Re: [PATCH v4 02/25] perf sample: Make sure perf_sample__init/exit are used

From: Namhyung Kim

Date: Thu Apr 02 2026 - 23:11:13 EST

On Fri, Mar 20, 2026 at 12:26:04PM -0700, Ian Rogers wrote:
> The deferred stack trace code wasn't using perf_sample__init/exit. Add
> the deferred stack trace clean up to perf_sample__exit which requires
> proper NULL initialization in perf_sample__init. Make the
> perf_sample__exit robust to being called more than once by using
> zfree. Make the error paths in evsel__parse_sample exit the
> sample. Add a merged_callchain boolean to capture that callchain is
> allocated, deferred_callchain doen't suffice for this. Pack the struct
> variables to avoid padding bytes for this.
>
> Similiarly powerpc_vpadtl_sample wasn't using perf_sample__init/exit,
> use it for consistency and potential issues with uninitialized
> variables.
>
> Signed-off-by: Ian Rogers <irogers@xxxxxxxxxx>
> ---
> tools/perf/builtin-inject.c | 6 +++++-
> tools/perf/tests/perf-record.c | 1 +
> tools/perf/tests/switch-tracking.c | 2 ++
> tools/perf/util/callchain.c | 10 ++++++---
> tools/perf/util/evlist.c | 5 ++++-
> tools/perf/util/evsel.c | 34 ++++++++++++++++++------------
> tools/perf/util/powerpc-vpadtl.c | 10 +++++----
> tools/perf/util/sample.c | 10 +++++++--
> tools/perf/util/sample.h | 17 +++++++++------
> tools/perf/util/session.c | 13 ++++++++----
> 10 files changed, 74 insertions(+), 34 deletions(-)
>
> diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
> index 5b29f4296861..8b9a0a4097af 100644
> --- a/tools/perf/builtin-inject.c
> +++ b/tools/perf/builtin-inject.c
> @@ -1087,6 +1087,7 @@ static int perf_inject__sched_stat(const struct perf_tool *tool,
> struct perf_sample sample_sw;
> struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
> u32 pid = evsel__intval(evsel, sample, "pid");
> + int ret;
>
> list_for_each_entry(ent, &inject->samples, node) {
> if (pid == ent->tid)
> @@ -1103,7 +1104,9 @@ static int perf_inject__sched_stat(const struct perf_tool *tool,
> perf_event__synthesize_sample(event_sw, evsel->core.attr.sample_type,
> evsel->core.attr.read_format, &sample_sw);
> build_id__mark_dso_hit(tool, event_sw, &sample_sw, evsel, machine);
> - return perf_event__repipe(tool, event_sw, &sample_sw, machine);
> + ret = perf_event__repipe(tool, event_sw, &sample_sw, machine);
> + perf_sample__exit(&sample_sw);
> + return ret;
> }
> #endif
>
> @@ -1826,6 +1829,7 @@ static int guest_session__inject_events(struct guest_session *gs, u64 timestamp)
> return -EINVAL;
> }
>
> + perf_sample__exit(sample);
> gs->fetched = false;

I don't see matching perf_sample__init() in guest_session__fetch(). And
as sashiko reported, there are paths missing perf_sample__exit().

In general, I prefer not having perf_sample__init() in
evsel__parse_sample() since it's already called from the callers and
it'd be easier to match with corresponding __exit() there.

Thanks,
Namhyung

>
> ret = output_bytes(inject, ev, ev->header.size);
> diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
> index efbd9cd60c63..7b881f08906d 100644
> --- a/tools/perf/tests/perf-record.c
> +++ b/tools/perf/tests/perf-record.c
> @@ -297,6 +297,7 @@ static int test__PERF_RECORD(struct test_suite *test __maybe_unused, int subtest
> }
>
> perf_mmap__consume(&md->core);
> + perf_sample__exit(&sample);
> }
> perf_mmap__read_done(&md->core);
> }
> diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
> index 15791fcb76b2..72a8289e846d 100644
> --- a/tools/perf/tests/switch-tracking.c
> +++ b/tools/perf/tests/switch-tracking.c
> @@ -239,11 +239,13 @@ static int add_event(struct evlist *evlist, struct list_head *events,
>
> if (!sample.time) {
> pr_debug("event with no time\n");
> + perf_sample__exit(&sample);
> return -1;
> }
>
> node->event_time = sample.time;
>
> + perf_sample__exit(&sample);
> return 0;
> }
>
> diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
> index 8ff0898799ee..19c97137103c 100644
> --- a/tools/perf/util/callchain.c
> +++ b/tools/perf/util/callchain.c
> @@ -1854,16 +1854,19 @@ int sample__merge_deferred_callchain(struct perf_sample *sample_orig,
> u64 nr_deferred = sample_callchain->callchain->nr;
> struct ip_callchain *callchain;
>
> + if (sample_orig->merged_callchain) {
> + /* Already merged. */
> + return -EINVAL;
> + }
> +
> if (sample_orig->callchain->nr < 2) {
> sample_orig->deferred_callchain = false;
> return -EINVAL;
> }
>
> callchain = calloc(1 + nr_orig + nr_deferred, sizeof(u64));
> - if (callchain == NULL) {
> - sample_orig->deferred_callchain = false;
> + if (callchain == NULL)
> return -ENOMEM;
> - }
>
> callchain->nr = nr_orig + nr_deferred;
> /* copy original including PERF_CONTEXT_USER_DEFERRED (but the cookie) */
> @@ -1872,6 +1875,7 @@ int sample__merge_deferred_callchain(struct perf_sample *sample_orig,
> memcpy(&callchain->ips[nr_orig], sample_callchain->callchain->ips,
> nr_deferred * sizeof(u64));
>
> + sample_orig->merged_callchain = true;
> sample_orig->callchain = callchain;
> return 0;
> }
> diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
> index 591bdf0b3e2a..bdb196425071 100644
> --- a/tools/perf/util/evlist.c
> +++ b/tools/perf/util/evlist.c
> @@ -1622,8 +1622,11 @@ int evlist__parse_sample(struct evlist *evlist, union perf_event *event, struct
> struct evsel *evsel = evlist__event2evsel(evlist, event);
> int ret;
>
> - if (!evsel)
> + if (!evsel) {
> + /* Ensure the sample is okay for perf_sample__exit. */
> + perf_sample__init(sample, /*all=*/false);
> return -EFAULT;
> + }
> ret = evsel__parse_sample(evsel, event, sample);
> if (ret)
> return ret;
> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> index f59228c1a39e..59efe460d9bc 100644
> --- a/tools/perf/util/evsel.c
> +++ b/tools/perf/util/evsel.c
> @@ -3067,7 +3067,7 @@ static inline bool overflow(const void *endp, u16 max_size, const void *offset,
> #define OVERFLOW_CHECK(offset, size, max_size) \
> do { \
> if (overflow(endp, (max_size), (offset), (size))) \
> - return -EFAULT; \
> + goto out_efault; \
> } while (0)
>
> #define OVERFLOW_CHECK_u64(offset) \
> @@ -3199,6 +3199,8 @@ static int __set_offcpu_sample(struct perf_sample *data)
> data->cgroup = *array;
>
> return 0;
> +out_efault:
> + return -EFAULT;
> }
>
> int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
> @@ -3217,7 +3219,7 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
> */
> union u64_swap u;
>
> - memset(data, 0, sizeof(*data));
> + perf_sample__init(data, /*all=*/true);
> data->cpu = data->pid = data->tid = -1;
> data->stream_id = data->id = data->time = -1ULL;
> data->period = evsel->core.attr.sample_period;
> @@ -3231,25 +3233,26 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
>
> data->callchain = (struct ip_callchain *)&event->callchain_deferred.nr;
> if (data->callchain->nr > max_callchain_nr)
> - return -EFAULT;
> + goto out_efault;
>
> data->deferred_cookie = event->callchain_deferred.cookie;
>
> if (evsel->core.attr.sample_id_all)
> perf_evsel__parse_id_sample(evsel, event, data);
> +
> return 0;
> }
>
> if (event->header.type != PERF_RECORD_SAMPLE) {
> - if (!evsel->core.attr.sample_id_all)
> - return 0;
> - return perf_evsel__parse_id_sample(evsel, event, data);
> + if (evsel->core.attr.sample_id_all)
> + perf_evsel__parse_id_sample(evsel, event, data);
> + return 0;
> }
>
> array = event->sample.array;
>
> if (perf_event__check_size(event, evsel->sample_size))
> - return -EFAULT;
> + goto out_efault;
>
> if (type & PERF_SAMPLE_IDENTIFIER) {
> data->id = *array;
> @@ -3342,7 +3345,7 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
> sizeof(struct sample_read_value);
>
> if (data->read.group.nr > max_group_nr)
> - return -EFAULT;
> + goto out_efault;
>
> sz = data->read.group.nr * sample_read_value_size(read_format);
> OVERFLOW_CHECK(array, sz, max_size);
> @@ -3370,7 +3373,7 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
> data->callchain = (struct ip_callchain *)array++;
> callchain_nr = data->callchain->nr;
> if (callchain_nr > max_callchain_nr)
> - return -EFAULT;
> + goto out_efault;
> sz = callchain_nr * sizeof(u64);
> /*
> * Save the cookie for the deferred user callchain. The last 2
> @@ -3428,7 +3431,7 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
> data->branch_stack = (struct branch_stack *)array++;
>
> if (data->branch_stack->nr > max_branch_nr)
> - return -EFAULT;
> + goto out_efault;
>
> sz = data->branch_stack->nr * sizeof(struct branch_entry);
> if (evsel__has_branch_hw_idx(evsel)) {
> @@ -3505,7 +3508,7 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
> data->user_stack.size = *array++;
> if (WARN_ONCE(data->user_stack.size > sz,
> "user stack dump failure\n"))
> - return -EFAULT;
> + goto out_efault;
> }
> }
>
> @@ -3582,10 +3585,15 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
> array = (void *)array + sz;
> }
>
> - if (evsel__is_offcpu_event(evsel))
> - return __set_offcpu_sample(data);
> + if (evsel__is_offcpu_event(evsel)) {
> + if (__set_offcpu_sample(data))
> + goto out_efault;
> + }
>
> return 0;
> +out_efault:
> + perf_sample__exit(data);
> + return -EFAULT;
> }
>
> int evsel__parse_sample_timestamp(struct evsel *evsel, union perf_event *event,
> diff --git a/tools/perf/util/powerpc-vpadtl.c b/tools/perf/util/powerpc-vpadtl.c
> index d1c3396f182f..993ab16614c7 100644
> --- a/tools/perf/util/powerpc-vpadtl.c
> +++ b/tools/perf/util/powerpc-vpadtl.c
> @@ -182,7 +182,9 @@ static int powerpc_vpadtl_sample(struct powerpc_vpadtl_entry *record,
> {
> struct perf_sample sample;
> union perf_event event;
> + int ret;
>
> + perf_sample__init(&sample, /*all=*/true);
> sample.ip = be64_to_cpu(record->srr0);
> sample.period = 1;
> sample.cpu = cpu;
> @@ -198,12 +200,12 @@ static int powerpc_vpadtl_sample(struct powerpc_vpadtl_entry *record,
> event.sample.header.misc = sample.cpumode;
> event.sample.header.size = sizeof(struct perf_event_header);
>
> - if (perf_session__deliver_synth_event(vpa->session, &event, &sample)) {
> + ret = perf_session__deliver_synth_event(vpa->session, &event, &sample);
> + if (ret)
> pr_debug("Failed to create sample for dtl entry\n");
> - return -1;
> - }
>
> - return 0;
> + perf_sample__exit(&sample);
> + return ret;
> }
>
> static int powerpc_vpadtl_get_buffer(struct powerpc_vpadtl_queue *vpaq)
> diff --git a/tools/perf/util/sample.c b/tools/perf/util/sample.c
> index 8f82aaf1aab6..2a30de4573f6 100644
> --- a/tools/perf/util/sample.c
> +++ b/tools/perf/util/sample.c
> @@ -21,13 +21,19 @@ void perf_sample__init(struct perf_sample *sample, bool all)
> } else {
> sample->user_regs = NULL;
> sample->intr_regs = NULL;
> + sample->merged_callchain = false;
> + sample->callchain = NULL;
> }
> }
>
> void perf_sample__exit(struct perf_sample *sample)
> {
> - free(sample->user_regs);
> - free(sample->intr_regs);
> + zfree(&sample->user_regs);
> + zfree(&sample->intr_regs);
> + if (sample->merged_callchain) {
> + zfree(&sample->callchain);
> + sample->merged_callchain = false;
> + }
> }
>
> struct regs_dump *perf_sample__user_regs(struct perf_sample *sample)
> diff --git a/tools/perf/util/sample.h b/tools/perf/util/sample.h
> index 8d4ace0e6594..5809c42631e5 100644
> --- a/tools/perf/util/sample.h
> +++ b/tools/perf/util/sample.h
> @@ -155,12 +155,6 @@ struct perf_sample {
> * intel-pt. The instruction itself is held in insn.
> */
> u16 insn_len;
> - /**
> - * @cpumode: The cpumode from struct perf_event_header misc variable
> - * masked with CPUMODE_MASK. Gives user, kernel and hypervisor
> - * information.
> - */
> - u8 cpumode;
> /** @misc: The entire struct perf_event_header misc variable. */
> u16 misc;
> /**
> @@ -174,6 +168,12 @@ struct perf_sample {
> * powerpc holds p_stage_cyc.
> */
> u16 weight3;
> + /**
> + * @cpumode: The cpumode from struct perf_event_header misc variable
> + * masked with CPUMODE_MASK. Gives user, kernel and hypervisor
> + * information.
> + */
> + u8 cpumode;
> /**
> * @no_hw_idx: For PERF_SAMPLE_BRANCH_STACK, true when
> * PERF_SAMPLE_BRANCH_HW_INDEX isn't set.
> @@ -184,6 +184,11 @@ struct perf_sample {
> * user callchain marker was encountered.
> */
> bool deferred_callchain;
> + /**
> + * @merged_callchain: A synthesized merged callchain that is allocated
> + * and needs freeing.
> + */
> + bool merged_callchain;
> /**
> * @deferred_cookie: Identifier of the deferred callchain in the later
> * PERF_RECORD_CALLCHAIN_DEFERRED event.
> diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
> index 4b465abfa36c..c48e840da7d4 100644
> --- a/tools/perf/util/session.c
> +++ b/tools/perf/util/session.c
> @@ -1367,14 +1367,18 @@ static int evlist__deliver_deferred_callchain(struct evlist *evlist,
> list_for_each_entry_safe(de, tmp, &evlist->deferred_samples, list) {
> struct perf_sample orig_sample;
>
> + perf_sample__init(&orig_sample, /*all=*/false);
> ret = evlist__parse_sample(evlist, de->event, &orig_sample);
> if (ret < 0) {
> pr_err("failed to parse original sample\n");
> + perf_sample__exit(&orig_sample);
> break;
> }
>
> - if (sample->tid != orig_sample.tid)
> + if (sample->tid != orig_sample.tid) {
> + perf_sample__exit(&orig_sample);
> continue;
> + }
>
> if (event->callchain_deferred.cookie == orig_sample.deferred_cookie)
> sample__merge_deferred_callchain(&orig_sample, sample);
> @@ -1385,9 +1389,7 @@ static int evlist__deliver_deferred_callchain(struct evlist *evlist,
> ret = evlist__deliver_sample(evlist, tool, de->event,
> &orig_sample, evsel, machine);
>
> - if (orig_sample.deferred_callchain)
> - free(orig_sample.callchain);
> -
> + perf_sample__exit(&orig_sample);
> list_del(&de->list);
> free(de->event);
> free(de);
> @@ -1414,9 +1416,11 @@ static int session__flush_deferred_samples(struct perf_session *session,
> list_for_each_entry_safe(de, tmp, &evlist->deferred_samples, list) {
> struct perf_sample sample;
>
> + perf_sample__init(&sample, /*all=*/false);
> ret = evlist__parse_sample(evlist, de->event, &sample);
> if (ret < 0) {
> pr_err("failed to parse original sample\n");
> + perf_sample__exit(&sample);
> break;
> }
>
> @@ -1424,6 +1428,7 @@ static int session__flush_deferred_samples(struct perf_session *session,
> ret = evlist__deliver_sample(evlist, tool, de->event,
> &sample, evsel, machine);
>
> + perf_sample__exit(&sample);
> list_del(&de->list);
> free(de->event);
> free(de);
> --
> 2.53.0.959.g497ff81fa9-goog
>