Re: [PATCH v3 3/3] perf evlist: Improve default event for s390
From: Thomas Richter
Date: Mon Mar 16 2026 - 08:14:04 EST
On 3/13/26 21:28, Ian Rogers wrote:
> Frame pointer callchains are not supported on s390 and dwarf
> callchains are only supported on software events.
>
> Switch the default event from cycles to cpu-clock or task-clock on
> s390 if callchains are enabled.
>
> If frame pointer callchains are requested on s390, warn and switch to
> dwarf callchains.
>
> Signed-off-by: Ian Rogers <irogers@xxxxxxxxxx>
> ---
> tools/perf/builtin-record.c | 3 ++-
> tools/perf/builtin-top.c | 2 +-
> tools/perf/tests/event_update.c | 4 +++-
> tools/perf/tests/expand-cgroup.c | 4 +++-
> tools/perf/tests/perf-record.c | 7 ++++--
> tools/perf/tests/topology.c | 4 +++-
> tools/perf/util/evlist.c | 37 +++++++++++++++++++-------------
> tools/perf/util/evlist.h | 2 +-
> tools/perf/util/evsel.c | 11 ++++++++--
> 9 files changed, 49 insertions(+), 25 deletions(-)
>
> diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
> index 60d764068302..07ecc8a5fec7 100644
> --- a/tools/perf/builtin-record.c
> +++ b/tools/perf/builtin-record.c
> @@ -4310,7 +4310,8 @@ int cmd_record(int argc, const char **argv)
> record.opts.tail_synthesize = true;
>
> if (rec->evlist->core.nr_entries == 0) {
> - struct evlist *def_evlist = evlist__new_default();
> + struct evlist *def_evlist = evlist__new_default(&rec->opts.target,
> + callchain_param.enabled);
>
> if (!def_evlist)
> goto out;
> diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
> index 710604c4f6f6..58bab595b024 100644
> --- a/tools/perf/builtin-top.c
> +++ b/tools/perf/builtin-top.c
> @@ -1695,7 +1695,7 @@ int cmd_top(int argc, const char **argv)
> goto out_delete_evlist;
>
> if (!top.evlist->core.nr_entries) {
> - struct evlist *def_evlist = evlist__new_default();
> + struct evlist *def_evlist = evlist__new_default(target, callchain_param.enabled);
>
> if (!def_evlist)
> goto out_delete_evlist;
> diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c
> index cb9e6de2e033..facc65e29f20 100644
> --- a/tools/perf/tests/event_update.c
> +++ b/tools/perf/tests/event_update.c
> @@ -8,6 +8,7 @@
> #include "header.h"
> #include "machine.h"
> #include "util/synthetic-events.h"
> +#include "target.h"
> #include "tool.h"
> #include "tests.h"
> #include "debug.h"
> @@ -81,7 +82,8 @@ static int test__event_update(struct test_suite *test __maybe_unused, int subtes
> {
> struct evsel *evsel;
> struct event_name tmp;
> - struct evlist *evlist = evlist__new_default();
> + struct target target = {};
> + struct evlist *evlist = evlist__new_default(&target, /*sample_callchains=*/false);
>
> TEST_ASSERT_VAL("failed to get evlist", evlist);
>
> diff --git a/tools/perf/tests/expand-cgroup.c b/tools/perf/tests/expand-cgroup.c
> index c7b32a220ca1..dd547f2f77cc 100644
> --- a/tools/perf/tests/expand-cgroup.c
> +++ b/tools/perf/tests/expand-cgroup.c
> @@ -8,6 +8,7 @@
> #include "parse-events.h"
> #include "pmu-events/pmu-events.h"
> #include "pfm.h"
> +#include "target.h"
> #include <subcmd/parse-options.h>
> #include <stdio.h>
> #include <stdlib.h>
> @@ -99,7 +100,8 @@ out: for (i = 0; i < nr_events; i++)
> static int expand_default_events(void)
> {
> int ret;
> - struct evlist *evlist = evlist__new_default();
> + struct target target = {};
> + struct evlist *evlist = evlist__new_default(&target, /*sample_callchains=*/false);
>
> TEST_ASSERT_VAL("failed to get evlist", evlist);
>
> diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
> index efbd9cd60c63..c6e31ab8a6b8 100644
> --- a/tools/perf/tests/perf-record.c
> +++ b/tools/perf/tests/perf-record.c
> @@ -84,8 +84,11 @@ static int test__PERF_RECORD(struct test_suite *test __maybe_unused, int subtest
> CPU_ZERO_S(cpu_mask_size, cpu_mask);
>
> perf_sample__init(&sample, /*all=*/false);
> - if (evlist == NULL) /* Fallback for kernels lacking PERF_COUNT_SW_DUMMY */
> - evlist = evlist__new_default();
> + if (evlist == NULL) { /* Fallback for kernels lacking PERF_COUNT_SW_DUMMY */
> + struct target target = {};
> +
> + evlist = evlist__new_default(&target, /*sample_callchains=*/false);
> + }
>
> if (evlist == NULL) {
> pr_debug("Not enough memory to create evlist\n");
> diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
> index ec01150d208d..a34a7ab19a80 100644
> --- a/tools/perf/tests/topology.c
> +++ b/tools/perf/tests/topology.c
> @@ -9,6 +9,7 @@
> #include "evlist.h"
> #include "debug.h"
> #include "pmus.h"
> +#include "target.h"
> #include <linux/err.h>
>
> #define TEMPL "/tmp/perf-test-XXXXXX"
> @@ -37,11 +38,12 @@ static int session_write_header(char *path)
> .path = path,
> .mode = PERF_DATA_MODE_WRITE,
> };
> + struct target target = {};
>
> session = perf_session__new(&data, NULL);
> TEST_ASSERT_VAL("can't get session", !IS_ERR(session));
>
> - session->evlist = evlist__new_default();
> + session->evlist = evlist__new_default(&target, /*sample_callchains=*/false);
> TEST_ASSERT_VAL("can't get evlist", session->evlist);
> session->evlist->session = session;
>
> diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
> index 591bdf0b3e2a..e6c518cc4a69 100644
> --- a/tools/perf/util/evlist.c
> +++ b/tools/perf/util/evlist.c
> @@ -13,6 +13,7 @@
> #include "util/mmap.h"
> #include "thread_map.h"
> #include "target.h"
> +#include "dwarf-regs.h"
> #include "evlist.h"
> #include "evsel.h"
> #include "record.h"
> @@ -98,38 +99,44 @@ struct evlist *evlist__new(void)
> return evlist;
> }
>
> -struct evlist *evlist__new_default(void)
> +struct evlist *evlist__new_default(const struct target *target, bool sample_callchains)
> {
> struct evlist *evlist = evlist__new();
> bool can_profile_kernel;
> struct perf_pmu *pmu = NULL;
> + struct evsel *evsel;
> + char buf[256];
> + int err;
>
> if (!evlist)
> return NULL;
>
> can_profile_kernel = perf_event_paranoid_check(1);
>
> - while ((pmu = perf_pmus__scan_core(pmu)) != NULL) {
> - char buf[256];
> - int err;
> -
> - snprintf(buf, sizeof(buf), "%s/cycles/%s", pmu->name,
> + if (EM_HOST == EM_S390 && sample_callchains) {
> + snprintf(buf, sizeof(buf), "software/%s/%s",
> + target__has_cpu(target) ? "cpu-clock" : "task-clock",
> can_profile_kernel ? "P" : "Pu");
> err = parse_event(evlist, buf);
> - if (err) {
> - evlist__delete(evlist);
> - return NULL;
> + if (err)
> + goto out_err;
> + } else {
> + while ((pmu = perf_pmus__scan_core(pmu)) != NULL) {
> + snprintf(buf, sizeof(buf), "%s/cycles/%s", pmu->name,
> + can_profile_kernel ? "P" : "Pu");
> + err = parse_event(evlist, buf);
> + if (err)
> + goto out_err;
> }
> }
>
> - if (evlist->core.nr_entries > 1) {
> - struct evsel *evsel;
> -
> - evlist__for_each_entry(evlist, evsel)
> - evsel__set_sample_id(evsel, /*can_sample_identifier=*/false);
> - }
> + evlist__for_each_entry(evlist, evsel)
> + evsel__set_sample_id(evsel, /*can_sample_identifier=*/false);
>
> return evlist;
> +out_err:
> + evlist__delete(evlist);
> + return NULL;
> }
>
> struct evlist *evlist__new_dummy(void)
> diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
> index d17c3b57a409..e507f5f20ef6 100644
> --- a/tools/perf/util/evlist.h
> +++ b/tools/perf/util/evlist.h
> @@ -104,7 +104,7 @@ struct evsel_str_handler {
> };
>
> struct evlist *evlist__new(void);
> -struct evlist *evlist__new_default(void);
> +struct evlist *evlist__new_default(const struct target *target, bool sample_callchains);
> struct evlist *evlist__new_dummy(void);
> void evlist__init(struct evlist *evlist, struct perf_cpu_map *cpus,
> struct perf_thread_map *threads);
> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> index bd14d9bbc91f..caa95dc06ac5 100644
> --- a/tools/perf/util/evsel.c
> +++ b/tools/perf/util/evsel.c
> @@ -1020,6 +1020,13 @@ static void __evsel__config_callchain(struct evsel *evsel, struct record_opts *o
> {
> bool function = evsel__is_function_event(evsel);
> struct perf_event_attr *attr = &evsel->core.attr;
> + enum perf_call_graph_mode record_mode = param->record_mode;
> +
> + if (EM_HOST == EM_S390 && param->record_mode == CALLCHAIN_FP) {
> + pr_warning("Framepointer unwinding switched to dwarf due to a lack of kernel support.\n"
> + "Use '--call-graph dwarf' to silence this warning.\n");
> + record_mode = CALLCHAIN_DWARF;
> + }
>
> evsel__set_sample_bit(evsel, CALLCHAIN);
>
> @@ -1029,7 +1036,7 @@ static void __evsel__config_callchain(struct evsel *evsel, struct record_opts *o
> attr->exclude_callchain_user = 1;
> if (opts->user_callchains)
> attr->exclude_callchain_kernel = 1;
> - if (param->record_mode == CALLCHAIN_LBR) {
> + if (record_mode == CALLCHAIN_LBR) {
> if (!opts->branch_stack) {
> if (attr->exclude_user) {
> pr_warning("LBR callstack option is only available "
> @@ -1048,7 +1055,7 @@ static void __evsel__config_callchain(struct evsel *evsel, struct record_opts *o
> "Falling back to framepointers.\n");
> }
>
> - if (param->record_mode == CALLCHAIN_DWARF) {
> + if (record_mode == CALLCHAIN_DWARF) {
> if (!function) {
> uint16_t e_machine = evsel__e_machine(evsel, /*e_flags=*/NULL);
>
Ian, Thanks very much.
Tested-by: Thomas Richter <tmricht@xxxxxxxxxxxxx>
The fall back to cpu-clock works nicely when --call-graph or -g is specified on s390.
--
Thomas Richter, Dept 3303, IBM s390 Linux Development, Boeblingen, Germany
--
IBM Deutschland Research & Development GmbH
Vorsitzender des Aufsichtsrats: Wolfgang Wendt
Geschäftsführung: David Faller
Sitz der Gesellschaft: Böblingen / Registergericht: Amtsgericht Stuttgart, HRB 243294