1 files changed, 142 insertions, 32 deletions

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 420e80e56e55..fbb99a61f714 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -5,6 +5,7 @@
 #if !defined(_TRACE_SCHED_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_SCHED_H
 
+#include <linux/kthread.h>
 #include <linux/sched/numa_balancing.h>
 #include <linux/tracepoint.h>
 #include <linux/binfmts.h>
@@ -51,6 +52,89 @@ TRACE_EVENT(sched_kthread_stop_ret,
 	TP_printk("ret=%d", __entry->ret)
 );
 
+/**
+ * sched_kthread_work_queue_work - called when a work gets queued
+ * @worker:	pointer to the kthread_worker
+ * @work:	pointer to struct kthread_work
+ *
+ * This event occurs when a work is queued immediately or once a
+ * delayed work is actually queued (ie: once the delay has been
+ * reached).
+ */
+TRACE_EVENT(sched_kthread_work_queue_work,
+
+	TP_PROTO(struct kthread_worker *worker,
+		 struct kthread_work *work),
+
+	TP_ARGS(worker, work),
+
+	TP_STRUCT__entry(
+		__field( void *,	work	)
+		__field( void *,	function)
+		__field( void *,	worker)
+	),
+
+	TP_fast_assign(
+		__entry->work		= work;
+		__entry->function	= work->func;
+		__entry->worker		= worker;
+	),
+
+	TP_printk("work struct=%p function=%ps worker=%p",
+		  __entry->work, __entry->function, __entry->worker)
+);
+
+/**
+ * sched_kthread_work_execute_start - called immediately before the work callback
+ * @work:	pointer to struct kthread_work
+ *
+ * Allows to track kthread work execution.
+ */
+TRACE_EVENT(sched_kthread_work_execute_start,
+
+	TP_PROTO(struct kthread_work *work),
+
+	TP_ARGS(work),
+
+	TP_STRUCT__entry(
+		__field( void *,	work	)
+		__field( void *,	function)
+	),
+
+	TP_fast_assign(
+		__entry->work		= work;
+		__entry->function	= work->func;
+	),
+
+	TP_printk("work struct %p: function %ps", __entry->work, __entry->function)
+);
+
+/**
+ * sched_kthread_work_execute_end - called immediately after the work callback
+ * @work:	pointer to struct work_struct
+ * @function:   pointer to worker function
+ *
+ * Allows to track workqueue execution.
+ */
+TRACE_EVENT(sched_kthread_work_execute_end,
+
+	TP_PROTO(struct kthread_work *work, kthread_work_func_t function),
+
+	TP_ARGS(work, function),
+
+	TP_STRUCT__entry(
+		__field( void *,	work	)
+		__field( void *,	function)
+	),
+
+	TP_fast_assign(
+		__entry->work		= work;
+		__entry->function	= function;
+	),
+
+	TP_printk("work struct %p: function %ps", __entry->work, __entry->function)
+);
+
 /*
  * Tracepoint for waking up a task:
  */
@@ -64,7 +148,6 @@ DECLARE_EVENT_CLASS(sched_wakeup_template,
 		__array(	char,	comm,	TASK_COMM_LEN	)
 		__field(	pid_t,	pid			)
 		__field(	int,	prio			)
-		__field(	int,	success			)
 		__field(	int,	target_cpu		)
 	),
 
@@ -72,7 +155,6 @@ DECLARE_EVENT_CLASS(sched_wakeup_template,
 		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
 		__entry->pid		= p->pid;
 		__entry->prio		= p->prio; /* XXX SCHED_DEADLINE */
-		__entry->success	= 1; /* rudiment, kill when possible */
 		__entry->target_cpu	= task_cpu(p);
 	),
 
@@ -90,8 +172,8 @@ DEFINE_EVENT(sched_wakeup_template, sched_waking,
 	     TP_ARGS(p));
 
 /*
- * Tracepoint called when the task is actually woken; p->state == TASK_RUNNNG.
- * It it not always called from the waking context.
+ * Tracepoint called when the task is actually woken; p->state == TASK_RUNNING.
+ * It is not always called from the waking context.
  */
 DEFINE_EVENT(sched_wakeup_template, sched_wakeup,
 	     TP_PROTO(struct task_struct *p),
@@ -105,7 +187,9 @@ DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new,
 	     TP_ARGS(p));
 
 #ifdef CREATE_TRACE_POINTS
-static inline long __trace_sched_switch_state(bool preempt, struct task_struct *p)
+static inline long __trace_sched_switch_state(bool preempt,
+					      unsigned int prev_state,
+					      struct task_struct *p)
 {
 	unsigned int state;
 
@@ -126,7 +210,7 @@ static inline long __trace_sched_switch_state(bool preempt, struct task_struct *
 	 * it for left shift operation to get the correct task->state
 	 * mapping.
 	 */
-	state = task_state_index(p);
+	state = __task_state_index(prev_state, p->exit_state);
 
 	return state ? (1 << (state - 1)) : state;
 }
@@ -139,9 +223,10 @@ TRACE_EVENT(sched_switch,
 
 	TP_PROTO(bool preempt,
 		 struct task_struct *prev,
-		 struct task_struct *next),
+		 struct task_struct *next,
+		 unsigned int prev_state),
 
-	TP_ARGS(preempt, prev, next),
+	TP_ARGS(preempt, prev, next, prev_state),
 
 	TP_STRUCT__entry(
 		__array(	char,	prev_comm,	TASK_COMM_LEN	)
@@ -157,7 +242,7 @@ TRACE_EVENT(sched_switch,
 		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(preempt, prev);
+		__entry->prev_state	= __trace_sched_switch_state(preempt, prev_state, prev);
 		memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
 		__entry->next_pid	= next->pid;
 		__entry->next_prio	= next->prio;
@@ -282,7 +367,7 @@ TRACE_EVENT(sched_process_wait,
 );
 
 /*
- * Tracepoint for do_fork:
+ * Tracepoint for kernel_clone:
  */
 TRACE_EVENT(sched_process_fork,
 
@@ -487,7 +572,11 @@ TRACE_EVENT(sched_process_hang,
 );
 #endif /* CONFIG_DETECT_HUNG_TASK */
 
-DECLARE_EVENT_CLASS(sched_move_task_template,
+/*
+ * Tracks migration of tasks from one runqueue to another. Can be used to
+ * detect if automatic NUMA balancing is bouncing between nodes.
+ */
+TRACE_EVENT(sched_move_numa,
 
 	TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu),
 
@@ -519,23 +608,7 @@ DECLARE_EVENT_CLASS(sched_move_task_template,
 			__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,
+DECLARE_EVENT_CLASS(sched_numa_pair_template,
 
 	TP_PROTO(struct task_struct *src_tsk, int src_cpu,
 		 struct task_struct *dst_tsk, int dst_cpu),
@@ -561,11 +634,11 @@ TRACE_EVENT(sched_swap_numa,
 		__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_pid	= dst_tsk ? task_pid_nr(dst_tsk) : 0;
+		__entry->dst_tgid	= dst_tsk ? task_tgid_nr(dst_tsk) : 0;
+		__entry->dst_ngid	= dst_tsk ? task_numa_group_id(dst_tsk) : 0;
 		__entry->dst_cpu	= dst_cpu;
-		__entry->dst_nid	= cpu_to_node(dst_cpu);
+		__entry->dst_nid	= dst_cpu >= 0 ? cpu_to_node(dst_cpu) : -1;
 	),
 
 	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",
@@ -575,6 +648,23 @@ TRACE_EVENT(sched_swap_numa,
 			__entry->dst_cpu, __entry->dst_nid)
 );
 
+DEFINE_EVENT(sched_numa_pair_template, sched_stick_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)
+);
+
+DEFINE_EVENT(sched_numa_pair_template, 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)
+);
+
+
 /*
  * Tracepoint for waking a polling cpu without an IPI.
  */
@@ -613,6 +703,10 @@ DECLARE_TRACE(pelt_dl_tp,
 	TP_PROTO(struct rq *rq),
 	TP_ARGS(rq));
 
+DECLARE_TRACE(pelt_thermal_tp,
+	TP_PROTO(struct rq *rq),
+	TP_ARGS(rq));
+
 DECLARE_TRACE(pelt_irq_tp,
 	TP_PROTO(struct rq *rq),
 	TP_ARGS(rq));
@@ -621,10 +715,26 @@ DECLARE_TRACE(pelt_se_tp,
 	TP_PROTO(struct sched_entity *se),
 	TP_ARGS(se));
 
+DECLARE_TRACE(sched_cpu_capacity_tp,
+	TP_PROTO(struct rq *rq),
+	TP_ARGS(rq));
+
 DECLARE_TRACE(sched_overutilized_tp,
 	TP_PROTO(struct root_domain *rd, bool overutilized),
 	TP_ARGS(rd, overutilized));
 
+DECLARE_TRACE(sched_util_est_cfs_tp,
+	TP_PROTO(struct cfs_rq *cfs_rq),
+	TP_ARGS(cfs_rq));
+
+DECLARE_TRACE(sched_util_est_se_tp,
+	TP_PROTO(struct sched_entity *se),
+	TP_ARGS(se));
+
+DECLARE_TRACE(sched_update_nr_running_tp,
+	TP_PROTO(struct rq *rq, int change),
+	TP_ARGS(rq, change));
+
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */