Merge tag 'perf-core-for-mingo-4.17-20180308' 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:

- Support to display the IPC/Cycle in 'annotate' TUI, for systems
  where this info can be obtained, like Intel's >= Skylake (Jin Yao)

- Support wildcards on PMU name in dynamic PMU events (Agustin Vega-Frias)

- Display pmu name when printing unmerged events in stat (Agustin Vega-Frias)

- Auto-merge PMU events created by prefix or glob match (Agustin Vega-Frias)

- Fix s390 'call' operations target function annotation (Thomas Richter)

- Handle s390 PC relative load and store instruction in the augmented
  'annotate', code, used so far in the TUI modes of 'perf report' and
  'perf annotate' (Thomas Richter)

- Provide libtraceevent with a kernel symbol resolver, so that
  symbols in tracepoint fields can be resolved when showing them in
  tools such as 'perf report' (Wang YanQing)

- Refactor the cgroups code to look more like other code in tools/perf,
  using cgroup__{put,get} for refcount operations instead of its
  open-coded equivalent, breaking larger functions, etc (Arnaldo Carvalho de Melo)

- Implement support for the -G/--cgroup target in 'perf trace', allowing
  strace like tracing (plus other events, backtraces, etc) for cgroups
  (Arnaldo Carvalho de Melo)

- Update thread shortname in 'perf sched map' when the thread's COMM
  changes (Changbin Du)

- refcount 'struct mem_info', for better sharing it over several
  users, avoid duplicating structs and fixing crashes related to
  use after free (Jiri Olsa)

- Display perf.data version, offsets in 'perf report --header' (Jiri Olsa)

- Record the machine's memory topology information in a perf.data
  feature section, to be used by tools such as 'perf c2c' (Jiri Olsa)

- Fix output of forced groups in the header for 'perf report' --stdio
  and --tui (Jiri Olsa)

- Better support llvm, clang, cxx make tests in the build process (Jiri Olsa)

- Streamline the 'struct perf_mmap' methods, storing some info in the
  struct instead of passing it via various methods, shortening its
  signatures (Kan Liang)

- Update the quipper perf.data parser library site information (Stephane Eranian)

- Correct perf's man pages title markers for asciidoctor (Takashi Iwai)

- Intel PT fixes and refactorings paving the way for implementing
  support for AUX area sampling (Adrian Hunter)

Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>

1 files changed, 91 insertions, 42 deletions

diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 83283fedb00f..4dfdee668b0c 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -254,6 +254,10 @@ struct thread_runtime {
 	u64 total_delay_time;
 
 	int last_state;
+
+	char shortname[3];
+	bool comm_changed;
+
 	u64 migrations;
 };
 
@@ -897,6 +901,37 @@ 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 +1515,7 @@ 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 +1555,28 @@ 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 +1594,7 @@ 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 +1612,14 @@ 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, "   ");
 	}
 
@@ -1580,14 +1628,15 @@ 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))
 			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);
+		tr->comm_changed = false;
 	}
 
 	if (sched->map.comp && new_cpu)
@@ -1691,6 +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[] = {
@@ -2200,37 +2280,6 @@ 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,
@@ -3291,7 +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,