Commit 5a40a9bb authored by Peter Zijlstra's avatar Peter Zijlstra
Browse files

sched/debug: Fix dl_server (re)start conditions 



There are two problems with sched_server_write_common() that can cause the
dl_server to malfunction upon attempting to change the parameters:

1) when, after having disabled the dl_server by setting runtime=0, it is
   enabled again while tasks are already enqueued. In this case is_active would
   still be 0 and dl_server_start() would not be called.

2) when dl_server_apply_params() would fail, runtime is not applied and does
   not reflect the new state.

Instead have dl_server_start() check its actual dl_runtime, and have
sched_server_write_common() unconditionally (re)start the dl_server. It will
automatically stop if there isn't anything to do, so spurious activation is
harmless -- while failing to start it is a problem.

While there, move the printk out of the locked region and make it symmetric,
also printing on enable.

Signed-off-by: default avatarPeter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20260203103407.GK1282955@noisy.programming.kicks-ass.net
parent 76d12132

kernel/sched/deadline.c

+2 −3
Original line number Diff line number Diff line
@@ -1799,7 +1799,7 @@ void dl_server_start(struct sched_dl_entity *dl_se) 
	struct rq *rq = dl_se->rq;



	dl_se->dl_defer_idle = 0;

	if (!dl_server(dl_se) || dl_se->dl_server_active)

	if (!dl_server(dl_se) || dl_se->dl_server_active || !dl_se->dl_runtime)

		return;



	/*
@@ -1898,7 +1898,6 @@ int dl_server_apply_params(struct sched_dl_entity *dl_se, u64 runtime, u64 perio 
	int cpu = cpu_of(rq);

	struct dl_bw *dl_b;

	unsigned long cap;

	int retval = 0;

	int cpus;



	dl_b = dl_bw_of(cpu);
@@ -1930,7 +1929,7 @@ int dl_server_apply_params(struct sched_dl_entity *dl_se, u64 runtime, u64 perio 
	dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);

	dl_se->dl_density = to_ratio(dl_se->dl_deadline, dl_se->dl_runtime);



	return retval;

	return 0;

}



/*

kernel/sched/debug.c

+14 −18
Original line number Diff line number Diff line
@@ -338,9 +338,9 @@ static ssize_t sched_server_write_common(struct file *filp, const char __user *u 
					 void *server)

{

	long cpu = (long) ((struct seq_file *) filp->private_data)->private;

	struct rq *rq = cpu_rq(cpu);

	struct sched_dl_entity *dl_se = (struct sched_dl_entity *)server;

	u64 runtime, period;

	u64 old_runtime, runtime, period;

	struct rq *rq = cpu_rq(cpu);

	int retval = 0;

	size_t err;

	u64 value;
@@ -350,9 +350,7 @@ static ssize_t sched_server_write_common(struct file *filp, const char __user *u 
		return err;



	scoped_guard (rq_lock_irqsave, rq) {

		bool is_active;



		runtime = dl_se->dl_runtime;

		old_runtime = runtime = dl_se->dl_runtime;

		period = dl_se->dl_period;



		switch (param) {
@@ -374,25 +372,23 @@ static ssize_t sched_server_write_common(struct file *filp, const char __user *u 
			return  -EINVAL;

		}



		is_active = dl_server_active(dl_se);

		if (is_active) {

		update_rq_clock(rq);

		dl_server_stop(dl_se);

		}



		retval = dl_server_apply_params(dl_se, runtime, period, 0);



		if (!runtime)

			printk_deferred("%s server disabled in CPU %d, system may crash due to starvation.\n",

					server == &rq->fair_server ? "Fair" : "Ext", cpu_of(rq));



		if (is_active && runtime)

		dl_server_start(dl_se);



		if (retval < 0)

			return retval;

	}



	if (!!old_runtime ^ !!runtime) {

		pr_info("%s server %sabled on CPU %d%s.\n",

			server == &rq->fair_server ? "Fair" : "Ext",

			runtime ? "en" : "dis",

			cpu_of(rq),

			runtime ? "" : ", system may malfunction due to starvation");

	}



	*ppos += cnt;

	return cnt;

}