perf sample: Make user_regs and intr_regs optional

The struct dump_regs contains 512 bytes of cache_regs, meaning the two
values in perf_sample contribute 1088 bytes of its total 1384 bytes
size. Initializing this much memory has a cost reported by Tavian
Barnes <tavianator@tavianator.com> as about 2.5% when running `perf
script --itrace=i0`:
https://lore.kernel.org/lkml/d841b97b3ad2ca8bcab07e4293375fb7c32dfce7.1736618095.git.tavianator@tavianator.com/

Adrian Hunter <adrian.hunter@intel.com> replied that the zero
initialization was necessary and couldn't simply be removed.

This patch aims to strike a middle ground of still zeroing the
perf_sample, but removing 79% of its size by make user_regs and
intr_regs optional pointers to zalloc-ed memory. To support the
allocation accessors are created for user_regs and intr_regs. To
support correct cleanup perf_sample__init and perf_sample__exit
functions are created and added throughout the code base.

Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250113194345.1537821-1-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>

18 files changed, 351 insertions, 147 deletions

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 5ec97e8d6b6d..034a6603d5a8 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -67,6 +67,7 @@ perf-util-y += maps.o
 perf-util-y += pstack.o
 perf-util-y += session.o
 perf-util-y += tool.o
+perf-util-y += sample.o
 perf-util-y += sample-raw.o
 perf-util-y += s390-sample-raw.o
 perf-util-y += amd-sample-raw.o
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 12761c39788f..251d214adf7f 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -379,8 +379,10 @@ static int arm_spe__synth_mem_sample(struct arm_spe_queue *speq,
 	struct arm_spe *spe = speq->spe;
 	struct arm_spe_record *record = &speq->decoder->record;
 	union perf_event *event = speq->event_buf;
-	struct perf_sample sample = { .ip = 0, };
+	struct perf_sample sample;
+	int ret;
 
+	perf_sample__init(&sample, /*all=*/true);
 	arm_spe_prep_sample(spe, speq, event, &sample);
 
 	sample.id = spe_events_id;
@@ -390,7 +392,9 @@ static int arm_spe__synth_mem_sample(struct arm_spe_queue *speq,
 	sample.data_src = data_src;
 	sample.weight = record->latency;
 
-	return arm_spe_deliver_synth_event(spe, speq, event, &sample);
+	ret = arm_spe_deliver_synth_event(spe, speq, event, &sample);
+	perf_sample__exit(&sample);
+	return ret;
 }
 
 static int arm_spe__synth_branch_sample(struct arm_spe_queue *speq,
@@ -399,8 +403,10 @@ static int arm_spe__synth_branch_sample(struct arm_spe_queue *speq,
 	struct arm_spe *spe = speq->spe;
 	struct arm_spe_record *record = &speq->decoder->record;
 	union perf_event *event = speq->event_buf;
-	struct perf_sample sample = { .ip = 0, };
+	struct perf_sample sample;
+	int ret;
 
+	perf_sample__init(&sample, /*all=*/true);
 	arm_spe_prep_sample(spe, speq, event, &sample);
 
 	sample.id = spe_events_id;
@@ -409,7 +415,9 @@ static int arm_spe__synth_branch_sample(struct arm_spe_queue *speq,
 	sample.weight = record->latency;
 	sample.flags = speq->flags;
 
-	return arm_spe_deliver_synth_event(spe, speq, event, &sample);
+	ret = arm_spe_deliver_synth_event(spe, speq, event, &sample);
+	perf_sample__exit(&sample);
+	return ret;
 }
 
 static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq,
@@ -418,7 +426,8 @@ static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq,
 	struct arm_spe *spe = speq->spe;
 	struct arm_spe_record *record = &speq->decoder->record;
 	union perf_event *event = speq->event_buf;
-	struct perf_sample sample = { .ip = 0, };
+	struct perf_sample sample;
+	int ret;
 
 	/*
 	 * Handles perf instruction sampling period.
@@ -428,6 +437,7 @@ static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq,
 		return 0;
 	speq->period_instructions = 0;
 
+	perf_sample__init(&sample, /*all=*/true);
 	arm_spe_prep_sample(spe, speq, event, &sample);
 
 	sample.id = spe_events_id;
@@ -439,7 +449,9 @@ static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq,
 	sample.weight = record->latency;
 	sample.flags = speq->flags;
 
-	return arm_spe_deliver_synth_event(spe, speq, event, &sample);
+	ret = arm_spe_deliver_synth_event(spe, speq, event, &sample);
+	perf_sample__exit(&sample);
+	return ret;
 }
 
 static const struct midr_range common_ds_encoding_cpus[] = {
diff --git a/tools/perf/util/arm64-frame-pointer-unwind-support.c b/tools/perf/util/arm64-frame-pointer-unwind-support.c
index 4940be4a0569..958afe8b821e 100644
--- a/tools/perf/util/arm64-frame-pointer-unwind-support.c
+++ b/tools/perf/util/arm64-frame-pointer-unwind-support.c
@@ -4,6 +4,7 @@
 #include "event.h"
 #include "perf_regs.h" // SMPL_REG_MASK
 #include "unwind.h"
+#include <string.h>
 
 #define perf_event_arm_regs perf_event_arm64_regs
 #include "../../arch/arm64/include/uapi/asm/perf_regs.h"
@@ -16,8 +17,13 @@ struct entries {
 
 static bool get_leaf_frame_caller_enabled(struct perf_sample *sample)
 {
-	return callchain_param.record_mode == CALLCHAIN_FP && sample->user_regs.regs
-		&& sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_LR);
+	struct regs_dump *regs;
+
+	if (callchain_param.record_mode != CALLCHAIN_FP)
+		return false;
+
+	regs = perf_sample__user_regs(sample);
+	return  regs->regs && regs->mask & SMPL_REG_MASK(PERF_REG_ARM64_LR);
 }
 
 static int add_entry(struct unwind_entry *entry, void *arg)
@@ -32,7 +38,7 @@ u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thr
 {
 	int ret;
 	struct entries entries = {};
-	struct regs_dump old_regs = sample->user_regs;
+	struct regs_dump old_regs, *regs;
 
 	if (!get_leaf_frame_caller_enabled(sample))
 		return 0;
@@ -42,19 +48,20 @@ u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thr
 	 * and set its mask. SP is not used when doing the unwinding but it
 	 * still needs to be set to prevent failures.
 	 */
-
-	if (!(sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_PC))) {
-		sample->user_regs.cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_PC);
-		sample->user_regs.cache_regs[PERF_REG_ARM64_PC] = sample->callchain->ips[usr_idx+1];
+	regs = perf_sample__user_regs(sample);
+	memcpy(&old_regs, regs, sizeof(*regs));
+	if (!(regs->mask & SMPL_REG_MASK(PERF_REG_ARM64_PC))) {
+		regs->cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_PC);
+		regs->cache_regs[PERF_REG_ARM64_PC] = sample->callchain->ips[usr_idx+1];
 	}
 
-	if (!(sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_SP))) {
-		sample->user_regs.cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_SP);
-		sample->user_regs.cache_regs[PERF_REG_ARM64_SP] = 0;
+	if (!(regs->mask & SMPL_REG_MASK(PERF_REG_ARM64_SP))) {
+		regs->cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_SP);
+		regs->cache_regs[PERF_REG_ARM64_SP] = 0;
 	}
 
 	ret = unwind__get_entries(add_entry, &entries, thread, sample, 2, true);
-	sample->user_regs = old_regs;
+	memcpy(regs, &old_regs, sizeof(*regs));
 
 	if (ret || entries.length != 2)
 		return ret;
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 4d1633d87eff..03211c2623de 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -1173,16 +1173,19 @@ static int auxtrace_queue_data_cb(struct perf_session *session,
 	if (!qd->samples || event->header.type != PERF_RECORD_SAMPLE)
 		return 0;
 
+	perf_sample__init(&sample, /*all=*/false);
 	err = evlist__parse_sample(session->evlist, event, &sample);
 	if (err)
-		return err;
-
-	if (!sample.aux_sample.size)
-		return 0;
+		goto out;
 
-	offset += sample.aux_sample.data - (void *)event;
+	if (sample.aux_sample.size) {
+		offset += sample.aux_sample.data - (void *)event;
 
-	return session->auxtrace->queue_data(session, &sample, NULL, offset);
+		err = session->auxtrace->queue_data(session, &sample, NULL, offset);
+	}
+out:
+	perf_sample__exit(&sample);
+	return err;
 }
 
 int auxtrace_queue_data(struct perf_session *session, bool samples, bool events)
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 0bf9e5c27b59..30f4bb3e7fa3 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -506,20 +506,27 @@ static int cs_etm__process_aux_output_hw_id(struct perf_session *session,
 	evsel = evlist__event2evsel(session->evlist, event);
 	if (!evsel)
 		return -EINVAL;
+	perf_sample__init(&sample, /*all=*/false);
 	err = evsel__parse_sample(evsel, event, &sample);
 	if (err)
-		return err;
+		goto out;
 	cpu = sample.cpu;
 	if (cpu == -1) {
 		/* no CPU in the sample - possibly recorded with an old version of perf */
 		pr_err("CS_ETM: no CPU AUX_OUTPUT_HW_ID sample. Use compatible perf to record.");
-		return -EINVAL;
+		err = -EINVAL;
+		goto out;
 	}
 
-	if (FIELD_GET(CS_AUX_HW_ID_MINOR_VERSION_MASK, hw_id) == 0)
-		return cs_etm__process_trace_id_v0(etm, cpu, hw_id);
+	if (FIELD_GET(CS_AUX_HW_ID_MINOR_VERSION_MASK, hw_id) == 0) {
+		err = cs_etm__process_trace_id_v0(etm, cpu, hw_id);
+		goto out;
+	}
 
-	return cs_etm__process_trace_id_v0_1(etm, cpu, hw_id);
+	err = cs_etm__process_trace_id_v0_1(etm, cpu, hw_id);
+out:
+	perf_sample__exit(&sample);
+	return err;
 }
 
 void cs_etm__etmq_set_traceid_queue_timestamp(struct cs_etm_queue *etmq,
@@ -1560,8 +1567,9 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 	int ret = 0;
 	struct cs_etm_auxtrace *etm = etmq->etm;
 	union perf_event *event = tidq->event_buf;
-	struct perf_sample sample = {.ip = 0,};
+	struct perf_sample sample;
 
+	perf_sample__init(&sample, /*all=*/true);
 	event->sample.header.type = PERF_RECORD_SAMPLE;
 	event->sample.header.misc = cs_etm__cpu_mode(etmq, addr, tidq->el);
 	event->sample.header.size = sizeof(struct perf_event_header);
@@ -1598,6 +1606,7 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 			"CS ETM Trace: failed to deliver instruction event, error %d\n",
 			ret);
 
+	perf_sample__exit(&sample);
 	return ret;
 }
 
@@ -3151,9 +3160,10 @@ static int cs_etm__queue_aux_records_cb(struct perf_session *session, union perf
 	evsel = evlist__event2evsel(session->evlist, event);
 	if (!evsel)
 		return -EINVAL;
+	perf_sample__init(&sample, /*all=*/false);
 	ret = evsel__parse_sample(evsel, event, &sample);
 	if (ret)
-		return ret;
+		goto out;
 
 	/*
 	 * Loop through the auxtrace index to find the buffer that matches up with this aux event.
@@ -3168,7 +3178,7 @@ static int cs_etm__queue_aux_records_cb(struct perf_session *session, union perf
 			 * 1 ('not found')
 			 */
 			if (ret != 1)
-				return ret;
+				goto out;
 		}
 	}
 
@@ -3178,7 +3188,10 @@ static int cs_etm__queue_aux_records_cb(struct perf_session *session, union perf
 	 */
 	pr_err("CS ETM: Couldn't find auxtrace buffer for aux_offset: %#"PRI_lx64
 	       " tid: %d cpu: %d\n", event->aux.aux_offset, sample.tid, sample.cpu);
-	return 0;
+	ret = 0;
+out:
+	perf_sample__exit(&sample);
+	return ret;
 }
 
 static int cs_etm__queue_aux_records(struct perf_session *session)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 4009f7d58415..4a0ef095db92 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -3174,17 +3174,19 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 	}
 
 	if (type & PERF_SAMPLE_REGS_USER) {
+		struct regs_dump *regs = perf_sample__user_regs(data);
+
 		OVERFLOW_CHECK_u64(array);
-		data->user_regs.abi = *array;
+		regs->abi = *array;
 		array++;
 
-		if (data->user_regs.abi) {
+		if (regs->abi) {
 			u64 mask = evsel->core.attr.sample_regs_user;
 
 			sz = hweight64(mask) * sizeof(u64);
 			OVERFLOW_CHECK(array, sz, max_size);
-			data->user_regs.mask = mask;
-			data->user_regs.regs = (u64 *)array;
+			regs->mask = mask;
+			regs->regs = (u64 *)array;
 			array = (void *)array + sz;
 		}
 	}
@@ -3228,19 +3230,20 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 		array++;
 	}
 
-	data->intr_regs.abi = PERF_SAMPLE_REGS_ABI_NONE;
 	if (type & PERF_SAMPLE_REGS_INTR) {
+		struct regs_dump *regs = perf_sample__intr_regs(data);
+
 		OVERFLOW_CHECK_u64(array);
-		data->intr_regs.abi = *array;
+		regs->abi = *array;
 		array++;
 
-		if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) {
+		if (regs->abi != PERF_SAMPLE_REGS_ABI_NONE) {
 			u64 mask = evsel->core.attr.sample_regs_intr;
 
 			sz = hweight64(mask) * sizeof(u64);
 			OVERFLOW_CHECK(array, sz, max_size);
-			data->intr_regs.mask = mask;
-			data->intr_regs.regs = (u64 *)array;
+			regs->mask = mask;
+			regs->regs = (u64 *)array;
 			array = (void *)array + sz;
 		}
 	}
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index a7c589fecb98..3625c6224750 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -275,12 +275,13 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
 	int ret;
 	struct intel_bts *bts = btsq->bts;
 	union perf_event event;
-	struct perf_sample sample = { .ip = 0, };
+	struct perf_sample sample;
 
 	if (bts->synth_opts.initial_skip &&
 	    bts->num_events++ <= bts->synth_opts.initial_skip)
 		return 0;
 
+	perf_sample__init(&sample, /*all=*/true);
 	sample.ip = le64_to_cpu(branch->from);
 	sample.cpumode = intel_bts_cpumode(bts, sample.ip);
 	sample.pid = btsq->pid;
@@ -312,6 +313,7 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
 		pr_err("Intel BTS: failed to deliver branch event, error %d\n",
 		       ret);
 
+	perf_sample__exit(&sample);
 	return ret;
 }
 
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 30be6dfe09eb..4e8a9b172fbc 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -1764,12 +1764,13 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
 {
 	struct intel_pt *pt = ptq->pt;
 	union perf_event *event = ptq->event_buf;
-	struct perf_sample sample = { .ip = 0, };
+	struct perf_sample sample;
 	struct dummy_branch_stack {
 		u64			nr;
 		u64			hw_idx;
 		struct branch_entry	entries;
 	} dummy_bs;
+	int ret;
 
 	if (pt->branches_filter && !(pt->branches_filter & ptq->flags))
 		return 0;
@@ -1777,6 +1778,7 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
 	if (intel_pt_skip_event(pt))
 		return 0;
 
+	perf_sample__init(&sample, /*all=*/true);
 	intel_pt_prep_b_sample(pt, ptq, event, &sample);
 
 	sample.id = ptq->pt->branches_id;
@@ -1806,8 +1808,10 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
 		ptq->last_br_cyc_cnt = ptq->ipc_cyc_cnt;
 	}
 
-	return intel_pt_deliver_synth_event(pt, event, &sample,
+	perf_sample__exit(&sample);
+	ret = intel_pt_deliver_synth_event(pt, event, &sample,
 					    pt->branches_sample_type);
+	return ret;
 }
 
 static void intel_pt_prep_sample(struct intel_pt *pt,
@@ -1835,11 +1839,13 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
 {
 	struct intel_pt *pt = ptq->pt;
 	union perf_event *event = ptq->event_buf;
-	struct perf_sample sample = { .ip = 0, };
+	struct perf_sample sample;
+	int ret;
 
 	if (intel_pt_skip_event(pt))
 		return 0;
 
+	perf_sample__init(&sample, /*all=*/true);
 	intel_pt_prep_sample(pt, ptq, event, &sample);
 
 	sample.id = ptq->pt->instructions_id;
@@ -1859,16 +1865,19 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
 
 	ptq->last_insn_cnt = ptq->state->tot_insn_cnt;
 
-	return intel_pt_deliver_synth_event(pt, event, &sample,
-					    pt->instructions_sample_type);
+	ret = intel_pt_deliver_synth_event(pt, event, &sample,
+					   pt->instructions_sample_type);
+	perf_sample__exit(&sample);
+	return ret;
 }
 
 static int intel_pt_synth_cycle_sample(struct intel_pt_queue *ptq)
 {
 	struct intel_pt *pt = ptq->pt;
 	union perf_event *event = ptq->event_buf;
-	struct perf_sample sample = { .ip = 0, };
+	struct perf_sample sample;
 	u64 period = 0;
+	int ret;
 
 	if (ptq->sample_ipc)
 		period = ptq->ipc_cyc_cnt - ptq->last_cy_cyc_cnt;
@@ -1876,6 +1885,7 @@ static int intel_pt_synth_cycle_sample(struct intel_pt_queue *ptq)
 	if (!period || intel_pt_skip_event(pt))
 		return 0;
 
+	perf_sample__init(&sample, /*all=*/true);
 	intel_pt_prep_sample(pt, ptq, event, &sample);
 
 	sample.id = ptq->pt->cycles_id;
@@ -1887,25 +1897,31 @@ static int intel_pt_synth_cycle_sample(struct intel_pt_queue *ptq)
 	ptq->last_cy_insn_cnt = ptq->ipc_insn_cnt;
 	ptq->last_cy_cyc_cnt = ptq->ipc_cyc_cnt;
 
-	return intel_pt_deliver_synth_event(pt, event, &sample, pt->cycles_sample_type);
+	ret = intel_pt_deliver_synth_event(pt, event, &sample, pt->cycles_sample_type);
+	perf_sample__exit(&sample);
+	return ret;
 }
 
 static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq)
 {
 	struct intel_pt *pt = ptq->pt;
 	union perf_event *event = ptq->event_buf;
-	struct perf_sample sample = { .ip = 0, };
+	struct perf_sample sample;
+	int ret;
 
 	if (intel_pt_skip_event(pt))
 		return 0;
 
+	perf_sample__init(&sample, /*all=*/true);
 	intel_pt_prep_sample(pt, ptq, event, &sample);
 
 	sample.id = ptq->pt->transactions_id;
 	sample.stream_id = ptq->pt->transactions_id;
 
-	return intel_pt_deliver_synth_event(pt, event, &sample,
-					    pt->transactions_sample_type);
+	ret = intel_pt_deliver_synth_event(pt, event, &sample,
+					   pt->transactions_sample_type);
+	perf_sample__exit(&sample);
+	return ret;
 }
 
 static void intel_pt_prep_p_sample(struct intel_pt *pt,
@@ -1953,15 +1969,17 @@ static int intel_pt_synth_cbr_sample(struct intel_pt_queue *ptq)
 {
 	struct intel_pt *pt = ptq->pt;
 	union perf_event *event = ptq->event_buf;
-	struct perf_sample sample = { .ip = 0, };
+	struct perf_sample sample;
 	struct perf_synth_intel_cbr raw;
 	u32 flags;
+	int ret;
 
 	if (intel_pt_skip_cbr_event(pt))
 		return 0;
 
 	ptq->cbr_seen = ptq->state->cbr;
 
+	perf_sample__init(&sample, /*all=*/true);
 	intel_pt_prep_p_sample(pt, ptq, event, &sample);
 
 	sample.id = ptq->pt->cbr_id;
@@ -1975,20 +1993,24 @@ static int intel_pt_synth_cbr_sample(struct intel_pt_queue *ptq)
 	sample.raw_size = perf_synth__raw_size(raw);
 	sample.raw_data = perf_synth__raw_data(&raw);
 
-	return intel_pt_deliver_synth_event(pt, event, &sample,
-					    pt->pwr_events_sample_type);
+	ret = intel_pt_deliver_synth_event(pt, event, &sample,
+					   pt->pwr_events_sample_type);
+	perf_sample__exit(&sample);
+	return ret;
 }
 
 static int intel_pt_synth_psb_sample(struct intel_pt_queue *ptq)
 {
 	struct intel_pt *pt = ptq->pt;
 	union perf_event *event = ptq->event_buf;
-	struct perf_sample sample = { .ip = 0, };
+	struct perf_sample sample;
 	struct perf_synth_intel_psb raw;
+	int ret;
 
 	if (intel_pt_skip_event(pt))
 		return 0;
 
+	perf_sample__init(&sample, /*all=*/true);
 	intel_pt_prep_p_sample(pt, ptq, event, &sample);
 
 	sample.id = ptq->pt->psb_id;
@@ -2001,20 +2023,24 @@ static int intel_pt_synth_psb_sample(struct intel_pt_queue *ptq)
 	sample.raw_size = perf_synth__raw_size(raw);
 	sample.raw_data = perf_synth__raw_data(&raw);
 
-	return intel_pt_deliver_synth_event(pt, event, &sample,
-					    pt->pwr_events_sample_type);
+	ret = intel_pt_deliver_synth_event(pt, event, &sample,
+					   pt->pwr_events_sample_type);
+	perf_sample__exit(&sample);
+	return ret;
 }
 
 static int intel_pt_synth_mwait_sample(struct intel_pt_queue *ptq)
 {
 	struct intel_pt *pt = ptq->pt;
 	union perf_event *event = ptq->event_buf;
-	struct perf_sample sample = { .ip = 0, };
+	struct perf_sample sample;
 	struct perf_synth_intel_mwait raw;
+	int ret;
 
 	if (intel_pt_skip_event(pt))
 		return 0;
 
+	perf_sample__init(&sample, /*all=*/true);
 	intel_pt_prep_p_sample(pt, ptq, event, &sample);
 
 	sample.id = ptq->pt->mwait_id;
@@ -2026,20 +2052,24 @@ static int intel_pt_synth_mwait_sample(struct intel_pt_queue *ptq)
 	sample.raw_size = perf_synth__raw_size(raw);
 	sample.raw_data = perf_synth__raw_data(&raw);
 
-	return intel_pt_deliver_synth_event(pt, event, &sample,
-					    pt->pwr_events_sample_type);
+	ret = intel_pt_deliver_synth_event(pt, event, &sample,
+					   pt->pwr_events_sample_type);
+	perf_sample__exit(&sample);
+	return ret;
 }
 
 static int intel_pt_synth_pwre_sample(struct intel_pt_queue *ptq)
 {
 	struct intel_pt *pt = ptq->pt;
 	union perf_event *event = ptq->event_buf;
-	struct perf_sample sample = { .ip = 0, };
+	struct perf_sample sample;
 	struct perf_synth_intel_pwre raw;
+	int ret;
 
 	if (intel_pt_skip_event(pt))
 		return 0;
 
+	perf_sample__init(&sample, /*all=*/true);
 	intel_pt_prep_p_sample(pt, ptq, event, &sample);
 
 	sample.id = ptq->pt->pwre_id;
@@ -2051,20 +2081,24 @@ static int intel_pt_synth_pwre_sample(struct intel_pt_queue *ptq)
 	sample.raw_size = perf_synth__raw_size(raw);
 	sample.raw_data = perf_synth__raw_data(&raw);
 
-	return intel_pt_deliver_synth_event(pt, event, &sample,
-					    pt->pwr_events_sample_type);
+	ret = intel_pt_deliver_synth_event(pt, event, &sample,
+					   pt->pwr_events_sample_type);
+	perf_sample__exit(&sample);
+	return ret;
 }
 
 static int intel_pt_synth_exstop_sample(struct intel_pt_queue *ptq)
 {
 	struct intel_pt *pt = ptq->pt;
 	union perf_event *event = ptq->event_buf;
-	struct perf_sample sample = { .ip = 0, };
+	struct perf_sample sample;
 	struct perf_synth_intel_exstop raw;
+	int ret;
 
 	if (intel_pt_skip_event(pt))
 		return 0;
 
+	perf_sample__init(&sample, /*all=*/true);
 	intel_pt_prep_p_sample(pt, ptq, event, &sample);
 
 	sample.id = ptq->pt->exstop_id;
@@ -2076,20 +2110,24 @@ static int intel_pt_synth_exstop_sample(struct intel_pt_queue *ptq)
 	sample.raw_size = perf_synth__raw_size(raw);
 	sample.raw_data = perf_synth__raw_data(&raw);
 
-	return intel_pt_deliver_synth_event(pt, event, &sample,
-					    pt->pwr_events_sample_type);
+	ret = intel_pt_deliver_synth_event(pt, event, &sample,
+					   pt->pwr_events_sample_type);
+	perf_sample__exit(&sample);
+	return ret;
 }
 
 static int intel_pt_synth_pwrx_sample(struct intel_pt_queue *ptq)
 {
 	struct intel_pt *pt = ptq->pt;
 	union perf_event *event = ptq->event_buf;
-	struct perf_sample sample = { .ip = 0, };
+	struct perf_sample sample;
 	struct perf_synth_intel_pwrx raw;
+	int ret;
 
 	if (intel_pt_skip_event(pt))
 		return 0;
 
+	perf_sample__init(&sample, /*all=*/true);
 	intel_pt_prep_p_sample(pt, ptq, event, &sample);
 
 	sample.id = ptq->pt->pwrx_id;
@@ -2101,8 +2139,10 @@ static int intel_pt_synth_pwrx_sample(struct intel_pt_queue *ptq)
 	sample.raw_size = perf_synth__raw_size(raw);
 	sample.raw_data = perf_synth__raw_data(&raw);
 
-	return intel_pt_deliver_synth_event(pt, event, &sample,
-					    pt->pwr_events_sample_type);
+	ret = intel_pt_deliver_synth_event(pt, event, &sample,
+					   pt->pwr_events_sample_type);
+	perf_sample__exit(&sample);
+	return ret;
 }
 
 /*
@@ -2235,16 +2275,18 @@ static void intel_pt_add_lbrs(struct branch_stack *br_stack,
 static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evsel *evsel, u64 id)
 {
 	const struct intel_pt_blk_items *items = &ptq->state->items;
-	struct perf_sample sample = { .ip = 0, };
+	struct perf_sample sample;
 	union perf_event *event = ptq->event_buf;
 	struct intel_pt *pt = ptq->pt;
 	u64 sample_type = evsel->core.attr.sample_type;
 	u8 cpumode;
-	u64 regs[8 * sizeof(sample.intr_regs.mask)];
+	u64 regs[8 * sizeof(sample.intr_regs->mask)];
+	int ret;
 
 	if (intel_pt_skip_event(pt))
 		return 0;
 
+	perf_sample__init(&sample, /*all=*/true);
 	intel_pt_prep_a_sample(ptq, event, &sample);
 
 	sample.id = id;
@@ -2291,15 +2333,16 @@ static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evse
 	     items->mask[INTEL_PT_XMM_POS])) {
 		u64 regs_mask = evsel->core.attr.sample_regs_intr;
 		u64 *pos;
+		struct regs_dump *intr_regs = perf_sample__intr_regs(&sample);
 
-		sample.intr_regs.abi = items->is_32_bit ?
+		intr_regs->abi = items->is_32_bit ?
 				       PERF_SAMPLE_REGS_ABI_32 :
 				       PERF_SAMPLE_REGS_ABI_64;
-		sample.intr_regs.regs = regs;
+		intr_regs->regs = regs;
 
-		pos = intel_pt_add_gp_regs(&sample.intr_regs, regs, items, regs_mask);
+		pos = intel_pt_add_gp_regs(intr_regs, regs, items, regs_mask);
 
-		intel_pt_add_xmm(&sample.intr_regs, pos, items, regs_mask);
+		intel_pt_add_xmm(intr_regs, pos, items, regs_mask);
 	}
 
 	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
@@ -2361,7 +2404,9 @@ static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evse
 		sample.transaction = txn;
 	}
 
-	return intel_pt_deliver_synth_event(pt, event, &sample, sample_type);
+	ret = intel_pt_deliver_synth_event(pt, event, &sample, sample_type);
+	perf_sample__exit(&sample);
+	return ret;
 }
 
 static int intel_pt_synth_single_pebs_sample(struct intel_pt_queue *ptq)
@@ -2407,16 +2452,17 @@ static int intel_pt_synth_events_sample(struct intel_pt_queue *ptq)
 {
 	struct intel_pt *pt = ptq->pt;
 	union perf_event *event = ptq->event_buf;
-	struct perf_sample sample = { .ip = 0, };
+	struct perf_sample sample;
 	struct {
 		struct perf_synth_intel_evt cfe;
 		struct perf_synth_intel_evd evd[INTEL_PT_MAX_EVDS];
 	} raw;
-	int i;
+	int i, ret;
 
 	if (intel_pt_skip_event(pt))
 		return 0;
 
+	perf_sample__init(&sample, /*all=*/true);
 	intel_pt_prep_p_sample(pt, ptq, event, &sample);
 
 	sample.id        = ptq->pt->evt_id;
@@ -2438,20 +2484,24 @@ static int intel_pt_synth_events_sample(struct intel_pt_queue *ptq)
 			  ptq->state->evd_cnt * sizeof(struct perf_synth_intel_evd);
 	sample.raw_data = perf_synth__raw_data(&raw);
 
-	return intel_pt_deliver_synth_event(pt, event, &sample,
-					    pt->evt_sample_type);
+	ret = intel_pt_deliver_synth_event(pt, event, &sample,
+					   pt->evt_sample_type);
+	perf_sample__exit(&sample);
+	return ret;
 }
 
 static int intel_pt_synth_iflag_chg_sample(struct intel_pt_queue *ptq)
 {
 	struct intel_pt *pt = ptq->pt;
 	union perf_event *event = ptq->event_buf;
-	struct perf_sample sample = { .ip = 0, };
+	struct perf_sample sample;
 	struct perf_synth_intel_iflag_chg raw;
+	int ret;
 
 	if (intel_pt_skip_event(pt))
 		return 0;
 
+	perf_sample__init(&sample, /*all=*/true);
 	intel_pt_prep_p_sample(pt, ptq, event, &sample);
 
 	sample.id = ptq->pt->iflag_chg_id;
@@ -2471,8 +2521,10 @@ static int intel_pt_synth_iflag_chg_sample(struct intel_pt_queue *ptq)
 	sample.raw_size = perf_synth__raw_size(raw);
 	sample.raw_data = perf_synth__raw_data(&raw);
 
-	return intel_pt_deliver_synth_event(pt, event, &sample,
-					    pt->iflag_chg_sample_type);
+	ret = intel_pt_deliver_synth_event(pt, event, &sample,
+					   pt->iflag_chg_sample_type);
+	perf_sample__exit(&sample);
+	return ret;
 }
 
 static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu,
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
index f23e21502bf8..624964f01b5f 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -516,7 +516,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr)
 	 * create pseudo sample to induce dso hit increment
 	 * use first address as sample address
 	 */
-	memset(&sample, 0, sizeof(sample));
+	perf_sample__init(&sample, /*all=*/true);
 	sample.cpumode = PERF_RECORD_MISC_USER;
 	sample.pid  = pid;
 	sample.tid  = tid;
@@ -535,6 +535,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr)
 		build_id__mark_dso_hit(tool, event, &sample, NULL, jd->machine);
 
 out:
+	perf_sample__exit(&sample);
 	free(event);
 	return ret;
 }
@@ -611,7 +612,7 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr)
 	 * create pseudo sample to induce dso hit increment
 	 * use first address as sample address
 	 */
-	memset(&sample, 0, sizeof(sample));
+	perf_sample__init(&sample, /*all=*/true);
 	sample.cpumode = PERF_RECORD_MISC_USER;
 	sample.pid  = pid;
 	sample.tid  = tid;
@@ -620,12 +621,13 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr)
 
 	ret = perf_event__process_mmap2(tool, event, &sample, jd->machine);
 	if (ret)
-		return ret;
+		goto out;
 
 	ret = jit_inject_event(jd, event);
 	if (!ret)
 		build_id__mark_dso_hit(tool, event, &sample, NULL, jd->machine);
-
+out:
+	perf_sample__exit(&sample);
 	return ret;
 }
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 321cc110698c..55d4977b9913 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2909,8 +2909,8 @@ static int thread__resolve_callchain_unwind(struct thread *thread,
 		return 0;
 
 	/* Bail out if nothing was captured. */
-	if ((!sample->user_regs.regs) ||
-	    (!sample->user_stack.size))
+	if (!sample->user_regs || !sample->user_regs->regs ||
+	    !sample->user_stack.size)
 		return 0;
 
 	if (!symbols)
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index b4bc57859f73..e2b9032c1311 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -270,6 +270,12 @@ static PyMemberDef pyrf_sample_event__members[] = {
 	{ .name = NULL, },
 };
 
+static void pyrf_sample_event__delete(struct pyrf_event *pevent)
+{
+	perf_sample__exit(&pevent->sample);
+	Py_TYPE(pevent)->tp_free((PyObject*)pevent);
+}
+
 static PyObject *pyrf_sample_event__repr(const struct pyrf_event *pevent)
 {
 	PyObject *ret;
@@ -428,6 +434,9 @@ static int pyrf_event__setup_types(void)
 	pyrf_sample_event__type.tp_new =
 	pyrf_context_switch_event__type.tp_new =
 	pyrf_throttle_event__type.tp_new = PyType_GenericNew;
+
+	pyrf_sample_event__type.tp_dealloc = (destructor)pyrf_sample_event__delete,
+
 	err = PyType_Ready(&pyrf_mmap_event__type);
 	if (err < 0)
 		goto out;
diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c
index 30638653ad2d..0ce52f0280b8 100644
--- a/tools/perf/util/s390-cpumsf.c
+++ b/tools/perf/util/s390-cpumsf.c
@@ -513,6 +513,7 @@ static bool s390_cpumsf_make_event(size_t pos,
 				.period = 1
 			    };
 	union perf_event event;
+	int ret;
 
 	memset(&event, 0, sizeof(event));
 	if (basic->CL == 1)	/* Native LPAR mode */
@@ -536,8 +537,9 @@ static bool s390_cpumsf_make_event(size_t pos,
 	pr_debug4("%s pos:%#zx ip:%#" PRIx64 " P:%d CL:%d pid:%d.%d cpumode:%d cpu:%d\n",
 		 __func__, pos, sample.ip, basic->P, basic->CL, sample.pid,
 		 sample.tid, sample.cpumode, sample.cpu);
-	if (perf_session__deliver_synth_event(sfq->sf->session, &event,
-					      &sample)) {
+	ret = perf_session__deliver_synth_event(sfq->sf->session, &event, &sample);
+	perf_sample__exit(&sample);
+	if (ret) {
 		pr_err("s390 Auxiliary Trace: failed to deliver event\n");
 		return false;
 	}
diff --git a/tools/perf/util/sample.c b/tools/perf/util/sample.c
new file mode 100644
index 000000000000..605fee971f55
--- /dev/null
+++ b/tools/perf/util/sample.c
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include "sample.h"
+#include "debug.h"
+#include <linux/zalloc.h>
+#include <stdlib.h>
+#include <string.h>
+
+void perf_sample__init(struct perf_sample *sample, bool all)
+{
+	if (all) {
+		memset(sample, 0, sizeof(*sample));
+	} else {
+		sample->user_regs = NULL;
+		sample->intr_regs = NULL;
+	}
+}
+
+void perf_sample__exit(struct perf_sample *sample)
+{
+	free(sample->user_regs);
+	free(sample->intr_regs);
+}
+
+struct regs_dump *perf_sample__user_regs(struct perf_sample *sample)
+{
+	if (!sample->user_regs) {
+		sample->user_regs = zalloc(sizeof(*sample->user_regs));
+		if (!sample->user_regs)
+			pr_err("Failure to allocate sample user_regs");
+	}
+	return sample->user_regs;
+}
+
+
+struct regs_dump *perf_sample__intr_regs(struct perf_sample *sample)
+{
+	if (!sample->intr_regs) {
+		sample->intr_regs = zalloc(sizeof(*sample->intr_regs));
+		if (!sample->intr_regs)
+			pr_err("Failure to allocate sample intr_regs");
+	}
+	return sample->intr_regs;
+}
diff --git a/tools/perf/util/sample.h b/tools/perf/util/sample.h
index 70b2c3135555..bbf71e6406c4 100644
--- a/tools/perf/util/sample.h
+++ b/tools/perf/util/sample.h
@@ -114,14 +114,19 @@ struct perf_sample {
 	struct ip_callchain *callchain;
 	struct branch_stack *branch_stack;
 	u64 *branch_stack_cntr;
-	struct regs_dump  user_regs;
-	struct regs_dump  intr_regs;
+	struct regs_dump  *user_regs;
+	struct regs_dump  *intr_regs;
 	struct stack_dump user_stack;
 	struct sample_read read;
 	struct aux_sample aux_sample;
 	struct simd_flags simd_flags;
 };
 
+void perf_sample__init(struct perf_sample *sample, bool all);
+void perf_sample__exit(struct perf_sample *sample);
+struct regs_dump *perf_sample__user_regs(struct perf_sample *sample);
+struct regs_dump *perf_sample__intr_regs(struct perf_sample *sample);
+
 /*
  * raw_data is always 4 bytes from an 8-byte boundary, so subtract 4 to get
  * 8-byte alignment.
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index b1b5e94537e4..520729e78965 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -745,19 +745,30 @@ static int set_regs_in_dict(PyObject *dict,
 	const char *arch = perf_env__arch(evsel__env(evsel));
 
 	int size = (__sw_hweight64(attr->sample_regs_intr) * MAX_REG_SIZE) + 1;
-	char *bf = malloc(size);
-	if (!bf)
-		return -1;
+	char *bf = NULL;
 
-	regs_map(&sample->intr_regs, attr->sample_regs_intr, arch, bf, size);
+	if (sample->intr_regs) {
+		bf = malloc(size);
+		if (!bf)
+			return -1;
 
-	pydict_set_item_string_decref(dict, "iregs",
-			_PyUnicode_FromString(bf));
+		regs_map(sample->intr_regs, attr->sample_regs_intr, arch, bf, size);
 
-	regs_map(&sample->user_regs, attr->sample_regs_user, arch, bf, size);
+		pydict_set_item_string_decref(dict, "iregs",
+					_PyUnicode_FromString(bf));
+	}
 
-	pydict_set_item_string_decref(dict, "uregs",
-			_PyUnicode_FromString(bf));
+	if (sample->user_regs) {
+		if (!bf) {
+			bf = malloc(size);
+			if (!bf)
+				return -1;
+		}
+		regs_map(sample->user_regs, attr->sample_regs_user, arch, bf, size);
+
+		pydict_set_item_string_decref(dict, "uregs",
+					_PyUnicode_FromString(bf));
+	}
 	free(bf);
 
 	return 0;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index c06e3020a976..c35b7e8ad51f 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -950,7 +950,12 @@ static void regs__printf(const char *type, struct regs_dump *regs, const char *a
 
 static void regs_user__printf(struct perf_sample *sample, const char *arch)
 {
-	struct regs_dump *user_regs = &sample->user_regs;
+	struct regs_dump *user_regs;
+
+	if (!sample->user_regs)
+		return;
+
+	user_regs = perf_sample__user_regs(sample);
 
 	if (user_regs->regs)
 		regs__printf("user", user_regs, arch);
@@ -958,7 +963,12 @@ static void regs_user__printf(struct perf_sample *sample, const char *arch)
 
 static void regs_intr__printf(struct perf_sample *sample, const char *arch)
 {
-	struct regs_dump *intr_regs = &sample->intr_regs;
+	struct regs_dump *intr_regs;
+
+	if (!sample->intr_regs)
+		return;
+
+	intr_regs = perf_sample__intr_regs(sample);
 
 	if (intr_regs->regs)
 		regs__printf("intr", intr_regs, arch);
@@ -1351,25 +1361,30 @@ static int perf_session__deliver_event(struct perf_session *session,
 				       const char *file_path)
 {
 	struct perf_sample sample;
-	int ret = evlist__parse_sample(session->evlist, event, &sample);
+	int ret;
 
+	perf_sample__init(&sample, /*all=*/false);
+	ret = evlist__parse_sample(session->evlist, event, &sample);
 	if (ret) {
 		pr_err("Can't parse sample, err = %d\n", ret);
-		return ret;
+		goto out;
 	}
 
 	ret = auxtrace__process_event(session, event, &sample, tool);
 	if (ret < 0)
-		return ret;
-	if (ret > 0)
-		return 0;
+		goto out;
+	if (ret > 0) {
+		ret = 0;
+		goto out;
+	}
 
 	ret = machines__deliver_event(&session->machines, session->evlist,
 				      event, &sample, tool, file_offset, file_path);
 
 	if (dump_trace && sample.aux_sample.size)
 		auxtrace__dump_auxtrace_sample(session, &sample);
-
+out:
+	perf_sample__exit(&sample);
 	return ret;
 }
 
@@ -1380,10 +1395,11 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 {
 	struct ordered_events *oe = &session->ordered_events;
 	const struct perf_tool *tool = session->tool;
-	struct perf_sample sample = { .time = 0, };
+	struct perf_sample sample;
 	int fd = perf_data__fd(session->data);
 	int err;
 
+	perf_sample__init(&sample, /*all=*/true);
 	if (event->header.type != PERF_RECORD_COMPRESSED || perf_tool__compressed_is_stub(tool))
 		dump_event(session->evlist, event, file_offset, &sample, file_path);
 
@@ -1395,15 +1411,17 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 			perf_session__set_id_hdr_size(session);
 			perf_session__set_comm_exec(session);
 		}
-		return err;
+		break;
 	case PERF_RECORD_EVENT_UPDATE:
-		return tool->event_update(tool, event, &session->evlist);
+		err = tool->event_update(tool, event, &session->evlist);
+		break;
 	case PERF_RECORD_HEADER_EVENT_TYPE:
 		/*
 		 * Deprecated, but we need to handle it for sake
 		 * of old data files create in pipe mode.
 		 */
-		return 0;
+		err = 0;
+		break;
 	case PERF_RECORD_HEADER_TRACING_DATA:
 		/*
 		 * Setup for reading amidst mmap, but only when we
@@ -1412,15 +1430,20 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 		 */
 		if (!perf_data__is_pipe(session->data))
 			lseek(fd, file_offset, SEEK_SET);
-		return tool->tracing_data(session, event);
+		err = tool->tracing_data(session, event);
+		break;
 	case PERF_RECORD_HEADER_BUILD_ID:
-		return tool->build_id(session, event);
+		err = tool->build_id(session, event);
+		break;
 	case PERF_RECORD_FINISHED_ROUND:
-		return tool->finished_round(tool, event, oe);
+		err = tool->finished_round(tool, event, oe);
+		break;
 	case PERF_RECORD_ID_INDEX:
-		return tool->id_index(session, event);
+		err = tool->id_index(session, event);
+		break;
 	case PERF_RECORD_AUXTRACE_INFO:
-		return tool->auxtrace_info(session, event);
+		err = tool->auxtrace_info(session, event);
+		break;
 	case PERF_RECORD_AUXTRACE:
 		/*
 		 * Setup for reading amidst mmap, but only when we
@@ -1429,35 +1452,48 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 		 */
 		if (!perf_data__is_pipe(session->data))
 			lseek(fd, file_offset + event->header.size, SEEK_SET);
-		return tool->auxtrace(session, event);
+		err = tool->auxtrace(session, event);
+		break;
 	case PERF_RECORD_AUXTRACE_ERROR:
 		perf_session__auxtrace_error_inc(session, event);
-		return tool->auxtrace_error(session, event);
+		err = tool->auxtrace_error(session, event);
+		break;
 	case PERF_RECORD_THREAD_MAP:
-		return tool->thread_map(session, event);
+		err = tool->thread_map(session, event);
+		break;
 	case PERF_RECORD_CPU_MAP:
-		return tool->cpu_map(session, event);
+		err = tool->cpu_map(session, event);
+		break;
 	case PERF_RECORD_STAT_CONFIG:
-		return tool->stat_config(session, event);
+		err = tool->stat_config(session, event);
+		break;
 	case PERF_RECORD_STAT:
-		return tool->stat(session, event);
+		err = tool->stat(session, event);
+		break;
 	case PERF_RECORD_STAT_ROUND:
-		return tool->stat_round(session, event);
+		err = tool->stat_round(session, event);
+		break;
 	case PERF_RECORD_TIME_CONV:
 		session->time_conv = event->time_conv;
-		return tool->time_conv(session, event);
+		err = tool->time_conv(session, event);
+		break;
 	case PERF_RECORD_HEADER_FEATURE:
-		return tool->feature(session, event);
+		err = tool->feature(session, event);
+		break;
 	case PERF_RECORD_COMPRESSED:
 		err = tool->compressed(session, event, file_offset, file_path);
 		if (err)
 			dump_event(session->evlist, event, file_offset, &sample, file_path);
-		return err;
+		break;
 	case PERF_RECORD_FINISHED_INIT:
-		return tool->finished_init(session, event);
+		err = tool->finished_init(session, event);
+		break;
 	default:
-		return -EINVAL;
+		err = -EINVAL;
+		break;
 	}
+	perf_sample__exit(&sample);
+	return err;
 }
 
 int perf_session__deliver_synth_event(struct perf_session *session,
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index 6923b0d5efed..2dfc4260d36d 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -1508,9 +1508,9 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 	}
 
 	if (type & PERF_SAMPLE_REGS_USER) {
-		if (sample->user_regs.abi) {
+		if (sample->user_regs && sample->user_regs->abi) {
 			result += sizeof(u64);
-			sz = hweight64(sample->user_regs.mask) * sizeof(u64);
+			sz = hweight64(sample->user_regs->mask) * sizeof(u64);
 			result += sz;
 		} else {
 			result += sizeof(u64);
@@ -1536,9 +1536,9 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 		result += sizeof(u64);
 
 	if (type & PERF_SAMPLE_REGS_INTR) {
-		if (sample->intr_regs.abi) {
+		if (sample->intr_regs && sample->intr_regs->abi) {
 			result += sizeof(u64);
-			sz = hweight64(sample->intr_regs.mask) * sizeof(u64);
+			sz = hweight64(sample->intr_regs->mask) * sizeof(u64);
 			result += sz;
 		} else {
 			result += sizeof(u64);
@@ -1707,10 +1707,10 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo
 	}
 
 	if (type & PERF_SAMPLE_REGS_USER) {
-		if (sample->user_regs.abi) {
-			*array++ = sample->user_regs.abi;
-			sz = hweight64(sample->user_regs.mask) * sizeof(u64);
-			memcpy(array, sample->user_regs.regs, sz);
+		if (sample->user_regs && sample->user_regs->abi) {
+			*array++ = sample->user_regs->abi;
+			sz = hweight64(sample->user_regs->mask) * sizeof(u64);
+			memcpy(array, sample->user_regs->regs, sz);
 			array = (void *)array + sz;
 		} else {
 			*array++ = 0;
@@ -1743,10 +1743,10 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo
 	}
 
 	if (type & PERF_SAMPLE_REGS_INTR) {
-		if (sample->intr_regs.abi) {
-			*array++ = sample->intr_regs.abi;
-			sz = hweight64(sample->intr_regs.mask) * sizeof(u64);
-			memcpy(array, sample->intr_regs.regs, sz);
+		if (sample->intr_regs && sample->intr_regs->abi) {
+			*array++ = sample->intr_regs->abi;
+			sz = hweight64(sample->intr_regs->mask) * sizeof(u64);
+			memcpy(array, sample->intr_regs->regs, sz);
 			array = (void *)array + sz;
 		} else {
 			*array++ = 0;
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index bde216e630d2..793d11832694 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -190,7 +190,10 @@ static bool memory_read(Dwfl *dwfl __maybe_unused, Dwarf_Addr addr, Dwarf_Word *
 	int offset;
 	int ret;
 
-	ret = perf_reg_value(&start, &ui->sample->user_regs,
+	if (!ui->sample->user_regs)
+		return false;
+
+	ret = perf_reg_value(&start, ui->sample->user_regs,
 			     perf_arch_reg_sp(arch));
 	if (ret)
 		return false;
@@ -273,7 +276,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 	Dwarf_Word ip;
 	int err = -EINVAL, i;
 
-	if (!data->user_regs.regs)
+	if (!data->user_regs || !data->user_regs->regs)
 		return -EINVAL;
 
 	ui = zalloc(sizeof(ui_buf) + sizeof(ui_buf.entries[0]) * max_stack);
@@ -286,7 +289,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 	if (!ui->dwfl)
 		goto out;
 
-	err = perf_reg_value(&ip, &data->user_regs, perf_arch_reg_ip(arch));
+	err = perf_reg_value(&ip, data->user_regs, perf_arch_reg_ip(arch));
 	if (err)
 		goto out;