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

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

User visible changes:

  - Fix UI bug after zoom into thread/dso/symbol and another, after fold/unfold,
    in the TUI hists browser (He Kuang)

  - Fixes for 'perf probe' to better handle aliased symbols, for instance in glibc (Masami Hiramatsu, Namhyung Kim)

  - 'perf kmem' improvements and fixes: (Namhyung Kim)
    - Fix segfault when invalid sort key is given
    - Allow -v option
    - Fix alignment of slab result table

  - 'perf stat' improvements and fixes: (Andi Kleen)
    - Output running time and run/enabled ratio in CSV mode
    - Fix IPC and other formulas with -A
    - Always correctly indent ratio column

  - Add tracepoint events fields CTF conversion support to 'perf data' (Sebastian Andrzej Siewior)

Infrastructure changes:

  - Output feature detection's gcc output to a file, to help in debugging (Arnaldo Carvalho de Melo)

  - Fix 'perf probe' compiles due to declarations using perf_probe_point (David Ahern)

  - Fix possible double free on error in 'perf probe' (He Kuang)

  - Remove superfluous thread->comm_set setting (Jiri Olsa)

  - Fix libbabeltrace detection (Jiri Olsa)

  - More work on separating ordered_events code out of perf_session (Arnaldo Carvalho de Melo)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

31 files changed, 673 insertions, 205 deletions

diff --git a/tools/perf/Documentation/perf-kmem.txt b/tools/perf/Documentation/perf-kmem.txt
index 7c8fbbf3f61c..150253cc3c97 100644
--- a/tools/perf/Documentation/perf-kmem.txt
+++ b/tools/perf/Documentation/perf-kmem.txt
@@ -25,6 +25,10 @@ OPTIONS
 --input=<file>::
 	Select the input file (default: perf.data unless stdin is a fifo)
 
+-v::
+--verbose::
+        Be more verbose. (show symbol address, etc)
+
 --caller::
 	Show per-callsite statistics
 
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index ec4c063ed9f3..933d70345f87 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -529,6 +529,7 @@ clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean config-clean
 	$(Q)$(RM) .config-detected
 	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32
 	$(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-FEATURES $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex*
+	$(call QUIET_CLEAN, feature-detect) $(RM) $(OUTPUT)config/feature-checks/.make-*.output
 	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
 	$(python-clean)
 
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 747f86103599..71bf7451c0ca 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -208,7 +208,7 @@ static int __cmd_annotate(struct perf_annotate *ann)
 			goto out;
 	}
 
-	ret = perf_session__process_events(session, &ann->tool);
+	ret = perf_session__process_events(session);
 	if (ret)
 		goto out;
 
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index ed3873b3e238..feb420f74c2d 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -74,7 +74,7 @@ static int perf_session__list_build_ids(bool force, bool with_hits)
 	 * the record stream. Buildids are stored as RECORD_HEADER_BUILD_ID
 	 */
 	if (with_hits || perf_data_file__is_pipe(&file))
-		perf_session__process_events(session, &build_id__mark_dso_hit_ops);
+		perf_session__process_events(session);
 
 	perf_session__fprintf_dsos_buildid(session, stdout, dso__skip_buildid, with_hits);
 	perf_session__delete(session);
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 74aada554b12..f800fc95f5d7 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -747,7 +747,7 @@ static int __cmd_diff(void)
 			goto out_delete;
 		}
 
-		ret = perf_session__process_events(d->session, &tool);
+		ret = perf_session__process_events(d->session);
 		if (ret) {
 			pr_err("Failed to process %s\n", d->file.path);
 			goto out_delete;
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index a13641e066f5..ea46df25368c 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -53,6 +53,13 @@ static int perf_event__repipe_synth(struct perf_tool *tool,
 	return 0;
 }
 
+static int perf_event__repipe_oe_synth(struct perf_tool *tool,
+				       union perf_event *event,
+				       struct ordered_events *oe __maybe_unused)
+{
+	return perf_event__repipe_synth(tool, event);
+}
+
 static int perf_event__repipe_op2_synth(struct perf_tool *tool,
 					union perf_event *event,
 					struct perf_session *session
@@ -359,8 +366,6 @@ static int __cmd_inject(struct perf_inject *inject)
 	} else if (inject->sched_stat) {
 		struct perf_evsel *evsel;
 
-		inject->tool.ordered_events = true;
-
 		evlist__for_each(session->evlist, evsel) {
 			const char *name = perf_evsel__name(evsel);
 
@@ -379,7 +384,7 @@ static int __cmd_inject(struct perf_inject *inject)
 	if (!file_out->is_pipe)
 		lseek(fd, session->header.data_offset, SEEK_SET);
 
-	ret = perf_session__process_events(session, &inject->tool);
+	ret = perf_session__process_events(session);
 
 	if (!file_out->is_pipe) {
 		if (inject->build_ids)
@@ -408,7 +413,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 			.unthrottle	= perf_event__repipe,
 			.attr		= perf_event__repipe_attr,
 			.tracing_data	= perf_event__repipe_op2_synth,
-			.finished_round	= perf_event__repipe_op2_synth,
+			.finished_round	= perf_event__repipe_oe_synth,
 			.build_id	= perf_event__repipe_op2_synth,
 			.id_index	= perf_event__repipe_op2_synth,
 		},
@@ -458,6 +463,8 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 		return -1;
 	}
 
+	inject.tool.ordered_events = inject.sched_stat;
+
 	file.path = inject.input_name;
 	inject.session = perf_session__new(&file, true, &inject.tool);
 	if (inject.session == NULL)
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index f295141025bc..8c85aeb3327a 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -275,10 +275,10 @@ static void __print_result(struct rb_root *root, struct perf_session *session,
 	struct rb_node *next;
 	struct machine *machine = &session->machines.host;
 
-	printf("%.102s\n", graph_dotted_line);
+	printf("%.105s\n", graph_dotted_line);
 	printf(" %-34s |",  is_caller ? "Callsite": "Alloc Ptr");
 	printf(" Total_alloc/Per | Total_req/Per   | Hit      | Ping-pong | Frag\n");
-	printf("%.102s\n", graph_dotted_line);
+	printf("%.105s\n", graph_dotted_line);
 
 	next = rb_first(root);
 
@@ -304,7 +304,7 @@ static void __print_result(struct rb_root *root, struct perf_session *session,
 			snprintf(buf, sizeof(buf), "%#" PRIx64 "", addr);
 		printf(" %-34s |", buf);
 
-		printf(" %9llu/%-5lu | %9llu/%-5lu | %8lu | %8lu | %6.3f%%\n",
+		printf(" %9llu/%-5lu | %9llu/%-5lu | %8lu | %9lu | %6.3f%%\n",
 		       (unsigned long long)data->bytes_alloc,
 		       (unsigned long)data->bytes_alloc / data->hit,
 		       (unsigned long long)data->bytes_req,
@@ -317,9 +317,9 @@ static void __print_result(struct rb_root *root, struct perf_session *session,
 	}
 
 	if (n_lines == -1)
-		printf(" ...                                | ...             | ...             | ...    | ...      | ...   \n");
+		printf(" ...                                | ...             | ...             | ...      | ...       | ...   \n");
 
-	printf("%.102s\n", graph_dotted_line);
+	printf("%.105s\n", graph_dotted_line);
 }
 
 static void print_summary(void)
@@ -426,7 +426,7 @@ static int __cmd_kmem(struct perf_session *session)
 	}
 
 	setup_pager();
-	err = perf_session__process_events(session, &perf_kmem);
+	err = perf_session__process_events(session);
 	if (err != 0)
 		goto out;
 	sort_result();
@@ -559,6 +559,7 @@ static int setup_sorting(struct list_head *sort_list, const char *arg)
 {
 	char *tok;
 	char *str = strdup(arg);
+	char *pos = str;
 
 	if (!str) {
 		pr_err("%s: strdup failed\n", __func__);
@@ -566,7 +567,7 @@ static int setup_sorting(struct list_head *sort_list, const char *arg)
 	}
 
 	while (true) {
-		tok = strsep(&str, ",");
+		tok = strsep(&pos, ",");
 		if (!tok)
 			break;
 		if (sort_dimension__add(tok, sort_list) < 0) {
@@ -662,6 +663,8 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 	const char * const default_sort_order = "frag,hit,bytes";
 	const struct option kmem_options[] = {
 	OPT_STRING('i', "input", &input_name, "file", "input file name"),
+	OPT_INCR('v', "verbose", &verbose,
+		    "be more verbose (show symbol address, etc)"),
 	OPT_CALLBACK_NOOPT(0, "caller", NULL, NULL,
 			   "show per-callsite statistics", parse_caller_opt),
 	OPT_CALLBACK_NOOPT(0, "alloc", NULL, NULL,
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 0894a817f67e..643722f40075 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -18,6 +18,7 @@
 #include "util/stat.h"
 #include "util/top.h"
 #include "util/data.h"
+#include "util/ordered-events.h"
 
 #include <sys/prctl.h>
 #ifdef HAVE_TIMERFD_SUPPORT
@@ -730,9 +731,9 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
 			return -1;
 		}
 
-		err = perf_session_queue_event(kvm->session, event, &kvm->tool, &sample, 0);
+		err = perf_session__queue_event(kvm->session, event, &sample, 0);
 		/*
-		 * FIXME: Here we can't consume the event, as perf_session_queue_event will
+		 * 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_evlist__mmap_consume(kvm->evlist, idx);
@@ -783,8 +784,10 @@ static int perf_kvm__mmap_read(struct perf_kvm_stat *kvm)
 
 	/* flush queue after each round in which we processed events */
 	if (ntotal) {
-		kvm->session->ordered_events.next_flush = flush_time;
-		err = kvm->tool.finished_round(&kvm->tool, NULL, kvm->session);
+		struct ordered_events *oe = &kvm->session->ordered_events;
+
+		oe->next_flush = flush_time;
+		err = ordered_events__flush(oe, OE_FLUSH__ROUND);
 		if (err) {
 			if (kvm->lost_events)
 				pr_info("\nLost events: %" PRIu64 "\n\n",
@@ -1066,7 +1069,7 @@ static int read_events(struct perf_kvm_stat *kvm)
 	if (ret < 0)
 		return ret;
 
-	return perf_session__process_events(kvm->session, &kvm->tool);
+	return perf_session__process_events(kvm->session);
 }
 
 static int parse_target_str(struct perf_kvm_stat *kvm)
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index e7ec71589da6..7893a9bba2a7 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -878,7 +878,7 @@ static int __cmd_report(bool display_info)
 	if (select_key())
 		goto out_delete;
 
-	err = perf_session__process_events(session, &eops);
+	err = perf_session__process_events(session);
 	if (err)
 		goto out_delete;
 
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 9b5663950a4d..46c69318de84 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -141,7 +141,7 @@ static int report_raw_events(struct perf_mem *mem)
 
 	printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
 
-	err = perf_session__process_events(session, &mem->tool);
+	err = perf_session__process_events(session);
 	if (err)
 		return err;
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4fdad06d37db..5a2ff510b75b 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -225,7 +225,7 @@ static int process_buildids(struct record *rec)
 	 */
 	symbol_conf.ignore_vmlinux_buildid = true;
 
-	return perf_session__process_events(session, &rec->tool);
+	return perf_session__process_events(session);
 }
 
 static void perf_event__synthesize_guest_os(struct machine *machine, void *data)
@@ -343,7 +343,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	signal(SIGINT, sig_handler);
 	signal(SIGTERM, sig_handler);
 
-	session = perf_session__new(file, false, NULL);
+	session = perf_session__new(file, false, tool);
 	if (session == NULL) {
 		pr_err("Perf session creation failed.\n");
 		return -1;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index fb350343b1d7..52f74e1367e9 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -482,7 +482,7 @@ static int __cmd_report(struct report *rep)
 	if (ret)
 		return ret;
 
-	ret = perf_session__process_events(session, &rep->tool);
+	ret = perf_session__process_events(session);
 	if (ret)
 		return ret;
 
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index a3ebf1d3c29d..3b3a5bb97059 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1467,7 +1467,7 @@ static int perf_sched__read_events(struct perf_sched *sched)
 		goto out_delete;
 
 	if (perf_session__has_traces(session, "record -R")) {
-		int err = perf_session__process_events(session, &sched->tool);
+		int err = perf_session__process_events(session);
 		if (err) {
 			pr_err("Failed to process events, error %d", err);
 			goto out_delete;
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index ce304dfd962a..c7e6750923ef 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -800,7 +800,7 @@ static int __cmd_script(struct perf_script *script)
 		script->tool.mmap2 = process_mmap2_event;
 	}
 
-	ret = perf_session__process_events(script->session, &script->tool);
+	ret = perf_session__process_events(script->session);
 
 	if (debug_mode)
 		pr_err("Misordered timestamps: %" PRIu64 "\n", nr_unordered);
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index d28949d210cc..d4d1b77da0bd 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -353,39 +353,40 @@ static struct perf_evsel *nth_evsel(int n)
  * more semantic information such as miss/hit ratios,
  * instruction rates, etc:
  */
-static void update_shadow_stats(struct perf_evsel *counter, u64 *count)
+static void update_shadow_stats(struct perf_evsel *counter, u64 *count,
+				int cpu)
 {
 	if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
-		update_stats(&runtime_nsecs_stats[0], count[0]);
+		update_stats(&runtime_nsecs_stats[cpu], count[0]);
 	else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
-		update_stats(&runtime_cycles_stats[0], count[0]);
+		update_stats(&runtime_cycles_stats[cpu], count[0]);
 	else if (transaction_run &&
 		 perf_evsel__cmp(counter, nth_evsel(T_CYCLES_IN_TX)))
-		update_stats(&runtime_cycles_in_tx_stats[0], count[0]);
+		update_stats(&runtime_cycles_in_tx_stats[cpu], count[0]);
 	else if (transaction_run &&
 		 perf_evsel__cmp(counter, nth_evsel(T_TRANSACTION_START)))
-		update_stats(&runtime_transaction_stats[0], count[0]);
+		update_stats(&runtime_transaction_stats[cpu], count[0]);
 	else if (transaction_run &&
 		 perf_evsel__cmp(counter, nth_evsel(T_ELISION_START)))
-		update_stats(&runtime_elision_stats[0], count[0]);
+		update_stats(&runtime_elision_stats[cpu], count[0]);
 	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
-		update_stats(&runtime_stalled_cycles_front_stats[0], count[0]);
+		update_stats(&runtime_stalled_cycles_front_stats[cpu], count[0]);
 	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
-		update_stats(&runtime_stalled_cycles_back_stats[0], count[0]);
+		update_stats(&runtime_stalled_cycles_back_stats[cpu], count[0]);
 	else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
-		update_stats(&runtime_branches_stats[0], count[0]);
+		update_stats(&runtime_branches_stats[cpu], count[0]);
 	else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
-		update_stats(&runtime_cacherefs_stats[0], count[0]);
+		update_stats(&runtime_cacherefs_stats[cpu], count[0]);
 	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
-		update_stats(&runtime_l1_dcache_stats[0], count[0]);
+		update_stats(&runtime_l1_dcache_stats[cpu], count[0]);
 	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
-		update_stats(&runtime_l1_icache_stats[0], count[0]);
+		update_stats(&runtime_l1_icache_stats[cpu], count[0]);
 	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL))
-		update_stats(&runtime_ll_cache_stats[0], count[0]);
+		update_stats(&runtime_ll_cache_stats[cpu], count[0]);
 	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
-		update_stats(&runtime_dtlb_cache_stats[0], count[0]);
+		update_stats(&runtime_dtlb_cache_stats[cpu], count[0]);
 	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
-		update_stats(&runtime_itlb_cache_stats[0], count[0]);
+		update_stats(&runtime_itlb_cache_stats[cpu], count[0]);
 }
 
 static void zero_per_pkg(struct perf_evsel *counter)
@@ -447,7 +448,8 @@ static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused,
 			perf_evsel__compute_deltas(evsel, cpu, count);
 		perf_counts_values__scale(count, scale, NULL);
 		evsel->counts->cpu[cpu] = *count;
-		update_shadow_stats(evsel, count->values);
+		if (aggr_mode == AGGR_NONE)
+			update_shadow_stats(evsel, count->values, cpu);
 		break;
 	case AGGR_GLOBAL:
 		aggr->val += count->val;
@@ -495,7 +497,7 @@ static int read_counter_aggr(struct perf_evsel *counter)
 	/*
 	 * Save the full runtime - to allow normalization during printout:
 	 */
-	update_shadow_stats(counter, count);
+	update_shadow_stats(counter, count, 0);
 
 	return 0;
 }
@@ -769,6 +771,19 @@ static int run_perf_stat(int argc, const char **argv)
 	return ret;
 }
 
+static void print_running(u64 run, u64 ena)
+{
+	if (csv_output) {
+		fprintf(output, "%s%" PRIu64 "%s%.2f",
+					csv_sep,
+					run,
+					csv_sep,
+					ena ? 100.0 * run / ena : 100.0);
+	} else if (run != ena) {
+		fprintf(output, "  (%.2f%%)", 100.0 * run / ena);
+	}
+}
+
 static void print_noise_pct(double total, double avg)
 {
 	double pct = rel_stddev_stats(total, avg);
@@ -1079,6 +1094,8 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 		if (total) {
 			ratio = avg / total;
 			fprintf(output, " #   %5.2f  insns per cycle        ", ratio);
+		} else {
+			fprintf(output, "                                   ");
 		}
 		total = avg_stats(&runtime_stalled_cycles_front_stats[cpu]);
 		total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[cpu]));
@@ -1148,6 +1165,8 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 		if (total) {
 			ratio = avg / total;
 			fprintf(output, " # %8.3f GHz                    ", ratio);
+		} else {
+			fprintf(output, "                                   ");
 		}
 	} else if (transaction_run &&
 		   perf_evsel__cmp(evsel, nth_evsel(T_CYCLES_IN_TX))) {
@@ -1252,6 +1271,7 @@ static void print_aggr(char *prefix)
 					fprintf(output, "%s%s",
 						csv_sep, counter->cgrp->name);
 
+				print_running(run, ena);
 				fputc('\n', output);
 				continue;
 			}
@@ -1262,13 +1282,10 @@ static void print_aggr(char *prefix)
 			else
 				abs_printout(id, nr, counter, uval);
 
-			if (!csv_output) {
+			if (!csv_output)
 				print_noise(counter, 1.0);
 
-				if (run != ena)
-					fprintf(output, "  (%.2f%%)",
-						100.0 * run / ena);
-			}
+			print_running(run, ena);
 			fputc('\n', output);
 		}
 	}
@@ -1284,6 +1301,10 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 	double avg = avg_stats(&ps->res_stats[0]);
 	int scaled = counter->counts->scaled;
 	double uval;
+	double avg_enabled, avg_running;
+
+	avg_enabled = avg_stats(&ps->res_stats[1]);
+	avg_running = avg_stats(&ps->res_stats[2]);
 
 	if (prefix)
 		fprintf(output, "%s", prefix);
@@ -1303,6 +1324,7 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 		if (counter->cgrp)
 			fprintf(output, "%s%s", csv_sep, counter->cgrp->name);
 
+		print_running(avg_running, avg_enabled);
 		fputc('\n', output);
 		return;
 	}
@@ -1316,19 +1338,7 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 
 	print_noise(counter, avg);
 
-	if (csv_output) {
-		fputc('\n', output);
-		return;
-	}
-
-	if (scaled) {
-		double avg_enabled, avg_running;
-
-		avg_enabled = avg_stats(&ps->res_stats[1]);
-		avg_running = avg_stats(&ps->res_stats[2]);
-
-		fprintf(output, " [%5.2f%%]", 100 * avg_running / avg_enabled);
-	}
+	print_running(avg_running, avg_enabled);
 	fprintf(output, "\n");
 }
 
@@ -1370,6 +1380,7 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 				fprintf(output, "%s%s",
 					csv_sep, counter->cgrp->name);
 
+			print_running(run, ena);
 			fputc('\n', output);
 			continue;
 		}
@@ -1381,13 +1392,10 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 		else
 			abs_printout(cpu, 0, counter, uval);
 
-		if (!csv_output) {
+		if (!csv_output)
 			print_noise(counter, 1.0);
+		print_running(run, ena);
 
-			if (run != ena)
-				fprintf(output, "  (%.2f%%)",
-					100.0 * run / ena);
-		}
 		fputc('\n', output);
 	}
 }
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index f3bb1a4bf060..51440d1fc722 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -1623,7 +1623,7 @@ static int __cmd_timechart(struct timechart *tchart, const char *output_name)
 		goto out_delete;
 	}
 
-	ret = perf_session__process_events(session, &tchart->tool);
+	ret = perf_session__process_events(session);
 	if (ret)
 		goto out_delete;
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 211614fba217..6969ba98ff2f 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2408,7 +2408,7 @@ static int trace__replay(struct trace *trace)
 
 	setup_pager();
 
-	err = perf_session__process_events(session, &trace->tool);
+	err = perf_session__process_events(session);
 	if (err)
 		pr_err("Failed to process events, error %d", err);
 
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index d44c64d64465..bd097187724b 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -184,7 +184,7 @@ endif
 
 feature_check = $(eval $(feature_check_code))
 define feature_check_code
-  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" -C config/feature-checks test-$1.bin >/dev/null 2>/dev/null && echo 1 || echo 0)
+  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" -C config/feature-checks test-$1.bin > $(OUTPUT)config/feature-checks/.make-$(1).output 2>&1 && echo 1 || echo 0)
 endef
 
 feature_set = $(eval $(feature_set_code))
diff --git a/tools/perf/config/feature-checks/test-libbabeltrace.c b/tools/perf/config/feature-checks/test-libbabeltrace.c
index 3b7dd68a4d52..9cf802a04885 100644
--- a/tools/perf/config/feature-checks/test-libbabeltrace.c
+++ b/tools/perf/config/feature-checks/test-libbabeltrace.c
@@ -1,5 +1,6 @@
 
 #include <babeltrace/ctf-writer/writer.h>
+#include <babeltrace/ctf-ir/stream-class.h>
 
 int main(void)
 {
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index ad312d91caed..49eddeb81458 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -48,6 +48,24 @@ static bool hist_browser__has_filter(struct hist_browser *hb)
 	return hists__has_filter(hb->hists) || hb->min_pcnt;
 }
 
+static int hist_browser__get_folding(struct hist_browser *browser)
+{
+	struct rb_node *nd;
+	struct hists *hists = browser->hists;
+	int unfolded_rows = 0;
+
+	for (nd = rb_first(&hists->entries);
+	     (nd = hists__filter_entries(nd, browser->min_pcnt)) != NULL;
+	     nd = rb_next(nd)) {
+		struct hist_entry *he =
+			rb_entry(nd, struct hist_entry, rb_node);
+
+		if (he->ms.unfolded)
+			unfolded_rows += he->nr_rows;
+	}
+	return unfolded_rows;
+}
+
 static u32 hist_browser__nr_entries(struct hist_browser *hb)
 {
 	u32 nr_entries;
@@ -57,6 +75,7 @@ static u32 hist_browser__nr_entries(struct hist_browser *hb)
 	else
 		nr_entries = hb->hists->nr_entries;
 
+	hb->nr_callchain_rows = hist_browser__get_folding(hb);
 	return nr_entries + hb->nr_callchain_rows;
 }
 
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index e372e03ff480..c6d62268cc2a 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -126,6 +126,177 @@ FUNC_VALUE_SET(s64)
 FUNC_VALUE_SET(u64)
 __FUNC_VALUE_SET(u64_hex, u64)
 
+static struct bt_ctf_field_type*
+get_tracepoint_field_type(struct ctf_writer *cw, struct format_field *field)
+{
+	unsigned long flags = field->flags;
+
+	if (flags & FIELD_IS_STRING)
+		return cw->data.string;
+
+	if (!(flags & FIELD_IS_SIGNED)) {
+		/* unsigned long are mostly pointers */
+		if (flags & FIELD_IS_LONG || flags & FIELD_IS_POINTER)
+			return cw->data.u64_hex;
+	}
+
+	if (flags & FIELD_IS_SIGNED) {
+		if (field->size == 8)
+			return cw->data.s64;
+		else
+			return cw->data.s32;
+	}
+
+	if (field->size == 8)
+		return cw->data.u64;
+	else
+		return cw->data.u32;
+}
+
+static int add_tracepoint_field_value(struct ctf_writer *cw,
+				      struct bt_ctf_event_class *event_class,
+				      struct bt_ctf_event *event,
+				      struct perf_sample *sample,
+				      struct format_field *fmtf)
+{
+	struct bt_ctf_field_type *type;
+	struct bt_ctf_field *array_field;
+	struct bt_ctf_field *field;
+	const char *name = fmtf->name;
+	void *data = sample->raw_data;
+	unsigned long long value_int;
+	unsigned long flags = fmtf->flags;
+	unsigned int n_items;
+	unsigned int i;
+	unsigned int offset;
+	unsigned int len;
+	int ret;
+
+	offset = fmtf->offset;
+	len = fmtf->size;
+	if (flags & FIELD_IS_STRING)
+		flags &= ~FIELD_IS_ARRAY;
+
+	if (flags & FIELD_IS_DYNAMIC) {
+		unsigned long long tmp_val;
+
+		tmp_val = pevent_read_number(fmtf->event->pevent,
+				data + offset, len);
+		offset = tmp_val;
+		len = offset >> 16;
+		offset &= 0xffff;
+	}
+
+	if (flags & FIELD_IS_ARRAY) {
+
+		type = bt_ctf_event_class_get_field_by_name(
+				event_class, name);
+		array_field = bt_ctf_field_create(type);
+		bt_ctf_field_type_put(type);
+		if (!array_field) {
+			pr_err("Failed to create array type %s\n", name);
+			return -1;
+		}
+
+		len = fmtf->size / fmtf->arraylen;
+		n_items = fmtf->arraylen;
+	} else {
+		n_items = 1;
+		array_field = NULL;
+	}
+
+	type = get_tracepoint_field_type(cw, fmtf);
+
+	for (i = 0; i < n_items; i++) {
+		if (!(flags & FIELD_IS_STRING))
+			value_int = pevent_read_number(
+					fmtf->event->pevent,
+					data + offset + i * len, len);
+
+		if (flags & FIELD_IS_ARRAY)
+			field = bt_ctf_field_array_get_field(array_field, i);
+		else
+			field = bt_ctf_field_create(type);
+
+		if (!field) {
+			pr_err("failed to create a field %s\n", name);
+			return -1;
+		}
+
+		if (flags & FIELD_IS_STRING)
+			ret = bt_ctf_field_string_set_value(field,
+					data + offset + i * len);
+		else if (!(flags & FIELD_IS_SIGNED))
+			ret = bt_ctf_field_unsigned_integer_set_value(
+					field, value_int);
+		else
+			ret = bt_ctf_field_signed_integer_set_value(
+					field, value_int);
+		if (ret) {
+			pr_err("failed to set file value %s\n", name);
+			goto err_put_field;
+		}
+		if (!(flags & FIELD_IS_ARRAY)) {
+			ret = bt_ctf_event_set_payload(event, name, field);
+			if (ret) {
+				pr_err("failed to set payload %s\n", name);
+				goto err_put_field;
+			}
+		}
+		bt_ctf_field_put(field);
+	}
+	if (flags & FIELD_IS_ARRAY) {
+		ret = bt_ctf_event_set_payload(event, name, array_field);
+		if (ret) {
+			pr_err("Failed add payload array %s\n", name);
+			return -1;
+		}
+		bt_ctf_field_put(array_field);
+	}
+	return 0;
+
+err_put_field:
+	bt_ctf_field_put(field);
+	return -1;
+}
+
+static int add_tracepoint_fields_values(struct ctf_writer *cw,
+					struct bt_ctf_event_class *event_class,
+					struct bt_ctf_event *event,
+					struct format_field *fields,
+					struct perf_sample *sample)
+{
+	struct format_field *field;
+	int ret;
+
+	for (field = fields; field; field = field->next) {
+		ret = add_tracepoint_field_value(cw, event_class, event, sample,
+				field);
+		if (ret)
+			return -1;
+	}
+	return 0;
+}
+
+static int add_tracepoint_values(struct ctf_writer *cw,
+				 struct bt_ctf_event_class *event_class,
+				 struct bt_ctf_event *event,
+				 struct perf_evsel *evsel,
+				 struct perf_sample *sample)
+{
+	struct format_field *common_fields = evsel->tp_format->format.common_fields;
+	struct format_field *fields        = evsel->tp_format->format.fields;
+	int ret;
+
+	ret = add_tracepoint_fields_values(cw, event_class, event,
+					   common_fields, sample);
+	if (!ret)
+		ret = add_tracepoint_fields_values(cw, event_class, event,
+						   fields, sample);
+
+	return ret;
+}
+
 static int add_generic_values(struct ctf_writer *cw,
 			      struct bt_ctf_event *event,
 			      struct perf_evsel *evsel,
@@ -246,11 +417,76 @@ static int process_sample_event(struct perf_tool *tool,
 	if (ret)
 		return -1;
 
+	if (evsel->attr.type == PERF_TYPE_TRACEPOINT) {
+		ret = add_tracepoint_values(cw, event_class, event,
+					    evsel, sample);
+		if (ret)
+			return -1;
+	}
+
 	bt_ctf_stream_append_event(cw->stream, event);
 	bt_ctf_event_put(event);
 	return 0;
 }
 
+static int add_tracepoint_fields_types(struct ctf_writer *cw,
+				       struct format_field *fields,
+				       struct bt_ctf_event_class *event_class)
+{
+	struct format_field *field;
+	int ret;
+
+	for (field = fields; field; field = field->next) {
+		struct bt_ctf_field_type *type;
+		unsigned long flags = field->flags;
+
+		pr2("  field '%s'\n", field->name);
+
+		type = get_tracepoint_field_type(cw, field);
+		if (!type)
+			return -1;
+
+		/*
+		 * A string is an array of chars. For this we use the string
+		 * type and don't care that it is an array. What we don't
+		 * support is an array of strings.
+		 */
+		if (flags & FIELD_IS_STRING)
+			flags &= ~FIELD_IS_ARRAY;
+
+		if (flags & FIELD_IS_ARRAY)
+			type = bt_ctf_field_type_array_create(type, field->arraylen);
+
+		ret = bt_ctf_event_class_add_field(event_class, type,
+				field->name);
+
+		if (flags & FIELD_IS_ARRAY)
+			bt_ctf_field_type_put(type);
+
+		if (ret) {
+			pr_err("Failed to add field '%s\n", field->name);
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+static int add_tracepoint_types(struct ctf_writer *cw,
+				struct perf_evsel *evsel,
+				struct bt_ctf_event_class *class)
+{
+	struct format_field *common_fields = evsel->tp_format->format.common_fields;
+	struct format_field *fields        = evsel->tp_format->format.fields;
+	int ret;
+
+	ret = add_tracepoint_fields_types(cw, common_fields, class);
+	if (!ret)
+		ret = add_tracepoint_fields_types(cw, fields, class);
+
+	return ret;
+}
+
 static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel,
 			     struct bt_ctf_event_class *event_class)
 {
@@ -328,6 +564,12 @@ static int add_event(struct ctf_writer *cw, struct perf_evsel *evsel)
 	if (ret)
 		goto err;
 
+	if (evsel->attr.type == PERF_TYPE_TRACEPOINT) {
+		ret = add_tracepoint_types(cw, evsel, event_class);
+		if (ret)
+			goto err;
+	}
+
 	ret = bt_ctf_stream_class_add_event_class(cw->stream_class, event_class);
 	if (ret) {
 		pr("Failed to add event class into stream.\n");
@@ -579,7 +821,7 @@ int bt_convert__perf2ctf(const char *input, const char *path)
 		return -1;
 
 	/* perf.data session */
-	session = perf_session__new(&file, 0, NULL);
+	session = perf_session__new(&file, 0, &c.tool);
 	if (!session)
 		goto free_writer;
 
@@ -591,7 +833,7 @@ int bt_convert__perf2ctf(const char *input, const char *path)
 	if (setup_events(cw, session))
 		goto free_session;
 
-	err = perf_session__process_events(session, &c.tool);
+	err = perf_session__process_events(session);
 	if (!err)
 		err = bt_ctf_stream_flush(cw->stream);
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 95f5ab707b74..d9a6d35eda17 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1171,6 +1171,7 @@ static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h
 	/* force fold unfiltered entry for simplicity */
 	h->ms.unfolded = false;
 	h->row_offset = 0;
+	h->nr_rows = 0;
 
 	hists->stats.nr_non_filtered_samples += h->stat.nr_events;
 
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
index 077ddd25189f..6002fa3fcf77 100644
--- a/tools/perf/util/ordered-events.c
+++ b/tools/perf/util/ordered-events.c
@@ -131,8 +131,8 @@ static struct ordered_event *alloc_event(struct ordered_events *oe,
 	return new;
 }
 
-struct ordered_event *
-ordered_events__new(struct ordered_events *oe, u64 timestamp,
+static struct ordered_event *
+ordered_events__new_event(struct ordered_events *oe, u64 timestamp,
 		    union perf_event *event)
 {
 	struct ordered_event *new;
@@ -153,10 +153,38 @@ void ordered_events__delete(struct ordered_events *oe, struct ordered_event *eve
 	free_dup_event(oe, event->event);
 }
 
-static int __ordered_events__flush(struct perf_session *s,
-				   struct perf_tool *tool)
+int ordered_events__queue(struct ordered_events *oe, union perf_event *event,
+			  struct perf_sample *sample, u64 file_offset)
+{
+	u64 timestamp = sample->time;
+	struct ordered_event *oevent;
+
+	if (!timestamp || timestamp == ~0ULL)
+		return -ETIME;
+
+	if (timestamp < oe->last_flush) {
+		pr_oe_time(timestamp,      "out of order event\n");
+		pr_oe_time(oe->last_flush, "last flush, last_flush_type %d\n",
+			   oe->last_flush_type);
+
+		oe->evlist->stats.nr_unordered_events++;
+	}
+
+	oevent = ordered_events__new_event(oe, timestamp, event);
+	if (!oevent) {
+		ordered_events__flush(oe, OE_FLUSH__HALF);
+		oevent = ordered_events__new_event(oe, timestamp, event);
+	}
+
+	if (!oevent)
+		return -ENOMEM;
+
+	oevent->file_offset = file_offset;
+	return 0;
+}
+
+static int __ordered_events__flush(struct ordered_events *oe)
 {
-	struct ordered_events *oe = &s->ordered_events;
 	struct list_head *head = &oe->events;
 	struct ordered_event *tmp, *iter;
 	struct perf_sample sample;
@@ -179,12 +207,11 @@ static int __ordered_events__flush(struct perf_session *s,
 		if (iter->timestamp > limit)
 			break;
 
-		ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample);
+		ret = perf_evlist__parse_sample(oe->evlist, iter->event, &sample);
 		if (ret)
 			pr_err("Can't parse sample, err = %d\n", ret);
 		else {
-			ret = perf_session__deliver_event(s, iter->event, &sample, tool,
-							  iter->file_offset);
+			ret = oe->deliver(oe, iter, &sample);
 			if (ret)
 				return ret;
 		}
@@ -204,10 +231,8 @@ static int __ordered_events__flush(struct perf_session *s,
 	return 0;
 }
 
-int ordered_events__flush(struct perf_session *s, struct perf_tool *tool,
-			  enum oe_flush how)
+int ordered_events__flush(struct ordered_events *oe, enum oe_flush how)
 {
-	struct ordered_events *oe = &s->ordered_events;
 	static const char * const str[] = {
 		"NONE",
 		"FINAL",
@@ -251,7 +276,7 @@ int ordered_events__flush(struct perf_session *s, struct perf_tool *tool,
 		   str[how], oe->nr_events);
 	pr_oe_time(oe->max_timestamp, "max_timestamp\n");
 
-	err = __ordered_events__flush(s, tool);
+	err = __ordered_events__flush(oe);
 
 	if (!err) {
 		if (how == OE_FLUSH__ROUND)
@@ -267,13 +292,19 @@ int ordered_events__flush(struct perf_session *s, struct perf_tool *tool,
 	return err;
 }
 
-void ordered_events__init(struct ordered_events *oe)
+void ordered_events__init(struct ordered_events *oe, struct machines *machines,
+			  struct perf_evlist *evlist, struct perf_tool *tool,
+			  ordered_events__deliver_t deliver)
 {
 	INIT_LIST_HEAD(&oe->events);
 	INIT_LIST_HEAD(&oe->cache);
 	INIT_LIST_HEAD(&oe->to_free);
 	oe->max_alloc_size = (u64) -1;
 	oe->cur_alloc_size = 0;
+	oe->evlist	   = evlist;
+	oe->machines	   = machines;
+	oe->tool	   = tool;
+	oe->deliver	   = deliver;
 }
 
 void ordered_events__free(struct ordered_events *oe)
diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h
index 7b8f9b011f38..173e13f28c08 100644
--- a/tools/perf/util/ordered-events.h
+++ b/tools/perf/util/ordered-events.h
@@ -2,9 +2,11 @@
 #define __ORDERED_EVENTS_H
 
 #include <linux/types.h>
-#include "tool.h"
 
-struct perf_session;
+struct perf_tool;
+struct perf_evlist;
+struct perf_sample;
+struct machines;
 
 struct ordered_event {
 	u64			timestamp;
@@ -20,6 +22,12 @@ enum oe_flush {
 	OE_FLUSH__HALF,
 };
 
+struct ordered_events;
+
+typedef int (*ordered_events__deliver_t)(struct ordered_events *oe,
+					 struct ordered_event *event,
+					 struct perf_sample *sample);
+
 struct ordered_events {
 	u64			last_flush;
 	u64			next_flush;
@@ -31,18 +39,23 @@ struct ordered_events {
 	struct list_head	to_free;
 	struct ordered_event	*buffer;
 	struct ordered_event	*last;
+	struct machines		*machines;
+	struct perf_evlist	*evlist;
+	struct perf_tool	*tool;
+	ordered_events__deliver_t deliver;
 	int			buffer_idx;
 	unsigned int		nr_events;
 	enum oe_flush		last_flush_type;
 	bool                    copy_on_queue;
 };
 
-struct ordered_event *ordered_events__new(struct ordered_events *oe, u64 timestamp,
-					  union perf_event *event);
+int ordered_events__queue(struct ordered_events *oe, union perf_event *event,
+			  struct perf_sample *sample, u64 file_offset);
 void ordered_events__delete(struct ordered_events *oe, struct ordered_event *event);
-int ordered_events__flush(struct perf_session *s, struct perf_tool *tool,
-			  enum oe_flush how);
-void ordered_events__init(struct ordered_events *oe);
+int ordered_events__flush(struct ordered_events *oe, enum oe_flush how);
+void ordered_events__init(struct ordered_events *oe, struct machines *machines,
+			  struct perf_evlist *evlsit, struct perf_tool *tool,
+			  ordered_events__deliver_t deliver);
 void ordered_events__free(struct ordered_events *oe);
 
 static inline
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 1c570c2fa7cc..f272a711ad15 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -80,6 +80,7 @@ static int init_symbol_maps(bool user_only)
 	int ret;
 
 	symbol_conf.sort_by_name = true;
+	symbol_conf.allow_aliases = true;
 	ret = symbol__init(NULL);
 	if (ret < 0) {
 		pr_debug("Failed to init symbol map.\n");
@@ -178,6 +179,25 @@ static struct map *kernel_get_module_map(const char *module)
 	return NULL;
 }
 
+static struct map *get_target_map(const char *target, bool user)
+{
+	/* Init maps of given executable or kernel */
+	if (user)
+		return dso__new_map(target);
+	else
+		return kernel_get_module_map(target);
+}
+
+static void put_target_map(struct map *map, bool user)
+{
+	if (map && user) {
+		/* Only the user map needs to be released */
+		dso__delete(map->dso);
+		map__delete(map);
+	}
+}
+
+
 static struct dso *kernel_get_module_dso(const char *module)
 {
 	struct dso *dso;
@@ -249,6 +269,13 @@ out:
 	return ret;
 }
 
+static void clear_perf_probe_point(struct perf_probe_point *pp)
+{
+	free(pp->file);
+	free(pp->function);
+	free(pp->lazy_line);
+}
+
 static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
 {
 	int i;
@@ -258,6 +285,99 @@ static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
 }
 
 #ifdef HAVE_DWARF_SUPPORT
+/*
+ * Some binaries like glibc have special symbols which are on the symbol
+ * table, but not in the debuginfo. If we can find the address of the
+ * symbol from map, we can translate the address back to the probe point.
+ */
+static int find_alternative_probe_point(struct debuginfo *dinfo,
+					struct perf_probe_point *pp,
+					struct perf_probe_point *result,
+					const char *target, bool uprobes)
+{
+	struct map *map = NULL;
+	struct symbol *sym;
+	u64 address = 0;
+	int ret = -ENOENT;
+
+	/* This can work only for function-name based one */
+	if (!pp->function || pp->file)
+		return -ENOTSUP;
+
+	map = get_target_map(target, uprobes);
+	if (!map)
+		return -EINVAL;
+
+	/* Find the address of given function */
+	map__for_each_symbol_by_name(map, pp->function, sym) {
+		address = sym->start;
+		break;
+	}
+	if (!address) {
+		ret = -ENOENT;
+		goto out;
+	}
+	pr_debug("Symbol %s address found : %lx\n", pp->function, address);
+
+	ret = debuginfo__find_probe_point(dinfo, (unsigned long)address,
+					  result);
+	if (ret <= 0)
+		ret = (!ret) ? -ENOENT : ret;
+	else {
+		result->offset += pp->offset;
+		result->line += pp->line;
+		ret = 0;
+	}
+
+out:
+	put_target_map(map, uprobes);
+	return ret;
+
+}
+
+static int get_alternative_probe_event(struct debuginfo *dinfo,
+				       struct perf_probe_event *pev,
+				       struct perf_probe_point *tmp,
+				       const char *target)
+{
+	int ret;
+
+	memcpy(tmp, &pev->point, sizeof(*tmp));
+	memset(&pev->point, 0, sizeof(pev->point));
+	ret = find_alternative_probe_point(dinfo, tmp, &pev->point,
+					   target, pev->uprobes);
+	if (ret < 0)
+		memcpy(&pev->point, tmp, sizeof(*tmp));
+
+	return ret;
+}
+
+static int get_alternative_line_range(struct debuginfo *dinfo,
+				      struct line_range *lr,
+				      const char *target, bool user)
+{
+	struct perf_probe_point pp = { .function = lr->function,
+				       .file = lr->file,
+				       .line = lr->start };
+	struct perf_probe_point result;
+	int ret, len = 0;
+
+	memset(&result, 0, sizeof(result));
+
+	if (lr->end != INT_MAX)
+		len = lr->end - lr->start;
+	ret = find_alternative_probe_point(dinfo, &pp, &result,
+					   target, user);
+	if (!ret) {
+		lr->function = result.function;
+		lr->file = result.file;
+		lr->start = result.line;
+		if (lr->end != INT_MAX)
+			lr->end = lr->start + len;
+		clear_perf_probe_point(&pp);
+	}
+	return ret;
+}
 
 /* Open new debuginfo of given module */
 static struct debuginfo *open_debuginfo(const char *module, bool silent)
@@ -466,6 +586,7 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 					  int max_tevs, const char *target)
 {
 	bool need_dwarf = perf_probe_event_need_dwarf(pev);
+	struct perf_probe_point tmp;
 	struct debuginfo *dinfo;
 	int ntevs, ret = 0;
 
@@ -482,6 +603,20 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 	/* Searching trace events corresponding to a probe event */
 	ntevs = debuginfo__find_trace_events(dinfo, pev, tevs, max_tevs);
 
+	if (ntevs == 0)	{  /* Not found, retry with an alternative */
+		ret = get_alternative_probe_event(dinfo, pev, &tmp, target);
+		if (!ret) {
+			ntevs = debuginfo__find_trace_events(dinfo, pev,
+							     tevs, max_tevs);
+			/*
+			 * Write back to the original probe_event for
+			 * setting appropriate (user given) event name
+			 */
+			clear_perf_probe_point(&pev->point);
+			memcpy(&pev->point, &tmp, sizeof(tmp));
+		}
+	}
+
 	debuginfo__delete(dinfo);
 
 	if (ntevs > 0) {	/* Succeeded to find trace events */
@@ -496,11 +631,9 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 	}
 
 	if (ntevs == 0)	{	/* No error but failed to find probe point. */
-		pr_warning("Probe point '%s' not found in debuginfo.\n",
+		pr_warning("Probe point '%s' not found.\n",
 			   synthesize_perf_probe_point(&pev->point));
-		if (need_dwarf)
-			return -ENOENT;
-		return 0;
+		return -ENOENT;
 	}
 	/* Error path : ntevs < 0 */
 	pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs);
@@ -625,7 +758,8 @@ static int _show_one_line(FILE *fp, int l, bool skip, bool show_num)
  * Show line-range always requires debuginfo to find source file and
  * line number.
  */
-static int __show_line_range(struct line_range *lr, const char *module)
+static int __show_line_range(struct line_range *lr, const char *module,
+			     bool user)
 {
 	int l = 1;
 	struct int_node *ln;
@@ -641,6 +775,11 @@ static int __show_line_range(struct line_range *lr, const char *module)
 		return -ENOENT;
 
 	ret = debuginfo__find_line_range(dinfo, lr);
+	if (!ret) {	/* Not found, retry with an alternative */
+		ret = get_alternative_line_range(dinfo, lr, module, user);
+		if (!ret)
+			ret = debuginfo__find_line_range(dinfo, lr);
+	}
 	debuginfo__delete(dinfo);
 	if (ret == 0 || ret == -ENOENT) {
 		pr_warning("Specified source line is not found.\n");
@@ -653,7 +792,11 @@ static int __show_line_range(struct line_range *lr, const char *module)
 	/* Convert source file path */
 	tmp = lr->path;
 	ret = get_real_path(tmp, lr->comp_dir, &lr->path);
-	free(tmp);	/* Free old path */
+
+	/* Free old path when new path is assigned */
+	if (tmp != lr->path)
+		free(tmp);
+
 	if (ret < 0) {
 		pr_warning("Failed to find source file path.\n");
 		return ret;
@@ -710,7 +853,7 @@ int show_line_range(struct line_range *lr, const char *module, bool user)
 	ret = init_symbol_maps(user);
 	if (ret < 0)
 		return ret;
-	ret = __show_line_range(lr, module);
+	ret = __show_line_range(lr, module, user);
 	exit_symbol_maps();
 
 	return ret;
@@ -719,12 +862,13 @@ int show_line_range(struct line_range *lr, const char *module, bool user)
 static int show_available_vars_at(struct debuginfo *dinfo,
 				  struct perf_probe_event *pev,
 				  int max_vls, struct strfilter *_filter,
-				  bool externs)
+				  bool externs, const char *target)
 {
 	char *buf;
 	int ret, i, nvars;
 	struct str_node *node;
 	struct variable_list *vls = NULL, *vl;
+	struct perf_probe_point tmp;
 	const char *var;
 
 	buf = synthesize_perf_probe_point(&pev->point);
@@ -734,6 +878,15 @@ static int show_available_vars_at(struct debuginfo *dinfo,
 
 	ret = debuginfo__find_available_vars_at(dinfo, pev, &vls,
 						max_vls, externs);
+	if (!ret) {  /* Not found, retry with an alternative */
+		ret = get_alternative_probe_event(dinfo, pev, &tmp, target);
+		if (!ret) {
+			ret = debuginfo__find_available_vars_at(dinfo, pev,
+						&vls, max_vls, externs);
+			/* Release the old probe_point */
+			clear_perf_probe_point(&tmp);
+		}
+	}
 	if (ret <= 0) {
 		if (ret == 0 || ret == -ENOENT) {
 			pr_err("Failed to find the address of %s\n", buf);
@@ -796,7 +949,7 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
 
 	for (i = 0; i < npevs && ret >= 0; i++)
 		ret = show_available_vars_at(dinfo, &pevs[i], max_vls, _filter,
-					     externs);
+					     externs, module);
 
 	debuginfo__delete(dinfo);
 out:
@@ -1742,15 +1895,12 @@ static int convert_to_perf_probe_event(struct probe_trace_event *tev,
 
 void clear_perf_probe_event(struct perf_probe_event *pev)
 {
-	struct perf_probe_point *pp = &pev->point;
 	struct perf_probe_arg_field *field, *next;
 	int i;
 
 	free(pev->event);
 	free(pev->group);
-	free(pp->file);
-	free(pp->function);
-	free(pp->lazy_line);
+	clear_perf_probe_point(&pev->point);
 
 	for (i = 0; i < pev->nargs; i++) {
 		free(pev->args[i].name);
@@ -2339,8 +2489,7 @@ static int find_probe_functions(struct map *map, char *name)
 	struct symbol *sym;
 
 	map__for_each_symbol_by_name(map, name, sym) {
-		if (sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL)
-			found++;
+		found++;
 	}
 
 	return found;
@@ -2367,11 +2516,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 	int num_matched_functions;
 	int ret, i;
 
-	/* Init maps of given executable or kernel */
-	if (pev->uprobes)
-		map = dso__new_map(target);
-	else
-		map = kernel_get_module_map(target);
+	map = get_target_map(target, pev->uprobes);
 	if (!map) {
 		ret = -EINVAL;
 		goto out;
@@ -2464,11 +2609,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 	}
 
 out:
-	if (map && pev->uprobes) {
-		/* Only when using uprobe(exec) map needs to be released */
-		dso__delete(map->dso);
-		map__delete(map);
-	}
+	put_target_map(map, pev->uprobes);
 	return ret;
 
 nomem_out:
@@ -2708,8 +2849,7 @@ static struct strfilter *available_func_filter;
 static int filter_available_functions(struct map *map __maybe_unused,
 				      struct symbol *sym)
 {
-	if ((sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) &&
-	    strfilter__compare(available_func_filter, sym->name))
+	if (strfilter__compare(available_func_filter, sym->name))
 		return 0;
 	return 1;
 }
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index ed4e5cf2bd9d..adf0740c563b 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -16,6 +16,12 @@
 #include "perf_regs.h"
 #include "asm/bug.h"
 
+static int machines__deliver_event(struct machines *machines,
+				   struct perf_evlist *evlist,
+				   union perf_event *event,
+				   struct perf_sample *sample,
+				   struct perf_tool *tool, u64 file_offset);
+
 static int perf_session__open(struct perf_session *session)
 {
 	struct perf_data_file *file = session->file;
@@ -86,6 +92,14 @@ static void perf_session__set_comm_exec(struct perf_session *session)
 	machines__set_comm_exec(&session->machines, comm_exec);
 }
 
+static int ordered_events__deliver_event(struct ordered_events *oe,
+					 struct ordered_event *event,
+					 struct perf_sample *sample)
+{
+	return machines__deliver_event(oe->machines, oe->evlist, event->event,
+				       sample, oe->tool, event->file_offset);
+}
+
 struct perf_session *perf_session__new(struct perf_data_file *file,
 				       bool repipe, struct perf_tool *tool)
 {
@@ -95,7 +109,6 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
 		goto out;
 
 	session->repipe = repipe;
-	ordered_events__init(&session->ordered_events);
 	machines__init(&session->machines);
 
 	if (file) {
@@ -126,6 +139,9 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
 	    tool->ordered_events && !perf_evlist__sample_id_all(session->evlist)) {
 		dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n");
 		tool->ordered_events = false;
+	} else {
+		ordered_events__init(&session->ordered_events, &session->machines,
+				     session->evlist, tool, ordered_events__deliver_event);
 	}
 
 	return session;
@@ -209,10 +225,17 @@ static int process_event_stub(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
+static int process_build_id_stub(struct perf_tool *tool __maybe_unused,
+				 union perf_event *event __maybe_unused,
+				 struct perf_session *session __maybe_unused)
+{
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
 static int process_finished_round_stub(struct perf_tool *tool __maybe_unused,
 				       union perf_event *event __maybe_unused,
-				       struct perf_session *perf_session
-				       __maybe_unused)
+				       struct ordered_events *oe __maybe_unused)
 {
 	dump_printf(": unhandled!\n");
 	return 0;
@@ -220,7 +243,7 @@ static int process_finished_round_stub(struct perf_tool *tool __maybe_unused,
 
 static int process_finished_round(struct perf_tool *tool,
 				  union perf_event *event,
-				  struct perf_session *session);
+				  struct ordered_events *oe);
 
 static int process_id_index_stub(struct perf_tool *tool __maybe_unused,
 				 union perf_event *event __maybe_unused,
@@ -258,7 +281,7 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 	if (tool->tracing_data == NULL)
 		tool->tracing_data = process_event_synth_tracing_data_stub;
 	if (tool->build_id == NULL)
-		tool->build_id = process_finished_round_stub;
+		tool->build_id = process_build_id_stub;
 	if (tool->finished_round == NULL) {
 		if (tool->ordered_events)
 			tool->finished_round = process_finished_round;
@@ -508,43 +531,17 @@ static perf_event__swap_op perf_event__swap_ops[] = {
  *      Flush every events below timestamp 7
  *      etc...
  */
-static int process_finished_round(struct perf_tool *tool,
+static int process_finished_round(struct perf_tool *tool __maybe_unused,
 				  union perf_event *event __maybe_unused,
-				  struct perf_session *session)
+				  struct ordered_events *oe)
 {
-	return ordered_events__flush(session, tool, OE_FLUSH__ROUND);
+	return ordered_events__flush(oe, OE_FLUSH__ROUND);
 }
 
-int perf_session_queue_event(struct perf_session *s, union perf_event *event,
-			     struct perf_tool *tool, struct perf_sample *sample,
-			     u64 file_offset)
+int perf_session__queue_event(struct perf_session *s, union perf_event *event,
+			      struct perf_sample *sample, u64 file_offset)
 {
-	struct ordered_events *oe = &s->ordered_events;
-	u64 timestamp = sample->time;
-	struct ordered_event *new;
-
-	if (!timestamp || timestamp == ~0ULL)
-		return -ETIME;
-
-	if (timestamp < oe->last_flush) {
-		pr_oe_time(timestamp,      "out of order event\n");
-		pr_oe_time(oe->last_flush, "last flush, last_flush_type %d\n",
-			   oe->last_flush_type);
-
-		s->evlist->stats.nr_unordered_events++;
-	}
-
-	new = ordered_events__new(oe, timestamp, event);
-	if (!new) {
-		ordered_events__flush(s, tool, OE_FLUSH__HALF);
-		new = ordered_events__new(oe, timestamp, event);
-	}
-
-	if (!new)
-		return -ENOMEM;
-
-	new->file_offset = file_offset;
-	return 0;
+	return ordered_events__queue(&s->ordered_events, event, sample, file_offset);
 }
 
 static void callchain__lbr_callstack_printf(struct perf_sample *sample)
@@ -886,12 +883,12 @@ static int
 					    &sample->read.one, machine);
 }
 
-int perf_session__deliver_event(struct perf_session *session,
-				union perf_event *event,
-				struct perf_sample *sample,
-				struct perf_tool *tool, u64 file_offset)
+static int machines__deliver_event(struct machines *machines,
+				   struct perf_evlist *evlist,
+				   union perf_event *event,
+				   struct perf_sample *sample,
+				   struct perf_tool *tool, u64 file_offset)
 {
-	struct perf_evlist *evlist = session->evlist;
 	struct perf_evsel *evsel;
 	struct machine *machine;
 
@@ -899,7 +896,7 @@ int perf_session__deliver_event(struct perf_session *session,
 
 	evsel = perf_evlist__id2evsel(evlist, sample->id);
 
-	machine = machines__find_for_cpumode(&session->machines, event, sample);
+	machine = machines__find_for_cpumode(machines, event, sample);
 
 	switch (event->header.type) {
 	case PERF_RECORD_SAMPLE:
@@ -941,9 +938,10 @@ int perf_session__deliver_event(struct perf_session *session,
 
 static s64 perf_session__process_user_event(struct perf_session *session,
 					    union perf_event *event,
-					    struct perf_tool *tool,
 					    u64 file_offset)
 {
+	struct ordered_events *oe = &session->ordered_events;
+	struct perf_tool *tool = oe->tool;
 	int fd = perf_data_file__fd(session->file);
 	int err;
 
@@ -971,7 +969,7 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 	case PERF_RECORD_HEADER_BUILD_ID:
 		return tool->build_id(tool, event, session);
 	case PERF_RECORD_FINISHED_ROUND:
-		return tool->finished_round(tool, event, session);
+		return tool->finished_round(tool, event, oe);
 	case PERF_RECORD_ID_INDEX:
 		return tool->id_index(tool, event, session);
 	default:
@@ -981,15 +979,17 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 
 int perf_session__deliver_synth_event(struct perf_session *session,
 				      union perf_event *event,
-				      struct perf_sample *sample,
-				      struct perf_tool *tool)
+				      struct perf_sample *sample)
 {
-	events_stats__inc(&session->evlist->stats, event->header.type);
+	struct perf_evlist *evlist = session->evlist;
+	struct perf_tool *tool = session->ordered_events.tool;
+
+	events_stats__inc(&evlist->stats, event->header.type);
 
 	if (event->header.type >= PERF_RECORD_USER_TYPE_START)
-		return perf_session__process_user_event(session, event, tool, 0);
+		return perf_session__process_user_event(session, event, 0);
 
-	return perf_session__deliver_event(session, event, sample, tool, 0);
+	return machines__deliver_event(&session->machines, evlist, event, sample, tool, 0);
 }
 
 static void event_swap(union perf_event *event, bool sample_id_all)
@@ -1057,11 +1057,10 @@ out_parse_sample:
 }
 
 static s64 perf_session__process_event(struct perf_session *session,
-				       union perf_event *event,
-				       struct perf_tool *tool,
-				       u64 file_offset)
+				       union perf_event *event, u64 file_offset)
 {
 	struct perf_evlist *evlist = session->evlist;
+	struct perf_tool *tool = session->ordered_events.tool;
 	struct perf_sample sample;
 	int ret;
 
@@ -1074,7 +1073,7 @@ static s64 perf_session__process_event(struct perf_session *session,
 	events_stats__inc(&evlist->stats, event->header.type);
 
 	if (event->header.type >= PERF_RECORD_USER_TYPE_START)
-		return perf_session__process_user_event(session, event, tool, file_offset);
+		return perf_session__process_user_event(session, event, file_offset);
 
 	/*
 	 * For all kernel events we get the sample data
@@ -1084,14 +1083,13 @@ static s64 perf_session__process_event(struct perf_session *session,
 		return ret;
 
 	if (tool->ordered_events) {
-		ret = perf_session_queue_event(session, event, tool, &sample,
-					       file_offset);
+		ret = perf_session__queue_event(session, event, &sample, file_offset);
 		if (ret != -ETIME)
 			return ret;
 	}
 
-	return perf_session__deliver_event(session, event, &sample, tool,
-					   file_offset);
+	return machines__deliver_event(&session->machines, evlist, event,
+				       &sample, tool, file_offset);
 }
 
 void perf_event_header__bswap(struct perf_event_header *hdr)
@@ -1164,9 +1162,10 @@ static void perf_tool__warn_about_errors(const struct perf_tool *tool,
 
 volatile int session_done;
 
-static int __perf_session__process_pipe_events(struct perf_session *session,
-					       struct perf_tool *tool)
+static int __perf_session__process_pipe_events(struct perf_session *session)
 {
+	struct ordered_events *oe = &session->ordered_events;
+	struct perf_tool *tool = oe->tool;
 	int fd = perf_data_file__fd(session->file);
 	union perf_event *event;
 	uint32_t size, cur_size = 0;
@@ -1230,7 +1229,7 @@ more:
 		}
 	}
 
-	if ((skip = perf_session__process_event(session, event, tool, head)) < 0) {
+	if ((skip = perf_session__process_event(session, event, head)) < 0) {
 		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
 		       head, event->header.size, event->header.type);
 		err = -EINVAL;
@@ -1246,7 +1245,7 @@ more:
 		goto more;
 done:
 	/* do the final flush for ordered samples */
-	err = ordered_events__flush(session, tool, OE_FLUSH__FINAL);
+	err = ordered_events__flush(oe, OE_FLUSH__FINAL);
 out_err:
 	free(buf);
 	perf_tool__warn_about_errors(tool, &session->evlist->stats);
@@ -1296,8 +1295,10 @@ fetch_mmaped_event(struct perf_session *session,
 
 static int __perf_session__process_events(struct perf_session *session,
 					  u64 data_offset, u64 data_size,
-					  u64 file_size, struct perf_tool *tool)
+					  u64 file_size)
 {
+	struct ordered_events *oe = &session->ordered_events;
+	struct perf_tool *tool = oe->tool;
 	int fd = perf_data_file__fd(session->file);
 	u64 head, page_offset, file_offset, file_pos, size;
 	int err, mmap_prot, mmap_flags, map_idx = 0;
@@ -1366,8 +1367,7 @@ more:
 	size = event->header.size;
 
 	if (size < sizeof(struct perf_event_header) ||
-	    (skip = perf_session__process_event(session, event, tool, file_pos))
-									< 0) {
+	    (skip = perf_session__process_event(session, event, file_pos)) < 0) {
 		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
 		       file_offset + head, event->header.size,
 		       event->header.type);
@@ -1391,7 +1391,7 @@ more:
 
 out:
 	/* do the final flush for ordered samples */
-	err = ordered_events__flush(session, tool, OE_FLUSH__FINAL);
+	err = ordered_events__flush(oe, OE_FLUSH__FINAL);
 out_err:
 	ui_progress__finish();
 	perf_tool__warn_about_errors(tool, &session->evlist->stats);
@@ -1400,8 +1400,7 @@ out_err:
 	return err;
 }
 
-int perf_session__process_events(struct perf_session *session,
-				 struct perf_tool *tool)
+int perf_session__process_events(struct perf_session *session)
 {
 	u64 size = perf_data_file__size(session->file);
 	int err;
@@ -1412,10 +1411,9 @@ int perf_session__process_events(struct perf_session *session,
 	if (!perf_data_file__is_pipe(session->file))
 		err = __perf_session__process_events(session,
 						     session->header.data_offset,
-						     session->header.data_size,
-						     size, tool);
+						     session->header.data_size, size);
 	else
-		err = __perf_session__process_pipe_events(session, tool);
+		err = __perf_session__process_pipe_events(session);
 
 	return err;
 }
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index fe859f379ca7..1310998f8318 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -48,20 +48,13 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset,
 			     union perf_event **event_ptr,
 			     struct perf_sample *sample);
 
-int perf_session__process_events(struct perf_session *session,
-				 struct perf_tool *tool);
+int perf_session__process_events(struct perf_session *session);
 
-int perf_session_queue_event(struct perf_session *s, union perf_event *event,
-			     struct perf_tool *tool, struct perf_sample *sample,
-			     u64 file_offset);
+int perf_session__queue_event(struct perf_session *s, union perf_event *event,
+			      struct perf_sample *sample, u64 file_offset);
 
 void perf_tool__fill_defaults(struct perf_tool *tool);
 
-int perf_session__deliver_event(struct perf_session *session,
-				union perf_event *event,
-				struct perf_sample *sample,
-				struct perf_tool *tool, u64 file_offset);
-
 int perf_session__resolve_callchain(struct perf_session *session,
 				    struct perf_evsel *evsel,
 				    struct thread *thread,
@@ -125,8 +118,7 @@ extern volatile int session_done;
 
 int perf_session__deliver_synth_event(struct perf_session *session,
 				      union perf_event *event,
-				      struct perf_sample *sample,
-				      struct perf_tool *tool);
+				      struct perf_sample *sample);
 
 int perf_event__process_id_index(struct perf_tool *tool,
 				 union perf_event *event,
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index ada16762fac2..62742e46c010 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -1048,7 +1048,8 @@ new_symbol:
 	 * For misannotated, zeroed, ASM function sizes.
 	 */
 	if (nr > 0) {
-		symbols__fixup_duplicate(&dso->symbols[map->type]);
+		if (!symbol_conf.allow_aliases)
+			symbols__fixup_duplicate(&dso->symbols[map->type]);
 		symbols__fixup_end(&dso->symbols[map->type]);
 		if (kmap) {
 			/*
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 1650dcb3a67b..efdaaa544041 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -87,6 +87,7 @@ struct symbol_conf {
 			ignore_vmlinux_buildid,
 			show_kernel_path,
 			use_modules,
+			allow_aliases,
 			sort_by_name,
 			show_nr_samples,
 			show_total_period,
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index a5dbba95107f..1c8fbc9588c5 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -206,7 +206,6 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
 		err = thread__set_comm(thread, comm, timestamp);
 		if (err)
 			return err;
-		thread->comm_set = true;
 	}
 
 	thread->ppid = parent->tid;
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index bb2708bbfaca..51d9e56c0f84 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -10,6 +10,7 @@ struct perf_evsel;
 struct perf_sample;
 struct perf_tool;
 struct machine;
+struct ordered_events;
 
 typedef int (*event_sample)(struct perf_tool *tool, union perf_event *event,
 			    struct perf_sample *sample,
@@ -25,6 +26,9 @@ typedef int (*event_attr_op)(struct perf_tool *tool,
 typedef int (*event_op2)(struct perf_tool *tool, union perf_event *event,
 			 struct perf_session *session);
 
+typedef int (*event_oe)(struct perf_tool *tool, union perf_event *event,
+			struct ordered_events *oe);
+
 struct perf_tool {
 	event_sample	sample,
 			read;
@@ -38,8 +42,8 @@ struct perf_tool {
 			unthrottle;
 	event_attr_op	attr;
 	event_op2	tracing_data;
-	event_op2	finished_round,
-			build_id,
+	event_oe	finished_round;
+	event_op2	build_id,
 			id_index;
 	bool		ordered_events;
 	bool		ordering_requires_timestamps;