cgroup/cpuset: Free DL BW in case can_attach() fails

cpuset_can_attach() can fail. Postpone DL BW allocation until all tasks
have been checked. DL BW is not allocated per-task but as a sum over
all DL tasks migrating.

If multiple controllers are attached to the cgroup next to the cpuset
controller a non-cpuset can_attach() can fail. In this case free DL BW
in cpuset_cancel_attach().

Finally, update cpuset DL task count (nr_deadline_tasks) only in
cpuset_attach().
Suggested-by: Waiman Long <longman@redhat.com>
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
Reviewed-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

include/linux/sched.h

@@ -1852,7 +1852,7 @@ current_restore_flags(unsigned long orig_flags, unsigned long 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_effective_cpus);
+extern int task_can_attach(struct task_struct *p);
 extern int dl_bw_alloc(int cpu, u64 dl_bw);
 extern void dl_bw_free(int cpu, u64 dl_bw);
 #ifdef CONFIG_SMP

kernel/cgroup/cpuset.c

@@ -198,6 +198,8 @@ struct cpuset {
 	 * know when to rebuild associated root domain bandwidth information.
 	 */
 	int nr_deadline_tasks;
+	int nr_migrate_dl_tasks;
+	u64 sum_migrate_dl_bw;
 
 	/* Invalid partition error code, not lock protected */
 	enum prs_errcode prs_err;
@@ -2496,16 +2498,23 @@ static int cpuset_can_attach_check(struct cpuset *cs)
 	return 0;
 }
 
+static void reset_migrate_dl_data(struct cpuset *cs)
+{
+	cs->nr_migrate_dl_tasks = 0;
+	cs->sum_migrate_dl_bw = 0;
+}
+
 /* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */
 static int cpuset_can_attach(struct cgroup_taskset *tset)
 {
 	struct cgroup_subsys_state *css;
-	struct cpuset *cs;
+	struct cpuset *cs, *oldcs;
 	struct task_struct *task;
 	int ret;
 
 	/* used later by cpuset_attach() */
 	cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css));
+	oldcs = cpuset_attach_old_cs;
 	cs = css_cs(css);
 
 	mutex_lock(&cpuset_mutex);
@@ -2516,7 +2525,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
 		goto out_unlock;
 
 	cgroup_taskset_for_each(task, css, tset) {
-		ret = task_can_attach(task, cs->effective_cpus);
+		ret = task_can_attach(task);
 		if (ret)
 			goto out_unlock;
 		ret = security_task_setscheduler(task);
@@ -2524,11 +2533,31 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
 			goto out_unlock;
 
 		if (dl_task(task)) {
-			cs->nr_deadline_tasks++;
-			cpuset_attach_old_cs->nr_deadline_tasks--;
+			cs->nr_migrate_dl_tasks++;
+			cs->sum_migrate_dl_bw += task->dl.dl_bw;
 		}
 	}
 
+	if (!cs->nr_migrate_dl_tasks)
+		goto out_success;
+
+	if (!cpumask_intersects(oldcs->effective_cpus, cs->effective_cpus)) {
+		int cpu = cpumask_any_and(cpu_active_mask, cs->effective_cpus);
+
+		if (unlikely(cpu >= nr_cpu_ids)) {
+			reset_migrate_dl_data(cs);
+			ret = -EINVAL;
+			goto out_unlock;
+		}
+
+		ret = dl_bw_alloc(cpu, cs->sum_migrate_dl_bw);
+		if (ret) {
+			reset_migrate_dl_data(cs);
+			goto out_unlock;
+		}
+	}
+
+out_success:
 	/*
 	 * Mark attach is in progress.  This makes validate_change() fail
 	 * changes which zero cpus/mems_allowed.
@@ -2551,6 +2580,14 @@ static void cpuset_cancel_attach(struct cgroup_taskset *tset)
 	cs->attach_in_progress--;
 	if (!cs->attach_in_progress)
 		wake_up(&cpuset_attach_wq);
+
+	if (cs->nr_migrate_dl_tasks) {
+		int cpu = cpumask_any(cs->effective_cpus);
+
+		dl_bw_free(cpu, cs->sum_migrate_dl_bw);
+		reset_migrate_dl_data(cs);
+	}
+
 	mutex_unlock(&cpuset_mutex);
 }
 
@@ -2651,6 +2688,12 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 out:
 	cs->old_mems_allowed = cpuset_attach_nodemask_to;
 
+	if (cs->nr_migrate_dl_tasks) {
+		cs->nr_deadline_tasks += cs->nr_migrate_dl_tasks;
+		oldcs->nr_deadline_tasks -= cs->nr_migrate_dl_tasks;
+		reset_migrate_dl_data(cs);
+	}
+
 	cs->attach_in_progress--;
 	if (!cs->attach_in_progress)
 		wake_up(&cpuset_attach_wq);
@@ -3330,7 +3373,7 @@ static int cpuset_can_fork(struct task_struct *task, struct css_set *cset)
 	if (ret)
 		goto out_unlock;
 
-	ret = task_can_attach(task, cs->effective_cpus);
+	ret = task_can_attach(task);
 	if (ret)
 		goto out_unlock;
 

kernel/sched/core.c

@@ -9294,8 +9294,7 @@ int cpuset_cpumask_can_shrink(const struct cpumask *cur,
 	return ret;
 }
 
-int task_can_attach(struct task_struct *p,
-		    const struct cpumask *cs_effective_cpus)
+int task_can_attach(struct task_struct *p)
 {
 	int ret = 0;
 
@@ -9308,21 +9307,9 @@ int task_can_attach(struct task_struct *p,
 	 * success of set_cpus_allowed_ptr() on all attached tasks
 	 * before cpus_mask may be changed.
 	 */
-	if (p->flags & PF_NO_SETAFFINITY) {
+	if (p->flags & PF_NO_SETAFFINITY)
 		ret = -EINVAL;
-		goto out;
-	}
-
-	if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span,
-					      cs_effective_cpus)) {
-		int cpu = cpumask_any_and(cpu_active_mask, cs_effective_cpus);
 
-		if (unlikely(cpu >= nr_cpu_ids))
-			return -EINVAL;
-		ret = dl_bw_alloc(cpu, p->dl.dl_bw);
-	}
-
-out:
 	return ret;
 }