--- zzzz-none-000/linux-3.10.107/include/trace/events/sched.h	2017-06-27 09:49:32.000000000 +0000
+++ scorpion-7490-727/linux-3.10.107/include/trace/events/sched.h	2021-02-04 17:41:59.000000000 +0000
@@ -55,9 +55,9 @@
  */
 DECLARE_EVENT_CLASS(sched_wakeup_template,
 
-	TP_PROTO(struct task_struct *p, int success),
+	TP_PROTO(struct task_struct *p),
 
-	TP_ARGS(p, success),
+	TP_ARGS(__perf_task(p)),
 
 	TP_STRUCT__entry(
 		__array(	char,	comm,	TASK_COMM_LEN	)
@@ -71,55 +71,63 @@
 		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
 		__entry->pid		= p->pid;
 		__entry->prio		= p->prio;
-		__entry->success	= success;
+		__entry->success	= 1; /* rudiment, kill when possible */
 		__entry->target_cpu	= task_cpu(p);
-	)
-	TP_perf_assign(
-		__perf_task(p);
 	),
 
-	TP_printk("comm=%s pid=%d prio=%d success=%d target_cpu=%03d",
+	TP_printk("comm=%s pid=%d prio=%d target_cpu=%03d",
 		  __entry->comm, __entry->pid, __entry->prio,
-		  __entry->success, __entry->target_cpu)
+		  __entry->target_cpu)
 );
 
+/*
+ * Tracepoint called when waking a task; this tracepoint is guaranteed to be
+ * called from the waking context.
+ */
+DEFINE_EVENT(sched_wakeup_template, sched_waking,
+	     TP_PROTO(struct task_struct *p),
+	     TP_ARGS(p));
+
+/*
+ * Tracepoint called when the task is actually woken; p->state == TASK_RUNNNG.
+ * It it not always called from the waking context.
+ */
 DEFINE_EVENT(sched_wakeup_template, sched_wakeup,
-	     TP_PROTO(struct task_struct *p, int success),
-	     TP_ARGS(p, success));
+	     TP_PROTO(struct task_struct *p),
+	     TP_ARGS(p));
 
 /*
  * Tracepoint for waking up a new task:
  */
 DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new,
-	     TP_PROTO(struct task_struct *p, int success),
-	     TP_ARGS(p, success));
+	     TP_PROTO(struct task_struct *p),
+	     TP_ARGS(p));
 
 #ifdef CREATE_TRACE_POINTS
-static inline long __trace_sched_switch_state(struct task_struct *p)
+static inline long __trace_sched_switch_state(bool preempt, struct task_struct *p)
 {
-	long state = p->state;
+#ifdef CONFIG_SCHED_DEBUG
+	BUG_ON(p != current);
+#endif /* CONFIG_SCHED_DEBUG */
 
-#ifdef CONFIG_PREEMPT
 	/*
-	 * For all intents and purposes a preempted task is a running task.
+	 * Preemption ignores task state, therefore preempted tasks are always
+	 * RUNNING (we will not have dequeued if state != RUNNING).
 	 */
-	if (task_thread_info(p)->preempt_count & PREEMPT_ACTIVE)
-		state = TASK_RUNNING | TASK_STATE_MAX;
-#endif
-
-	return state;
+	return preempt ? TASK_RUNNING | TASK_STATE_MAX : p->state;
 }
-#endif
+#endif /* CREATE_TRACE_POINTS */
 
 /*
  * Tracepoint for task switches, performed by the scheduler:
  */
 TRACE_EVENT(sched_switch,
 
-	TP_PROTO(struct task_struct *prev,
+	TP_PROTO(bool preempt,
+		 struct task_struct *prev,
 		 struct task_struct *next),
 
-	TP_ARGS(prev, next),
+	TP_ARGS(preempt, prev, next),
 
 	TP_STRUCT__entry(
 		__array(	char,	prev_comm,	TASK_COMM_LEN	)
@@ -135,7 +143,7 @@
 		memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
 		__entry->prev_pid	= prev->pid;
 		__entry->prev_prio	= prev->prio;
-		__entry->prev_state	= __trace_sched_switch_state(prev);
+		__entry->prev_state	= __trace_sched_switch_state(preempt, prev);
 		memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
 		__entry->next_pid	= next->pid;
 		__entry->next_prio	= next->prio;
@@ -147,7 +155,8 @@
 		  __print_flags(__entry->prev_state & (TASK_STATE_MAX-1), "|",
 				{ 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" },
 				{ 16, "Z" }, { 32, "X" }, { 64, "x" },
-				{ 128, "K" }, { 256, "W" }, { 512, "P" }) : "R",
+				{ 128, "K" }, { 256, "W" }, { 512, "P" },
+				{ 1024, "N" }) : "R",
 		__entry->prev_state & TASK_STATE_MAX ? "+" : "",
 		__entry->next_comm, __entry->next_pid, __entry->next_prio)
 );
@@ -313,7 +322,7 @@
 
 	TP_PROTO(struct task_struct *tsk, u64 delay),
 
-	TP_ARGS(tsk, delay),
+	TP_ARGS(__perf_task(tsk), __perf_count(delay)),
 
 	TP_STRUCT__entry(
 		__array( char,	comm,	TASK_COMM_LEN	)
@@ -325,10 +334,6 @@
 		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
 		__entry->pid	= tsk->pid;
 		__entry->delay	= delay;
-	)
-	TP_perf_assign(
-		__perf_count(delay);
-		__perf_task(tsk);
 	),
 
 	TP_printk("comm=%s pid=%d delay=%Lu [ns]",
@@ -372,11 +377,11 @@
  * Tracepoint for accounting runtime (time the task is executing
  * on a CPU).
  */
-TRACE_EVENT(sched_stat_runtime,
+DECLARE_EVENT_CLASS(sched_stat_runtime,
 
 	TP_PROTO(struct task_struct *tsk, u64 runtime, u64 vruntime),
 
-	TP_ARGS(tsk, runtime, vruntime),
+	TP_ARGS(tsk, __perf_count(runtime), vruntime),
 
 	TP_STRUCT__entry(
 		__array( char,	comm,	TASK_COMM_LEN	)
@@ -390,9 +395,6 @@
 		__entry->pid		= tsk->pid;
 		__entry->runtime	= runtime;
 		__entry->vruntime	= vruntime;
-	)
-	TP_perf_assign(
-		__perf_count(runtime);
 	),
 
 	TP_printk("comm=%s pid=%d runtime=%Lu [ns] vruntime=%Lu [ns]",
@@ -401,6 +403,10 @@
 			(unsigned long long)__entry->vruntime)
 );
 
+DEFINE_EVENT(sched_stat_runtime, sched_stat_runtime,
+	     TP_PROTO(struct task_struct *tsk, u64 runtime, u64 vruntime),
+	     TP_ARGS(tsk, runtime, vruntime));
+
 /*
  * Tracepoint for showing priority inheritance modifying a tasks
  * priority.
@@ -430,6 +436,132 @@
 			__entry->oldprio, __entry->newprio)
 );
 
+#ifdef CONFIG_DETECT_HUNG_TASK
+TRACE_EVENT(sched_process_hang,
+	TP_PROTO(struct task_struct *tsk),
+	TP_ARGS(tsk),
+
+	TP_STRUCT__entry(
+		__array( char,	comm,	TASK_COMM_LEN	)
+		__field( pid_t,	pid			)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+		__entry->pid = tsk->pid;
+	),
+
+	TP_printk("comm=%s pid=%d", __entry->comm, __entry->pid)
+);
+#endif /* CONFIG_DETECT_HUNG_TASK */
+
+DECLARE_EVENT_CLASS(sched_move_task_template,
+
+	TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu),
+
+	TP_ARGS(tsk, src_cpu, dst_cpu),
+
+	TP_STRUCT__entry(
+		__field( pid_t,	pid			)
+		__field( pid_t,	tgid			)
+		__field( pid_t,	ngid			)
+		__field( int,	src_cpu			)
+		__field( int,	src_nid			)
+		__field( int,	dst_cpu			)
+		__field( int,	dst_nid			)
+	),
+
+	TP_fast_assign(
+		__entry->pid		= task_pid_nr(tsk);
+		__entry->tgid		= task_tgid_nr(tsk);
+		__entry->ngid		= task_numa_group_id(tsk);
+		__entry->src_cpu	= src_cpu;
+		__entry->src_nid	= cpu_to_node(src_cpu);
+		__entry->dst_cpu	= dst_cpu;
+		__entry->dst_nid	= cpu_to_node(dst_cpu);
+	),
+
+	TP_printk("pid=%d tgid=%d ngid=%d src_cpu=%d src_nid=%d dst_cpu=%d dst_nid=%d",
+			__entry->pid, __entry->tgid, __entry->ngid,
+			__entry->src_cpu, __entry->src_nid,
+			__entry->dst_cpu, __entry->dst_nid)
+);
+
+/*
+ * Tracks migration of tasks from one runqueue to another. Can be used to
+ * detect if automatic NUMA balancing is bouncing between nodes
+ */
+DEFINE_EVENT(sched_move_task_template, sched_move_numa,
+	TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu),
+
+	TP_ARGS(tsk, src_cpu, dst_cpu)
+);
+
+DEFINE_EVENT(sched_move_task_template, sched_stick_numa,
+	TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu),
+
+	TP_ARGS(tsk, src_cpu, dst_cpu)
+);
+
+TRACE_EVENT(sched_swap_numa,
+
+	TP_PROTO(struct task_struct *src_tsk, int src_cpu,
+		 struct task_struct *dst_tsk, int dst_cpu),
+
+	TP_ARGS(src_tsk, src_cpu, dst_tsk, dst_cpu),
+
+	TP_STRUCT__entry(
+		__field( pid_t,	src_pid			)
+		__field( pid_t,	src_tgid		)
+		__field( pid_t,	src_ngid		)
+		__field( int,	src_cpu			)
+		__field( int,	src_nid			)
+		__field( pid_t,	dst_pid			)
+		__field( pid_t,	dst_tgid		)
+		__field( pid_t,	dst_ngid		)
+		__field( int,	dst_cpu			)
+		__field( int,	dst_nid			)
+	),
+
+	TP_fast_assign(
+		__entry->src_pid	= task_pid_nr(src_tsk);
+		__entry->src_tgid	= task_tgid_nr(src_tsk);
+		__entry->src_ngid	= task_numa_group_id(src_tsk);
+		__entry->src_cpu	= src_cpu;
+		__entry->src_nid	= cpu_to_node(src_cpu);
+		__entry->dst_pid	= task_pid_nr(dst_tsk);
+		__entry->dst_tgid	= task_tgid_nr(dst_tsk);
+		__entry->dst_ngid	= task_numa_group_id(dst_tsk);
+		__entry->dst_cpu	= dst_cpu;
+		__entry->dst_nid	= cpu_to_node(dst_cpu);
+	),
+
+	TP_printk("src_pid=%d src_tgid=%d src_ngid=%d src_cpu=%d src_nid=%d dst_pid=%d dst_tgid=%d dst_ngid=%d dst_cpu=%d dst_nid=%d",
+			__entry->src_pid, __entry->src_tgid, __entry->src_ngid,
+			__entry->src_cpu, __entry->src_nid,
+			__entry->dst_pid, __entry->dst_tgid, __entry->dst_ngid,
+			__entry->dst_cpu, __entry->dst_nid)
+);
+
+/*
+ * Tracepoint for waking a polling cpu without an IPI.
+ */
+TRACE_EVENT(sched_wake_idle_without_ipi,
+
+	TP_PROTO(int cpu),
+
+	TP_ARGS(cpu),
+
+	TP_STRUCT__entry(
+		__field(	int,	cpu	)
+	),
+
+	TP_fast_assign(
+		__entry->cpu	= cpu;
+	),
+
+	TP_printk("cpu=%d", __entry->cpu)
+);
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */