1 files changed, 238 insertions, 139 deletions

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index f0dd174e2deb..ee971d15b3c6 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -13,6 +13,7 @@
 #include "util/mmap.h"
 #include "thread_map.h"
 #include "target.h"
+#include "dwarf-regs.h"
 #include "evlist.h"
 #include "evsel.h"
 #include "record.h"
@@ -35,6 +36,8 @@
 #include "util/util.h"
 #include "util/env.h"
 #include "util/intel-tpebs.h"
+#include "util/metricgroup.h"
+#include "util/strbuf.h"
 #include <signal.h>
 #include <unistd.h>
 #include <sched.h>
@@ -82,6 +85,8 @@ void evlist__init(struct evlist *evlist, struct perf_cpu_map *cpus,
 	evlist->ctl_fd.ack = -1;
 	evlist->ctl_fd.pos = -1;
 	evlist->nr_br_cntr = -1;
+	metricgroup__rblist_init(&evlist->metric_events);
+	INIT_LIST_HEAD(&evlist->deferred_samples);
 }
 
 struct evlist *evlist__new(void)
@@ -94,30 +99,47 @@ struct evlist *evlist__new(void)
 	return evlist;
 }
 
-struct evlist *evlist__new_default(void)
+struct evlist *evlist__new_default(const struct target *target, bool sample_callchains)
 {
 	struct evlist *evlist = evlist__new();
 	bool can_profile_kernel;
+	struct perf_pmu *pmu = NULL;
+	struct evsel *evsel;
+	char buf[256];
 	int err;
 
 	if (!evlist)
 		return NULL;
 
 	can_profile_kernel = perf_event_paranoid_check(1);
-	err = parse_event(evlist, can_profile_kernel ? "cycles:P" : "cycles:Pu");
-	if (err) {
-		evlist__delete(evlist);
-		return NULL;
+
+	if (EM_HOST == EM_S390 && sample_callchains) {
+		snprintf(buf, sizeof(buf), "software/%s/%s",
+			 target__has_cpu(target) ? "cpu-clock" : "task-clock",
+			 can_profile_kernel ? "P" : "Pu");
+		err = parse_event(evlist, buf);
+		if (err)
+			goto out_err;
+	} else {
+		while ((pmu = perf_pmus__scan_core(pmu)) != NULL) {
+			snprintf(buf, sizeof(buf), "%s/cycles/%s", pmu->name,
+				can_profile_kernel ? "P" : "Pu");
+			err = parse_event(evlist, buf);
+			if (err)
+				goto out_err;
+		}
 	}
 
+	/* If there is only 1 event a sample identifier isn't necessary. */
 	if (evlist->core.nr_entries > 1) {
-		struct evsel *evsel;
-
 		evlist__for_each_entry(evlist, evsel)
 			evsel__set_sample_id(evsel, /*can_sample_identifier=*/false);
 	}
 
 	return evlist;
+out_err:
+	evlist__delete(evlist);
+	return NULL;
 }
 
 struct evlist *evlist__new_dummy(void)
@@ -172,6 +194,7 @@ static void evlist__purge(struct evlist *evlist)
 
 void evlist__exit(struct evlist *evlist)
 {
+	metricgroup__rblist_exit(&evlist->metric_events);
 	event_enable_timer__exit(&evlist->eet);
 	zfree(&evlist->mmap);
 	zfree(&evlist->overwrite_mmap);
@@ -183,7 +206,6 @@ void evlist__delete(struct evlist *evlist)
 	if (evlist == NULL)
 		return;
 
-	tpebs_delete();
 	evlist__free_stats(evlist);
 	evlist__munmap(evlist);
 	evlist__close(evlist);
@@ -347,36 +369,107 @@ int evlist__add_newtp(struct evlist *evlist, const char *sys, const char *name,
 }
 #endif
 
-struct evlist_cpu_iterator evlist__cpu_begin(struct evlist *evlist, struct affinity *affinity)
+/*
+ * Should sched_setaffinity be used with evlist__for_each_cpu? Determine if
+ * migrating the thread will avoid possibly numerous IPIs.
+ */
+static bool evlist__use_affinity(struct evlist *evlist)
 {
-	struct evlist_cpu_iterator itr = {
+	struct evsel *pos;
+	struct perf_cpu_map *used_cpus = NULL;
+	bool ret = false;
+
+	if (evlist->no_affinity || !evlist->core.user_requested_cpus ||
+	    cpu_map__is_dummy(evlist->core.user_requested_cpus))
+		return false;
+
+	evlist__for_each_entry(evlist, pos) {
+		struct perf_cpu_map *intersect;
+
+		if (!perf_pmu__benefits_from_affinity(pos->pmu))
+			continue;
+
+		if (evsel__is_dummy_event(pos)) {
+			/*
+			 * The dummy event is opened on all CPUs so assume >1
+			 * event with shared CPUs.
+			 */
+			ret = true;
+			break;
+		}
+		if (evsel__is_retire_lat(pos)) {
+			/*
+			 * Retirement latency events are similar to tool ones in
+			 * their implementation, and so don't require affinity.
+			 */
+			continue;
+		}
+		if (perf_cpu_map__is_empty(used_cpus)) {
+			/* First benefitting event, we want >1 on a common CPU. */
+			used_cpus = perf_cpu_map__get(pos->core.cpus);
+			continue;
+		}
+		if ((pos->core.attr.read_format & PERF_FORMAT_GROUP) &&
+		    evsel__leader(pos) != pos) {
+			/* Skip members of the same sample group. */
+			continue;
+		}
+		intersect = perf_cpu_map__intersect(used_cpus, pos->core.cpus);
+		if (!perf_cpu_map__is_empty(intersect)) {
+			/* >1 event with shared CPUs. */
+			perf_cpu_map__put(intersect);
+			ret = true;
+			break;
+		}
+		perf_cpu_map__put(intersect);
+		perf_cpu_map__merge(&used_cpus, pos->core.cpus);
+	}
+	perf_cpu_map__put(used_cpus);
+	return ret;
+}
+
+void evlist_cpu_iterator__init(struct evlist_cpu_iterator *itr, struct evlist *evlist)
+{
+	*itr = (struct evlist_cpu_iterator){
 		.container = evlist,
 		.evsel = NULL,
 		.cpu_map_idx = 0,
 		.evlist_cpu_map_idx = 0,
 		.evlist_cpu_map_nr = perf_cpu_map__nr(evlist->core.all_cpus),
 		.cpu = (struct perf_cpu){ .cpu = -1},
-		.affinity = affinity,
+		.affinity = NULL,
 	};
 
 	if (evlist__empty(evlist)) {
 		/* Ensure the empty list doesn't iterate. */
-		itr.evlist_cpu_map_idx = itr.evlist_cpu_map_nr;
-	} else {
-		itr.evsel = evlist__first(evlist);
-		if (itr.affinity) {
-			itr.cpu = perf_cpu_map__cpu(evlist->core.all_cpus, 0);
-			affinity__set(itr.affinity, itr.cpu.cpu);
-			itr.cpu_map_idx = perf_cpu_map__idx(itr.evsel->core.cpus, itr.cpu);
-			/*
-			 * If this CPU isn't in the evsel's cpu map then advance
-			 * through the list.
-			 */
-			if (itr.cpu_map_idx == -1)
-				evlist_cpu_iterator__next(&itr);
-		}
+		itr->evlist_cpu_map_idx = itr->evlist_cpu_map_nr;
+		return;
+	}
+
+	if (evlist__use_affinity(evlist)) {
+		if (affinity__setup(&itr->saved_affinity) == 0)
+			itr->affinity = &itr->saved_affinity;
 	}
-	return itr;
+	itr->evsel = evlist__first(evlist);
+	itr->cpu = perf_cpu_map__cpu(evlist->core.all_cpus, 0);
+	if (itr->affinity)
+		affinity__set(itr->affinity, itr->cpu.cpu);
+	itr->cpu_map_idx = perf_cpu_map__idx(itr->evsel->core.cpus, itr->cpu);
+	/*
+	 * If this CPU isn't in the evsel's cpu map then advance
+	 * through the list.
+	 */
+	if (itr->cpu_map_idx == -1)
+		evlist_cpu_iterator__next(itr);
+}
+
+void evlist_cpu_iterator__exit(struct evlist_cpu_iterator *itr)
+{
+	if (!itr->affinity)
+		return;
+
+	affinity__cleanup(itr->affinity);
+	itr->affinity = NULL;
 }
 
 void evlist_cpu_iterator__next(struct evlist_cpu_iterator *evlist_cpu_itr)
@@ -406,14 +499,11 @@ void evlist_cpu_iterator__next(struct evlist_cpu_iterator *evlist_cpu_itr)
 		 */
 		if (evlist_cpu_itr->cpu_map_idx == -1)
 			evlist_cpu_iterator__next(evlist_cpu_itr);
+	} else {
+		evlist_cpu_iterator__exit(evlist_cpu_itr);
 	}
 }
 
-bool evlist_cpu_iterator__end(const struct evlist_cpu_iterator *evlist_cpu_itr)
-{
-	return evlist_cpu_itr->evlist_cpu_map_idx >= evlist_cpu_itr->evlist_cpu_map_nr;
-}
-
 static int evsel__strcmp(struct evsel *pos, char *evsel_name)
 {
 	if (!evsel_name)
@@ -441,19 +531,11 @@ static void __evlist__disable(struct evlist *evlist, char *evsel_name, bool excl
 {
 	struct evsel *pos;
 	struct evlist_cpu_iterator evlist_cpu_itr;
-	struct affinity saved_affinity, *affinity = NULL;
 	bool has_imm = false;
 
-	// See explanation in evlist__close()
-	if (!cpu_map__is_dummy(evlist->core.user_requested_cpus)) {
-		if (affinity__setup(&saved_affinity) < 0)
-			return;
-		affinity = &saved_affinity;
-	}
-
 	/* Disable 'immediate' events last */
 	for (int imm = 0; imm <= 1; imm++) {
-		evlist__for_each_cpu(evlist_cpu_itr, evlist, affinity) {
+		evlist__for_each_cpu(evlist_cpu_itr, evlist) {
 			pos = evlist_cpu_itr.evsel;
 			if (evsel__strcmp(pos, evsel_name))
 				continue;
@@ -471,7 +553,6 @@ static void __evlist__disable(struct evlist *evlist, char *evsel_name, bool excl
 			break;
 	}
 
-	affinity__cleanup(affinity);
 	evlist__for_each_entry(evlist, pos) {
 		if (evsel__strcmp(pos, evsel_name))
 			continue;
@@ -511,16 +592,8 @@ static void __evlist__enable(struct evlist *evlist, char *evsel_name, bool excl_
 {
 	struct evsel *pos;
 	struct evlist_cpu_iterator evlist_cpu_itr;
-	struct affinity saved_affinity, *affinity = NULL;
-
-	// See explanation in evlist__close()
-	if (!cpu_map__is_dummy(evlist->core.user_requested_cpus)) {
-		if (affinity__setup(&saved_affinity) < 0)
-			return;
-		affinity = &saved_affinity;
-	}
 
-	evlist__for_each_cpu(evlist_cpu_itr, evlist, affinity) {
+	evlist__for_each_cpu(evlist_cpu_itr, evlist) {
 		pos = evlist_cpu_itr.evsel;
 		if (evsel__strcmp(pos, evsel_name))
 			continue;
@@ -530,7 +603,6 @@ static void __evlist__enable(struct evlist *evlist, char *evsel_name, bool excl_
 			continue;
 		evsel__enable_cpu(pos, evlist_cpu_itr.cpu_map_idx);
 	}
-	affinity__cleanup(affinity);
 	evlist__for_each_entry(evlist, pos) {
 		if (evsel__strcmp(pos, evsel_name))
 			continue;
@@ -753,9 +825,8 @@ static struct mmap *evlist__alloc_mmap(struct evlist *evlist,
 				       bool overwrite)
 {
 	int i;
-	struct mmap *map;
+	struct mmap *map = calloc(evlist->core.nr_mmaps, sizeof(struct mmap));
 
-	map = zalloc(evlist->core.nr_mmaps * sizeof(struct mmap));
 	if (!map)
 		return NULL;
 
@@ -1006,8 +1077,7 @@ int evlist__create_maps(struct evlist *evlist, struct target *target)
 	 * per-thread data. thread_map__new_str will call
 	 * thread_map__new_all_cpus to enumerate all threads.
 	 */
-	threads = thread_map__new_str(target->pid, target->tid, target->uid,
-				      all_threads);
+	threads = thread_map__new_str(target->pid, target->tid, all_threads);
 
 	if (!threads)
 		return -1;
@@ -1328,28 +1398,14 @@ void evlist__close(struct evlist *evlist)
 {
 	struct evsel *evsel;
 	struct evlist_cpu_iterator evlist_cpu_itr;
-	struct affinity affinity;
 
-	/*
-	 * With perf record core.user_requested_cpus is usually NULL.
-	 * Use the old method to handle this for now.
-	 */
-	if (!evlist->core.user_requested_cpus ||
-	    cpu_map__is_dummy(evlist->core.user_requested_cpus)) {
-		evlist__for_each_entry_reverse(evlist, evsel)
-			evsel__close(evsel);
-		return;
-	}
-
-	if (affinity__setup(&affinity) < 0)
-		return;
-
-	evlist__for_each_cpu(evlist_cpu_itr, evlist, &affinity) {
+	evlist__for_each_cpu(evlist_cpu_itr, evlist) {
+		if (evlist_cpu_itr.cpu_map_idx == 0 && evsel__is_retire_lat(evlist_cpu_itr.evsel))
+			evsel__tpebs_close(evlist_cpu_itr.evsel);
 		perf_evsel__close_cpu(&evlist_cpu_itr.evsel->core,
 				      evlist_cpu_itr.cpu_map_idx);
 	}
 
-	affinity__cleanup(&affinity);
 	evlist__for_each_entry_reverse(evlist, evsel) {
 		perf_evsel__free_fd(&evsel->core);
 		perf_evsel__free_id(&evsel->core);
@@ -1373,19 +1429,18 @@ static int evlist__create_syswide_maps(struct evlist *evlist)
 	 */
 	cpus = perf_cpu_map__new_online_cpus();
 	if (!cpus)
-		goto out;
+		return -ENOMEM;
 
 	threads = perf_thread_map__new_dummy();
-	if (!threads)
-		goto out_put;
+	if (!threads) {
+		perf_cpu_map__put(cpus);
+		return -ENOMEM;
+	}
 
 	perf_evlist__set_maps(&evlist->core, cpus, threads);
-
 	perf_thread_map__put(threads);
-out_put:
 	perf_cpu_map__put(cpus);
-out:
-	return -ENOMEM;
+	return 0;
 }
 
 int evlist__open(struct evlist *evlist)
@@ -1576,8 +1631,11 @@ int evlist__parse_sample(struct evlist *evlist, union perf_event *event, struct
 	struct evsel *evsel = evlist__event2evsel(evlist, event);
 	int ret;
 
-	if (!evsel)
+	if (!evsel) {
+		/* Ensure the sample is okay for perf_sample__exit. */
+		perf_sample__init(sample, /*all=*/false);
 		return -EFAULT;
+	}
 	ret = evsel__parse_sample(evsel, event, sample);
 	if (ret)
 		return ret;
@@ -1604,14 +1662,14 @@ int evlist__parse_sample_timestamp(struct evlist *evlist, union perf_event *even
 int evlist__strerror_open(struct evlist *evlist, int err, char *buf, size_t size)
 {
 	int printed, value;
-	char sbuf[STRERR_BUFSIZE], *emsg = str_error_r(err, sbuf, sizeof(sbuf));
 
 	switch (err) {
 	case EACCES:
 	case EPERM:
+		errno = err;
 		printed = scnprintf(buf, size,
-				    "Error:\t%s.\n"
-				    "Hint:\tCheck /proc/sys/kernel/perf_event_paranoid setting.", emsg);
+				    "Error:\t%m.\n"
+				    "Hint:\tCheck /proc/sys/kernel/perf_event_paranoid setting.");
 
 		value = perf_event_paranoid();
 
@@ -1638,16 +1696,18 @@ int evlist__strerror_open(struct evlist *evlist, int err, char *buf, size_t size
 		if (first->core.attr.sample_freq < (u64)max_freq)
 			goto out_default;
 
+		errno = err;
 		printed = scnprintf(buf, size,
-				    "Error:\t%s.\n"
+				    "Error:\t%m.\n"
 				    "Hint:\tCheck /proc/sys/kernel/perf_event_max_sample_rate.\n"
 				    "Hint:\tThe current value is %d and %" PRIu64 " is being requested.",
-				    emsg, max_freq, first->core.attr.sample_freq);
+				    max_freq, first->core.attr.sample_freq);
 		break;
 	}
 	default:
 out_default:
-		scnprintf(buf, size, "%s", emsg);
+		errno = err;
+		scnprintf(buf, size, "%m");
 		break;
 	}
 
@@ -1656,17 +1716,17 @@ out_default:
 
 int evlist__strerror_mmap(struct evlist *evlist, int err, char *buf, size_t size)
 {
-	char sbuf[STRERR_BUFSIZE], *emsg = str_error_r(err, sbuf, sizeof(sbuf));
 	int pages_attempted = evlist->core.mmap_len / 1024, pages_max_per_user, printed = 0;
 
 	switch (err) {
 	case EPERM:
 		sysctl__read_int("kernel/perf_event_mlock_kb", &pages_max_per_user);
+		errno = err;
 		printed += scnprintf(buf + printed, size - printed,
-				     "Error:\t%s.\n"
+				     "Error:\t%m.\n"
 				     "Hint:\tCheck /proc/sys/kernel/perf_event_mlock_kb (%d kB) setting.\n"
 				     "Hint:\tTried using %zd kB.\n",
-				     emsg, pages_max_per_user, pages_attempted);
+				     pages_max_per_user, pages_attempted);
 
 		if (pages_attempted >= pages_max_per_user) {
 			printed += scnprintf(buf + printed, size - printed,
@@ -1678,7 +1738,8 @@ int evlist__strerror_mmap(struct evlist *evlist, int err, char *buf, size_t size
 				     "Hint:\tTry using a smaller -m/--mmap-pages value.");
 		break;
 	default:
-		scnprintf(buf, size, "%s", emsg);
+		errno = err;
+		scnprintf(buf, size, "%m");
 		break;
 	}
 
@@ -1910,8 +1971,8 @@ static int evlist__parse_control_fifo(const char *str, int *ctl_fd, int *ctl_fd_
 	 */
 	fd = open(s, O_RDWR | O_NONBLOCK | O_CLOEXEC);
 	if (fd < 0) {
-		pr_err("Failed to open '%s'\n", s);
 		ret = -errno;
+		pr_err("Failed to open '%s': %m\n", s);
 		goto out_free;
 	}
 	*ctl_fd = fd;
@@ -1921,7 +1982,7 @@ static int evlist__parse_control_fifo(const char *str, int *ctl_fd, int *ctl_fd_
 		/* O_RDWR | O_NONBLOCK means the other end need not be open */
 		fd = open(p, O_RDWR | O_NONBLOCK | O_CLOEXEC);
 		if (fd < 0) {
-			pr_err("Failed to open '%s'\n", p);
+			pr_err("Failed to open '%s': %m\n", p);
 			ret = -errno;
 			goto out_free;
 		}
@@ -1935,7 +1996,8 @@ out_free:
 
 int evlist__parse_control(const char *str, int *ctl_fd, int *ctl_fd_ack, bool *ctl_fd_close)
 {
-	char *comma = NULL, *endptr = NULL;
+	const char *comma = NULL;
+	char *endptr = NULL;
 
 	*ctl_fd_close = false;
 
@@ -2353,7 +2415,7 @@ int evlist__parse_event_enable_time(struct evlist *evlist, struct record_opts *o
 	eet->timerfd = timerfd_create(CLOCK_MONOTONIC, TFD_CLOEXEC);
 	if (eet->timerfd == -1) {
 		err = -errno;
-		pr_err("timerfd_create failed: %s\n", strerror(errno));
+		pr_err("timerfd_create failed: %m\n");
 		goto free_eet_times;
 	}
 
@@ -2388,7 +2450,7 @@ static int event_enable_timer__set_timer(struct event_enable_timer *eet, int ms)
 
 	if (timerfd_settime(eet->timerfd, 0, &its, NULL) < 0) {
 		err = -errno;
-		pr_err("timerfd_settime failed: %s\n", strerror(errno));
+		pr_err("timerfd_settime failed: %m\n");
 	}
 	return err;
 }
@@ -2469,23 +2531,36 @@ struct evsel *evlist__find_evsel(struct evlist *evlist, int idx)
 	return NULL;
 }
 
-int evlist__scnprintf_evsels(struct evlist *evlist, size_t size, char *bf)
+void evlist__format_evsels(struct evlist *evlist, struct strbuf *sb, size_t max_length)
 {
-	struct evsel *evsel;
-	int printed = 0;
+	struct evsel *evsel, *leader = NULL;
+	bool first = true;
 
 	evlist__for_each_entry(evlist, evsel) {
+		struct evsel *new_leader = evsel__leader(evsel);
+
 		if (evsel__is_dummy_event(evsel))
 			continue;
-		if (size > (strlen(evsel__name(evsel)) + (printed ? 2 : 1))) {
-			printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "," : "", evsel__name(evsel));
-		} else {
-			printed += scnprintf(bf + printed, size - printed, "%s...", printed ? "," : "");
-			break;
+
+		if (leader != new_leader && leader && leader->core.nr_members > 1)
+			strbuf_addch(sb, '}');
+
+		if (!first)
+			strbuf_addch(sb, ',');
+
+		if (sb->len > max_length) {
+			strbuf_addstr(sb, "...");
+			return;
 		}
-	}
+		if (leader != new_leader && new_leader->core.nr_members > 1)
+			strbuf_addch(sb, '{');
 
-	return printed;
+		strbuf_addstr(sb, evsel__name(evsel));
+		first = false;
+		leader = new_leader;
+	}
+	if (leader && leader->core.nr_members > 1)
+		strbuf_addch(sb, '}');
 }
 
 void evlist__check_mem_load_aux(struct evlist *evlist)
@@ -2535,51 +2610,61 @@ void evlist__warn_user_requested_cpus(struct evlist *evlist, const char *cpu_lis
 		return;
 
 	evlist__for_each_entry(evlist, pos) {
-		struct perf_cpu_map *intersect, *to_test;
-		const struct perf_pmu *pmu = evsel__find_pmu(pos);
+		evsel__warn_user_requested_cpus(pos, user_requested_cpus);
+	}
+	perf_cpu_map__put(user_requested_cpus);
+}
 
-		to_test = pmu && pmu->is_core ? pmu->cpus : cpu_map__online();
-		intersect = perf_cpu_map__intersect(to_test, user_requested_cpus);
-		if (!perf_cpu_map__equal(intersect, user_requested_cpus)) {
-			char buf[128];
+/* Should uniquify be disabled for the evlist? */
+static bool evlist__disable_uniquify(const struct evlist *evlist)
+{
+	struct evsel *counter;
+	struct perf_pmu *last_pmu = NULL;
+	bool first = true;
 
-			cpu_map__snprint(to_test, buf, sizeof(buf));
-			pr_warning("WARNING: A requested CPU in '%s' is not supported by PMU '%s' (CPUs %s) for event '%s'\n",
-				cpu_list, pmu ? pmu->name : "cpu", buf, evsel__name(pos));
+	evlist__for_each_entry(evlist, counter) {
+		/* If PMUs vary then uniquify can be useful. */
+		if (!first && counter->pmu != last_pmu)
+			return false;
+		first = false;
+		if (counter->pmu) {
+			/* Allow uniquify for uncore PMUs. */
+			if (!counter->pmu->is_core)
+				return false;
+			/* Keep hybrid event names uniquified for clarity. */
+			if (perf_pmus__num_core_pmus() > 1)
+				return false;
 		}
-		perf_cpu_map__put(intersect);
+		last_pmu = counter->pmu;
 	}
-	perf_cpu_map__put(user_requested_cpus);
+	return true;
 }
 
-void evlist__uniquify_name(struct evlist *evlist)
+static bool evlist__set_needs_uniquify(struct evlist *evlist, const struct perf_stat_config *config)
 {
-	char *new_name, empty_attributes[2] = ":", *attributes;
-	struct evsel *pos;
-
-	if (perf_pmus__num_core_pmus() == 1)
-		return;
+	struct evsel *counter;
+	bool needs_uniquify = false;
 
-	evlist__for_each_entry(evlist, pos) {
-		if (!evsel__is_hybrid(pos))
-			continue;
+	if (evlist__disable_uniquify(evlist)) {
+		evlist__for_each_entry(evlist, counter)
+			counter->uniquified_name = true;
+		return false;
+	}
 
-		if (strchr(pos->name, '/'))
-			continue;
+	evlist__for_each_entry(evlist, counter) {
+		if (evsel__set_needs_uniquify(counter, config))
+			needs_uniquify = true;
+	}
+	return needs_uniquify;
+}
 
-		attributes = strchr(pos->name, ':');
-		if (attributes)
-			*attributes = '\0';
-		else
-			attributes = empty_attributes;
+void evlist__uniquify_evsel_names(struct evlist *evlist, const struct perf_stat_config *config)
+{
+	if (evlist__set_needs_uniquify(evlist, config)) {
+		struct evsel *pos;
 
-		if (asprintf(&new_name, "%s/%s/%s", pos->pmu ? pos->pmu->name : "",
-			     pos->name, attributes + 1)) {
-			free(pos->name);
-			pos->name = new_name;
-		} else {
-			*attributes = ':';
-		}
+		evlist__for_each_entry(evlist, pos)
+			evsel__uniquify_counter(pos);
 	}
 }
 
@@ -2594,3 +2679,17 @@ bool evlist__has_bpf_output(struct evlist *evlist)
 
 	return false;
 }
+
+bool evlist__needs_bpf_sb_event(struct evlist *evlist)
+{
+	struct evsel *evsel;
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (evsel__is_dummy_event(evsel))
+			continue;
+		if (!evsel->core.attr.exclude_kernel)
+			return true;
+	}
+
+	return false;
+}