From b91473ff6e979c0028f02f90e40c844959c736d8 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 23 Mar 2017 15:56:12 +0100
Subject: [PATCH] sched,tracing: Update trace_sched_pi_setprio()

Pass the PI donor task, instead of a numerical priority.

Numerical priorities are not sufficient to describe state ever since
SCHED_DEADLINE.

Annotate all sched tracepoints that are currently broken; fixing them
will bork userspace. *hate*.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Cc: juri.lelli@arm.com
Cc: bigeasy@linutronix.de
Cc: xlpang@redhat.com
Cc: mathieu.desnoyers@efficios.com
Cc: jdesfossez@efficios.com
Cc: bristot@redhat.com
Link: http://lkml.kernel.org/r/20170323150216.353599881@infradead.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/trace/events/sched.h | 16 +++++++++-------
 kernel/sched/core.c          |  2 +-
 2 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 9e3ef6c99e4b..ae1409ffe99a 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -70,7 +70,7 @@ DECLARE_EVENT_CLASS(sched_wakeup_template,
 	TP_fast_assign(
 		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
 		__entry->pid		= p->pid;
-		__entry->prio		= p->prio;
+		__entry->prio		= p->prio; /* XXX SCHED_DEADLINE */
 		__entry->success	= 1; /* rudiment, kill when possible */
 		__entry->target_cpu	= task_cpu(p);
 	),
@@ -147,6 +147,7 @@ TRACE_EVENT(sched_switch,
 		memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
 		__entry->next_pid	= next->pid;
 		__entry->next_prio	= next->prio;
+		/* XXX SCHED_DEADLINE */
 	),
 
 	TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s%s ==> next_comm=%s next_pid=%d next_prio=%d",
@@ -181,7 +182,7 @@ TRACE_EVENT(sched_migrate_task,
 	TP_fast_assign(
 		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
 		__entry->pid		= p->pid;
-		__entry->prio		= p->prio;
+		__entry->prio		= p->prio; /* XXX SCHED_DEADLINE */
 		__entry->orig_cpu	= task_cpu(p);
 		__entry->dest_cpu	= dest_cpu;
 	),
@@ -206,7 +207,7 @@ DECLARE_EVENT_CLASS(sched_process_template,
 	TP_fast_assign(
 		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
 		__entry->pid		= p->pid;
-		__entry->prio		= p->prio;
+		__entry->prio		= p->prio; /* XXX SCHED_DEADLINE */
 	),
 
 	TP_printk("comm=%s pid=%d prio=%d",
@@ -253,7 +254,7 @@ TRACE_EVENT(sched_process_wait,
 	TP_fast_assign(
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
 		__entry->pid		= pid_nr(pid);
-		__entry->prio		= current->prio;
+		__entry->prio		= current->prio; /* XXX SCHED_DEADLINE */
 	),
 
 	TP_printk("comm=%s pid=%d prio=%d",
@@ -413,9 +414,9 @@ DEFINE_EVENT(sched_stat_runtime, sched_stat_runtime,
  */
 TRACE_EVENT(sched_pi_setprio,
 
-	TP_PROTO(struct task_struct *tsk, int newprio),
+	TP_PROTO(struct task_struct *tsk, struct task_struct *pi_task),
 
-	TP_ARGS(tsk, newprio),
+	TP_ARGS(tsk, pi_task),
 
 	TP_STRUCT__entry(
 		__array( char,	comm,	TASK_COMM_LEN	)
@@ -428,7 +429,8 @@ TRACE_EVENT(sched_pi_setprio,
 		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
 		__entry->pid		= tsk->pid;
 		__entry->oldprio	= tsk->prio;
-		__entry->newprio	= newprio;
+		__entry->newprio	= pi_task ? pi_task->prio : tsk->prio;
+		/* XXX SCHED_DEADLINE bits missing */
 	),
 
 	TP_printk("comm=%s pid=%d oldprio=%d newprio=%d",
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 37b152a782ae..0c443bbdaaca 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3752,7 +3752,7 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 		goto out_unlock;
 	}
 
-	trace_sched_pi_setprio(p, prio); /* broken */
+	trace_sched_pi_setprio(p, pi_task);
 	oldprio = p->prio;
 
 	if (oldprio == prio)
-- 
2.42.0