[PATCH 0/4] some scheduler code movements and small cleanup

[PATCH 0/4] some scheduler code movements and small cleanup

[Nicolas Pitre]

On Tue, 13 Jun 2017, Ingo Molnar wrote:

> So I'm fine with most of the code movement - let's try this series
> without any of the more controversial bits which should make future
> arguments easier.

Here it is. Big diffstat due to code movement which should untangle
scheduler classes from common code some more, and isolating PI futex
support, with the net effect of reducing the common code file size.

Sidenote: I just discovered that the default git diff algorithm produces
awful results with this series at least, with 1270 extra diff lines
compared to the output from the patience or minimal diff algorithms.
Using --diff-algorithm=minimal produces a much saner diffstat, way more
representative of the actual changes in this case.


 include/linux/futex.h   |    7 +-
 init/Kconfig            |    8 +-
 kernel/futex.c          | 1559 +---------------------------------------
 kernel/futex_pi.c       | 1563 +++++++++++++++++++++++++++++++++++++++++
 kernel/sched/core.c     |  655 +----------------
 kernel/sched/deadline.c |  336 +++++++++
 kernel/sched/rt.c       |  310 ++++++++
 kernel/sched/sched.h    |   19 +
 8 files changed, 2272 insertions(+), 2185 deletions(-)

[PATCH 1/4] cpuset/sched: cpuset makes sense for SMP only

[Nicolas Pitre]

Make CONFIG_CPUSETS depend on SMP as this feature makes no sense
on UP. This allows for configuring out cpuset_cpumask_can_shrink()
and task_can_attach() entirely.

Signed-off-by: Nicolas Pitre <nico@linaro.org>
---
 init/Kconfig        | 1 +
 kernel/sched/core.c | 7 +++----
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/init/Kconfig b/init/Kconfig
index 4ef946b466..b9aed60cac 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1156,6 +1156,7 @@ config CGROUP_HUGETLB
 
 config CPUSETS
 	bool "Cpuset controller"
+	depends on SMP
 	help
 	  This option will let you create and manage CPUSETs which
 	  allow dynamically partitioning a system into sets of CPUs and
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2a2c9c4fb3..94fa712791 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5463,6 +5463,8 @@ void init_idle(struct task_struct *idle, int cpu)
 #endif
 }
 
+#ifdef CONFIG_SMP
+
 int cpuset_cpumask_can_shrink(const struct cpumask *cur,
 			      const struct cpumask *trial)
 {
@@ -5506,7 +5508,6 @@ int task_can_attach(struct task_struct *p,
 		goto out;
 	}
 
-#ifdef CONFIG_SMP
 	if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span,
 					      cs_cpus_allowed)) {
 		unsigned int dest_cpu = cpumask_any_and(cpu_active_mask,
@@ -5536,13 +5537,11 @@ int task_can_attach(struct task_struct *p,
 		rcu_read_unlock_sched();
 
 	}
-#endif
+
 out:
 	return ret;
 }
 
-#ifdef CONFIG_SMP
-
 bool sched_smp_initialized __read_mostly;
 
 #ifdef CONFIG_NUMA_BALANCING
-- 
2.9.4

[PATCH 2/4] sched/deadline: move dl related code out of sched/core.c

[Nicolas Pitre]

... to sched/deadline.c. This helps making sched/core.c smaller and
hopefully easier to understand and maintain.

Signed-off-by: Nicolas Pitre <nico@linaro.org>
---
 kernel/sched/core.c     | 335 +----------------------------------------------
 kernel/sched/deadline.c | 336 ++++++++++++++++++++++++++++++++++++++++++++++++
 kernel/sched/sched.h    |  14 ++
 3 files changed, 356 insertions(+), 329 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 94fa712791..93ce28ea34 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2148,23 +2148,6 @@ int wake_up_state(struct task_struct *p, unsigned int state)
 }
 
 /*
- * This function clears the sched_dl_entity static params.
- */
-void __dl_clear_params(struct task_struct *p)
-{
-	struct sched_dl_entity *dl_se = &p->dl;
-
-	dl_se->dl_runtime = 0;
-	dl_se->dl_deadline = 0;
-	dl_se->dl_period = 0;
-	dl_se->flags = 0;
-	dl_se->dl_bw = 0;
-
-	dl_se->dl_throttled = 0;
-	dl_se->dl_yielded = 0;
-}
-
-/*
  * Perform scheduler related setup for a newly forked process p.
  * p is forked by current.
  *
@@ -2443,90 +2426,6 @@ unsigned long to_ratio(u64 period, u64 runtime)
 	return div64_u64(runtime << 20, period);
 }
 
-#ifdef CONFIG_SMP
-inline struct dl_bw *dl_bw_of(int i)
-{
-	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
-			 "sched RCU must be held");
-	return &cpu_rq(i)->rd->dl_bw;
-}
-
-static inline int dl_bw_cpus(int i)
-{
-	struct root_domain *rd = cpu_rq(i)->rd;
-	int cpus = 0;
-
-	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
-			 "sched RCU must be held");
-	for_each_cpu_and(i, rd->span, cpu_active_mask)
-		cpus++;
-
-	return cpus;
-}
-#else
-inline struct dl_bw *dl_bw_of(int i)
-{
-	return &cpu_rq(i)->dl.dl_bw;
-}
-
-static inline int dl_bw_cpus(int i)
-{
-	return 1;
-}
-#endif
-
-/*
- * We must be sure that accepting a new task (or allowing changing the
- * parameters of an existing one) is consistent with the bandwidth
- * constraints. If yes, this function also accordingly updates the currently
- * allocated bandwidth to reflect the new situation.
- *
- * This function is called while holding p's rq->lock.
- *
- * XXX we should delay bw change until the task's 0-lag point, see
- * __setparam_dl().
- */
-static int dl_overflow(struct task_struct *p, int policy,
-		       const struct sched_attr *attr)
-{
-
-	struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
-	u64 period = attr->sched_period ?: attr->sched_deadline;
-	u64 runtime = attr->sched_runtime;
-	u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
-	int cpus, err = -1;
-
-	/* !deadline task may carry old deadline bandwidth */
-	if (new_bw == p->dl.dl_bw && task_has_dl_policy(p))
-		return 0;
-
-	/*
-	 * Either if a task, enters, leave, or stays -deadline but changes
-	 * its parameters, we may need to update accordingly the total
-	 * allocated bandwidth of the container.
-	 */
-	raw_spin_lock(&dl_b->lock);
-	cpus = dl_bw_cpus(task_cpu(p));
-	if (dl_policy(policy) && !task_has_dl_policy(p) &&
-	    !__dl_overflow(dl_b, cpus, 0, new_bw)) {
-		__dl_add(dl_b, new_bw);
-		err = 0;
-	} else if (dl_policy(policy) && task_has_dl_policy(p) &&
-		   !__dl_overflow(dl_b, cpus, p->dl.dl_bw, new_bw)) {
-		__dl_clear(dl_b, p->dl.dl_bw);
-		__dl_add(dl_b, new_bw);
-		err = 0;
-	} else if (!dl_policy(policy) && task_has_dl_policy(p)) {
-		__dl_clear(dl_b, p->dl.dl_bw);
-		err = 0;
-	}
-	raw_spin_unlock(&dl_b->lock);
-
-	return err;
-}
-
-extern void init_dl_bw(struct dl_bw *dl_b);
-
 /*
  * wake_up_new_task - wake up a newly created task for the first time.
  *
@@ -4009,46 +3908,6 @@ static struct task_struct *find_process_by_pid(pid_t pid)
 }
 
 /*
- * This function initializes the sched_dl_entity of a newly becoming
- * SCHED_DEADLINE task.
- *
- * Only the static values are considered here, the actual runtime and the
- * absolute deadline will be properly calculated when the task is enqueued
- * for the first time with its new policy.
- */
-static void
-__setparam_dl(struct task_struct *p, const struct sched_attr *attr)
-{
-	struct sched_dl_entity *dl_se = &p->dl;
-
-	dl_se->dl_runtime = attr->sched_runtime;
-	dl_se->dl_deadline = attr->sched_deadline;
-	dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline;
-	dl_se->flags = attr->sched_flags;
-	dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
-
-	/*
-	 * Changing the parameters of a task is 'tricky' and we're not doing
-	 * the correct thing -- also see task_dead_dl() and switched_from_dl().
-	 *
-	 * What we SHOULD do is delay the bandwidth release until the 0-lag
-	 * point. This would include retaining the task_struct until that time
-	 * and change dl_overflow() to not immediately decrement the current
-	 * amount.
-	 *
-	 * Instead we retain the current runtime/deadline and let the new
-	 * parameters take effect after the current reservation period lapses.
-	 * This is safe (albeit pessimistic) because the 0-lag point is always
-	 * before the current scheduling deadline.
-	 *
-	 * We can still have temporary overloads because we do not delay the
-	 * change in bandwidth until that time; so admission control is
-	 * not on the safe side. It does however guarantee tasks will never
-	 * consume more than promised.
-	 */
-}
-
-/*
  * sched_setparam() passes in -1 for its policy, to let the functions
  * it calls know not to change it.
  */
@@ -4101,59 +3960,6 @@ static void __setscheduler(struct rq *rq, struct task_struct *p,
 		p->sched_class = &fair_sched_class;
 }
 
-static void
-__getparam_dl(struct task_struct *p, struct sched_attr *attr)
-{
-	struct sched_dl_entity *dl_se = &p->dl;
-
-	attr->sched_priority = p->rt_priority;
-	attr->sched_runtime = dl_se->dl_runtime;
-	attr->sched_deadline = dl_se->dl_deadline;
-	attr->sched_period = dl_se->dl_period;
-	attr->sched_flags = dl_se->flags;
-}
-
-/*
- * This function validates the new parameters of a -deadline task.
- * We ask for the deadline not being zero, and greater or equal
- * than the runtime, as well as the period of being zero or
- * greater than deadline. Furthermore, we have to be sure that
- * user parameters are above the internal resolution of 1us (we
- * check sched_runtime only since it is always the smaller one) and
- * below 2^63 ns (we have to check both sched_deadline and
- * sched_period, as the latter can be zero).
- */
-static bool
-__checkparam_dl(const struct sched_attr *attr)
-{
-	/* deadline != 0 */
-	if (attr->sched_deadline == 0)
-		return false;
-
-	/*
-	 * Since we truncate DL_SCALE bits, make sure we're at least
-	 * that big.
-	 */
-	if (attr->sched_runtime < (1ULL << DL_SCALE))
-		return false;
-
-	/*
-	 * Since we use the MSB for wrap-around and sign issues, make
-	 * sure it's not set (mind that period can be equal to zero).
-	 */
-	if (attr->sched_deadline & (1ULL << 63) ||
-	    attr->sched_period & (1ULL << 63))
-		return false;
-
-	/* runtime <= deadline <= period (if period != 0) */
-	if ((attr->sched_period != 0 &&
-	     attr->sched_period < attr->sched_deadline) ||
-	    attr->sched_deadline < attr->sched_runtime)
-		return false;
-
-	return true;
-}
-
 /*
  * Check the target process has a UID that matches the current process's:
  */
@@ -4170,19 +3976,6 @@ static bool check_same_owner(struct task_struct *p)
 	return match;
 }
 
-static bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)
-{
-	struct sched_dl_entity *dl_se = &p->dl;
-
-	if (dl_se->dl_runtime != attr->sched_runtime ||
-		dl_se->dl_deadline != attr->sched_deadline ||
-		dl_se->dl_period != attr->sched_period ||
-		dl_se->flags != attr->sched_flags)
-		return true;
-
-	return false;
-}
-
 static int __sched_setscheduler(struct task_struct *p,
 				const struct sched_attr *attr,
 				bool user, bool pi)
@@ -4362,7 +4155,7 @@ static int __sched_setscheduler(struct task_struct *p,
 	 * of a SCHED_DEADLINE task) we need to check if enough bandwidth
 	 * is available.
 	 */
-	if ((dl_policy(policy) || dl_task(p)) && dl_overflow(p, policy, attr)) {
+	if ((dl_policy(policy) || dl_task(p)) && sched_dl_overflow(p, policy, attr)) {
 		task_rq_unlock(rq, p, &rf);
 		return -EBUSY;
 	}
@@ -5468,23 +5261,12 @@ void init_idle(struct task_struct *idle, int cpu)
 int cpuset_cpumask_can_shrink(const struct cpumask *cur,
 			      const struct cpumask *trial)
 {
-	int ret = 1, trial_cpus;
-	struct dl_bw *cur_dl_b;
-	unsigned long flags;
+	int ret = 1;
 
 	if (!cpumask_weight(cur))
 		return ret;
 
-	rcu_read_lock_sched();
-	cur_dl_b = dl_bw_of(cpumask_any(cur));
-	trial_cpus = cpumask_weight(trial);
-
-	raw_spin_lock_irqsave(&cur_dl_b->lock, flags);
-	if (cur_dl_b->bw != -1 &&
-	    cur_dl_b->bw * trial_cpus < cur_dl_b->total_bw)
-		ret = 0;
-	raw_spin_unlock_irqrestore(&cur_dl_b->lock, flags);
-	rcu_read_unlock_sched();
+	ret = dl_cpuset_cpumask_can_shrink(cur, trial);
 
 	return ret;
 }
@@ -5509,34 +5291,8 @@ int task_can_attach(struct task_struct *p,
 	}
 
 	if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span,
-					      cs_cpus_allowed)) {
-		unsigned int dest_cpu = cpumask_any_and(cpu_active_mask,
-							cs_cpus_allowed);
-		struct dl_bw *dl_b;
-		bool overflow;
-		int cpus;
-		unsigned long flags;
-
-		rcu_read_lock_sched();
-		dl_b = dl_bw_of(dest_cpu);
-		raw_spin_lock_irqsave(&dl_b->lock, flags);
-		cpus = dl_bw_cpus(dest_cpu);
-		overflow = __dl_overflow(dl_b, cpus, 0, p->dl.dl_bw);
-		if (overflow)
-			ret = -EBUSY;
-		else {
-			/*
-			 * We reserve space for this task in the destination
-			 * root_domain, as we can't fail after this point.
-			 * We will free resources in the source root_domain
-			 * later on (see set_cpus_allowed_dl()).
-			 */
-			__dl_add(dl_b, p->dl.dl_bw);
-		}
-		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
-		rcu_read_unlock_sched();
-
-	}
+					      cs_cpus_allowed))
+		ret = dl_task_can_attach(p, cs_cpus_allowed);
 
 out:
 	return ret;
@@ -5804,23 +5560,8 @@ static void cpuset_cpu_active(void)
 
 static int cpuset_cpu_inactive(unsigned int cpu)
 {
-	unsigned long flags;
-	struct dl_bw *dl_b;
-	bool overflow;
-	int cpus;
-
 	if (!cpuhp_tasks_frozen) {
-		rcu_read_lock_sched();
-		dl_b = dl_bw_of(cpu);
-
-		raw_spin_lock_irqsave(&dl_b->lock, flags);
-		cpus = dl_bw_cpus(cpu);
-		overflow = __dl_overflow(dl_b, cpus, 0, 0);
-		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
-
-		rcu_read_unlock_sched();
-
-		if (overflow)
+		if (dl_cpu_busy(cpu))
 			return -EBUSY;
 		cpuset_update_active_cpus();
 	} else {
@@ -6740,70 +6481,6 @@ static int sched_rt_global_constraints(void)
 }
 #endif /* CONFIG_RT_GROUP_SCHED */
 
-static int sched_dl_global_validate(void)
-{
-	u64 runtime = global_rt_runtime();
-	u64 period = global_rt_period();
-	u64 new_bw = to_ratio(period, runtime);
-	struct dl_bw *dl_b;
-	int cpu, ret = 0;
-	unsigned long flags;
-
-	/*
-	 * Here we want to check the bandwidth not being set to some
-	 * value smaller than the currently allocated bandwidth in
-	 * any of the root_domains.
-	 *
-	 * FIXME: Cycling on all the CPUs is overdoing, but simpler than
-	 * cycling on root_domains... Discussion on different/better
-	 * solutions is welcome!
-	 */
-	for_each_possible_cpu(cpu) {
-		rcu_read_lock_sched();
-		dl_b = dl_bw_of(cpu);
-
-		raw_spin_lock_irqsave(&dl_b->lock, flags);
-		if (new_bw < dl_b->total_bw)
-			ret = -EBUSY;
-		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
-
-		rcu_read_unlock_sched();
-
-		if (ret)
-			break;
-	}
-
-	return ret;
-}
-
-static void sched_dl_do_global(void)
-{
-	u64 new_bw = -1;
-	struct dl_bw *dl_b;
-	int cpu;
-	unsigned long flags;
-
-	def_dl_bandwidth.dl_period = global_rt_period();
-	def_dl_bandwidth.dl_runtime = global_rt_runtime();
-
-	if (global_rt_runtime() != RUNTIME_INF)
-		new_bw = to_ratio(global_rt_period(), global_rt_runtime());
-
-	/*
-	 * FIXME: As above...
-	 */
-	for_each_possible_cpu(cpu) {
-		rcu_read_lock_sched();
-		dl_b = dl_bw_of(cpu);
-
-		raw_spin_lock_irqsave(&dl_b->lock, flags);
-		dl_b->bw = new_bw;
-		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
-
-		rcu_read_unlock_sched();
-	}
-}
-
 static int sched_rt_global_validate(void)
 {
 	if (sysctl_sched_rt_period <= 0)
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index a2ce590156..e879feae5f 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -17,6 +17,7 @@
 #include "sched.h"
 
 #include <linux/slab.h>
+#include <uapi/linux/sched/types.h>
 
 struct dl_bandwidth def_dl_bandwidth;
 
@@ -1854,6 +1855,341 @@ const struct sched_class dl_sched_class = {
 	.update_curr		= update_curr_dl,
 };
 
+#ifdef CONFIG_SMP
+struct dl_bw *dl_bw_of(int i)
+{
+	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
+			 "sched RCU must be held");
+	return &cpu_rq(i)->rd->dl_bw;
+}
+
+static inline int dl_bw_cpus(int i)
+{
+	struct root_domain *rd = cpu_rq(i)->rd;
+	int cpus = 0;
+
+	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
+			 "sched RCU must be held");
+	for_each_cpu_and(i, rd->span, cpu_active_mask)
+		cpus++;
+
+	return cpus;
+}
+#else
+struct dl_bw *dl_bw_of(int i)
+{
+	return &cpu_rq(i)->dl.dl_bw;
+}
+
+static inline int dl_bw_cpus(int i)
+{
+	return 1;
+}
+#endif
+
+int sched_dl_global_validate(void)
+{
+	u64 runtime = global_rt_runtime();
+	u64 period = global_rt_period();
+	u64 new_bw = to_ratio(period, runtime);
+	struct dl_bw *dl_b;
+	int cpu, ret = 0;
+	unsigned long flags;
+
+	/*
+	 * Here we want to check the bandwidth not being set to some
+	 * value smaller than the currently allocated bandwidth in
+	 * any of the root_domains.
+	 *
+	 * FIXME: Cycling on all the CPUs is overdoing, but simpler than
+	 * cycling on root_domains... Discussion on different/better
+	 * solutions is welcome!
+	 */
+	for_each_possible_cpu(cpu) {
+		rcu_read_lock_sched();
+		dl_b = dl_bw_of(cpu);
+
+		raw_spin_lock_irqsave(&dl_b->lock, flags);
+		if (new_bw < dl_b->total_bw)
+			ret = -EBUSY;
+		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+
+		rcu_read_unlock_sched();
+
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+void sched_dl_do_global(void)
+{
+	u64 new_bw = -1;
+	struct dl_bw *dl_b;
+	int cpu;
+	unsigned long flags;
+
+	def_dl_bandwidth.dl_period = global_rt_period();
+	def_dl_bandwidth.dl_runtime = global_rt_runtime();
+
+	if (global_rt_runtime() != RUNTIME_INF)
+		new_bw = to_ratio(global_rt_period(), global_rt_runtime());
+
+	/*
+	 * FIXME: As above...
+	 */
+	for_each_possible_cpu(cpu) {
+		rcu_read_lock_sched();
+		dl_b = dl_bw_of(cpu);
+
+		raw_spin_lock_irqsave(&dl_b->lock, flags);
+		dl_b->bw = new_bw;
+		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+
+		rcu_read_unlock_sched();
+	}
+}
+
+/*
+ * We must be sure that accepting a new task (or allowing changing the
+ * parameters of an existing one) is consistent with the bandwidth
+ * constraints. If yes, this function also accordingly updates the currently
+ * allocated bandwidth to reflect the new situation.
+ *
+ * This function is called while holding p's rq->lock.
+ *
+ * XXX we should delay bw change until the task's 0-lag point, see
+ * __setparam_dl().
+ */
+int sched_dl_overflow(struct task_struct *p, int policy,
+		      const struct sched_attr *attr)
+{
+	struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+	u64 period = attr->sched_period ?: attr->sched_deadline;
+	u64 runtime = attr->sched_runtime;
+	u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
+	int cpus, err = -1;
+
+	/* !deadline task may carry old deadline bandwidth */
+	if (new_bw == p->dl.dl_bw && task_has_dl_policy(p))
+		return 0;
+
+	/*
+	 * Either if a task, enters, leave, or stays -deadline but changes
+	 * its parameters, we may need to update accordingly the total
+	 * allocated bandwidth of the container.
+	 */
+	raw_spin_lock(&dl_b->lock);
+	cpus = dl_bw_cpus(task_cpu(p));
+	if (dl_policy(policy) && !task_has_dl_policy(p) &&
+	    !__dl_overflow(dl_b, cpus, 0, new_bw)) {
+		__dl_add(dl_b, new_bw);
+		err = 0;
+	} else if (dl_policy(policy) && task_has_dl_policy(p) &&
+		   !__dl_overflow(dl_b, cpus, p->dl.dl_bw, new_bw)) {
+		__dl_clear(dl_b, p->dl.dl_bw);
+		__dl_add(dl_b, new_bw);
+		err = 0;
+	} else if (!dl_policy(policy) && task_has_dl_policy(p)) {
+		__dl_clear(dl_b, p->dl.dl_bw);
+		err = 0;
+	}
+	raw_spin_unlock(&dl_b->lock);
+
+	return err;
+}
+
+/*
+ * This function initializes the sched_dl_entity of a newly becoming
+ * SCHED_DEADLINE task.
+ *
+ * Only the static values are considered here, the actual runtime and the
+ * absolute deadline will be properly calculated when the task is enqueued
+ * for the first time with its new policy.
+ */
+void __setparam_dl(struct task_struct *p, const struct sched_attr *attr)
+{
+	struct sched_dl_entity *dl_se = &p->dl;
+
+	dl_se->dl_runtime = attr->sched_runtime;
+	dl_se->dl_deadline = attr->sched_deadline;
+	dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline;
+	dl_se->flags = attr->sched_flags;
+	dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
+
+	/*
+	 * Changing the parameters of a task is 'tricky' and we're not doing
+	 * the correct thing -- also see task_dead_dl() and switched_from_dl().
+	 *
+	 * What we SHOULD do is delay the bandwidth release until the 0-lag
+	 * point. This would include retaining the task_struct until that time
+	 * and change sched_dl_overflow() to not immediately decrement the
+	 * current amount.
+	 *
+	 * Instead we retain the current runtime/deadline and let the new
+	 * parameters take effect after the current reservation period lapses.
+	 * This is safe (albeit pessimistic) because the 0-lag point is always
+	 * before the current scheduling deadline.
+	 *
+	 * We can still have temporary overloads because we do not delay the
+	 * change in bandwidth until that time; so admission control is
+	 * not on the safe side. It does however guarantee tasks will never
+	 * consume more than promised.
+	 */
+}
+
+void __getparam_dl(struct task_struct *p, struct sched_attr *attr)
+{
+	struct sched_dl_entity *dl_se = &p->dl;
+
+	attr->sched_priority = p->rt_priority;
+	attr->sched_runtime = dl_se->dl_runtime;
+	attr->sched_deadline = dl_se->dl_deadline;
+	attr->sched_period = dl_se->dl_period;
+	attr->sched_flags = dl_se->flags;
+}
+
+/*
+ * This function validates the new parameters of a -deadline task.
+ * We ask for the deadline not being zero, and greater or equal
+ * than the runtime, as well as the period of being zero or
+ * greater than deadline. Furthermore, we have to be sure that
+ * user parameters are above the internal resolution of 1us (we
+ * check sched_runtime only since it is always the smaller one) and
+ * below 2^63 ns (we have to check both sched_deadline and
+ * sched_period, as the latter can be zero).
+ */
+bool __checkparam_dl(const struct sched_attr *attr)
+{
+	/* deadline != 0 */
+	if (attr->sched_deadline == 0)
+		return false;
+
+	/*
+	 * Since we truncate DL_SCALE bits, make sure we're at least
+	 * that big.
+	 */
+	if (attr->sched_runtime < (1ULL << DL_SCALE))
+		return false;
+
+	/*
+	 * Since we use the MSB for wrap-around and sign issues, make
+	 * sure it's not set (mind that period can be equal to zero).
+	 */
+	if (attr->sched_deadline & (1ULL << 63) ||
+	    attr->sched_period & (1ULL << 63))
+		return false;
+
+	/* runtime <= deadline <= period (if period != 0) */
+	if ((attr->sched_period != 0 &&
+	     attr->sched_period < attr->sched_deadline) ||
+	    attr->sched_deadline < attr->sched_runtime)
+		return false;
+
+	return true;
+}
+
+/*
+ * This function clears the sched_dl_entity static params.
+ */
+void __dl_clear_params(struct task_struct *p)
+{
+	struct sched_dl_entity *dl_se = &p->dl;
+
+	dl_se->dl_runtime = 0;
+	dl_se->dl_deadline = 0;
+	dl_se->dl_period = 0;
+	dl_se->flags = 0;
+	dl_se->dl_bw = 0;
+
+	dl_se->dl_throttled = 0;
+	dl_se->dl_yielded = 0;
+}
+
+bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)
+{
+	struct sched_dl_entity *dl_se = &p->dl;
+
+	if (dl_se->dl_runtime != attr->sched_runtime ||
+	    dl_se->dl_deadline != attr->sched_deadline ||
+	    dl_se->dl_period != attr->sched_period ||
+	    dl_se->flags != attr->sched_flags)
+		return true;
+
+	return false;
+}
+
+#ifdef CONFIG_SMP
+int dl_task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed)
+{
+	unsigned int dest_cpu = cpumask_any_and(cpu_active_mask,
+							cs_cpus_allowed);
+	struct dl_bw *dl_b;
+	bool overflow;
+	int cpus, ret;
+	unsigned long flags;
+
+	rcu_read_lock_sched();
+	dl_b = dl_bw_of(dest_cpu);
+	raw_spin_lock_irqsave(&dl_b->lock, flags);
+	cpus = dl_bw_cpus(dest_cpu);
+	overflow = __dl_overflow(dl_b, cpus, 0, p->dl.dl_bw);
+	if (overflow)
+		ret = -EBUSY;
+	else {
+		/*
+		 * We reserve space for this task in the destination
+		 * root_domain, as we can't fail after this point.
+		 * We will free resources in the source root_domain
+		 * later on (see set_cpus_allowed_dl()).
+		 */
+		__dl_add(dl_b, p->dl.dl_bw);
+		ret = 0;
+	}
+	raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+	rcu_read_unlock_sched();
+	return ret;
+}
+
+int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur,
+				 const struct cpumask *trial)
+{
+	int ret = 1, trial_cpus;
+	struct dl_bw *cur_dl_b;
+	unsigned long flags;
+
+	rcu_read_lock_sched();
+	cur_dl_b = dl_bw_of(cpumask_any(cur));
+	trial_cpus = cpumask_weight(trial);
+
+	raw_spin_lock_irqsave(&cur_dl_b->lock, flags);
+	if (cur_dl_b->bw != -1 &&
+	    cur_dl_b->bw * trial_cpus < cur_dl_b->total_bw)
+		ret = 0;
+	raw_spin_unlock_irqrestore(&cur_dl_b->lock, flags);
+	rcu_read_unlock_sched();
+	return ret;
+}
+
+bool dl_cpu_busy(unsigned int cpu)
+{
+	unsigned long flags;
+	struct dl_bw *dl_b;
+	bool overflow;
+	int cpus;
+
+	rcu_read_lock_sched();
+	dl_b = dl_bw_of(cpu);
+	raw_spin_lock_irqsave(&dl_b->lock, flags);
+	cpus = dl_bw_cpus(cpu);
+	overflow = __dl_overflow(dl_b, cpus, 0, 0);
+	raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+	rcu_read_unlock_sched();
+	return overflow;
+}
+#endif
+
 #ifdef CONFIG_SCHED_DEBUG
 extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq);
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 053f60afb7..4a845c19b8 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -245,6 +245,20 @@ bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw)
 }
 
 extern void init_dl_bw(struct dl_bw *dl_b);
+extern int sched_dl_global_validate(void);
+extern void sched_dl_do_global(void);
+extern int sched_dl_overflow(struct task_struct *p, int policy,
+			     const struct sched_attr *attr);
+extern void __setparam_dl(struct task_struct *p, const struct sched_attr *attr);
+extern void __getparam_dl(struct task_struct *p, struct sched_attr *attr);
+extern bool __checkparam_dl(const struct sched_attr *attr);
+extern void __dl_clear_params(struct task_struct *p);
+extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr);
+extern int dl_task_can_attach(struct task_struct *p,
+			      const struct cpumask *cs_cpus_allowed);
+extern int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur,
+					const struct cpumask *trial);
+extern bool dl_cpu_busy(unsigned int cpu);
 
 #ifdef CONFIG_CGROUP_SCHED
 
-- 
2.9.4

[PATCH 3/4] sched/rt: move rt related code out of sched/core.c

[Nicolas Pitre]

... to sched/rt.c. This helps making sched/core.c smaller and hopefully
easier to understand and maintain.

Signed-off-by: Nicolas Pitre <nico@linaro.org>
---
 kernel/sched/core.c  | 315 ---------------------------------------------------
 kernel/sched/rt.c    | 310 ++++++++++++++++++++++++++++++++++++++++++++++++++
 kernel/sched/sched.h |   5 +
 3 files changed, 315 insertions(+), 315 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 93ce28ea34..9923c4b742 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6247,321 +6247,6 @@ void sched_move_task(struct task_struct *tsk)
 
 	task_rq_unlock(rq, tsk, &rf);
 }
-#endif /* CONFIG_CGROUP_SCHED */
-
-#ifdef CONFIG_RT_GROUP_SCHED
-/*
- * Ensure that the real time constraints are schedulable.
- */
-static DEFINE_MUTEX(rt_constraints_mutex);
-
-/* Must be called with tasklist_lock held */
-static inline int tg_has_rt_tasks(struct task_group *tg)
-{
-	struct task_struct *g, *p;
-
-	/*
-	 * Autogroups do not have RT tasks; see autogroup_create().
-	 */
-	if (task_group_is_autogroup(tg))
-		return 0;
-
-	for_each_process_thread(g, p) {
-		if (rt_task(p) && task_group(p) == tg)
-			return 1;
-	}
-
-	return 0;
-}
-
-struct rt_schedulable_data {
-	struct task_group *tg;
-	u64 rt_period;
-	u64 rt_runtime;
-};
-
-static int tg_rt_schedulable(struct task_group *tg, void *data)
-{
-	struct rt_schedulable_data *d = data;
-	struct task_group *child;
-	unsigned long total, sum = 0;
-	u64 period, runtime;
-
-	period = ktime_to_ns(tg->rt_bandwidth.rt_period);
-	runtime = tg->rt_bandwidth.rt_runtime;
-
-	if (tg == d->tg) {
-		period = d->rt_period;
-		runtime = d->rt_runtime;
-	}
-
-	/*
-	 * Cannot have more runtime than the period.
-	 */
-	if (runtime > period && runtime != RUNTIME_INF)
-		return -EINVAL;
-
-	/*
-	 * Ensure we don't starve existing RT tasks.
-	 */
-	if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg))
-		return -EBUSY;
-
-	total = to_ratio(period, runtime);
-
-	/*
-	 * Nobody can have more than the global setting allows.
-	 */
-	if (total > to_ratio(global_rt_period(), global_rt_runtime()))
-		return -EINVAL;
-
-	/*
-	 * The sum of our children's runtime should not exceed our own.
-	 */
-	list_for_each_entry_rcu(child, &tg->children, siblings) {
-		period = ktime_to_ns(child->rt_bandwidth.rt_period);
-		runtime = child->rt_bandwidth.rt_runtime;
-
-		if (child == d->tg) {
-			period = d->rt_period;
-			runtime = d->rt_runtime;
-		}
-
-		sum += to_ratio(period, runtime);
-	}
-
-	if (sum > total)
-		return -EINVAL;
-
-	return 0;
-}
-
-static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
-{
-	int ret;
-
-	struct rt_schedulable_data data = {
-		.tg = tg,
-		.rt_period = period,
-		.rt_runtime = runtime,
-	};
-
-	rcu_read_lock();
-	ret = walk_tg_tree(tg_rt_schedulable, tg_nop, &data);
-	rcu_read_unlock();
-
-	return ret;
-}
-
-static int tg_set_rt_bandwidth(struct task_group *tg,
-		u64 rt_period, u64 rt_runtime)
-{
-	int i, err = 0;
-
-	/*
-	 * Disallowing the root group RT runtime is BAD, it would disallow the
-	 * kernel creating (and or operating) RT threads.
-	 */
-	if (tg == &root_task_group && rt_runtime == 0)
-		return -EINVAL;
-
-	/* No period doesn't make any sense. */
-	if (rt_period == 0)
-		return -EINVAL;
-
-	mutex_lock(&rt_constraints_mutex);
-	read_lock(&tasklist_lock);
-	err = __rt_schedulable(tg, rt_period, rt_runtime);
-	if (err)
-		goto unlock;
-
-	raw_spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock);
-	tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period);
-	tg->rt_bandwidth.rt_runtime = rt_runtime;
-
-	for_each_possible_cpu(i) {
-		struct rt_rq *rt_rq = tg->rt_rq[i];
-
-		raw_spin_lock(&rt_rq->rt_runtime_lock);
-		rt_rq->rt_runtime = rt_runtime;
-		raw_spin_unlock(&rt_rq->rt_runtime_lock);
-	}
-	raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
-unlock:
-	read_unlock(&tasklist_lock);
-	mutex_unlock(&rt_constraints_mutex);
-
-	return err;
-}
-
-static int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us)
-{
-	u64 rt_runtime, rt_period;
-
-	rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period);
-	rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC;
-	if (rt_runtime_us < 0)
-		rt_runtime = RUNTIME_INF;
-
-	return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
-}
-
-static long sched_group_rt_runtime(struct task_group *tg)
-{
-	u64 rt_runtime_us;
-
-	if (tg->rt_bandwidth.rt_runtime == RUNTIME_INF)
-		return -1;
-
-	rt_runtime_us = tg->rt_bandwidth.rt_runtime;
-	do_div(rt_runtime_us, NSEC_PER_USEC);
-	return rt_runtime_us;
-}
-
-static int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us)
-{
-	u64 rt_runtime, rt_period;
-
-	rt_period = rt_period_us * NSEC_PER_USEC;
-	rt_runtime = tg->rt_bandwidth.rt_runtime;
-
-	return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
-}
-
-static long sched_group_rt_period(struct task_group *tg)
-{
-	u64 rt_period_us;
-
-	rt_period_us = ktime_to_ns(tg->rt_bandwidth.rt_period);
-	do_div(rt_period_us, NSEC_PER_USEC);
-	return rt_period_us;
-}
-#endif /* CONFIG_RT_GROUP_SCHED */
-
-#ifdef CONFIG_RT_GROUP_SCHED
-static int sched_rt_global_constraints(void)
-{
-	int ret = 0;
-
-	mutex_lock(&rt_constraints_mutex);
-	read_lock(&tasklist_lock);
-	ret = __rt_schedulable(NULL, 0, 0);
-	read_unlock(&tasklist_lock);
-	mutex_unlock(&rt_constraints_mutex);
-
-	return ret;
-}
-
-static int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
-{
-	/* Don't accept realtime tasks when there is no way for them to run */
-	if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0)
-		return 0;
-
-	return 1;
-}
-
-#else /* !CONFIG_RT_GROUP_SCHED */
-static int sched_rt_global_constraints(void)
-{
-	unsigned long flags;
-	int i;
-
-	raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
-	for_each_possible_cpu(i) {
-		struct rt_rq *rt_rq = &cpu_rq(i)->rt;
-
-		raw_spin_lock(&rt_rq->rt_runtime_lock);
-		rt_rq->rt_runtime = global_rt_runtime();
-		raw_spin_unlock(&rt_rq->rt_runtime_lock);
-	}
-	raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
-
-	return 0;
-}
-#endif /* CONFIG_RT_GROUP_SCHED */
-
-static int sched_rt_global_validate(void)
-{
-	if (sysctl_sched_rt_period <= 0)
-		return -EINVAL;
-
-	if ((sysctl_sched_rt_runtime != RUNTIME_INF) &&
-		(sysctl_sched_rt_runtime > sysctl_sched_rt_period))
-		return -EINVAL;
-
-	return 0;
-}
-
-static void sched_rt_do_global(void)
-{
-	def_rt_bandwidth.rt_runtime = global_rt_runtime();
-	def_rt_bandwidth.rt_period = ns_to_ktime(global_rt_period());
-}
-
-int sched_rt_handler(struct ctl_table *table, int write,
-		void __user *buffer, size_t *lenp,
-		loff_t *ppos)
-{
-	int old_period, old_runtime;
-	static DEFINE_MUTEX(mutex);
-	int ret;
-
-	mutex_lock(&mutex);
-	old_period = sysctl_sched_rt_period;
-	old_runtime = sysctl_sched_rt_runtime;
-
-	ret = proc_dointvec(table, write, buffer, lenp, ppos);
-
-	if (!ret && write) {
-		ret = sched_rt_global_validate();
-		if (ret)
-			goto undo;
-
-		ret = sched_dl_global_validate();
-		if (ret)
-			goto undo;
-
-		ret = sched_rt_global_constraints();
-		if (ret)
-			goto undo;
-
-		sched_rt_do_global();
-		sched_dl_do_global();
-	}
-	if (0) {
-undo:
-		sysctl_sched_rt_period = old_period;
-		sysctl_sched_rt_runtime = old_runtime;
-	}
-	mutex_unlock(&mutex);
-
-	return ret;
-}
-
-int sched_rr_handler(struct ctl_table *table, int write,
-		void __user *buffer, size_t *lenp,
-		loff_t *ppos)
-{
-	int ret;
-	static DEFINE_MUTEX(mutex);
-
-	mutex_lock(&mutex);
-	ret = proc_dointvec(table, write, buffer, lenp, ppos);
-	/*
-	 * Make sure that internally we keep jiffies.
-	 * Also, writing zero resets the timeslice to default:
-	 */
-	if (!ret && write) {
-		sched_rr_timeslice =
-			sysctl_sched_rr_timeslice <= 0 ? RR_TIMESLICE :
-			msecs_to_jiffies(sysctl_sched_rr_timeslice);
-	}
-	mutex_unlock(&mutex);
-	return ret;
-}
-
-#ifdef CONFIG_CGROUP_SCHED
 
 static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
 {
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 979b734100..29c48a6cfb 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2438,6 +2438,316 @@ const struct sched_class rt_sched_class = {
 	.update_curr		= update_curr_rt,
 };
 
+#ifdef CONFIG_RT_GROUP_SCHED
+/*
+ * Ensure that the real time constraints are schedulable.
+ */
+static DEFINE_MUTEX(rt_constraints_mutex);
+
+/* Must be called with tasklist_lock held */
+static inline int tg_has_rt_tasks(struct task_group *tg)
+{
+	struct task_struct *g, *p;
+
+	/*
+	 * Autogroups do not have RT tasks; see autogroup_create().
+	 */
+	if (task_group_is_autogroup(tg))
+		return 0;
+
+	for_each_process_thread(g, p) {
+		if (rt_task(p) && task_group(p) == tg)
+			return 1;
+	}
+
+	return 0;
+}
+
+struct rt_schedulable_data {
+	struct task_group *tg;
+	u64 rt_period;
+	u64 rt_runtime;
+};
+
+static int tg_rt_schedulable(struct task_group *tg, void *data)
+{
+	struct rt_schedulable_data *d = data;
+	struct task_group *child;
+	unsigned long total, sum = 0;
+	u64 period, runtime;
+
+	period = ktime_to_ns(tg->rt_bandwidth.rt_period);
+	runtime = tg->rt_bandwidth.rt_runtime;
+
+	if (tg == d->tg) {
+		period = d->rt_period;
+		runtime = d->rt_runtime;
+	}
+
+	/*
+	 * Cannot have more runtime than the period.
+	 */
+	if (runtime > period && runtime != RUNTIME_INF)
+		return -EINVAL;
+
+	/*
+	 * Ensure we don't starve existing RT tasks.
+	 */
+	if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg))
+		return -EBUSY;
+
+	total = to_ratio(period, runtime);
+
+	/*
+	 * Nobody can have more than the global setting allows.
+	 */
+	if (total > to_ratio(global_rt_period(), global_rt_runtime()))
+		return -EINVAL;
+
+	/*
+	 * The sum of our children's runtime should not exceed our own.
+	 */
+	list_for_each_entry_rcu(child, &tg->children, siblings) {
+		period = ktime_to_ns(child->rt_bandwidth.rt_period);
+		runtime = child->rt_bandwidth.rt_runtime;
+
+		if (child == d->tg) {
+			period = d->rt_period;
+			runtime = d->rt_runtime;
+		}
+
+		sum += to_ratio(period, runtime);
+	}
+
+	if (sum > total)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
+{
+	int ret;
+
+	struct rt_schedulable_data data = {
+		.tg = tg,
+		.rt_period = period,
+		.rt_runtime = runtime,
+	};
+
+	rcu_read_lock();
+	ret = walk_tg_tree(tg_rt_schedulable, tg_nop, &data);
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static int tg_set_rt_bandwidth(struct task_group *tg,
+		u64 rt_period, u64 rt_runtime)
+{
+	int i, err = 0;
+
+	/*
+	 * Disallowing the root group RT runtime is BAD, it would disallow the
+	 * kernel creating (and or operating) RT threads.
+	 */
+	if (tg == &root_task_group && rt_runtime == 0)
+		return -EINVAL;
+
+	/* No period doesn't make any sense. */
+	if (rt_period == 0)
+		return -EINVAL;
+
+	mutex_lock(&rt_constraints_mutex);
+	read_lock(&tasklist_lock);
+	err = __rt_schedulable(tg, rt_period, rt_runtime);
+	if (err)
+		goto unlock;
+
+	raw_spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock);
+	tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period);
+	tg->rt_bandwidth.rt_runtime = rt_runtime;
+
+	for_each_possible_cpu(i) {
+		struct rt_rq *rt_rq = tg->rt_rq[i];
+
+		raw_spin_lock(&rt_rq->rt_runtime_lock);
+		rt_rq->rt_runtime = rt_runtime;
+		raw_spin_unlock(&rt_rq->rt_runtime_lock);
+	}
+	raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
+unlock:
+	read_unlock(&tasklist_lock);
+	mutex_unlock(&rt_constraints_mutex);
+
+	return err;
+}
+
+int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us)
+{
+	u64 rt_runtime, rt_period;
+
+	rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period);
+	rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC;
+	if (rt_runtime_us < 0)
+		rt_runtime = RUNTIME_INF;
+
+	return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
+}
+
+long sched_group_rt_runtime(struct task_group *tg)
+{
+	u64 rt_runtime_us;
+
+	if (tg->rt_bandwidth.rt_runtime == RUNTIME_INF)
+		return -1;
+
+	rt_runtime_us = tg->rt_bandwidth.rt_runtime;
+	do_div(rt_runtime_us, NSEC_PER_USEC);
+	return rt_runtime_us;
+}
+
+int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us)
+{
+	u64 rt_runtime, rt_period;
+
+	rt_period = rt_period_us * NSEC_PER_USEC;
+	rt_runtime = tg->rt_bandwidth.rt_runtime;
+
+	return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
+}
+
+long sched_group_rt_period(struct task_group *tg)
+{
+	u64 rt_period_us;
+
+	rt_period_us = ktime_to_ns(tg->rt_bandwidth.rt_period);
+	do_div(rt_period_us, NSEC_PER_USEC);
+	return rt_period_us;
+}
+
+static int sched_rt_global_constraints(void)
+{
+	int ret = 0;
+
+	mutex_lock(&rt_constraints_mutex);
+	read_lock(&tasklist_lock);
+	ret = __rt_schedulable(NULL, 0, 0);
+	read_unlock(&tasklist_lock);
+	mutex_unlock(&rt_constraints_mutex);
+
+	return ret;
+}
+
+int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
+{
+	/* Don't accept realtime tasks when there is no way for them to run */
+	if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0)
+		return 0;
+
+	return 1;
+}
+
+#else /* !CONFIG_RT_GROUP_SCHED */
+static int sched_rt_global_constraints(void)
+{
+	unsigned long flags;
+	int i;
+
+	raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
+	for_each_possible_cpu(i) {
+		struct rt_rq *rt_rq = &cpu_rq(i)->rt;
+
+		raw_spin_lock(&rt_rq->rt_runtime_lock);
+		rt_rq->rt_runtime = global_rt_runtime();
+		raw_spin_unlock(&rt_rq->rt_runtime_lock);
+	}
+	raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
+
+	return 0;
+}
+#endif /* CONFIG_RT_GROUP_SCHED */
+
+static int sched_rt_global_validate(void)
+{
+	if (sysctl_sched_rt_period <= 0)
+		return -EINVAL;
+
+	if ((sysctl_sched_rt_runtime != RUNTIME_INF) &&
+		(sysctl_sched_rt_runtime > sysctl_sched_rt_period))
+		return -EINVAL;
+
+	return 0;
+}
+
+static void sched_rt_do_global(void)
+{
+	def_rt_bandwidth.rt_runtime = global_rt_runtime();
+	def_rt_bandwidth.rt_period = ns_to_ktime(global_rt_period());
+}
+
+int sched_rt_handler(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp,
+		loff_t *ppos)
+{
+	int old_period, old_runtime;
+	static DEFINE_MUTEX(mutex);
+	int ret;
+
+	mutex_lock(&mutex);
+	old_period = sysctl_sched_rt_period;
+	old_runtime = sysctl_sched_rt_runtime;
+
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+
+	if (!ret && write) {
+		ret = sched_rt_global_validate();
+		if (ret)
+			goto undo;
+
+		ret = sched_dl_global_validate();
+		if (ret)
+			goto undo;
+
+		ret = sched_rt_global_constraints();
+		if (ret)
+			goto undo;
+
+		sched_rt_do_global();
+		sched_dl_do_global();
+	}
+	if (0) {
+undo:
+		sysctl_sched_rt_period = old_period;
+		sysctl_sched_rt_runtime = old_runtime;
+	}
+	mutex_unlock(&mutex);
+
+	return ret;
+}
+
+int sched_rr_handler(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp,
+		loff_t *ppos)
+{
+	int ret;
+	static DEFINE_MUTEX(mutex);
+
+	mutex_lock(&mutex);
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+	/*
+	 * Make sure that internally we keep jiffies.
+	 * Also, writing zero resets the timeslice to default:
+	 */
+	if (!ret && write) {
+		sched_rr_timeslice =
+			sysctl_sched_rr_timeslice <= 0 ? RR_TIMESLICE :
+			msecs_to_jiffies(sysctl_sched_rr_timeslice);
+	}
+	mutex_unlock(&mutex);
+	return ret;
+}
+
 #ifdef CONFIG_SCHED_DEBUG
 extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq);
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 4a845c19b8..84ab1be493 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -380,6 +380,11 @@ extern int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent
 extern void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
 		struct sched_rt_entity *rt_se, int cpu,
 		struct sched_rt_entity *parent);
+extern int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us);
+extern int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us);
+extern long sched_group_rt_runtime(struct task_group *tg);
+extern long sched_group_rt_period(struct task_group *tg);
+extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk);
 
 extern struct task_group *sched_create_group(struct task_group *parent);
 extern void sched_online_group(struct task_group *tg,
-- 
2.9.4

Re: [PATCH 0/4] some scheduler code movements and small cleanup

[Nicolas Pitre]

Ping.


On Wed, 14 Jun 2017, Nicolas Pitre wrote:

> On Tue, 13 Jun 2017, Ingo Molnar wrote:
> 
> > So I'm fine with most of the code movement - let's try this series
> > without any of the more controversial bits which should make future
> > arguments easier.
> 
> Here it is. Big diffstat due to code movement which should untangle
> scheduler classes from common code some more, and isolating PI futex
> support, with the net effect of reducing the common code file size.
> 
> Sidenote: I just discovered that the default git diff algorithm produces
> awful results with this series at least, with 1270 extra diff lines
> compared to the output from the patience or minimal diff algorithms.
> Using --diff-algorithm=minimal produces a much saner diffstat, way more
> representative of the actual changes in this case.
> 
> 
>  include/linux/futex.h   |    7 +-
>  init/Kconfig            |    8 +-
>  kernel/futex.c          | 1559 +---------------------------------------
>  kernel/futex_pi.c       | 1563 +++++++++++++++++++++++++++++++++++++++++
>  kernel/sched/core.c     |  655 +----------------
>  kernel/sched/deadline.c |  336 +++++++++
>  kernel/sched/rt.c       |  310 ++++++++
>  kernel/sched/sched.h    |   19 +
>  8 files changed, 2272 insertions(+), 2185 deletions(-)
> 

Re: [PATCH 0/4] some scheduler code movements and small cleanup

[Ingo Molnar]

* Nicolas Pitre <nicolas.pitre@linaro.org> wrote:

> Ping.

I've applied the first patch to the scheduler tree yesterday, but the other 
changes unfortunately conflicted with other pending scheduler work - could you 
please re-post the other 3 patches on top of tip:sched/core?

Thanks,

	Ingo

[tip:sched/core] sched/cpuset: Only offer CONFIG_CPUSETS if SMP is enabled

[tip-bot for Nicolas Pitre]

Commit-ID:  e1d4eeec5aaa28d25f249c0195b0e1d9b9feb7bd
Gitweb:     http://git.kernel.org/tip/e1d4eeec5aaa28d25f249c0195b0e1d9b9feb7bd
Author:     Nicolas Pitre <nicolas.pitre@linaro.org>
AuthorDate: Wed, 14 Jun 2017 13:19:23 -0400
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Fri, 23 Jun 2017 10:46:44 +0200

sched/cpuset: Only offer CONFIG_CPUSETS if SMP is enabled

Make CONFIG_CPUSETS=y depend on SMP as this feature makes no sense
on UP. This allows for configuring out cpuset_cpumask_can_shrink()
and task_can_attach() entirely, which shrinks the kernel a bit.

Signed-off-by: Nicolas Pitre <nico@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20170614171926.8345-2-nicolas.pitre@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 init/Kconfig        | 1 +
 kernel/sched/core.c | 7 +++----
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/init/Kconfig b/init/Kconfig
index 1d3475f..c359038 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1156,6 +1156,7 @@ config CGROUP_HUGETLB
 
 config CPUSETS
 	bool "Cpuset controller"
+	depends on SMP
 	help
 	  This option will let you create and manage CPUSETs which
 	  allow dynamically partitioning a system into sets of CPUs and
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 62166da..7faf4b3 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5451,6 +5451,8 @@ void init_idle(struct task_struct *idle, int cpu)
 #endif
 }
 
+#ifdef CONFIG_SMP
+
 int cpuset_cpumask_can_shrink(const struct cpumask *cur,
 			      const struct cpumask *trial)
 {
@@ -5494,7 +5496,6 @@ int task_can_attach(struct task_struct *p,
 		goto out;
 	}
 
-#ifdef CONFIG_SMP
 	if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span,
 					      cs_cpus_allowed)) {
 		unsigned int dest_cpu = cpumask_any_and(cpu_active_mask,
@@ -5524,13 +5525,11 @@ int task_can_attach(struct task_struct *p,
 		rcu_read_unlock_sched();
 
 	}
-#endif
+
 out:
 	return ret;
 }
 
-#ifdef CONFIG_SMP
-
 bool sched_smp_initialized __read_mostly;
 
 #ifdef CONFIG_NUMA_BALANCING