[GIT pull] scheduler fixes for 4.17

[GIT pull] scheduler fixes for 4.17

[Thomas Gleixner]

Linus,

please pull the latest sched-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched-urgent-for-linus

Three fixes for scheduler and kthread code:

 - Allow calling kthread_park() on an already parked thread

 - Restore the sched_pi_setprio() tracepoint behaviour

 - Clarify the unclear string for the scheduling domain debug output

Thanks,

	tglx

------------------>
Juri Lelli (1):
      sched/topology: Clarify root domain(s) debug string

Peter Zijlstra (1):
      kthread: Allow kthread_park() on a parked kthread

Sebastian Andrzej Siewior (1):
      sched, tracing: Fix trace_sched_pi_setprio() for deboosting


 include/trace/events/sched.h | 4 +++-
 kernel/kthread.c             | 6 ++----
 kernel/sched/topology.c      | 2 +-
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index bc01e06bc716..0be866c91f62 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -435,7 +435,9 @@ TRACE_EVENT(sched_pi_setprio,
 		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
 		__entry->pid		= tsk->pid;
 		__entry->oldprio	= tsk->prio;
-		__entry->newprio	= pi_task ? pi_task->prio : tsk->prio;
+		__entry->newprio	= pi_task ?
+				min(tsk->normal_prio, pi_task->prio) :
+				tsk->normal_prio;
 		/* XXX SCHED_DEADLINE bits missing */
 	),
 
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 2017a39ab490..481951bf091d 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -193,7 +193,7 @@ EXPORT_SYMBOL_GPL(kthread_parkme);
 
 void kthread_park_complete(struct task_struct *k)
 {
-	complete(&to_kthread(k)->parked);
+	complete_all(&to_kthread(k)->parked);
 }
 
 static int kthread(void *_create)
@@ -459,6 +459,7 @@ void kthread_unpark(struct task_struct *k)
 	if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
 		__kthread_bind(k, kthread->cpu, TASK_PARKED);
 
+	reinit_completion(&kthread->parked);
 	clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
 	wake_up_state(k, TASK_PARKED);
 }
@@ -483,9 +484,6 @@ int kthread_park(struct task_struct *k)
 	if (WARN_ON(k->flags & PF_EXITING))
 		return -ENOSYS;
 
-	if (WARN_ON_ONCE(test_bit(KTHREAD_SHOULD_PARK, &kthread->flags)))
-		return -EBUSY;
-
 	set_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
 	if (k != current) {
 		wake_up_process(k);
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 64cc564f5255..61a1125c1ae4 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1708,7 +1708,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 	rcu_read_unlock();
 
 	if (rq && sched_debug_enabled) {
-		pr_info("span: %*pbl (max cpu_capacity = %lu)\n",
+		pr_info("root domain span: %*pbl (max cpu_capacity = %lu)\n",
 			cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity);
 	}
 

[GIT pull] scheduler fixes for 4.17

[Thomas Gleixner]

Linus,

please pull the latest sched-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched-urgent-for-linus

A set of scheduler fixes:

 - Two patches addressing the problem that the scheduler allows under
   certain conditions user space tasks to be scheduled on CPUs which are
   not yet fully booted which causes a few subtle and hard to debug issue.

 - Add a missing runqueue clock update in the deadline scheduler which
   triggers a warning under certain circumstances.

 - Fix a silly typo in the scheduler header file.

Thanks,

	tglx

------------------>
Davidlohr Bueso (1):
      sched/headers: Fix typo

Juri Lelli (1):
      sched/deadline: Fix missing clock update

Paul Burton (1):
      sched/core: Require cpu_active() in select_task_rq(), for user tasks

Peter Zijlstra (1):
      sched/core: Fix rules for running on online && !active CPUs


 kernel/sched/core.c     | 45 +++++++++++++++++++++++++++++++--------------
 kernel/sched/deadline.c |  6 +++---
 kernel/sched/sched.h    |  2 +-
 3 files changed, 35 insertions(+), 18 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 092f7c4de903..211890edf37e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -881,6 +881,33 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 }
 
 #ifdef CONFIG_SMP
+
+static inline bool is_per_cpu_kthread(struct task_struct *p)
+{
+	if (!(p->flags & PF_KTHREAD))
+		return false;
+
+	if (p->nr_cpus_allowed != 1)
+		return false;
+
+	return true;
+}
+
+/*
+ * Per-CPU kthreads are allowed to run on !actie && online CPUs, see
+ * __set_cpus_allowed_ptr() and select_fallback_rq().
+ */
+static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
+{
+	if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
+		return false;
+
+	if (is_per_cpu_kthread(p))
+		return cpu_online(cpu);
+
+	return cpu_active(cpu);
+}
+
 /*
  * This is how migration works:
  *
@@ -938,16 +965,8 @@ struct migration_arg {
 static struct rq *__migrate_task(struct rq *rq, struct rq_flags *rf,
 				 struct task_struct *p, int dest_cpu)
 {
-	if (p->flags & PF_KTHREAD) {
-		if (unlikely(!cpu_online(dest_cpu)))
-			return rq;
-	} else {
-		if (unlikely(!cpu_active(dest_cpu)))
-			return rq;
-	}
-
 	/* Affinity changed (again). */
-	if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
+	if (!is_cpu_allowed(p, dest_cpu))
 		return rq;
 
 	update_rq_clock(rq);
@@ -1476,10 +1495,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 	for (;;) {
 		/* Any allowed, online CPU? */
 		for_each_cpu(dest_cpu, &p->cpus_allowed) {
-			if (!(p->flags & PF_KTHREAD) && !cpu_active(dest_cpu))
-				continue;
-			if (!cpu_online(dest_cpu))
+			if (!is_cpu_allowed(p, dest_cpu))
 				continue;
+
 			goto out;
 		}
 
@@ -1542,8 +1560,7 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
 	 * [ this allows ->select_task() to simply return task_cpu(p) and
 	 *   not worry about this generic constraint ]
 	 */
-	if (unlikely(!cpumask_test_cpu(cpu, &p->cpus_allowed) ||
-		     !cpu_online(cpu)))
+	if (unlikely(!is_cpu_allowed(p, cpu)))
 		cpu = select_fallback_rq(task_cpu(p), p);
 
 	return cpu;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 1356afd1eeb6..fbfc3f1d368a 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1259,6 +1259,9 @@ static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer)
 
 	rq = task_rq_lock(p, &rf);
 
+	sched_clock_tick();
+	update_rq_clock(rq);
+
 	if (!dl_task(p) || p->state == TASK_DEAD) {
 		struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
 
@@ -1278,9 +1281,6 @@ static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer)
 	if (dl_se->dl_non_contending == 0)
 		goto unlock;
 
-	sched_clock_tick();
-	update_rq_clock(rq);
-
 	sub_running_bw(dl_se, &rq->dl);
 	dl_se->dl_non_contending = 0;
 unlock:
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 1f0a4bc6a39d..cb467c221b15 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -983,7 +983,7 @@ static inline void rq_clock_skip_update(struct rq *rq)
 }
 
 /*
- * See rt task throttoling, which is the only time a skip
+ * See rt task throttling, which is the only time a skip
  * request is cancelled.
  */
 static inline void rq_clock_cancel_skipupdate(struct rq *rq)

[GIT pull] scheduler fixes for 4.17

[Thomas Gleixner]

Linus,

please pull the latest sched-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched-urgent-for-linus

Three trivial fixlets for the scheduler:

 - Move print_rt_rq() and print_dl_rq() declarations to the right place

 - Make grub_reclaim() static

 - Fix the bogus documentation reference in Kconfig

Thanks,

	tglx

------------------>
Mathieu Malaterre (2):
      sched/debug: Move the print_rt_rq() and print_dl_rq() declarations to kernel/sched/sched.h
      sched/deadline: Make the grub_reclaim() function static

Sebastian Andrzej Siewior (1):
      sched/fair: Fix documentation file path


 init/Kconfig            | 2 +-
 kernel/sched/deadline.c | 4 +---
 kernel/sched/rt.c       | 2 --
 kernel/sched/sched.h    | 5 +++--
 4 files changed, 5 insertions(+), 8 deletions(-)

diff --git a/init/Kconfig b/init/Kconfig
index f013afc74b11..18b151f0ddc1 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -738,7 +738,7 @@ config CFS_BANDWIDTH
 	  tasks running within the fair group scheduler.  Groups with no limit
 	  set are considered to be unconstrained and will run with no
 	  restriction.
-	  See tip/Documentation/scheduler/sched-bwc.txt for more information.
+	  See Documentation/scheduler/sched-bwc.txt for more information.
 
 config RT_GROUP_SCHED
 	bool "Group scheduling for SCHED_RR/FIFO"
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index e7b3008b85bb..1356afd1eeb6 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1117,7 +1117,7 @@ extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
  * should be larger than 2^(64 - 20 - 8), which is more than 64 seconds.
  * So, overflow is not an issue here.
  */
-u64 grub_reclaim(u64 delta, struct rq *rq, struct sched_dl_entity *dl_se)
+static u64 grub_reclaim(u64 delta, struct rq *rq, struct sched_dl_entity *dl_se)
 {
 	u64 u_inact = rq->dl.this_bw - rq->dl.running_bw; /* Utot - Uact */
 	u64 u_act;
@@ -2731,8 +2731,6 @@ bool dl_cpu_busy(unsigned int cpu)
 #endif
 
 #ifdef CONFIG_SCHED_DEBUG
-extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq);
-
 void print_dl_stats(struct seq_file *m, int cpu)
 {
 	print_dl_rq(m, cpu, &cpu_rq(cpu)->dl);
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 7aef6b4e885a..ef3c4e6f5345 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2701,8 +2701,6 @@ int sched_rr_handler(struct ctl_table *table, int write,
 }
 
 #ifdef CONFIG_SCHED_DEBUG
-extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq);
-
 void print_rt_stats(struct seq_file *m, int cpu)
 {
 	rt_rq_iter_t iter;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 15750c222ca2..1f0a4bc6a39d 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2025,8 +2025,9 @@ extern bool sched_debug_enabled;
 extern void print_cfs_stats(struct seq_file *m, int cpu);
 extern void print_rt_stats(struct seq_file *m, int cpu);
 extern void print_dl_stats(struct seq_file *m, int cpu);
-extern void
-print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
+extern void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
+extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq);
+extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq);
 #ifdef CONFIG_NUMA_BALANCING
 extern void
 show_numa_stats(struct task_struct *p, struct seq_file *m);