From 9044855f697bfa1e51d0f784a8276560a5460185 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 21 Apr 2020 12:09:13 +0200 Subject: [PATCH] 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 Change-Id: I52ed4f1253e82ba3e8f40f3aa1aff62580163f25 Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Ingo Molnar Tested-by: Paul E. McKenney --- include/linux/sched.h | 3 +++ kernel/sched/core.c | 47 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 50 insertions(+) diff --git a/include/linux/sched.h b/include/linux/sched.h index 74fe1d4e0807..9fb6635f0bcd 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1814,6 +1814,9 @@ 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); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f45a1020fcd0..30930250bcca 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5337,6 +5337,8 @@ static int _sched_setscheduler(struct task_struct *p, int policy, * @policy: new policy. * @param: structure containing the new RT priority. * + * Use sched_set_fifo(), read its comment. + * * Return: 0 on success. An error code otherwise. * * NOTE that the task may be already dead. @@ -5380,6 +5382,51 @@ int sched_setscheduler_nocheck(struct task_struct *p, int policy, } EXPORT_SYMBOL_GPL(sched_setscheduler_nocheck); +/* + * SCHED_FIFO is a broken scheduler model; that is, it is fundamentally + * incapable of resource management, which is the one thing an OS really should + * be doing. + * + * This is of course the reason it is limited to privileged users only. + * + * Worse still; it is fundamentally impossible to compose static priority + * workloads. You cannot take two correctly working static prio workloads + * and smash them together and still expect them to work. + * + * For this reason 'all' FIFO tasks the kernel creates are basically at: + * + * MAX_RT_PRIO / 2 + * + * 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) +{ + struct sched_param sp = { .sched_priority = MAX_RT_PRIO / 2 }; + return sched_setscheduler_nocheck(p, SCHED_FIFO, &sp); +} +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) +{ + struct sched_param sp = { .sched_priority = 1 }; + return sched_setscheduler_nocheck(p, SCHED_FIFO, &sp); +} +EXPORT_SYMBOL_GPL(sched_set_fifo_low); + +int 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); +} +EXPORT_SYMBOL_GPL(sched_set_normal); + static int do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) {