[PATCH] sched/rt: optimize checking group rt scheduler constraints

[Konstantin Khlebnikov]

Group RT scheduler contains protection against setting zero runtime for
cgroup with rt tasks. Right now function tg_set_rt_bandwidth() iterates
over all cpu cgroups and calls tg_has_rt_tasks() for any cgroup which
runtime is zero (not only for changed one). Default rt runtime is zero,
thus tg_has_rt_tasks() will is called for almost at cpu cgroups.

This protection already is slightly racy: runtime limit could be changed
between cpu_cgroup_can_attach() and cpu_cgroup_attach() because changing
cgroup attribute does not lock cgroup_mutex while attach does not lock
rt_constraints_mutex. Changing task scheduler class also races with
changing rt runtime: check in __sched_setscheduler() isn't protected.

Function tg_has_rt_tasks() iterates over all threads in the system.
This gives NR_CGROUPS * NR_TASKS operations under single tasklist_lock
locked for read tg_set_rt_bandwidth(). Any concurrent attempt of locking
tasklist_lock for write (for example fork) will stuck with disabled irqs.

This patch makes two optimizations:
1) Remove locking tasklist_lock and iterate only tasks in cgroup
2) Call tg_has_rt_tasks() iff rt runtime changes from non-zero to zero

All changed code is under CONFIG_RT_GROUP_SCHED.

Testcase:
# mkdir /sys/fs/cgroup/cpu/test{1..10000}
# echo 0 | tee /sys/fs/cgroup/cpu/test*/cpu.rt_runtime_us

At the same time without patch fork time will be >100ms:
# perf trace -e clone --duration 100 stress-ng --fork 1

Also remote ping will show timings >100ms caused by irq latency.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@xxxxxxxxxxxxxx>
---
 kernel/sched/rt.c |   24 +++++++++++-------------
 1 file changed, 11 insertions(+), 13 deletions(-)

diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index e591d40fd645..95d1d7be84ef 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2396,10 +2396,11 @@ const struct sched_class rt_sched_class = {
  */
 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;
+	struct task_struct *task;
+	struct css_task_iter it;
+	int ret = 0;
 
 	/*
 	 * Autogroups do not have RT tasks; see autogroup_create().
@@ -2407,12 +2408,12 @@ static inline int tg_has_rt_tasks(struct task_group *tg)
 	if (task_group_is_autogroup(tg))
 		return 0;
 
-	for_each_process_thread(g, p) {
-		if (rt_task(p) && task_group(p) == tg)
-			return 1;
-	}
+	css_task_iter_start(&tg->css, 0, &it);
+	while (!ret && (task = css_task_iter_next(&it)))
+		ret |= rt_task(task);
+	css_task_iter_end(&it);
 
-	return 0;
+	return ret;
 }
 
 struct rt_schedulable_data {
@@ -2443,9 +2444,10 @@ static int tg_rt_schedulable(struct task_group *tg, void *data)
 		return -EINVAL;
 
 	/*
-	 * Ensure we don't starve existing RT tasks.
+	 * Ensure we don't starve existing RT tasks if runtime turns zero.
 	 */
-	if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg))
+	if (rt_bandwidth_enabled() && !runtime &&
+	    tg->rt_bandwidth.rt_runtime && tg_has_rt_tasks(tg))
 		return -EBUSY;
 
 	total = to_ratio(period, runtime);
@@ -2511,7 +2513,6 @@ static int tg_set_rt_bandwidth(struct task_group *tg,
 		return -EINVAL;
 
 	mutex_lock(&rt_constraints_mutex);
-	read_lock(&tasklist_lock);
 	err = __rt_schedulable(tg, rt_period, rt_runtime);
 	if (err)
 		goto unlock;
@@ -2529,7 +2530,6 @@ static int tg_set_rt_bandwidth(struct task_group *tg,
 	}
 	raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
 unlock:
-	read_unlock(&tasklist_lock);
 	mutex_unlock(&rt_constraints_mutex);
 
 	return err;
@@ -2588,9 +2588,7 @@ 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;