[RFC][PATCH 04/22] sched: SCHED_DEADLINE SMP-related data structures

[Raistlin <raistlin@linux.it>]

[-- Attachment #1: Type: text/plain, Size: 4600 bytes --]


Introduce data structures relevant for implementing dynamic
migration of -deadline tasks.

Mainly, this is the logic for checking if runqueues are
overloaded with -deadline tasks and for choosing where
a task should migrate, when it is the case.

Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
---
 include/linux/sched.h |    1 +
 kernel/sched.c        |   58 ++++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 58 insertions(+), 1 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index c72a132..f94da51 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1336,6 +1336,7 @@ struct task_struct {
 
 	struct list_head tasks;
 	struct plist_node pushable_tasks;
+	struct rb_node pushable_dl_tasks;
 
 	struct mm_struct *mm, *active_mm;
 #if defined(SPLIT_RSS_COUNTING)
diff --git a/kernel/sched.c b/kernel/sched.c
index d157358..b11e888 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -424,6 +424,35 @@ struct dl_rq {
 	struct rb_node *rb_leftmost;
 
 	unsigned long dl_nr_running;
+
+#ifdef CONFIG_SMP
+	/*
+	 * Deadline values of the currently executing and the
+	 * earliest ready task on this rq. Caching these facilitates
+	 * the decision wether or not a ready but not running task
+	 * should migrate somewhere else.
+	 */
+	struct {
+		u64 curr;
+		u64 next;
+	} earliest_dl;
+
+	unsigned long dl_nr_migratory;
+	unsigned long dl_nr_total;
+	int overloaded;
+
+	/*
+	 * Tasks on this rq that can be pushed away. They are kept in
+	 * an rb-tree, ordered by tasks' deadlines, with caching
+	 * of the leftmost (earliest deadline) element.
+	 */
+	struct rb_root pushable_dl_tasks_root;
+	struct rb_node *pushable_dl_tasks_leftmost;
+#endif
+
+#ifdef CONFIG_DEADLINE_GROUP_SCHED
+	struct rq *rq;
+#endif
 };
 
 #ifdef CONFIG_SMP
@@ -442,6 +471,13 @@ struct root_domain {
 	cpumask_var_t online;
 
 	/*
+	 * The bit corresponding to a CPU gets set here if such CPU has more
+	 * than one runnable -deadline task (as it is below for RT tasks).
+	 */
+	cpumask_var_t dlo_mask;
+	atomic_t dlo_count;
+
+	/*
 	 * The "RT overload" flag: it gets set if a CPU has more than
 	 * one runnable RT task.
 	 */
@@ -2742,6 +2778,7 @@ void sched_fork(struct task_struct *p, int clone_flags)
 	/* Want to start with kernel preemption disabled. */
 	task_thread_info(p)->preempt_count = 1;
 #endif
+	RB_CLEAR_NODE(&p->pushable_dl_tasks);
 	plist_node_init(&p->pushable_tasks, MAX_PRIO);
 
 	put_cpu();
@@ -5804,6 +5841,7 @@ again:
 		p->sched_class->set_cpus_allowed(p, new_mask);
 	else {
 		cpumask_copy(&p->cpus_allowed, new_mask);
+		p->dl.nr_cpus_allowed = cpumask_weight(new_mask);
 		p->rt.nr_cpus_allowed = cpumask_weight(new_mask);
 	}
 
@@ -6551,6 +6589,7 @@ static void free_rootdomain(struct root_domain *rd)
 
 	cpupri_cleanup(&rd->cpupri);
 
+	free_cpumask_var(rd->dlo_mask);
 	free_cpumask_var(rd->rto_mask);
 	free_cpumask_var(rd->online);
 	free_cpumask_var(rd->span);
@@ -6602,8 +6641,10 @@ static int init_rootdomain(struct root_domain *rd)
 		goto out;
 	if (!alloc_cpumask_var(&rd->online, GFP_KERNEL))
 		goto free_span;
-	if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+	if (!alloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL))
 		goto free_online;
+	if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+		goto free_dlo_mask;
 
 	if (cpupri_init(&rd->cpupri) != 0)
 		goto free_rto_mask;
@@ -6611,6 +6652,8 @@ static int init_rootdomain(struct root_domain *rd)
 
 free_rto_mask:
 	free_cpumask_var(rd->rto_mask);
+free_dlo_mask:
+	free_cpumask_var(rd->dlo_mask);
 free_online:
 	free_cpumask_var(rd->online);
 free_span:
@@ -8033,6 +8076,19 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
 static void init_dl_rq(struct dl_rq *dl_rq, struct rq *rq)
 {
 	dl_rq->rb_root = RB_ROOT;
+
+#ifdef CONFIG_SMP
+	/* zero means no -deadline tasks */
+	dl_rq->earliest_dl.curr = dl_rq->earliest_dl.next = 0;
+
+	dl_rq->dl_nr_migratory = 0;
+	dl_rq->overloaded = 0;
+	dl_rq->pushable_dl_tasks_root = RB_ROOT;
+#endif
+
+#ifdef CONFIG_DEADLINE_GROUP_SCHED
+	dl_rq->rq = rq;
+#endif
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-- 
1.7.2.3


-- 
<<This happens because I choose it to happen!>> (Raistlin Majere)
----------------------------------------------------------------------
Dario Faggioli, ReTiS Lab, Scuola Superiore Sant'Anna, Pisa  (Italy)

http://blog.linux.it/raistlin / raistlin@ekiga.net /
dario.faggioli@jabber.org

[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 198 bytes --]