Merge v7.1.5linux-rolling-stable

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

79 files changed, 1700 insertions, 526 deletions

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 333ddd0e4bd8..33f90968c8a9 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -109,6 +109,7 @@ endif
 
 ifeq ($(ARCH),s390)
   CFLAGS += -fPIC
+  CXXFLAGS += -fPIC
 endif
 
 ifeq ($(ARCH),mips)
diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c
index 21836f70f231..ad0cab830a4d 100644
--- a/tools/perf/arch/common.c
+++ b/tools/perf/arch/common.c
@@ -237,5 +237,7 @@ int perf_env__lookup_objdump(struct perf_env *env, char **path)
  */
 bool perf_env__single_address_space(struct perf_env *env)
 {
-	return strcmp(perf_env__arch(env), "sparc");
+	const char *arch = perf_env__arch(env);
+
+	return strcmp(arch, "s390") && strcmp(arch, "sparc");
 }
diff --git a/tools/perf/arch/powerpc/util/auxtrace.c b/tools/perf/arch/powerpc/util/auxtrace.c
index e39deff6c857..4600a1661b4f 100644
--- a/tools/perf/arch/powerpc/util/auxtrace.c
+++ b/tools/perf/arch/powerpc/util/auxtrace.c
@@ -71,6 +71,12 @@ struct auxtrace_record *auxtrace_record__init(struct evlist *evlist,
 	struct evsel *pos;
 	int found = 0;
 
+	/*
+	 * Set err value to zero here. Any fail later
+	 * will set appropriate return code to err.
+	 */
+	*err = 0;
+
 	evlist__for_each_entry(evlist, pos) {
 		if (strstarts(pos->name, "vpa_dtl")) {
 			found = 1;
diff --git a/tools/perf/arch/x86/tests/amd-ibs-period.c b/tools/perf/arch/x86/tests/amd-ibs-period.c
index cee9e11c05e0..6a92b3a23ed7 100644
--- a/tools/perf/arch/x86/tests/amd-ibs-period.c
+++ b/tools/perf/arch/x86/tests/amd-ibs-period.c
@@ -932,7 +932,7 @@ static bool kernel_v6_15_or_newer(void)
 	endptr++;
 	minor = strtol(endptr, NULL, 10);
 
-	return major >= 6 && minor >= 15;
+	return major > 6 || (major == 6 && minor >= 15);
 }
 
 int test__amd_ibs_period(struct test_suite *test __maybe_unused,
diff --git a/tools/perf/bench/inject-buildid.c b/tools/perf/bench/inject-buildid.c
index aad572a78d7f..bfd2c5ec9488 100644
--- a/tools/perf/bench/inject-buildid.c
+++ b/tools/perf/bench/inject-buildid.c
@@ -228,9 +228,12 @@ static ssize_t synthesize_sample(struct bench_data *data, struct bench_dso *dso,
 
 	event.header.type = PERF_RECORD_SAMPLE;
 	event.header.misc = PERF_RECORD_MISC_USER;
-	event.header.size = perf_event__sample_event_size(&sample, bench_sample_type, 0);
-
-	perf_event__synthesize_sample(&event, bench_sample_type, 0, &sample);
+	event.header.size = perf_event__sample_event_size(&sample, bench_sample_type,
+							   /*read_format=*/0,
+							   /*branch_sample_type=*/0);
+	perf_event__synthesize_sample(&event, bench_sample_type,
+				      /*read_format=*/0,
+				      /*branch_sample_type=*/0, &sample);
 
 	return writen(data->input_pipe[1], &event, event.header.size);
 }
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 5e57b78548f4..bdc7adc83b47 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -298,7 +298,8 @@ static int process_sample_event(const struct perf_tool *tool,
 		goto out_put;
 	}
 
-	if (ann->cpu_list && !test_bit(sample->cpu, ann->cpu_bitmap))
+	if (ann->cpu_list && (sample->cpu >= MAX_NR_CPUS ||
+			     !test_bit(sample->cpu, ann->cpu_bitmap)))
 		goto out_put;
 
 	if (!al.filtered &&
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index a91bbb34ac94..e0881b0ac38f 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -61,7 +61,7 @@ static int sysfs__fprintf_build_id(FILE *fp)
 	int ret;
 
 	ret = sysfs__snprintf_build_id("/", sbuild_id, sizeof(sbuild_id));
-	if (ret != sizeof(sbuild_id))
+	if (ret + 1 != sizeof(sbuild_id))
 		return ret < 0 ? ret : -EINVAL;
 
 	return fprintf(fp, "%s\n", sbuild_id);
@@ -73,7 +73,7 @@ static int filename__fprintf_build_id(const char *name, FILE *fp)
 	int ret;
 
 	ret = filename__snprintf_build_id(name, sbuild_id, sizeof(sbuild_id));
-	if (ret != sizeof(sbuild_id))
+	if (ret + 1 != sizeof(sbuild_id))
 		return ret < 0 ? ret : -EINVAL;
 
 	return fprintf(fp, "%s\n", sbuild_id);
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 72a7802775ee..e7b9909e1ac2 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -180,7 +180,8 @@ static void c2c_he_free(void *he)
 
 	c2c_he = container_of(he, struct c2c_hist_entry, he);
 	if (c2c_he->hists) {
-		hists__delete_entries(&c2c_he->hists->hists);
+		hists__delete_all_entries(&c2c_he->hists->hists);
+		perf_hpp__reset_output_field(&c2c_he->hists->list);
 		zfree(&c2c_he->hists);
 	}
 
@@ -221,6 +222,8 @@ he__get_c2c_hists(struct hist_entry *he,
 
 	ret = c2c_hists__init(hists, sort, nr_header_lines, env);
 	if (ret) {
+		perf_hpp__reset_output_field(&hists->list);
+		c2c_he->hists = NULL;
 		free(hists);
 		return NULL;
 	}
@@ -241,6 +244,10 @@ static void c2c_he__set_cpu(struct c2c_hist_entry *c2c_he,
 		      "WARNING: no sample cpu value"))
 		return;
 
+	/* cpuset bitmap has c2c.cpus_cnt bits from env->nr_cpus_avail */
+	if (sample->cpu >= (unsigned int)c2c.cpus_cnt)
+		return;
+
 	__set_bit(sample->cpu, c2c_he->cpuset);
 }
 
@@ -258,6 +265,10 @@ static void c2c_he__set_node(struct c2c_hist_entry *c2c_he,
 	if (WARN_ONCE(node < 0, "WARNING: failed to find node\n"))
 		return;
 
+	/* nodeset bitmap has c2c.nodes_cnt bits from env->nr_numa_nodes */
+	if (node >= c2c.nodes_cnt)
+		return;
+
 	__set_bit(node, c2c_he->nodeset);
 
 	if (c2c_he->paddr != sample->phys_addr) {
@@ -386,7 +397,12 @@ static int process_sample_event(const struct perf_tool *tool __maybe_unused,
 		 * Doing node stats only for single callchain data.
 		 */
 		int cpu = sample->cpu == (unsigned int) -1 ? 0 : sample->cpu;
-		int node = c2c.cpu2node[cpu];
+		int node;
+
+		/* cpu2node[] has c2c.cpus_cnt entries; large u32 wraps signed negative */
+		if (cpu < 0 || cpu >= c2c.cpus_cnt)
+			cpu = 0;
+		node = c2c.cpu2node[cpu];
 
 		c2c_hists = he__get_c2c_hists(he, c2c.cl_sort, 2, machine->env);
 		if (!c2c_hists) {
@@ -405,7 +421,9 @@ static int process_sample_event(const struct perf_tool *tool __maybe_unused,
 		c2c_he = container_of(he, struct c2c_hist_entry, he);
 		c2c_add_stats(&c2c_he->stats, &stats);
 		c2c_add_stats(&c2c_hists->stats, &stats);
-		c2c_add_stats(&c2c_he->node_stats[node], &stats);
+		/* node_stats[] has c2c.nodes_cnt entries */
+		if (node >= 0 && node < c2c.nodes_cnt)
+			c2c_add_stats(&c2c_he->node_stats[node], &stats);
 
 		compute_stats(c2c_he, &stats, sample->weight);
 
@@ -2351,6 +2369,10 @@ static int setup_nodes(struct perf_session *session)
 		nodes[node] = set;
 
 		perf_cpu_map__for_each_cpu_skip_any(cpu, idx, map) {
+			/* topology CPU IDs from perf.data may exceed nr_cpus_avail */
+			if (cpu.cpu < 0 || cpu.cpu >= c2c.cpus_cnt)
+				continue;
+
 			__set_bit(cpu.cpu, set);
 
 			if (WARN_ONCE(cpu2node[cpu.cpu] != -1, "node/cpu topology bug"))
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 1b3df868849a..29db0afc53ca 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -416,7 +416,8 @@ static int diff__process_sample_event(const struct perf_tool *tool,
 		goto out;
 	}
 
-	if (cpu_list && !test_bit(sample->cpu, cpu_bitmap)) {
+	if (cpu_list && (sample->cpu >= MAX_NR_CPUS ||
+			!test_bit(sample->cpu, cpu_bitmap))) {
 		ret = 0;
 		goto out;
 	}
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index f174bc69cec4..7a64935b7e2b 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -26,6 +26,7 @@
 #include "util/synthetic-events.h"
 #include "util/thread.h"
 #include "util/namespaces.h"
+#include "util/unwind.h"
 #include "util/util.h"
 #include "util/tsc.h"
 
@@ -215,12 +216,23 @@ static int perf_event__repipe_op4_synth(const struct perf_tool *tool,
 	return perf_event__repipe_synth(tool, event);
 }
 
+static int perf_event__repipe_synth_cb(const struct perf_tool *tool,
+				       union perf_event *event,
+				       struct perf_sample *sample __maybe_unused,
+				       struct machine *machine __maybe_unused)
+{
+	return perf_event__repipe_synth(tool, event);
+}
+
 static int perf_event__repipe_attr(const struct perf_tool *tool,
 				   union perf_event *event,
 				   struct evlist **pevlist)
 {
 	struct perf_inject *inject = container_of(tool, struct perf_inject,
 						  tool);
+	struct perf_event_attr attr;
+	size_t n_ids;
+	u64 *ids;
 	int ret;
 
 	ret = perf_event__process_attr(tool, event, pevlist);
@@ -231,7 +243,37 @@ static int perf_event__repipe_attr(const struct perf_tool *tool,
 	if (!inject->output.is_pipe)
 		return 0;
 
-	return perf_event__repipe_synth(tool, event);
+	if (!inject->itrace_synth_opts.set)
+		return perf_event__repipe_synth(tool, event);
+
+	if (event->header.size < sizeof(struct perf_event_header) + sizeof(u64)) {
+		pr_err("Attribute event size %u is too small\n", event->header.size);
+		return -EINVAL;
+	}
+
+	if (event->header.size - sizeof(event->header) < event->attr.attr.size) {
+		pr_err("Attribute event size %u is too small for attr.size %u\n",
+		       event->header.size, event->attr.attr.size);
+		return -EINVAL;
+	}
+
+	memset(&attr, 0, sizeof(attr));
+	memcpy(&attr, &event->attr.attr,
+	       min_t(size_t, sizeof(attr), (size_t)event->attr.attr.size));
+
+	n_ids = event->header.size - sizeof(event->header) - event->attr.attr.size;
+	n_ids /= sizeof(u64);
+	ids = perf_record_header_attr_id(event);
+
+	attr.size = sizeof(struct perf_event_attr);
+	attr.sample_type &= ~PERF_SAMPLE_AUX;
+
+	if (inject->itrace_synth_opts.add_last_branch) {
+		attr.sample_type |= PERF_SAMPLE_BRANCH_STACK;
+		attr.branch_sample_type |= PERF_SAMPLE_BRANCH_HW_INDEX;
+	}
+	return perf_event__synthesize_attr(tool, &attr, (u32)n_ids, ids,
+					   perf_event__repipe_synth_cb);
 }
 
 static int perf_event__repipe_event_update(const struct perf_tool *tool,
@@ -330,8 +372,8 @@ perf_inject__cut_auxtrace_sample(struct perf_inject *inject,
 				 union perf_event *event,
 				 struct perf_sample *sample)
 {
-	size_t sz1 = sample->aux_sample.data - (void *)event;
-	size_t sz2 = event->header.size - sample->aux_sample.size - sz1;
+	size_t sz1 = sample->aux_sample.data - (void *)event - sizeof(u64);
+	size_t sz2 = event->header.size - sample->aux_sample.size - (sz1 + sizeof(u64));
 	union perf_event *ev;
 
 	if (inject->event_copy == NULL) {
@@ -342,13 +384,12 @@ perf_inject__cut_auxtrace_sample(struct perf_inject *inject,
 	ev = (union perf_event *)inject->event_copy;
 	if (sz1 > event->header.size || sz2 > event->header.size ||
 	    sz1 + sz2 > event->header.size ||
-	    sz1 < sizeof(struct perf_event_header) + sizeof(u64))
+	    sz1 < sizeof(struct perf_event_header))
 		return event;
 
 	memcpy(ev, event, sz1);
 	memcpy((void *)ev + sz1, (void *)event + event->header.size - sz2, sz2);
 	ev->header.size = sz1 + sz2;
-	((u64 *)((void *)ev + sz1))[-1] = 0;
 
 	return ev;
 }
@@ -368,14 +409,77 @@ static int perf_event__repipe_sample(const struct perf_tool *tool,
 	struct perf_inject *inject = container_of(tool, struct perf_inject,
 						  tool);
 
-	if (evsel && evsel->handler) {
+	if (evsel == NULL)
+		return perf_event__repipe_synth(tool, event);
+
+	if (evsel->handler) {
 		inject_handler f = evsel->handler;
 		return f(tool, event, sample, evsel, machine);
 	}
 
 	build_id__mark_dso_hit(tool, event, sample, evsel, machine);
 
-	if (inject->itrace_synth_opts.set && sample->aux_sample.size) {
+	if (inject->itrace_synth_opts.set &&
+	    (inject->itrace_synth_opts.last_branch ||
+	     inject->itrace_synth_opts.add_last_branch)) {
+		union perf_event *event_copy = (void *)inject->event_copy;
+		struct branch_stack dummy_bs = { .nr = 0, .hw_idx = 0 };
+		int err;
+		size_t sz;
+		u64 orig_type = evsel->core.attr.sample_type;
+		u64 orig_branch_type = evsel->core.attr.branch_sample_type;
+
+		struct branch_stack *orig_bs = sample->branch_stack;
+
+		if (event_copy == NULL) {
+			inject->event_copy = malloc(PERF_SAMPLE_MAX_SIZE);
+			if (!inject->event_copy)
+				return -ENOMEM;
+
+			event_copy = (void *)inject->event_copy;
+		}
+
+		if (!sample->branch_stack)
+			sample->branch_stack = &dummy_bs;
+
+		if (inject->itrace_synth_opts.add_last_branch) {
+			/* Temporarily add in type bits for synthesis. */
+			evsel->core.attr.sample_type |= PERF_SAMPLE_BRANCH_STACK;
+			evsel->core.attr.branch_sample_type |= PERF_SAMPLE_BRANCH_HW_INDEX;
+		}
+		evsel->core.attr.sample_type &= ~PERF_SAMPLE_AUX;
+
+		sz = perf_event__sample_event_size(sample, evsel->core.attr.sample_type,
+						   evsel->core.attr.read_format,
+						   evsel->core.attr.branch_sample_type);
+
+		if (sz >= PERF_SAMPLE_MAX_SIZE) {
+			pr_err("Sample size %zu exceeds max size %d\n", sz, PERF_SAMPLE_MAX_SIZE);
+			evsel->core.attr.sample_type = orig_type;
+			evsel->core.attr.branch_sample_type = orig_branch_type;
+			sample->branch_stack = orig_bs;
+			return -EFAULT;
+		}
+
+		event_copy->header.type = PERF_RECORD_SAMPLE;
+		event_copy->header.misc = event->header.misc;
+		event_copy->header.size = sz;
+
+		err = perf_event__synthesize_sample(event_copy, evsel->core.attr.sample_type,
+						    evsel->core.attr.read_format,
+						    evsel->core.attr.branch_sample_type, sample);
+
+		evsel->core.attr.sample_type = orig_type;
+		evsel->core.attr.branch_sample_type = orig_branch_type;
+		sample->branch_stack = orig_bs;
+
+		if (err) {
+			pr_err("Failed to synthesize sample\n");
+			return err;
+		}
+		event = event_copy;
+	} else if (inject->itrace_synth_opts.set &&
+		   (evsel->core.attr.sample_type & PERF_SAMPLE_AUX)) {
 		event = perf_inject__cut_auxtrace_sample(inject, event, sample);
 		if (IS_ERR(event))
 			return PTR_ERR(event);
@@ -396,7 +500,7 @@ static int perf_event__convert_sample_callchain(const struct perf_tool *tool,
 	struct callchain_cursor_node *node;
 	struct thread *thread;
 	u64 sample_type = evsel->core.attr.sample_type;
-	u32 sample_size = event->header.size;
+	size_t sz;
 	u64 i, k;
 	int ret;
 
@@ -438,7 +542,8 @@ static int perf_event__convert_sample_callchain(const struct perf_tool *tool,
 
 	node = cursor->first;
 	for (k = 0; k < cursor->nr && i < PERF_MAX_STACK_DEPTH; k++) {
-		if (machine__kernel_ip(machine, node->ip))
+		if (machine->single_address_space &&
+		    machine__kernel_ip(machine, node->ip))
 			/* kernel IPs were added already */;
 		else if (node->ms.sym && node->ms.sym->inlined)
 			/* we can't handle inlined callchains */;
@@ -454,17 +559,25 @@ static int perf_event__convert_sample_callchain(const struct perf_tool *tool,
 out:
 	memcpy(event_copy, event, sizeof(event->header));
 
-	/* adjust sample size for stack and regs */
-	sample_size -= sample->user_stack.size;
-	sample_size -= (hweight64(evsel->core.attr.sample_regs_user) + 1) * sizeof(u64);
-	sample_size += (sample->callchain->nr + 1) * sizeof(u64);
-	event_copy->header.size = sample_size;
-
 	/* remove sample_type {STACK,REGS}_USER for synthesize */
 	sample_type &= ~(PERF_SAMPLE_STACK_USER | PERF_SAMPLE_REGS_USER);
 
-	perf_event__synthesize_sample(event_copy, sample_type,
-				      evsel->core.attr.read_format, sample);
+	sz = perf_event__sample_event_size(sample, sample_type,
+					   evsel->core.attr.read_format,
+					   evsel->core.attr.branch_sample_type);
+	if (sz >= PERF_SAMPLE_MAX_SIZE) {
+		pr_err("Sample size %zu exceeds max size %d\n", sz, PERF_SAMPLE_MAX_SIZE);
+		return -EFAULT;
+	}
+	event_copy->header.size = sz;
+
+	ret = perf_event__synthesize_sample(event_copy, sample_type,
+					    evsel->core.attr.read_format,
+					    evsel->core.attr.branch_sample_type, sample);
+	if (ret) {
+		pr_err("Failed to synthesize sample\n");
+		return ret;
+	}
 	return perf_event__repipe_synth(tool, event_copy);
 }
 
@@ -1100,7 +1213,8 @@ found:
 	sample_sw.period = sample->period;
 	sample_sw.time	 = sample->time;
 	perf_event__synthesize_sample(event_sw, evsel->core.attr.sample_type,
-				      evsel->core.attr.read_format, &sample_sw);
+				      evsel->core.attr.read_format,
+				      evsel->core.attr.branch_sample_type, &sample_sw);
 	build_id__mark_dso_hit(tool, event_sw, &sample_sw, evsel, machine);
 	ret = perf_event__repipe(tool, event_sw, &sample_sw, machine);
 	perf_sample__exit(&sample_sw);
@@ -2434,12 +2548,27 @@ static int __cmd_inject(struct perf_inject *inject)
 		 * synthesized hardware events, so clear the feature flag.
 		 */
 		if (inject->itrace_synth_opts.set) {
+			struct evsel *evsel;
+
 			perf_header__clear_feat(&session->header,
 						HEADER_AUXTRACE);
-			if (inject->itrace_synth_opts.last_branch ||
-			    inject->itrace_synth_opts.add_last_branch)
+
+			evlist__for_each_entry(session->evlist, evsel) {
+				evsel->core.attr.sample_type &= ~PERF_SAMPLE_AUX;
+			}
+
+			if (inject->itrace_synth_opts.add_last_branch) {
 				perf_header__set_feat(&session->header,
 						      HEADER_BRANCH_STACK);
+
+				evlist__for_each_entry(session->evlist, evsel) {
+					evsel->core.attr.sample_type |= PERF_SAMPLE_BRANCH_STACK;
+					if (evsel->core.attr.size < PERF_ATTR_SIZE_VER2)
+						evsel->core.attr.size = PERF_ATTR_SIZE_VER2;
+					evsel->core.attr.branch_sample_type |=
+						PERF_SAMPLE_BRANCH_HW_INDEX;
+				}
+			}
 		}
 
 		/*
@@ -2562,6 +2691,9 @@ int cmd_inject(int argc, const char **argv)
 		OPT_STRING(0, "guestmount", &symbol_conf.guestmount, "directory",
 			   "guest mount directory under which every guest os"
 			   " instance has a subdir"),
+		OPT_CALLBACK(0, "unwind-style", NULL, "unwind style",
+			     "unwind styles (libdw,libunwind)",
+			     unwind__option),
 		OPT_BOOLEAN(0, "convert-callchain", &inject.convert_callchain,
 			    "Generate callchains using DWARF and drop register/stack data"),
 		OPT_END()
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4a5eba498c02..1593cf3a834b 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -865,6 +865,7 @@ static int record__auxtrace_init(struct record *rec)
 	}
 
 	if (!rec->itr) {
+		err = -EINVAL;
 		rec->itr = auxtrace_record__init(rec->evlist, &err);
 		if (err)
 			return err;
@@ -3079,6 +3080,7 @@ static int record__mmap_cpu_mask_alloc(struct mmap_cpu_mask *mask, int nr_bits)
 static void record__mmap_cpu_mask_free(struct mmap_cpu_mask *mask)
 {
 	bitmap_free(mask->bits);
+	mask->bits = NULL;
 	mask->nbits = 0;
 }
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 95c0bdba6b11..3a5cf1b64adb 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -48,6 +48,7 @@
 #include "util/time-utils.h"
 #include "util/auxtrace.h"
 #include "util/units.h"
+#include "util/unwind.h"
 #include "util/util.h" // perf_tip()
 #include "ui/ui.h"
 #include "ui/progress.h"
@@ -299,7 +300,8 @@ static int process_sample_event(const struct perf_tool *tool,
 	if (symbol_conf.hide_unresolved && al.sym == NULL)
 		goto out_put;
 
-	if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap))
+	if (rep->cpu_list && (sample->cpu >= MAX_NR_CPUS ||
+			     !test_bit(sample->cpu, rep->cpu_bitmap)))
 		goto out_put;
 
 	if (sort__mode == SORT_MODE__BRANCH) {
@@ -1449,6 +1451,9 @@ int cmd_report(int argc, const char **argv)
 	OPT_CALLBACK(0, "addr2line-style", NULL, "addr2line style",
 		     "addr2line styles (libdw,llvm,libbfd,addr2line)",
 		     report_parse_addr2line_config),
+	OPT_CALLBACK(0, "unwind-style", NULL, "unwind style",
+		     "unwind styles (libdw,libunwind)",
+		     unwind__option),
 	OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle,
 		    "Symbol demangling. Enabled by default, use --no-demangle to disable."),
 	OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 555247568e7a..b97b41c7655c 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -54,6 +54,7 @@
 #define COMM_LEN		20
 #define SYM_LEN			129
 #define MAX_PID			1024000
+#define PID_MAX_LIMIT		4194304 /* kernel limit on 64-bit */
 #define MAX_PRIO		140
 #define SEP_LEN			100
 
@@ -273,6 +274,7 @@ struct thread_runtime {
 	u64 migrations;
 
 	int prio;
+	bool color;
 };
 
 /* per event run time data */
@@ -364,14 +366,25 @@ get_new_event(struct task_desc *task, u64 timestamp)
 	struct sched_atom *event = zalloc(sizeof(*event));
 	unsigned long idx = task->nr_events;
 	size_t size;
+	struct sched_atom **atoms_p;
+
+	if (event == NULL) {
+		pr_err("ERROR: sched: failed to allocate event\n");
+		return NULL;
+	}
 
 	event->timestamp = timestamp;
 	event->nr = idx;
 
+	size = sizeof(struct sched_atom *) * (task->nr_events + 1);
+	atoms_p = realloc(task->atoms, size);
+	if (!atoms_p) {
+		pr_err("ERROR: sched: failed to grow atoms array\n");
+		free(event);
+		return NULL;
+	}
+	task->atoms = atoms_p;
 	task->nr_events++;
-	size = sizeof(struct sched_atom *) * task->nr_events;
-	task->atoms = realloc(task->atoms, size);
-	BUG_ON(!task->atoms);
 
 	task->atoms[idx] = event;
 
@@ -402,6 +415,8 @@ static void add_sched_event_run(struct perf_sched *sched, struct task_desc *task
 	}
 
 	event = get_new_event(task, timestamp);
+	if (event == NULL)
+		return;
 
 	event->type = SCHED_EVENT_RUN;
 	event->duration = duration;
@@ -415,6 +430,8 @@ static void add_sched_event_wakeup(struct perf_sched *sched, struct task_desc *t
 	struct sched_atom *event, *wakee_event;
 
 	event = get_new_event(task, timestamp);
+	if (event == NULL)
+		return;
 	event->type = SCHED_EVENT_WAKEUP;
 	event->wakee = wakee;
 
@@ -429,6 +446,10 @@ static void add_sched_event_wakeup(struct perf_sched *sched, struct task_desc *t
 	}
 
 	wakee_event->wait_sem = zalloc(sizeof(*wakee_event->wait_sem));
+	if (!wakee_event->wait_sem) {
+		pr_err("ERROR: sched: failed to allocate semaphore\n");
+		return;
+	}
 	sem_init(wakee_event->wait_sem, 0, 0);
 	event->wait_sem = wakee_event->wait_sem;
 
@@ -440,6 +461,9 @@ static void add_sched_event_sleep(struct perf_sched *sched, struct task_desc *ta
 {
 	struct sched_atom *event = get_new_event(task, timestamp);
 
+	if (event == NULL)
+		return;
+
 	event->type = SCHED_EVENT_SLEEP;
 
 	sched->nr_sleep_events++;
@@ -448,17 +472,28 @@ static void add_sched_event_sleep(struct perf_sched *sched, struct task_desc *ta
 static struct task_desc *register_pid(struct perf_sched *sched,
 				      unsigned long pid, const char *comm)
 {
-	struct task_desc *task;
+	struct task_desc *task, **tasks_p;
 	static int pid_max;
 
+	/* perf.data is untrusted — cap pid to prevent overflow in size calculations */
+	if (pid >= PID_MAX_LIMIT) {
+		pr_err("pid %lu exceeds limit %d, skipping\n", pid, PID_MAX_LIMIT);
+		return NULL;
+	}
+
 	if (sched->pid_to_task == NULL) {
 		if (sysctl__read_int("kernel/pid_max", &pid_max) < 0)
 			pid_max = MAX_PID;
-		BUG_ON((sched->pid_to_task = calloc(pid_max, sizeof(struct task_desc *))) == NULL);
+		sched->pid_to_task = calloc(pid_max, sizeof(struct task_desc *));
+		if (sched->pid_to_task == NULL)
+			return NULL;
 	}
 	if (pid >= (unsigned long)pid_max) {
-		BUG_ON((sched->pid_to_task = realloc(sched->pid_to_task, (pid + 1) *
-			sizeof(struct task_desc *))) == NULL);
+		void *p = realloc(sched->pid_to_task, (pid + 1) * sizeof(struct task_desc *));
+
+		if (p == NULL)
+			return NULL;
+		sched->pid_to_task = p;
 		while (pid >= (unsigned long)pid_max)
 			sched->pid_to_task[pid_max++] = NULL;
 	}
@@ -469,9 +504,11 @@ static struct task_desc *register_pid(struct perf_sched *sched,
 		return task;
 
 	task = zalloc(sizeof(*task));
+	if (task == NULL)
+		return NULL;
 	task->pid = pid;
-	task->nr = sched->nr_tasks;
-	strcpy(task->comm, comm);
+	if (comm)
+		strlcpy(task->comm, comm, sizeof(task->comm));
 	/*
 	 * every task starts in sleeping state - this gets ignored
 	 * if there's no wakeup pointing to this sleep state:
@@ -479,10 +516,12 @@ static struct task_desc *register_pid(struct perf_sched *sched,
 	add_sched_event_sleep(sched, task, 0);
 
 	sched->pid_to_task[pid] = task;
-	sched->nr_tasks++;
-	sched->tasks = realloc(sched->tasks, sched->nr_tasks * sizeof(struct task_desc *));
-	BUG_ON(!sched->tasks);
-	sched->tasks[task->nr] = task;
+	tasks_p = realloc(sched->tasks, (sched->nr_tasks + 1) * sizeof(struct task_desc *));
+	if (!tasks_p)
+		return NULL;
+	sched->tasks = tasks_p;
+	sched->tasks[sched->nr_tasks] = task;
+	task->nr = sched->nr_tasks++;
 
 	if (verbose > 0)
 		printf("registered task #%ld, PID %ld (%s)\n", sched->nr_tasks, pid, comm);
@@ -841,6 +880,8 @@ replay_wakeup_event(struct perf_sched *sched,
 
 	waker = register_pid(sched, sample->tid, "<unknown>");
 	wakee = register_pid(sched, pid, comm);
+	if (waker == NULL || wakee == NULL)
+		return -1;
 
 	add_sched_event_wakeup(sched, waker, sample->time, wakee);
 	return 0;
@@ -882,6 +923,8 @@ static int replay_switch_event(struct perf_sched *sched,
 
 	prev = register_pid(sched, prev_pid, prev_comm);
 	next = register_pid(sched, next_pid, next_comm);
+	if (prev == NULL || next == NULL)
+		return -1;
 
 	sched->cpu_last_switched[cpu] = timestamp;
 
@@ -1147,7 +1190,12 @@ static int latency_switch_event(struct perf_sched *sched,
 	int cpu = sample->cpu, err = -1;
 	s64 delta;
 
-	BUG_ON(cpu >= MAX_CPUS || cpu < 0);
+	/* perf.data is untrusted input — CPU may be absent or corrupted */
+	if (cpu >= MAX_CPUS || cpu < 0) {
+		pr_warning("WARNING: at offset %#" PRIx64 ": out-of-bound sample CPU %d, skipping sample\n",
+			   sample->file_offset, cpu);
+		return 0;
+	}
 
 	timestamp0 = sched->cpu_last_switched[cpu];
 	sched->cpu_last_switched[cpu] = timestamp;
@@ -1177,7 +1225,7 @@ static int latency_switch_event(struct perf_sched *sched,
 		}
 	}
 	if (add_sched_out_event(out_events, prev_state, timestamp))
-		return -1;
+		goto out_put;
 
 	in_events = thread_atoms_search(&sched->atom_root, sched_in, &sched->cmp_pid);
 	if (!in_events) {
@@ -1211,14 +1259,22 @@ static int latency_runtime_event(struct perf_sched *sched,
 	const u32 pid	   = evsel__intval(evsel, sample, "pid");
 	const u64 runtime  = evsel__intval(evsel, sample, "runtime");
 	struct thread *thread = machine__findnew_thread(machine, -1, pid);
-	struct work_atoms *atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid);
+	struct work_atoms *atoms;
 	u64 timestamp = sample->time;
 	int cpu = sample->cpu, err = -1;
 
 	if (thread == NULL)
 		return -1;
 
-	BUG_ON(cpu >= MAX_CPUS || cpu < 0);
+	atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid);
+
+	/* perf.data is untrusted input — CPU may be absent or corrupted */
+	if (cpu >= MAX_CPUS || cpu < 0) {
+		pr_warning("WARNING: at offset %#" PRIx64 ": out-of-bound sample CPU %d, skipping sample\n",
+			   sample->file_offset, cpu);
+		err = 0;
+		goto out_put;
+	}
 	if (!atoms) {
 		if (thread_atoms_insert(sched, thread))
 			goto out_put;
@@ -1541,22 +1597,32 @@ static int process_sched_wakeup_ignore(const struct perf_tool *tool __maybe_unus
 
 static bool thread__has_color(struct thread *thread)
 {
-	return thread__priv(thread) != NULL;
+	struct thread_runtime *tr = thread__priv(thread);
+
+	return tr != NULL && tr->color;
 }
 
 static struct thread*
 map__findnew_thread(struct perf_sched *sched, struct machine *machine, pid_t pid, pid_t tid)
 {
 	struct thread *thread = machine__findnew_thread(machine, pid, tid);
-	bool color = false;
 
-	if (!sched->map.color_pids || !thread || thread__priv(thread))
+	if (!sched->map.color_pids || !thread)
 		return thread;
 
-	if (thread_map__has(sched->map.color_pids, tid))
-		color = true;
+	/*
+	 * Always check the color-pids map, even if thread__priv() is
+	 * already set.  COMM events processed before the first sched_switch
+	 * allocate a thread_runtime via thread__get_runtime(), so priv is
+	 * non-NULL before we ever get here.  Skipping the check on non-NULL
+	 * priv would prevent those threads from being colored.
+	 */
+	if (thread_map__has(sched->map.color_pids, tid)) {
+		struct thread_runtime *tr = thread__get_runtime(thread);
 
-	thread__set_priv(thread, color ? ((void*)1) : NULL);
+		if (tr)
+			tr->color = true;
+	}
 	return thread;
 }
 
@@ -1647,7 +1713,12 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel,
 	const char *str;
 	int ret = -1;
 
-	BUG_ON(this_cpu.cpu >= MAX_CPUS || this_cpu.cpu < 0);
+	/* perf.data is untrusted input — CPU may be absent or corrupted */
+	if (this_cpu.cpu >= MAX_CPUS || this_cpu.cpu < 0) {
+		pr_warning("WARNING: at offset %#" PRIx64 ": out-of-bound sample CPU %d, skipping sample\n",
+			   sample->file_offset, this_cpu.cpu);
+		return 0;
+	}
 
 	if (this_cpu.cpu > sched->max_cpu.cpu)
 		sched->max_cpu = this_cpu;
@@ -1659,7 +1730,7 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel,
 			new_cpu = true;
 		}
 	} else
-		cpus_nr = sched->max_cpu.cpu;
+		cpus_nr = sched->max_cpu.cpu + 1;
 
 	timestamp0 = sched->cpu_last_switched[this_cpu.cpu];
 	sched->cpu_last_switched[this_cpu.cpu] = timestamp;
@@ -2175,7 +2246,8 @@ static void timehist_print_sample(struct perf_sched *sched,
 	char nstr[30];
 	u64 wait_time;
 
-	if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
+	if (cpu_list && (sample->cpu >= MAX_NR_CPUS ||
+			!test_bit(sample->cpu, cpu_bitmap)))
 		return;
 
 	timestamp__scnprintf_usec(t, tstr, sizeof(tstr));
@@ -2439,10 +2511,13 @@ static void free_idle_threads(void)
 			struct idle_thread_runtime *itr;
 
 			itr = thread__priv(idle);
-			if (itr)
+			if (itr) {
 				thread__put(itr->last_thread);
+				free_callchain(&itr->callchain);
+				callchain_cursor_cleanup(&itr->cursor);
+			}
 
-			thread__delete(idle);
+			thread__put(idle);
 		}
 	}
 
@@ -2475,8 +2550,11 @@ static struct thread *get_idle_thread(int cpu)
 		idle_threads[cpu] = thread__new(0, 0);
 
 		if (idle_threads[cpu]) {
-			if (init_idle_thread(idle_threads[cpu]) < 0)
+			if (init_idle_thread(idle_threads[cpu]) < 0) {
+				/* clean up so next call doesn't find a half-initialized thread */
+				thread__zput(idle_threads[cpu]);
 				return NULL;
+			}
 		}
 	}
 
@@ -2528,12 +2606,16 @@ static struct thread *timehist_get_thread(struct perf_sched *sched,
 			idle = get_idle_thread(sample->cpu);
 			if (idle == NULL) {
 				pr_err("Failed to get idle thread for cpu %d.\n", sample->cpu);
+				thread__put(thread);
 				return NULL;
 			}
 
 			itr = thread__priv(idle);
-			if (itr == NULL)
+			if (itr == NULL) {
+				thread__put(idle);
+				thread__put(thread);
 				return NULL;
+			}
 
 			thread__put(itr->last_thread);
 			itr->last_thread = thread__get(thread);
@@ -2541,6 +2623,8 @@ static struct thread *timehist_get_thread(struct perf_sched *sched,
 			/* copy task callchain when entering to idle */
 			if (evsel__intval(evsel, sample, "next_pid") == 0)
 				save_idle_callchain(sched, itr, sample);
+
+			thread__put(idle);
 		}
 	}
 
@@ -2574,7 +2658,9 @@ static bool timehist_skip_sample(struct perf_sched *sched,
 		else if (evsel__name_is(evsel, "sched:sched_switch"))
 			prio = evsel__intval(evsel, sample, "prev_prio");
 
-		if (prio != -1 && !test_bit(prio, sched->prio_bitmap)) {
+		/* negative prio means no info; out-of-range prio can't match the filter */
+		if (prio >= 0 &&
+		    (prio >= MAX_PRIO || !test_bit(prio, sched->prio_bitmap))) {
 			rc = true;
 			sched->skipped_samples++;
 		}
@@ -2856,8 +2942,15 @@ static int timehist_sched_change_event(const struct perf_tool *tool,
 			t = ptime->end;
 	}
 
-	if (!sched->idle_hist || thread__tid(thread) == 0) {
-		if (!cpu_list || test_bit(sample->cpu, cpu_bitmap))
+	/*
+	 * Use is_idle_sample() not thread__tid() == 0: a crafted perf.data
+	 * can set common_pid=0 with prev_pid!=0, giving us a machine thread
+	 * whose priv is thread_runtime, not idle_thread_runtime — the cast
+	 * below would read past the allocation.
+	 */
+	if (!sched->idle_hist || is_idle_sample(sample, evsel)) {
+		if (!cpu_list || (sample->cpu < MAX_NR_CPUS &&
+				 test_bit(sample->cpu, cpu_bitmap)))
 			timehist_update_runtime_stats(tr, t, tprev);
 
 		if (sched->idle_hist) {
@@ -2887,7 +2980,7 @@ static int timehist_sched_change_event(const struct perf_tool *tool,
 			if (itr->cursor.nr)
 				callchain_append(&itr->callchain, &itr->cursor, t - tprev);
 
-			itr->last_thread = NULL;
+			thread__zput(itr->last_thread);
 		}
 
 		if (!sched->summary_only)
@@ -3051,7 +3144,8 @@ static size_t timehist_print_idlehist_callchain(struct rb_root_cached *root)
 	size_t ret = 0;
 	FILE *fp = stdout;
 	struct callchain_node *chain;
-	struct rb_node *rb_node = rb_first_cached(root);
+	/* sort() uses rb_insert_color() on rb_root, not rb_root_cached */
+	struct rb_node *rb_node = rb_first(&root->rb_root);
 
 	printf("  %16s  %8s  %s\n", "Idle time (msec)", "Count", "Callchains");
 	printf("  %.16s  %.8s  %.50s\n", graph_dotted_line, graph_dotted_line,
@@ -3193,7 +3287,9 @@ static int perf_timehist__process_sample(const struct perf_tool *tool,
 		.cpu = sample->cpu,
 	};
 
-	if (this_cpu.cpu > sched->max_cpu.cpu)
+	/* max_cpu indexes arrays allocated with MAX_CPUS entries */
+	if (this_cpu.cpu >= 0 && this_cpu.cpu < MAX_CPUS &&
+	    this_cpu.cpu > sched->max_cpu.cpu)
 		sched->max_cpu = this_cpu;
 
 	if (evsel->handler != NULL) {
@@ -3299,6 +3395,7 @@ static int perf_sched__timehist(struct perf_sched *sched)
 	 */
 	sched->tool.sample	 = perf_timehist__process_sample;
 	sched->tool.mmap	 = perf_event__process_mmap;
+	sched->tool.mmap2	 = perf_event__process_mmap2;
 	sched->tool.comm	 = perf_event__process_comm;
 	sched->tool.exit	 = perf_event__process_exit;
 	sched->tool.fork	 = perf_event__process_fork;
@@ -3362,8 +3459,8 @@ static int perf_sched__timehist(struct perf_sched *sched)
 		perf_session__set_tracepoints_handlers(session, migrate_handlers))
 		goto out;
 
-	/* pre-allocate struct for per-CPU idle stats */
-	sched->max_cpu.cpu = env->nr_cpus_online;
+	/* pre-allocate struct for per-CPU idle stats; cap to array bounds */
+	sched->max_cpu.cpu = min(env->nr_cpus_online, MAX_CPUS);
 	if (sched->max_cpu.cpu == 0)
 		sched->max_cpu.cpu = 4;
 	if (init_idle_threads(sched->max_cpu.cpu))
@@ -3556,10 +3653,8 @@ out_free_cpus_switch_event:
 
 static int setup_map_cpus(struct perf_sched *sched)
 {
-	sched->max_cpu.cpu  = sysconf(_SC_NPROCESSORS_CONF);
-
 	if (sched->map.comp) {
-		sched->map.comp_cpus = calloc(sched->max_cpu.cpu, sizeof(int));
+		sched->map.comp_cpus = calloc(MAX_CPUS, sizeof(*sched->map.comp_cpus));
 		if (!sched->map.comp_cpus)
 			return -1;
 	}
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index c8ac9f01a36b..ed372762276b 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -63,6 +63,7 @@
 #include <linux/err.h>
 #include "util/dlfilter.h"
 #include "util/record.h"
+#include "util/unwind.h"
 #include "util/util.h"
 #include "util/cgroup.h"
 #include "util/annotate.h"
@@ -2637,7 +2638,7 @@ static int cleanup_scripting(void)
 
 static bool filter_cpu(struct perf_sample *sample)
 {
-	if (cpu_list && sample->cpu != (u32)-1)
+	if (cpu_list && sample->cpu != (u32)-1 && sample->cpu < MAX_NR_CPUS)
 		return !test_bit(sample->cpu, cpu_bitmap);
 	return false;
 }
@@ -4159,6 +4160,9 @@ int cmd_script(int argc, const char **argv)
 			"Enable symbol demangling"),
 	OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
 			"Enable kernel symbol demangling"),
+	OPT_CALLBACK(0, "unwind-style", NULL, "unwind style",
+		     "unwind styles (libdw,libunwind)",
+		     unwind__option),
 	OPT_STRING(0, "addr2line", &symbol_conf.addr2line_path, "path",
 			"addr2line binary to use for line numbers"),
 	OPT_STRING(0, "time", &script.time_str, "str",
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 99d7db372b48..a04466ea3b0a 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1637,9 +1637,10 @@ static struct aggr_cpu_id perf_env__get_socket_aggr_by_cpu(struct perf_cpu cpu,
 {
 	struct perf_env *env = data;
 	struct aggr_cpu_id id = aggr_cpu_id__empty();
+	struct cpu_topology_map *topo = perf_env__get_cpu_topology(env, cpu);
 
-	if (cpu.cpu != -1)
-		id.socket = env->cpu[cpu.cpu].socket_id;
+	if (topo)
+		id.socket = topo->socket_id;
 
 	return id;
 }
@@ -1648,15 +1649,16 @@ static struct aggr_cpu_id perf_env__get_die_aggr_by_cpu(struct perf_cpu cpu, voi
 {
 	struct perf_env *env = data;
 	struct aggr_cpu_id id = aggr_cpu_id__empty();
+	struct cpu_topology_map *topo = perf_env__get_cpu_topology(env, cpu);
 
-	if (cpu.cpu != -1) {
+	if (topo) {
 		/*
 		 * die_id is relative to socket, so start
 		 * with the socket ID and then add die to
 		 * make a unique ID.
 		 */
-		id.socket = env->cpu[cpu.cpu].socket_id;
-		id.die = env->cpu[cpu.cpu].die_id;
+		id.socket = topo->socket_id;
+		id.die = topo->die_id;
 	}
 
 	return id;
@@ -1704,12 +1706,13 @@ static struct aggr_cpu_id perf_env__get_cache_aggr_by_cpu(struct perf_cpu cpu,
 {
 	struct perf_env *env = data;
 	struct aggr_cpu_id id = aggr_cpu_id__empty();
+	struct cpu_topology_map *topo = perf_env__get_cpu_topology(env, cpu);
 
-	if (cpu.cpu != -1) {
+	if (topo) {
 		u32 cache_level = (perf_stat.aggr_level) ?: stat_config.aggr_level;
 
-		id.socket = env->cpu[cpu.cpu].socket_id;
-		id.die = env->cpu[cpu.cpu].die_id;
+		id.socket = topo->socket_id;
+		id.die = topo->die_id;
 		perf_env__get_cache_id_for_cpu(cpu, env, cache_level, &id);
 	}
 
@@ -1721,11 +1724,12 @@ static struct aggr_cpu_id perf_env__get_cluster_aggr_by_cpu(struct perf_cpu cpu,
 {
 	struct perf_env *env = data;
 	struct aggr_cpu_id id = aggr_cpu_id__empty();
+	struct cpu_topology_map *topo = perf_env__get_cpu_topology(env, cpu);
 
-	if (cpu.cpu != -1) {
-		id.socket = env->cpu[cpu.cpu].socket_id;
-		id.die = env->cpu[cpu.cpu].die_id;
-		id.cluster = env->cpu[cpu.cpu].cluster_id;
+	if (topo) {
+		id.socket = topo->socket_id;
+		id.die = topo->die_id;
+		id.cluster = topo->cluster_id;
 	}
 
 	return id;
@@ -1735,16 +1739,17 @@ static struct aggr_cpu_id perf_env__get_core_aggr_by_cpu(struct perf_cpu cpu, vo
 {
 	struct perf_env *env = data;
 	struct aggr_cpu_id id = aggr_cpu_id__empty();
+	struct cpu_topology_map *topo = perf_env__get_cpu_topology(env, cpu);
 
-	if (cpu.cpu != -1) {
+	if (topo) {
 		/*
 		 * core_id is relative to socket, die and cluster, we need a
 		 * global id. So we set socket, die id, cluster id and core id.
 		 */
-		id.socket = env->cpu[cpu.cpu].socket_id;
-		id.die = env->cpu[cpu.cpu].die_id;
-		id.cluster = env->cpu[cpu.cpu].cluster_id;
-		id.core = env->cpu[cpu.cpu].core_id;
+		id.socket = topo->socket_id;
+		id.die = topo->die_id;
+		id.cluster = topo->cluster_id;
+		id.core = topo->core_id;
 	}
 
 	return id;
@@ -1754,18 +1759,19 @@ static struct aggr_cpu_id perf_env__get_cpu_aggr_by_cpu(struct perf_cpu cpu, voi
 {
 	struct perf_env *env = data;
 	struct aggr_cpu_id id = aggr_cpu_id__empty();
+	struct cpu_topology_map *topo = perf_env__get_cpu_topology(env, cpu);
 
-	if (cpu.cpu != -1) {
+	if (topo) {
 		/*
 		 * core_id is relative to socket and die,
 		 * we need a global id. So we set
 		 * socket, die id and core id
 		 */
-		id.socket = env->cpu[cpu.cpu].socket_id;
-		id.die = env->cpu[cpu.cpu].die_id;
-		id.core = env->cpu[cpu.cpu].core_id;
-		id.cpu = cpu;
+		id.socket = topo->socket_id;
+		id.die = topo->die_id;
+		id.core = topo->core_id;
 	}
+	id.cpu = cpu;
 
 	return id;
 }
diff --git a/tools/perf/pmu-events/amd_metrics.py b/tools/perf/pmu-events/amd_metrics.py
index e2defaffde3e..971f6e7af1f8 100755
--- a/tools/perf/pmu-events/amd_metrics.py
+++ b/tools/perf/pmu-events/amd_metrics.py
@@ -268,7 +268,7 @@ def AmdDtlb() -> Optional[MetricGroup]:
 def AmdItlb():
     global _zen_model
     l2h = Event("bp_l1_tlb_miss_l2_tlb_hit", "bp_l1_tlb_miss_l2_hit")
-    l2m = Event("l2_itlb_misses")
+    l2m = Event("bp_l1_tlb_miss_l2_tlb_miss.all", "l2_itlb_misses",)
     l2r = l2h + l2m
 
     itlb_l1_mg = None
diff --git a/tools/perf/pmu-events/metric.py b/tools/perf/pmu-events/metric.py
index 585454828c2f..ac582db785fc 100644
--- a/tools/perf/pmu-events/metric.py
+++ b/tools/perf/pmu-events/metric.py
@@ -25,7 +25,6 @@ def LoadEvents(directory: str) -> None:
       "cycles",
       "duration_time",
       "instructions",
-      "l2_itlb_misses",
   }
   for file in os.listdir(os.fsencode(directory)):
     filename = os.fsdecode(file)
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 47043a3a2fb4..e82ecdc95777 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -471,8 +471,11 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 			goto out;
 		}
 
-		decomp = true;
-		objdump_name = decomp_name;
+		/* empty pathname means file wasn't actually compressed */
+		if (decomp_name[0] != '\0') {
+			decomp = true;
+			objdump_name = decomp_name;
+		}
 	}
 
 	/* Read the object code using objdump */
diff --git a/tools/perf/tests/dlfilter-test.c b/tools/perf/tests/dlfilter-test.c
index e63790c61d53..204663571943 100644
--- a/tools/perf/tests/dlfilter-test.c
+++ b/tools/perf/tests/dlfilter-test.c
@@ -188,8 +188,12 @@ static int write_sample(struct test_data *td, u64 sample_type, u64 id, pid_t pid
 
 	event->header.type = PERF_RECORD_SAMPLE;
 	event->header.misc = PERF_RECORD_MISC_USER;
-	event->header.size = perf_event__sample_event_size(&sample, sample_type, 0);
-	err = perf_event__synthesize_sample(event, sample_type, 0, &sample);
+	event->header.size = perf_event__sample_event_size(&sample, sample_type,
+							   /*read_format=*/0,
+							   /*branch_sample_type=*/0);
+	err = perf_event__synthesize_sample(event, sample_type,
+					    /*read_format=*/0,
+					    /*branch_sample_type=*/0, &sample);
 	if (err)
 		return test_result("perf_event__synthesize_sample() failed", TEST_FAIL);
 
diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c
index a99716862168..b1609a7e1d8c 100644
--- a/tools/perf/tests/pmu-events.c
+++ b/tools/perf/tests/pmu-events.c
@@ -15,6 +15,7 @@
 #include "util/expr.h"
 #include "util/hashmap.h"
 #include "util/parse-events.h"
+#include "util/tool_pmu.h"
 #include "metricgroup.h"
 #include "stat.h"
 
@@ -817,6 +818,26 @@ struct metric {
 	struct metric_ref metric_ref;
 };
 
+static bool is_expected_broken_metric(const struct pmu_metric *pm)
+{
+	if (!strcmp(pm->metric_name, "M1") || !strcmp(pm->metric_name, "M2") ||
+	    !strcmp(pm->metric_name, "M3"))
+		return true;
+
+#if defined(__aarch64__)
+	/*
+	 * Arm64 platforms may return "#slots == 0", which is treated as a
+	 * syntax error by the parser. Don't test these metrics when running
+	 * on such platforms.
+	 */
+	if (strstr(pm->metric_expr, "#slots") &&
+	    !tool_pmu__cpu_slots_per_cycle())
+		return true;
+#endif
+
+	return false;
+}
+
 static int test__parsing_callback(const struct pmu_metric *pm,
 				  const struct pmu_metrics_table *table,
 				  void *data)
@@ -852,8 +873,7 @@ static int test__parsing_callback(const struct pmu_metric *pm,
 
 	err = metricgroup__parse_groups_test(evlist, table, pm->metric_name);
 	if (err) {
-		if (!strcmp(pm->metric_name, "M1") || !strcmp(pm->metric_name, "M2") ||
-		    !strcmp(pm->metric_name, "M3")) {
+		if (is_expected_broken_metric(pm)) {
 			(*failures)--;
 			pr_debug("Expected broken metric %s skipping\n", pm->metric_name);
 			err = 0;
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index a7327c942ca2..55f0b73ca20e 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -310,7 +310,8 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
 		sample.read.one.lost  = 1;
 	}
 
-	sz = perf_event__sample_event_size(&sample, sample_type, read_format);
+	sz = perf_event__sample_event_size(&sample, sample_type, read_format,
+					   evsel.core.attr.branch_sample_type);
 	bufsz = sz + 4096; /* Add a bit for overrun checking */
 	event = malloc(bufsz);
 	if (!event) {
@@ -324,7 +325,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
 	event->header.size = sz;
 
 	err = perf_event__synthesize_sample(event, sample_type, read_format,
-					    &sample);
+					    evsel.core.attr.branch_sample_type, &sample);
 	if (err) {
 		pr_debug("%s failed for sample_type %#"PRIx64", error %d\n",
 			 "perf_event__synthesize_sample", sample_type, err);
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index dc88427b4ae5..321187b204d3 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -513,6 +513,9 @@ unsigned int ui_browser__list_head_refresh(struct ui_browser *browser)
 	struct list_head *head = browser->entries;
 	int row = 0;
 
+	if (browser->nr_entries == 0)
+		return 0;
+
 	if (browser->top == NULL || browser->top == browser->entries)
                 browser->top = ui_browser__list_head_filter_entries(browser, head->next);
 
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index ea17e6d29a7e..0261cd922183 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -449,6 +449,9 @@ static bool annotate_browser__toggle_source(struct annotate_browser *browser,
 	struct annotation_line *al;
 	off_t offset = browser->b.index - browser->b.top_idx;
 
+	if (browser->b.nr_entries == 0)
+		return false;
+
 	browser->b.seek(&browser->b, offset, SEEK_CUR);
 	al = list_entry(browser->b.top, struct annotation_line, node);
 
@@ -542,8 +545,8 @@ static void annotate_browser__show_full_location(struct ui_browser *browser)
 static void ui_browser__init_asm_mode(struct ui_browser *browser)
 {
 	struct annotation *notes = browser__annotation(browser);
-	ui_browser__reset_index(browser);
 	browser->nr_entries = notes->src->nr_asm_entries;
+	ui_browser__reset_index(browser);
 }
 
 static int sym_title(struct symbol *sym, struct map *map, char *title,
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 70cc91d00804..01edfccebb88 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -216,6 +216,7 @@ ifndef CONFIG_SETNS
 perf-util-y += setns.o
 endif
 
+perf-util-y += unwind.o
 perf-util-$(CONFIG_LIBDW) += probe-finder.o
 perf-util-$(CONFIG_LIBDW) += dwarf-aux.o
 perf-util-$(CONFIG_LIBDW) += dwarf-regs.o
diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c
index 1eff0a27237d..63e3c54fab42 100644
--- a/tools/perf/util/annotate-data.c
+++ b/tools/perf/util/annotate-data.c
@@ -74,7 +74,8 @@ void pr_debug_type_name(Dwarf_Die *die, enum type_state_kind kind)
 		break;
 	}
 
-	dwarf_aggregate_size(die, &size);
+	if (dwarf_aggregate_size(die, &size) != 0)
+		size = 0;
 
 	strbuf_init(&sb, 32);
 	die_get_typename_from_type(die, &sb);
@@ -146,9 +147,9 @@ static void pr_debug_scope(Dwarf_Die *scope_die)
 
 	tag = dwarf_tag(scope_die);
 	if (tag == DW_TAG_subprogram)
-		pr_info("[function] %s\n", dwarf_diename(scope_die));
+		pr_info("[function] %s\n", die_name(scope_die));
 	else if (tag == DW_TAG_inlined_subroutine)
-		pr_info("[inlined] %s\n", dwarf_diename(scope_die));
+		pr_info("[inlined] %s\n", die_name(scope_die));
 	else if (tag == DW_TAG_lexical_block)
 		pr_info("[block]\n");
 	else
@@ -250,9 +251,12 @@ static int __add_member_cb(Dwarf_Die *die, void *arg)
 	if (dwarf_aggregate_size(&die_mem, &size) < 0)
 		size = 0;
 
-	if (dwarf_attr_integrate(die, DW_AT_data_member_location, &attr))
-		dwarf_formudata(&attr, &loc);
-	else {
+	if (dwarf_attr_integrate(die, DW_AT_data_member_location, &attr)) {
+		if (dwarf_formudata(&attr, &loc) != 0) {
+			if (die_get_data_member_location(die, &loc) != 0)
+				loc = 0;
+		}
+	} else {
 		/* bitfield member */
 		if (dwarf_attr_integrate(die, DW_AT_data_bit_offset, &attr) &&
 		    dwarf_formudata(&attr, &loc) == 0)
@@ -273,7 +277,9 @@ static int __add_member_cb(Dwarf_Die *die, void *arg)
 				     dwarf_diename(die), (long)bit_size) < 0)
 				member->var_name = NULL;
 		} else {
-			member->var_name = strdup(dwarf_diename(die));
+			const char *name = dwarf_diename(die);
+
+			member->var_name = name ? strdup(name) : NULL;
 		}
 
 		if (member->var_name == NULL) {
@@ -370,7 +376,8 @@ static struct annotated_data_type *dso__findnew_data_type(struct dso *dso,
 	if (dwarf_tag(type_die) == DW_TAG_typedef)
 		die_get_real_type(type_die, type_die);
 
-	dwarf_aggregate_size(type_die, &size);
+	if (dwarf_aggregate_size(type_die, &size) != 0)
+		size = 0;
 
 	/* Check existing nodes in dso->data_types tree */
 	key.self.type_name = type_name;
@@ -1569,7 +1576,7 @@ static int find_data_type_die(struct data_loc_info *dloc, Dwarf_Die *type_die)
 	offset = loc->offset;
 
 	pr_debug_dtp("CU for %s (die:%#lx)\n",
-		     dwarf_diename(&cu_die), (long)dwarf_dieoffset(&cu_die));
+		     die_name(&cu_die), (long)dwarf_dieoffset(&cu_die));
 
 	if (reg == DWARF_REG_PC) {
 		if (get_global_var_type(&cu_die, dloc, dloc->ip, dloc->var_addr,
@@ -1636,7 +1643,7 @@ retry:
 		}
 
 		pr_debug_dtp("found \"%s\" (die: %#lx) in scope=%d/%d (die: %#lx) ",
-			     dwarf_diename(&var_die), (long)dwarf_dieoffset(&var_die),
+			     die_name(&var_die), (long)dwarf_dieoffset(&var_die),
 			     i+1, nr_scopes, (long)dwarf_dieoffset(&scopes[i]));
 
 		if (reg == DWARF_REG_PC) {
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index e5835042acdf..3e54ed41653b 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -482,10 +482,30 @@ static void arm_spe__prep_branch_stack(struct arm_spe_queue *speq)
 	bstack->hw_idx = -1ULL;
 }
 
-static int arm_spe__inject_event(union perf_event *event, struct perf_sample *sample, u64 type)
+static int arm_spe__inject_event(struct arm_spe *spe, union perf_event *event,
+				 struct perf_sample *sample, u64 type)
 {
-	event->header.size = perf_event__sample_event_size(sample, type, 0);
-	return perf_event__synthesize_sample(event, type, 0, sample);
+	struct evsel *evsel = sample->evsel;
+	u64 branch_sample_type = 0;
+	size_t sz;
+
+	if (!evsel && spe->session && spe->session->evlist)
+		evsel = evlist__id2evsel(spe->session->evlist, sample->id);
+
+	if (evsel)
+		branch_sample_type = evsel->core.attr.branch_sample_type;
+
+	event->header.type = PERF_RECORD_SAMPLE;
+	sz = perf_event__sample_event_size(sample, type, /*read_format=*/0,
+					   branch_sample_type);
+	if (sz >= PERF_SAMPLE_MAX_SIZE) {
+		pr_err("Sample size %zu exceeds max size %d\n", sz, PERF_SAMPLE_MAX_SIZE);
+		return -EFAULT;
+	}
+	event->header.size = sz;
+
+	return perf_event__synthesize_sample(event, type, /*read_format=*/0,
+					     branch_sample_type, sample);
 }
 
 static inline int
@@ -497,7 +517,7 @@ arm_spe_deliver_synth_event(struct arm_spe *spe,
 	int ret;
 
 	if (spe->synth_opts.inject) {
-		ret = arm_spe__inject_event(event, sample, spe->sample_type);
+		ret = arm_spe__inject_event(spe, event, sample, spe->sample_type);
 		if (ret)
 			return ret;
 	}
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index a224687ffbc1..47e2004b91d7 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -372,7 +372,8 @@ static bool filter_cpu(struct perf_session *session, struct perf_cpu cpu)
 {
 	unsigned long *cpu_bitmap = session->itrace_synth_opts->cpu_bitmap;
 
-	return cpu_bitmap && cpu.cpu != -1 && !test_bit(cpu.cpu, cpu_bitmap);
+	return cpu_bitmap && cpu.cpu >= 0 && cpu.cpu < MAX_NR_CPUS &&
+	       !test_bit(cpu.cpu, cpu_bitmap);
 }
 
 static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues,
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index a27945c279ef..fa3ebc8ea7f0 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -36,7 +36,7 @@ static int snprintf_hex(char *buf, size_t size, unsigned char *data, size_t len)
 	size_t i;
 
 	for (i = 0; i < len; i++)
-		ret += snprintf(buf + ret, size - ret, "%02x", data[i]);
+		ret += scnprintf(buf + ret, size - ret, "%02x", data[i]);
 	return ret;
 }
 
@@ -59,6 +59,10 @@ static int machine__process_bpf_event_load(struct machine *machine,
 		return 0;
 	info_linear = info_node->info_linear;
 
+	/* jited_ksyms is only valid if bpil_offs_to_addr() converted it */
+	if (!(info_linear->arrays & (1UL << PERF_BPIL_JITED_KSYMS)))
+		return 0;
+
 	for (i = 0; i < info_linear->info.nr_jited_ksyms; i++) {
 		u64 *addrs = (u64 *)(uintptr_t)(info_linear->info.jited_ksyms);
 		u64 addr = addrs[i];
@@ -140,22 +144,26 @@ static int synthesize_bpf_prog_name(char *buf, int size,
 	const struct btf_type *t;
 	int name_len;
 
-	name_len = snprintf(buf, size, "bpf_prog_");
+	name_len = scnprintf(buf, size, "bpf_prog_");
 	name_len += snprintf_hex(buf + name_len, size - name_len,
 				 prog_tags[sub_id], BPF_TAG_SIZE);
-	if (btf) {
+	if (btf &&
+	    info->func_info_rec_size >= sizeof(*finfo) &&
+	    sub_id < info->nr_func_info) {
 		finfo = func_infos + sub_id * info->func_info_rec_size;
 		t = btf__type_by_id(btf, finfo->type_id);
-		short_name = btf__name_by_offset(btf, t->name_off);
+		if (t)
+			short_name = btf__name_by_offset(btf, t->name_off);
 	} else if (sub_id == 0 && sub_prog_cnt == 1) {
 		/* no subprog */
 		if (info->name[0])
 			short_name = info->name;
 	} else
 		short_name = "F";
-	if (short_name)
-		name_len += snprintf(buf + name_len, size - name_len,
-				     "_%s", short_name);
+	if (short_name) {
+		name_len += scnprintf(buf + name_len, size - name_len,
+				      "_%s", short_name);
+	}
 	return name_len;
 }
 
@@ -365,6 +373,15 @@ static struct bpf_metadata *bpf_metadata_alloc(__u32 nr_prog_tags,
 
 	event_size = sizeof(metadata->event->bpf_metadata) +
 	    nr_variables * sizeof(metadata->event->bpf_metadata.entries[0]);
+	/*
+	 * header.size is __u16.  synthesize_perf_record_bpf_metadata()
+	 * adds machine->id_hdr_size (up to ~64 bytes) after this, so
+	 * leave headroom to prevent the final size from wrapping.
+	 */
+	if (event_size > UINT16_MAX - 256) {
+		bpf_metadata_free(metadata);
+		return NULL;
+	}
 	metadata->event = zalloc(event_size);
 	if (!metadata->event) {
 		bpf_metadata_free(metadata);
@@ -393,8 +410,10 @@ static struct bpf_metadata *bpf_metadata_create(struct bpf_prog_info *info)
 			continue;
 
 		metadata = bpf_metadata_alloc(info->nr_prog_tags, map.num_vars);
-		if (!metadata)
+		if (!metadata) {
+			bpf_metadata_free_map_data(&map);
 			continue;
+		}
 
 		bpf_metadata_fill_event(&map, &metadata->event->bpf_metadata);
 
@@ -869,6 +888,7 @@ static int perf_env__add_bpf_info(struct perf_env *env, u32 id)
 		if (!perf_env__insert_bpf_prog_info(env, info_node)) {
 			pr_debug("%s: duplicate add bpf info request for id %u\n",
 				 __func__, btf_id);
+			bpf_metadata_free(info_node->metadata);
 			free(info_linear);
 			free(info_node);
 			goto out;
@@ -943,12 +963,15 @@ int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env)
 	return evlist__add_sb_event(evlist, &attr, bpf_event__sb_cb, env);
 }
 
-void __bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
+void __bpf_event__print_bpf_prog_info(struct perf_bpil *info_linear,
 				      struct perf_env *env,
 				      FILE *fp)
 {
-	__u32 *prog_lens = (__u32 *)(uintptr_t)(info->jited_func_lens);
-	__u64 *prog_addrs = (__u64 *)(uintptr_t)(info->jited_ksyms);
+	struct bpf_prog_info *info = &info_linear->info;
+	__u64 required_arrays = (1UL << PERF_BPIL_JITED_KSYMS) |
+				(1UL << PERF_BPIL_JITED_FUNC_LENS);
+	__u32 *prog_lens;
+	__u64 *prog_addrs;
 	char name[KSYM_NAME_LEN];
 	struct btf *btf = NULL;
 	u32 sub_prog_cnt, i;
@@ -958,6 +981,13 @@ void __bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
 	    sub_prog_cnt != info->nr_jited_func_lens)
 		return;
 
+	/* Ensure the arrays were present and converted by bpil_offs_to_addr() */
+	if ((info_linear->arrays & required_arrays) != required_arrays)
+		return;
+
+	prog_lens = (__u32 *)(uintptr_t)(info->jited_func_lens);
+	prog_addrs = (__u64 *)(uintptr_t)(info->jited_ksyms);
+
 	if (info->btf_id) {
 		struct btf_node *node;
 
diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h
index 60d2c6637af5..da4eeb4a1a73 100644
--- a/tools/perf/util/bpf-event.h
+++ b/tools/perf/util/bpf-event.h
@@ -40,7 +40,7 @@ struct btf_node {
 int machine__process_bpf(struct machine *machine, union perf_event *event,
 			 struct perf_sample *sample);
 int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env);
-void __bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
+void __bpf_event__print_bpf_prog_info(struct perf_bpil *info_linear,
 				      struct perf_env *env,
 				      FILE *fp);
 void bpf_metadata_free(struct bpf_metadata *metadata);
@@ -58,7 +58,7 @@ static inline int evlist__add_bpf_sb_event(struct evlist *evlist __maybe_unused,
 	return 0;
 }
 
-static inline void __bpf_event__print_bpf_prog_info(struct bpf_prog_info *info __maybe_unused,
+static inline void __bpf_event__print_bpf_prog_info(struct perf_bpil *info_linear __maybe_unused,
 						    struct perf_env *env __maybe_unused,
 						    FILE *fp __maybe_unused)
 {
diff --git a/tools/perf/util/bpf-utils.c b/tools/perf/util/bpf-utils.c
index d6d2c9c190f7..69148197b1ef 100644
--- a/tools/perf/util/bpf-utils.c
+++ b/tools/perf/util/bpf-utils.c
@@ -264,12 +264,28 @@ void bpil_offs_to_addr(struct perf_bpil *info_linear)
 	for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) {
 		const struct bpil_array_desc *desc = &bpil_array_desc[i];
 		__u64 addr, offs;
+		__u32 count, size;
 
 		if ((info_linear->arrays & (1UL << i)) == 0)
 			continue;
 
 		offs = bpf_prog_info_read_offset_u64(&info_linear->info,
 						     desc->array_offset);
+		count = bpf_prog_info_read_offset_u32(&info_linear->info,
+						      desc->count_offset);
+		size = bpf_prog_info_read_offset_u32(&info_linear->info,
+						     desc->size_offset);
+		/* offset and extent from perf.data are untrusted — keep within data[] */
+		if (offs >= info_linear->data_len ||
+		    (u64)count * size > info_linear->data_len - offs) {
+			bpf_prog_info_set_offset_u64(&info_linear->info,
+						     desc->array_offset, 0);
+			bpf_prog_info_set_offset_u32(&info_linear->info,
+						     desc->count_offset, 0);
+			/* clear the bit so bpil_addr_to_offs() won't reverse a zeroed address */
+			info_linear->arrays &= ~(1UL << i);
+			continue;
+		}
 		addr = offs + ptr_to_u64(info_linear->data);
 		bpf_prog_info_set_offset_u64(&info_linear->info,
 					     desc->array_offset, addr);
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index fdb35133fde4..3c286cdbe6e0 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -93,8 +93,11 @@ int build_id__snprintf(const struct build_id *build_id, char *bf, size_t bf_size
 		return 0;
 	}
 
-	for (size_t i = 0; i < build_id->size && offs < bf_size; ++i)
-		offs += snprintf(bf + offs, bf_size - offs, "%02x", build_id->data[i]);
+	if (bf_size > 0)
+		bf[0] = '\0';
+
+	for (size_t i = 0; i < build_id->size && offs + 1 < bf_size; ++i)
+		offs += scnprintf(bf + offs, bf_size - offs, "%02x", build_id->data[i]);
 
 	return offs;
 }
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index f031cbbeeba8..5e0498a1faf8 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -1578,6 +1578,21 @@ void free_callchain(struct callchain_root *root)
 	free_callchain_node(&root->node);
 }
 
+void callchain_cursor_cleanup(struct callchain_cursor *cursor)
+{
+	struct callchain_cursor_node *node, *next;
+
+	callchain_cursor_reset(cursor);
+
+	for (node = cursor->first; node; node = next) {
+		next = node->next;
+		free(node);
+	}
+	cursor->first = NULL;
+	cursor->last = &cursor->first;
+	cursor->curr = NULL;
+}
+
 static u64 decay_callchain_node(struct callchain_node *node)
 {
 	struct callchain_node *child;
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 06d463ccc7a0..60008f379b22 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -290,6 +290,7 @@ int callchain_list_counts__printf_value(struct callchain_list *clist,
 					FILE *fp, char *bf, int bfsize);
 
 void free_callchain(struct callchain_root *root);
+void callchain_cursor_cleanup(struct callchain_cursor *cursor);
 void decay_callchain(struct callchain_root *root);
 int callchain_node__make_parent_list(struct callchain_node *node);
 
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 087002fb1b9b..7988149dc7ed 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -23,6 +23,7 @@
 #include "build-id.h"
 #include "debug.h"
 #include "config.h"
+#include "unwind.h"
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <stdlib.h>
@@ -525,6 +526,9 @@ int perf_default_config(const char *var, const char *value,
 	if (strstarts(var, "addr2line."))
 		return addr2line_configure(var, value, dummy);
 
+	if (strstarts(var, "unwind."))
+		return unwind__configure(var, value, dummy);
+
 	/* Add other config variables here. */
 	return 0;
 }
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 11922e1ded84..dbbec195cffd 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -420,6 +420,12 @@ static int get_max_num(char *path, int *max)
 
 	buf[num] = '\0';
 
+	/* empty file — nothing to parse */
+	if (num == 0) {
+		err = -1;
+		goto out;
+	}
+
 	/* start on the right, to find highest node num */
 	while (--num) {
 		if ((buf[num] == ',') || (buf[num] == '-')) {
@@ -466,6 +472,16 @@ static void set_max_cpu_num(void)
 	if (ret)
 		goto out;
 
+	/*
+	 * struct perf_cpu.cpu is int16_t (libperf ABI) — clamp to avoid
+	 * truncation to negative.  See tools/lib/perf/TODO for the ABI
+	 * widening plan.
+	 */
+	if (max > INT16_MAX) {
+		pr_warning("WARNING: max possible cpus %d exceeds int16_t, clamping to %d\n",
+			   max, INT16_MAX);
+		max = INT16_MAX;
+	}
 	max_cpu_num.cpu = max;
 
 	/* get the highest present cpu number for a sparse allocation */
@@ -478,11 +494,12 @@ static void set_max_cpu_num(void)
 	ret = get_max_num(path, &max);
 
 	if (!ret && max > INT16_MAX) {
-		pr_err("Read out of bounds max cpus of %d\n", max);
-		ret = -1;
+		pr_warning("WARNING: max present cpus %d exceeds int16_t, clamping to %d\n",
+			   max, INT16_MAX);
+		max = INT16_MAX;
 	}
 	if (!ret)
-		max_present_cpu_num.cpu = (int16_t)max;
+		max_present_cpu_num.cpu = max;
 out:
 	if (ret)
 		pr_err("Failed to read max cpus, using default of %d\n", max_cpu_num.cpu);
@@ -548,6 +565,10 @@ int cpu__get_node(struct perf_cpu cpu)
 		return -1;
 	}
 
+	/* cpunode_map allocated for max_cpu_num entries; input may be untrusted */
+	if (cpu.cpu < 0 || cpu.cpu >= max_cpu_num.cpu)
+		return -1;
+
 	return cpunode_map[cpu.cpu];
 }
 
@@ -615,7 +636,9 @@ int cpu__setup_cpunode_map(void)
 		while ((dent2 = readdir(dir2)) != NULL) {
 			if (dent2->d_type != DT_LNK || sscanf(dent2->d_name, "cpu%u", &cpu) < 1)
 				continue;
-			cpunode_map[cpu] = mem;
+			/* cpunode_map allocated for max_cpu_num entries */
+			if (cpu < (unsigned int)max_cpu_num.cpu)
+				cpunode_map[cpu] = mem;
 		}
 		closedir(dir2);
 	}
@@ -641,21 +664,21 @@ size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size)
 		if (start == -1) {
 			start = i;
 			if (last) {
-				ret += snprintf(buf + ret, size - ret,
-						"%s%d", COMMA,
-						perf_cpu_map__cpu(map, i).cpu);
+				ret += scnprintf(buf + ret, size - ret,
+						 "%s%d", COMMA,
+						 perf_cpu_map__cpu(map, i).cpu);
 			}
 		} else if (((i - start) != (cpu.cpu - perf_cpu_map__cpu(map, start).cpu)) || last) {
 			int end = i - 1;
 
 			if (start == end) {
-				ret += snprintf(buf + ret, size - ret,
-						"%s%d", COMMA,
-						perf_cpu_map__cpu(map, start).cpu);
+				ret += scnprintf(buf + ret, size - ret,
+						 "%s%d", COMMA,
+						 perf_cpu_map__cpu(map, start).cpu);
 			} else {
-				ret += snprintf(buf + ret, size - ret,
-						"%s%d-%d", COMMA,
-						perf_cpu_map__cpu(map, start).cpu, perf_cpu_map__cpu(map, end).cpu);
+				ret += scnprintf(buf + ret, size - ret,
+						 "%s%d-%d", COMMA,
+						 perf_cpu_map__cpu(map, start).cpu, perf_cpu_map__cpu(map, end).cpu);
 			}
 			first = false;
 			start = i;
diff --git a/tools/perf/util/cs-etm-base.c b/tools/perf/util/cs-etm-base.c
index 4abe416e3feb..aebef71d3a0a 100644
--- a/tools/perf/util/cs-etm-base.c
+++ b/tools/perf/util/cs-etm-base.c
@@ -170,7 +170,9 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
 	u64 *ptr = NULL;
 	u64 hdr_version;
 
-	if (auxtrace_info->header.size < (event_header_size + INFO_HEADER_SIZE))
+	/* Ensure priv[] is large enough for the global header entries */
+	if (auxtrace_info->header.size < (event_header_size + INFO_HEADER_SIZE +
+					  CS_ETM_HEADER_SIZE))
 		return -EINVAL;
 
 	/* First the global part */
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index dee3020ceaa9..26940f1f1b0b 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -402,6 +402,8 @@ cs_etm_decoder__buffer_packet(struct cs_etm_queue *etmq,
 	packet_queue->packet_buffer[et].flags = 0;
 	packet_queue->packet_buffer[et].exception_number = UINT32_MAX;
 	packet_queue->packet_buffer[et].trace_chan_id = trace_chan_id;
+	packet_queue->packet_buffer[et].el = ocsd_EL_unknown;
+	packet_queue->packet_buffer[et].tid = -1;
 
 	if (packet_queue->packet_count == CS_ETM_PACKET_MAX_BUFFER - 1)
 		return OCSD_RESP_WAIT;
@@ -449,6 +451,7 @@ cs_etm_decoder__buffer_range(struct cs_etm_queue *etmq,
 	packet->last_instr_type = elem->last_i_type;
 	packet->last_instr_subtype = elem->last_i_subtype;
 	packet->last_instr_cond = elem->last_instr_cond;
+	packet->el = elem->context.exception_level;
 
 	if (elem->last_i_type == OCSD_INSTR_BR || elem->last_i_type == OCSD_INSTR_BR_INDIRECT)
 		packet->last_instr_taken_branch = elem->last_instr_exec;
@@ -525,7 +528,9 @@ cs_etm_decoder__set_tid(struct cs_etm_queue *etmq,
 			const ocsd_generic_trace_elem *elem,
 			const uint8_t trace_chan_id)
 {
+	struct cs_etm_packet *packet;
 	pid_t tid = -1;
+	int ret;
 
 	/*
 	 * Process the PE_CONTEXT packets if we have a valid contextID or VMID.
@@ -546,12 +551,18 @@ cs_etm_decoder__set_tid(struct cs_etm_queue *etmq,
 		break;
 	}
 
-	if (cs_etm__etmq_set_tid_el(etmq, tid, trace_chan_id,
-				    elem->context.exception_level))
+	if (cs_etm__etmq_update_decode_context(etmq, trace_chan_id,
+				elem->context.exception_level, tid))
 		return OCSD_RESP_FATAL_SYS_ERR;
 
-	if (tid == -1)
-		return OCSD_RESP_CONT;
+	ret = cs_etm_decoder__buffer_packet(etmq, packet_queue, trace_chan_id,
+					    CS_ETM_CONTEXT);
+	if (ret != OCSD_RESP_CONT && ret != OCSD_RESP_WAIT)
+		return ret;
+
+	packet = &packet_queue->packet_buffer[packet_queue->tail];
+	packet->tid = tid;
+	packet->el = elem->context.exception_level;
 
 	/*
 	 * A timestamp is generated after a PE_CONTEXT element so make sure
@@ -559,7 +570,7 @@ cs_etm_decoder__set_tid(struct cs_etm_queue *etmq,
 	 */
 	cs_etm_decoder__reset_timestamp(packet_queue);
 
-	return OCSD_RESP_CONT;
+	return ret;
 }
 
 static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer(
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 8a639d2e51a4..5ca55b527183 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -6,6 +6,7 @@
  * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
  */
 
+#include <limits.h>
 #include <linux/bitfield.h>
 #include <linux/bitops.h>
 #include <linux/coresight-pmu.h>
@@ -85,15 +86,22 @@ struct cs_etm_traceid_queue {
 	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;
 	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;
+
+	struct thread *decode_thread;
+	ocsd_ex_level decode_el;
+
+	/*
+	 * The frontend accesses the EL from '[prev_]packet' because it needs
+	 * previous EL for branch and current EL for instruction samples. It's
+	 * not possible to change thread in a single branch sample so no need to
+	 * store or access the thread through the packet.
+	 */
+	struct thread *frontend_thread;
 };
 
 enum cs_etm_format {
@@ -284,8 +292,11 @@ static struct cs_etm_queue *cs_etm__get_queue(struct cs_etm_auxtrace *etm, int c
 {
 	if (etm->per_thread_decoding)
 		return etm->queues.queue_array[0].priv;
-	else
-		return etm->queues.queue_array[cpu].priv;
+
+	if (cpu < 0 || cpu >= (int)etm->queues.nr_queues)
+		return NULL;
+
+	return etm->queues.queue_array[cpu].priv;
 }
 
 static int cs_etm__map_trace_id_v0(struct cs_etm_auxtrace *etm, u8 trace_chan_id,
@@ -298,6 +309,9 @@ static int cs_etm__map_trace_id_v0(struct cs_etm_auxtrace *etm, u8 trace_chan_id
 	 * queue associated with that CPU so only one decoder is made.
 	 */
 	etmq = cs_etm__get_queue(etm, cpu_metadata[CS_ETM_CPU]);
+	if (!etmq)
+		return -EINVAL;
+
 	if (etmq->format == UNFORMATTED)
 		return cs_etm__insert_trace_id_node(etmq, trace_chan_id,
 						    cpu_metadata);
@@ -310,6 +324,9 @@ static int cs_etm__map_trace_id_v0(struct cs_etm_auxtrace *etm, u8 trace_chan_id
 		int ret;
 
 		etmq = etm->queues.queue_array[i].priv;
+		if (!etmq)
+			continue;
+
 		ret = cs_etm__insert_trace_id_node(etmq, trace_chan_id,
 						   cpu_metadata);
 		if (ret)
@@ -350,6 +367,9 @@ static int cs_etm__process_trace_id_v0_1(struct cs_etm_auxtrace *etm, int cpu,
 	u32 sink_id = FIELD_GET(CS_AUX_HW_ID_SINK_ID_MASK, hw_id);
 	u8 trace_id = FIELD_GET(CS_AUX_HW_ID_TRACE_ID_MASK, hw_id);
 
+	if (!etmq)
+		return -EINVAL;
+
 	/*
 	 * Check sink id hasn't changed in per-cpu mode. In per-thread mode,
 	 * let it pass for now until an actual overlapping trace ID is hit. In
@@ -367,6 +387,9 @@ static int cs_etm__process_trace_id_v0_1(struct cs_etm_auxtrace *etm, int cpu,
 	for (unsigned int i = 0; i < etm->queues.nr_queues; ++i) {
 		struct cs_etm_queue *other_etmq = etm->queues.queue_array[i].priv;
 
+		if (!other_etmq)
+			continue;
+
 		/* Different sinks, skip */
 		if (other_etmq->sink_id != etmq->sink_id)
 			continue;
@@ -388,6 +411,9 @@ static int cs_etm__process_trace_id_v0_1(struct cs_etm_auxtrace *etm, int cpu,
 	}
 
 	cpu_data = get_cpu_data(etm, cpu);
+	if (!cpu_data)
+		return -EINVAL;
+
 	ret = cs_etm__insert_trace_id_node(etmq, trace_id, cpu_data);
 	if (ret)
 		return ret;
@@ -614,10 +640,11 @@ static int cs_etm__init_traceid_queue(struct cs_etm_queue *etmq,
 
 	queue = &etmq->etm->queues.queue_array[etmq->queue_nr];
 	tidq->trace_chan_id = trace_chan_id;
-	tidq->el = tidq->prev_packet_el = ocsd_EL_unknown;
-	tidq->thread = machine__findnew_thread(&etm->session->machines.host, -1,
+	tidq->decode_el = ocsd_EL_unknown;
+	tidq->frontend_thread = machine__findnew_thread(&etm->session->machines.host, -1,
+					       queue->tid);
+	tidq->decode_thread = machine__findnew_thread(&etm->session->machines.host, -1,
 					       queue->tid);
-	tidq->prev_packet_thread = machine__idle_thread(&etm->session->machines.host);
 
 	tidq->packet = zalloc(sizeof(struct cs_etm_packet));
 	if (!tidq->packet)
@@ -750,21 +777,10 @@ static void cs_etm__packet_swap(struct cs_etm_auxtrace *etm,
 		/*
 		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
 		 * the next incoming packet.
-		 *
-		 * Threads and exception levels are also tracked for both the
-		 * previous and current packets. This is because the previous
-		 * packet is used for the 'from' IP for branch samples, so the
-		 * thread at that time must also be assigned to that sample.
-		 * Across discontinuity packets the thread can change, so by
-		 * tracking the thread for the previous packet the branch sample
-		 * will have the correct info.
 		 */
 		tmp = tidq->packet;
 		tidq->packet = tidq->prev_packet;
 		tidq->prev_packet = tmp;
-		tidq->prev_packet_el = tidq->el;
-		thread__put(tidq->prev_packet_thread);
-		tidq->prev_packet_thread = thread__get(tidq->thread);
 	}
 }
 
@@ -937,8 +953,8 @@ static void cs_etm__free_traceid_queues(struct cs_etm_queue *etmq)
 
 		/* Free this traceid_queue from the array */
 		tidq = etmq->traceid_queues[idx];
-		thread__zput(tidq->thread);
-		thread__zput(tidq->prev_packet_thread);
+		thread__zput(tidq->frontend_thread);
+		thread__zput(tidq->decode_thread);
 		zfree(&tidq->event_buf);
 		zfree(&tidq->last_branch);
 		zfree(&tidq->last_branch_rb);
@@ -1083,47 +1099,43 @@ static u8 cs_etm__cpu_mode(struct cs_etm_queue *etmq, u64 address,
 	}
 }
 
-static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u8 trace_chan_id,
-			      u64 address, size_t size, u8 *buffer,
-			      const ocsd_mem_space_acc_t mem_space)
+static u32 __cs_etm__mem_access(struct cs_etm_queue *etmq,
+				u64 address, size_t size, u8 *buffer,
+				const ocsd_mem_space_acc_t mem_space,
+				ocsd_ex_level el, struct thread *thread)
 {
 	u8  cpumode;
 	u64 offset;
 	int len;
 	struct addr_location al;
 	struct dso *dso;
-	struct cs_etm_traceid_queue *tidq;
 	int ret = 0;
 
 	if (!etmq)
 		return 0;
 
 	addr_location__init(&al);
-	tidq = cs_etm__etmq_get_traceid_queue(etmq, trace_chan_id);
-	if (!tidq)
-		goto out;
 
 	/*
-	 * We've already tracked EL along side the PID in cs_etm__set_thread()
-	 * so double check that it matches what OpenCSD thinks as well. It
-	 * doesn't distinguish between EL0 and EL1 for this mem access callback
-	 * so we had to do the extra tracking. Skip validation if it's any of
-	 * the 'any' values.
+	 * We track EL for the frontend and the backend when receiving context
+	 * and range packets. OpenCSD doesn't distinguish between EL0 and EL1
+	 * for this mem access callback so we had to do the extra tracking. Skip
+	 * validation if it's any of the 'any' values.
 	 */
 	if (!(mem_space == OCSD_MEM_SPACE_ANY ||
 	      mem_space == OCSD_MEM_SPACE_N || mem_space == OCSD_MEM_SPACE_S)) {
 		if (mem_space & OCSD_MEM_SPACE_EL1N) {
 			/* Includes both non secure EL1 and EL0 */
-			assert(tidq->el == ocsd_EL1 || tidq->el == ocsd_EL0);
+			assert(el == ocsd_EL1 || el == ocsd_EL0);
 		} else if (mem_space & OCSD_MEM_SPACE_EL2)
-			assert(tidq->el == ocsd_EL2);
+			assert(el == ocsd_EL2);
 		else if (mem_space & OCSD_MEM_SPACE_EL3)
-			assert(tidq->el == ocsd_EL3);
+			assert(el == ocsd_EL3);
 	}
 
-	cpumode = cs_etm__cpu_mode(etmq, address, tidq->el);
+	cpumode = cs_etm__cpu_mode(etmq, address, el);
 
-	if (!thread__find_map(tidq->thread, cpumode, address, &al))
+	if (!thread__find_map(thread, cpumode, address, &al))
 		goto out;
 
 	dso = map__dso(al.map);
@@ -1138,7 +1150,7 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u8 trace_chan_id,
 
 	map__load(al.map);
 
-	len = dso__data_read_offset(dso, maps__machine(thread__maps(tidq->thread)),
+	len = dso__data_read_offset(dso, maps__machine(thread__maps(thread)),
 				    offset, buffer, size);
 
 	if (len <= 0) {
@@ -1158,6 +1170,30 @@ out:
 	return ret;
 }
 
+static u32 cs_etm__frontend_mem_access(struct cs_etm_queue *etmq,
+				       struct cs_etm_traceid_queue *tidq,
+				       struct cs_etm_packet *packet,
+				       u64 address, size_t size, u8 *buffer)
+{
+	return __cs_etm__mem_access(etmq, address, size, buffer, 0, packet->el,
+				    tidq->frontend_thread);
+}
+
+static u32 cs_etm__decoder_mem_access(struct cs_etm_queue *etmq, u8 trace_chan_id,
+				      u64 address, size_t size, u8 *buffer,
+				      const ocsd_mem_space_acc_t mem_space)
+{
+	struct cs_etm_traceid_queue *tidq;
+
+	tidq = cs_etm__etmq_get_traceid_queue(etmq, trace_chan_id);
+	if (!tidq)
+		return 0;
+
+	return __cs_etm__mem_access(etmq, address, size, buffer,
+				    mem_space, tidq->decode_el,
+				    tidq->decode_thread);
+}
+
 static struct cs_etm_queue *cs_etm__alloc_queue(void)
 {
 	struct cs_etm_queue *etmq = zalloc(sizeof(*etmq));
@@ -1333,12 +1369,13 @@ void cs_etm__reset_last_branch_rb(struct cs_etm_traceid_queue *tidq)
 }
 
 static inline int cs_etm__t32_instr_size(struct cs_etm_queue *etmq,
-					 u8 trace_chan_id, u64 addr)
+					 struct cs_etm_traceid_queue *tidq,
+					 struct cs_etm_packet *packet, u64 addr)
 {
 	u8 instrBytes[2];
 
-	cs_etm__mem_access(etmq, trace_chan_id, addr, ARRAY_SIZE(instrBytes),
-			   instrBytes, 0);
+	cs_etm__frontend_mem_access(etmq, tidq, packet, addr,
+				    ARRAY_SIZE(instrBytes), instrBytes);
 	/*
 	 * T32 instruction size is indicated by bits[15:11] of the first
 	 * 16-bit word of the instruction: 0b11101, 0b11110 and 0b11111
@@ -1371,16 +1408,16 @@ u64 cs_etm__last_executed_instr(const struct cs_etm_packet *packet)
 }
 
 static inline u64 cs_etm__instr_addr(struct cs_etm_queue *etmq,
-				     u64 trace_chan_id,
-				     const struct cs_etm_packet *packet,
+				     struct cs_etm_traceid_queue *tidq,
+				     struct cs_etm_packet *packet,
 				     u64 offset)
 {
 	if (packet->isa == CS_ETM_ISA_T32) {
 		u64 addr = packet->start_addr;
 
 		while (offset) {
-			addr += cs_etm__t32_instr_size(etmq,
-						       trace_chan_id, addr);
+			addr += cs_etm__t32_instr_size(etmq, tidq, packet,
+						       addr);
 			offset--;
 		}
 		return addr;
@@ -1422,11 +1459,29 @@ static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq,
 		bs->nr += 1;
 }
 
-static int cs_etm__inject_event(union perf_event *event,
+static int cs_etm__inject_event(struct cs_etm_auxtrace *etm, union perf_event *event,
 			       struct perf_sample *sample, u64 type)
 {
-	event->header.size = perf_event__sample_event_size(sample, type, 0);
-	return perf_event__synthesize_sample(event, type, 0, sample);
+	struct evsel *evsel = sample->evsel;
+	u64 branch_sample_type = 0;
+	size_t sz;
+
+	if (!evsel && etm->session && etm->session->evlist)
+		evsel = evlist__id2evsel(etm->session->evlist, sample->id);
+
+	if (evsel)
+		branch_sample_type = evsel->core.attr.branch_sample_type;
+
+	sz = perf_event__sample_event_size(sample, type, /*read_format=*/0,
+					   branch_sample_type);
+	if (sz >= PERF_SAMPLE_MAX_SIZE) {
+		pr_err("Sample size %zu exceeds max size %d\n", sz, PERF_SAMPLE_MAX_SIZE);
+		return -EFAULT;
+	}
+	event->header.size = sz;
+
+	return perf_event__synthesize_sample(event, type, /*read_format=*/0,
+					     branch_sample_type, sample);
 }
 
 
@@ -1472,34 +1527,51 @@ cs_etm__get_trace(struct cs_etm_queue *etmq)
 	return etmq->buf_len;
 }
 
-static void cs_etm__set_thread(struct cs_etm_queue *etmq,
-			       struct cs_etm_traceid_queue *tidq, pid_t tid,
-			       ocsd_ex_level el)
+/*
+ * Convert a raw thread number to a thread struct and assign it to **thread.
+ */
+static int cs_etm__etmq_update_thread(struct cs_etm_queue *etmq,
+				      ocsd_ex_level el, pid_t tid,
+				      struct thread **thread)
 {
 	struct machine *machine = cs_etm__get_machine(etmq, el);
 
+	if (!machine || !*thread)
+		return -EINVAL;
+
 	if (tid != -1) {
-		thread__zput(tidq->thread);
-		tidq->thread = machine__find_thread(machine, -1, tid);
+		thread__zput(*thread);
+		*thread = machine__find_thread(machine, -1, tid);
 	}
 
 	/* Couldn't find a known thread */
-	if (!tidq->thread)
-		tidq->thread = machine__idle_thread(machine);
+	if (!*thread)
+		*thread = machine__idle_thread(machine);
 
-	tidq->el = el;
+	return 0;
 }
 
-int cs_etm__etmq_set_tid_el(struct cs_etm_queue *etmq, pid_t tid,
-			    u8 trace_chan_id, ocsd_ex_level el)
+/*
+ * Set the thread and EL of the decode context which is ahead in time of the
+ * frontend context.
+ */
+int cs_etm__etmq_update_decode_context(struct cs_etm_queue *etmq,
+				       u8 trace_chan_id,
+				       ocsd_ex_level el, pid_t tid)
 {
 	struct cs_etm_traceid_queue *tidq;
+	int ret;
 
 	tidq = cs_etm__etmq_get_traceid_queue(etmq, trace_chan_id);
 	if (!tidq)
 		return -EINVAL;
 
-	cs_etm__set_thread(etmq, tidq, tid, el);
+	ret = cs_etm__etmq_update_thread(etmq, el, tid,
+					 &tidq->decode_thread);
+	if (ret)
+		return ret;
+
+	tidq->decode_el = el;
 	return 0;
 }
 
@@ -1509,8 +1581,8 @@ bool cs_etm__etmq_is_timeless(struct cs_etm_queue *etmq)
 }
 
 static void cs_etm__copy_insn(struct cs_etm_queue *etmq,
-			      u64 trace_chan_id,
-			      const struct cs_etm_packet *packet,
+			      struct cs_etm_traceid_queue *tidq,
+			      struct cs_etm_packet *packet,
 			      struct perf_sample *sample)
 {
 	/*
@@ -1527,14 +1599,14 @@ static void cs_etm__copy_insn(struct cs_etm_queue *etmq,
 	 * cs_etm__t32_instr_size().
 	 */
 	if (packet->isa == CS_ETM_ISA_T32)
-		sample->insn_len = cs_etm__t32_instr_size(etmq, trace_chan_id,
+		sample->insn_len = cs_etm__t32_instr_size(etmq, tidq, packet,
 							  sample->ip);
 	/* Otherwise, A64 and A32 instruction size are always 32-bit. */
 	else
 		sample->insn_len = 4;
 
-	cs_etm__mem_access(etmq, trace_chan_id, sample->ip, sample->insn_len,
-			   (void *)sample->insn, 0);
+	cs_etm__frontend_mem_access(etmq, tidq, packet, sample->ip,
+				    sample->insn_len, (void *)sample->insn);
 }
 
 u64 cs_etm__convert_sample_time(struct cs_etm_queue *etmq, u64 cs_timestamp)
@@ -1561,6 +1633,7 @@ static inline u64 cs_etm__resolve_sample_time(struct cs_etm_queue *etmq,
 
 static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 					    struct cs_etm_traceid_queue *tidq,
+					    struct cs_etm_packet *packet,
 					    u64 addr, u64 period)
 {
 	int ret = 0;
@@ -1570,29 +1643,29 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 
 	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.misc = cs_etm__cpu_mode(etmq, addr, packet->el);
 	event->sample.header.size = sizeof(struct perf_event_header);
 
 	/* Set time field based on etm auxtrace config. */
 	sample.time = cs_etm__resolve_sample_time(etmq, tidq);
 
 	sample.ip = addr;
-	sample.pid = thread__pid(tidq->thread);
-	sample.tid = thread__tid(tidq->thread);
+	sample.pid = thread__pid(tidq->frontend_thread);
+	sample.tid = thread__tid(tidq->frontend_thread);
 	sample.id = etmq->etm->instructions_id;
 	sample.stream_id = etmq->etm->instructions_id;
 	sample.period = period;
-	sample.cpu = tidq->packet->cpu;
+	sample.cpu = packet->cpu;
 	sample.flags = tidq->prev_packet->flags;
 	sample.cpumode = event->sample.header.misc;
 
-	cs_etm__copy_insn(etmq, tidq->trace_chan_id, tidq->packet, &sample);
+	cs_etm__copy_insn(etmq, tidq, packet, &sample);
 
 	if (etm->synth_opts.last_branch)
 		sample.branch_stack = tidq->last_branch;
 
 	if (etm->synth_opts.inject) {
-		ret = cs_etm__inject_event(event, &sample,
+		ret = cs_etm__inject_event(etm, event, &sample,
 					   etm->instructions_sample_type);
 		if (ret)
 			return ret;
@@ -1631,15 +1704,15 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq,
 
 	event->sample.header.type = PERF_RECORD_SAMPLE;
 	event->sample.header.misc = cs_etm__cpu_mode(etmq, ip,
-						     tidq->prev_packet_el);
+						     tidq->prev_packet->el);
 	event->sample.header.size = sizeof(struct perf_event_header);
 
 	/* Set time field based on etm auxtrace config. */
 	sample.time = cs_etm__resolve_sample_time(etmq, tidq);
 
 	sample.ip = ip;
-	sample.pid = thread__pid(tidq->prev_packet_thread);
-	sample.tid = thread__tid(tidq->prev_packet_thread);
+	sample.pid = thread__pid(tidq->frontend_thread);
+	sample.tid = thread__tid(tidq->frontend_thread);
 	sample.addr = cs_etm__first_executed_instr(tidq->packet);
 	sample.id = etmq->etm->branches_id;
 	sample.stream_id = etmq->etm->branches_id;
@@ -1648,8 +1721,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq,
 	sample.flags = tidq->prev_packet->flags;
 	sample.cpumode = event->sample.header.misc;
 
-	cs_etm__copy_insn(etmq, tidq->trace_chan_id, tidq->prev_packet,
-			  &sample);
+	cs_etm__copy_insn(etmq, tidq, tidq->prev_packet, &sample);
 
 	/*
 	 * perf report cannot handle events without a branch stack
@@ -1667,7 +1739,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq,
 	}
 
 	if (etm->synth_opts.inject) {
-		ret = cs_etm__inject_event(event, &sample,
+		ret = cs_etm__inject_event(etm, event, &sample,
 					   etm->branches_sample_type);
 		if (ret)
 			return ret;
@@ -1770,7 +1842,6 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
 {
 	struct cs_etm_auxtrace *etm = etmq->etm;
 	int ret;
-	u8 trace_chan_id = tidq->trace_chan_id;
 	u64 instrs_prev;
 
 	/* Get instructions remainder from previous packet */
@@ -1856,10 +1927,10 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
 			 * been executed, but PC has not advanced to next
 			 * instruction)
 			 */
-			addr = cs_etm__instr_addr(etmq, trace_chan_id,
-						  tidq->packet, offset - 1);
+			addr = cs_etm__instr_addr(etmq, tidq, tidq->packet,
+						  offset - 1);
 			ret = cs_etm__synth_instruction_sample(
-				etmq, tidq, addr,
+				etmq, tidq, tidq->packet, addr,
 				etm->instructions_sample_period);
 			if (ret)
 				return ret;
@@ -1941,7 +2012,7 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
 		addr = cs_etm__last_executed_instr(tidq->prev_packet);
 
 		err = cs_etm__synth_instruction_sample(
-			etmq, tidq, addr,
+			etmq, tidq, tidq->prev_packet, addr,
 			tidq->period_instructions);
 		if (err)
 			return err;
@@ -1996,7 +2067,7 @@ static int cs_etm__end_block(struct cs_etm_queue *etmq,
 		addr = cs_etm__last_executed_instr(tidq->prev_packet);
 
 		err = cs_etm__synth_instruction_sample(
-			etmq, tidq, addr,
+			etmq, tidq, tidq->prev_packet, addr,
 			tidq->period_instructions);
 		if (err)
 			return err;
@@ -2033,9 +2104,9 @@ static int cs_etm__get_data_block(struct cs_etm_queue *etmq)
 	return etmq->buf_len;
 }
 
-static bool cs_etm__is_svc_instr(struct cs_etm_queue *etmq, u8 trace_chan_id,
-				 struct cs_etm_packet *packet,
-				 u64 end_addr)
+static bool cs_etm__is_svc_instr(struct cs_etm_queue *etmq,
+				 struct cs_etm_traceid_queue *tidq,
+				 struct cs_etm_packet *packet, u64 end_addr)
 {
 	/* Initialise to keep compiler happy */
 	u16 instr16 = 0;
@@ -2057,8 +2128,8 @@ static bool cs_etm__is_svc_instr(struct cs_etm_queue *etmq, u8 trace_chan_id,
 		 * so below only read 2 bytes as instruction size for T32.
 		 */
 		addr = end_addr - 2;
-		cs_etm__mem_access(etmq, trace_chan_id, addr, sizeof(instr16),
-				   (u8 *)&instr16, 0);
+		cs_etm__frontend_mem_access(etmq, tidq, packet, addr,
+					    sizeof(instr16), (u8 *)&instr16);
 		if ((instr16 & 0xFF00) == 0xDF00)
 			return true;
 
@@ -2073,8 +2144,8 @@ static bool cs_etm__is_svc_instr(struct cs_etm_queue *etmq, u8 trace_chan_id,
 		 * +---------+---------+-------------------------+
 		 */
 		addr = end_addr - 4;
-		cs_etm__mem_access(etmq, trace_chan_id, addr, sizeof(instr32),
-				   (u8 *)&instr32, 0);
+		cs_etm__frontend_mem_access(etmq, tidq, packet, addr,
+					    sizeof(instr32), (u8 *)&instr32);
 		if ((instr32 & 0x0F000000) == 0x0F000000 &&
 		    (instr32 & 0xF0000000) != 0xF0000000)
 			return true;
@@ -2090,8 +2161,8 @@ static bool cs_etm__is_svc_instr(struct cs_etm_queue *etmq, u8 trace_chan_id,
 		 * +-----------------------+---------+-----------+
 		 */
 		addr = end_addr - 4;
-		cs_etm__mem_access(etmq, trace_chan_id, addr, sizeof(instr32),
-				   (u8 *)&instr32, 0);
+		cs_etm__frontend_mem_access(etmq, tidq, packet, addr,
+					    sizeof(instr32), (u8 *)&instr32);
 		if ((instr32 & 0xFFE0001F) == 0xd4000001)
 			return true;
 
@@ -2107,7 +2178,6 @@ static bool cs_etm__is_svc_instr(struct cs_etm_queue *etmq, u8 trace_chan_id,
 static bool cs_etm__is_syscall(struct cs_etm_queue *etmq,
 			       struct cs_etm_traceid_queue *tidq, u64 magic)
 {
-	u8 trace_chan_id = tidq->trace_chan_id;
 	struct cs_etm_packet *packet = tidq->packet;
 	struct cs_etm_packet *prev_packet = tidq->prev_packet;
 
@@ -2122,7 +2192,7 @@ static bool cs_etm__is_syscall(struct cs_etm_queue *etmq,
 	 */
 	if (magic == __perf_cs_etmv4_magic) {
 		if (packet->exception_number == CS_ETMV4_EXC_CALL &&
-		    cs_etm__is_svc_instr(etmq, trace_chan_id, prev_packet,
+		    cs_etm__is_svc_instr(etmq, tidq, prev_packet,
 					 prev_packet->end_addr))
 			return true;
 	}
@@ -2160,7 +2230,6 @@ static bool cs_etm__is_sync_exception(struct cs_etm_queue *etmq,
 				      struct cs_etm_traceid_queue *tidq,
 				      u64 magic)
 {
-	u8 trace_chan_id = tidq->trace_chan_id;
 	struct cs_etm_packet *packet = tidq->packet;
 	struct cs_etm_packet *prev_packet = tidq->prev_packet;
 
@@ -2186,7 +2255,7 @@ static bool cs_etm__is_sync_exception(struct cs_etm_queue *etmq,
 		 * (SMC, HVC) are taken as sync exceptions.
 		 */
 		if (packet->exception_number == CS_ETMV4_EXC_CALL &&
-		    !cs_etm__is_svc_instr(etmq, trace_chan_id, prev_packet,
+		    !cs_etm__is_svc_instr(etmq, tidq, prev_packet,
 					  prev_packet->end_addr))
 			return true;
 
@@ -2210,7 +2279,6 @@ static int cs_etm__set_sample_flags(struct cs_etm_queue *etmq,
 {
 	struct cs_etm_packet *packet = tidq->packet;
 	struct cs_etm_packet *prev_packet = tidq->prev_packet;
-	u8 trace_chan_id = tidq->trace_chan_id;
 	u64 magic;
 	int ret;
 
@@ -2291,11 +2359,11 @@ static int cs_etm__set_sample_flags(struct cs_etm_queue *etmq,
 		if (prev_packet->flags == (PERF_IP_FLAG_BRANCH |
 					   PERF_IP_FLAG_RETURN |
 					   PERF_IP_FLAG_INTERRUPT) &&
-		    cs_etm__is_svc_instr(etmq, trace_chan_id,
-					 packet, packet->start_addr))
+		    cs_etm__is_svc_instr(etmq, tidq, packet, packet->start_addr)) {
 			prev_packet->flags = PERF_IP_FLAG_BRANCH |
 					     PERF_IP_FLAG_RETURN |
 					     PERF_IP_FLAG_SYSCALLRET;
+		}
 		break;
 	case CS_ETM_DISCONTINUITY:
 		/*
@@ -2376,6 +2444,7 @@ static int cs_etm__set_sample_flags(struct cs_etm_queue *etmq,
 					     PERF_IP_FLAG_RETURN |
 					     PERF_IP_FLAG_INTERRUPT;
 		break;
+	case CS_ETM_CONTEXT:
 	case CS_ETM_EMPTY:
 	default:
 		break;
@@ -2451,6 +2520,19 @@ static int cs_etm__process_traceid_queue(struct cs_etm_queue *etmq,
 			 */
 			cs_etm__sample(etmq, tidq);
 			break;
+		case CS_ETM_CONTEXT:
+			/*
+			 * Update context but don't swap packet. Keep the
+			 * previous one for branch source address info, if
+			 * tracing the kernel the context packet will be emitted
+			 * between two ranges.
+			 */
+			ret = cs_etm__etmq_update_thread(etmq, tidq->packet->el,
+							 tidq->packet->tid,
+							 &tidq->frontend_thread);
+			if (ret)
+				goto out;
+			break;
 		case CS_ETM_EXCEPTION:
 		case CS_ETM_EXCEPTION_RET:
 			/*
@@ -2479,6 +2561,7 @@ static int cs_etm__process_traceid_queue(struct cs_etm_queue *etmq,
 		}
 	}
 
+out:
 	return ret;
 }
 
@@ -2602,7 +2685,7 @@ static int cs_etm__process_timeless_queues(struct cs_etm_auxtrace *etm,
 			if (!tidq)
 				continue;
 
-			if (tid == -1 || thread__tid(tidq->thread) == tid)
+			if (tid == -1 || thread__tid(tidq->frontend_thread) == tid)
 				cs_etm__run_per_thread_timeless_decoder(etmq);
 		} else
 			cs_etm__run_per_cpu_timeless_decoder(etmq);
@@ -3079,6 +3162,9 @@ static int cs_etm__queue_aux_fragment(struct perf_session *session, off_t file_o
 	    aux_offset + aux_size <= auxtrace_event->offset + auxtrace_event->size) {
 		struct cs_etm_queue *etmq = cs_etm__get_queue(etm, auxtrace_event->cpu);
 
+		if (!etmq)
+			return -EINVAL;
+
 		/*
 		 * If this AUX event was inside this buffer somewhere, create a new auxtrace event
 		 * based on the sizes of the aux event, and queue that fragment.
@@ -3310,7 +3396,7 @@ static int cs_etm__create_queue_decoders(struct cs_etm_queue *etmq)
 	 */
 	if (cs_etm_decoder__add_mem_access_cb(etmq->decoder,
 					      0x0L, ((u64) -1L),
-					      cs_etm__mem_access))
+					      cs_etm__decoder_mem_access))
 		goto out_free_decoder;
 
 	zfree(&t_params);
@@ -3366,6 +3452,18 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event,
 	/* First the global part */
 	ptr = (u64 *) auxtrace_info->priv;
 	num_cpu = ptr[CS_PMU_TYPE_CPUS] & 0xffffffff;
+
+	/*
+	 * Bound num_cpu by the event size: the global header consumes
+	 * CS_ETM_HEADER_SIZE bytes, and each CPU needs at least one u64
+	 * metadata entry after that.
+	 */
+	priv_size = total_size - event_header_size - INFO_HEADER_SIZE -
+		    CS_ETM_HEADER_SIZE;
+	if (num_cpu <= 0 || priv_size <= 0 ||
+	    num_cpu > priv_size / (int)sizeof(u64))
+		return -EINVAL;
+
 	metadata = zalloc(sizeof(*metadata) * num_cpu);
 	if (!metadata)
 		return -ENOMEM;
@@ -3404,7 +3502,13 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event,
 			goto err_free_metadata;
 		}
 
-		if ((int) metadata[j][CS_ETM_CPU] > max_cpu)
+		/* CPU id comes from perf.data and must fit max_cpu + 1 without overflow */
+		if (metadata[j][CS_ETM_CPU] >= INT_MAX) {
+			err = -EINVAL;
+			goto err_free_metadata;
+		}
+
+		if ((int)metadata[j][CS_ETM_CPU] > max_cpu)
 			max_cpu = metadata[j][CS_ETM_CPU];
 	}
 
diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h
index aa9bb4a32eca..b81099c2b301 100644
--- a/tools/perf/util/cs-etm.h
+++ b/tools/perf/util/cs-etm.h
@@ -158,6 +158,7 @@ enum cs_etm_sample_type {
 	CS_ETM_DISCONTINUITY,
 	CS_ETM_EXCEPTION,
 	CS_ETM_EXCEPTION_RET,
+	CS_ETM_CONTEXT,
 };
 
 enum cs_etm_isa {
@@ -184,6 +185,8 @@ struct cs_etm_packet {
 	u8 last_instr_size;
 	u8 trace_chan_id;
 	int cpu;
+	int el;
+	pid_t tid;
 };
 
 #define CS_ETM_PACKET_MAX_BUFFER 1024
@@ -259,8 +262,9 @@ enum cs_etm_pid_fmt {
 #include <opencsd/ocsd_if_types.h>
 int cs_etm__get_cpu(struct cs_etm_queue *etmq, u8 trace_chan_id, int *cpu);
 enum cs_etm_pid_fmt cs_etm__get_pid_fmt(struct cs_etm_queue *etmq);
-int cs_etm__etmq_set_tid_el(struct cs_etm_queue *etmq, pid_t tid,
-			    u8 trace_chan_id, ocsd_ex_level el);
+int cs_etm__etmq_update_decode_context(struct cs_etm_queue *etmq,
+				       u8 trace_chan_id, ocsd_ex_level el,
+				       pid_t tid);
 bool cs_etm__etmq_is_timeless(struct cs_etm_queue *etmq);
 void cs_etm__etmq_set_traceid_queue_timestamp(struct cs_etm_queue *etmq,
 					      u8 trace_chan_id);
diff --git a/tools/perf/util/data-convert-json.c b/tools/perf/util/data-convert-json.c
index d526c91312ed..6a8d00c80394 100644
--- a/tools/perf/util/data-convert-json.c
+++ b/tools/perf/util/data-convert-json.c
@@ -177,6 +177,7 @@ static int process_sample_event(const struct perf_tool *tool,
 
 	if (perf_time__ranges_skip_sample(c->ptime_range, c->range_num, sample->time)) {
 		++c->skipped;
+		addr_location__exit(&al);
 		return 0;
 	}
 
diff --git a/tools/perf/util/debuginfo.c b/tools/perf/util/debuginfo.c
index 0e35c13abd04..84a78b30ceac 100644
--- a/tools/perf/util/debuginfo.c
+++ b/tools/perf/util/debuginfo.c
@@ -42,6 +42,7 @@ static int debuginfo__init_offline_dwarf(struct debuginfo *dbg,
 {
 	GElf_Addr dummy;
 	int fd;
+	bool fd_consumed = false;
 
 	fd = open(path, O_RDONLY);
 	if (fd < 0)
@@ -55,6 +56,7 @@ static int debuginfo__init_offline_dwarf(struct debuginfo *dbg,
 	dbg->mod = dwfl_report_offline(dbg->dwfl, "", "", fd);
 	if (!dbg->mod)
 		goto error;
+	fd_consumed = true;
 
 	dbg->dbg = dwfl_module_getdwarf(dbg->mod, &dbg->bias);
 	if (!dbg->dbg)
@@ -62,13 +64,14 @@ static int debuginfo__init_offline_dwarf(struct debuginfo *dbg,
 
 	dwfl_module_build_id(dbg->mod, &dbg->build_id, &dummy);
 
-	dwfl_report_end(dbg->dwfl, NULL, NULL);
+	if (dwfl_report_end(dbg->dwfl, NULL, NULL) != 0)
+		goto error;
 
 	return 0;
 error:
 	if (dbg->dwfl)
 		dwfl_end(dbg->dwfl);
-	else
+	if (!fd_consumed)
 		close(fd);
 	memset(dbg, 0, sizeof(*dbg));
 
@@ -167,7 +170,7 @@ int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
 	/* Search the relocation related .text section */
 	for (i = 0; i < n; i++) {
 		p = dwfl_module_relocation_info(dbg->mod, i, &shndx);
-		if (strcmp(p, ".text") == 0) {
+		if (p && strcmp(p, ".text") == 0) {
 			/* OK, get the section header */
 			scn = elf_getscn(elf, shndx);
 			if (!scn)
diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c
index 59ba88e1f744..0a1a7e9cf3ef 100644
--- a/tools/perf/util/disasm.c
+++ b/tools/perf/util/disasm.c
@@ -1577,8 +1577,11 @@ int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 		if (dso__decompress_kmodule_path(dso, symfs_filename, tmp, sizeof(tmp)) < 0)
 			return -1;
 
-		decomp = true;
-		strcpy(symfs_filename, tmp);
+		/* empty pathname means file wasn't actually compressed */
+		if (tmp[0] != '\0') {
+			decomp = true;
+			strcpy(symfs_filename, tmp);
+		}
 	}
 
 	/*
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index b791e1b6b2cf..170637a9b8e0 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -343,10 +343,16 @@ int filename__decompress(const char *name, char *pathname,
 	 * To keep this transparent, we detect this and return the file
 	 * descriptor to the uncompressed file.
 	 */
-	if (!compressions[comp].is_compressed(name))
-		return open(name, O_RDONLY);
+	if (!compressions[comp].is_compressed(name)) {
+		fd = open(name, O_RDONLY | O_CLOEXEC);
+		if (fd < 0)
+			*err = errno;
+		if (pathname && len > 0)
+			pathname[0] = '\0';
+		return fd;
+	}
 
-	fd = mkstemp(tmpbuf);
+	fd = mkostemp(tmpbuf, O_CLOEXEC);
 	if (fd < 0) {
 		*err = errno;
 		return -1;
@@ -594,12 +600,28 @@ static char *dso__get_filename(struct dso *dso, const char *root_dir,
 		size_t len = sizeof(newpath);
 
 		if (dso__decompress_kmodule_path(dso, name, newpath, len) < 0) {
-			errno = *dso__load_errno(dso);
+			/*
+			 * Use a standard errno value, not the negative custom
+			 * DSO_LOAD_ERRNO stored in dso__load_errno(dso):
+			 * __open_dso() computes fd = -errno, so a negative
+			 * errno produces a positive fd that looks valid.
+			 */
+			errno = EIO;
 			goto out;
 		}
 
-		*decomp = true;
-		strcpy(name, newpath);
+		/* empty pathname means file wasn't actually compressed */
+		if (newpath[0] != '\0') {
+			char *tmp = strdup(newpath);
+
+			if (!tmp) {
+				unlink(newpath);
+				goto out;
+			}
+			free(name);
+			name = tmp;
+			*decomp = true;
+		}
 	}
 	return name;
 
@@ -864,6 +886,12 @@ static ssize_t bpf_read(struct dso *dso, u64 offset, char *data)
 		return -1;
 	}
 
+	/* jited_prog_insns is only valid if bpil_offs_to_addr() converted it */
+	if (!(node->info_linear->arrays & (1UL << PERF_BPIL_JITED_INSNS))) {
+		dso__data(dso)->status = DSO_DATA_STATUS_ERROR;
+		return -1;
+	}
+
 	len = node->info_linear->info.jited_prog_len;
 	buf = (u8 *)(uintptr_t)node->info_linear->info.jited_prog_insns;
 
@@ -1766,7 +1794,7 @@ void dso__read_running_kernel_build_id(struct dso *dso, struct machine *machine)
 
 	if (machine__is_default_guest(machine))
 		return;
-	sprintf(path, "%s/sys/kernel/notes", machine->root_dir);
+	snprintf(path, sizeof(path), "%s/sys/kernel/notes", machine->root_dir);
 	sysfs__read_build_id(path, &bid);
 	dso__set_build_id(dso, &bid);
 }
@@ -1904,7 +1932,7 @@ static const u8 *__dso__read_symbol(struct dso *dso, const char *symfs_filename,
 	int saved_errno;
 
 	nsinfo__mountns_enter(dso__nsinfo(dso), &nsc);
-	fd = open(symfs_filename, O_RDONLY);
+	fd = open(symfs_filename, O_RDONLY | O_CLOEXEC);
 	saved_errno = errno;
 	nsinfo__mountns_exit(&nsc);
 	if (fd < 0) {
@@ -1972,6 +2000,10 @@ const u8 *dso__read_symbol(struct dso *dso, const char *symfs_filename,
 			return NULL;
 		}
 		info_linear = info_node->info_linear;
+		if (!(info_linear->arrays & (1UL << PERF_BPIL_JITED_INSNS))) {
+			errno = SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF;
+			return NULL;
+		}
 		assert(len <= info_linear->info.jited_prog_len);
 		*out_buf_len = len;
 		return (const u8 *)(uintptr_t)(info_linear->info.jited_prog_insns);
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index 92db2fccc788..d7160f87ac7d 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -125,7 +125,8 @@ int cu_find_lineinfo(Dwarf_Die *cu_die, Dwarf_Addr addr,
 	    && die_entrypc(&die_mem, &faddr) == 0 &&
 	    faddr == addr) {
 		*fname = die_get_decl_file(&die_mem);
-		dwarf_decl_line(&die_mem, lineno);
+		if (dwarf_decl_line(&die_mem, lineno) != 0)
+			return -ENOENT;
 		goto out;
 	}
 
@@ -171,7 +172,6 @@ int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr,
 	}
 
 	return ret;
-
 }
 
 /**
@@ -460,7 +460,7 @@ int die_get_data_member_location(Dwarf_Die *mb_die, Dwarf_Word *offs)
 	size_t nexpr;
 	int ret;
 
-	if (dwarf_attr(mb_die, DW_AT_data_member_location, &attr) == NULL)
+	if (dwarf_attr_integrate(mb_die, DW_AT_data_member_location, &attr) == NULL)
 		return -ENOENT;
 
 	if (dwarf_formudata(&attr, offs) != 0) {
@@ -620,7 +620,7 @@ Dwarf_Die *die_find_tailfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
 	ad.addr = addr;
 	ad.die_mem = die_mem;
 	/* dwarf_getscopes can't find subprogram. */
-	if (!dwarf_getfuncs(cu_die, __die_search_func_tail_cb, &ad, 0))
+	if (dwarf_getfuncs(cu_die, __die_search_func_tail_cb, &ad, 0) <= 0)
 		return NULL;
 	else
 		return die_mem;
@@ -659,7 +659,7 @@ Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
 	ad.addr = addr;
 	ad.die_mem = die_mem;
 	/* dwarf_getscopes can't find subprogram. */
-	if (!dwarf_getfuncs(cu_die, __die_search_func_cb, &ad, 0))
+	if (dwarf_getfuncs(cu_die, __die_search_func_cb, &ad, 0) <= 0)
 		return NULL;
 	else
 		return die_mem;
@@ -796,8 +796,7 @@ static int __die_walk_instances_cb(Dwarf_Die *inst, void *data)
 
 	/* Ignore redundant instances */
 	if (dwarf_tag(inst) == DW_TAG_inlined_subroutine) {
-		dwarf_decl_line(origin, &tmp);
-		if (die_get_call_lineno(inst) == tmp) {
+		if (dwarf_decl_line(origin, &tmp) == 0 && die_get_call_lineno(inst) == tmp) {
 			tmp = die_get_decl_fileno(origin);
 			if (die_get_call_fileno(inst) == tmp)
 				return DIE_FIND_CB_CONTINUE;
@@ -951,11 +950,6 @@ int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback, void *data)
 		cu_die = dwarf_diecu(rt_die, &die_mem, NULL, NULL);
 		dwarf_decl_line(rt_die, &decl);
 		decf = die_get_decl_file(rt_die);
-		if (!decf) {
-			pr_debug2("Failed to get the declared file name of %s\n",
-				  dwarf_diename(rt_die));
-			return -EINVAL;
-		}
 	} else
 		cu_die = rt_die;
 	if (!cu_die) {
@@ -999,11 +993,12 @@ int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback, void *data)
 			if (die_find_inlinefunc(rt_die, addr, &die_mem)) {
 				/* Call-site check */
 				inf = die_get_call_file(&die_mem);
-				if ((inf && !strcmp(inf, decf)) &&
+				if ((inf == decf || (inf && decf && !strcmp(inf, decf))) &&
 				    die_get_call_lineno(&die_mem) == lineno)
 					goto found;
 
-				dwarf_decl_line(&die_mem, &inl);
+				if (dwarf_decl_line(&die_mem, &inl) != 0)
+					inl = 0;
 				if (inl != decl ||
 				    decf != die_get_decl_file(&die_mem))
 					continue;
@@ -1035,8 +1030,10 @@ found:
 			.data = data,
 			.retval = 0,
 		};
-		dwarf_getfuncs(cu_die, __die_walk_culines_cb, &param, 0);
-		ret = param.retval;
+		if (dwarf_getfuncs(cu_die, __die_walk_culines_cb, &param, 0) < 0)
+			ret = -EINVAL;
+		else
+			ret = param.retval;
 	}
 
 	return ret;
@@ -1940,10 +1937,12 @@ static bool die_get_postprologue_addr(unsigned long entrypc_idx,
 			break;
 	}
 
-	dwarf_lineaddr(line, postprologue_addr);
-	if (*postprologue_addr >= highpc)
-		dwarf_lineaddr(dwarf_onesrcline(lines, i - 1),
-			       postprologue_addr);
+	if (dwarf_lineaddr(line, postprologue_addr) != 0)
+		return false;
+	if (*postprologue_addr >= highpc) {
+		if (dwarf_lineaddr(dwarf_onesrcline(lines, i - 1), postprologue_addr) != 0)
+			return false;
+	}
 
 	return true;
 }
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index a79968a2e573..161f0bf980b6 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -10,6 +10,11 @@
 #include <elfutils/libdwfl.h>
 #include <elfutils/version.h>
 
+static inline const char *die_name(Dwarf_Die *die)
+{
+	return dwarf_diename(die) ?: "<unknown>";
+}
+
 struct strbuf;
 
 /* Find the realpath of the target file */
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index c7052ac1f856..25ba16290280 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -185,6 +185,20 @@ const char *perf_env__pmu_mappings(struct perf_env *env);
 
 int perf_env__read_cpu_topology_map(struct perf_env *env);
 
+/*
+ * Safe accessor for env->cpu[] topology array.  env->cpu can be NULL when
+ * reading old-format perf.data that predates topology information —
+ * process_cpu_topology() in header.c frees it while nr_cpus_avail remains
+ * set, so callers must not index env->cpu[] without this check.
+ */
+static inline struct cpu_topology_map *
+perf_env__get_cpu_topology(struct perf_env *env, struct perf_cpu cpu)
+{
+	if (env->cpu && cpu.cpu >= 0 && cpu.cpu < env->nr_cpus_avail)
+		return &env->cpu[cpu.cpu];
+	return NULL;
+}
+
 void cpu_cache_level__free(struct cpu_cache_level *cache);
 
 const char *perf_env__arch(struct perf_env *env);
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 66f4843bb235..ea75816d126a 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -14,6 +14,7 @@
 #include <linux/perf_event.h>
 #include "cpumap.h"
 #include "dso.h"
+#include "env.h"
 #include "event.h"
 #include "debug.h"
 #include "hist.h"
@@ -836,8 +837,18 @@ int machine__resolve(struct machine *machine, struct addr_location *al,
 	if (al->cpu >= 0) {
 		struct perf_env *env = machine->env;
 
-		if (env && env->cpu)
-			al->socket = env->cpu[al->cpu].socket_id;
+		/*
+		 * Bounds-check al->cpu (s32) before casting to struct perf_cpu
+		 * (int16_t): without this, e.g. 65536 truncates to 0 and silently
+		 * returns CPU 0's topology.  Can go once perf_cpu.cpu is widened.
+		 */
+		if (env && al->cpu < env->nr_cpus_avail) {
+			struct cpu_topology_map *topo;
+
+			topo = perf_env__get_cpu_topology(env, (struct perf_cpu){ al->cpu });
+			if (topo)
+				al->socket = topo->socket_id;
+		}
 	}
 
 	/* Account for possible out-of-order switch events. */
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index f30e48eb3fc3..7bea1c41ced7 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -158,15 +158,25 @@ int do_write(struct feat_fd *ff, const void *buf, size_t size)
 /* Return: 0 if succeeded, -ERR if failed. */
 static int do_write_bitmap(struct feat_fd *ff, unsigned long *set, u64 size)
 {
-	u64 *p = (u64 *) set;
+	size_t byte_size = BITS_TO_LONGS(size) * sizeof(unsigned long);
 	int i, ret;
 
 	ret = do_write(ff, &size, sizeof(size));
 	if (ret < 0)
 		return ret;
 
+	/*
+	 * The on-disk format uses u64 elements, but the in-memory bitmap
+	 * uses unsigned long, which is only 4 bytes on 32-bit architectures.
+	 * Copy with bounded size so the last element doesn't read past the
+	 * bitmap allocation when BITS_TO_LONGS(size) is odd.
+	 */
 	for (i = 0; (u64) i < BITS_TO_U64(size); i++) {
-		ret = do_write(ff, p + i, sizeof(*p));
+		u64 val = 0;
+		size_t off = i * sizeof(val);
+
+		memcpy(&val, (char *)set + off, min(sizeof(val), byte_size - off));
+		ret = do_write(ff, &val, sizeof(val));
 		if (ret < 0)
 			return ret;
 	}
@@ -297,7 +307,20 @@ static int do_read_bitmap(struct feat_fd *ff, unsigned long **pset, u64 *psize)
 	if (ret)
 		return ret;
 
-	set = bitmap_zalloc(size);
+	/* Bitmap APIs use int for nbits; reject u64 values that truncate. */
+	if (size > INT_MAX ||
+	    BITS_TO_U64(size) > (ff->size - ff->offset) / sizeof(u64)) {
+		pr_debug("do_read_bitmap: size %" PRIu64 " exceeds section bounds\n", size);
+		return -1;
+	}
+
+	/*
+	 * bitmap_zalloc() allocates in unsigned long units, which are only
+	 * 4 bytes on 32-bit architectures. The read loop below casts the
+	 * buffer to u64 * and writes 8-byte elements, so allocate in u64
+	 * units to ensure the buffer is large enough.
+	 */
+	set = calloc(BITS_TO_U64(size), sizeof(u64));
 	if (!set)
 		return -ENOMEM;
 
@@ -2035,8 +2058,7 @@ static void print_bpf_prog_info(struct feat_fd *ff __maybe_unused, FILE *fp)
 		node = rb_entry(next, struct bpf_prog_info_node, rb_node);
 		next = rb_next(&node->rb_node);
 
-		__bpf_event__print_bpf_prog_info(&node->info_linear->info,
-						 env, fp);
+		__bpf_event__print_bpf_prog_info(node->info_linear, env, fp);
 	}
 
 	up_read(&env->bpf_progs.lock);
@@ -2135,9 +2157,28 @@ static struct evsel *read_event_desc(struct feat_fd *ff)
 	if (do_read_u32(ff, &nre))
 		goto error;
 
+	/* Size of each of the nre attributes. */
 	if (do_read_u32(ff, &sz))
 		goto error;
 
+	/*
+	 * Require at least one event with an attr no smaller than the
+	 * first published struct, and reject sz values where
+	 * sz + sizeof(u32) would overflow size_t (possible on 32-bit)
+	 * or nre == UINT32_MAX where nre + 1 wraps to 0 in the calloc.
+	 *
+	 * The minimum section footprint per event is sz bytes for the
+	 * attr plus a u32 for the id count, check that nre events fit.
+	 */
+	if (!nre || sz < PERF_ATTR_SIZE_VER0 ||
+	    sz > ff->size || (size_t)sz > SIZE_MAX - sizeof(u32) ||
+	    nre == UINT32_MAX ||
+	    nre > (ff->size - ff->offset) / (sz + sizeof(u32))) {
+		pr_err("Invalid HEADER_EVENT_DESC: nre=%u sz=%u (min %d)\n",
+		       nre, sz, PERF_ATTR_SIZE_VER0);
+		goto error;
+	}
+
 	/* buffer to hold on file attr struct */
 	buf = malloc(sz);
 	if (!buf)
@@ -2153,6 +2194,9 @@ static struct evsel *read_event_desc(struct feat_fd *ff)
 		msz = sz;
 
 	for (i = 0, evsel = events; i < nre; evsel++, i++) {
+		struct perf_event_attr *attr = buf;
+		u32 attr_size;
+
 		evsel->core.idx = i;
 
 		/*
@@ -2162,6 +2206,32 @@ static struct evsel *read_event_desc(struct feat_fd *ff)
 		if (__do_read(ff, buf, sz))
 			goto error;
 
+		/* Reject before attr_swap to prevent OOB via bswap_safe() */
+		attr_size = ff->ph->needs_swap ? bswap_32(attr->size) : attr->size;
+		/* ABI0: size == 0 means the producer didn't set it */
+		if (!attr_size) {
+			attr_size = PERF_ATTR_SIZE_VER0;
+			/*
+			 * Write back so free_event_desc() doesn't
+			 * treat this event as the end-of-array sentinel
+			 * (it iterates while attr.size != 0).
+			 *
+			 * Only for native — the swap path must NOT
+			 * write native-endian VER0 here because
+			 * perf_event__attr_swap() would re-swap it
+			 * to 0x40000000, defeating bswap_safe() bounds.
+			 * perf_event__attr_swap() has its own ABI0
+			 * fallback that sets VER0 after swapping.
+			 */
+			if (!ff->ph->needs_swap)
+				attr->size = attr_size;
+		}
+		if (attr_size < PERF_ATTR_SIZE_VER0 || attr_size > sz) {
+			pr_err("Event %d attr.size (%u) invalid (min: %d, max: %u)\n",
+			       i, attr_size, PERF_ATTR_SIZE_VER0, sz);
+			goto error;
+		}
+
 		if (ff->ph->needs_swap)
 			perf_event__attr_swap(buf);
 
@@ -2183,6 +2253,12 @@ static struct evsel *read_event_desc(struct feat_fd *ff)
 		if (!nr)
 			continue;
 
+		/* Prevent oversized allocation from crafted nr */
+		if (nr > (ff->size - ff->offset) / sizeof(*id)) {
+			pr_err("Event %d: id count %u exceeds remaining section\n", i, nr);
+			goto error;
+		}
+
 		id = calloc(nr, sizeof(*id));
 		if (!id)
 			goto error;
@@ -3357,7 +3433,8 @@ static int process_mem_topology(struct feat_fd *ff,
 		return -1;
 	}
 
-	if (ff->size < 3 * sizeof(u64) + nr * 2 * sizeof(u64)) {
+	/* Per node: node_id(u64) + mem_size(u64) + bitmap_nr_bits(u64) */
+	if (ff->size < 3 * sizeof(u64) + nr * 3 * sizeof(u64)) {
 		pr_err("Invalid HEADER_MEM_TOPOLOGY: section too small (%zu) for %llu nodes\n",
 		       ff->size, (unsigned long long)nr);
 		return -1;
@@ -3392,7 +3469,7 @@ static int process_mem_topology(struct feat_fd *ff,
 
 out:
 	if (ret)
-		free(nodes);
+		memory_node__delete_nodes(nodes, nr);
 	return ret;
 }
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 747fdc455c80..aca9ff15518a 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -2963,9 +2963,10 @@ int __hists__scnprintf_title(struct hists *hists, char *bf, size_t size, bool sh
 			   ev_name, sample_freq_str, enable_ref ? ref : " ", nr_events);
 
 
-	if (hists->uid_filter_str)
-		printed += snprintf(bf + printed, size - printed,
-				    ", UID: %s", hists->uid_filter_str);
+	if (hists->uid_filter_str) {
+		printed += scnprintf(bf + printed, size - printed,
+				     ", UID: %s", hists->uid_filter_str);
+	}
 	if (thread) {
 		if (hists__has(hists, thread)) {
 			printed += scnprintf(bf + printed, size - printed,
@@ -3040,7 +3041,7 @@ static void hists__delete_remaining_entries(struct rb_root_cached *root)
 	}
 }
 
-static void hists__delete_all_entries(struct hists *hists)
+void hists__delete_all_entries(struct hists *hists)
 {
 	hists__delete_entries(hists);
 	hists__delete_remaining_entries(&hists->entries_in_array[0]);
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index d97a4efb9250..3a59200d2517 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -392,6 +392,7 @@ int hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
 
 void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel);
 void hists__delete_entries(struct hists *hists);
+void hists__delete_all_entries(struct hists *hists);
 void hists__output_recalc_col_len(struct hists *hists, int max_rows);
 
 struct hist_entry *hists__get_entry(struct hists *hists, int idx);
diff --git a/tools/perf/util/hwmon_pmu.c b/tools/perf/util/hwmon_pmu.c
index fb3ffa8d32ad..ed544dca70c3 100644
--- a/tools/perf/util/hwmon_pmu.c
+++ b/tools/perf/util/hwmon_pmu.c
@@ -202,7 +202,8 @@ bool parse_hwmon_filename(const char *filename,
 	fn_item_len = strlen(fn_item);
 	if (fn_item_len > 6 && !strcmp(&fn_item[fn_item_len - 6], "_alarm")) {
 		assert(strlen(LONGEST_HWMON_ITEM_STR) < sizeof(fn_type));
-		strlcpy(fn_type, fn_item, fn_item_len - 5);
+		/* fn_item_len - 5 strips "_alarm"; clamp to buffer size */
+		strlcpy(fn_type, fn_item, min_t(size_t, fn_item_len - 5, sizeof(fn_type)));
 		fn_item = fn_type;
 		*alarm = true;
 	}
@@ -289,13 +290,16 @@ static int hwmon_pmu__read_events(struct hwmon_pmu *pmu)
 			if (fd < 0)
 				continue;
 
-			read_len = read(fd, buf, sizeof(buf));
+			read_len = read(fd, buf, sizeof(buf) - 1);
 
 			while (read_len > 0 && buf[read_len - 1] == '\n')
 				read_len--;
 
-			if (read_len > 0)
-				buf[read_len] = '\0';
+			if (read_len <= 0) {
+				close(fd);
+				continue;
+			}
+			buf[read_len] = '\0';
 
 			if (buf[0] == '\0') {
 				pr_debug("hwmon_pmu: empty label file %s %s\n",
@@ -431,8 +435,8 @@ static size_t hwmon_pmu__describe_items(struct hwmon_pmu *hwm, char *out_buf, si
 			hwmon_item_strs[bit],
 			is_alarm ? "_alarm" : "");
 		fd = openat(dir, buf, O_RDONLY);
-		if (fd > 0) {
-			ssize_t read_len = read(fd, buf, sizeof(buf));
+		if (fd >= 0) {
+			ssize_t read_len = read(fd, buf, sizeof(buf) - 1);
 
 			while (read_len > 0 && buf[read_len - 1] == '\n')
 				read_len--;
@@ -442,12 +446,12 @@ static size_t hwmon_pmu__describe_items(struct hwmon_pmu *hwm, char *out_buf, si
 
 				buf[read_len] = '\0';
 				val = strtoll(buf, /*endptr=*/NULL, 10);
-				len += snprintf(out_buf + len, out_buf_len - len, "%s%s%s=%g%s",
-						len == 0 ? " " : ", ",
-						hwmon_item_strs[bit],
-						is_alarm ? "_alarm" : "",
-						(double)val / 1000.0,
-						hwmon_units[key.type]);
+				len += scnprintf(out_buf + len, out_buf_len - len, "%s%s%s=%g%s",
+						 len == 0 ? " " : ", ",
+						 hwmon_item_strs[bit],
+						 is_alarm ? "_alarm" : "",
+						 (double)val / 1000.0,
+						 hwmon_units[key.type]);
 			}
 			close(fd);
 		}
@@ -514,14 +518,14 @@ int hwmon_pmu__for_each_event(struct perf_pmu *pmu, void *state, pmu_event_callb
 		int ret;
 		size_t len;
 
-		len = snprintf(alias_buf, sizeof(alias_buf), "%s%d",
-			       hwmon_type_strs[key.type], key.num);
+		scnprintf(alias_buf, sizeof(alias_buf), "%s%d",
+			  hwmon_type_strs[key.type], key.num);
 		if (!info.name) {
 			info.name = info.alias;
 			info.alias = NULL;
 		}
 
-		len = snprintf(desc_buf, sizeof(desc_buf), "%s in unit %s named %s.",
+		len = scnprintf(desc_buf, sizeof(desc_buf), "%s in unit %s named %s.",
 			hwmon_desc[key.type],
 			pmu->name + 6,
 			value->label ?: info.name);
@@ -816,7 +820,7 @@ int evsel__hwmon_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread)
 
 	count = perf_counts(evsel->counts, cpu_map_idx, thread);
 	fd = FD(evsel, cpu_map_idx, thread);
-	len = pread(fd, buf, sizeof(buf), 0);
+	len = pread(fd, buf, sizeof(buf) - 1, 0);
 	if (len <= 0) {
 		count->lost++;
 		return -EINVAL;
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 382255393fb3..0b18ebd13f7c 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -303,7 +303,8 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
 		event.sample.header.size = bts->branches_event_size;
 		ret = perf_event__synthesize_sample(&event,
 						    bts->branches_sample_type,
-						    0, &sample);
+						    /*read_format=*/0, /*branch_sample_type=*/0,
+						    &sample);
 		if (ret)
 			return ret;
 	}
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
index 72c7a4e15d61..f90fcbc4302d 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
@@ -220,7 +220,6 @@ const char *dump_insn(struct perf_insn *x, uint64_t ip __maybe_unused,
 {
 	struct insn insn;
 	int n, i, ret;
-	int left;
 
 	ret = insn_decode(&insn, inbuf, inlen,
 			  x->is64bit ? INSN_MODE_64 : INSN_MODE_32);
@@ -229,13 +228,9 @@ const char *dump_insn(struct perf_insn *x, uint64_t ip __maybe_unused,
 		return "<bad>";
 	if (lenp)
 		*lenp = insn.length;
-	left = sizeof(x->out);
-	n = snprintf(x->out, left, "insn: ");
-	left -= n;
-	for (i = 0; i < insn.length; i++) {
-		n += snprintf(x->out + n, left, "%02x ", inbuf[i]);
-		left -= n;
-	}
+	n = scnprintf(x->out, sizeof(x->out), "insn: ");
+	for (i = 0; i < insn.length; i++)
+		n += scnprintf(x->out + n, sizeof(x->out) - n, "%02x ", inbuf[i]);
 	return x->out;
 }
 
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index fc9eec8b54b8..d9c86ac49748 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -1307,7 +1307,8 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 			goto out_free;
 	}
 
-	if (pt->synth_opts.last_branch || pt->synth_opts.other_events) {
+	if (pt->synth_opts.last_branch || pt->synth_opts.add_last_branch ||
+	    pt->synth_opts.other_events) {
 		unsigned int entry_cnt = max(LBRS_MAX, pt->br_stack_sz);
 
 		ptq->last_branch = intel_pt_alloc_br_stack(entry_cnt);
@@ -1728,11 +1729,30 @@ static void intel_pt_prep_b_sample(struct intel_pt *pt,
 	event->sample.header.misc = sample->cpumode;
 }
 
-static int intel_pt_inject_event(union perf_event *event,
+static int intel_pt_inject_event(struct intel_pt *pt, union perf_event *event,
 				 struct perf_sample *sample, u64 type)
 {
-	event->header.size = perf_event__sample_event_size(sample, type, 0);
-	return perf_event__synthesize_sample(event, type, 0, sample);
+	struct evsel *evsel = sample->evsel;
+	u64 branch_sample_type = 0;
+	size_t sz;
+
+	if (!evsel && pt->session && pt->session->evlist)
+		evsel = evlist__id2evsel(pt->session->evlist, sample->id);
+
+	if (evsel)
+		branch_sample_type = evsel->core.attr.branch_sample_type;
+
+	event->header.type = PERF_RECORD_SAMPLE;
+	sz = perf_event__sample_event_size(sample, type, /*read_format=*/0,
+					   branch_sample_type);
+	if (sz >= PERF_SAMPLE_MAX_SIZE) {
+		pr_err("Sample size %zu exceeds max size %d\n", sz, PERF_SAMPLE_MAX_SIZE);
+		return -EFAULT;
+	}
+	event->header.size = sz;
+
+	return perf_event__synthesize_sample(event, type, /*read_format=*/0,
+					     branch_sample_type, sample);
 }
 
 static inline int intel_pt_opt_inject(struct intel_pt *pt,
@@ -1742,7 +1762,7 @@ static inline int intel_pt_opt_inject(struct intel_pt *pt,
 	if (!pt->synth_opts.inject)
 		return 0;
 
-	return intel_pt_inject_event(event, sample, type);
+	return intel_pt_inject_event(pt, event, sample, type);
 }
 
 static int intel_pt_deliver_synth_event(struct intel_pt *pt,
@@ -2486,7 +2506,7 @@ static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evse
 		intel_pt_add_xmm(intr_regs, pos, items, regs_mask);
 	}
 
-	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
+	if ((sample_type | evsel->synth_sample_type) & PERF_SAMPLE_BRANCH_STACK) {
 		if (items->mask[INTEL_PT_LBR_0_POS] ||
 		    items->mask[INTEL_PT_LBR_1_POS] ||
 		    items->mask[INTEL_PT_LBR_2_POS]) {
@@ -2557,7 +2577,8 @@ static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evse
 		sample.transaction = txn;
 	}
 
-	ret = intel_pt_deliver_synth_event(pt, event, &sample, sample_type);
+	ret = intel_pt_deliver_synth_event(pt, event, &sample,
+					   sample_type | evsel->synth_sample_type);
 	perf_sample__exit(&sample);
 	return ret;
 }
diff --git a/tools/perf/util/libdw.c b/tools/perf/util/libdw.c
index 216977884103..15bf646d104f 100644
--- a/tools/perf/util/libdw.c
+++ b/tools/perf/util/libdw.c
@@ -60,7 +60,10 @@ struct Dwfl *dso__libdw_dwfl(struct dso *dso)
 		return NULL;
 	}
 
-	dwfl_report_end(dwfl, /*removed=*/NULL, /*arg=*/NULL);
+	if (dwfl_report_end(dwfl, /*removed=*/NULL, /*arg=*/NULL) != 0) {
+		dwfl_end(dwfl);
+		return NULL;
+	}
 	dso__set_libdw(dso, dwfl);
 
 	return dwfl;
@@ -72,18 +75,19 @@ struct libdw_a2l_cb_args {
 	struct inline_node *node;
 	char *leaf_srcline;
 	bool leaf_srcline_used;
+	int err;
 };
 
 static int libdw_a2l_cb(Dwarf_Die *die, void *_args)
 {
 	struct libdw_a2l_cb_args *args  = _args;
-	struct symbol *inline_sym = new_inline_sym(args->dso, args->sym, dwarf_diename(die));
+	struct symbol *inline_sym = new_inline_sym(args->dso, args->sym, die_name(die));
 	const char *call_fname = die_get_call_file(die);
 	char *call_srcline = srcline__unknown;
 	struct inline_list *ilist;
 
 	if (!inline_sym)
-		return -ENOMEM;
+		goto abort_enomem;
 
 	/* Assign caller information to the parent. */
 	if (call_fname)
@@ -103,12 +107,27 @@ static int libdw_a2l_cb(Dwarf_Die *die, void *_args)
 
 	/* Add this symbol to the chain as the leaf. */
 	if (!args->leaf_srcline_used) {
-		inline_list__append_tail(inline_sym, args->leaf_srcline, args->node);
+		if (inline_list__append_tail(inline_sym, args->leaf_srcline, args->node) != 0)
+			goto abort_delete_sym;
 		args->leaf_srcline_used = true;
 	} else {
-		inline_list__append_tail(inline_sym, strdup(args->leaf_srcline), args->node);
+		char *srcline = strdup(args->leaf_srcline);
+
+		if (!srcline)
+			goto abort_delete_sym;
+		if (inline_list__append_tail(inline_sym, srcline, args->node) != 0) {
+			free(srcline);
+			goto abort_delete_sym;
+		}
 	}
 	return 0;
+
+abort_delete_sym:
+	if (inline_sym->inlined)
+		symbol__delete(inline_sym);
+abort_enomem:
+	args->err = -ENOMEM;
+	return DWARF_CB_ABORT;
 }
 
 int libdw__addr2line(u64 addr, char **file, unsigned int *line_nr,
@@ -162,11 +181,29 @@ int libdw__addr2line(u64 addr, char **file, unsigned int *line_nr,
 			.leaf_srcline = srcline_from_fileline(src ?: "<unknown>", lineno),
 		};
 
+		if (!args.leaf_srcline) {
+			if (file && *file) {
+				free(*file);
+				*file = NULL;
+			}
+			return 0;
+		}
+
 		/* Walk from the parent down to the leaf. */
-		cu_walk_functions_at(cudie, addr, libdw_a2l_cb, &args);
+		if (cudie)
+			cu_walk_functions_at(cudie, addr, libdw_a2l_cb, &args);
 
 		if (!args.leaf_srcline_used)
 			free(args.leaf_srcline);
+
+		if (args.err) {
+			if (file && *file) {
+				free(*file);
+				*file = NULL;
+			}
+			inline_node__clear_frames(node);
+			return 0;
+		}
 	}
 	return 1;
 }
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index e76f8c86e62a..d48d96e4b37d 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -327,7 +327,7 @@ struct machine *machines__findnew(struct machines *machines, pid_t pid)
 	if ((pid != HOST_KERNEL_ID) &&
 	    (pid != DEFAULT_GUEST_KERNEL_ID) &&
 	    (symbol_conf.guestmount)) {
-		sprintf(path, "%s/%d", symbol_conf.guestmount, pid);
+		snprintf(path, sizeof(path), "%s/%d", symbol_conf.guestmount, pid);
 		if (access(path, R_OK)) {
 			static struct strlist *seen;
 
@@ -1239,9 +1239,9 @@ int machines__create_guest_kernel_maps(struct machines *machines)
 					 namelist[i]->d_name);
 				continue;
 			}
-			sprintf(path, "%s/%s/proc/kallsyms",
-				symbol_conf.guestmount,
-				namelist[i]->d_name);
+			snprintf(path, sizeof(path), "%s/%s/proc/kallsyms",
+				 symbol_conf.guestmount,
+				 namelist[i]->d_name);
 			ret = access(path, R_OK);
 			if (ret) {
 				pr_debug("Can't access file %s\n", path);
@@ -1319,7 +1319,7 @@ static char *get_kernel_version(const char *root_dir)
 	char *name, *tmp;
 	const char *prefix = "Linux version ";
 
-	sprintf(version, "%s/proc/version", root_dir);
+	snprintf(version, sizeof(version), "%s/proc/version", root_dir);
 	file = fopen(version, "r");
 	if (!file)
 		return NULL;
@@ -1522,22 +1522,30 @@ static void machine__set_kernel_mmap(struct machine *machine,
 		map__set_end(machine->vmlinux_map, ~0ULL);
 }
 
-static int machine__update_kernel_mmap(struct machine *machine,
-				     u64 start, u64 end)
+struct kernel_mmap_mutation_ctx {
+	u64 start;
+	u64 end;
+};
+
+static int kernel_mmap_mutate_cb(struct map *map, void *data)
 {
-	struct map *orig, *updated;
-	int err;
+	struct kernel_mmap_mutation_ctx *ctx = data;
 
-	orig = machine->vmlinux_map;
-	updated = map__get(orig);
+	map__set_start(map, ctx->start);
+	map__set_end(map, ctx->end);
+	if (ctx->start == 0 && ctx->end == 0)
+		map__set_end(map, ~0ULL);
+	return 0;
+}
 
-	machine->vmlinux_map = updated;
-	maps__remove(machine__kernel_maps(machine), orig);
-	machine__set_kernel_mmap(machine, start, end);
-	err = maps__insert(machine__kernel_maps(machine), updated);
-	map__put(orig);
+static int machine__update_kernel_mmap(struct machine *machine,
+				       u64 start, u64 end)
+{
+	struct kernel_mmap_mutation_ctx ctx = { .start = start, .end = end };
 
-	return err;
+	return maps__mutate_mapping(machine__kernel_maps(machine),
+				     machine->vmlinux_map,
+				     kernel_mmap_mutate_cb, &ctx);
 }
 
 int machine__create_kernel_maps(struct machine *machine)
diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c
index 81a97ac34077..6cdafded61bc 100644
--- a/tools/perf/util/maps.c
+++ b/tools/perf/util/maps.c
@@ -575,6 +575,48 @@ void maps__remove(struct maps *maps, struct map *map)
 #endif
 }
 
+/**
+ * maps__mutate_mapping - Apply write-protected mutations to a map.
+ * @maps: The maps collection containing the map.
+ * @map: The map to mutate.
+ * @mutate_cb: Callback function that performs the actual mutations.
+ * @data: Private data passed to the callback.
+ *
+ * This acquires the write lock on the maps semaphore to safely protect
+ * concurrent readers from seeing partially mutated or unsorted map boundaries.
+ *
+ * WARNING: Acquiring down_write() here can trigger a recursive self-deadlock if
+ * the caller already holds the read lock (e.g., during maps__for_each_map() or
+ * maps__find() iteration paths that trigger lazy symbol loading). To completely
+ * avoid this deadlock, all kernel/module maps must be pre-loaded up-front (via
+ * maps__load_maps()) under a clean, single-threaded context before entering
+ * multi-threaded event processing loops.
+ */
+int maps__mutate_mapping(struct maps *maps, struct map *map,
+			 int (*mutate_cb)(struct map *map, void *data), void *data)
+{
+	int err = 0;
+
+	if (maps) {
+		down_write(maps__lock(maps));
+
+		err = mutate_cb(map, data);
+
+		RC_CHK_ACCESS(maps)->maps_by_address_sorted = false;
+		RC_CHK_ACCESS(maps)->maps_by_name_sorted = false;
+
+		up_write(maps__lock(maps));
+
+#ifdef HAVE_LIBDW_SUPPORT
+		libdw__invalidate_dwfl(maps, maps__libdw_addr_space_dwfl(maps));
+#endif
+	} else {
+		err = mutate_cb(map, data);
+	}
+
+	return err;
+}
+
 bool maps__empty(struct maps *maps)
 {
 	bool res;
@@ -625,6 +667,41 @@ int maps__for_each_map(struct maps *maps, int (*cb)(struct map *map, void *data)
 	return ret;
 }
 
+int maps__load_maps(struct maps *maps)
+{
+	struct map **maps_copy;
+	unsigned int nr_maps;
+	int err = 0;
+
+	if (!maps)
+		return 0;
+
+	down_read(maps__lock(maps));
+	nr_maps = maps__nr_maps(maps);
+	if (nr_maps == 0) {
+		up_read(maps__lock(maps));
+		return 0;
+	}
+	maps_copy = calloc(nr_maps, sizeof(*maps_copy));
+	if (!maps_copy) {
+		up_read(maps__lock(maps));
+		return -ENOMEM;
+	}
+	for (unsigned int i = 0; i < nr_maps; i++)
+		maps_copy[i] = map__get(maps__maps_by_address(maps)[i]);
+	up_read(maps__lock(maps));
+
+	for (unsigned int i = 0; i < nr_maps; i++) {
+		if (map__load(maps_copy[i]) < 0) {
+			pr_warning("Failed to load map %s\n", dso__name(map__dso(maps_copy[i])));
+			err = -1;
+		}
+		map__put(maps_copy[i]);
+	}
+	free(maps_copy);
+	return err;
+}
+
 void maps__remove_maps(struct maps *maps, bool (*cb)(struct map *map, void *data), void *data)
 {
 	struct map **maps_by_address;
@@ -667,40 +744,57 @@ struct symbol *maps__find_symbol(struct maps *maps, u64 addr, struct map **mapp)
 	return result;
 }
 
-struct maps__find_symbol_by_name_args {
-	struct map **mapp;
-	const char *name;
-	struct symbol *sym;
-};
-
-static int maps__find_symbol_by_name_cb(struct map *map, void *data)
+struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp)
 {
-	struct maps__find_symbol_by_name_args *args = data;
+	struct map **maps_copy;
+	unsigned int nr_maps;
+	struct symbol *sym = NULL;
 
-	args->sym = map__find_symbol_by_name(map, args->name);
-	if (!args->sym)
-		return 0;
+	if (!maps)
+		return NULL;
 
-	if (!map__contains_symbol(map, args->sym)) {
-		args->sym = NULL;
-		return 0;
+	/*
+	 * First, ensure all maps are loaded. We pre-load them outside of any
+	 * read-to-write locks to avoid deadlocks. Even if some fail, we proceed.
+	 */
+	maps__load_maps(maps);
+
+	/*
+	 * Create a local snapshot of the maps while holding the read lock.
+	 * This prevents deadlocking if iteration triggers further map insertions.
+	 */
+	down_read(maps__lock(maps));
+	nr_maps = maps__nr_maps(maps);
+	maps_copy = calloc(nr_maps, sizeof(*maps_copy));
+	if (maps_copy) {
+		for (unsigned int i = 0; i < nr_maps; i++) {
+			struct map *map = maps__maps_by_address(maps)[i];
+
+			maps_copy[i] = map__get(map);
+		}
 	}
+	up_read(maps__lock(maps));
 
-	if (args->mapp != NULL)
-		*args->mapp = map__get(map);
-	return 1;
-}
+	if (!maps_copy)
+		return NULL;
 
-struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp)
-{
-	struct maps__find_symbol_by_name_args args = {
-		.mapp = mapp,
-		.name = name,
-		.sym = NULL,
-	};
+	for (unsigned int i = 0; i < nr_maps; i++) {
+		struct map *map = maps_copy[i];
+
+		sym = map__find_symbol_by_name(map, name);
+		if (sym && map__contains_symbol(map, sym)) {
+			if (mapp)
+				*mapp = map__get(map);
+			break;
+		}
+		sym = NULL;
+	}
+
+	for (unsigned int i = 0; i < nr_maps; i++)
+		map__put(maps_copy[i]);
 
-	maps__for_each_map(maps, maps__find_symbol_by_name_cb, &args);
-	return args.sym;
+	free(maps_copy);
+	return sym;
 }
 
 int maps__find_ams(struct maps *maps, struct addr_map_symbol *ams)
diff --git a/tools/perf/util/maps.h b/tools/perf/util/maps.h
index 20c52084ba9e..b3f00f5c32fc 100644
--- a/tools/perf/util/maps.h
+++ b/tools/perf/util/maps.h
@@ -59,8 +59,11 @@ void maps__set_libdw_addr_space_dwfl(struct maps *maps, void *dwfl);
 
 size_t maps__fprintf(struct maps *maps, FILE *fp);
 
+int maps__load_maps(struct maps *maps);
 int maps__insert(struct maps *maps, struct map *map);
 void maps__remove(struct maps *maps, struct map *map);
+int maps__mutate_mapping(struct maps *maps, struct map *map,
+			 int (*mutate_cb)(struct map *map, void *data), void *data);
 
 struct map *maps__find(struct maps *maps, u64 addr);
 struct symbol *maps__find_symbol(struct maps *maps, u64 addr, struct map **mapp);
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index b69f926d314b..358e70c4f3ed 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -89,10 +89,10 @@ static int perf_mmap__aio_alloc(struct mmap *map, int idx)
 
 static void perf_mmap__aio_free(struct mmap *map, int idx)
 {
-	if (map->aio.data[idx]) {
-		munmap(map->aio.data[idx], mmap__mmap_len(map));
-		map->aio.data[idx] = NULL;
-	}
+	if (!map->aio.data || !map->aio.data[idx])
+		return;
+	munmap(map->aio.data[idx], mmap__mmap_len(map));
+	map->aio.data[idx] = NULL;
 }
 
 static int perf_mmap__aio_bind(struct mmap *map, int idx, struct perf_cpu cpu, int affinity)
@@ -104,9 +104,15 @@ static int perf_mmap__aio_bind(struct mmap *map, int idx, struct perf_cpu cpu, i
 	int err = 0;
 
 	if (affinity != PERF_AFFINITY_SYS && cpu__max_node() > 1) {
+		int node;
+
 		data = map->aio.data[idx];
 		mmap_len = mmap__mmap_len(map);
-		node_index = cpu__get_node(cpu);
+		node = cpu__get_node(cpu);
+		/* -1 sign-extends to ULONG_MAX, wrapping bitmap_zalloc(0) and OOB __set_bit */
+		if (node < 0)
+			return 0;
+		node_index = node;
 		node_mask = bitmap_zalloc(node_index + 1);
 		if (!node_mask) {
 			pr_err("Failed to allocate node mask for mbind: error %m\n");
@@ -135,6 +141,8 @@ static int perf_mmap__aio_alloc(struct mmap *map, int idx)
 
 static void perf_mmap__aio_free(struct mmap *map, int idx)
 {
+	if (!map->aio.data)
+		return;
 	zfree(&(map->aio.data[idx]));
 }
 
@@ -230,6 +238,8 @@ static void perf_mmap__aio_munmap(struct mmap *map __maybe_unused)
 void mmap__munmap(struct mmap *map)
 {
 	bitmap_free(map->affinity_mask.bits);
+	map->affinity_mask.bits = NULL;
+	map->affinity_mask.nbits = 0;
 
 	zstd_fini(&map->zstd_data);
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 23337d2fa281..64544e1e6810 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -314,7 +314,7 @@ static int perf_pmu__parse_scale(struct perf_pmu *pmu, struct perf_pmu_alias *al
 		goto error;
 
 	sret = read(fd, scale, sizeof(scale)-1);
-	if (sret < 0)
+	if (sret <= 0)
 		goto error;
 
 	if (scale[sret - 1] == '\n')
@@ -346,7 +346,7 @@ static int perf_pmu__parse_unit(struct perf_pmu *pmu, struct perf_pmu_alias *ali
 		return -1;
 
 	sret = read(fd, alias->unit, UNIT_MAX_LEN);
-	if (sret < 0)
+	if (sret <= 0)
 		goto error;
 
 	close(fd);
@@ -865,6 +865,12 @@ static char *pmu_id(const char *name)
 	if (filename__read_str(path, &str, &len) < 0)
 		return NULL;
 
+	/* empty identifier file — nothing useful */
+	if (len == 0) {
+		free(str);
+		return NULL;
+	}
+
 	str[len - 1] = 0; /* remove line feed */
 
 	return str;
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 64328abeef8b..f3f9a1573502 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -79,7 +79,7 @@ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr,
 	unsigned int regn;
 	Dwarf_Word offs = 0;
 	bool ref = false;
-	const char *regs;
+	const char *regs, *name;
 	int ret, ret2 = 0;
 
 	if (dwarf_attr(vr_die, DW_AT_external, &attr) != NULL)
@@ -93,7 +93,8 @@ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr,
 		if (!tvar)
 			return 0;
 
-		dwarf_formsdata(&attr, &snum);
+		if (dwarf_formsdata(&attr, &snum) != 0)
+			return -ENOENT;
 		ret = asprintf(&tvar->value, "\\%ld", (long)snum);
 
 		return ret < 0 ? -ENOMEM : 0;
@@ -103,8 +104,7 @@ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr,
 	if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL)
 		return -EINVAL;	/* Broken DIE ? */
 	if (dwarf_getlocation_addr(&attr, addr, &op, &nops, 1) <= 0) {
-		ret = dwarf_entrypc(sp_die, &tmp);
-		if (ret)
+		if (dwarf_entrypc(sp_die, &tmp) != 0)
 			return -ENOENT;
 
 		if (probe_conf.show_location_range &&
@@ -115,8 +115,7 @@ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr,
 			return -ENOENT;
 		}
 
-		ret = dwarf_highpc(sp_die, &tmp);
-		if (ret)
+		if (dwarf_highpc(sp_die, &tmp) != 0)
 			return -ENOENT;
 		/*
 		 * This is fuzzed by fentry mcount. We try to find the
@@ -138,12 +137,16 @@ found:
 static_var:
 		if (!tvar)
 			return ret2;
+
 		/* Static variables on memory (not stack), make @varname */
-		ret = strlen(dwarf_diename(vr_die));
+		name = dwarf_diename(vr_die);
+		if (!name)
+			return -ENOENT;
+		ret = strlen(name);
 		tvar->value = zalloc(ret + 2);
 		if (tvar->value == NULL)
 			return -ENOMEM;
-		snprintf(tvar->value, ret + 2, "@%s", dwarf_diename(vr_die));
+		snprintf(tvar->value, ret + 2, "@%s", name);
 		tvar->ref = alloc_trace_arg_ref((long)offs);
 		if (tvar->ref == NULL)
 			return -ENOMEM;
@@ -234,13 +237,14 @@ static int convert_variable_type(Dwarf_Die *vr_die,
 	}
 
 	if (die_get_real_type(vr_die, &type) == NULL) {
-		pr_warning("Failed to get a type information of %s.\n",
-			   dwarf_diename(vr_die));
+		const char *name = dwarf_diename(vr_die);
+
+		pr_warning("Failed to get a type information of %s.\n", name ?: "<unknown>");
 		return -ENOENT;
 	}
 
 	pr_debug("%s type is %s.\n",
-		 dwarf_diename(vr_die), dwarf_diename(&type));
+		 die_name(vr_die), die_name(&type));
 
 	if (cast && (!strcmp(cast, "string") || !strcmp(cast, "ustring"))) {
 		/* String type */
@@ -249,7 +253,7 @@ static int convert_variable_type(Dwarf_Die *vr_die,
 		    ret != DW_TAG_array_type) {
 			pr_warning("Failed to cast into string: "
 				   "%s(%s) is not a pointer nor array.\n",
-				   dwarf_diename(vr_die), dwarf_diename(&type));
+				   die_name(vr_die), die_name(&type));
 			return -EINVAL;
 		}
 		if (die_get_real_type(&type, &type) == NULL) {
@@ -272,7 +276,7 @@ static int convert_variable_type(Dwarf_Die *vr_die,
 		    !die_compare_name(&type, "unsigned char")) {
 			pr_warning("Failed to cast into string: "
 				   "%s is not (unsigned) char *.\n",
-				   dwarf_diename(vr_die));
+				   die_name(vr_die));
 			return -EINVAL;
 		}
 		tvar->type = strdup(cast);
@@ -299,7 +303,7 @@ static int convert_variable_type(Dwarf_Die *vr_die,
 	/* Check the bitwidth */
 	if (ret > MAX_BASIC_TYPE_BITS) {
 		pr_info("%s exceeds max-bitwidth. Cut down to %d bits.\n",
-			dwarf_diename(&type), MAX_BASIC_TYPE_BITS);
+			die_name(&type), MAX_BASIC_TYPE_BITS);
 		ret = MAX_BASIC_TYPE_BITS;
 	}
 	ret = snprintf(buf, 16, "%c%d", prefix, ret);
@@ -333,12 +337,14 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
 		pr_warning("Failed to get the type of %s.\n", varname);
 		return -ENOENT;
 	}
-	pr_debug2("Var real type: %s (%x)\n", dwarf_diename(&type),
+	pr_debug2("Var real type: %s (%x)\n", die_name(&type),
 		  (unsigned)dwarf_dieoffset(&type));
 	tag = dwarf_tag(&type);
 
 	if (field->name[0] == '[' &&
 	    (tag == DW_TAG_array_type || tag == DW_TAG_pointer_type)) {
+		int bsize;
+
 		/* Save original type for next field or type */
 		memcpy(die_mem, &type, sizeof(*die_mem));
 		/* Get the type of this array */
@@ -346,7 +352,7 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
 			pr_warning("Failed to get the type of %s.\n", varname);
 			return -ENOENT;
 		}
-		pr_debug2("Array real type: %s (%x)\n", dwarf_diename(&type),
+		pr_debug2("Array real type: %s (%x)\n", die_name(&type),
 			 (unsigned)dwarf_dieoffset(&type));
 		if (tag == DW_TAG_pointer_type) {
 			ref = zalloc(sizeof(struct probe_trace_arg_ref));
@@ -357,7 +363,15 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
 			else
 				*ref_ptr = ref;
 		}
-		ref->offset += dwarf_bytesize(&type) * field->index;
+		bsize = dwarf_bytesize(&type);
+
+		if (bsize < 0)
+			return -EINVAL;
+		if (!ref) {
+			pr_warning("Array indexing not supported for variables in registers.\n");
+			return -ENOTSUP;
+		}
+		ref->offset += bsize * field->index;
 		ref->user_access = user_access;
 		goto next;
 	} else if (tag == DW_TAG_pointer_type) {
@@ -414,7 +428,7 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
 
 	if (die_find_member(&type, field->name, die_mem) == NULL) {
 		pr_warning("%s(type:%s) has no member %s.\n", varname,
-			   dwarf_diename(&type), field->name);
+			   die_name(&type), field->name);
 		return -EINVAL;
 	}
 
@@ -461,7 +475,7 @@ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
 	int ret;
 
 	pr_debug("Converting variable %s into trace event.\n",
-		 dwarf_diename(vr_die));
+		 die_name(vr_die));
 
 	ret = convert_variable_location(vr_die, pf->addr, pf->fb_ops,
 					&pf->sp_die, pf, pf->tvar);
@@ -542,7 +556,7 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod,
 	/* Verify the address is correct */
 	if (!dwarf_haspc(sp_die, paddr)) {
 		pr_warning("Specified offset is out of %s\n",
-			   dwarf_diename(sp_die));
+			   die_name(sp_die));
 		return -EINVAL;
 	}
 
@@ -599,7 +613,7 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
 		if (!die_find_realfunc(&pf->cu_die, pf->addr, &pf->sp_die)) {
 			if (die_find_tailfunc(&pf->cu_die, pf->addr, &pf->sp_die)) {
 				pr_warning("Ignoring tail call from %s\n",
-						dwarf_diename(&pf->sp_die));
+						die_name(&pf->sp_die));
 				return 0;
 			} else {
 				pr_warning("Failed to find probe point in any "
@@ -611,10 +625,16 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
 		memcpy(&pf->sp_die, sc_die, sizeof(Dwarf_Die));
 
 	/* Get the frame base attribute/ops from subprogram */
-	dwarf_attr(&pf->sp_die, DW_AT_frame_base, &fb_attr);
-	ret = dwarf_getlocation_addr(&fb_attr, pf->addr, &pf->fb_ops, &nops, 1);
-	if (ret <= 0 || nops == 0) {
+	if (dwarf_attr(&pf->sp_die, DW_AT_frame_base, &fb_attr) == NULL) {
 		pf->fb_ops = NULL;
+	} else {
+		ret = dwarf_getlocation_addr(&fb_attr, pf->addr, &pf->fb_ops, &nops, 1);
+		if (ret <= 0 || nops == 0)
+			pf->fb_ops = NULL;
+	}
+
+	if (pf->fb_ops == NULL) {
+		/* Not supported */
 	} else if (nops == 1 && pf->fb_ops[0].atom == DW_OP_call_frame_cfa &&
 		   (pf->cfi_eh != NULL || pf->cfi_dbg != NULL)) {
 		if ((dwarf_cfi_addrframe(pf->cfi_eh, pf->addr, &frame) != 0 &&
@@ -667,8 +687,8 @@ static int find_best_scope_cb(Dwarf_Die *fn_die, void *data)
 		}
 	} else {
 		/* With the line number, find the nearest declared DIE */
-		dwarf_decl_line(fn_die, &lno);
-		if (lno < fsp->line && fsp->diff > fsp->line - lno) {
+		if (dwarf_decl_line(fn_die, &lno) == 0 && lno < fsp->line &&
+		    fsp->diff > fsp->line - lno) {
 			/* Keep a candidate and continue */
 			fsp->diff = fsp->line - lno;
 			memcpy(fsp->die_mem, fn_die, sizeof(Dwarf_Die));
@@ -924,12 +944,12 @@ static int probe_point_inline_cb(Dwarf_Die *in_die, void *data)
 		/* Get probe address */
 		if (die_entrypc(in_die, &addr) != 0) {
 			pr_warning("Failed to get entry address of %s.\n",
-				   dwarf_diename(in_die));
+				   die_name(in_die));
 			return -ENOENT;
 		}
 		if (addr == 0) {
 			pr_debug("%s has no valid entry address. skipped.\n",
-				 dwarf_diename(in_die));
+				 die_name(in_die));
 			return -ENOENT;
 		}
 		pf->addr = addr;
@@ -971,12 +991,13 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 	if (pp->file && fname && strtailcmp(pp->file, fname))
 		return DWARF_CB_OK;
 
-	pr_debug("Matched function: %s [%lx]\n", dwarf_diename(sp_die),
+	pr_debug("Matched function: %s [%lx]\n", die_name(sp_die),
 		 (unsigned long)dwarf_dieoffset(sp_die));
 	pf->fname = fname;
 	pf->abstrace_dieoffset = dwarf_dieoffset(sp_die);
 	if (pp->line) { /* Function relative line */
-		dwarf_decl_line(sp_die, &pf->lno);
+		if (dwarf_decl_line(sp_die, &pf->lno) != 0)
+			return DWARF_CB_OK;
 		pf->lno += pp->line;
 		param->retval = find_probe_point_by_line(pf);
 	} else if (die_is_func_instance(sp_die)) {
@@ -985,7 +1006,7 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 		/* But in some case the entry address is 0 */
 		if (pf->addr == 0) {
 			pr_debug("%s has no entry PC. Skipped\n",
-				 dwarf_diename(sp_die));
+				 die_name(sp_die));
 			param->retval = 0;
 		/* Real function */
 		} else if (pp->lazy_line)
@@ -1018,7 +1039,8 @@ static int find_probe_point_by_func(struct probe_finder *pf)
 {
 	struct dwarf_callback_param _param = {.data = (void *)pf,
 					      .retval = 0};
-	dwarf_getfuncs(&pf->cu_die, probe_point_search_cb, &_param, 0);
+	if (dwarf_getfuncs(&pf->cu_die, probe_point_search_cb, &_param, 0) < 0)
+		pr_debug("Failed to get functions from CU\n");
 	return _param.retval;
 }
 
@@ -1207,7 +1229,8 @@ static int copy_variables_cb(Dwarf_Die *die_mem, void *data)
 		 * points to correct die.
 		 */
 		if (dwarf_attr(die_mem, DW_AT_abstract_origin, &attr)) {
-			dwarf_formref_die(&attr, &var_die);
+			if (dwarf_formref_die(&attr, &var_die) == NULL)
+				goto out;
 			if (pf->abstrace_dieoffset != dwarf_dieoffset(&var_die))
 				goto out;
 		}
@@ -1293,13 +1316,16 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf)
 	if (ret < 0)
 		goto end;
 
-	tev->point.realname = strdup(dwarf_diename(sc_die));
+	tev->point.realname = strdup(die_name(sc_die));
 	if (!tev->point.realname) {
 		ret = -ENOMEM;
 		goto end;
 	}
 
-	tev->lang = dwarf_srclang(dwarf_diecu(sc_die, &pf->cu_die, NULL, NULL));
+	if (dwarf_diecu(sc_die, &pf->cu_die, NULL, NULL) != NULL)
+		tev->lang = dwarf_srclang(&pf->cu_die);
+	else
+		tev->lang = DW_LANG_C; /* Fallback */
 
 	pr_debug("Probe point found: %s+%lu\n", tev->point.symbol,
 		 tev->point.offset);
@@ -1794,7 +1820,8 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data)
 
 	if (die_match_name(sp_die, lr->function) && die_is_func_def(sp_die)) {
 		lf->fname = die_get_decl_file(sp_die);
-		dwarf_decl_line(sp_die, &lr->offset);
+		if (dwarf_decl_line(sp_die, &lr->offset) != 0)
+			lr->offset = 0; /* Fallback if no line info */
 		pr_debug("fname: %s, lineno:%d\n", lf->fname, lr->offset);
 		lf->lno_s = lr->offset + lr->start;
 		if (lf->lno_s < 0)	/* Overflow */
@@ -1818,7 +1845,8 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data)
 static int find_line_range_by_func(struct line_finder *lf)
 {
 	struct dwarf_callback_param param = {.data = (void *)lf, .retval = 0};
-	dwarf_getfuncs(&lf->cu_die, line_range_search_cb, &param, 0);
+	if (dwarf_getfuncs(&lf->cu_die, line_range_search_cb, &param, 0) < 0)
+		pr_debug("Failed to get functions from CU\n");
 	return param.retval;
 }
 
diff --git a/tools/perf/util/sample.h b/tools/perf/util/sample.h
index e556c9b656ea..c4eae8b2fd06 100644
--- a/tools/perf/util/sample.h
+++ b/tools/perf/util/sample.h
@@ -158,6 +158,8 @@ struct perf_sample {
 	u64 code_page_size;
 	/** @cgroup: The sample event PERF_SAMPLE_CGROUP value. */
 	u64 cgroup;
+	/** @file_offset: Byte offset of this event in the perf.data file. */
+	u64 file_offset;
 	/** @flags: Extra flag data from auxiliary events like intel-pt. */
 	u32 flags;
 	/** @machine_pid: The guest machine pid derived from the sample id. */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index fe0de2a0277f..2bc093bd2f24 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1352,6 +1352,7 @@ static int evlist__deliver_sample(struct evlist *evlist, const struct perf_tool
 struct deferred_event {
 	struct list_head list;
 	union perf_event *event;
+	u64 file_offset;
 };
 
 /*
@@ -1387,6 +1388,7 @@ static int evlist__deliver_deferred_callchain(struct evlist *evlist,
 			perf_sample__exit(&orig_sample);
 			break;
 		}
+		orig_sample.file_offset = de->file_offset;
 
 		if (sample->tid != orig_sample.tid) {
 			perf_sample__exit(&orig_sample);
@@ -1435,6 +1437,7 @@ static int session__flush_deferred_samples(struct perf_session *session,
 			perf_sample__exit(&sample);
 			break;
 		}
+		sample.file_offset = de->file_offset;
 
 		sample.evsel = evlist__id2evsel(evlist, sample.id);
 		ret = evlist__deliver_sample(evlist, tool, de->event,
@@ -1496,6 +1499,7 @@ static int machines__deliver_event(struct machines *machines,
 				return -ENOMEM;
 			}
 			memcpy(de->event, event, sz);
+			de->file_offset = sample->file_offset;
 			list_add_tail(&de->list, &evlist->deferred_samples);
 			return 0;
 		}
@@ -1589,6 +1593,7 @@ static int perf_session__deliver_event(struct perf_session *session,
 		ret = 0;
 		goto out;
 	}
+	sample.file_offset = file_offset;
 
 	ret = machines__deliver_event(&session->machines, session->evlist,
 				      event, &sample, tool, file_offset, file_path);
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index db164d258163..62884428fb5a 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -429,10 +429,13 @@ struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr,
 	return addr2inlines(dso_name, addr, dso, sym);
 }
 
-void inline_node__delete(struct inline_node *node)
+void inline_node__clear_frames(struct inline_node *node)
 {
 	struct inline_list *ilist, *tmp;
 
+	if (node == NULL)
+		return;
+
 	list_for_each_entry_safe(ilist, tmp, &node->val, list) {
 		list_del_init(&ilist->list);
 		zfree_srcline(&ilist->srcline);
@@ -441,7 +444,11 @@ void inline_node__delete(struct inline_node *node)
 			symbol__delete(ilist->symbol);
 		free(ilist);
 	}
+}
 
+void inline_node__delete(struct inline_node *node)
+{
+	inline_node__clear_frames(node);
 	free(node);
 }
 
diff --git a/tools/perf/util/srcline.h b/tools/perf/util/srcline.h
index 7c37b3bf9ce7..1018cbc886d6 100644
--- a/tools/perf/util/srcline.h
+++ b/tools/perf/util/srcline.h
@@ -47,6 +47,7 @@ struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr,
 					    struct symbol *sym);
 /* free resources associated to the inline node list */
 void inline_node__delete(struct inline_node *node);
+void inline_node__clear_frames(struct inline_node *node);
 
 /* insert the inline node list into the DSO, which will take ownership */
 void inlines__tree_insert(struct rb_root_cached *tree,
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index e360e7736c7b..826bd2577344 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -47,13 +47,13 @@ static double cpu2slot(int cpu)
 }
 
 static int *topology_map;
+static int topology_map_size;
 
 static double cpu2y(int cpu)
 {
-	if (topology_map)
+	if (topology_map && cpu >= 0 && cpu < topology_map_size)
 		return cpu2slot(topology_map[cpu]) * SLOT_MULT;
-	else
-		return cpu2slot(cpu) * SLOT_MULT;
+	return cpu2slot(cpu) * SLOT_MULT;
 }
 
 static double time2pixels(u64 __time)
@@ -736,7 +736,8 @@ static int str_to_bitmap(char *s, cpumask_t *b, int nr_cpus)
 		return -1;
 
 	perf_cpu_map__for_each_cpu(cpu, idx, map) {
-		if (cpu.cpu >= nr_cpus) {
+		/* perf_cpu_map__new("") returns cpu.cpu == -1 */
+		if (cpu.cpu < 0 || cpu.cpu >= nr_cpus) {
 			ret = -1;
 			break;
 		}
@@ -794,6 +795,7 @@ int svg_build_topology_map(struct perf_env *env)
 		fprintf(stderr, "topology: no memory\n");
 		goto exit;
 	}
+	topology_map_size = nr_cpus;
 
 	for (i = 0; i < nr_cpus; i++)
 		topology_map[i] = -1;
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 7afa8a117139..2007f8f003e3 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -217,7 +217,7 @@ bool filename__has_section(const char *filename, const char *sec)
 	GElf_Shdr shdr;
 	bool found = false;
 
-	fd = open(filename, O_RDONLY);
+	fd = open(filename, O_RDONLY | O_CLOEXEC);
 	if (fd < 0)
 		return false;
 
@@ -834,10 +834,24 @@ static int elf_read_build_id(Elf *elf, void *bf, size_t size)
 	ptr = data->d_buf;
 	while (ptr < (data->d_buf + data->d_size)) {
 		GElf_Nhdr *nhdr = ptr;
-		size_t namesz = NOTE_ALIGN(nhdr->n_namesz),
-		       descsz = NOTE_ALIGN(nhdr->n_descsz);
+		size_t namesz, descsz, remaining;
 		const char *name;
 
+		/* ensure the note header fits within the section */
+		if (ptr + sizeof(*nhdr) > data->d_buf + data->d_size)
+			break;
+
+		namesz = NOTE_ALIGN(nhdr->n_namesz);
+		descsz = NOTE_ALIGN(nhdr->n_descsz);
+
+		/* validate individually to avoid size_t overflow on 32-bit */
+		remaining = data->d_buf + data->d_size - ptr - sizeof(*nhdr);
+		if (namesz > remaining || descsz > remaining - namesz) {
+			pr_warning("%s: oversized note: n_namesz=%u, n_descsz=%u\n",
+				   __func__, nhdr->n_namesz, nhdr->n_descsz);
+			break;
+		}
+
 		ptr += sizeof(*nhdr);
 		name = ptr;
 		ptr += namesz;
@@ -871,7 +885,7 @@ static int read_build_id(const char *filename, struct build_id *bid)
 	if (size < BUILD_ID_SIZE)
 		goto out;
 
-	fd = open(filename, O_RDONLY);
+	fd = open(filename, O_RDONLY | O_CLOEXEC);
 	if (fd < 0)
 		goto out;
 
@@ -919,12 +933,14 @@ int filename__read_build_id(const char *filename, struct build_id *bid)
 			return -1;
 		}
 		close(fd);
-		filename = path;
+		/* non-empty path means a temp file was created */
+		if (path[0] != '\0')
+			filename = path;
 	}
 
 	err = read_build_id(filename, bid);
 
-	if (m.comp)
+	if (m.comp && filename == path)
 		unlink(filename);
 	return err;
 }
@@ -934,7 +950,7 @@ int sysfs__read_build_id(const char *filename, struct build_id *bid)
 	size_t size = sizeof(bid->data);
 	int fd, err = -1;
 
-	fd = open(filename, O_RDONLY);
+	fd = open(filename, O_RDONLY | O_CLOEXEC);
 	if (fd < 0)
 		goto out;
 
@@ -960,17 +976,28 @@ int sysfs__read_build_id(const char *filename, struct build_id *bid)
 					err = 0;
 					break;
 				}
-			} else if (read(fd, bf, descsz) != (ssize_t)descsz)
-				break;
+			} else {
+				/* descsz from untrusted file — clamp to buffer */
+				if (descsz > sizeof(bf))
+					break;
+				if (read(fd, bf, descsz) != (ssize_t)descsz)
+					break;
+			}
 		} else {
-			int n = namesz + descsz;
+			size_t n;
 
-			if (n > (int)sizeof(bf)) {
+			/* int sum of namesz+descsz can overflow negative, bypassing size check */
+			if (namesz > sizeof(bf) || descsz > sizeof(bf) - namesz) {
 				n = sizeof(bf);
 				pr_debug("%s: truncating reading of build id in sysfs file %s: n_namesz=%u, n_descsz=%u.\n",
 					 __func__, filename, nhdr.n_namesz, nhdr.n_descsz);
+			} else {
+				n = namesz + descsz;
 			}
-			if (read(fd, bf, n) != n)
+			/* no valid note has both namesz and descsz zero */
+			if (n == 0)
+				break;
+			if (read(fd, bf, n) != (ssize_t)n)
 				break;
 		}
 	}
@@ -994,7 +1021,7 @@ int filename__read_debuglink(const char *filename, char *debuglink,
 	if (err >= 0)
 		goto out;
 
-	fd = open(filename, O_RDONLY);
+	fd = open(filename, O_RDONLY | O_CLOEXEC);
 	if (fd < 0)
 		goto out;
 
@@ -1023,7 +1050,14 @@ int filename__read_debuglink(const char *filename, char *debuglink,
 		goto out_elf_end;
 
 	/* the start of this section is a zero-terminated string */
-	strncpy(debuglink, data->d_buf, size);
+	if (data->d_size > 0) {
+		size_t len = min(size - 1, data->d_size);
+
+		memcpy(debuglink, data->d_buf, len);
+		debuglink[len] = '\0';
+	} else {
+		debuglink[0] = '\0';
+	}
 
 	err = 0;
 
@@ -1108,9 +1142,9 @@ static Elf *read_gnu_debugdata(struct dso *dso, Elf *elf, const char *name, int
 		return NULL;
 	}
 
-	temp_fd = mkstemp(temp_filename);
+	temp_fd = mkostemp(temp_filename, O_CLOEXEC);
 	if (temp_fd < 0) {
-		pr_debug("%s: mkstemp: %m\n", __func__);
+		pr_debug("%s: mkostemp: %m\n", __func__);
 		*dso__load_errno(dso) = -errno;
 		fclose(wrapped);
 		return NULL;
@@ -1152,7 +1186,7 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 
 		type = dso__symtab_type(dso);
 	} else {
-		fd = open(name, O_RDONLY);
+		fd = open(name, O_RDONLY | O_CLOEXEC);
 		if (fd < 0) {
 			*dso__load_errno(dso) = errno;
 			return -1;
@@ -1341,6 +1375,24 @@ static u64 ref_reloc(struct kmap *kmap)
 void __weak arch__sym_update(struct symbol *s __maybe_unused,
 		GElf_Sym *sym __maybe_unused) { }
 
+struct remap_kernel_ctx {
+	u64 sh_addr;
+	u64 sh_size;
+	u64 sh_offset;
+	struct kmap *kmap;
+};
+
+static int remap_kernel_cb(struct map *map, void *data)
+{
+	struct remap_kernel_ctx *ctx = data;
+
+	map__set_start(map, ctx->sh_addr + ref_reloc(ctx->kmap));
+	map__set_end(map, map__start(map) + ctx->sh_size);
+	map__set_pgoff(map, ctx->sh_offset);
+	map__set_mapping_type(map, MAPPING_TYPE__DSO);
+	return 0;
+}
+
 static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
 				      GElf_Sym *sym, GElf_Shdr *shdr,
 				      struct maps *kmaps, struct kmap *kmap,
@@ -1371,22 +1423,15 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
 		 * map to the kernel dso.
 		 */
 		if (*remap_kernel && dso__kernel(dso) && !kmodule) {
+			struct remap_kernel_ctx ctx = {
+				.sh_addr = shdr->sh_addr,
+				.sh_size = shdr->sh_size,
+				.sh_offset = shdr->sh_offset,
+				.kmap = kmap
+			};
+
 			*remap_kernel = false;
-			map__set_start(map, shdr->sh_addr + ref_reloc(kmap));
-			map__set_end(map, map__start(map) + shdr->sh_size);
-			map__set_pgoff(map, shdr->sh_offset);
-			map__set_mapping_type(map, MAPPING_TYPE__DSO);
-			/* Ensure maps are correctly ordered */
-			if (kmaps) {
-				int err;
-				struct map *tmp = map__get(map);
-
-				maps__remove(kmaps, map);
-				err = maps__insert(kmaps, map);
-				map__put(tmp);
-				if (err)
-					return err;
-			}
+			maps__mutate_mapping(kmaps, map, remap_kernel_cb, &ctx);
 		}
 
 		/*
@@ -1945,7 +1990,7 @@ static int kcore__open(struct kcore *kcore, const char *filename)
 {
 	GElf_Ehdr *ehdr;
 
-	kcore->fd = open(filename, O_RDONLY);
+	kcore->fd = open(filename, O_RDONLY | O_CLOEXEC);
 	if (kcore->fd == -1)
 		return -1;
 
@@ -1976,9 +2021,9 @@ static int kcore__init(struct kcore *kcore, char *filename, int elfclass,
 	kcore->elfclass = elfclass;
 
 	if (temp)
-		kcore->fd = mkstemp(filename);
+		kcore->fd = mkostemp(filename, O_CLOEXEC);
 	else
-		kcore->fd = open(filename, O_WRONLY | O_CREAT | O_EXCL, 0400);
+		kcore->fd = open(filename, O_WRONLY | O_CREAT | O_EXCL | O_CLOEXEC, 0400);
 	if (kcore->fd == -1)
 		return -1;
 
@@ -2454,11 +2499,11 @@ static int kcore_copy__compare_files(const char *from_filename,
 {
 	int from, to, err = -1;
 
-	from = open(from_filename, O_RDONLY);
+	from = open(from_filename, O_RDONLY | O_CLOEXEC);
 	if (from < 0)
 		return -1;
 
-	to = open(to_filename, O_RDONLY);
+	to = open(to_filename, O_RDONLY | O_CLOEXEC);
 	if (to < 0)
 		goto out_close_from;
 
@@ -2876,7 +2921,7 @@ int get_sdt_note_list(struct list_head *head, const char *target)
 	Elf *elf;
 	int fd, ret;
 
-	fd = open(target, O_RDONLY);
+	fd = open(target, O_RDONLY | O_CLOEXEC);
 	if (fd < 0)
 		return -EBADF;
 
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index 8221dc9868f7..0a71d1463952 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -1,3 +1,4 @@
+#include "debug.h"
 #include "dso.h"
 #include "symbol.h"
 #include "symsrc.h"
@@ -44,7 +45,7 @@ static int read_build_id(void *note_data, size_t note_len, struct build_id *bid,
 	ptr = note_data;
 	while ((ptr + sizeof(*nhdr)) < (note_data + note_len)) {
 		const char *name;
-		size_t namesz, descsz;
+		size_t namesz, descsz, remaining;
 
 		nhdr = ptr;
 		if (need_swap) {
@@ -56,6 +57,14 @@ static int read_build_id(void *note_data, size_t note_len, struct build_id *bid,
 		namesz = NOTE_ALIGN(nhdr->n_namesz);
 		descsz = NOTE_ALIGN(nhdr->n_descsz);
 
+		/* validate individually to avoid size_t overflow on 32-bit */
+		remaining = note_data + note_len - ptr - sizeof(*nhdr);
+		if (namesz > remaining || descsz > remaining - namesz) {
+			pr_warning("%s: oversized note: n_namesz=%u, n_descsz=%u\n",
+				   __func__, nhdr->n_namesz, nhdr->n_descsz);
+			break;
+		}
+
 		ptr += sizeof(*nhdr);
 		name = ptr;
 		ptr += namesz;
@@ -166,7 +175,7 @@ int filename__read_build_id(const char *filename, struct build_id *bid)
 			if (elf32) {
 				hdrs.phdr32[i].p_type = bswap_32(hdrs.phdr32[i].p_type);
 				hdrs.phdr32[i].p_offset = bswap_32(hdrs.phdr32[i].p_offset);
-				hdrs.phdr32[i].p_filesz = bswap_32(hdrs.phdr32[i].p_offset);
+				hdrs.phdr32[i].p_filesz = bswap_32(hdrs.phdr32[i].p_filesz);
 			} else {
 				hdrs.phdr64[i].p_type = bswap_32(hdrs.phdr64[i].p_type);
 				hdrs.phdr64[i].p_offset = bswap_64(hdrs.phdr64[i].p_offset);
@@ -177,6 +186,9 @@ int filename__read_build_id(const char *filename, struct build_id *bid)
 			continue;
 
 		p_filesz = elf32 ? hdrs.phdr32[i].p_filesz : hdrs.phdr64[i].p_filesz;
+		/* ssize_t can go negative with crafted ELF p_filesz values */
+		if (p_filesz <= 0)
+			continue;
 		if (p_filesz > buf_size) {
 			void *tmp;
 
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index fcaeeddbbb6b..85bdb3cbe0b8 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -48,6 +48,13 @@
 #include <symbol/kallsyms.h>
 #include <sys/utsname.h>
 
+static int map_fixup_cb(struct map *map, void *data __maybe_unused)
+{
+	map__fixup_start(map);
+	map__fixup_end(map);
+	return 0;
+}
+
 static int dso__load_kernel_sym(struct dso *dso, struct map *map);
 static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map);
 static bool symbol__is_idle(const char *name);
@@ -2121,10 +2128,11 @@ do_kallsyms:
 	free(kallsyms_allocated_filename);
 
 	if (err > 0 && !dso__is_kcore(dso)) {
+		struct maps *kmaps = map__kmaps(map);
+
 		dso__set_binary_type(dso, DSO_BINARY_TYPE__KALLSYMS);
 		dso__set_long_name(dso, DSO__NAME_KALLSYMS, false);
-		map__fixup_start(map);
-		map__fixup_end(map);
+		maps__mutate_mapping(kmaps, map, map_fixup_cb, NULL);
 	}
 
 	return err;
@@ -2156,7 +2164,7 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map)
 		if (!kallsyms_filename)
 			return -1;
 	} else {
-		sprintf(path, "%s/proc/kallsyms", machine->root_dir);
+		snprintf(path, sizeof(path), "%s/proc/kallsyms", machine->root_dir);
 		kallsyms_filename = path;
 	}
 
@@ -2164,10 +2172,11 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map)
 	if (err > 0)
 		pr_debug("Using %s for symbols\n", kallsyms_filename);
 	if (err > 0 && !dso__is_kcore(dso)) {
+		struct maps *kmaps = map__kmaps(map);
+
 		dso__set_binary_type(dso, DSO_BINARY_TYPE__GUEST_KALLSYMS);
 		dso__set_long_name(dso, machine->mmap_name, false);
-		map__fixup_start(map);
-		map__fixup_end(map);
+		maps__mutate_mapping(kmaps, map, map_fixup_cb, NULL);
 	}
 
 	return err;
diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h
index 6cd454d7c98e..0dee5aa6a534 100644
--- a/tools/perf/util/symbol_conf.h
+++ b/tools/perf/util/symbol_conf.h
@@ -9,6 +9,15 @@
 struct strlist;
 struct intlist;
 
+enum unwind_style {
+	UNWIND_STYLE_UNKNOWN = 0,
+	UNWIND_STYLE_LIBDW,
+	UNWIND_STYLE_LIBUNWIND,
+};
+
+#define MAX_UNWIND_STYLE (UNWIND_STYLE_LIBUNWIND + 1)
+
+
 enum a2l_style {
 	A2L_STYLE_UNKNOWN = 0,
 	A2L_STYLE_LIBDW,
@@ -81,6 +90,7 @@ struct symbol_conf {
 	const char		*addr2line_path;
 	enum a2l_style	addr2line_style[MAX_A2L_STYLE];
 	int             addr2line_timeout_ms;
+	enum unwind_style unwind_style[MAX_UNWIND_STYLE];
 	unsigned long	time_quantum;
        struct strlist	*dso_list,
 			*comm_list,
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index 85bee747f4cd..2461f25a4d7d 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -1455,7 +1455,8 @@ int perf_event__synthesize_stat_round(const struct perf_tool *tool,
 	return process(tool, (union perf_event *) &event, NULL, machine);
 }
 
-size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, u64 read_format)
+size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, u64 read_format,
+				     u64 branch_sample_type)
 {
 	size_t sz, result = sizeof(struct perf_record_sample);
 
@@ -1515,8 +1516,10 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 
 	if (type & PERF_SAMPLE_BRANCH_STACK) {
 		sz = sample->branch_stack->nr * sizeof(struct branch_entry);
-		/* nr, hw_idx */
-		sz += 2 * sizeof(u64);
+		/* nr */
+		sz += sizeof(u64);
+		if (branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX)
+			sz += sizeof(u64);
 		result += sz;
 	}
 
@@ -1605,7 +1608,7 @@ static __u64 *copy_read_group_values(__u64 *array, __u64 read_format,
 }
 
 int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_format,
-				  const struct perf_sample *sample)
+				  u64 branch_sample_type, const struct perf_sample *sample)
 {
 	__u64 *array;
 	size_t sz;
@@ -1719,9 +1722,17 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo
 
 	if (type & PERF_SAMPLE_BRANCH_STACK) {
 		sz = sample->branch_stack->nr * sizeof(struct branch_entry);
-		/* nr, hw_idx */
-		sz += 2 * sizeof(u64);
-		memcpy(array, sample->branch_stack, sz);
+
+		*array++ = sample->branch_stack->nr;
+
+		if (branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX) {
+			if (sample->no_hw_idx)
+				*array++ = 0;
+			else
+				*array++ = sample->branch_stack->hw_idx;
+		}
+
+		memcpy(array, perf_sample__branch_entries((struct perf_sample *)sample), sz);
 		array = (void *)array + sz;
 	}
 
diff --git a/tools/perf/util/synthetic-events.h b/tools/perf/util/synthetic-events.h
index b0edad0c3100..8c7f49f9ccf5 100644
--- a/tools/perf/util/synthetic-events.h
+++ b/tools/perf/util/synthetic-events.h
@@ -81,7 +81,8 @@ int perf_event__synthesize_mmap_events(const struct perf_tool *tool, union perf_
 int perf_event__synthesize_modules(const struct perf_tool *tool, perf_event__handler_t process, struct machine *machine);
 int perf_event__synthesize_namespaces(const struct perf_tool *tool, union perf_event *event, pid_t pid, pid_t tgid, perf_event__handler_t process, struct machine *machine);
 int perf_event__synthesize_cgroups(const struct perf_tool *tool, perf_event__handler_t process, struct machine *machine);
-int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_format, const struct perf_sample *sample);
+int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_format,
+				  u64 branch_sample_type, const struct perf_sample *sample);
 int perf_event__synthesize_stat_config(const struct perf_tool *tool, struct perf_stat_config *config, perf_event__handler_t process, struct machine *machine);
 int perf_event__synthesize_stat_events(struct perf_stat_config *config, const struct perf_tool *tool, struct evlist *evlist, perf_event__handler_t process, bool attrs);
 int perf_event__synthesize_stat_round(const struct perf_tool *tool, u64 time, u64 type, perf_event__handler_t process, struct machine *machine);
@@ -97,7 +98,8 @@ void perf_event__synthesize_final_bpf_metadata(struct perf_session *session,
 
 int perf_tool__process_synth_event(const struct perf_tool *tool, union perf_event *event, struct machine *machine, perf_event__handler_t process);
 
-size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, u64 read_format);
+size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
+				     u64 read_format, u64 branch_sample_type);
 
 int __machine__synthesize_threads(struct machine *machine, const struct perf_tool *tool,
 				  struct target *target, struct perf_thread_map *threads,
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 22be77225bb0..2faa258f9c15 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -294,6 +294,11 @@ int thread__set_comm_from_proc(struct thread *thread)
 	if (!(snprintf(path, sizeof(path), "%d/task/%d/comm",
 		       thread__pid(thread), thread__tid(thread)) >= (int)sizeof(path)) &&
 	    procfs__read_str(path, &comm, &sz) == 0) {
+		/* sz==0: read got nothing, e.g. race during exit teardown */
+		if (sz == 0) {
+			free(comm);
+			return -1;
+		}
 		comm[sz - 1] = '\0';
 		err = thread__set_comm(thread, comm, 0);
 	}
diff --git a/tools/perf/util/tool.c b/tools/perf/util/tool.c
index 013c7839e2cf..ff2150517b75 100644
--- a/tools/perf/util/tool.c
+++ b/tools/perf/util/tool.c
@@ -285,6 +285,7 @@ void perf_tool__init(struct perf_tool *tool, bool ordered_events)
 	tool->no_warn = false;
 	tool->show_feat_hdr = SHOW_FEAT_NO_HEADER;
 	tool->merge_deferred_callchains = true;
+	tool->dont_split_sample_group = false;
 
 	tool->sample = process_event_sample_stub;
 	tool->mmap = process_event_stub;
@@ -433,6 +434,8 @@ CREATE_DELEGATE_OP2(stat_config);
 CREATE_DELEGATE_OP2(stat_round);
 CREATE_DELEGATE_OP2(thread_map);
 CREATE_DELEGATE_OP2(time_conv);
+CREATE_DELEGATE_OP2(schedstat_cpu);
+CREATE_DELEGATE_OP2(schedstat_domain);
 CREATE_DELEGATE_OP2(tracing_data);
 
 #define CREATE_DELEGATE_OP3(name)					\
@@ -470,6 +473,7 @@ void delegate_tool__init(struct delegate_tool *tool, struct perf_tool *delegate)
 	tool->tool.no_warn = delegate->no_warn;
 	tool->tool.show_feat_hdr = delegate->show_feat_hdr;
 	tool->tool.merge_deferred_callchains = delegate->merge_deferred_callchains;
+	tool->tool.dont_split_sample_group = delegate->dont_split_sample_group;
 
 	tool->tool.sample = delegate_sample;
 	tool->tool.read = delegate_read;
@@ -516,4 +520,6 @@ void delegate_tool__init(struct delegate_tool *tool, struct perf_tool *delegate)
 	tool->tool.bpf_metadata = delegate_bpf_metadata;
 	tool->tool.compressed = delegate_compressed;
 	tool->tool.auxtrace = delegate_auxtrace;
+	tool->tool.schedstat_cpu = delegate_schedstat_cpu;
+	tool->tool.schedstat_domain = delegate_schedstat_domain;
 }
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 05e8e68bd49c..7f35042be567 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -339,7 +339,7 @@ frame_callback(Dwfl_Frame *state, void *arg)
 	       DWARF_CB_ABORT : DWARF_CB_OK;
 }
 
-int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
+int libdw__get_entries(unwind_entry_cb_t cb, void *arg,
 			struct thread *thread,
 			struct perf_sample *data,
 			int max_stack,
@@ -353,10 +353,10 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 	static struct unwind_info *ui;
 	Dwfl *dwfl;
 	Dwarf_Word ip;
-	int err = -EINVAL, i;
+	int err = -EINVAL, i, entries;
 
 	if (!data->user_regs || !data->user_regs->regs)
-		return -EINVAL;
+		return 0;
 
 	ui = zalloc(sizeof(*ui) + sizeof(ui->entries[0]) * max_stack);
 	if (!ui)
@@ -430,6 +430,18 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 		map_symbol__exit(&ui->entries[i].ms);
 
 	dwfl_ui_ti->ui = NULL;
+	entries = (int)ui->idx;
 	free(ui);
-	return 0;
+	/*
+	 * Unwinder return contract:
+	 *  > 0 : unwinding succeeded (stops fallback). If we found frames but hit an error
+	 *        (e.g. truncated stack), report success to preserve existing frames.
+	 *    0 : unwinding failed without yielding frames. Ignore non-fatal errors
+	 *        (e.g. missing debug info, DWARF corruption) to allow fallback unwinder or
+	 *        kernel callchain resolution to proceed.
+	 *  < 0 : fatal error (e.g. -ENOMEM). Aborts unwinding entirely.
+	 */
+	if (err)
+		return (err == -ENOMEM) ? -ENOMEM : (entries > 0 ? 1 : 0);
+	return entries;
 }
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 87d496e9dfa6..27e2f7b31789 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -744,7 +744,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 	ret = perf_reg_value(&val, perf_sample__user_regs(ui->sample),
 			     perf_arch_reg_ip(e_machine));
 	if (ret)
-		return ret;
+		return 0;
 
 	ips[i++] = (unw_word_t) val;
 
@@ -757,7 +757,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 		addr_space = maps__addr_space(thread__maps(ui->thread));
 
 		if (addr_space == NULL)
-			return -1;
+			return 0;
 
 		ret = unw_init_remote(&c, addr_space, ui);
 		if (ret && !ui->best_effort)
@@ -785,15 +785,30 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 	/*
 	 * Display what we got based on the order setup.
 	 */
+	int entries = 0;
 	for (i = 0; i < max_stack && !ret; i++) {
 		int j = i;
 
 		if (callchain_param.order == ORDER_CALLER)
 			j = max_stack - i - 1;
-		ret = ips[j] ? entry(ips[j], ui->thread, cb, arg) : 0;
+		if (ips[j]) {
+			ret = entry(ips[j], ui->thread, cb, arg);
+			if (ret)
+				break;
+			entries++;
+		}
 	}
 
-	return ret;
+	/*
+	 * Unwinder return contract:
+	 *  > 0 : unwinding succeeded (stops fallback).
+	 *    0 : unwinding failed without yielding frames. Ignore non-fatal errors
+	 *        (e.g. stepping failure) to allow fallback unwinder or kernel callchains.
+	 *  < 0 : fatal error (e.g. -ENOMEM). Aborts unwinding entirely.
+	 */
+	if (ret == -ENOMEM)
+		return -ENOMEM;
+	return (entries > 0 || ret == 0) ? entries : 0;
 }
 
 static int _unwind__get_entries(unwind_entry_cb_t cb, void *arg,
@@ -809,10 +824,10 @@ static int _unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 	};
 
 	if (!data->user_regs || !data->user_regs->regs)
-		return -EINVAL;
+		return 0;
 
 	if (max_stack <= 0)
-		return -EINVAL;
+		return 0;
 
 	return get_entries(&ui, cb, arg, max_stack);
 }
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index cb8be6acfb6f..a0016b897dae 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -79,7 +79,7 @@ void unwind__finish_access(struct maps *maps)
 		ops->finish_access(maps);
 }
 
-int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
+int libunwind__get_entries(unwind_entry_cb_t cb, void *arg,
 			 struct thread *thread,
 			 struct perf_sample *data, int max_stack,
 			 bool best_effort)
diff --git a/tools/perf/util/unwind.c b/tools/perf/util/unwind.c
new file mode 100644
index 000000000000..4ed4b1d55c69
--- /dev/null
+++ b/tools/perf/util/unwind.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "debug.h"
+#include "symbol_conf.h"
+#include "unwind.h"
+#include <linux/string.h>
+#include <string.h>
+#include <stdlib.h>
+
+int unwind__get_entries(unwind_entry_cb_t cb __maybe_unused, void *arg __maybe_unused,
+			struct thread *thread __maybe_unused,
+			struct perf_sample *data __maybe_unused,
+			int max_stack __maybe_unused,
+			bool best_effort __maybe_unused)
+{
+	int ret = 0;
+
+#if defined(HAVE_LIBDW_SUPPORT) || defined(HAVE_LIBUNWIND_SUPPORT)
+	if (symbol_conf.unwind_style[0] == UNWIND_STYLE_UNKNOWN) {
+		int i = 0;
+#ifdef HAVE_LIBDW_SUPPORT
+		symbol_conf.unwind_style[i++] = UNWIND_STYLE_LIBDW;
+#endif
+#ifdef HAVE_LIBUNWIND_SUPPORT
+		symbol_conf.unwind_style[i++] = UNWIND_STYLE_LIBUNWIND;
+#endif
+	}
+#endif //defined(HAVE_LIBDW_SUPPORT) || defined(HAVE_LIBUNWIND_SUPPORT)
+
+	for (size_t i = 0; i < ARRAY_SIZE(symbol_conf.unwind_style); i++) {
+		switch (symbol_conf.unwind_style[i]) {
+		case UNWIND_STYLE_LIBDW:
+			ret = libdw__get_entries(cb, arg, thread, data, max_stack, best_effort);
+			break;
+		case UNWIND_STYLE_LIBUNWIND:
+			ret = libunwind__get_entries(cb, arg, thread, data, max_stack, best_effort);
+			break;
+		case UNWIND_STYLE_UNKNOWN:
+		default:
+#if !defined(HAVE_LIBDW_SUPPORT) && !defined(HAVE_LIBUNWIND_SUPPORT)
+			pr_warning_once(
+				"Error: dwarf unwinding not supported, build perf with libdw or libunwind.\n");
+#endif
+			ret = 0;
+			break;
+		}
+		if (ret > 0) {
+			ret = 0;
+			break;
+		}
+		if (ret < 0)
+			break;
+	}
+	return ret;
+}
+
+int unwind__configure(const char *var, const char *value, void *cb __maybe_unused)
+{
+	static const char * const unwind_style_names[] = {
+		[UNWIND_STYLE_LIBDW] = "libdw",
+		[UNWIND_STYLE_LIBUNWIND] = "libunwind",
+		NULL
+	};
+	char *s, *p, *saveptr;
+	size_t i = 0;
+
+	if (strcmp(var, "unwind.style"))
+		return 0;
+
+	if (!value)
+		return -1;
+
+	s = strdup(value);
+	if (!s)
+		return -1;
+
+	memset(symbol_conf.unwind_style, 0, sizeof(symbol_conf.unwind_style));
+
+	p = strtok_r(s, ",", &saveptr);
+	while (p && i < ARRAY_SIZE(symbol_conf.unwind_style)) {
+		bool found = false;
+		char *q = strim(p);
+
+		for (size_t j = UNWIND_STYLE_LIBDW; j < MAX_UNWIND_STYLE; j++) {
+			if (!strcasecmp(q, unwind_style_names[j])) {
+				symbol_conf.unwind_style[i++] = j;
+				found = true;
+				break;
+			}
+		}
+		if (!found)
+			pr_warning("Unknown unwind style: %s\n", q);
+		p = strtok_r(NULL, ",", &saveptr);
+	}
+
+	free(s);
+	return 0;
+}
+
+int unwind__option(const struct option *opt __maybe_unused,
+		   const char *arg,
+		   int unset __maybe_unused)
+{
+	return unwind__configure("unwind.style", arg, NULL);
+}
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index 9f7164c6d9aa..69ba08afda79 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -4,9 +4,10 @@
 
 #include <linux/compiler.h>
 #include <linux/types.h>
-#include "util/map_symbol.h"
+#include "map_symbol.h"
 
 struct maps;
+struct option;
 struct perf_sample;
 struct thread;
 
@@ -26,7 +27,9 @@ struct unwind_libunwind_ops {
 			   struct perf_sample *data, int max_stack, bool best_effort);
 };
 
-#ifdef HAVE_DWARF_UNWIND_SUPPORT
+int unwind__configure(const char *var, const char *value, void *cb);
+int unwind__option(const struct option *opt, const char *arg, int unset);
+
 /*
  * When best_effort is set, don't report errors and fail silently. This could
  * be expanded in the future to be more permissive about things other than
@@ -36,8 +39,31 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 			struct thread *thread,
 			struct perf_sample *data, int max_stack,
 			bool best_effort);
-/* libunwind specific */
+
+#ifdef HAVE_LIBDW_SUPPORT
+int libdw__get_entries(unwind_entry_cb_t cb, void *arg,
+		       struct thread *thread,
+		       struct perf_sample *data, int max_stack,
+		       bool best_effort);
+#else
+#include "debug.h"
+static inline int libdw__get_entries(unwind_entry_cb_t cb __maybe_unused, void *arg __maybe_unused,
+				     struct thread *thread __maybe_unused,
+				     struct perf_sample *data __maybe_unused,
+				     int max_stack __maybe_unused,
+				     bool best_effort __maybe_unused)
+{
+	pr_warning_once("Error: libdw dwarf unwinding not built into perf\n");
+	return 0;
+}
+#endif
+
 #ifdef HAVE_LIBUNWIND_SUPPORT
+/* libunwind specific */
+int libunwind__get_entries(unwind_entry_cb_t cb, void *arg,
+			   struct thread *thread,
+			   struct perf_sample *data, int max_stack,
+			   bool best_effort);
 #ifndef LIBUNWIND__ARCH_REG_ID
 #define LIBUNWIND__ARCH_REG_ID(regnum) libunwind__arch_reg_id(regnum)
 #endif
@@ -47,25 +73,15 @@ int unwind__prepare_access(struct maps *maps, struct map *map, bool *initialized
 void unwind__flush_access(struct maps *maps);
 void unwind__finish_access(struct maps *maps);
 #else
-static inline int unwind__prepare_access(struct maps *maps __maybe_unused,
-					 struct map *map __maybe_unused,
-					 bool *initialized __maybe_unused)
-{
-	return 0;
-}
-
-static inline void unwind__flush_access(struct maps *maps __maybe_unused) {}
-static inline void unwind__finish_access(struct maps *maps __maybe_unused) {}
-#endif
-#else
-static inline int
-unwind__get_entries(unwind_entry_cb_t cb __maybe_unused,
-		    void *arg __maybe_unused,
-		    struct thread *thread __maybe_unused,
-		    struct perf_sample *data __maybe_unused,
-		    int max_stack __maybe_unused,
-		    bool best_effort __maybe_unused)
+#include "debug.h"
+static inline int libunwind__get_entries(unwind_entry_cb_t cb __maybe_unused,
+					 void *arg __maybe_unused,
+					 struct thread *thread __maybe_unused,
+					 struct perf_sample *data __maybe_unused,
+					 int max_stack __maybe_unused,
+					 bool best_effort __maybe_unused)
 {
+	pr_warning_once("Error: libunwind dwarf unwinding not built into perf\n");
 	return 0;
 }
 
@@ -78,5 +94,6 @@ static inline int unwind__prepare_access(struct maps *maps __maybe_unused,
 
 static inline void unwind__flush_access(struct maps *maps __maybe_unused) {}
 static inline void unwind__finish_access(struct maps *maps __maybe_unused) {}
-#endif /* HAVE_DWARF_UNWIND_SUPPORT */
+#endif
+
 #endif /* __UNWIND_H */