From 7318d4cc14c8c8a5dde2b0b72ea50fd2545f0b7a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 21 Apr 2020 12:09:13 +0200 Subject: sched: Provide sched_set_fifo() SCHED_FIFO (or any static priority scheduler) is a broken scheduler model; it is fundamentally incapable of resource management, the one thing an OS is actually supposed to do. It is impossible to compose static priority workloads. One cannot take two well designed and functional static priority workloads and mash them together and still expect them to work. Therefore it doesn't make sense to expose the priority field; the kernel is fundamentally incapable of setting a sensible value, it needs systems knowledge that it doesn't have. Take away sched_setschedule() / sched_setattr() from modules and replace them with: - sched_set_fifo(p); create a FIFO task (at prio 50) - sched_set_fifo_low(p); create a task higher than NORMAL, which ends up being a FIFO task at prio 1. - sched_set_normal(p, nice); (re)set the task to normal This stops the proliferation of randomly chosen, and irrelevant, FIFO priorities that dont't really mean anything anyway. The system administrator/integrator, whoever has insight into the actual system design and requirements (userspace) can set-up appropriate priorities if and when needed. Cc: airlied@redhat.com Cc: alexander.deucher@amd.com Cc: awalls@md.metrocast.net Cc: axboe@kernel.dk Cc: broonie@kernel.org Cc: daniel.lezcano@linaro.org Cc: gregkh@linuxfoundation.org Cc: hannes@cmpxchg.org Cc: herbert@gondor.apana.org.au Cc: hverkuil@xs4all.nl Cc: john.stultz@linaro.org Cc: nico@fluxnic.net Cc: paulmck@kernel.org Cc: rafael.j.wysocki@intel.com Cc: rmk+kernel@arm.linux.org.uk Cc: sudeep.holla@arm.com Cc: tglx@linutronix.de Cc: ulf.hansson@linaro.org Cc: wim@linux-watchdog.org Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Ingo Molnar Tested-by: Paul E. McKenney --- include/linux/sched.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index b62e6aaf28f0..b792b8f0f4cf 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1653,6 +1653,9 @@ extern int idle_cpu(int cpu); extern int available_idle_cpu(int cpu); extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *); extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *); +extern int sched_set_fifo(struct task_struct *p); +extern int sched_set_fifo_low(struct task_struct *p); +extern int sched_set_normal(struct task_struct *p, int nice); extern int sched_setattr(struct task_struct *, const struct sched_attr *); extern int sched_setattr_nocheck(struct task_struct *, const struct sched_attr *); extern struct task_struct *idle_task(int cpu); -- cgit From 8b700983de82f79e05b2c1136d6513ea4c9b22c4 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 22 Apr 2020 13:10:04 +0200 Subject: sched: Remove sched_set_*() return value Ingo suggested that since the new sched_set_*() functions are implemented using the 'nocheck' variants, they really shouldn't ever fail, so remove the return value. Cc: axboe@kernel.dk Cc: daniel.lezcano@linaro.org Cc: sudeep.holla@arm.com Cc: airlied@redhat.com Cc: broonie@kernel.org Cc: paulmck@kernel.org Suggested-by: Ingo Molnar Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Ingo Molnar --- drivers/block/drbd/drbd_receiver.c | 4 +--- drivers/firmware/psci/psci_checker.c | 3 +-- drivers/gpu/drm/msm/msm_drv.c | 5 +---- drivers/platform/chrome/cros_ec_spi.c | 7 +++---- include/linux/sched.h | 6 +++--- kernel/rcu/rcutorture.c | 5 +---- kernel/sched/core.c | 12 ++++++------ 7 files changed, 16 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 140fd98274b1..280615efef74 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -6020,9 +6020,7 @@ int drbd_ack_receiver(struct drbd_thread *thi) int expect = header_size; bool ping_timeout_active = false; - rv = sched_set_fifo_low(current); - if (rv < 0) - drbd_err(connection, "drbd_ack_receiver: ERROR set priority, ret=%d\n", rv); + sched_set_fifo_low(current); while (get_t_state(thi) == RUNNING) { drbd_thread_current_set_cpu(thi); diff --git a/drivers/firmware/psci/psci_checker.c b/drivers/firmware/psci/psci_checker.c index a5279a430274..6fff482847e7 100644 --- a/drivers/firmware/psci/psci_checker.c +++ b/drivers/firmware/psci/psci_checker.c @@ -281,8 +281,7 @@ static int suspend_test_thread(void *arg) wait_for_completion(&suspend_threads_started); /* Set maximum priority to preempt all other threads on this CPU. */ - if (sched_set_fifo(current)) - pr_warn("Failed to set suspend thread scheduler on CPU %d\n", cpu); + sched_set_fifo(current); dev = this_cpu_read(cpuidle_devices); drv = cpuidle_get_cpu_driver(dev); diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 89a8b9c7e044..556cca38487c 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -509,10 +509,7 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv) goto err_msm_uninit; } - ret = sched_set_fifo(priv->event_thread[i].thread); - if (ret) - dev_warn(dev, "event_thread set priority failed:%d\n", - ret); + sched_set_fifo(priv->event_thread[i].thread); } ret = drm_vblank_init(ddev, priv->num_crtcs); diff --git a/drivers/platform/chrome/cros_ec_spi.c b/drivers/platform/chrome/cros_ec_spi.c index c20a43a97040..d09260382550 100644 --- a/drivers/platform/chrome/cros_ec_spi.c +++ b/drivers/platform/chrome/cros_ec_spi.c @@ -725,10 +725,9 @@ static int cros_ec_spi_devm_high_pri_alloc(struct device *dev, if (err) return err; - err = sched_set_fifo(ec_spi->high_pri_worker->task); - if (err) - dev_err(dev, "Can't set cros_ec high pri priority: %d\n", err); - return err; + sched_set_fifo(ec_spi->high_pri_worker->task); + + return 0; } static int cros_ec_spi_probe(struct spi_device *spi) diff --git a/include/linux/sched.h b/include/linux/sched.h index b792b8f0f4cf..ae7664492af2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1653,9 +1653,9 @@ extern int idle_cpu(int cpu); extern int available_idle_cpu(int cpu); extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *); extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *); -extern int sched_set_fifo(struct task_struct *p); -extern int sched_set_fifo_low(struct task_struct *p); -extern int sched_set_normal(struct task_struct *p, int nice); +extern void sched_set_fifo(struct task_struct *p); +extern void sched_set_fifo_low(struct task_struct *p); +extern void sched_set_normal(struct task_struct *p, int nice); extern int sched_setattr(struct task_struct *, const struct sched_attr *); extern int sched_setattr_nocheck(struct task_struct *, const struct sched_attr *); extern struct task_struct *idle_task(int cpu); diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index bbc3c8a9e7b9..b4c1146de414 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -893,10 +893,7 @@ static int rcu_torture_boost(void *arg) VERBOSE_TOROUT_STRING("rcu_torture_boost started"); /* Set real-time priority. */ - if (sched_set_fifo_low(current) < 0) { - VERBOSE_TOROUT_STRING("rcu_torture_boost RT prio failed!"); - n_rcu_torture_boost_rterror++; - } + sched_set_fifo_low(current); init_rcu_head_on_stack(&rbi.rcu); /* Each pass through the following loop does one boost-test cycle. */ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f882d3d74dad..41d3778ea80e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5183,30 +5183,30 @@ int sched_setscheduler_nocheck(struct task_struct *p, int policy, * The administrator _MUST_ configure the system, the kernel simply doesn't * know enough information to make a sensible choice. */ -int sched_set_fifo(struct task_struct *p) +void sched_set_fifo(struct task_struct *p) { struct sched_param sp = { .sched_priority = MAX_RT_PRIO / 2 }; - return sched_setscheduler_nocheck(p, SCHED_FIFO, &sp); + WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0); } EXPORT_SYMBOL_GPL(sched_set_fifo); /* * For when you don't much care about FIFO, but want to be above SCHED_NORMAL. */ -int sched_set_fifo_low(struct task_struct *p) +void sched_set_fifo_low(struct task_struct *p) { struct sched_param sp = { .sched_priority = 1 }; - return sched_setscheduler_nocheck(p, SCHED_FIFO, &sp); + WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0); } EXPORT_SYMBOL_GPL(sched_set_fifo_low); -int sched_set_normal(struct task_struct *p, int nice) +void sched_set_normal(struct task_struct *p, int nice) { struct sched_attr attr = { .sched_policy = SCHED_NORMAL, .sched_nice = nice, }; - return sched_setattr_nocheck(p, &attr); + WARN_ON_ONCE(sched_setattr_nocheck(p, &attr) != 0); } EXPORT_SYMBOL_GPL(sched_set_normal); -- cgit