diff mbox series

[2/7] cpuset: Rebuild root domain deadline accounting information

Message ID 1502918443-30169-3-git-send-email-mathieu.poirier@linaro.org
State Superseded
Headers show
Series sched/deadline: fix cpusets bandwidth accounting | expand

Commit Message

Mathieu Poirier Aug. 16, 2017, 9:20 p.m. UTC
When the topology of root domains is modified by CPUset or CPUhotplug
operations information about the current deadline bandwidth held in the
root domain is lost.

This patch address the issue by recalculating the lost deadline
bandwidth information by circling through the deadline tasks held in
CPUsets and adding their current load to the root domain they are
associated with.

Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>

---
 include/linux/sched.h          |  3 ++
 include/linux/sched/deadline.h |  8 ++++++
 kernel/cgroup/cpuset.c         | 63 +++++++++++++++++++++++++++++++++++++++++-
 kernel/sched/deadline.c        | 31 +++++++++++++++++++++
 kernel/sched/sched.h           |  3 --
 kernel/sched/topology.c        | 14 +++++++++-
 6 files changed, 117 insertions(+), 5 deletions(-)

-- 
2.7.4
diff mbox series

Patch

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8337e2db0bb2..bb07b194d951 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -241,6 +241,9 @@  struct vtime {
 	u64			gtime;
 };
 
+extern struct root_domain def_root_domain;
+extern struct mutex sched_domains_mutex;
+
 struct sched_info {
 #ifdef CONFIG_SCHED_INFO
 	/* Cumulative counters: */
diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h
index 975be862e083..fcef5565dc94 100644
--- a/include/linux/sched/deadline.h
+++ b/include/linux/sched/deadline.h
@@ -28,4 +28,12 @@  static inline bool dl_time_before(u64 a, u64 b)
 	return (s64)(a - b) < 0;
 }
 
+#ifdef CONFIG_SMP
+
+struct root_domain;
+extern void dl_add_task_root_domain(struct task_struct *p);
+extern void dl_clear_root_domain(struct root_domain *rd);
+
+#endif /* CONFIG_SMP */
+
 #endif /* _LINUX_SCHED_DEADLINE_H */
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 63ce8bbb476e..f6d1e485dc2d 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -44,6 +44,7 @@ 
 #include <linux/proc_fs.h>
 #include <linux/rcupdate.h>
 #include <linux/sched.h>
+#include <linux/sched/deadline.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/task.h>
 #include <linux/seq_file.h>
@@ -800,6 +801,66 @@  static int generate_sched_domains(cpumask_var_t **domains,
 	return ndoms;
 }
 
+static void update_tasks_root_domain(struct cpuset *cs)
+{
+	struct css_task_iter it;
+	struct task_struct *task;
+
+	css_task_iter_start(&cs->css, &it);
+
+	while ((task = css_task_iter_next(&it)))
+		dl_add_task_root_domain(task);
+
+	css_task_iter_end(&it);
+}
+
+/*
+ * Called with cpuset_mutex held (rebuild_sched_domains())
+ * Called with hotplug lock held (rebuild_sched_domains_locked())
+ * Called with sched_domains_mutex held (partition_and_rebuild_domains())
+ */
+static void rebuild_root_domains(void)
+{
+	struct cpuset *cs = NULL;
+	struct cgroup_subsys_state *pos_css;
+
+	rcu_read_lock();
+
+	/*
+	 * Clear default root domain DL accounting, it will be computed again
+	 * if a task belongs to it.
+	 */
+	dl_clear_root_domain(&def_root_domain);
+
+	cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) {
+
+		if (cpumask_empty(cs->effective_cpus)) {
+			pos_css = css_rightmost_descendant(pos_css);
+			continue;
+		}
+
+		css_get(&cs->css);
+
+		rcu_read_unlock();
+
+		update_tasks_root_domain(cs);
+
+		rcu_read_lock();
+		css_put(&cs->css);
+	}
+	rcu_read_unlock();
+}
+
+static void
+partition_and_rebuild_domains(int ndoms_new, cpumask_var_t doms_new[],
+			      struct sched_domain_attr *dattr_new)
+{
+	mutex_lock(&sched_domains_mutex);
+	partition_sched_domains_locked(ndoms_new, doms_new, dattr_new);
+	rebuild_root_domains();
+	mutex_unlock(&sched_domains_mutex);
+}
+
 /*
  * Rebuild scheduler domains.
  *
@@ -832,7 +893,7 @@  static void rebuild_sched_domains_locked(void)
 	ndoms = generate_sched_domains(&doms, &attr);
 
 	/* Have scheduler rebuild the domains */
-	partition_sched_domains(ndoms, doms, attr);
+	partition_and_rebuild_domains(ndoms, doms, attr);
 out:
 	put_online_cpus();
 }
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 755bd3f1a1a9..ba64a5b8f40b 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2214,6 +2214,37 @@  void __init init_sched_dl_class(void)
 					GFP_KERNEL, cpu_to_node(i));
 }
 
+void dl_add_task_root_domain(struct task_struct *p)
+{
+	unsigned long flags;
+	struct rq_flags rf;
+	struct rq *rq;
+	struct dl_bw *dl_b;
+
+	rq = task_rq_lock(p, &rf);
+	if (!dl_task(p))
+		goto unlock;
+
+	dl_b = &rq->rd->dl_bw;
+	raw_spin_lock_irqsave(&dl_b->lock, flags);
+
+	dl_b->total_bw += p->dl.dl_bw;
+
+	raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+
+unlock:
+	task_rq_unlock(rq, p, &rf);
+}
+
+void dl_clear_root_domain(struct root_domain *rd)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&rd->dl_bw.lock, flags);
+	rd->dl_bw.total_bw = 0;
+	raw_spin_unlock_irqrestore(&rd->dl_bw.lock, flags);
+}
+
 #endif /* CONFIG_SMP */
 
 static void switched_from_dl(struct rq *rq, struct task_struct *p)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index eeef1a3086d1..cfd3b5b5fe7f 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -650,9 +650,6 @@  struct root_domain {
 	unsigned long max_cpu_capacity;
 };
 
-extern struct root_domain def_root_domain;
-extern struct mutex sched_domains_mutex;
-
 extern void init_defrootdomain(void);
 extern int sched_init_domains(const struct cpumask *cpu_map);
 extern void rq_attach_root(struct rq *rq, struct root_domain *rd);
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 58133f2ce889..3522dfc2566f 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -2,6 +2,7 @@ 
  * Scheduler topology setup/handling methods
  */
 #include <linux/sched.h>
+#include <linux/sched/deadline.h>
 #include <linux/mutex.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
@@ -1862,8 +1863,19 @@  void partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[],
 	for (i = 0; i < ndoms_cur; i++) {
 		for (j = 0; j < n && !new_topology; j++) {
 			if (cpumask_equal(doms_cur[i], doms_new[j])
-			    && dattrs_equal(dattr_cur, i, dattr_new, j))
+			    && dattrs_equal(dattr_cur, i, dattr_new, j)) {
+				struct root_domain *rd;
+
+				/*
+				 * This domain won't be destroyed and as such
+				 * its dl_bw->total_bw needs to be cleared.  It
+				 * will be recomputed in function
+				 * update_tasks_root_domain().
+				 */
+				rd = cpu_rq(cpumask_any(doms_cur[i]))->rd;
+				dl_clear_root_domain(rd);
 				goto match1;
+			}
 		}
 		/* No match - a current sched domain not in new doms_new[] */
 		detach_destroy_domains(doms_cur[i]);