#undef TRACE_SYSTEM
#define TRACE_SYSTEM sched

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

#include <linux/sched.h>
#include <linux/tracepoint.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("task %s:%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 waiting on task to unschedule:
 *
 * (NOTE: the 'rq' argument is not used by generic trace events,
 *        but used by the latency tracer plugin. )
 */
TRACE_EVENT(sched_wait_task,

	TP_PROTO(struct rq *rq, struct task_struct *p),

	TP_ARGS(rq, 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;
	),

	TP_printk("task %s:%d [%d]",
		  __entry->comm, __entry->pid, __entry->prio)
);

/*
 * Tracepoint for waking up a task:
 *
 * (NOTE: the 'rq' argument is not used by generic trace events,
 *        but used by the latency tracer plugin. )
 */
TRACE_EVENT(sched_wakeup,

	TP_PROTO(struct rq *rq, struct task_struct *p, int success),

	TP_ARGS(rq, p, success),

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

	TP_fast_assign(
		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
		__entry->pid		= p->pid;
		__entry->prio		= p->prio;
		__entry->success	= success;
		__entry->cpu		= task_cpu(p);
	),

	TP_printk("task %s:%d [%d] success=%d [%03d]",
		  __entry->comm, __entry->pid, __entry->prio,
		  __entry->success, __entry->cpu)
);

/*
 * Tracepoint for waking up a new task:
 *
 * (NOTE: the 'rq' argument is not used by generic trace events,
 *        but used by the latency tracer plugin. )
 */
TRACE_EVENT(sched_wakeup_new,

	TP_PROTO(struct rq *rq, struct task_struct *p, int success),

	TP_ARGS(rq, p, success),

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

	TP_fast_assign(
		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
		__entry->pid		= p->pid;
		__entry->prio		= p->prio;
		__entry->success	= success;
		__entry->cpu		= task_cpu(p);
	),

	TP_printk("task %s:%d [%d] success=%d [%03d]",
		  __entry->comm, __entry->pid, __entry->prio,
		  __entry->success, __entry->cpu)
);

/*
 * Tracepoint for task switches, performed by the scheduler:
 *
 * (NOTE: the 'rq' argument is not used by generic trace events,
 *        but used by the latency tracer plugin. )
 */
TRACE_EVENT(sched_switch,

	TP_PROTO(struct rq *rq, struct task_struct *prev,
		 struct task_struct *next),

	TP_ARGS(rq, 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	= prev->state;
		memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
		__entry->next_pid	= next->pid;
		__entry->next_prio	= next->prio;
	),

	TP_printk("task %s:%d [%d] (%s) ==> %s:%d [%d]",
		__entry->prev_comm, __entry->prev_pid, __entry->prev_prio,
		__entry->prev_state ?
		  __print_flags(__entry->prev_state, "|",
				{ 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" },
				{ 16, "Z" }, { 32, "X" }, { 64, "x" },
				{ 128, "W" }) : "R",
		__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;
		__entry->orig_cpu	= task_cpu(p);
		__entry->dest_cpu	= dest_cpu;
	),

	TP_printk("task %s:%d [%d] from: %d  to: %d",
		  __entry->comm, __entry->pid, __entry->prio,
		  __entry->orig_cpu, __entry->dest_cpu)
);

/*
 * Tracepoint for freeing a task:
 */
TRACE_EVENT(sched_process_free,

	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;
	),

	TP_printk("task %s:%d [%d]",
		  __entry->comm, __entry->pid, __entry->prio)
);

/*
 * Tracepoint for a task exiting:
 */
TRACE_EVENT(sched_process_exit,

	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;
	),

	TP_printk("task %s:%d [%d]",
		  __entry->comm, __entry->pid, __entry->prio)
);

/*
 * 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;
	),

	TP_printk("task %s:%d [%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("parent %s:%d  child %s:%d",
		__entry->parent_comm, __entry->parent_pid,
		__entry->child_comm, __entry->child_pid)
);

/*
 * Tracepoint for sending a signal:
 */
TRACE_EVENT(sched_signal_send,

	TP_PROTO(int sig, struct task_struct *p),

	TP_ARGS(sig, p),

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

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

	TP_printk("sig: %d  task %s:%d",
		  __entry->sig, __entry->comm, __entry->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.
 */

/*
 * Tracepoint for accounting wait time (time the task is runnable
 * but not actually running due to scheduler contention).
 */
TRACE_EVENT(sched_stat_wait,

	TP_PROTO(struct task_struct *tsk, u64 delay),

	TP_ARGS(tsk, 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_perf_assign(
		__perf_count(delay);
	),

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

/*
 * Tracepoint for accounting sleep time (time the task is not runnable,
 * including iowait, see below).
 */
TRACE_EVENT(sched_stat_sleep,

	TP_PROTO(struct task_struct *tsk, u64 delay),

	TP_ARGS(tsk, 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_perf_assign(
		__perf_count(delay);
	),

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

/*
 * Tracepoint for accounting iowait time (time the task is not runnable
 * due to waiting on IO to complete).
 */
TRACE_EVENT(sched_stat_iowait,

	TP_PROTO(struct task_struct *tsk, u64 delay),

	TP_ARGS(tsk, 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_perf_assign(
		__perf_count(delay);
	),

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

#endif /* _TRACE_SCHED_H */

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