include/trace/events/sched.h

/* SPDX-License-Identifier: GPL-2.0 */
#undef TRACE_SYSTEM
#define TRACE_SYSTEM sched

#if !defined(_TRACE_SCHED_H) || defined(TRACE_HEADER_MULTI_READ)
#define _TRACE_SCHED_H

#include <linux/sched/numa_balancing.h>
#include <linux/tracepoint.h>
#include <linux/binfmts.h>

/*
 * Tracepoint for calling kthread_stop, performed to end a kthread:
 */
TRACE_EVENT(sched_kthread_stop,

	TP_PROTO(struct task_struct *t),

	TP_ARGS(t),

	TP_STRUCT__entry(
		__array(	char,	comm,	TASK_COMM_LEN	)
		__field(	pid_t,	pid			)
	),

	TP_fast_assign(
		memcpy(__entry->comm, t->comm, TASK_COMM_LEN);
		__entry->pid	= t->pid;
	),

	TP_printk("comm=%s pid=%d", __entry->comm, __entry->pid)
);

/*
 * Tracepoint for the return value of the kthread stopping:
 */
TRACE_EVENT(sched_kthread_stop_ret,

	TP_PROTO(int ret),

	TP_ARGS(ret),

	TP_STRUCT__entry(
		__field(	int,	ret	)
	),

	TP_fast_assign(
		__entry->ret	= ret;
	),

	TP_printk("ret=%d", __entry->ret)
);

/*
 * Tracepoint for waking up a task:
 */
DECLARE_EVENT_CLASS(sched_wakeup_template,

	TP_PROTO(struct task_struct *p),

	TP_ARGS(__perf_task(p)),

	TP_STRUCT__entry(
		__array(	char,	comm,	TASK_COMM_LEN	)
		__field(	pid_t,	pid			)
		__field(	int,	prio			)
		__field(	int,	success			)
		__field(	int,	target_cpu		)
	),

	TP_fast_assign(
		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);
	),

	TP_printk("comm=%s pid=%d prio=%d target_cpu=%03d",
		  __entry->comm, __entry->pid, __entry->prio,
		  __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),
	     TP_ARGS(p));

/*
 * Tracepoint for waking up a new task:
 */
DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new,
	     TP_PROTO(struct task_struct *p),
	     TP_ARGS(p));

#ifdef CREATE_TRACE_POINTS
static inline long __trace_sched_switch_state(bool preempt, struct task_struct *p)
{
	unsigned int state;

#ifdef CONFIG_SCHED_DEBUG
	BUG_ON(p != current);
#endif /* CONFIG_SCHED_DEBUG */

	/*
	 * Preemption ignores task state, therefore preempted tasks are always
	 * RUNNING (we will not have dequeued if state != RUNNING).
	 */
	if (preempt)
		return TASK_REPORT_MAX;

	/*
	 * task_state_index() uses fls() and returns a value from 0-8 range.
	 * Decrement it by 1 (except TASK_RUNNING state i.e 0) before using
	 * it for left shift operation to get the correct task->state
	 * mapping.
	 */
	state = task_state_index(p);

	return state ? (1 << (state - 1)) : state;
}
#endif /* CREATE_TRACE_POINTS */

/*
 * Tracepoint for task switches, performed by the scheduler:
 */
TRACE_EVENT(sched_switch,

	TP_PROTO(bool preempt,
		 struct task_struct *prev,
		 struct task_struct *next),

	TP_ARGS(preempt, prev, next),

	TP_STRUCT__entry(
		__array(	char,	prev_comm,	TASK_COMM_LEN	)
		__field(	pid_t,	prev_pid			)
		__field(	int,	prev_prio			)
		__field(	long,	prev_state			)
		__array(	char,	next_comm,	TASK_COMM_LEN	)
		__field(	pid_t,	next_pid			)
		__field(	int,	next_prio			)
	),

	TP_fast_assign(
		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);
		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",
		__entry->prev_comm, __entry->prev_pid, __entry->prev_prio,

		(__entry->prev_state & (TASK_REPORT_MAX - 1)) ?
		  __print_flags(__entry->prev_state & (TASK_REPORT_MAX - 1), "|",
				{ TASK_INTERRUPTIBLE, "S" },
				{ TASK_UNINTERRUPTIBLE, "D" },
				{ __TASK_STOPPED, "T" },
				{ __TASK_TRACED, "t" },
				{ EXIT_DEAD, "X" },
				{ EXIT_ZOMBIE, "Z" },
				{ TASK_PARKED, "P" },
				{ TASK_DEAD, "I" }) :
		  "R",

		__entry->prev_state & TASK_REPORT_MAX ? "+" : "",
		__entry->next_comm, __entry->next_pid, __entry->next_prio)
);

/*
 * Tracepoint for a task being migrated:
 */
TRACE_EVENT(sched_migrate_task,

	TP_PROTO(struct task_struct *p, int dest_cpu),

	TP_ARGS(p, dest_cpu),

	TP_STRUCT__entry(
		__array(	char,	comm,	TASK_COMM_LEN	)
		__field(	pid_t,	pid			)
		__field(	int,	prio			)
		__field(	int,	orig_cpu		)
		__field(	int,	dest_cpu		)
	),

	TP_fast_assign(
		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
		__entry->pid		= p->pid;
		__entry->prio		= p->prio; /* XXX SCHED_DEADLINE */
		__entry->orig_cpu	= task_cpu(p);
		__entry->dest_cpu	= dest_cpu;
	),

	TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d",
		  __entry->comm, __entry->pid, __entry->prio,
		  __entry->orig_cpu, __entry->dest_cpu)
);

DECLARE_EVENT_CLASS(sched_process_template,

	TP_PROTO(struct task_struct *p),

	TP_ARGS(p),

	TP_STRUCT__entry(
		__array(	char,	comm,	TASK_COMM_LEN	)
		__field(	pid_t,	pid			)
		__field(	int,	prio			)
	),

	TP_fast_assign(
		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
		__entry->pid		= p->pid;
		__entry->prio		= p->prio; /* XXX SCHED_DEADLINE */
	),

	TP_printk("comm=%s pid=%d prio=%d",
		  __entry->comm, __entry->pid, __entry->prio)
);

/*
 * Tracepoint for freeing a task:
 */
DEFINE_EVENT(sched_process_template, sched_process_free,
	     TP_PROTO(struct task_struct *p),
	     TP_ARGS(p));
	     

/*
 * Tracepoint for a task exiting:
 */
DEFINE_EVENT(sched_process_template, sched_process_exit,
	     TP_PROTO(struct task_struct *p),
	     TP_ARGS(p));

/*
 * Tracepoint for waiting on task to unschedule:
 */
DEFINE_EVENT(sched_process_template, sched_wait_task,
	TP_PROTO(struct task_struct *p),
	TP_ARGS(p));

/*
 * Tracepoint for a waiting task:
 */
TRACE_EVENT(sched_process_wait,

	TP_PROTO(struct pid *pid),

	TP_ARGS(pid),

	TP_STRUCT__entry(
		__array(	char,	comm,	TASK_COMM_LEN	)
		__field(	pid_t,	pid			)
		__field(	int,	prio			)
	),

	TP_fast_assign(
		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
		__entry->pid		= pid_nr(pid);
		__entry->prio		= current->prio; /* XXX SCHED_DEADLINE */
	),

	TP_printk("comm=%s pid=%d prio=%d",
		  __entry->comm, __entry->pid, __entry->prio)
);

/*
 * Tracepoint for do_fork:
 */
TRACE_EVENT(sched_process_fork,

	TP_PROTO(struct task_struct *parent, struct task_struct *child),

	TP_ARGS(parent, child),

	TP_STRUCT__entry(
		__array(	char,	parent_comm,	TASK_COMM_LEN	)
		__field(	pid_t,	parent_pid			)
		__array(	char,	child_comm,	TASK_COMM_LEN	)
		__field(	pid_t,	child_pid			)
	),

	TP_fast_assign(
		memcpy(__entry->parent_comm, parent->comm, TASK_COMM_LEN);
		__entry->parent_pid	= parent->pid;
		memcpy(__entry->child_comm, child->comm, TASK_COMM_LEN);
		__entry->child_pid	= child->pid;
	),

	TP_printk("comm=%s pid=%d child_comm=%s child_pid=%d",
		__entry->parent_comm, __entry->parent_pid,
		__entry->child_comm, __entry->child_pid)
);

/*
 * Tracepoint for exec:
 */
TRACE_EVENT(sched_process_exec,

	TP_PROTO(struct task_struct *p, pid_t old_pid,
		 struct linux_binprm *bprm),

	TP_ARGS(p, old_pid, bprm),

	TP_STRUCT__entry(
		__string(	filename,	bprm->filename	)
		__field(	pid_t,		pid		)
		__field(	pid_t,		old_pid		)
	),

	TP_fast_assign(
		__assign_str(filename, bprm->filename);
		__entry->pid		= p->pid;
		__entry->old_pid	= old_pid;
	),

	TP_printk("filename=%s pid=%d old_pid=%d", __get_str(filename),
		  __entry->pid, __entry->old_pid)
);

/*
 * XXX the below sched_stat tracepoints only apply to SCHED_OTHER/BATCH/IDLE
 *     adding sched_stat support to SCHED_FIFO/RR would be welcome.
 */
DECLARE_EVENT_CLASS(sched_stat_template,

	TP_PROTO(struct task_struct *tsk, u64 delay),

	TP_ARGS(__perf_task(tsk), __perf_count(delay)),

	TP_STRUCT__entry(
		__array( char,	comm,	TASK_COMM_LEN	)
		__field( pid_t,	pid			)
		__field( u64,	delay			)
	),

	TP_fast_assign(
		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
		__entry->pid	= tsk->pid;
		__entry->delay	= delay;
	),

	TP_printk("comm=%s pid=%d delay=%Lu [ns]",
			__entry->comm, __entry->pid,
			(unsigned long long)__entry->delay)
);


/*
 * Tracepoint for accounting wait time (time the task is runnable
 * but not actually running due to scheduler contention).
 */
DEFINE_EVENT(sched_stat_template, sched_stat_wait,
	     TP_PROTO(struct task_struct *tsk, u64 delay),
	     TP_ARGS(tsk, delay));

/*
 * Tracepoint for accounting sleep time (time the task is not runnable,
 * including iowait, see below).
 */
DEFINE_EVENT(sched_stat_template, sched_stat_sleep,
	     TP_PROTO(struct task_struct *tsk, u64 delay),
	     TP_ARGS(tsk, delay));

/*
 * Tracepoint for accounting iowait time (time the task is not runnable
 * due to waiting on IO to complete).
 */
DEFINE_EVENT(sched_stat_template, sched_stat_iowait,
	     TP_PROTO(struct task_struct *tsk, u64 delay),
	     TP_ARGS(tsk, delay));

/*
 * Tracepoint for accounting blocked time (time the task is in uninterruptible).
 */
DEFINE_EVENT(sched_stat_template, sched_stat_blocked,
	     TP_PROTO(struct task_struct *tsk, u64 delay),
	     TP_ARGS(tsk, delay));

/*
 * Tracepoint for recording the cause of uninterruptible sleep.
 */
TRACE_EVENT(sched_blocked_reason,

	TP_PROTO(struct task_struct *tsk),

	TP_ARGS(tsk),

	TP_STRUCT__entry(
		__field( pid_t,	pid	)
		__field( void*, caller	)
		__field( bool, io_wait	)
	),

	TP_fast_assign(
		__entry->pid	= tsk->pid;
		__entry->caller = (void*)get_wchan(tsk);
		__entry->io_wait = tsk->in_iowait;
	),

	TP_printk("pid=%d iowait=%d caller=%pS", __entry->pid, __entry->io_wait, __entry->caller)
);

/*
 * Tracepoint for accounting runtime (time the task is executing
 * on a CPU).
 */
DECLARE_EVENT_CLASS(sched_stat_runtime,

	TP_PROTO(struct task_struct *tsk, u64 runtime, u64 vruntime),

	TP_ARGS(tsk, __perf_count(runtime), vruntime),

	TP_STRUCT__entry(
		__array( char,	comm,	TASK_COMM_LEN	)
		__field( pid_t,	pid			)
		__field( u64,	runtime			)
		__field( u64,	vruntime			)
	),

	TP_fast_assign(
		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
		__entry->pid		= tsk->pid;
		__entry->runtime	= runtime;
		__entry->vruntime	= vruntime;
	),

	TP_printk("comm=%s pid=%d runtime=%Lu [ns] vruntime=%Lu [ns]",
			__entry->comm, __entry->pid,
			(unsigned long long)__entry->runtime,
			(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.
 */
TRACE_EVENT(sched_pi_setprio,

	TP_PROTO(struct task_struct *tsk, struct task_struct *pi_task),

	TP_ARGS(tsk, pi_task),

	TP_STRUCT__entry(
		__array( char,	comm,	TASK_COMM_LEN	)
		__field( pid_t,	pid			)
		__field( int,	oldprio			)
		__field( int,	newprio			)
	),

	TP_fast_assign(
		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
		__entry->pid		= tsk->pid;
		__entry->oldprio	= tsk->prio;
		__entry->newprio	= pi_task ?
				min(tsk->normal_prio, pi_task->prio) :
				tsk->normal_prio;
		/* XXX SCHED_DEADLINE bits missing */
	),

	TP_printk("comm=%s pid=%d oldprio=%d newprio=%d",
			__entry->comm, __entry->pid,
			__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)
);

#ifdef CONFIG_SMP
#ifdef CREATE_TRACE_POINTS
static inline
int __trace_sched_cpu(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
#ifdef CONFIG_FAIR_GROUP_SCHED
	struct rq *rq = cfs_rq ? cfs_rq->rq : NULL;
#else
	struct rq *rq = cfs_rq ? container_of(cfs_rq, struct rq, cfs) : NULL;
#endif
	return rq ? cpu_of(rq)
		  : task_cpu((container_of(se, struct task_struct, se)));
}

static inline
int __trace_sched_path(struct cfs_rq *cfs_rq, char *path, int len)
{
#ifdef CONFIG_FAIR_GROUP_SCHED
	int l = path ? len : 0;

	if (cfs_rq && task_group_is_autogroup(cfs_rq->tg))
		return autogroup_path(cfs_rq->tg, path, l) + 1;
	else if (cfs_rq && cfs_rq->tg->css.cgroup)
		return cgroup_path(cfs_rq->tg->css.cgroup, path, l) + 1;
#endif
	if (path)
		strcpy(path, "(null)");

	return strlen("(null)");
}

static inline
struct cfs_rq *__trace_sched_group_cfs_rq(struct sched_entity *se)
{
#ifdef CONFIG_FAIR_GROUP_SCHED
	return se->my_q;
#else
	return NULL;
#endif
}
#endif /* CREATE_TRACE_POINTS */

/*
 * Tracepoint for cfs_rq load tracking:
 */
TRACE_EVENT(sched_load_cfs_rq,

	TP_PROTO(struct cfs_rq *cfs_rq),

	TP_ARGS(cfs_rq),

	TP_STRUCT__entry(
		__field(	int,		cpu			)
		__dynamic_array(char,		path,
				__trace_sched_path(cfs_rq, NULL, 0)	)
		__field(	unsigned long,	load			)
		__field(	unsigned long,	rbl_load		)
		__field(	unsigned long,	util			)
	),

	TP_fast_assign(
		__entry->cpu		= __trace_sched_cpu(cfs_rq, NULL);
		__trace_sched_path(cfs_rq, __get_dynamic_array(path),
				   __get_dynamic_array_len(path));
		__entry->load		= cfs_rq->avg.load_avg;
		__entry->rbl_load 	= cfs_rq->avg.runnable_load_avg;
		__entry->util		= cfs_rq->avg.util_avg;
	),

	TP_printk("cpu=%d path=%s load=%lu rbl_load=%lu util=%lu",
		  __entry->cpu, __get_str(path), __entry->load,
		  __entry->rbl_load,__entry->util)
);

/*
 * Tracepoint for rt_rq load tracking:
 */
struct rq;
TRACE_EVENT(sched_load_rt_rq,

	TP_PROTO(struct rq *rq),

	TP_ARGS(rq),

	TP_STRUCT__entry(
		__field(	int,		cpu			)
		__field(	unsigned long,	util			)
	),

	TP_fast_assign(
		__entry->cpu	= rq->cpu;
		__entry->util	= rq->avg_rt.util_avg;
	),

	TP_printk("cpu=%d util=%lu", __entry->cpu,
		  __entry->util)
);

/*
 * Tracepoint for sched_entity load tracking:
 */
TRACE_EVENT(sched_load_se,

	TP_PROTO(struct sched_entity *se),

	TP_ARGS(se),

	TP_STRUCT__entry(
		__field(	int,		cpu			      )
		__dynamic_array(char,		path,
		  __trace_sched_path(__trace_sched_group_cfs_rq(se), NULL, 0) )
		__array(	char,		comm,	TASK_COMM_LEN	      )
		__field(	pid_t,		pid			      )
		__field(	unsigned long,	load			      )
		__field(	unsigned long,	rbl_load		      )
		__field(	unsigned long,	util			      )
	),

	TP_fast_assign(
		struct cfs_rq *gcfs_rq = __trace_sched_group_cfs_rq(se);
		struct task_struct *p = gcfs_rq ? NULL
				    : container_of(se, struct task_struct, se);

		__entry->cpu		= __trace_sched_cpu(gcfs_rq, se);
		__trace_sched_path(gcfs_rq, __get_dynamic_array(path),
				   __get_dynamic_array_len(path));
		memcpy(__entry->comm, p ? p->comm : "(null)",
				      p ? TASK_COMM_LEN : sizeof("(null)"));
		__entry->pid = p ? p->pid : -1;
		__entry->load = se->avg.load_avg;
		__entry->rbl_load = se->avg.runnable_load_avg;
		__entry->util = se->avg.util_avg;
	),

	TP_printk("cpu=%d path=%s comm=%s pid=%d load=%lu rbl_load=%lu util=%lu",
		  __entry->cpu, __get_str(path), __entry->comm, __entry->pid,
		  __entry->load, __entry->rbl_load, __entry->util)
);

/*
 * Tracepoint for task_group load tracking:
 */
#ifdef CONFIG_FAIR_GROUP_SCHED
TRACE_EVENT(sched_load_tg,

	TP_PROTO(struct cfs_rq *cfs_rq),

	TP_ARGS(cfs_rq),

	TP_STRUCT__entry(
		__field(	int,	cpu				)
		__dynamic_array(char,	path,
				__trace_sched_path(cfs_rq, NULL, 0)	)
		__field(	long,	load				)
	),

	TP_fast_assign(
		__entry->cpu	= cfs_rq->rq->cpu;
		__trace_sched_path(cfs_rq, __get_dynamic_array(path),
				   __get_dynamic_array_len(path));
		__entry->load	= atomic_long_read(&cfs_rq->tg->load_avg);
	),

	TP_printk("cpu=%d path=%s load=%ld", __entry->cpu, __get_str(path),
		  __entry->load)
);
#endif /* CONFIG_FAIR_GROUP_SCHED */

/*
 * Tracepoint for tasks' estimated utilization.
 */
TRACE_EVENT(sched_util_est_task,

	TP_PROTO(struct task_struct *tsk, struct sched_avg *avg),

	TP_ARGS(tsk, avg),

	TP_STRUCT__entry(
		__array( char,	comm,	TASK_COMM_LEN		)
		__field( pid_t,		pid			)
		__field( int,		cpu			)
		__field( unsigned int,	util_avg		)
		__field( unsigned int,	est_enqueued		)
		__field( unsigned int,	est_ewma		)

	),

	TP_fast_assign(
		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
		__entry->pid			= tsk->pid;
		__entry->cpu			= task_cpu(tsk);
		__entry->util_avg		= avg->util_avg;
		__entry->est_enqueued		= avg->util_est.enqueued;
		__entry->est_ewma		= avg->util_est.ewma;
	),

	TP_printk("comm=%s pid=%d cpu=%d util_avg=%u util_est_ewma=%u util_est_enqueued=%u",
		  __entry->comm,
		  __entry->pid,
		  __entry->cpu,
		  __entry->util_avg,
		  __entry->est_ewma,
		  __entry->est_enqueued)
);

/*
 * Tracepoint for root cfs_rq's estimated utilization.
 */
TRACE_EVENT(sched_util_est_cpu,

	TP_PROTO(int cpu, struct cfs_rq *cfs_rq),

	TP_ARGS(cpu, cfs_rq),

	TP_STRUCT__entry(
		__field( int,		cpu			)
		__field( unsigned int,	util_avg		)
		__field( unsigned int,	util_est_enqueued	)
	),

	TP_fast_assign(
		__entry->cpu			= cpu;
		__entry->util_avg		= cfs_rq->avg.util_avg;
		__entry->util_est_enqueued	= cfs_rq->avg.util_est.enqueued;
	),

	TP_printk("cpu=%d util_avg=%u util_est_enqueued=%u",
		  __entry->cpu,
		  __entry->util_avg,
		  __entry->util_est_enqueued)
);

/*
 * Tracepoint for find_best_target
 */
TRACE_EVENT(sched_find_best_target,

	TP_PROTO(struct task_struct *tsk, bool prefer_idle,
		 unsigned long min_util, int best_idle, int best_active,
		 int target, int backup),

	TP_ARGS(tsk, prefer_idle, min_util, best_idle,
		best_active, target, backup),

	TP_STRUCT__entry(
		__array( char,  comm,   TASK_COMM_LEN   )
		__field( pid_t, pid                     )
		__field( unsigned long, min_util        )
		__field( bool,  prefer_idle             )
		__field( int,   best_idle               )
		__field( int,   best_active             )
		__field( int,   target                  )
		__field( int,   backup                  )
		),

	TP_fast_assign(
		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
		__entry->pid            = tsk->pid;
		__entry->min_util       = min_util;
		__entry->prefer_idle    = prefer_idle;
		__entry->best_idle      = best_idle;
		__entry->best_active    = best_active;
		__entry->target         = target;
		__entry->backup         = backup;
		),

	TP_printk("pid=%d comm=%s prefer_idle=%d "
		  "best_idle=%d best_active=%d target=%d backup=%d",
		  __entry->pid, __entry->comm, __entry->prefer_idle,
		  __entry->best_idle, __entry->best_active,
		  __entry->target, __entry->backup)
);

/*
 * Tracepoint for accounting CPU  boosted utilization
 */
TRACE_EVENT(sched_boost_cpu,

	TP_PROTO(int cpu, unsigned long util, long margin),

	TP_ARGS(cpu, util, margin),

	TP_STRUCT__entry(
		__field( int,           cpu	)
		__field( unsigned long, util	)
		__field(long,           margin	)
	),

	TP_fast_assign(
		__entry->cpu    = cpu;
		__entry->util   = util;
		__entry->margin = margin;
	),

	TP_printk("cpu=%d util=%lu margin=%ld",
		__entry->cpu,
		__entry->util,
		__entry->margin)
);

/*
 * Tracepoint for schedtune_tasks_update
 */
TRACE_EVENT(sched_tune_tasks_update,

	TP_PROTO(struct task_struct *tsk, int cpu, int tasks, int idx,
		int boost, int max_boost, u64 group_ts),

	TP_ARGS(tsk, cpu, tasks, idx, boost, max_boost, group_ts),

	TP_STRUCT__entry(
		__array( char,  comm,   TASK_COMM_LEN   )
		__field( pid_t,         pid             )
		__field( int,           cpu             )
		__field( int,           tasks           )
		__field( int,           idx             )
		__field( int,           boost           )
		__field( int,           max_boost       )
		__field( u64,		group_ts	)
	),

	TP_fast_assign(
		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
		__entry->pid            = tsk->pid;
		__entry->cpu            = cpu;
		__entry->tasks          = tasks;
		__entry->idx            = idx;
		__entry->boost          = boost;
		__entry->max_boost      = max_boost;
		__entry->group_ts	= group_ts;
	),

	TP_printk("pid=%d comm=%s "
		"cpu=%d tasks=%d idx=%d boost=%d max_boost=%d timeout=%llu",
		__entry->pid, __entry->comm,
		__entry->cpu, __entry->tasks, __entry->idx,
		__entry->boost, __entry->max_boost,
		__entry->group_ts)
);

/*
 * Tracepoint for schedtune_boostgroup_update
 */
TRACE_EVENT(sched_tune_boostgroup_update,

	TP_PROTO(int cpu, int variation, int max_boost),

	TP_ARGS(cpu, variation, max_boost),

	TP_STRUCT__entry(
		__field( int,   cpu		)
		__field( int,   variation	)
		__field( int,   max_boost	)
	),

	TP_fast_assign(
		__entry->cpu            = cpu;
		__entry->variation      = variation;
		__entry->max_boost      = max_boost;
	),

	TP_printk("cpu=%d variation=%d max_boost=%d",
		__entry->cpu, __entry->variation, __entry->max_boost)
);

/*
 * Tracepoint for accounting task boosted utilization
 */
TRACE_EVENT(sched_boost_task,

	TP_PROTO(struct task_struct *tsk, unsigned long util, long margin),

	TP_ARGS(tsk, util, margin),

	TP_STRUCT__entry(
		__array( char,  comm,   TASK_COMM_LEN	)
		__field( pid_t,         pid		)
		__field( unsigned long, util		)
		__field( long,          margin		)

	),

	TP_fast_assign(
		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
		__entry->pid    = tsk->pid;
		__entry->util   = util;
		__entry->margin = margin;
	),

	TP_printk("comm=%s pid=%d util=%lu margin=%ld",
		__entry->comm, __entry->pid,
		__entry->util,
		__entry->margin)
);

/*
 * Tracepoint for system overutilized flag
*/
TRACE_EVENT(sched_overutilized,

	TP_PROTO(int overutilized),

	TP_ARGS(overutilized),

	TP_STRUCT__entry(
		__field( int,  overutilized    )
	),

	TP_fast_assign(
		__entry->overutilized   = overutilized;
	),

	TP_printk("overutilized=%d",
		__entry->overutilized)
);

#endif /* CONFIG_SMP */
#endif /* _TRACE_SCHED_H */

/* This part must be outside protection */
#include <trace/define_trace.h>