tools lib traceevent: Fix prev/next_prio for deadline tasks

[ Upstream commit 07485918 ]

Currently, the sched:sched_switch tracepoint reports deadline tasks with
priority -1. But when reading the trace via perf script I've got the
following output:

  # ./d & # (d is a deadline task, see [1])
  # perf record -e sched:sched_switch -a sleep 1
  # perf script
      ...
         swapper     0 [000]  2146.962441: sched:sched_switch: swapper/0:0 [120] R ==> d:2593 [4294967295]
               d  2593 [000]  2146.972472: sched:sched_switch: d:2593 [4294967295] R ==> g:2590 [4294967295]

The task d reports the wrong priority [4294967295]. This happens because
the "int prio" is stored in an unsigned long long val. Although it is
set as a %lld, as int is shorter than unsigned long long,
trace_seq_printf prints it as a positive number.

The fix is just to cast the val as an int, and print it as a %d,
as in the sched:sched_switch tracepoint's "format".

The output with the fix is:

  # ./d &
  # perf record -e sched:sched_switch -a sleep 1
  # perf script
      ...
         swapper     0 [000]  4306.374037: sched:sched_switch: swapper/0:0 [120] R ==> d:10941 [-1]
               d 10941 [000]  4306.383823: sched:sched_switch: d:10941 [-1] R ==> swapper/0:0 [120]

[1] d.c

 ---
  #include <stdio.h>
  #include <unistd.h>
  #include <sys/syscall.h>
  #include <linux/types.h>
  #include <linux/sched.h>

  struct sched_attr {
	__u32 size, sched_policy;
	__u64 sched_flags;
	__s32 sched_nice;
	__u32 sched_priority;
	__u64 sched_runtime, sched_deadline, sched_period;
  };

  int sched_setattr(pid_t pid, const struct sched_attr *attr, unsigned int flags)
  {
	return syscall(__NR_sched_setattr, pid, attr, flags);
  }

  int main(void)
  {
	struct sched_attr attr = {
		.size		= sizeof(attr),
		.sched_policy	= SCHED_DEADLINE, /* This creates a 10ms/30ms reservation */
		.sched_runtime	= 10 * 1000 * 1000,
		.sched_period	= attr.sched_deadline = 30 * 1000 * 1000,
	};

	if (sched_setattr(0, &attr, 0) < 0) {
		perror("sched_setattr");
		return -1;
	}

	for(;;);
  }
 ---

Committer notes:

Got the program from the provided URL, http://bristot.me/lkml/d.c,
trimmed it and included in the cset log above, so that we have
everything needed to test it in one place.
Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Daniel Bristot de Oliveira <bristot@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/866ef75bcebf670ae91c6a96daa63597ba981f0d.1483443552.git.bristot@redhat.comSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>

tools/lib/traceevent/plugin_sched_switch.c

@@ -111,7 +111,7 @@ static int sched_switch_handler(struct trace_seq *s,
 	trace_seq_printf(s, "%lld ", val);
 
 	if (pevent_get_field_val(s, event, "prev_prio", record, &val, 0) == 0)
-		trace_seq_printf(s, "[%lld] ", val);
+		trace_seq_printf(s, "[%d] ", (int) val);
 
 	if (pevent_get_field_val(s,  event, "prev_state", record, &val, 0) == 0)
 		write_state(s, val);
@@ -129,7 +129,7 @@ static int sched_switch_handler(struct trace_seq *s,
 	trace_seq_printf(s, "%lld", val);
 
 	if (pevent_get_field_val(s, event, "next_prio", record, &val, 0) == 0)
-		trace_seq_printf(s, " [%lld]", val);
+		trace_seq_printf(s, " [%d]", (int) val);
 
 	return 0;
 }