sched/deadline: Ensure that updates to exclusive cpusets don't break AC

How we deal with updates to exclusive cpusets is currently broken.
As an example, suppose we have an exclusive cpuset composed of
two cpus: A[cpu0,cpu1]. We can assign SCHED_DEADLINE task to it
up to the allowed bandwidth. If we want now to modify cpusetA's
cpumask, we have to check that removing a cpu's amount of
bandwidth doesn't break AC guarantees. This thing isn't checked
in the current code.

This patch fixes the problem above, denying an update if the
new cpumask won't have enough bandwidth for SCHED_DEADLINE tasks
that are currently active.

Signed-off-by: Juri Lelli <juri.lelli@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Li Zefan <lizefan@huawei.com>
Cc: cgroups@vger.kernel.org
Link: http://lkml.kernel.org/r/5433E6AF.5080105@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

3 files changed, 31 insertions, 0 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1d1fa081d44f..320a9779f1b4 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2052,6 +2052,8 @@ static inline void tsk_restore_flags(struct task_struct *task,
 	task->flags |= orig_flags & flags;
 }
 
+extern int cpuset_cpumask_can_shrink(const struct cpumask *cur,
+				     const struct cpumask *trial);
 extern int task_can_attach(struct task_struct *p,
 			   const struct cpumask *cs_cpus_allowed);
 #ifdef CONFIG_SMP
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 7af8577fc8f8..723cfc9d0ad7 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -506,6 +506,16 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
 			goto out;
 	}
 
+	/*
+	 * We can't shrink if we won't have enough room for SCHED_DEADLINE
+	 * tasks.
+	 */
+	ret = -EBUSY;
+	if (is_cpu_exclusive(cur) &&
+	    !cpuset_cpumask_can_shrink(cur->cpus_allowed,
+				       trial->cpus_allowed))
+		goto out;
+
 	ret = 0;
 out:
 	rcu_read_unlock();
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9993feeb8b10..0456a55fc27f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4650,6 +4650,25 @@ void init_idle(struct task_struct *idle, int cpu)
 #endif
 }
 
+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;
+
+	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);
+
+	return ret;
+}
+
 int task_can_attach(struct task_struct *p,
 		    const struct cpumask *cs_cpus_allowed)
 {