Merge tag 'perf-core-for-mingo-5.4-20190814' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo:

Intel PT:

  Adrian Hunter:

  - Add PEBS via Intel PT support, the kernel bits went via PeterZ.

perf record:

  Alexander Shishkin:

  - Add an option to take an AUX snapshot on exit.

  Tan Xiaojun:

  - Support aarch64 random socket_id assignment, just like was fixed for S/390.

tools:

  Andy Shevchenko:

  - Keep list of tools in alphabetical order on 'make -C tools help'.

perf session:

  Arnaldo Carvalho de Melo:

  - Avoid infinite loop when seeing invalid header.size, reported by
    Vince Weaver using a perf.data fuzzer.

Documentation:

  Vince Weaver:

  - Clarify HEADER_SAMPLE_TOPOLOGY format in the perf.data spec.

perf config:

  Arnaldo Carvalho de Melo:

  - Honour $PERF_CONFIG env var to specify alternate .perfconfig.

perf test:

  Arnaldo Carvalho de Melo:

  - Disable ~/.perfconfig to get default output in 'perf trace' tests.

perf top:

  Arnaldo Carvalho de Melo:

  - Set display thread COMM to help with debugging.

  - Collapse and resort evsels in a group, so that we have output
    similar to 'perf report' when using event groups, i.e.

      perf top -e '{cycles,instructions}'

    Will have two columns, and the instructions one will work.

core:

  Igor Lubashev:

  - Detect if libcap development files are available so that we
    can use capabilities to match the checks made by the kernel instead
    of using plain (geteuid() == 0).

Intel:

  Haiyan Song:

  - Add Icelake V1.00 event file.

perf trace:

  Leo Yan:

  - Fix segmentation fault when access syscall info on arm64.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

25 files changed, 197 insertions, 15 deletions

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 7abf05131889..7cda749059a9 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -148,6 +148,8 @@ perf-$(CONFIG_ZLIB) += zlib.o
 perf-$(CONFIG_LZMA) += lzma.o
 perf-$(CONFIG_ZSTD) += zstd.o
 
+perf-$(CONFIG_LIBCAP) += cap.o
+
 perf-y += demangle-java.o
 perf-y += demangle-rust.o
 
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 91d4fc3e78cf..e0518dc4c4d2 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1122,7 +1122,7 @@ static int disasm_line__parse(char *line, const char **namep, char **rawp)
 		goto out;
 
 	(*rawp)[0] = tmp;
-	*rawp = skip_spaces(*rawp);
+	*rawp = strim(*rawp);
 
 	return 0;
 
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 65728cdeefb6..60428576426e 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -539,9 +539,9 @@ int auxtrace_record__snapshot_start(struct auxtrace_record *itr)
 	return 0;
 }
 
-int auxtrace_record__snapshot_finish(struct auxtrace_record *itr)
+int auxtrace_record__snapshot_finish(struct auxtrace_record *itr, bool on_exit)
 {
-	if (itr && itr->snapshot_finish)
+	if (!on_exit && itr && itr->snapshot_finish)
 		return itr->snapshot_finish(itr);
 	return 0;
 }
@@ -577,6 +577,16 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
 	if (!str)
 		return 0;
 
+	/* PMU-agnostic options */
+	switch (*str) {
+	case 'e':
+		opts->auxtrace_snapshot_on_exit = true;
+		str++;
+		break;
+	default:
+		break;
+	}
+
 	if (itr)
 		return itr->parse_snapshot_options(itr, opts, str);
 
@@ -964,6 +974,7 @@ void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts,
 	synth_opts->transactions = true;
 	synth_opts->ptwrites = true;
 	synth_opts->pwr_events = true;
+	synth_opts->other_events = true;
 	synth_opts->errors = true;
 	if (no_sample) {
 		synth_opts->period_type = PERF_ITRACE_PERIOD_INSTRUCTIONS;
@@ -1061,6 +1072,9 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
 		case 'p':
 			synth_opts->pwr_events = true;
 			break;
+		case 'o':
+			synth_opts->other_events = true;
+			break;
 		case 'e':
 			synth_opts->errors = true;
 			break;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 17eb04a1da4d..8e637ac3918e 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -60,6 +60,8 @@ enum itrace_period_type {
  * @transactions: whether to synthesize events for transactions
  * @ptwrites: whether to synthesize events for ptwrites
  * @pwr_events: whether to synthesize power events
+ * @other_events: whether to synthesize other events recorded due to the use of
+ *                aux_output
  * @errors: whether to synthesize decoder error events
  * @dont_decode: whether to skip decoding entirely
  * @log: write a decoding log
@@ -86,6 +88,7 @@ struct itrace_synth_opts {
 	bool			transactions;
 	bool			ptwrites;
 	bool			pwr_events;
+	bool			other_events;
 	bool			errors;
 	bool			dont_decode;
 	bool			log;
@@ -499,7 +502,7 @@ int auxtrace_record__info_fill(struct auxtrace_record *itr,
 			       size_t priv_size);
 void auxtrace_record__free(struct auxtrace_record *itr);
 int auxtrace_record__snapshot_start(struct auxtrace_record *itr);
-int auxtrace_record__snapshot_finish(struct auxtrace_record *itr);
+int auxtrace_record__snapshot_finish(struct auxtrace_record *itr, bool on_exit);
 int auxtrace_record__find_snapshot(struct auxtrace_record *itr, int idx,
 				   struct auxtrace_mmap *mm,
 				   unsigned char *data, u64 *head, u64 *old);
diff --git a/tools/perf/util/cap.c b/tools/perf/util/cap.c
new file mode 100644
index 000000000000..c3ba841bbf37
--- /dev/null
+++ b/tools/perf/util/cap.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Capability utilities
+ */
+
+#ifdef HAVE_LIBCAP_SUPPORT
+
+#include "cap.h"
+#include <stdbool.h>
+#include <sys/capability.h>
+
+bool perf_cap__capable(cap_value_t cap)
+{
+	cap_flag_value_t val;
+	cap_t caps = cap_get_proc();
+
+	if (!caps)
+		return false;
+
+	if (cap_get_flag(caps, cap, CAP_EFFECTIVE, &val) != 0)
+		val = CAP_CLEAR;
+
+	if (cap_free(caps) != 0)
+		return false;
+
+	return val == CAP_SET;
+}
+
+#endif  /* HAVE_LIBCAP_SUPPORT */
diff --git a/tools/perf/util/cap.h b/tools/perf/util/cap.h
new file mode 100644
index 000000000000..051dc590ceee
--- /dev/null
+++ b/tools/perf/util/cap.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_CAP_H
+#define __PERF_CAP_H
+
+#include <stdbool.h>
+#include <linux/capability.h>
+#include <linux/compiler.h>
+
+#ifdef HAVE_LIBCAP_SUPPORT
+
+#include <sys/capability.h>
+
+bool perf_cap__capable(cap_value_t cap);
+
+#else
+
+#include <unistd.h>
+#include <sys/types.h>
+
+static inline bool perf_cap__capable(int cap __maybe_unused)
+{
+	return geteuid() == 0;
+}
+
+#endif /* HAVE_LIBCAP_SUPPORT */
+
+/* For older systems */
+#ifndef CAP_SYSLOG
+#define CAP_SYSLOG	34
+#endif
+
+#endif /* __PERF_CAP_H */
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 71d4d7b35a57..beb3525e9e45 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -537,7 +537,10 @@ size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size)
 	unsigned char *bitmap;
 	int last_cpu = cpu_map__cpu(map, map->nr - 1);
 
-	bitmap = zalloc((last_cpu + 7) / 8);
+	if (buf == NULL)
+		return 0;
+
+	bitmap = zalloc(last_cpu / 8 + 1);
 	if (bitmap == NULL) {
 		buf[0] = '\0';
 		return 0;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 70841d115349..0e164e8ae28d 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -851,6 +851,7 @@ void  cpu_map_data__synthesize(struct cpu_map_data *data, struct perf_cpu_map *m
 void event_attr_init(struct perf_event_attr *attr);
 
 int perf_event_paranoid(void);
+bool perf_event_paranoid_check(int max_level);
 
 extern int sysctl_perf_event_max_stack;
 extern int sysctl_perf_event_max_contexts_per_stack;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 64bc32ed6dfa..0a33f7322ecc 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -833,6 +833,9 @@ static void apply_config_terms(struct evsel *evsel,
 			break;
 		case PERF_EVSEL__CONFIG_TERM_PERCORE:
 			break;
+		case PERF_EVSEL__CONFIG_TERM_AUX_OUTPUT:
+			attr->aux_output = term->val.aux_output ? 1 : 0;
+			break;
 		default:
 			break;
 		}
@@ -1587,6 +1590,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 	PRINT_ATTRf(namespaces, p_unsigned);
 	PRINT_ATTRf(ksymbol, p_unsigned);
 	PRINT_ATTRf(bpf_event, p_unsigned);
+	PRINT_ATTRf(aux_output, p_unsigned);
 
 	PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned);
 	PRINT_ATTRf(bp_type, p_unsigned);
@@ -1734,7 +1738,8 @@ int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,
 	int pid = -1, err;
 	enum { NO_CHANGE, SET_TO_MAX, INCREASED_MAX } set_rlimit = NO_CHANGE;
 
-	if (perf_missing_features.write_backward && evsel->core.attr.write_backward)
+	if ((perf_missing_features.write_backward && evsel->core.attr.write_backward) ||
+	    (perf_missing_features.aux_output     && evsel->core.attr.aux_output))
 		return -EINVAL;
 
 	if (cpus == NULL) {
@@ -1908,7 +1913,11 @@ try_fallback:
 	 * Must probe features in the order they were added to the
 	 * perf_event_attr interface.
 	 */
-	if (!perf_missing_features.bpf_event && evsel->core.attr.bpf_event) {
+	if (!perf_missing_features.aux_output && evsel->core.attr.aux_output) {
+		perf_missing_features.aux_output = true;
+		pr_debug2("Kernel has no attr.aux_output support, bailing out\n");
+		goto out_close;
+	} else if (!perf_missing_features.bpf_event && evsel->core.attr.bpf_event) {
 		perf_missing_features.bpf_event = true;
 		pr_debug2("switching off bpf_event\n");
 		goto fallback_missing_features;
@@ -2922,6 +2931,8 @@ int perf_evsel__open_strerror(struct evsel *evsel, struct target *target,
 			return scnprintf(msg, size, "clockid feature not supported.");
 		if (perf_missing_features.clockid_wrong)
 			return scnprintf(msg, size, "wrong clockid (%d).", clockid);
+		if (perf_missing_features.aux_output)
+			return scnprintf(msg, size, "The 'aux_output' feature is not supported, update the kernel.");
 		break;
 	default:
 		break;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 3cf35aa782b9..9cd6e3ae479a 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -52,6 +52,7 @@ enum term_type {
 	PERF_EVSEL__CONFIG_TERM_DRV_CFG,
 	PERF_EVSEL__CONFIG_TERM_BRANCH,
 	PERF_EVSEL__CONFIG_TERM_PERCORE,
+	PERF_EVSEL__CONFIG_TERM_AUX_OUTPUT,
 };
 
 struct perf_evsel_config_term {
@@ -70,6 +71,7 @@ struct perf_evsel_config_term {
 		char	*branch;
 		unsigned long max_events;
 		bool	percore;
+		bool	aux_output;
 	} val;
 	bool weak;
 };
@@ -182,6 +184,7 @@ struct perf_missing_features {
 	bool group_read;
 	bool ksymbol;
 	bool bpf_event;
+	bool aux_output;
 };
 
 extern struct perf_missing_features perf_missing_features;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index b04c2b6b28b3..1f2965a07bef 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2252,8 +2252,10 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 	/* On s390 the socket_id number is not related to the numbers of cpus.
 	 * The socket_id number might be higher than the numbers of cpus.
 	 * This depends on the configuration.
+	 * AArch64 is the same.
 	 */
-	if (ph->env.arch && !strncmp(ph->env.arch, "s390", 4))
+	if (ph->env.arch && (!strncmp(ph->env.arch, "s390", 4)
+			  || !strncmp(ph->env.arch, "aarch64", 7)))
 		do_core_id_test = false;
 
 	for (i = 0; i < (u32)cpu_nr; i++) {
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 4297f56b1e05..8efbf58dc3d0 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -2436,7 +2436,7 @@ void hists__match(struct hists *leader, struct hists *other)
 {
 	struct rb_root_cached *root;
 	struct rb_node *nd;
-	struct hist_entry *pos, *pair;
+	struct hist_entry *pos, *pair, *pos_pair, *tmp_pair;
 
 	if (symbol_conf.report_hierarchy) {
 		/* hierarchy report always collapses entries */
@@ -2453,8 +2453,24 @@ void hists__match(struct hists *leader, struct hists *other)
 		pos  = rb_entry(nd, struct hist_entry, rb_node_in);
 		pair = hists__find_entry(other, pos);
 
-		if (pair)
+		if (pair && list_empty(&pair->pairs.node)) {
+			list_for_each_entry_safe(pos_pair, tmp_pair, &pos->pairs.head, pairs.node) {
+				if (pos_pair->hists == other) {
+					/*
+					 * XXX maybe decayed entries can appear
+					 * here?  but then we would have use
+					 * after free, as decayed entries are
+					 * freed see hists__delete_entry
+					 */
+					BUG_ON(!pos_pair->dummy);
+					list_del_init(&pos_pair->pairs.node);
+					hist_entry__delete(pos_pair);
+					break;
+				}
+			}
+
 			hist_entry__add_pair(pair, pos);
+		}
 	}
 }
 
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 4c52204868d8..ea504fa9b623 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -2894,6 +2894,22 @@ static int intel_pt_synth_events(struct intel_pt *pt,
 	return 0;
 }
 
+static void intel_pt_setup_pebs_events(struct intel_pt *pt)
+{
+	struct evsel *evsel;
+
+	if (!pt->synth_opts.other_events)
+		return;
+
+	evlist__for_each_entry(pt->session->evlist, evsel) {
+		if (evsel->core.attr.aux_output && evsel->id) {
+			pt->sample_pebs = true;
+			pt->pebs_evsel = evsel;
+			return;
+		}
+	}
+}
+
 static struct evsel *intel_pt_find_sched_switch(struct evlist *evlist)
 {
 	struct evsel *evsel;
@@ -3263,6 +3279,8 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 	if (err)
 		goto err_delete_thread;
 
+	intel_pt_setup_pebs_events(pt);
+
 	err = auxtrace_queues__process_index(&pt->queues, session);
 	if (err)
 		goto err_delete_thread;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index f6ee7fbad3e4..5734460fc89e 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1378,6 +1378,7 @@ static int machine__set_modules_path(struct machine *machine)
 	return map_groups__set_modules_path_dir(&machine->kmaps, modules_path, 0);
 }
 int __weak arch__fix_module_text_start(u64 *start __maybe_unused,
+				u64 *size __maybe_unused,
 				const char *name __maybe_unused)
 {
 	return 0;
@@ -1389,7 +1390,7 @@ static int machine__create_module(void *arg, const char *name, u64 start,
 	struct machine *machine = arg;
 	struct map *map;
 
-	if (arch__fix_module_text_start(&start, name) < 0)
+	if (arch__fix_module_text_start(&start, &size, name) < 0)
 		return -1;
 
 	map = machine__findnew_module_map(machine, start, name);
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index ef803f08ae12..8b9d7157276d 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -222,7 +222,7 @@ struct symbol *machine__find_kernel_symbol_by_name(struct machine *machine,
 
 struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 					const char *filename);
-int arch__fix_module_text_start(u64 *start, const char *name);
+int arch__fix_module_text_start(u64 *start, u64 *size, const char *name);
 
 int machine__load_kallsyms(struct machine *machine, const char *filename);
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 2cfec3b7a982..9101568946d2 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -963,6 +963,7 @@ static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = {
 	[PARSE_EVENTS__TERM_TYPE_NOOVERWRITE]		= "no-overwrite",
 	[PARSE_EVENTS__TERM_TYPE_DRV_CFG]		= "driver-config",
 	[PARSE_EVENTS__TERM_TYPE_PERCORE]		= "percore",
+	[PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT]		= "aux-output",
 };
 
 static bool config_term_shrinked;
@@ -1083,6 +1084,9 @@ do {									   \
 			return -EINVAL;
 		}
 		break;
+	case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT:
+		CHECK_TYPE_VAL(NUM);
+		break;
 	default:
 		err->str = strdup("unknown term");
 		err->idx = term->err_term;
@@ -1133,6 +1137,7 @@ static int config_term_tracepoint(struct perf_event_attr *attr,
 	case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS:
 	case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
 	case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE:
+	case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT:
 		return config_term_common(attr, term, err);
 	default:
 		if (err) {
@@ -1225,6 +1230,9 @@ do {								\
 			ADD_CONFIG_TERM(PERCORE, percore,
 					term->val.num ? true : false);
 			break;
+		case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT:
+			ADD_CONFIG_TERM(AUX_OUTPUT, aux_output, term->val.num ? 1 : 0);
+			break;
 		default:
 			break;
 		}
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 48111b8fc232..616ca1eda0eb 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -76,6 +76,7 @@ enum {
 	PARSE_EVENTS__TERM_TYPE_OVERWRITE,
 	PARSE_EVENTS__TERM_TYPE_DRV_CFG,
 	PARSE_EVENTS__TERM_TYPE_PERCORE,
+	PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT,
 	__PARSE_EVENTS__TERM_TYPE_NR,
 };
 
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index ca6098874fe2..7469497cd28e 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -284,6 +284,7 @@ no-inherit		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOINHERIT); }
 overwrite		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_OVERWRITE); }
 no-overwrite		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOOVERWRITE); }
 percore			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_PERCORE); }
+aux-output		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT); }
 ,			{ return ','; }
 "/"			{ BEGIN(INITIAL); return '/'; }
 {name_minus}		{ return str(yyscanner, PE_NAME); }
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 235bd9803390..c6dd478956f1 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -7,6 +7,7 @@
 
 util/python.c
 ../lib/ctype.c
+util/cap.c
 util/evlist.c
 util/evsel.c
 util/cpumap.c
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 11e6093c941b..b9fe71d11bf6 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <inttypes.h>
+#include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
 #include <traceevent/event-parse.h>
@@ -1955,7 +1956,9 @@ fetch_mmaped_event(struct perf_session *session,
 		/* We're not fetching the event so swap back again */
 		if (session->header.needs_swap)
 			perf_event_header__bswap(&event->header);
-		return NULL;
+		pr_debug("%s: head=%#" PRIx64 " event->header_size=%#x, mmap_size=%#zx: fuzzed perf.data?\n",
+			 __func__, head, event->header.size, mmap_size);
+		return ERR_PTR(-EINVAL);
 	}
 
 	return event;
@@ -1973,6 +1976,9 @@ static int __perf_session__process_decomp_events(struct perf_session *session)
 	while (decomp->head < decomp->size && !session_done()) {
 		union perf_event *event = fetch_mmaped_event(session, decomp->head, decomp->size, decomp->data);
 
+		if (IS_ERR(event))
+			return PTR_ERR(event);
+
 		if (!event)
 			break;
 
@@ -2072,6 +2078,9 @@ remap:
 
 more:
 	event = fetch_mmaped_event(session, head, mmap_size, buf);
+	if (IS_ERR(event))
+		return PTR_ERR(event);
+
 	if (!event) {
 		if (mmaps[map_idx]) {
 			munmap(mmaps[map_idx], mmap_size);
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index d48f9cd58964..aa344a163eaf 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -59,6 +59,8 @@ ext_sources = list(map(lambda x: '%s/%s' % (src_perf, x) , ext_sources))
 extra_libraries = []
 if '-DHAVE_LIBNUMA_SUPPORT' in cflags:
     extra_libraries = [ 'numa' ]
+if '-DHAVE_LIBCAP_SUPPORT' in cflags:
+    extra_libraries += [ 'cap' ]
 
 perf = Extension('perf',
 		  sources = ext_sources,
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 173f3378aaa0..4efde7879474 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -92,6 +92,11 @@ static int prefix_underscores_count(const char *str)
 	return tail - str;
 }
 
+void __weak arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
+{
+	p->end = c->start;
+}
+
 const char * __weak arch__normalize_symbol_name(const char *name)
 {
 	return name;
@@ -218,7 +223,7 @@ void symbols__fixup_end(struct rb_root_cached *symbols)
 		curr = rb_entry(nd, struct symbol, rb_node);
 
 		if (prev->end == prev->start && prev->end != curr->start)
-			prev->end = curr->start;
+			arch__symbols__fixup_end(prev, curr);
 	}
 
 	/* Last entry */
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 12755b42ea93..183f630cb5f1 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -288,6 +288,7 @@ const char *arch__normalize_symbol_name(const char *name);
 #define SYMBOL_A 0
 #define SYMBOL_B 1
 
+void arch__symbols__fixup_end(struct symbol *p, struct symbol *c);
 int arch__compare_symbol_names(const char *namea, const char *nameb);
 int arch__compare_symbol_names_n(const char *namea, const char *nameb,
 				 unsigned int n);
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 873ab505ca80..590793cc5142 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -214,14 +214,24 @@ struct comm *thread__comm(const struct thread *thread)
 
 struct comm *thread__exec_comm(const struct thread *thread)
 {
-	struct comm *comm, *last = NULL;
+	struct comm *comm, *last = NULL, *second_last = NULL;
 
 	list_for_each_entry(comm, &thread->comm_list, list) {
 		if (comm->exec)
 			return comm;
+		second_last = last;
 		last = comm;
 	}
 
+	/*
+	 * 'last' with no start time might be the parent's comm of a synthesized
+	 * thread (created by processing a synthesized fork event). For a main
+	 * thread, that is very probably wrong. Prefer a later comm to avoid
+	 * that case.
+	 */
+	if (second_last && !last->start && thread->pid_ == thread->tid)
+		return second_last;
+
 	return last;
 }
 
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 9c3c97697387..6fd130a5d8f2 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -16,10 +16,12 @@
 #include <string.h>
 #include <errno.h>
 #include <limits.h>
+#include <linux/capability.h>
 #include <linux/kernel.h>
 #include <linux/log2.h>
 #include <linux/time64.h>
 #include <unistd.h>
+#include "cap.h"
 #include "strlist.h"
 #include "string2.h"
 
@@ -403,6 +405,13 @@ int perf_event_paranoid(void)
 
 	return value;
 }
+
+bool perf_event_paranoid_check(int max_level)
+{
+	return perf_cap__capable(CAP_SYS_ADMIN) ||
+			perf_event_paranoid() <= max_level;
+}
+
 static int
 fetch_ubuntu_kernel_version(unsigned int *puint)
 {