Merge tag 'sched-fifo-2020-08-04' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull sched/fifo updates from Ingo Molnar:
 "This adds the sched_set_fifo*() encapsulation APIs to remove static
  priority level knowledge from non-scheduler code.

  The three APIs for non-scheduler code to set SCHED_FIFO are:

   - sched_set_fifo()
   - sched_set_fifo_low()
   - sched_set_normal()

  These are two FIFO priority levels: default (high), and a 'low'
  priority level, plus sched_set_normal() to set the policy back to
  non-SCHED_FIFO.

  Since the changes affect a lot of non-scheduler code, we kept this in
  a separate tree"

* tag 'sched-fifo-2020-08-04' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (24 commits)
  sched,tracing: Convert to sched_set_fifo()
  sched: Remove sched_set_*() return value
  sched: Remove sched_setscheduler*() EXPORTs
  sched,psi: Convert to sched_set_fifo_low()
  sched,rcutorture: Convert to sched_set_fifo_low()
  sched,rcuperf: Convert to sched_set_fifo_low()
  sched,locktorture: Convert to sched_set_fifo()
  sched,irq: Convert to sched_set_fifo()
  sched,watchdog: Convert to sched_set_fifo()
  sched,serial: Convert to sched_set_fifo()
  sched,powerclamp: Convert to sched_set_fifo()
  sched,ion: Convert to sched_set_normal()
  sched,powercap: Convert to sched_set_fifo*()
  sched,spi: Convert to sched_set_fifo*()
  sched,mmc: Convert to sched_set_fifo*()
  sched,ivtv: Convert to sched_set_fifo*()
  sched,drm/scheduler: Convert to sched_set_fifo*()
  sched,msm: Convert to sched_set_fifo*()
  sched,psci: Convert to sched_set_fifo*()
  sched,drbd: Convert to sched_set_fifo*()
  ...

2 files changed, 48 insertions, 7 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4a0e7b449b88..84758f34cdb0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5496,6 +5496,8 @@ 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.
@@ -5505,13 +5507,11 @@ int sched_setscheduler(struct task_struct *p, int policy,
 {
 	return _sched_setscheduler(p, policy, param, true);
 }
-EXPORT_SYMBOL_GPL(sched_setscheduler);
 
 int sched_setattr(struct task_struct *p, const struct sched_attr *attr)
 {
 	return __sched_setscheduler(p, attr, true, true);
 }
-EXPORT_SYMBOL_GPL(sched_setattr);
 
 int sched_setattr_nocheck(struct task_struct *p, const struct sched_attr *attr)
 {
@@ -5536,7 +5536,51 @@ int sched_setscheduler_nocheck(struct task_struct *p, int policy,
 {
 	return _sched_setscheduler(p, policy, param, false);
 }
-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.
+ */
+void sched_set_fifo(struct task_struct *p)
+{
+	struct sched_param sp = { .sched_priority = MAX_RT_PRIO / 2 };
+	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.
+ */
+void sched_set_fifo_low(struct task_struct *p)
+{
+	struct sched_param sp = { .sched_priority = 1 };
+	WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0);
+}
+EXPORT_SYMBOL_GPL(sched_set_fifo_low);
+
+void sched_set_normal(struct task_struct *p, int nice)
+{
+	struct sched_attr attr = {
+		.sched_policy = SCHED_NORMAL,
+		.sched_nice = nice,
+	};
+	WARN_ON_ONCE(sched_setattr_nocheck(p, &attr) != 0);
+}
+EXPORT_SYMBOL_GPL(sched_set_normal);
 
 static int
 do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index e53b711bd643..967732c0766c 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -616,11 +616,8 @@ out:
 static int psi_poll_worker(void *data)
 {
 	struct psi_group *group = (struct psi_group *)data;
-	struct sched_param param = {
-		.sched_priority = 1,
-	};
 
-	sched_setscheduler_nocheck(current, SCHED_FIFO, &param);
+	sched_set_fifo_low(current);
 
 	while (true) {
 		wait_event_interruptible(group->poll_wait,