tracing, sched: LTTng instrumentation - scheduler

Instrument the scheduler activity (sched_switch, migration, wakeups,
wait for a task, signal delivery) and process/thread
creation/destruction (fork, exit, kthread stop). Actually, kthread
creation is not instrumented in this patch because it is architecture
dependent. It allows to connect tracers such as ftrace which detects
scheduling latencies, good/bad scheduler decisions. Tools like LTTng can
export this scheduler information along with instrumentation of the rest
of the kernel activity to perform post-mortem analysis on the scheduler
activity.

About the performance impact of tracepoints (which is comparable to
markers), even without immediate values optimizations, tests done by
Hideo Aoki on ia64 show no regression. His test case was using hackbench
on a kernel where scheduler instrumentation (about 5 events in code
scheduler code) was added. See the "Tracepoints" patch header for
performance result detail.

Changelog :

- Change instrumentation location and parameter to match ftrace
  instrumentation, previously done with kernel markers.

[ mingo@elte.hu: conflict resolutions ]
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Acked-by: 'Peter Zijlstra' <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

include/trace/sched.h

@@ -0,0 +1,45 @@
+#ifndef _TRACE_SCHED_H
+#define _TRACE_SCHED_H
+
+#include <linux/sched.h>
+#include <linux/tracepoint.h>
+
+DEFINE_TRACE(sched_kthread_stop,
+	TPPROTO(struct task_struct *t),
+	TPARGS(t));
+DEFINE_TRACE(sched_kthread_stop_ret,
+	TPPROTO(int ret),
+	TPARGS(ret));
+DEFINE_TRACE(sched_wait_task,
+	TPPROTO(struct rq *rq, struct task_struct *p),
+	TPARGS(rq, p));
+DEFINE_TRACE(sched_wakeup,
+	TPPROTO(struct rq *rq, struct task_struct *p),
+	TPARGS(rq, p));
+DEFINE_TRACE(sched_wakeup_new,
+	TPPROTO(struct rq *rq, struct task_struct *p),
+	TPARGS(rq, p));
+DEFINE_TRACE(sched_switch,
+	TPPROTO(struct rq *rq, struct task_struct *prev,
+		struct task_struct *next),
+	TPARGS(rq, prev, next));
+DEFINE_TRACE(sched_migrate_task,
+	TPPROTO(struct rq *rq, struct task_struct *p, int dest_cpu),
+	TPARGS(rq, p, dest_cpu));
+DEFINE_TRACE(sched_process_free,
+	TPPROTO(struct task_struct *p),
+	TPARGS(p));
+DEFINE_TRACE(sched_process_exit,
+	TPPROTO(struct task_struct *p),
+	TPARGS(p));
+DEFINE_TRACE(sched_process_wait,
+	TPPROTO(struct pid *pid),
+	TPARGS(pid));
+DEFINE_TRACE(sched_process_fork,
+	TPPROTO(struct task_struct *parent, struct task_struct *child),
+	TPARGS(parent, child));
+DEFINE_TRACE(sched_signal_send,
+	TPPROTO(int sig, struct task_struct *p),
+	TPARGS(sig, p));
+
+#endif

kernel/exit.c

@@ -47,6 +47,7 @@
 #include <linux/blkdev.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/tracehook.h>
+#include <trace/sched.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -149,7 +150,10 @@ static void __exit_signal(struct task_struct *tsk)
 
 static void delayed_put_task_struct(struct rcu_head *rhp)
 {
-	put_task_struct(container_of(rhp, struct task_struct, rcu));
+	struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
+
+	trace_sched_process_free(tsk);
+	put_task_struct(tsk);
 }
 
 
@@ -1074,6 +1078,8 @@ NORET_TYPE void do_exit(long code)
 
 	if (group_dead)
 		acct_process();
+	trace_sched_process_exit(tsk);
+
 	exit_sem(tsk);
 	exit_files(tsk);
 	exit_fs(tsk);
@@ -1675,6 +1681,8 @@ static long do_wait(enum pid_type type, struct pid *pid, int options,
 	struct task_struct *tsk;
 	int retval;
 
+	trace_sched_process_wait(pid);
+
 	add_wait_queue(&current->signal->wait_chldexit,&wait);
 repeat:
 	/*

kernel/fork.c

@@ -58,6 +58,7 @@
 #include <linux/tty.h>
 #include <linux/proc_fs.h>
 #include <linux/blkdev.h>
+#include <trace/sched.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -1364,6 +1365,8 @@ long do_fork(unsigned long clone_flags,
 	if (!IS_ERR(p)) {
 		struct completion vfork;
 
+		trace_sched_process_fork(current, p);
+
 		nr = task_pid_vnr(p);
 
 		if (clone_flags & CLONE_PARENT_SETTID)

kernel/kthread.c

@@ -13,6 +13,7 @@
 #include <linux/file.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <trace/sched.h>
 
 #define KTHREAD_NICE_LEVEL (-5)
 
@@ -206,6 +207,8 @@ int kthread_stop(struct task_struct *k)
 	/* It could exit after stop_info.k set, but before wake_up_process. */
 	get_task_struct(k);
 
+	trace_sched_kthread_stop(k);
+
 	/* Must init completion *before* thread sees kthread_stop_info.k */
 	init_completion(&kthread_stop_info.done);
 	smp_wmb();
@@ -221,6 +224,8 @@ int kthread_stop(struct task_struct *k)
 	ret = kthread_stop_info.err;
 	mutex_unlock(&kthread_stop_lock);
 
+	trace_sched_kthread_stop_ret(ret);
+
 	return ret;
 }
 EXPORT_SYMBOL(kthread_stop);

kernel/sched.c

@@ -71,6 +71,7 @@
 #include <linux/debugfs.h>
 #include <linux/ctype.h>
 #include <linux/ftrace.h>
+#include <trace/sched.h>
 
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
@@ -1936,6 +1937,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 		 * just go back and repeat.
 		 */
 		rq = task_rq_lock(p, &flags);
+		trace_sched_wait_task(rq, p);
 		running = task_running(rq, p);
 		on_rq = p->se.on_rq;
 		ncsw = 0;
@@ -2297,9 +2299,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
 	success = 1;
 
 out_running:
-	trace_mark(kernel_sched_wakeup,
+	trace_sched_wakeup(rq, p);
-		"pid %d state %ld ## rq %p task %p rq->curr %p",
-		p->pid, p->state, rq, p, rq->curr);
 	check_preempt_curr(rq, p, sync);
 
 	p->state = TASK_RUNNING;
@@ -2432,9 +2432,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
 		p->sched_class->task_new(rq, p);
 		inc_nr_running(rq);
 	}
-	trace_mark(kernel_sched_wakeup_new,
+	trace_sched_wakeup_new(rq, p);
-		"pid %d state %ld ## rq %p task %p rq->curr %p",
-		p->pid, p->state, rq, p, rq->curr);
 	check_preempt_curr(rq, p, 0);
 #ifdef CONFIG_SMP
 	if (p->sched_class->task_wake_up)
@@ -2607,11 +2605,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
 	struct mm_struct *mm, *oldmm;
 
 	prepare_task_switch(rq, prev, next);
-	trace_mark(kernel_sched_schedule,
+	trace_sched_switch(rq, prev, next);
-		"prev_pid %d next_pid %d prev_state %ld "
-		"## rq %p prev %p next %p",
-		prev->pid, next->pid, prev->state,
-		rq, prev, next);
 	mm = next->mm;
 	oldmm = prev->active_mm;
 	/*
@@ -2851,6 +2845,7 @@ static void sched_migrate_task(struct task_struct *p, int dest_cpu)
 	    || unlikely(!cpu_active(dest_cpu)))
 		goto out;
 
+	trace_sched_migrate_task(rq, p, dest_cpu);
 	/* force the process onto the specified CPU */
 	if (migrate_task(p, dest_cpu, &req)) {
 		/* Need to wait for migration thread (might exit: take ref). */

kernel/signal.c

@@ -27,6 +27,7 @@
 #include <linux/freezer.h>
 #include <linux/pid_namespace.h>
 #include <linux/nsproxy.h>
+#include <trace/sched.h>
 
 #include <asm/param.h>
 #include <asm/uaccess.h>
@@ -803,6 +804,8 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
 	struct sigpending *pending;
 	struct sigqueue *q;
 
+	trace_sched_signal_send(sig, t);
+
 	assert_spin_locked(&t->sighand->siglock);
 	if (!prepare_signal(sig, t))
 		return 0;