Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip into next

Pull perf updates from Ingo Molnar:
 "The tooling changes maintained by Jiri Olsa until Arnaldo is on
  vacation:

  User visible changes:
   - Add -F option for specifying output fields (Namhyung Kim)
   - Propagate exit status of a command line workload for record command
     (Namhyung Kim)
   - Use tid for finding thread (Namhyung Kim)
   - Clarify the output of perf sched map plus small sched command
     fixes (Dongsheng Yang)
   - Wire up perf_regs and unwind support for ARM64 (Jean Pihet)
   - Factor hists statistics counts processing which in turn also fixes
     several bugs in TUI report command (Namhyung Kim)
   - Add --percentage option to control absolute/relative percentage
     output (Namhyung Kim)
   - Add --list-cmds to 'kmem', 'mem', 'lock' and 'sched', for use by
     completion scripts (Ramkumar Ramachandra)

  Development/infrastructure changes and fixes:
   - Android related fixes for pager and map dso resolving (Michael
     Lentine)
   - Add libdw DWARF post unwind support for ARM (Jean Pihet)
   - Consolidate types.h for ARM and ARM64 (Jean Pihet)
   - Fix possible null pointer dereference in session.c (Masanari Iida)
   - Cleanup, remove unused variables in map_switch_event() (Dongsheng
     Yang)
   - Remove nr_state_machine_bugs in perf latency (Dongsheng Yang)
   - Remove usage of trace_sched_wakeup(.success) (Peter Zijlstra)
   - Cleanups for perf.h header (Jiri Olsa)
   - Consolidate types.h and export.h within tools (Borislav Petkov)
   - Move u64_swap union to its single user's header, evsel.h (Borislav
     Petkov)
   - Fix for s390 to properly parse tracepoints plus test code
     (Alexander Yarygin)
   - Handle EINTR error for readn/writen (Namhyung Kim)
   - Add a test case for hists filtering (Namhyung Kim)
   - Share map_groups among threads of the same group (Arnaldo Carvalho
     de Melo, Jiri Olsa)
   - Making some code (cpu node map and report parse callchain callback)
     global to be usable by upcomming changes (Don Zickus)
   - Fix pmu object compilation error (Jiri Olsa)

  Kernel side changes:
   - intrusive uprobes fixes from Oleg Nesterov.  Since the interface is
     admin-only, and the bug only affects user-space ("any probed
     jmp/call can kill the application"), we queued these fixes via the
     development tree, as a special exception.
   - more fuzzer motivated race fixes and related refactoring and
     robustization.
   - allow PMU drivers to be built as modules.  (No actual module yet,
     because the x86 Intel uncore module wasn't ready in time for this)"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (114 commits)
  perf tools: Add automatic remapping of Android libraries
  perf tools: Add cat as fallback pager
  perf tests: Add a testcase for histogram output sorting
  perf tests: Factor out print_hists_*()
  perf tools: Introduce reset_output_field()
  perf tools: Get rid of obsolete hist_entry__sort_list
  perf hists: Reset width of output fields with header length
  perf tools: Skip elided sort entries
  perf top: Add --fields option to specify output fields
  perf report/tui: Fix a bug when --fields/sort is given
  perf tools: Add ->sort() member to struct sort_entry
  perf report: Add -F option to specify output fields
  perf tools: Call perf_hpp__init() before setting up GUI browsers
  perf tools: Consolidate management of default sort orders
  perf tools: Allow hpp fields to be sort keys
  perf ui: Get rid of callback from __hpp__fmt()
  perf tools: Consolidate output field handling to hpp format routines
  perf tools: Use hpp formats to sort final output
  perf tools: Support event grouping in hpp ->sort()
  perf tools: Use hpp formats to sort hist entries
  ...

1 files changed, 39 insertions, 41 deletions

diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 9ac0a495c95..d7176830b9b 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -66,7 +66,7 @@ struct sched_atom {
 	struct task_desc	*wakee;
 };
 
-#define TASK_STATE_TO_CHAR_STR "RSDTtZX"
+#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWP"
 
 enum thread_state {
 	THREAD_SLEEPING = 0,
@@ -149,7 +149,6 @@ struct perf_sched {
 	unsigned long	 nr_runs;
 	unsigned long	 nr_timestamps;
 	unsigned long	 nr_unordered_timestamps;
-	unsigned long	 nr_state_machine_bugs;
 	unsigned long	 nr_context_switch_bugs;
 	unsigned long	 nr_events;
 	unsigned long	 nr_lost_chunks;
@@ -1007,17 +1006,12 @@ static int latency_wakeup_event(struct perf_sched *sched,
 				struct perf_sample *sample,
 				struct machine *machine)
 {
-	const u32 pid	  = perf_evsel__intval(evsel, sample, "pid"),
-		  success = perf_evsel__intval(evsel, sample, "success");
+	const u32 pid	  = perf_evsel__intval(evsel, sample, "pid");
 	struct work_atoms *atoms;
 	struct work_atom *atom;
 	struct thread *wakee;
 	u64 timestamp = sample->time;
 
-	/* Note for later, it may be interesting to observe the failing cases */
-	if (!success)
-		return 0;
-
 	wakee = machine__findnew_thread(machine, 0, pid);
 	atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid);
 	if (!atoms) {
@@ -1037,12 +1031,18 @@ static int latency_wakeup_event(struct perf_sched *sched,
 	atom = list_entry(atoms->work_list.prev, struct work_atom, list);
 
 	/*
+	 * As we do not guarantee the wakeup event happens when
+	 * task is out of run queue, also may happen when task is
+	 * on run queue and wakeup only change ->state to TASK_RUNNING,
+	 * then we should not set the ->wake_up_time when wake up a
+	 * task which is on run queue.
+	 *
 	 * You WILL be missing events if you've recorded only
 	 * one CPU, or are only looking at only one, so don't
-	 * make useless noise.
+	 * skip in this case.
 	 */
 	if (sched->profile_cpu == -1 && atom->state != THREAD_SLEEPING)
-		sched->nr_state_machine_bugs++;
+		return 0;
 
 	sched->nr_timestamps++;
 	if (atom->sched_out_time > timestamp) {
@@ -1266,9 +1266,8 @@ static int process_sched_wakeup_event(struct perf_tool *tool,
 static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 			    struct perf_sample *sample, struct machine *machine)
 {
-	const u32 prev_pid = perf_evsel__intval(evsel, sample, "prev_pid"),
-		  next_pid = perf_evsel__intval(evsel, sample, "next_pid");
-	struct thread *sched_out __maybe_unused, *sched_in;
+	const u32 next_pid = perf_evsel__intval(evsel, sample, "next_pid");
+	struct thread *sched_in;
 	int new_shortname;
 	u64 timestamp0, timestamp = sample->time;
 	s64 delta;
@@ -1291,7 +1290,6 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 		return -1;
 	}
 
-	sched_out = machine__findnew_thread(machine, 0, prev_pid);
 	sched_in = machine__findnew_thread(machine, 0, next_pid);
 
 	sched->curr_thread[this_cpu] = sched_in;
@@ -1300,17 +1298,25 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 
 	new_shortname = 0;
 	if (!sched_in->shortname[0]) {
-		sched_in->shortname[0] = sched->next_shortname1;
-		sched_in->shortname[1] = sched->next_shortname2;
-
-		if (sched->next_shortname1 < 'Z') {
-			sched->next_shortname1++;
+		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] = ' ';
 		} else {
-			sched->next_shortname1='A';
-			if (sched->next_shortname2 < '9') {
-				sched->next_shortname2++;
+			sched_in->shortname[0] = sched->next_shortname1;
+			sched_in->shortname[1] = sched->next_shortname2;
+
+			if (sched->next_shortname1 < 'Z') {
+				sched->next_shortname1++;
 			} else {
-				sched->next_shortname2='0';
+				sched->next_shortname1 = 'A';
+				if (sched->next_shortname2 < '9')
+					sched->next_shortname2++;
+				else
+					sched->next_shortname2 = '0';
 			}
 		}
 		new_shortname = 1;
@@ -1322,12 +1328,9 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 		else
 			printf("*");
 
-		if (sched->curr_thread[cpu]) {
-			if (sched->curr_thread[cpu]->tid)
-				printf("%2s ", sched->curr_thread[cpu]->shortname);
-			else
-				printf(".  ");
-		} else
+		if (sched->curr_thread[cpu])
+			printf("%2s ", sched->curr_thread[cpu]->shortname);
+		else
 			printf("   ");
 	}
 
@@ -1496,14 +1499,6 @@ static void print_bad_events(struct perf_sched *sched)
 			(double)sched->nr_lost_events/(double)sched->nr_events * 100.0,
 			sched->nr_lost_events, sched->nr_events, sched->nr_lost_chunks);
 	}
-	if (sched->nr_state_machine_bugs && sched->nr_timestamps) {
-		printf("  INFO: %.3f%% state machine bugs (%ld out of %ld)",
-			(double)sched->nr_state_machine_bugs/(double)sched->nr_timestamps*100.0,
-			sched->nr_state_machine_bugs, sched->nr_timestamps);
-		if (sched->nr_lost_events)
-			printf(" (due to lost events?)");
-		printf("\n");
-	}
 	if (sched->nr_context_switch_bugs && sched->nr_timestamps) {
 		printf("  INFO: %.3f%% context switch bugs (%ld out of %ld)",
 			(double)sched->nr_context_switch_bugs/(double)sched->nr_timestamps*100.0,
@@ -1635,6 +1630,7 @@ static int __cmd_record(int argc, const char **argv)
 		"-e", "sched:sched_stat_runtime",
 		"-e", "sched:sched_process_fork",
 		"-e", "sched:sched_wakeup",
+		"-e", "sched:sched_wakeup_new",
 		"-e", "sched:sched_migrate_task",
 	};
 
@@ -1713,8 +1709,10 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 		"perf sched replay [<options>]",
 		NULL
 	};
-	const char * const sched_usage[] = {
-		"perf sched [<options>] {record|latency|map|replay|script}",
+	const char *const sched_subcommands[] = { "record", "latency", "map",
+						  "replay", "script", NULL };
+	const char *sched_usage[] = {
+		NULL,
 		NULL
 	};
 	struct trace_sched_handler lat_ops  = {
@@ -1736,8 +1734,8 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 	for (i = 0; i < ARRAY_SIZE(sched.curr_pid); i++)
 		sched.curr_pid[i] = -1;
 
-	argc = parse_options(argc, argv, sched_options, sched_usage,
-			     PARSE_OPT_STOP_AT_NON_OPTION);
+	argc = parse_options_subcommand(argc, argv, sched_options, sched_subcommands,
+					sched_usage, PARSE_OPT_STOP_AT_NON_OPTION);
 	if (!argc)
 		usage_with_options(sched_usage, sched_options);