perf/core improvements and fixes

index 5dd9b5ea314d..2e2aa6c86107 100644
@@ -153,7 +153,7 @@ void close_cgroup(struct cgroup_sel *cgrp)
 	}
 }
 
-int parse_cgroups(const struct option *opt __maybe_unused, const char *str,
+int parse_cgroups(const struct option *opt, const char *str,
 		  int unset __maybe_unused)
 {
 	struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;

index 2e2aa6c86107..6ce291f45f2d 100644
@@ -93,7 +93,7 @@ static int open_cgroup(char *name)
 static int add_cgroup(struct perf_evlist *evlist, char *str)
 {
 	struct perf_evsel *counter;
-	struct cgroup_sel *cgrp = NULL;
+	struct cgroup *cgrp = NULL;
 	int n;
 	/*
 	 * check if cgrp is already defined, if so we reuse it

@@ -144,7 +144,7 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
 	return 0;
 }
 
-void close_cgroup(struct cgroup_sel *cgrp)
+void close_cgroup(struct cgroup *cgrp)
 {
 	if (cgrp && refcount_dec_and_test(&cgrp->refcnt)) {
 		close(cgrp->fd);

@@ -158,7 +158,7 @@ int parse_cgroups(const struct option *opt, const char *str,
 {
 	struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
 	struct perf_evsel *counter;
-	struct cgroup_sel *cgrp = NULL;
+	struct cgroup *cgrp = NULL;
 	const char *p, *e, *eos = str + strlen(str);
 	char *s;
 	int ret, i;

index afafc87e9201..934daa8e4c19 100644
@@ -6,7 +6,7 @@
 
 struct option;
 
-struct cgroup_sel {
+struct cgroup {
 	char *name;
 	int fd;
 	refcount_t refcnt;

@@ -14,7 +14,8 @@ struct cgroup_sel {
 
 
 extern int nr_cgroups; /* number of explicit cgroups defined */
-void close_cgroup(struct cgroup_sel *cgrp);
+void close_cgroup(struct cgroup *cgrp);
+
 int parse_cgroups(const struct option *opt, const char *str, int unset);
 
 #endif /* __CGROUP_H__ */

index a7487c6d1866..92ba001b627f 100644
@@ -30,7 +30,7 @@ struct perf_sample_id {
 	u64			period;
 };
 
-struct cgroup_sel;
+struct cgroup;
 
 /*
  * The 'struct perf_evsel_config_term' is used to pass event

@@ -107,7 +107,7 @@ struct perf_evsel {
 	struct perf_stat_evsel  *stats;
 	void			*priv;
 	u64			db_id;
-	struct cgroup_sel	*cgrp;
+	struct cgroup		*cgrp;
 	void			*handler;
 	struct cpu_map		*cpus;
 	struct cpu_map		*own_cpus;

index 6ce291f45f2d..4dd52feb1ae6 100644
@@ -144,12 +144,17 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
 	return 0;
 }
 
+static void cgroup__delete(struct cgroup *cgroup)
+{
+	close(cgroup->fd);
+	zfree(&cgroup->name);
+	free(cgroup);
+}
+
 void close_cgroup(struct cgroup *cgrp)
 {
 	if (cgrp && refcount_dec_and_test(&cgrp->refcnt)) {
-		close(cgrp->fd);
-		zfree(&cgrp->name);
-		free(cgrp);
+		cgroup__delete(cgrp);
 	}
 }
 

index 4dd52feb1ae6..b078d54d4245 100644
@@ -135,9 +135,8 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
 			goto found;
 		n++;
 	}
-	if (refcount_dec_and_test(&cgrp->refcnt))
-		free(cgrp);
 
+	cgroup__put(cgrp);
 	return -1;
 found:
 	counter->cgrp = cgrp;

@@ -151,7 +150,7 @@ static void cgroup__delete(struct cgroup *cgroup)
 	free(cgroup);
 }
 
-void close_cgroup(struct cgroup *cgrp)
+void cgroup__put(struct cgroup *cgrp)
 {
 	if (cgrp && refcount_dec_and_test(&cgrp->refcnt)) {
 		cgroup__delete(cgrp);

index 934daa8e4c19..69169fbf8d13 100644
@@ -14,7 +14,8 @@ struct cgroup {
 
 
 extern int nr_cgroups; /* number of explicit cgroups defined */
-void close_cgroup(struct cgroup *cgrp);
+
+void cgroup__put(struct cgroup *cgroup);
 
 int parse_cgroups(const struct option *opt, const char *str, int unset);
 

index b56e1c2ddaee..f1f883bb41a8 100644
@@ -1233,7 +1233,7 @@ void perf_evsel__exit(struct perf_evsel *evsel)
 	perf_evsel__free_fd(evsel);
 	perf_evsel__free_id(evsel);
 	perf_evsel__free_config_terms(evsel);
-	close_cgroup(evsel->cgrp);
+	cgroup__put(evsel->cgrp);
 	cpu_map__put(evsel->cpus);
 	cpu_map__put(evsel->own_cpus);
 	thread_map__put(evsel->threads);

index b078d54d4245..8ea964461eb7 100644
@@ -99,15 +99,12 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
 	 * check if cgrp is already defined, if so we reuse it
 	 */
 	evlist__for_each_entry(evlist, counter) {
-		cgrp = counter->cgrp;
-		if (!cgrp)
+		if (!counter->cgrp)
 			continue;
-		if (!strcmp(cgrp->name, str)) {
-			refcount_inc(&cgrp->refcnt);
+		if (!strcmp(counter->cgrp->name, str)) {
+			cgrp = cgroup__get(counter->cgrp);
 			break;
 		}
-
-		cgrp = NULL;
 	}
 
 	if (!cgrp) {

@@ -157,6 +154,13 @@ void cgroup__put(struct cgroup *cgrp)
 	}
 }
 
+struct cgroup *cgroup__get(struct cgroup *cgroup)
+{
+       if (cgroup)
+		refcount_inc(&cgroup->refcnt);
+       return cgroup;
+}
+
 int parse_cgroups(const struct option *opt, const char *str,
 		  int unset __maybe_unused)
 {

index 69169fbf8d13..34a6c11543dc 100644
@@ -15,6 +15,7 @@ struct cgroup {
 
 extern int nr_cgroups; /* number of explicit cgroups defined */
 
+struct cgroup *cgroup__get(struct cgroup *cgroup);
 void cgroup__put(struct cgroup *cgroup);
 
 int parse_cgroups(const struct option *opt, const char *str, int unset);

index 8ea964461eb7..84dfc34a6d0f 100644
@@ -90,11 +90,10 @@ static int open_cgroup(char *name)
 	return fd;
 }
 
-static int add_cgroup(struct perf_evlist *evlist, char *str)
+static struct cgroup *evlist__find_cgroup(struct perf_evlist *evlist, char *str)
 {
 	struct perf_evsel *counter;
 	struct cgroup *cgrp = NULL;
-	int n;
 	/*
 	 * check if cgrp is already defined, if so we reuse it
 	 */

@@ -107,6 +106,15 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
 		}
 	}
 
+	return cgrp;
+}
+
+static int add_cgroup(struct perf_evlist *evlist, char *str)
+{
+	struct perf_evsel *counter;
+	struct cgroup *cgrp = evlist__find_cgroup(evlist, str);
+	int n;
+
 	if (!cgrp) {
 		cgrp = zalloc(sizeof(*cgrp));
 		if (!cgrp)

index 84dfc34a6d0f..26a837037797 100644
@@ -109,6 +109,25 @@ static struct cgroup *evlist__find_cgroup(struct perf_evlist *evlist, char *str)
 	return cgrp;
 }
 
+static struct cgroup *cgroup__new(char *name)
+{
+	struct cgroup *cgroup = zalloc(sizeof(*cgroup));
+
+	if (cgroup != NULL) {
+		cgroup->name = name;
+		refcount_set(&cgroup->refcnt, 1);
+
+		cgroup->fd = open_cgroup(name);
+		if (cgroup->fd == -1)
+			goto out_err;
+	}
+
+	return cgroup;
+out_err:
+	free(cgroup);
+	return NULL;
+}
+
 static int add_cgroup(struct perf_evlist *evlist, char *str)
 {
 	struct perf_evsel *counter;

@@ -116,18 +135,9 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
 	int n;
 
 	if (!cgrp) {
-		cgrp = zalloc(sizeof(*cgrp));
+		cgrp = cgroup__new(str);
 		if (!cgrp)
 			return -1;
-
-		cgrp->name = str;
-		refcount_set(&cgrp->refcnt, 1);
-
-		cgrp->fd = open_cgroup(str);
-		if (cgrp->fd == -1) {
-			free(cgrp);
-			return -1;
-		}
 	}
 
 	/*

index 83283fedb00f..0a632a6b6228 100644
@@ -254,6 +254,8 @@ struct thread_runtime {
 	u64 total_delay_time;
 
 	int last_state;
+
+	char shortname[3];
 	u64 migrations;
 };
 

@@ -897,6 +899,37 @@ struct sort_dimension {
 	struct list_head	list;
 };
 
+/*
+ * handle runtime stats saved per thread
+ */
+static struct thread_runtime *thread__init_runtime(struct thread *thread)
+{
+	struct thread_runtime *r;
+
+	r = zalloc(sizeof(struct thread_runtime));
+	if (!r)
+		return NULL;
+
+	init_stats(&r->run_stats);
+	thread__set_priv(thread, r);
+
+	return r;
+}
+
+static struct thread_runtime *thread__get_runtime(struct thread *thread)
+{
+	struct thread_runtime *tr;
+
+	tr = thread__priv(thread);
+	if (tr == NULL) {
+		tr = thread__init_runtime(thread);
+		if (tr == NULL)
+			pr_debug("Failed to malloc memory for runtime data.\n");
+	}
+
+	return tr;
+}
+
 static int
 thread_lat_cmp(struct list_head *list, struct work_atoms *l, struct work_atoms *r)
 {

@@ -1480,6 +1513,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 {
 	const u32 next_pid = perf_evsel__intval(evsel, sample, "next_pid");
 	struct thread *sched_in;
+	struct thread_runtime *tr;
 	int new_shortname;
 	u64 timestamp0, timestamp = sample->time;
 	s64 delta;

@@ -1519,22 +1553,28 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 	if (sched_in == NULL)
 		return -1;
 
+	tr = thread__get_runtime(sched_in);
+	if (tr == NULL) {
+		thread__put(sched_in);
+		return -1;
+	}
+
 	sched->curr_thread[this_cpu] = thread__get(sched_in);
 
 	printf("  ");
 
 	new_shortname = 0;
-	if (!sched_in->shortname[0]) {
+	if (!tr->shortname[0]) {
 		if (!strcmp(thread__comm_str(sched_in), "swapper")) {
 			/*
 			 * Don't allocate a letter-number for swapper:0
 			 * as a shortname. Instead, we use '.' for it.
 			 */
-			sched_in->shortname[0] = '.';
-			sched_in->shortname[1] = ' ';
+			tr->shortname[0] = '.';
+			tr->shortname[1] = ' ';
 		} else {
-			sched_in->shortname[0] = sched->next_shortname1;
-			sched_in->shortname[1] = sched->next_shortname2;
+			tr->shortname[0] = sched->next_shortname1;
+			tr->shortname[1] = sched->next_shortname2;
 
 			if (sched->next_shortname1 < 'Z') {
 				sched->next_shortname1++;

@@ -1552,6 +1592,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 	for (i = 0; i < cpus_nr; i++) {
 		int cpu = sched->map.comp ? sched->map.comp_cpus[i] : i;
 		struct thread *curr_thread = sched->curr_thread[cpu];
+		struct thread_runtime *curr_tr;
 		const char *pid_color = color;
 		const char *cpu_color = color;
 

@@ -1569,9 +1610,14 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 		else
 			color_fprintf(stdout, cpu_color, "*");
 
-		if (sched->curr_thread[cpu])
-			color_fprintf(stdout, pid_color, "%2s ", sched->curr_thread[cpu]->shortname);
-		else
+		if (sched->curr_thread[cpu]) {
+			curr_tr = thread__get_runtime(sched->curr_thread[cpu]);
+			if (curr_tr == NULL) {
+				thread__put(sched_in);
+				return -1;
+			}
+			color_fprintf(stdout, pid_color, "%2s ", curr_tr->shortname);
+		} else
 			color_fprintf(stdout, color, "   ");
 	}
 

@@ -1587,7 +1633,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 			pid_color = COLOR_PIDS;
 
 		color_fprintf(stdout, pid_color, "%s => %s:%d",
-		       sched_in->shortname, thread__comm_str(sched_in), sched_in->tid);
+		       tr->shortname, thread__comm_str(sched_in), sched_in->tid);
 	}
 
 	if (sched->map.comp && new_cpu)

@@ -2200,37 +2246,6 @@ static void save_idle_callchain(struct idle_thread_runtime *itr,
 	callchain_cursor__copy(&itr->cursor, &callchain_cursor);
 }
 
-/*
- * handle runtime stats saved per thread
- */
-static struct thread_runtime *thread__init_runtime(struct thread *thread)
-{
-	struct thread_runtime *r;
-
-	r = zalloc(sizeof(struct thread_runtime));
-	if (!r)
-		return NULL;
-
-	init_stats(&r->run_stats);
-	thread__set_priv(thread, r);
-
-	return r;
-}
-
-static struct thread_runtime *thread__get_runtime(struct thread *thread)
-{
-	struct thread_runtime *tr;
-
-	tr = thread__priv(thread);
-	if (tr == NULL) {
-		tr = thread__init_runtime(thread);
-		if (tr == NULL)
-			pr_debug("Failed to malloc memory for runtime data.\n");
-	}
-
-	return tr;
-}
-
 static struct thread *timehist_get_thread(struct perf_sched *sched,
 					  struct perf_sample *sample,
 					  struct machine *machine,

index 40cfa36c022a..14d44c3235b8 100644
@@ -26,7 +26,6 @@ struct thread {
 	pid_t			ppid;
 	int			cpu;
 	refcount_t		refcnt;
-	char			shortname[3];
 	bool			comm_set;
 	int			comm_len;
 	bool			dead; /* if set thread has exited */

index 0a632a6b6228..4dfdee668b0c 100644
@@ -256,6 +256,8 @@ struct thread_runtime {
 	int last_state;
 
 	char shortname[3];
+	bool comm_changed;
+
 	u64 migrations;
 };
 

@@ -1626,7 +1628,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 
 	timestamp__scnprintf_usec(timestamp, stimestamp, sizeof(stimestamp));
 	color_fprintf(stdout, color, "  %12s secs ", stimestamp);
-	if (new_shortname || (verbose > 0 && sched_in->tid)) {
+	if (new_shortname || tr->comm_changed || (verbose > 0 && sched_in->tid)) {
 		const char *pid_color = color;
 
 		if (thread__has_color(sched_in))

@@ -1634,6 +1636,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 
 		color_fprintf(stdout, pid_color, "%s => %s:%d",
 		       tr->shortname, thread__comm_str(sched_in), sched_in->tid);
+		tr->comm_changed = false;
 	}
 
 	if (sched->map.comp && new_cpu)

@@ -1737,6 +1740,37 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_
 	return err;
 }
 
+static int perf_sched__process_comm(struct perf_tool *tool __maybe_unused,
+				    union perf_event *event,
+				    struct perf_sample *sample,
+				    struct machine *machine)
+{
+	struct thread *thread;
+	struct thread_runtime *tr;
+	int err;
+
+	err = perf_event__process_comm(tool, event, sample, machine);
+	if (err)
+		return err;
+
+	thread = machine__find_thread(machine, sample->pid, sample->tid);
+	if (!thread) {
+		pr_err("Internal error: can't find thread\n");
+		return -1;
+	}
+
+	tr = thread__get_runtime(thread);
+	if (tr == NULL) {
+		thread__put(thread);
+		return -1;
+	}
+
+	tr->comm_changed = true;
+	thread__put(thread);
+
+	return 0;
+}
+
 static int perf_sched__read_events(struct perf_sched *sched)
 {
 	const struct perf_evsel_str_handler handlers[] = {

@@ -3306,7 +3340,7 @@ int cmd_sched(int argc, const char **argv)
 	struct perf_sched sched = {
 		.tool = {
 			.sample		 = perf_sched__process_tracepoint_sample,
-			.comm		 = perf_event__process_comm,
+			.comm		 = perf_sched__process_comm,
 			.namespaces	 = perf_event__process_namespaces,
 			.lost		 = perf_event__process_lost,
 			.fork		 = perf_sched__process_fork_event,

index 12230ddb6506..14d82f0fe5cc 100644
@@ -274,6 +274,24 @@ static void record__read_auxtrace_snapshot(struct record *rec)
 	}
 }
 
+static int record__auxtrace_init(struct record *rec)
+{
+	int err;
+
+	if (!rec->itr) {
+		rec->itr = auxtrace_record__init(rec->evlist, &err);
+		if (err)
+			return err;
+	}
+
+	err = auxtrace_parse_snapshot_options(rec->itr, &rec->opts,
+					      rec->opts.auxtrace_snapshot_opts);
+	if (err)
+		return err;
+
+	return auxtrace_parse_filters(rec->evlist);
+}
+
 #else
 
 static inline

@@ -294,6 +312,11 @@ int auxtrace_record__snapshot_start(struct auxtrace_record *itr __maybe_unused)
 	return 0;
 }
 
+static int record__auxtrace_init(struct record *rec __maybe_unused)
+{
+	return 0;
+}
+
 #endif
 
 static int record__mmap_evlist(struct record *rec,

@@ -1727,17 +1750,6 @@ int cmd_record(int argc, const char **argv)
 		alarm(rec->switch_output.time);
 	}
 
-	if (!rec->itr) {
-		rec->itr = auxtrace_record__init(rec->evlist, &err);
-		if (err)
-			goto out;
-	}
-
-	err = auxtrace_parse_snapshot_options(rec->itr, &rec->opts,
-					      rec->opts.auxtrace_snapshot_opts);
-	if (err)
-		goto out;
-
 	/*
 	 * Allow aliases to facilitate the lookup of symbols for address
 	 * filters. Refer to auxtrace_parse_filters().

@@ -1746,7 +1758,7 @@ int cmd_record(int argc, const char **argv)
 
 	symbol__init(NULL);
 
-	err = auxtrace_parse_filters(rec->evlist);
+	err = record__auxtrace_init(rec);
 	if (err)
 		goto out;
 

index 26a837037797..6fd33ffc2488 100644
@@ -128,18 +128,21 @@ static struct cgroup *cgroup__new(char *name)
 	return NULL;
 }
 
+struct cgroup *evlist__findnew_cgroup(struct perf_evlist *evlist, char *name)
+{
+	struct cgroup *cgroup = evlist__find_cgroup(evlist, name);
+
+	return cgroup ?: cgroup__new(name);
+}
+
 static int add_cgroup(struct perf_evlist *evlist, char *str)
 {
 	struct perf_evsel *counter;
-	struct cgroup *cgrp = evlist__find_cgroup(evlist, str);
+	struct cgroup *cgrp = evlist__findnew_cgroup(evlist, str);
 	int n;
 
-	if (!cgrp) {
-		cgrp = cgroup__new(str);
-		if (!cgrp)
-			return -1;
-	}
-
+	if (!cgrp)
+		return -1;
 	/*
 	 * find corresponding event
 	 * if add cgroup N, then need to find event N

index 34a6c11543dc..0e377e6340dd 100644
@@ -18,6 +18,10 @@ extern int nr_cgroups; /* number of explicit cgroups defined */
 struct cgroup *cgroup__get(struct cgroup *cgroup);
 void cgroup__put(struct cgroup *cgroup);
 
+struct perf_evlist;
+
+struct cgroup *evlist__findnew_cgroup(struct perf_evlist *evlist, char *name);
+
 int parse_cgroups(const struct option *opt, const char *str, int unset);
 
 #endif /* __CGROUP_H__ */

index 6fd33ffc2488..d8cd0e601c56 100644
@@ -182,6 +182,20 @@ struct cgroup *cgroup__get(struct cgroup *cgroup)
        return cgroup;
 }
 
+static void evsel__set_default_cgroup(struct perf_evsel *evsel, struct cgroup *cgroup)
+{
+	if (evsel->cgrp == NULL)
+		evsel->cgrp = cgroup__get(cgroup);
+}
+
+void evlist__set_default_cgroup(struct perf_evlist *evlist, struct cgroup *cgroup)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each_entry(evlist, evsel)
+		evsel__set_default_cgroup(evsel, cgroup);
+}
+
 int parse_cgroups(const struct option *opt, const char *str,
 		  int unset __maybe_unused)
 {

index 0e377e6340dd..b213f5e9a3ed 100644
@@ -22,6 +22,8 @@ struct perf_evlist;
 
 struct cgroup *evlist__findnew_cgroup(struct perf_evlist *evlist, char *name);
 
+void evlist__set_default_cgroup(struct perf_evlist *evlist, struct cgroup *cgroup);
+
 int parse_cgroups(const struct option *opt, const char *str, int unset);
 
 #endif /* __CGROUP_H__ */

index d8cd0e601c56..78408f5c4bad 100644
@@ -71,7 +71,7 @@ cgroupfs_find_mountpoint(char *buf, size_t maxlen)
 	return -1;
 }
 
-static int open_cgroup(char *name)
+static int open_cgroup(const char *name)
 {
 	char path[PATH_MAX + 1];
 	char mnt[PATH_MAX + 1];

@@ -90,7 +90,7 @@ static int open_cgroup(char *name)
 	return fd;
 }
 
-static struct cgroup *evlist__find_cgroup(struct perf_evlist *evlist, char *str)
+static struct cgroup *evlist__find_cgroup(struct perf_evlist *evlist, const char *str)
 {
 	struct perf_evsel *counter;
 	struct cgroup *cgrp = NULL;

@@ -109,33 +109,38 @@ static struct cgroup *evlist__find_cgroup(struct perf_evlist *evlist, char *str)
 	return cgrp;
 }
 
-static struct cgroup *cgroup__new(char *name)
+static struct cgroup *cgroup__new(const char *name)
 {
 	struct cgroup *cgroup = zalloc(sizeof(*cgroup));
 
 	if (cgroup != NULL) {
-		cgroup->name = name;
 		refcount_set(&cgroup->refcnt, 1);
 
+		cgroup->name = strdup(name);
+		if (!cgroup->name)
+			goto out_err;
 		cgroup->fd = open_cgroup(name);
 		if (cgroup->fd == -1)
-			goto out_err;
+			goto out_free_name;
 	}
 
 	return cgroup;
+
+out_free_name:
+	free(cgroup->name);
 out_err:
 	free(cgroup);
 	return NULL;
 }
 
-struct cgroup *evlist__findnew_cgroup(struct perf_evlist *evlist, char *name)
+struct cgroup *evlist__findnew_cgroup(struct perf_evlist *evlist, const char *name)
 {
 	struct cgroup *cgroup = evlist__find_cgroup(evlist, name);
 
 	return cgroup ?: cgroup__new(name);
 }
 
-static int add_cgroup(struct perf_evlist *evlist, char *str)
+static int add_cgroup(struct perf_evlist *evlist, const char *str)
 {
 	struct perf_evsel *counter;
 	struct cgroup *cgrp = evlist__findnew_cgroup(evlist, str);

@@ -222,10 +227,9 @@ int parse_cgroups(const struct option *opt, const char *str,
 			if (!s)
 				return -1;
 			ret = add_cgroup(evlist, s);
-			if (ret) {
-				free(s);
+			free(s);
+			if (ret)
 				return -1;
-			}
 		}
 		/* nr_cgroups is increased een for empty cgroups */
 		nr_cgroups++;

index b213f5e9a3ed..f033a80c1b14 100644
@@ -20,7 +20,7 @@ void cgroup__put(struct cgroup *cgroup);
 
 struct perf_evlist;
 
-struct cgroup *evlist__findnew_cgroup(struct perf_evlist *evlist, char *name);
+struct cgroup *evlist__findnew_cgroup(struct perf_evlist *evlist, const char *name);
 
 void evlist__set_default_cgroup(struct perf_evlist *evlist, struct cgroup *cgroup);
 

92 lines not on this page · raw message

index 453c148d2158..e731f55da072 100644
@@ -130,6 +130,7 @@ struct auxtrace_index {
 /**
  * struct auxtrace - session callbacks to allow AUX area data decoding.
  * @process_event: lets the decoder see all session events
+ * @process_auxtrace_event: process a PERF_RECORD_AUXTRACE event
  * @flush_events: process any remaining data
  * @free_events: free resources associated with event processing
  * @free: free resources associated with the session

@@ -301,6 +302,7 @@ struct auxtrace_mmap_params {
  * @parse_snapshot_options: parse snapshot options
  * @reference: provide a 64-bit reference number for auxtrace_event
  * @read_finish: called after reading from an auxtrace mmap
+ * @alignment: alignment (if any) for AUX area data
  */
 struct auxtrace_record {
 	int (*recording_options)(struct auxtrace_record *itr,

index 6470ea2aa25e..6ea840ec5b7f 100644
@@ -233,9 +233,9 @@ static void *auxtrace_copy_data(u64 size, struct perf_session *session)
 	return p;
 }
 
-static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues,
-				       unsigned int idx,
-				       struct auxtrace_buffer *buffer)
+static int auxtrace_queues__queue_buffer(struct auxtrace_queues *queues,
+					 unsigned int idx,
+					 struct auxtrace_buffer *buffer)
 {
 	struct auxtrace_queue *queue;
 	int err;

@@ -286,7 +286,7 @@ static int auxtrace_queues__split_buffer(struct auxtrace_queues *queues,
 			return -ENOMEM;
 		b->size = BUFFER_LIMIT_FOR_32_BIT;
 		b->consecutive = consecutive;
-		err = auxtrace_queues__add_buffer(queues, idx, b);
+		err = auxtrace_queues__queue_buffer(queues, idx, b);
 		if (err) {
 			auxtrace_buffer__free(b);
 			return err;

@@ -302,10 +302,10 @@ static int auxtrace_queues__split_buffer(struct auxtrace_queues *queues,
 	return 0;
 }
 
-static int auxtrace_queues__add_event_buffer(struct auxtrace_queues *queues,
-					     struct perf_session *session,
-					     unsigned int idx,
-					     struct auxtrace_buffer *buffer)
+static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues,
+				       struct perf_session *session,
+				       unsigned int idx,
+				       struct auxtrace_buffer *buffer)
 {
 	if (session->one_mmap) {
 		buffer->data = buffer->data_offset - session->one_mmap_offset +

@@ -324,7 +324,7 @@ static int auxtrace_queues__add_event_buffer(struct auxtrace_queues *queues,
 			return err;
 	}
 
-	return auxtrace_queues__add_buffer(queues, idx, buffer);
+	return auxtrace_queues__queue_buffer(queues, idx, buffer);
 }
 
 static bool filter_cpu(struct perf_session *session, int cpu)

@@ -359,7 +359,7 @@ int auxtrace_queues__add_event(struct auxtrace_queues *queues,
 	buffer->size = event->auxtrace.size;
 	idx = event->auxtrace.idx;
 
-	err = auxtrace_queues__add_event_buffer(queues, session, idx, buffer);
+	err = auxtrace_queues__add_buffer(queues, session, idx, buffer);
 	if (err)
 		goto out_err;
 

index 6ea840ec5b7f..fb357a00dd86 100644
@@ -305,8 +305,11 @@ static int auxtrace_queues__split_buffer(struct auxtrace_queues *queues,
 static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues,
 				       struct perf_session *session,
 				       unsigned int idx,
-				       struct auxtrace_buffer *buffer)
+				       struct auxtrace_buffer *buffer,
+				       struct auxtrace_buffer **buffer_ptr)
 {
+	int err;
+
 	if (session->one_mmap) {
 		buffer->data = buffer->data_offset - session->one_mmap_offset +
 			       session->one_mmap_addr;

@@ -317,14 +320,20 @@ static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues,
 		buffer->data_needs_freeing = true;
 	} else if (BITS_PER_LONG == 32 &&
 		   buffer->size > BUFFER_LIMIT_FOR_32_BIT) {
-		int err;
-
 		err = auxtrace_queues__split_buffer(queues, idx, buffer);
 		if (err)
 			return err;
 	}
 
-	return auxtrace_queues__queue_buffer(queues, idx, buffer);
+	err = auxtrace_queues__queue_buffer(queues, idx, buffer);
+	if (err)
+		return err;
+
+	/* FIXME: Doesn't work for split buffer */
+	if (buffer_ptr)
+		*buffer_ptr = buffer;
+
+	return 0;
 }
 
 static bool filter_cpu(struct perf_session *session, int cpu)

@@ -359,13 +368,11 @@ int auxtrace_queues__add_event(struct auxtrace_queues *queues,
 	buffer->size = event->auxtrace.size;
 	idx = event->auxtrace.idx;
 
-	err = auxtrace_queues__add_buffer(queues, session, idx, buffer);
+	err = auxtrace_queues__add_buffer(queues, session, idx, buffer,
+					  buffer_ptr);
 	if (err)
 		goto out_err;
 
-	if (buffer_ptr)
-		*buffer_ptr = buffer;
-
 	return 0;
 
 out_err:

index 3a022b3e5c02..0fa9ea3a6d92 100644
@@ -1251,6 +1251,31 @@ static void aggr_update_shadow(void)
 	}
 }
 
+static void uniquify_event_name(struct perf_evsel *counter)
+{
+	char *new_name;
+	char *config;
+
+	if (!counter->pmu_name || !strncmp(counter->name, counter->pmu_name,
+					   strlen(counter->pmu_name)))
+		return;
+
+	config = strchr(counter->name, '/');
+	if (config) {
+		if (asprintf(&new_name,
+			     "%s%s", counter->pmu_name, config) > 0) {
+			free(counter->name);
+			counter->name = new_name;
+		}
+	} else {
+		if (asprintf(&new_name,
+			     "%s [%s]", counter->name, counter->pmu_name) > 0) {
+			free(counter->name);
+			counter->name = new_name;
+		}
+	}
+}
+
 static void collect_all_aliases(struct perf_evsel *counter,
 			    void (*cb)(struct perf_evsel *counter, void *data,
 				       bool first),

@@ -1279,7 +1304,9 @@ static bool collect_data(struct perf_evsel *counter,
 	if (counter->merged_stat)
 		return false;
 	cb(counter, data, true);
-	if (!no_merge && counter->auto_merge_stats)
+	if (no_merge)
+		uniquify_event_name(counter);
+	else if (counter->auto_merge_stats)
 		collect_all_aliases(counter, cb, data);
 	return true;
 }

index f1f883bb41a8..e937894654b2 100644
@@ -244,6 +244,7 @@ void perf_evsel__init(struct perf_evsel *evsel,
 	evsel->metric_name   = NULL;
 	evsel->metric_events = NULL;
 	evsel->collect_stat  = false;
+	evsel->pmu_name      = NULL;
 }
 
 struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)

index 92ba001b627f..55ae1cda7396 100644
@@ -142,6 +142,7 @@ struct perf_evsel {
 	struct perf_evsel	**metric_events;
 	bool			collect_stat;
 	bool			weak_group;
+	const char		*pmu_name;
 };
 
 union u64_swap {

index 34589c427e52..bafc91edcb44 100644
@@ -1247,7 +1247,12 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,
 	if (!head_config) {
 		attr.type = pmu->type;
 		evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats);
-		return evsel ? 0 : -ENOMEM;
+		if (evsel) {
+			evsel->pmu_name = name;
+			return 0;
+		} else {
+			return -ENOMEM;
+		}
 	}
 
 	if (perf_pmu__check_alias(pmu, head_config, &info))

@@ -1276,6 +1281,7 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,
 		evsel->snapshot = info.snapshot;
 		evsel->metric_expr = info.metric_expr;
 		evsel->metric_name = info.metric_name;
+		evsel->pmu_name = name;
 	}
 
 	return evsel ? 0 : -ENOMEM;

index bafc91edcb44..4e80ca320399 100644
@@ -1217,7 +1217,7 @@ int parse_events_add_numeric(struct parse_events_state *parse_state,
 			 get_config_name(head_config), &config_terms);
 }
 
-static int __parse_events_add_pmu(struct parse_events_state *parse_state,
+int parse_events_add_pmu(struct parse_events_state *parse_state,
 			 struct list_head *list, char *name,
 			 struct list_head *head_config, bool auto_merge_stats)
 {

@@ -1287,13 +1287,6 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,
 	return evsel ? 0 : -ENOMEM;
 }
 
-int parse_events_add_pmu(struct parse_events_state *parse_state,
-			 struct list_head *list, char *name,
-			 struct list_head *head_config)
-{
-	return __parse_events_add_pmu(parse_state, list, name, head_config, false);
-}
-
 int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 			       char *str, struct list_head **listp)
 {

@@ -1323,8 +1316,8 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 					return -1;
 				list_add_tail(&term->list, head);
 
-				if (!__parse_events_add_pmu(parse_state, list,
-							    pmu->name, head, true)) {
+				if (!parse_events_add_pmu(parse_state, list,
+							  pmu->name, head, true)) {
 					pr_debug("%s -> %s/%s/\n", str,
 						 pmu->name, alias->str);
 					ok++;

index 88108cd11b4c..5015cfd58277 100644
@@ -167,7 +167,7 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx,
 				void *ptr, char *type, u64 len);
 int parse_events_add_pmu(struct parse_events_state *parse_state,
 			 struct list_head *list, char *name,
-			 struct list_head *head_config);
+			 struct list_head *head_config, bool auto_merge_stats);
 
 int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 			       char *str,

index 41a4666f1519..a59281d64368 100644
@@ -722,7 +722,8 @@ void perf_evlist__munmap(struct perf_evlist *evlist)
 	zfree(&evlist->overwrite_mmap);
 }
 
-static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist)
+static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist,
+						 bool overwrite)
 {
 	int i;
 	struct perf_mmap *map;

@@ -736,6 +737,7 @@ static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		map[i].fd = -1;
+		map[i].overwrite = overwrite;
 		/*
 		 * When the perf_mmap() call is made we grab one refcount, plus
 		 * one extra to let perf_mmap__consume() get the last

@@ -779,7 +781,7 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 			maps = evlist->overwrite_mmap;
 
 			if (!maps) {
-				maps = perf_evlist__alloc_mmap(evlist);
+				maps = perf_evlist__alloc_mmap(evlist, true);
 				if (!maps)
 					return -1;
 				evlist->overwrite_mmap = maps;

@@ -1029,7 +1031,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 	struct mmap_params mp;
 
 	if (!evlist->mmap)
-		evlist->mmap = perf_evlist__alloc_mmap(evlist);
+		evlist->mmap = perf_evlist__alloc_mmap(evlist, false);
 	if (!evlist->mmap)
 		return -ENOMEM;
 

index ec7d3a24e276..71137977af28 100644
@@ -20,6 +20,7 @@ struct perf_mmap {
 	int		 fd;
 	refcount_t	 refcnt;
 	u64		 prev;
+	bool		 overwrite;
 	struct auxtrace_mmap auxtrace_mmap;
 	char		 event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8);
 };

index 4f27c464ce0b..09acaf7392bb 100644
@@ -250,13 +250,15 @@ int perf_mmap__read_init(struct perf_mmap *md, bool overwrite,
 
 	*startp = overwrite ? head : old;
 	*endp = overwrite ? old : head;
+	md->start = md->overwrite ? head : old;
+	md->end = md->overwrite ? old : head;
 
-	if (*startp == *endp)
+	if (md->start == md->end)
 		return -EAGAIN;
 
-	size = *endp - *startp;
+	size = md->end - md->start;
 	if (size > (unsigned long)(md->mask) + 1) {
-		if (!overwrite) {
+		if (!md->overwrite) {
 			WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");
 
 			md->prev = head;

@@ -268,8 +270,10 @@ int perf_mmap__read_init(struct perf_mmap *md, bool overwrite,
 		 * Backward ring buffer is full. We still have a chance to read
 		 * most of data from it.
 		 */
-		if (overwrite_rb_find_range(data, md->mask, head, startp, endp))
+		if (overwrite_rb_find_range(data, md->mask, head, &md->start, &md->end))
 			return -EINVAL;
+		*startp = md->start;
+		*endp = md->end;
 	}
 
 	return 0;

index 71137977af28..9359e934ab14 100644
@@ -20,6 +20,8 @@ struct perf_mmap {
 	int		 fd;
 	refcount_t	 refcnt;
 	u64		 prev;
+	u64		 start;
+	u64		 end;
 	bool		 overwrite;
 	struct auxtrace_mmap auxtrace_mmap;
 	char		 event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8);

index 14d82f0fe5cc..753ffcecf254 100644
@@ -533,7 +533,7 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
 		struct auxtrace_mmap *mm = &maps[i].auxtrace_mmap;
 
 		if (maps[i].base) {
-			if (perf_mmap__push(&maps[i], overwrite, rec, record__pushfn) != 0) {
+			if (perf_mmap__push(&maps[i], rec, record__pushfn) != 0) {
 				rc = -1;
 				goto out;
 			}

index 09acaf7392bb..8c1d033638c2 100644
@@ -279,8 +279,8 @@ int perf_mmap__read_init(struct perf_mmap *md, bool overwrite,
 	return 0;
 }
 
-int perf_mmap__push(struct perf_mmap *md, bool overwrite,
-		    void *to, int push(void *to, void *buf, size_t size))
+int perf_mmap__push(struct perf_mmap *md, void *to,
+		    int push(void *to, void *buf, size_t size))
 {
 	u64 head = perf_mmap__read_head(md);
 	u64 end, start;

@@ -289,16 +289,16 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite,
 	void *buf;
 	int rc = 0;
 
-	rc = perf_mmap__read_init(md, overwrite, &start, &end);
+	rc = perf_mmap__read_init(md, md->overwrite, &start, &end);
 	if (rc < 0)
 		return (rc == -EAGAIN) ? 0 : -1;
 
-	size = end - start;
+	size = md->end - md->start;
 
-	if ((start & md->mask) + size != (end & md->mask)) {
-		buf = &data[start & md->mask];
-		size = md->mask + 1 - (start & md->mask);
-		start += size;
+	if ((md->start & md->mask) + size != (md->end & md->mask)) {
+		buf = &data[md->start & md->mask];
+		size = md->mask + 1 - (md->start & md->mask);
+		md->start += size;
 
 		if (push(to, buf, size) < 0) {
 			rc = -1;

@@ -306,9 +306,9 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite,
 		}
 	}
 
-	buf = &data[start & md->mask];
-	size = end - start;
-	start += size;
+	buf = &data[md->start & md->mask];
+	size = md->end - md->start;
+	md->start += size;
 
 	if (push(to, buf, size) < 0) {
 		rc = -1;

@@ -316,7 +316,7 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite,
 	}
 
 	md->prev = head;
-	perf_mmap__consume(md, overwrite);
+	perf_mmap__consume(md, md->overwrite);
 out:
 	return rc;
 }

index 9359e934ab14..65f5b26d8668 100644
@@ -93,8 +93,8 @@ union perf_event *perf_mmap__read_event(struct perf_mmap *map,
 					bool overwrite,
 					u64 *startp, u64 end);
 
-int perf_mmap__push(struct perf_mmap *md, bool backward,
-		    void *to, int push(void *to, void *buf, size_t size));
+int perf_mmap__push(struct perf_mmap *md, void *to,
+		    int push(void *to, void *buf, size_t size));
 
 size_t perf_mmap__mmap_len(struct perf_mmap *map);
 

index 8c1d033638c2..2933942abfe2 100644
@@ -76,8 +76,9 @@ static union perf_event *perf_mmap__read(struct perf_mmap *map,
  * perf_mmap__read_done()
  */
 union perf_event *perf_mmap__read_event(struct perf_mmap *map,
-					bool overwrite,
-					u64 *startp, u64 end)
+					bool overwrite __maybe_unused,
+					u64 *startp __maybe_unused,
+					u64 end __maybe_unused)
 {
 	union perf_event *event;
 

@@ -87,17 +88,14 @@ union perf_event *perf_mmap__read_event(struct perf_mmap *map,
 	if (!refcount_read(&map->refcnt))
 		return NULL;
 
-	if (startp == NULL)
-		return NULL;
-
 	/* non-overwirte doesn't pause the ringbuffer */
-	if (!overwrite)
-		end = perf_mmap__read_head(map);
+	if (!map->overwrite)
+		map->end = perf_mmap__read_head(map);
 
-	event = perf_mmap__read(map, startp, end);
+	event = perf_mmap__read(map, &map->start, map->end);
 
-	if (!overwrite)
-		map->prev = *startp;
+	if (!map->overwrite)
+		map->prev = map->start;
 
 	return event;
 }

index 2933942abfe2..8a2dac90056c 100644
@@ -118,9 +118,9 @@ void perf_mmap__put(struct perf_mmap *map)
 		perf_mmap__munmap(map);
 }
 
-void perf_mmap__consume(struct perf_mmap *map, bool overwrite)
+void perf_mmap__consume(struct perf_mmap *map, bool overwrite __maybe_unused)
 {
-	if (!overwrite) {
+	if (!map->overwrite) {
 		u64 old = map->prev;
 
 		perf_mmap__write_tail(map, old);

index 7f82d91ef473..a9bc77df6a65 100644
@@ -134,7 +134,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 				comm2_time = sample.time;
 			}
 next_event:
-			perf_mmap__consume(md, false);
+			perf_mmap__consume(md);
 		}
 		perf_mmap__read_done(md);
 	}

index d2703d3b8366..165c044616b6 100644
@@ -760,7 +760,7 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
 	while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
 		err = perf_evlist__parse_sample_timestamp(evlist, event, &timestamp);
 		if (err) {
-			perf_mmap__consume(md, false);
+			perf_mmap__consume(md);
 			pr_err("Failed to parse sample\n");
 			return -1;
 		}

@@ -770,7 +770,7 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
 		 * FIXME: Here we can't consume the event, as perf_session__queue_event will
 		 *        point to it, and it'll get possibly overwritten by the kernel.
 		 */
-		perf_mmap__consume(md, false);
+		perf_mmap__consume(md);
 
 		if (err) {
 			pr_err("Failed to enqueue sample: %d\n", err);

index bb4f9fafd11d..11b4a413039f 100644
@@ -879,7 +879,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 		} else
 			++session->evlist->stats.nr_unknown_events;
 next_event:
-		perf_mmap__consume(md, opts->overwrite);
+		perf_mmap__consume(md);
 	}
 
 	perf_mmap__read_done(md);

index 5b81060a8117..27eadf3018c6 100644
@@ -2522,7 +2522,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 
 			trace__handle_event(trace, event, &sample);
 next_event:
-			perf_mmap__consume(md, false);
+			perf_mmap__consume(md);
 
 			if (interrupted)
 				goto out_disable;

index 03ed8c77b1bb..f7c199acb7ac 100644
@@ -420,7 +420,7 @@ static int process_events(struct machine *machine, struct perf_evlist *evlist,
 
 		while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
 			ret = process_event(machine, evlist, event, state);
-			perf_mmap__consume(md, false);
+			perf_mmap__consume(md);
 			if (ret < 0)
 				return ret;
 		}

index 4590d8fb91ab..1f1db5965d05 100644
@@ -42,7 +42,7 @@ static int find_comm(struct perf_evlist *evlist, const char *comm)
 			    (pid_t)event->comm.tid == getpid() &&
 			    strcmp(event->comm.comm, comm) == 0)
 				found += 1;
-			perf_mmap__consume(md, false);
+			perf_mmap__consume(md);
 		}
 		perf_mmap__read_done(md);
 	}

index 44c58d69cd87..f473e106aeba 100644
@@ -135,7 +135,7 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse
 			goto out_delete_evlist;
 		}
 		nr_events[evsel->idx]++;
-		perf_mmap__consume(md, false);
+		perf_mmap__consume(md);
 	}
 	perf_mmap__read_done(md);
 

index 620b21023f72..7837ae936679 100644
@@ -101,7 +101,7 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest
 				++nr_events;
 
 				if (type != PERF_RECORD_SAMPLE) {
-					perf_mmap__consume(md, false);
+					perf_mmap__consume(md);
 					continue;
 				}
 

index 31f3f70adca6..6ff5f99b3e0e 100644
@@ -272,7 +272,7 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus
 					++errs;
 				}
 
-				perf_mmap__consume(md, false);
+				perf_mmap__consume(md);
 			}
 			perf_mmap__read_done(md);
 		}

index e6320e267ba5..b58297b9a83d 100644
@@ -114,7 +114,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 		total_periods += sample.period;
 		nr_samples++;
 next_event:
-		perf_mmap__consume(md, false);
+		perf_mmap__consume(md);
 	}
 	perf_mmap__read_done(md);
 

index 10c4dcdc2324..dbf9e20f7d56 100644
@@ -270,7 +270,7 @@ static int process_events(struct perf_evlist *evlist,
 		while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
 			cnt += 1;
 			ret = add_event(evlist, &events, event);
-			 perf_mmap__consume(md, false);
+			 perf_mmap__consume(md);
 			if (ret < 0)
 				goto out_free_nodes;
 		}

index 02b0888b72a3..5aa2e68e9d05 100644
@@ -120,7 +120,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 		if (event->header.type == PERF_RECORD_EXIT)
 			nr_exit++;
 
-		perf_mmap__consume(md, false);
+		perf_mmap__consume(md);
 	}
 	perf_mmap__read_done(md);
 

index 8a2dac90056c..62312e06d75b 100644
@@ -118,7 +118,7 @@ void perf_mmap__put(struct perf_mmap *map)
 		perf_mmap__munmap(map);
 }
 
-void perf_mmap__consume(struct perf_mmap *map, bool overwrite __maybe_unused)
+void perf_mmap__consume(struct perf_mmap *map)
 {
 	if (!map->overwrite) {
 		u64 old = map->prev;

@@ -260,7 +260,7 @@ int perf_mmap__read_init(struct perf_mmap *md, bool overwrite,
 			WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");
 
 			md->prev = head;
-			perf_mmap__consume(md, overwrite);
+			perf_mmap__consume(md);
 			return -EAGAIN;
 		}
 

@@ -314,7 +314,7 @@ int perf_mmap__push(struct perf_mmap *md, void *to,
 	}
 
 	md->prev = head;
-	perf_mmap__consume(md, md->overwrite);
+	perf_mmap__consume(md);
 out:
 	return rc;
 }

index 65f5b26d8668..043916a20de6 100644
@@ -66,7 +66,7 @@ void perf_mmap__munmap(struct perf_mmap *map);
 void perf_mmap__get(struct perf_mmap *map);
 void perf_mmap__put(struct perf_mmap *map);
 
-void perf_mmap__consume(struct perf_mmap *map, bool overwrite);
+void perf_mmap__consume(struct perf_mmap *map);
 
 static inline u64 perf_mmap__read_head(struct perf_mmap *mm)
 {

index 35fb5ef7d290..ca077f8be1f0 100644
@@ -1013,7 +1013,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 		err = perf_evsel__parse_sample(evsel, event, &pevent->sample);
 
 		/* Consume the even only after we parsed it out. */
-		perf_mmap__consume(md, false);
+		perf_mmap__consume(md);
 
 		if (err)
 			return PyErr_Format(PyExc_OSError,

index a9bc77df6a65..17cf7fc3c7d5 100644
@@ -115,7 +115,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 		if (perf_mmap__read_init(md, false, &start, &end) < 0)
 			continue;
 
-		while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
+		while ((event = perf_mmap__read_event(md)) != NULL) {
 			struct perf_sample sample;
 
 			if (event->header.type != PERF_RECORD_COMM ||

index 165c044616b6..e9f69b8f8e25 100644
@@ -757,7 +757,7 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
 	if (err < 0)
 		return (err == -EAGAIN) ? 0 : -1;
 
-	while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
+	while ((event = perf_mmap__read_event(md)) != NULL) {
 		err = perf_evlist__parse_sample_timestamp(evlist, event, &timestamp);
 		if (err) {
 			perf_mmap__consume(md);

index 11b4a413039f..eb19cf92a388 100644
@@ -824,7 +824,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 	if (perf_mmap__read_init(md, opts->overwrite, &start, &end) < 0)
 		return;
 
-	while ((event = perf_mmap__read_event(md, opts->overwrite, &start, end)) != NULL) {
+	while ((event = perf_mmap__read_event(md)) != NULL) {
 		ret = perf_evlist__parse_sample(evlist, event, &sample);
 		if (ret) {
 			pr_err("Can't parse sample, err = %d\n", ret);

index 27eadf3018c6..29fda506ac75 100644
@@ -2509,7 +2509,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 		if (perf_mmap__read_init(md, false, &start, &end) < 0)
 			continue;
 
-		while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
+		while ((event = perf_mmap__read_event(md)) != NULL) {
 			struct perf_sample sample;
 
 			++trace->nr_events;

index e0b1b414d466..e0eae1053ddc 100644
@@ -36,7 +36,7 @@ static int count_samples(struct perf_evlist *evlist, int *sample_count,
 		u64 start, end;
 
 		perf_mmap__read_init(map, true, &start, &end);
-		while ((event = perf_mmap__read_event(map, true, &start, end)) != NULL) {
+		while ((event = perf_mmap__read_event(map)) != NULL) {
 			const u32 type = event->header.type;
 
 			switch (type) {

index 09c9c9f9e827..384c20f4c902 100644
@@ -183,7 +183,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
 		if (perf_mmap__read_init(md, false, &start, &end) < 0)
 			continue;
 
-		while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
+		while ((event = perf_mmap__read_event(md)) != NULL) {
 			const u32 type = event->header.type;
 
 			if (type == PERF_RECORD_SAMPLE)

index f7c199acb7ac..f7919666bc2c 100644
@@ -418,7 +418,7 @@ static int process_events(struct machine *machine, struct perf_evlist *evlist,
 		if (perf_mmap__read_init(md, false, &start, &end) < 0)
 			continue;
 
-		while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
+		while ((event = perf_mmap__read_event(md)) != NULL) {
 			ret = process_event(machine, evlist, event, state);
 			perf_mmap__consume(md);
 			if (ret < 0)

index 1f1db5965d05..ad477b7cf238 100644
@@ -36,7 +36,7 @@ static int find_comm(struct perf_evlist *evlist, const char *comm)
 		md = &evlist->mmap[i];
 		if (perf_mmap__read_init(md, false, &start, &end) < 0)
 			continue;
-		while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
+		while ((event = perf_mmap__read_event(md)) != NULL) {
 			if (event->header.type == PERF_RECORD_COMM &&
 			    (pid_t)event->comm.pid == getpid() &&
 			    (pid_t)event->comm.tid == getpid() &&

index f473e106aeba..7790eb3303e6 100644
@@ -112,7 +112,7 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse
 	if (perf_mmap__read_init(md, false, &start, &end) < 0)
 		goto out_init;
 
-	while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
+	while ((event = perf_mmap__read_event(md)) != NULL) {
 		struct perf_sample sample;
 
 		if (event->header.type != PERF_RECORD_SAMPLE) {

index 7837ae936679..b0be2da65da7 100644
@@ -93,7 +93,7 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest
 			if (perf_mmap__read_init(md, false, &start, &end) < 0)
 				continue;
 
-			while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
+			while ((event = perf_mmap__read_event(md)) != NULL) {
 				const u32 type = event->header.type;
 				int tp_flags;
 				struct perf_sample sample;

index 6ff5f99b3e0e..59be0942b787 100644
@@ -171,7 +171,7 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus
 			if (perf_mmap__read_init(md, false, &start, &end) < 0)
 				continue;
 
-			while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
+			while ((event = perf_mmap__read_event(md)) != NULL) {
 				const u32 type = event->header.type;
 				const char *name = perf_event__name(type);
 

index b58297b9a83d..403f2d9cee96 100644
@@ -99,7 +99,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 	if (perf_mmap__read_init(md, false, &start, &end) < 0)
 		goto out_init;
 
-	while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
+	while ((event = perf_mmap__read_event(md)) != NULL) {
 		struct perf_sample sample;
 
 		if (event->header.type != PERF_RECORD_SAMPLE)

index dbf9e20f7d56..99839de3caee 100644
@@ -267,7 +267,7 @@ static int process_events(struct perf_evlist *evlist,
 		if (perf_mmap__read_init(md, false, &start, &end) < 0)
 			continue;
 
-		while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
+		while ((event = perf_mmap__read_event(md)) != NULL) {
 			cnt += 1;
 			ret = add_event(evlist, &events, event);
 			 perf_mmap__consume(md);

index 5aa2e68e9d05..2df0c0573e2c 100644
@@ -116,7 +116,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 	if (perf_mmap__read_init(md, false, &start, &end) < 0)
 		goto out_init;
 
-	while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
+	while ((event = perf_mmap__read_event(md)) != NULL) {
 		if (event->header.type == PERF_RECORD_EXIT)
 			nr_exit++;
 

index 62312e06d75b..2fbe4c8a02d2 100644
@@ -75,10 +75,7 @@ static union perf_event *perf_mmap__read(struct perf_mmap *map,
  * }
  * perf_mmap__read_done()
  */
-union perf_event *perf_mmap__read_event(struct perf_mmap *map,
-					bool overwrite __maybe_unused,
-					u64 *startp __maybe_unused,
-					u64 end __maybe_unused)
+union perf_event *perf_mmap__read_event(struct perf_mmap *map)
 {
 	union perf_event *event;
 

index 043916a20de6..ae9499b80110 100644
@@ -89,9 +89,7 @@ static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail)
 
 union perf_event *perf_mmap__read_forward(struct perf_mmap *map);
 
-union perf_event *perf_mmap__read_event(struct perf_mmap *map,
-					bool overwrite,
-					u64 *startp, u64 end);
+union perf_event *perf_mmap__read_event(struct perf_mmap *map);
 
 int perf_mmap__push(struct perf_mmap *md, void *to,
 		    int push(void *to, void *buf, size_t size));

index ca077f8be1f0..4798db93e7ee 100644
@@ -995,7 +995,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 	if (perf_mmap__read_init(md, false, &start, &end) < 0)
 		goto end;
 
-	event = perf_mmap__read_event(md, false, &start, end);
+	event = perf_mmap__read_event(md);
 	if (event != NULL) {
 		PyObject *pyevent = pyrf_event__new(event);
 		struct pyrf_event *pevent = (struct pyrf_event *)pyevent;

index 17cf7fc3c7d5..7a7721604b86 100644
@@ -61,7 +61,6 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 	u64 test_tsc, comm1_tsc, comm2_tsc;
 	u64 test_time, comm1_time = 0, comm2_time = 0;
 	struct perf_mmap *md;
-	u64 end, start;
 
 	threads = thread_map__new(-1, getpid(), UINT_MAX);
 	CHECK_NOT_NULL__(threads);

@@ -112,7 +111,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		md = &evlist->mmap[i];
-		if (perf_mmap__read_init(md, false, &start, &end) < 0)
+		if (perf_mmap__read_init(md) < 0)
 			continue;
 
 		while ((event = perf_mmap__read_event(md)) != NULL) {

index e9f69b8f8e25..72e2ca096bf5 100644
@@ -746,14 +746,13 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
 	struct perf_evlist *evlist = kvm->evlist;
 	union perf_event *event;
 	struct perf_mmap *md;
-	u64 end, start;
 	u64 timestamp;
 	s64 n = 0;
 	int err;
 
 	*mmap_time = ULLONG_MAX;
 	md = &evlist->mmap[idx];
-	err = perf_mmap__read_init(md, false, &start, &end);
+	err = perf_mmap__read_init(md);
 	if (err < 0)
 		return (err == -EAGAIN) ? 0 : -1;
 

index eb19cf92a388..0a26b56afcc5 100644
@@ -817,11 +817,10 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 	struct perf_session *session = top->session;
 	union perf_event *event;
 	struct machine *machine;
-	u64 end, start;
 	int ret;
 
 	md = opts->overwrite ? &evlist->overwrite_mmap[idx] : &evlist->mmap[idx];
-	if (perf_mmap__read_init(md, opts->overwrite, &start, &end) < 0)
+	if (perf_mmap__read_init(md) < 0)
 		return;
 
 	while ((event = perf_mmap__read_event(md)) != NULL) {

index 29fda506ac75..87b95c9410b4 100644
@@ -2503,10 +2503,9 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		union perf_event *event;
 		struct perf_mmap *md;
-		u64 end, start;
 
 		md = &evlist->mmap[i];
-		if (perf_mmap__read_init(md, false, &start, &end) < 0)
+		if (perf_mmap__read_init(md) < 0)
 			continue;
 
 		while ((event = perf_mmap__read_event(md)) != NULL) {

index e0eae1053ddc..6d598cc071ae 100644
@@ -33,9 +33,8 @@ static int count_samples(struct perf_evlist *evlist, int *sample_count,
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		struct perf_mmap *map = &evlist->overwrite_mmap[i];
 		union perf_event *event;
-		u64 start, end;
 
-		perf_mmap__read_init(map, true, &start, &end);
+		perf_mmap__read_init(map);
 		while ((event = perf_mmap__read_event(map)) != NULL) {
 			const u32 type = event->header.type;
 

index 384c20f4c902..79b54f8ddebf 100644
@@ -177,10 +177,9 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		union perf_event *event;
 		struct perf_mmap *md;
-		u64 end, start;
 
 		md = &evlist->mmap[i];
-		if (perf_mmap__read_init(md, false, &start, &end) < 0)
+		if (perf_mmap__read_init(md) < 0)
 			continue;
 
 		while ((event = perf_mmap__read_event(md)) != NULL) {

index f7919666bc2c..99936352df4f 100644
@@ -410,12 +410,11 @@ static int process_events(struct machine *machine, struct perf_evlist *evlist,
 {
 	union perf_event *event;
 	struct perf_mmap *md;
-	u64 end, start;
 	int i, ret;
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		md = &evlist->mmap[i];
-		if (perf_mmap__read_init(md, false, &start, &end) < 0)
+		if (perf_mmap__read_init(md) < 0)
 			continue;
 
 		while ((event = perf_mmap__read_event(md)) != NULL) {

index ad477b7cf238..17c46f3e6f1e 100644
@@ -28,13 +28,12 @@ static int find_comm(struct perf_evlist *evlist, const char *comm)
 {
 	union perf_event *event;
 	struct perf_mmap *md;
-	u64 end, start;
 	int i, found;
 
 	found = 0;
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		md = &evlist->mmap[i];
-		if (perf_mmap__read_init(md, false, &start, &end) < 0)
+		if (perf_mmap__read_init(md) < 0)
 			continue;
 		while ((event = perf_mmap__read_event(md)) != NULL) {
 			if (event->header.type == PERF_RECORD_COMM &&

index 7790eb3303e6..bb8e6bcb0d96 100644
@@ -39,7 +39,6 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse
 	struct perf_evsel *evsels[nsyscalls], *evsel;
 	char sbuf[STRERR_BUFSIZE];
 	struct perf_mmap *md;
-	u64 end, start;
 
 	threads = thread_map__new(-1, getpid(), UINT_MAX);
 	if (threads == NULL) {

@@ -109,7 +108,7 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse
 		}
 
 	md = &evlist->mmap[0];
-	if (perf_mmap__read_init(md, false, &start, &end) < 0)
+	if (perf_mmap__read_init(md) < 0)
 		goto out_init;
 
 	while ((event = perf_mmap__read_event(md)) != NULL) {

index b0be2da65da7..344dc3ac2469 100644
@@ -87,10 +87,9 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest
 		for (i = 0; i < evlist->nr_mmaps; i++) {
 			union perf_event *event;
 			struct perf_mmap *md;
-			u64 end, start;
 
 			md = &evlist->mmap[i];
-			if (perf_mmap__read_init(md, false, &start, &end) < 0)
+			if (perf_mmap__read_init(md) < 0)
 				continue;
 
 			while ((event = perf_mmap__read_event(md)) != NULL) {

index 59be0942b787..34394cc05077 100644
@@ -165,10 +165,9 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus
 		for (i = 0; i < evlist->nr_mmaps; i++) {
 			union perf_event *event;
 			struct perf_mmap *md;
-			u64 end, start;
 
 			md = &evlist->mmap[i];
-			if (perf_mmap__read_init(md, false, &start, &end) < 0)
+			if (perf_mmap__read_init(md) < 0)
 				continue;
 
 			while ((event = perf_mmap__read_event(md)) != NULL) {

index 403f2d9cee96..f9490b237893 100644
@@ -40,7 +40,6 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 	struct cpu_map *cpus;
 	struct thread_map *threads;
 	struct perf_mmap *md;
-	u64 end, start;
 
 	attr.sample_freq = 500;
 

@@ -96,7 +95,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 	perf_evlist__disable(evlist);
 
 	md = &evlist->mmap[0];
-	if (perf_mmap__read_init(md, false, &start, &end) < 0)
+	if (perf_mmap__read_init(md) < 0)
 		goto out_init;
 
 	while ((event = perf_mmap__read_event(md)) != NULL) {

index 99839de3caee..9b5be51e5e7b 100644
@@ -259,12 +259,11 @@ static int process_events(struct perf_evlist *evlist,
 	LIST_HEAD(events);
 	struct event_node *events_array, *node;
 	struct perf_mmap *md;
-	u64 end, start;
 	int i, ret;
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		md = &evlist->mmap[i];
-		if (perf_mmap__read_init(md, false, &start, &end) < 0)
+		if (perf_mmap__read_init(md) < 0)
 			continue;
 
 		while ((event = perf_mmap__read_event(md)) != NULL) {

index 2df0c0573e2c..e92fa6029ac7 100644
@@ -48,7 +48,6 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 	struct cpu_map *cpus;
 	struct thread_map *threads;
 	struct perf_mmap *md;
-	u64 end, start;
 
 	signal(SIGCHLD, sig_handler);
 

@@ -113,7 +112,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 
 retry:
 	md = &evlist->mmap[0];
-	if (perf_mmap__read_init(md, false, &start, &end) < 0)
+	if (perf_mmap__read_init(md) < 0)
 		goto out_init;
 
 	while ((event = perf_mmap__read_event(md)) != NULL) {

index 2fbe4c8a02d2..074c4fd3b67e 100644
@@ -235,16 +235,13 @@ static int overwrite_rb_find_range(void *buf, int mask, u64 head, u64 *start, u6
 /*
  * Report the start and end of the available data in ringbuffer
  */
-int perf_mmap__read_init(struct perf_mmap *md, bool overwrite,
-			 u64 *startp, u64 *endp)
+int perf_mmap__read_init(struct perf_mmap *md)
 {
 	u64 head = perf_mmap__read_head(md);
 	u64 old = md->prev;
 	unsigned char *data = md->base + page_size;
 	unsigned long size;
 
-	*startp = overwrite ? head : old;
-	*endp = overwrite ? old : head;
 	md->start = md->overwrite ? head : old;
 	md->end = md->overwrite ? old : head;
 

@@ -267,8 +264,6 @@ int perf_mmap__read_init(struct perf_mmap *md, bool overwrite,
 		 */
 		if (overwrite_rb_find_range(data, md->mask, head, &md->start, &md->end))
 			return -EINVAL;
-		*startp = md->start;
-		*endp = md->end;
 	}
 
 	return 0;

@@ -278,13 +273,12 @@ int perf_mmap__push(struct perf_mmap *md, void *to,
 		    int push(void *to, void *buf, size_t size))
 {
 	u64 head = perf_mmap__read_head(md);
-	u64 end, start;
 	unsigned char *data = md->base + page_size;
 	unsigned long size;
 	void *buf;
 	int rc = 0;
 
-	rc = perf_mmap__read_init(md, md->overwrite, &start, &end);
+	rc = perf_mmap__read_init(md);
 	if (rc < 0)
 		return (rc == -EAGAIN) ? 0 : -1;
 

index ae9499b80110..d82294db1295 100644
@@ -96,7 +96,6 @@ int perf_mmap__push(struct perf_mmap *md, void *to,
 
 size_t perf_mmap__mmap_len(struct perf_mmap *map);
 
-int perf_mmap__read_init(struct perf_mmap *md, bool overwrite,
-			 u64 *startp, u64 *endp);
+int perf_mmap__read_init(struct perf_mmap *md);
 void perf_mmap__read_done(struct perf_mmap *map);
 #endif /*__PERF_MMAP_H */

index 4798db93e7ee..b956868fd445 100644
@@ -984,7 +984,6 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 	int sample_id_all = 1, cpu;
 	static char *kwlist[] = { "cpu", "sample_id_all", NULL };
 	struct perf_mmap *md;
-	u64 end, start;
 	int err;
 
 	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "i|i", kwlist,

@@ -992,7 +991,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 		return NULL;
 
 	md = &evlist->mmap[cpu];
-	if (perf_mmap__read_init(md, false, &start, &end) < 0)
+	if (perf_mmap__read_init(md) < 0)
 		goto end;
 
 	event = perf_mmap__read_event(md);

index aa1593ce551d..00f25f4b5f48 100644
@@ -2390,14 +2390,6 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
 	return &decoder->state;
 }
 
-static bool intel_pt_at_psb(unsigned char *buf, size_t len)
-{
-	if (len < INTEL_PT_PSB_LEN)
-		return false;
-	return memmem(buf, INTEL_PT_PSB_LEN, INTEL_PT_PSB_STR,
-		      INTEL_PT_PSB_LEN);
-}
-
 /**
  * intel_pt_next_psb - move buffer pointer to the start of the next PSB packet.
  * @buf: pointer to buffer pointer

@@ -2486,6 +2478,7 @@ static unsigned char *intel_pt_last_psb(unsigned char *buf, size_t len)
  * @buf: buffer
  * @len: size of buffer
  * @tsc: TSC value returned
+ * @rem: returns remaining size when TSC is found
  *
  * Find a TSC packet in @buf and return the TSC value.  This function assumes
  * that @buf starts at a PSB and that PSB+ will contain TSC and so stops if a

@@ -2493,7 +2486,8 @@ static unsigned char *intel_pt_last_psb(unsigned char *buf, size_t len)
  *
  * Return: %true if TSC is found, false otherwise.
  */
-static bool intel_pt_next_tsc(unsigned char *buf, size_t len, uint64_t *tsc)
+static bool intel_pt_next_tsc(unsigned char *buf, size_t len, uint64_t *tsc,
+			      size_t *rem)
 {
 	struct intel_pt_pkt packet;
 	int ret;

@@ -2504,6 +2498,7 @@ static bool intel_pt_next_tsc(unsigned char *buf, size_t len, uint64_t *tsc)
 			return false;
 		if (packet.type == INTEL_PT_TSC) {
 			*tsc = packet.payload;
+			*rem = len;
 			return true;
 		}
 		if (packet.type == INTEL_PT_PSBEND)

@@ -2554,6 +2549,8 @@ static int intel_pt_tsc_cmp(uint64_t tsc1, uint64_t tsc2)
  * @len_a: size of first buffer
  * @buf_b: second buffer
  * @len_b: size of second buffer
+ * @consecutive: returns true if there is data in buf_b that is consecutive
+ *               to buf_a
  *
  * If the trace contains TSC we can look at the last TSC of @buf_a and the
  * first TSC of @buf_b in order to determine if the buffers overlap, and then

@@ -2566,33 +2563,41 @@ static int intel_pt_tsc_cmp(uint64_t tsc1, uint64_t tsc2)
 static unsigned char *intel_pt_find_overlap_tsc(unsigned char *buf_a,
 						size_t len_a,
 						unsigned char *buf_b,
-						size_t len_b)
+						size_t len_b, bool *consecutive)
 {
 	uint64_t tsc_a, tsc_b;
 	unsigned char *p;
-	size_t len;
+	size_t len, rem_a, rem_b;
 
 	p = intel_pt_last_psb(buf_a, len_a);
 	if (!p)
 		return buf_b; /* No PSB in buf_a => no overlap */
 
 	len = len_a - (p - buf_a);
-	if (!intel_pt_next_tsc(p, len, &tsc_a)) {
+	if (!intel_pt_next_tsc(p, len, &tsc_a, &rem_a)) {
 		/* The last PSB+ in buf_a is incomplete, so go back one more */
 		len_a -= len;
 		p = intel_pt_last_psb(buf_a, len_a);
 		if (!p)
 			return buf_b; /* No full PSB+ => assume no overlap */
 		len = len_a - (p - buf_a);
-		if (!intel_pt_next_tsc(p, len, &tsc_a))
+		if (!intel_pt_next_tsc(p, len, &tsc_a, &rem_a))
 			return buf_b; /* No TSC in buf_a => assume no overlap */
 	}
 
 	while (1) {
 		/* Ignore PSB+ with no TSC */
-		if (intel_pt_next_tsc(buf_b, len_b, &tsc_b) &&
-		    intel_pt_tsc_cmp(tsc_a, tsc_b) < 0)
-			return buf_b; /* tsc_a < tsc_b => no overlap */
+		if (intel_pt_next_tsc(buf_b, len_b, &tsc_b, &rem_b)) {
+			int cmp = intel_pt_tsc_cmp(tsc_a, tsc_b);
+
+			/* Same TSC, so buffers are consecutive */
+			if (!cmp && rem_b >= rem_a) {
+				*consecutive = true;
+				return buf_b + len_b - (rem_b - rem_a);
+			}
+			if (cmp < 0)
+				return buf_b; /* tsc_a < tsc_b => no overlap */
+		}
 
 		if (!intel_pt_step_psb(&buf_b, &len_b))
 			return buf_b + len_b; /* No PSB in buf_b => no data */

@@ -2606,6 +2611,8 @@ static unsigned char *intel_pt_find_overlap_tsc(unsigned char *buf_a,
  * @buf_b: second buffer
  * @len_b: size of second buffer
  * @have_tsc: can use TSC packets to detect overlap
+ * @consecutive: returns true if there is data in buf_b that is consecutive
+ *               to buf_a
  *
  * When trace samples or snapshots are recorded there is the possibility that
  * the data overlaps.  Note that, for the purposes of decoding, data is only

@@ -2616,7 +2623,7 @@ static unsigned char *intel_pt_find_overlap_tsc(unsigned char *buf_a,
  */
 unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a,
 				     unsigned char *buf_b, size_t len_b,
-				     bool have_tsc)
+				     bool have_tsc, bool *consecutive)
 {
 	unsigned char *found;
 

@@ -2628,7 +2635,8 @@ unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a,
 		return buf_b; /* No overlap */
 
 	if (have_tsc) {
-		found = intel_pt_find_overlap_tsc(buf_a, len_a, buf_b, len_b);
+		found = intel_pt_find_overlap_tsc(buf_a, len_a, buf_b, len_b,
+						  consecutive);
 		if (found)
 			return found;
 	}

@@ -2643,28 +2651,16 @@ unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a,
 	}
 
 	/* Now len_b >= len_a */
-	if (len_b > len_a) {
-		/* The leftover buffer 'b' must start at a PSB */
-		while (!intel_pt_at_psb(buf_b + len_a, len_b - len_a)) {
-			if (!intel_pt_step_psb(&buf_a, &len_a))
-				return buf_b; /* No overlap */
-		}
-	}
-
 	while (1) {
 		/* Potential overlap so check the bytes */
 		found = memmem(buf_a, len_a, buf_b, len_a);
-		if (found)
+		if (found) {
+			*consecutive = true;
 			return buf_b + len_a;
+		}
 
 		/* Try again at next PSB in buffer 'a' */
 		if (!intel_pt_step_psb(&buf_a, &len_a))
 			return buf_b; /* No overlap */
-
-		/* The leftover buffer 'b' must start at a PSB */
-		while (!intel_pt_at_psb(buf_b + len_a, len_b - len_a)) {
-			if (!intel_pt_step_psb(&buf_a, &len_a))
-				return buf_b; /* No overlap */
-		}
 	}
 }

index 921b22e8ca0e..fc1752d50019 100644
@@ -117,7 +117,7 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder);
 
 unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a,
 				     unsigned char *buf_b, size_t len_b,
-				     bool have_tsc);
+				     bool have_tsc, bool *consecutive);
 
 int intel_pt__strerror(int code, char *buf, size_t buflen);
 

index 3773d9c54f45..4a7746249999 100644
@@ -207,14 +207,17 @@ static void intel_pt_dump_event(struct intel_pt *pt, unsigned char *buf,
 static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *a,
 				   struct auxtrace_buffer *b)
 {
+	bool consecutive = false;
 	void *start;
 
 	start = intel_pt_find_overlap(a->data, a->size, b->data, b->size,
-				      pt->have_tsc);
+				      pt->have_tsc, &consecutive);
 	if (!start)
 		return -EINVAL;
 	b->use_size = b->data + b->size - start;
 	b->use_data = start;
+	if (b->use_size && consecutive)
+		b->consecutive = true;
 	return 0;
 }
 

index 4a7746249999..0979a6e8b2b7 100644
@@ -143,6 +143,7 @@ struct intel_pt_queue {
 	bool stop;
 	bool step_through_buffers;
 	bool use_buffer_pid_tid;
+	bool sync_switch;
 	pid_t pid, tid;
 	int cpu;
 	int switch_state;

@@ -963,10 +964,12 @@ static int intel_pt_setup_queue(struct intel_pt *pt,
 			if (pt->timeless_decoding || !pt->have_sched_switch)
 				ptq->use_buffer_pid_tid = true;
 		}
+
+		ptq->sync_switch = pt->sync_switch;
 	}
 
 	if (!ptq->on_heap &&
-	    (!pt->sync_switch ||
+	    (!ptq->sync_switch ||
 	     ptq->switch_state != INTEL_PT_SS_EXPECTING_SWITCH_EVENT)) {
 		const struct intel_pt_state *state;
 		int ret;

@@ -1549,7 +1552,7 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 	if (pt->synth_opts.last_branch)
 		intel_pt_update_last_branch_rb(ptq);
 
-	if (!pt->sync_switch)
+	if (!ptq->sync_switch)
 		return 0;
 
 	if (intel_pt_is_switch_ip(ptq, state->to_ip)) {

@@ -1630,6 +1633,21 @@ static u64 intel_pt_switch_ip(struct intel_pt *pt, u64 *ptss_ip)
 	return switch_ip;
 }
 
+static void intel_pt_enable_sync_switch(struct intel_pt *pt)
+{
+	unsigned int i;
+
+	pt->sync_switch = true;
+
+	for (i = 0; i < pt->queues.nr_queues; i++) {
+		struct auxtrace_queue *queue = &pt->queues.queue_array[i];
+		struct intel_pt_queue *ptq = queue->priv;
+
+		if (ptq)
+			ptq->sync_switch = true;
+	}
+}
+
 static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp)
 {
 	const struct intel_pt_state *state = ptq->state;

@@ -1646,7 +1664,7 @@ static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp)
 			if (pt->switch_ip) {
 				intel_pt_log("switch_ip: %"PRIx64" ptss_ip: %"PRIx64"\n",
 					     pt->switch_ip, pt->ptss_ip);
-				pt->sync_switch = true;
+				intel_pt_enable_sync_switch(pt);
 			}
 		}
 	}

@@ -1662,9 +1680,9 @@ static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp)
 		if (state->err) {
 			if (state->err == INTEL_PT_ERR_NODATA)
 				return 1;
-			if (pt->sync_switch &&
+			if (ptq->sync_switch &&
 			    state->from_ip >= pt->kernel_start) {
-				pt->sync_switch = false;
+				ptq->sync_switch = false;
 				intel_pt_next_tid(pt, ptq);
 			}
 			if (pt->synth_opts.errors) {

@@ -1690,7 +1708,7 @@ static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp)
 				     state->timestamp, state->est_timestamp);
 			ptq->timestamp = state->est_timestamp;
 		/* Use estimated TSC in unknown switch state */
-		} else if (pt->sync_switch &&
+		} else if (ptq->sync_switch &&
 			   ptq->switch_state == INTEL_PT_SS_UNKNOWN &&
 			   intel_pt_is_switch_ip(ptq, state->to_ip) &&
 			   ptq->next_tid == -1) {

@@ -1837,7 +1855,7 @@ static int intel_pt_sync_switch(struct intel_pt *pt, int cpu, pid_t tid,
 		return 1;
 
 	ptq = intel_pt_cpu_to_ptq(pt, cpu);
-	if (!ptq)
+	if (!ptq || !ptq->sync_switch)
 		return 1;
 
 	switch (ptq->switch_state) {

index 00f25f4b5f48..5e4d0bbafc8b 100644
@@ -1616,6 +1616,7 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder)
 		case INTEL_PT_PWRX:
 			intel_pt_log("ERROR: Missing TIP after FUP\n");
 			decoder->pkt_state = INTEL_PT_STATE_ERR3;
+			decoder->pkt_step = 0;
 			return -ENOENT;
 
 		case INTEL_PT_OVF:

index 5e4d0bbafc8b..f9157aed1289 100644
@@ -1378,6 +1378,7 @@ static int intel_pt_overflow(struct intel_pt_decoder *decoder)
 	intel_pt_clear_tx_flags(decoder);
 	decoder->have_tma = false;
 	decoder->cbr = 0;
+	decoder->timestamp_insn_cnt = 0;
 	decoder->pkt_state = INTEL_PT_STATE_ERR_RESYNC;
 	decoder->overflow = true;
 	return -EOVERFLOW;

index 6aa3f2a38321..b135af62011c 100644
@@ -37,15 +37,11 @@ struct auxtrace_record *auxtrace_record__init_intel(struct perf_evlist *evlist,
 	intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME);
 	intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME);
 
-	if (evlist) {
-		evlist__for_each_entry(evlist, evsel) {
-			if (intel_pt_pmu &&
-			    evsel->attr.type == intel_pt_pmu->type)
-				found_pt = true;
-			if (intel_bts_pmu &&
-			    evsel->attr.type == intel_bts_pmu->type)
-				found_bts = true;
-		}
+	evlist__for_each_entry(evlist, evsel) {
+		if (intel_pt_pmu && evsel->attr.type == intel_pt_pmu->type)
+			found_pt = true;
+		if (intel_bts_pmu && evsel->attr.type == intel_bts_pmu->type)
+			found_bts = true;
 	}
 
 	if (found_pt && found_bts) {

index 0979a6e8b2b7..cfb3614f5def 100644
@@ -222,32 +222,6 @@ static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *
 	return 0;
 }
 
-static void intel_pt_use_buffer_pid_tid(struct intel_pt_queue *ptq,
-					struct auxtrace_queue *queue,
-					struct auxtrace_buffer *buffer)
-{
-	if (queue->cpu == -1 && buffer->cpu != -1)
-		ptq->cpu = buffer->cpu;
-
-	ptq->pid = buffer->pid;
-	ptq->tid = buffer->tid;
-
-	intel_pt_log("queue %u cpu %d pid %d tid %d\n",
-		     ptq->queue_nr, ptq->cpu, ptq->pid, ptq->tid);
-
-	thread__zput(ptq->thread);
-
-	if (ptq->tid != -1) {
-		if (ptq->pid != -1)
-			ptq->thread = machine__findnew_thread(ptq->pt->machine,
-							      ptq->pid,
-							      ptq->tid);
-		else
-			ptq->thread = machine__find_thread(ptq->pt->machine, -1,
-							   ptq->tid);
-	}
-}
-
 /* This function assumes data is processed sequentially only */
 static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
 {