Skip to contentSkip to conversation

sched/rt: fix bad task migration for rt tasks

PATCH Superseded Schspa Shi 2 participants 6 messages Jul 12, 2022 Scheduler

v5 of 8 Superseded Latest is v8 →

lore
Share & tools
lore

Schspa Shi

author
#0 lore raw

PATCH v5 1/2 sched/rt: fix bad task migration for rt tasks

Commit 95158a89dd50 ("sched,rt: Use the full cpumask for balancing") allow find_lock_lowest_rq to pick a task with migration disabled. This commit is intended to push the current running task on this CPU away.

There is a race scenarios, which allows a migration disabled task to be migrated to another CPU.

When there is a RT task with higher priority, rt sched class was intended to migrate higher priority task to lowest rq via push_rt_tasks, this BUG will happen here.

With the system running on PREEMPT_RT, rt_spin_lock will disable migration, this will make the problem easier to reproduce.

I have seen this crash on PREEMPT_RT, from the logs, there is a race when trying to migrate higher priority tasks to the lowest rq.

Please refer to the following scenarios.

CPU0 CPU1
------------------------------------------------------------------
push_rt_task
check is_migration_disabled(next_task)
task not running and migration_disabled == 0

  find_lock_lowest_rq(next_task, rq);
    _double_lock_balance(this_rq, busiest);
      raw_spin_rq_unlock(this_rq);
      double_rq_lock(this_rq, busiest);
        <<wait for busiest rq>>
                                            <wakeup>
                                        task become running
                                        migrate_disable();
                                          <context out>
  deactivate_task(rq, next_task, 0);
  set_task_cpu(next_task, lowest_rq->cpu);
    WARN_ON_ONCE(is_migration_disabled(p));
      ---------OOPS-------------

Crash logs as fellowing:

[123671.996430] WARNING: CPU: 2 PID: 13470 at kernel/sched/core.c:2485
set_task_cpu+0x8c/0x108
[123671.996800] pstate: 20400009 (nzCv daif +PAN -UAO -TCO BTYPE=--)
[123671.996811] pc : set_task_cpu+0x8c/0x108
[123671.996820] lr : set_task_cpu+0x7c/0x108
[123671.996828] sp : ffff80001268bd30
[123671.996832] pmr_save: 00000060
[123671.996835] x29: ffff80001268bd30 x28: ffff0001a3d68e80
[123671.996844] x27: ffff80001225f4a8 x26: ffff800010ab62cb
[123671.996854] x25: ffff80026d95e000 x24: 0000000000000005
[123671.996864] x23: ffff00019746c1b0 x22: 0000000000000000
[123671.996873] x21: ffff00027ee33a80 x20: 0000000000000000
[123671.996882] x19: ffff00019746ba00 x18: 0000000000000000
[123671.996890] x17: 0000000000000000 x16: 0000000000000000
[123671.996899] x15: 000000000000000a x14: 000000000000349e
[123671.996908] x13: ffff800012f4503d x12: 0000000000000001
[123671.996916] x11: 0000000000000000 x10: 0000000000000000
[123671.996925] x9 : 00000000000c0000 x8 : ffff00027ee58700
[123671.996933] x7 : ffff00027ee8da80 x6 : ffff00027ee8e580
[123671.996942] x5 : ffff00027ee8dcc0 x4 : 0000000000000005
[123671.996951] x3 : ffff00027ee8e338 x2 : 0000000000000000
[123671.996959] x1 : 00000000000000ff x0 : 0000000000000002
[123671.996969] Call trace:
[123671.996975]  set_task_cpu+0x8c/0x108
[123671.996984]  push_rt_task.part.0+0x144/0x184
[123671.996995]  push_rt_tasks+0x28/0x3c
[123671.997002]  task_woken_rt+0x58/0x68
[123671.997009]  ttwu_do_wakeup+0x5c/0xd0
[123671.997019]  ttwu_do_activate+0xc0/0xd4
[123671.997028]  try_to_wake_up+0x244/0x288
[123671.997036]  wake_up_process+0x18/0x24
[123671.997045]  __irq_wake_thread+0x64/0x80
[123671.997056]  __handle_irq_event_percpu+0x110/0x124
[123671.997064]  handle_irq_event_percpu+0x50/0xac
[123671.997072]  handle_irq_event+0x84/0xfc

To fix it, we need to check migration_disabled flag again to avoid bad migration.

Fixes 95158a89dd50 ("sched,rt: Use the full cpumask for balancing")

--

Changelog:
v1 -> v2:
- Modify commit message to add fixed commit information.
- Going to retry to push the current running task on this CPU away, instead doing nothing for this migrate disabled task.
v2 -> v3:
- Change migration disabled check to the correct position
v3 -> v4:
- Check migrate disabled in find_lock_lowest_rq to avoid not necessary check when task rq is not released as Steven advised.
v4 -> v5:
- Adjust the comment as Steve advised to make it clear.

---
 kernel/sched/deadline.c | 1 +
 kernel/sched/rt.c       | 4 ++++
 2 files changed, 5 insertions(+)
kernel/sched/deadline.c +1 -0
index b5152961b7432..cb3b886a081c3 100644
@@ -2238,6 +2238,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
 				     !cpumask_test_cpu(later_rq->cpu, &task->cpus_mask) ||
 				     task_running(rq, task) ||
 				     !dl_task(task) ||
+				     is_migration_disabled(task) ||
 				     !task_on_rq_queued(task))) {
 				double_unlock_balance(rq, later_rq);
 				later_rq = NULL;
kernel/sched/rt.c +4 -0
index 8c9ed96648409..7c32ba51b6d85 100644
@@ -1998,11 +1998,15 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 			 * the mean time, task could have
 			 * migrated already or had its affinity changed.
 			 * Also make sure that it wasn't scheduled on its rq.
+			 * It is possible the task was scheduled, set
+			 * "migrate_disabled" and then got preempted, And we
+			 * check task migration disable flag here too.
 			 */
 			if (unlikely(task_rq(task) != rq ||
 				     !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_mask) ||
 				     task_running(rq, task) ||
 				     !rt_task(task) ||
+				     is_migration_disabled(task) ||
 				     !task_on_rq_queued(task))) {
 
 				double_unlock_balance(rq, lowest_rq);
Signature · 1 line
2.37.0
author
#1 lore raw

PATCH v5 2/2 sched/rt: Trying to push current task when target disable migrating

When the task to push disable migration, retry to push the current running task on this CPU away, instead doing nothing for this migrate disabled task.

---
 kernel/sched/core.c | 6 +++++-
 kernel/sched/rt.c   | 6 ++++++
 2 files changed, 11 insertions(+), 1 deletion(-)
kernel/sched/core.c +5 -1
index da0bf6fe9ecdc..0b1fefd97d874 100644
@@ -2509,8 +2509,12 @@ int push_cpu_stop(void *arg)
 	if (p->sched_class->find_lock_rq)
 		lowest_rq = p->sched_class->find_lock_rq(p, rq);
 
-	if (!lowest_rq)
+	if (!lowest_rq) {
+		if (unlikely(is_migration_disabled(p)))
+			p->migration_flags |= MDF_PUSH;
+
 		goto out_unlock;
+	}
 
 	// XXX validate p is still the highest prio task
 	if (task_rq(p) == rq) {
kernel/sched/rt.c +6 -0
index 7c32ba51b6d85..877380e465b7a 100644
@@ -2136,6 +2136,12 @@ static int push_rt_task(struct rq *rq, bool pull)
 		 */
 		task = pick_next_pushable_task(rq);
 		if (task == next_task) {
+			/*
+			 * If next task has now disabled migrating, see if we
+			 * can push the current task.
+			 */
+			if (unlikely(is_migration_disabled(task)))
+				goto retry;
 			/*
 			 * The task hasn't migrated, and is still the next
 			 * eligible task, but we failed to find a run-queue
Signature · 1 line
2.37.0
#2 lore raw

Re: [PATCH v5 2/2] sched/rt: Trying to push current task when target disable migrating

Quoted 15 lines · On Tue, 12 Jul 2022 09:31:25 +0800 Schspa Shi <[email protected]> wrote:

When the task to push disable migration, retry to push the current running task on this CPU away, instead doing nothing for this migrate disabled task.

---
 kernel/sched/core.c | 6 +++++-
 kernel/sched/rt.c   | 6 ++++++
 2 files changed, 11 insertions(+), 1 deletion(-)
kernel/sched/core.c +0 -0
index da0bf6fe9ecdc..0b1fefd97d874 100644

kernel/sched/core.c int push_cpu_stop(void *arg) · line 2512

Quoted 5 lines
kernel/sched/core.c +1 -1
@@ -2509,8 +2509,12 @@ int push_cpu_stop(void *arg)
 	if (p->sched_class->find_lock_rq)
 		lowest_rq = p->sched_class->find_lock_rq(p, rq);
 
-	if (!lowest_rq)
+	if (!lowest_rq) {

Probably should add a comment reminding us that the find_lock() function above could have released the rq lock and allow p to schedule and be preempted again, and that lowest_rq could be NULL because p now has the migrate_disable flag set and not because it could not find the lowest rq.

-- Steve

Quoted 25 lines
kernel/sched/core.c +4 -0
+		if (unlikely(is_migration_disabled(p)))
+			p->migration_flags |= MDF_PUSH;
+
 		goto out_unlock;
+	}
 
 	// XXX validate p is still the highest prio task
 	if (task_rq(p) == rq) {
kernel/sched/rt.c +6 -0
index 7c32ba51b6d85..877380e465b7a 100644
@@ -2136,6 +2136,12 @@ static int push_rt_task(struct rq *rq, bool pull)
 		 */
 		task = pick_next_pushable_task(rq);
 		if (task == next_task) {
+			/*
+			 * If next task has now disabled migrating, see if we
+			 * can push the current task.
+			 */
+			if (unlikely(is_migration_disabled(task)))
+				goto retry;
 			/*
 			 * The task hasn't migrated, and is still the next
 			 * eligible task, but we failed to find a run-queue
author
#3 lore raw

Re: [PATCH v5 2/2] sched/rt: Trying to push current task when target disable migrating

Quoted 21 lines · Steven Rostedt
Quoted 18 lines · On Tue, 12 Jul 2022 09:31:25 +0800 Schspa Shi <[email protected]> wrote:

When the task to push disable migration, retry to push the current running task on this CPU away, instead doing nothing for this migrate disabled task.

---
 kernel/sched/core.c | 6 +++++-
 kernel/sched/rt.c   | 6 ++++++
 2 files changed, 11 insertions(+), 1 deletion(-)
kernel/sched/core.c +0 -0
index da0bf6fe9ecdc..0b1fefd97d874 100644
@@ -2509,8 +2509,12 @@ int push_cpu_stop(void *arg)
 	if (p->sched_class->find_lock_rq)
 		lowest_rq = p->sched_class->find_lock_rq(p, rq);
 
Quoted 8 lines

kernel/sched/core.c int push_cpu_stop(void *arg) · line 2512

Quoted 2 lines
kernel/sched/core.c +1 -1
-	if (!lowest_rq)
+	if (!lowest_rq) {

Probably should add a comment reminding us that the find_lock() function above could have released the rq lock and allow p to schedule and be preempted again, and that lowest_rq could be NULL because p now has the migrate_disable flag set and not because it could not find the lowest rq.

OK, it will be better.

Let me upload a v6 patch for that.

Quoted 28 lines

-- Steve

Quoted 25 lines
kernel/sched/core.c +4 -0
+		if (unlikely(is_migration_disabled(p)))
+			p->migration_flags |= MDF_PUSH;
+
 		goto out_unlock;
+	}
 
 	// XXX validate p is still the highest prio task
 	if (task_rq(p) == rq) {
kernel/sched/rt.c +6 -0
index 7c32ba51b6d85..877380e465b7a 100644
@@ -2136,6 +2136,12 @@ static int push_rt_task(struct rq *rq, bool pull)
 		 */
 		task = pick_next_pushable_task(rq);
 		if (task == next_task) {
+			/*
+			 * If next task has now disabled migrating, see if we
+			 * can push the current task.
+			 */
+			if (unlikely(is_migration_disabled(task)))
+				goto retry;
 			/*
 			 * The task hasn't migrated, and is still the next
 			 * eligible task, but we failed to find a run-queue
Signature · 2 lines
BRs
Schspa Shi
reviewer Reviewed-by on v5 1/2
#4 lore raw
In reply to Schspa Shi

kernel/sched/rt.c static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) · line 2003

Quoted 7 lines · On Tue, 12 Jul 2022 09:31:24 +0800 Schspa Shi <[email protected]> wrote:
kernel/sched/rt.c +3 -0
@@ -1998,11 +1998,15 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 			 * the mean time, task could have
 			 * migrated already or had its affinity changed.
 			 * Also make sure that it wasn't scheduled on its rq.
+			 * It is possible the task was scheduled, set
+			 * "migrate_disabled" and then got preempted, And we
+			 * check task migration disable flag here too.

Nit. "got preempted, so we must check the task migration disable flag here too".

But other than that.

-- Steve

Quoted 1 line
(quoted diff) +0 -0
 			 */
author
#5 lore raw
Quoted 14 lines · Steven Rostedt

kernel/sched/rt.c static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) · line 2003

Quoted 7 lines · On Tue, 12 Jul 2022 09:31:24 +0800 Schspa Shi <[email protected]> wrote:
kernel/sched/rt.c +3 -0
@@ -1998,11 +1998,15 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 			 * the mean time, task could have
 			 * migrated already or had its affinity changed.
 			 * Also make sure that it wasn't scheduled on its rq.
+			 * It is possible the task was scheduled, set
+			 * "migrate_disabled" and then got preempted, And we
+			 * check task migration disable flag here too.

Nit. "got preempted, so we must check the task migration disable flag here too".

OK, I will make a upload for this too.

Quoted 7 lines

But other than that.

-- Steve

Quoted 1 line
(quoted diff) +0 -0
 			 */
Signature · 2 lines
BRs
Schspa Shi