir/data" -C 0 \
>> +        -e cs_etm/aux-action=start-paused,timestamp/u \
> 
> Timestamp needs a value on newer kernels or Perf returns an error. But 
> do you need to provide the option at all? It's on by default for per-CPU 
> mode.
> 
>> +        -e cycles/aux-action=resume,period=550019/u \
>> +        -e cycles/aux-action=pause,period=100003,call-graph=fp/u -- \
>> +        taskset --cpu-list 0 perf test -w context_switch_loop 100000 \
> 
> The other Coresight tests use --workload-ctl to record less data and 
> save some decode time. I think this test might benefit from it too.
> 
>> +        >/dev/null 2>"$tmpdir/stderr"; then
>> +        return 0
>> +    fi
>> +
>> +    echo "Failed to record ETM trace with AUX pause/resume" >&2
>> +    cat "$tmpdir/stderr" >&2
>> +    return 1
>> +}
>> +
>> +decode()
>> +{
>> +    local size=$1
>> +    local output=$2
>> +
>> +    if perf script -i "$tmpdir/data" --itrace="L$size" \
>> +        -F comm,pid,tid,event,ip,brstack >"$output" \
>> +        2>"$tmpdir/stderr"; then
>> +        return 0
>> +    fi
>> +
>> +    if grep -q "itrace=L requires virtual timestamped trace" \
>> +        "$tmpdir/stderr"; then
>> +        echo "[Skip] Virtual CoreSight timestamps are not available"
>> +        cleanup
>> +        exit 2
>> +    fi
>> +
>> +    cat "$tmpdir/stderr" >&2
>> +    return 1
>> +}
>> +
>> +check_process_samples()
>> +{
>> +    local output=$1
>> +    local comm
>> +
>> +    for comm in proc1 proc2; do
>> +        awk -v comm="$comm" '
>> +            $1 == comm && /cycles\/aux-action=pause/ {
>> +                in_sample = 1
>> +                next
>> +            }
>> +            !NF {
>> +                in_sample = 0
>> +                next
>> +            }
>> +            in_sample && /0x[[:xdigit:]]+\/0x[[:xdigit:]]+\// {
>> +                found = 1
>> +            }
>> +            END { exit !found }
>> +        ' "$output" || {
>> +            echo "No pause-event branch stack found for $comm" >&2
>> +            return 1
>> +        }
>> +    done
>> +}
>> +
>> +check_callchains()
>> +{
>> +    local output="$tmpdir/script-callchain"
>> +
>> +    perf script -i "$tmpdir/data" -F comm,event,ip >"$output" 2>/dev/ 
>> null
>> +
>> +    awk '
>> +        /cycles\/aux-action=pause/ {
>> +            in_sample = 1
>> +            frames = 0
>> +            next
>> +        }
>> +        !NF {
>> +            if (in_sample && frames >= 2)
>> +                found = 1
>> +            in_sample = 0
>> +            next
>> +        }
>> +        in_sample && /^[[:space:]]+[[:xdigit:]]+([[:space:]]|$)/ {
>> +            frames++
>> +        }
>> +        END {
>> +            if (in_sample && frames >= 2)
>> +                found = 1
>> +            exit !found
>> +        }
>> +    ' "$output" || {
>> +        echo "No multi-frame pause-event callchain found" >&2
>> +        return 1
>> +    }
> 
> Can you add some example output in the test saying what these awks are 
> looking for. It failed for me but I wasn't sure why. I've attached my 
> script-callchain file if that helps.
> 
> 
Of course I forgot to attach