Merge tag 'perf-tools-for-v6.12-1-2024-09-19' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools

Pull perf tools updates from Arnaldo Carvalho de Melo:

 - Use BPF + BTF to collect and pretty print syscall and tracepoint
   arguments in 'perf trace', done as an GSoC activity

 - Data-type profiling improvements:

     - Cache debuginfo to speed up data type resolution

     - Add the 'typecln' sort order, to show which cacheline in a target
       is hot or cold. The following shows members in the cfs_rq's first
       cache line:

         $ perf report -s type,typecln,typeoff -H
         ...
         -    2.67%        struct cfs_rq
            +    1.23%        struct cfs_rq: cache-line 2
            +    0.57%        struct cfs_rq: cache-line 4
            +    0.46%        struct cfs_rq: cache-line 6
            -    0.41%        struct cfs_rq: cache-line 0
                    0.39%        struct cfs_rq +0x14 (h_nr_running)
                    0.02%        struct cfs_rq +0x38 (tasks_timeline.rb_leftmost)

     - When a typedef resolves to a unnamed struct, use the typedef name

     - When a struct has just one basic type field (int, etc), resolve
       the type sort order to the name of the struct, not the type of
       the field

     - Support type folding/unfolding in the data-type annotation TUI

     - Fix bitfields offsets and sizes

     - Initial support for PowerPC, using libcapstone and the usual
       objdump disassembly parsing routines

 - Add support for disassembling and addr2line using the LLVM libraries,
   speeding up those operations

 - Support --addr2line option in 'perf script' as with other tools

 - Intel branch counters (LBR event logging) support, only available in
   recent Intel processors, for instance, the new "brcntr" field can be
   asked from 'perf script' to print the information collected from this
   feature:

     $ perf script -F +brstackinsn,+brcntr

     # Branch counter abbr list:
     # branch-instructions:ppp = A
     # branch-misses = B
     # '-' No event occurs
     # '+' Event occurrences may be lost due to branch counter saturated
         tchain_edit  332203 3366329.405674:  53030 branch-instructions:ppp:    401781 f3+0x2c (home/sdp/test/tchain_edit)
            f3+31:
         0000000000401774   insn: eb 04                  br_cntr: AA  # PRED 5 cycles [5]
         000000000040177a   insn: 81 7d fc 0f 27 00 00
         0000000000401781   insn: 7e e3                  br_cntr: A   # PRED 1 cycles [6] 2.00 IPC
         0000000000401766   insn: 8b 45 fc
         0000000000401769   insn: 83 e0 01
         000000000040176c   insn: 85 c0
         000000000040176e   insn: 74 06                  br_cntr: A   # PRED 1 cycles [7] 4.00 IPC
         0000000000401776   insn: 83 45 fc 01
         000000000040177a   insn: 81 7d fc 0f 27 00 00
         0000000000401781   insn: 7e e3                  br_cntr: A   # PRED 7 cycles [14] 0.43 IPC

 - Support Timed PEBS (Precise Event-Based Sampling), a recent hardware
   feature in Intel processors

 - Add 'perf ftrace profile' subcommand, using ftrace's function-graph
   tracer so that users can see the total, average, max execution time
   as well as the number of invocations easily, for instance:

     $ sudo perf ftrace profile -G __x64_sys_perf_event_open -- \
       perf stat -e cycles -C1 true 2> /dev/null | head
     # Total (us)  Avg (us)  Max (us)  Count  Function
           65.611    65.611    65.611      1  __x64_sys_perf_event_open
           30.527    30.527    30.527      1  anon_inode_getfile
           30.260    30.260    30.260      1  __anon_inode_getfile
           29.700    29.700    29.700      1  alloc_file_pseudo
           17.578    17.578    17.578      1  d_alloc_pseudo
           17.382    17.382    17.382      1  __d_alloc
           16.738    16.738    16.738      1  kmem_cache_alloc_lru
           15.686    15.686    15.686      1  perf_event_alloc
           14.012     7.006    11.264      2  obj_cgroup_charge

 - 'perf sched timehist' improvements, including the addition of
   priority showing/filtering command line options

 - Varios improvements to the 'perf probe', including 'perf test'
   regression testings

 - Introduce the 'perf check', initially to check if some feature is
   in place, using it in 'perf test'

 - Various fixes for 32-bit systems

 - Address more leak sanitizer failures

 - Fix memory leaks (LBR, disasm lock ops, etc)

 - More reference counting fixes (branch_info, etc)

 - Constify 'struct perf_tool' parameters to improve code generation
   and reduce the chances of having its internals changed, which isn't
   expected

 - More constifications in various other places

 - Add more build tests, including for JEVENTS

 - Add more 'perf test' entries ('perf record LBR', pipe/inject,
   --setup-filter, 'perf ftrace', 'cgroup sampling', etc)

 - Inject build ids for all entries in a call chain in 'perf inject',
   not just for the main sample

 - Improve the BPF based sample filter, allowing root to setup filters
   in bpffs that then can be used by non-root users

 - Allow filtering by cgroups with the BPF based sample filter

 - Allow a more compact way for 'perf mem report' using the
   -T/--type-profile and also provide a --sort option similar to the one
   in 'perf report', 'perf top', to setup the sort order manually

 - Fix --group behavior in 'perf annotate' when leader has no samples,
   where it was not showing anything even when other events in the group
   had samples

 - Fix spinlock and rwlock accounting in 'perf lock contention'

 - Fix libsubcmd fixdep Makefile dependencies

 - Improve 'perf ftrace' error message when ftrace isn't available

 - Update various Intel JSON vendor event files

 - ARM64 CoreSight hardware tracing infrastructure improvements, mostly
   not visible to users

 - Update power10 JSON events

* tag 'perf-tools-for-v6.12-1-2024-09-19' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (310 commits)
  perf trace: Mark the 'head' arg in the set_robust_list syscall as coming from user space
  perf trace: Mark the 'rseq' arg in the rseq syscall as coming from user space
  perf env: Find correct branch counter info on hybrid
  perf evlist: Print hint for group
  tools: Drop nonsensical -O6
  perf pmu: To info add event_type_desc
  perf evsel: Add accessor for tool_event
  perf pmus: Fake PMU clean up
  perf list: Avoid potential out of bounds memory read
  perf help: Fix a typo ("bellow")
  perf ftrace: Detect whether ftrace is enabled on system
  perf test shell probe_vfs_getname: Remove extraneous '=' from probe line number regex
  perf build: Require at least clang 16.0.6 to build BPF skeletons
  perf trace: If a syscall arg is marked as 'const', assume it is coming _from_ userspace
  perf parse-events: Remove duplicated include in parse-events.c
  perf callchain: Allow symbols to be optional when resolving a callchain
  perf inject: Lazy build-id mmap2 event insertion
  perf inject: Add new mmap2-buildid-all option
  perf inject: Fix build ID injection
  perf annotate-data: Add pr_debug_scope()
  ...

1 files changed, 192 insertions, 40 deletions

diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 8750b5f2d49b..5981cc51abc8 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -51,6 +51,7 @@
 #define COMM_LEN		20
 #define SYM_LEN			129
 #define MAX_PID			1024000
+#define MAX_PRIO		140
 
 static const char *cpu_list;
 static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
@@ -228,11 +229,14 @@ struct perf_sched {
 	bool		show_next;
 	bool		show_migrations;
 	bool		show_state;
+	bool		show_prio;
 	u64		skipped_samples;
 	const char	*time_str;
 	struct perf_time_interval ptime;
 	struct perf_time_interval hist_time;
 	volatile bool   thread_funcs_exit;
+	const char	*prio_str;
+	DECLARE_BITMAP(prio_bitmap, MAX_PRIO);
 };
 
 /* per thread run time data */
@@ -258,6 +262,8 @@ struct thread_runtime {
 	bool comm_changed;
 
 	u64 migrations;
+
+	int prio;
 };
 
 /* per event run time data */
@@ -920,6 +926,11 @@ struct sort_dimension {
 	struct list_head	list;
 };
 
+static inline void init_prio(struct thread_runtime *r)
+{
+	r->prio = -1;
+}
+
 /*
  * handle runtime stats saved per thread
  */
@@ -932,6 +943,7 @@ static struct thread_runtime *thread__init_runtime(struct thread *thread)
 		return NULL;
 
 	init_stats(&r->run_stats);
+	init_prio(r);
 	thread__set_priv(thread, r);
 
 	return r;
@@ -1489,7 +1501,7 @@ again:
 	}
 }
 
-static int process_sched_wakeup_event(struct perf_tool *tool,
+static int process_sched_wakeup_event(const struct perf_tool *tool,
 				      struct evsel *evsel,
 				      struct perf_sample *sample,
 				      struct machine *machine)
@@ -1502,7 +1514,7 @@ static int process_sched_wakeup_event(struct perf_tool *tool,
 	return 0;
 }
 
-static int process_sched_wakeup_ignore(struct perf_tool *tool __maybe_unused,
+static int process_sched_wakeup_ignore(const struct perf_tool *tool __maybe_unused,
 				      struct evsel *evsel __maybe_unused,
 				      struct perf_sample *sample __maybe_unused,
 				      struct machine *machine __maybe_unused)
@@ -1770,7 +1782,7 @@ out:
 	return 0;
 }
 
-static int process_sched_switch_event(struct perf_tool *tool,
+static int process_sched_switch_event(const struct perf_tool *tool,
 				      struct evsel *evsel,
 				      struct perf_sample *sample,
 				      struct machine *machine)
@@ -1796,7 +1808,7 @@ static int process_sched_switch_event(struct perf_tool *tool,
 	return err;
 }
 
-static int process_sched_runtime_event(struct perf_tool *tool,
+static int process_sched_runtime_event(const struct perf_tool *tool,
 				       struct evsel *evsel,
 				       struct perf_sample *sample,
 				       struct machine *machine)
@@ -1809,7 +1821,7 @@ static int process_sched_runtime_event(struct perf_tool *tool,
 	return 0;
 }
 
-static int perf_sched__process_fork_event(struct perf_tool *tool,
+static int perf_sched__process_fork_event(const struct perf_tool *tool,
 					  union perf_event *event,
 					  struct perf_sample *sample,
 					  struct machine *machine)
@@ -1826,7 +1838,7 @@ static int perf_sched__process_fork_event(struct perf_tool *tool,
 	return 0;
 }
 
-static int process_sched_migrate_task_event(struct perf_tool *tool,
+static int process_sched_migrate_task_event(const struct perf_tool *tool,
 					    struct evsel *evsel,
 					    struct perf_sample *sample,
 					    struct machine *machine)
@@ -1839,12 +1851,12 @@ static int process_sched_migrate_task_event(struct perf_tool *tool,
 	return 0;
 }
 
-typedef int (*tracepoint_handler)(struct perf_tool *tool,
+typedef int (*tracepoint_handler)(const struct perf_tool *tool,
 				  struct evsel *evsel,
 				  struct perf_sample *sample,
 				  struct machine *machine);
 
-static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_unused,
+static int perf_sched__process_tracepoint_sample(const struct perf_tool *tool __maybe_unused,
 						 union perf_event *event __maybe_unused,
 						 struct perf_sample *sample,
 						 struct evsel *evsel,
@@ -1860,7 +1872,7 @@ 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,
+static int perf_sched__process_comm(const struct perf_tool *tool __maybe_unused,
 				    union perf_event *event,
 				    struct perf_sample *sample,
 				    struct machine *machine)
@@ -2036,6 +2048,24 @@ static char *timehist_get_commstr(struct thread *thread)
 	return str;
 }
 
+/* prio field format: xxx or xxx->yyy */
+#define MAX_PRIO_STR_LEN 8
+static char *timehist_get_priostr(struct evsel *evsel,
+				  struct thread *thread,
+				  struct perf_sample *sample)
+{
+	static char prio_str[16];
+	int prev_prio = (int)evsel__intval(evsel, sample, "prev_prio");
+	struct thread_runtime *tr = thread__priv(thread);
+
+	if (tr->prio != prev_prio && tr->prio != -1)
+		scnprintf(prio_str, sizeof(prio_str), "%d->%d", tr->prio, prev_prio);
+	else
+		scnprintf(prio_str, sizeof(prio_str), "%d", prev_prio);
+
+	return prio_str;
+}
+
 static void timehist_header(struct perf_sched *sched)
 {
 	u32 ncpus = sched->max_cpu.cpu + 1;
@@ -2053,8 +2083,14 @@ static void timehist_header(struct perf_sched *sched)
 		printf(" ");
 	}
 
-	printf(" %-*s  %9s  %9s  %9s", comm_width,
-		"task name", "wait time", "sch delay", "run time");
+	if (sched->show_prio) {
+		printf(" %-*s  %-*s  %9s  %9s  %9s",
+		       comm_width, "task name", MAX_PRIO_STR_LEN, "prio",
+		       "wait time", "sch delay", "run time");
+	} else {
+		printf(" %-*s  %9s  %9s  %9s", comm_width,
+		       "task name", "wait time", "sch delay", "run time");
+	}
 
 	if (sched->show_state)
 		printf("  %s", "state");
@@ -2069,8 +2105,14 @@ static void timehist_header(struct perf_sched *sched)
 	if (sched->show_cpu_visual)
 		printf(" %*s ", ncpus, "");
 
-	printf(" %-*s  %9s  %9s  %9s", comm_width,
-	       "[tid/pid]", "(msec)", "(msec)", "(msec)");
+	if (sched->show_prio) {
+		printf(" %-*s  %-*s  %9s  %9s  %9s",
+		       comm_width, "[tid/pid]", MAX_PRIO_STR_LEN, "",
+		       "(msec)", "(msec)", "(msec)");
+	} else {
+		printf(" %-*s  %9s  %9s  %9s", comm_width,
+		       "[tid/pid]", "(msec)", "(msec)", "(msec)");
+	}
 
 	if (sched->show_state)
 		printf("  %5s", "");
@@ -2085,9 +2127,15 @@ static void timehist_header(struct perf_sched *sched)
 	if (sched->show_cpu_visual)
 		printf(" %.*s ", ncpus, graph_dotted_line);
 
-	printf(" %.*s  %.9s  %.9s  %.9s", comm_width,
-		graph_dotted_line, graph_dotted_line, graph_dotted_line,
-		graph_dotted_line);
+	if (sched->show_prio) {
+		printf(" %.*s  %.*s  %.9s  %.9s  %.9s",
+		       comm_width, graph_dotted_line, MAX_PRIO_STR_LEN, graph_dotted_line,
+		       graph_dotted_line, graph_dotted_line, graph_dotted_line);
+	} else {
+		printf(" %.*s  %.9s  %.9s  %.9s", comm_width,
+		       graph_dotted_line, graph_dotted_line, graph_dotted_line,
+		       graph_dotted_line);
+	}
 
 	if (sched->show_state)
 		printf("  %.5s", graph_dotted_line);
@@ -2134,6 +2182,9 @@ static void timehist_print_sample(struct perf_sched *sched,
 
 	printf(" %-*s ", comm_width, timehist_get_commstr(thread));
 
+	if (sched->show_prio)
+		printf(" %-*s ", MAX_PRIO_STR_LEN, timehist_get_priostr(evsel, thread, sample));
+
 	wait_time = tr->dt_sleep + tr->dt_iowait + tr->dt_preempt;
 	print_sched_time(wait_time, 6);
 
@@ -2301,6 +2352,7 @@ static int init_idle_thread(struct thread *thread)
 	if (itr == NULL)
 		return -ENOMEM;
 
+	init_prio(&itr->tr);
 	init_stats(&itr->tr.run_stats);
 	callchain_init(&itr->callchain);
 	callchain_cursor_reset(&itr->cursor);
@@ -2455,12 +2507,33 @@ static bool timehist_skip_sample(struct perf_sched *sched,
 				 struct perf_sample *sample)
 {
 	bool rc = false;
+	int prio = -1;
+	struct thread_runtime *tr = NULL;
 
 	if (thread__is_filtered(thread)) {
 		rc = true;
 		sched->skipped_samples++;
 	}
 
+	if (sched->prio_str) {
+		/*
+		 * Because priority may be changed during task execution,
+		 * first read priority from prev sched_in event for current task.
+		 * If prev sched_in event is not saved, then read priority from
+		 * current task sched_out event.
+		 */
+		tr = thread__get_runtime(thread);
+		if (tr && tr->prio != -1)
+			prio = tr->prio;
+		else if (evsel__name_is(evsel, "sched:sched_switch"))
+			prio = evsel__intval(evsel, sample, "prev_prio");
+
+		if (prio != -1 && !test_bit(prio, sched->prio_bitmap)) {
+			rc = true;
+			sched->skipped_samples++;
+		}
+	}
+
 	if (sched->idle_hist) {
 		if (!evsel__name_is(evsel, "sched:sched_switch"))
 			rc = true;
@@ -2506,7 +2579,7 @@ static void timehist_print_wakeup_event(struct perf_sched *sched,
 	printf("\n");
 }
 
-static int timehist_sched_wakeup_ignore(struct perf_tool *tool __maybe_unused,
+static int timehist_sched_wakeup_ignore(const struct perf_tool *tool __maybe_unused,
 					union perf_event *event __maybe_unused,
 					struct evsel *evsel __maybe_unused,
 					struct perf_sample *sample __maybe_unused,
@@ -2515,7 +2588,7 @@ static int timehist_sched_wakeup_ignore(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-static int timehist_sched_wakeup_event(struct perf_tool *tool,
+static int timehist_sched_wakeup_event(const struct perf_tool *tool,
 				       union perf_event *event __maybe_unused,
 				       struct evsel *evsel,
 				       struct perf_sample *sample,
@@ -2599,7 +2672,7 @@ static void timehist_print_migration_event(struct perf_sched *sched,
 	printf("\n");
 }
 
-static int timehist_migrate_task_event(struct perf_tool *tool,
+static int timehist_migrate_task_event(const struct perf_tool *tool,
 				       union perf_event *event __maybe_unused,
 				       struct evsel *evsel,
 				       struct perf_sample *sample,
@@ -2627,7 +2700,31 @@ static int timehist_migrate_task_event(struct perf_tool *tool,
 	return 0;
 }
 
-static int timehist_sched_change_event(struct perf_tool *tool,
+static void timehist_update_task_prio(struct evsel *evsel,
+				      struct perf_sample *sample,
+				      struct machine *machine)
+{
+	struct thread *thread;
+	struct thread_runtime *tr = NULL;
+	const u32 next_pid = evsel__intval(evsel, sample, "next_pid");
+	const u32 next_prio = evsel__intval(evsel, sample, "next_prio");
+
+	if (next_pid == 0)
+		thread = get_idle_thread(sample->cpu);
+	else
+		thread = machine__findnew_thread(machine, -1, next_pid);
+
+	if (thread == NULL)
+		return;
+
+	tr = thread__get_runtime(thread);
+	if (tr == NULL)
+		return;
+
+	tr->prio = next_prio;
+}
+
+static int timehist_sched_change_event(const struct perf_tool *tool,
 				       union perf_event *event,
 				       struct evsel *evsel,
 				       struct perf_sample *sample,
@@ -2650,6 +2747,9 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 		goto out;
 	}
 
+	if (sched->show_prio || sched->prio_str)
+		timehist_update_task_prio(evsel, sample, machine);
+
 	thread = timehist_get_thread(sched, sample, machine, evsel);
 	if (thread == NULL) {
 		rc = -1;
@@ -2683,9 +2783,12 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 	 * - previous sched event is out of window - we are done
 	 * - sample time is beyond window user cares about - reset it
 	 *   to close out stats for time window interest
+	 * - If tprev is 0, that is, sched_in event for current task is
+	 *   not recorded, cannot determine whether sched_in event is
+	 *   within time window interest - ignore it
 	 */
 	if (ptime->end) {
-		if (tprev > ptime->end)
+		if (!tprev || tprev > ptime->end)
 			goto out;
 
 		if (t > ptime->end)
@@ -2700,8 +2803,6 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 			struct idle_thread_runtime *itr = (void *)tr;
 			struct thread_runtime *last_tr;
 
-			BUG_ON(thread__tid(thread) != 0);
-
 			if (itr->last_thread == NULL)
 				goto out;
 
@@ -2727,10 +2828,10 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 
 			itr->last_thread = NULL;
 		}
-	}
 
-	if (!sched->summary_only)
-		timehist_print_sample(sched, evsel, sample, &al, thread, t, state);
+		if (!sched->summary_only)
+			timehist_print_sample(sched, evsel, sample, &al, thread, t, state);
+	}
 
 out:
 	if (sched->hist_time.start == 0 && t >= ptime->start)
@@ -2758,7 +2859,7 @@ out:
 	return rc;
 }
 
-static int timehist_sched_switch_event(struct perf_tool *tool,
+static int timehist_sched_switch_event(const struct perf_tool *tool,
 			     union perf_event *event,
 			     struct evsel *evsel,
 			     struct perf_sample *sample,
@@ -2767,7 +2868,7 @@ static int timehist_sched_switch_event(struct perf_tool *tool,
 	return timehist_sched_change_event(tool, event, evsel, sample, machine);
 }
 
-static int process_lost(struct perf_tool *tool __maybe_unused,
+static int process_lost(const struct perf_tool *tool __maybe_unused,
 			union perf_event *event,
 			struct perf_sample *sample,
 			struct machine *machine __maybe_unused)
@@ -3010,13 +3111,13 @@ static void timehist_print_summary(struct perf_sched *sched,
 	printf(" (x %d)\n", sched->max_cpu.cpu);
 }
 
-typedef int (*sched_handler)(struct perf_tool *tool,
+typedef int (*sched_handler)(const struct perf_tool *tool,
 			  union perf_event *event,
 			  struct evsel *evsel,
 			  struct perf_sample *sample,
 			  struct machine *machine);
 
-static int perf_timehist__process_sample(struct perf_tool *tool,
+static int perf_timehist__process_sample(const struct perf_tool *tool,
 					 union perf_event *event,
 					 struct perf_sample *sample,
 					 struct evsel *evsel,
@@ -3066,6 +3167,47 @@ static int timehist_check_attr(struct perf_sched *sched,
 	return 0;
 }
 
+static int timehist_parse_prio_str(struct perf_sched *sched)
+{
+	char *p;
+	unsigned long start_prio, end_prio;
+	const char *str = sched->prio_str;
+
+	if (!str)
+		return 0;
+
+	while (isdigit(*str)) {
+		p = NULL;
+		start_prio = strtoul(str, &p, 0);
+		if (start_prio >= MAX_PRIO || (*p != '\0' && *p != ',' && *p != '-'))
+			return -1;
+
+		if (*p == '-') {
+			str = ++p;
+			p = NULL;
+			end_prio = strtoul(str, &p, 0);
+
+			if (end_prio >= MAX_PRIO || (*p != '\0' && *p != ','))
+				return -1;
+
+			if (end_prio < start_prio)
+				return -1;
+		} else {
+			end_prio = start_prio;
+		}
+
+		for (; start_prio <= end_prio; start_prio++)
+			__set_bit(start_prio, sched->prio_bitmap);
+
+		if (*p)
+			++p;
+
+		str = p;
+	}
+
+	return 0;
+}
+
 static int perf_sched__timehist(struct perf_sched *sched)
 {
 	struct evsel_str_handler handlers[] = {
@@ -3100,7 +3242,6 @@ static int perf_sched__timehist(struct perf_sched *sched)
 	sched->tool.tracing_data = perf_event__process_tracing_data;
 	sched->tool.build_id	 = perf_event__process_build_id;
 
-	sched->tool.ordered_events = true;
 	sched->tool.ordering_requires_timestamps = true;
 
 	symbol_conf.use_callchain = sched->show_callchain;
@@ -3121,12 +3262,18 @@ static int perf_sched__timehist(struct perf_sched *sched)
 
 	if (perf_time__parse_str(&sched->ptime, sched->time_str) != 0) {
 		pr_err("Invalid time string\n");
-		return -EINVAL;
+		err = -EINVAL;
+		goto out;
 	}
 
 	if (timehist_check_attr(sched, evlist) != 0)
 		goto out;
 
+	if (timehist_parse_prio_str(sched) != 0) {
+		pr_err("Invalid prio string\n");
+		goto out;
+	}
+
 	setup_pager();
 
 	/* prefer sched_waking if it is captured */
@@ -3605,14 +3752,6 @@ int cmd_sched(int argc, const char **argv)
 {
 	static const char default_sort_order[] = "avg, max, switch, runtime";
 	struct perf_sched sched = {
-		.tool = {
-			.sample		 = perf_sched__process_tracepoint_sample,
-			.comm		 = perf_sched__process_comm,
-			.namespaces	 = perf_event__process_namespaces,
-			.lost		 = perf_event__process_lost,
-			.fork		 = perf_sched__process_fork_event,
-			.ordered_events = true,
-		},
 		.cmp_pid	      = LIST_HEAD_INIT(sched.cmp_pid),
 		.sort_list	      = LIST_HEAD_INIT(sched.sort_list),
 		.sort_order	      = default_sort_order,
@@ -3691,6 +3830,9 @@ int cmd_sched(int argc, const char **argv)
 	OPT_STRING('t', "tid", &symbol_conf.tid_list_str, "tid[,tid...]",
 		   "analyze events only for given thread id(s)"),
 	OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
+	OPT_BOOLEAN(0, "show-prio", &sched.show_prio, "Show task priority"),
+	OPT_STRING(0, "prio", &sched.prio_str, "prio",
+		   "analyze events only for given task priority(ies)"),
 	OPT_PARENT(sched_options)
 	};
 
@@ -3733,6 +3875,13 @@ int cmd_sched(int argc, const char **argv)
 	};
 	int ret;
 
+	perf_tool__init(&sched.tool, /*ordered_events=*/true);
+	sched.tool.sample	 = perf_sched__process_tracepoint_sample;
+	sched.tool.comm		 = perf_sched__process_comm;
+	sched.tool.namespaces	 = perf_event__process_namespaces;
+	sched.tool.lost		 = perf_event__process_lost;
+	sched.tool.fork		 = perf_sched__process_fork_event;
+
 	argc = parse_options_subcommand(argc, argv, sched_options, sched_subcommands,
 					sched_usage, PARSE_OPT_STOP_AT_NON_OPTION);
 	if (!argc)
@@ -3805,5 +3954,8 @@ int cmd_sched(int argc, const char **argv)
 		usage_with_options(sched_usage, sched_options);
 	}
 
+	/* free usage string allocated by parse_options_subcommand */
+	free((void *)sched_usage[0]);
+
 	return 0;
 }