[PATCH v3] sched/fair: Clear ->h_load_next when unregistering cgroup

Peng Wang posted 1 patch 3 months, 2 weeks ago
kernel/sched/fair.c | 9 +++++++++
1 file changed, 9 insertions(+)
[PATCH v3] sched/fair: Clear ->h_load_next when unregistering cgroup
Posted by Peng Wang 3 months, 2 weeks ago
An invalid pointer dereference bug was reported on arm64 cpu, and has
not yet been seen on x86. A partial oops looks like:

 Call trace:
  update_cfs_rq_h_load+0x80/0xb0
  wake_affine+0x158/0x168
  select_task_rq_fair+0x364/0x3a8
  try_to_wake_up+0x154/0x648
  wake_up_q+0x68/0xd0
  futex_wake_op+0x280/0x4c8
  do_futex+0x198/0x1c0
  __arm64_sys_futex+0x11c/0x198

Link: https://lore.kernel.org/all/20251013071820.1531295-1-CruzZhao@linux.alibaba.com/

We found that the task_group corresponding to the problematic se
is not in the parent task_group’s children list, indicating that
h_load_next points to an invalid address. Consider the following
cgroup and task hierarchy:

         A
        / \
       /   \
      B     E
     / \    |
    /   \   t2
   C     D
   |     |
   t0    t1

Here follows a timing sequence that may be responsible for triggering
the problem:

CPU X                   CPU Y                   CPU Z
wakeup t0
set list A->B->C
traverse A->B->C
t0 exits
destroy C
                        wakeup t2
                        set list A->E           wakeup t1
                                                set list A->B->D
                        traverse A->B->C
                        panic

CPU Z sets ->h_load_next list to A->B->D, but due to arm64 weaker memory
ordering, Y may observe A->B before it sees B->D, then in this time window,
it can traverse A->B->C and reach an invalid se.

We can avoid stale pointer accesses by clearing ->h_load_next when
unregistering cgroup.

Suggested-by: Vincent Guittot <vincent.guittot@linaro.org>
Fixes: 685207963be9 ("sched: Move h_load calculation to task_h_load()")
Cc: <stable@vger.kernel.org>
Co-developed-by: Cruz Zhao <CruzZhao@linux.alibaba.com>
Signed-off-by: Cruz Zhao <CruzZhao@linux.alibaba.com>
Signed-off-by: Peng Wang <peng_wang@linux.alibaba.com>
---
 kernel/sched/fair.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index cee1793e8277..32b466605925 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -13418,6 +13418,8 @@ void unregister_fair_sched_group(struct task_group *tg)
 		struct rq *rq = cpu_rq(cpu);
 
 		if (se) {
+			struct cfs_rq *parent_cfs_rq = cfs_rq_of(se);
+
 			if (se->sched_delayed) {
 				guard(rq_lock_irqsave)(rq);
 				if (se->sched_delayed) {
@@ -13427,6 +13429,13 @@ void unregister_fair_sched_group(struct task_group *tg)
 				list_del_leaf_cfs_rq(cfs_rq);
 			}
 			remove_entity_load_avg(se);
+
+			/*
+			 * Clear parent's h_load_next if it points to the
+			 * sched_entity being freed to avoid stale pointer.
+			 */
+			if (READ_ONCE(parent_cfs_rq->h_load_next) == se)
+				WRITE_ONCE(parent_cfs_rq->h_load_next, NULL);
 		}
 
 		/*
-- 
2.27.0

Re: [PATCH v3] sched/fair: Clear ->h_load_next when unregistering cgroup
Posted by Vincent Guittot 3 months, 2 weeks ago
On Fri, 24 Oct 2025 at 09:24, Peng Wang <peng_wang@linux.alibaba.com> wrote:
>
> An invalid pointer dereference bug was reported on arm64 cpu, and has
> not yet been seen on x86. A partial oops looks like:
>
>  Call trace:
>   update_cfs_rq_h_load+0x80/0xb0
>   wake_affine+0x158/0x168
>   select_task_rq_fair+0x364/0x3a8
>   try_to_wake_up+0x154/0x648
>   wake_up_q+0x68/0xd0
>   futex_wake_op+0x280/0x4c8
>   do_futex+0x198/0x1c0
>   __arm64_sys_futex+0x11c/0x198
>
> Link: https://lore.kernel.org/all/20251013071820.1531295-1-CruzZhao@linux.alibaba.com/
>
> We found that the task_group corresponding to the problematic se
> is not in the parent task_group’s children list, indicating that
> h_load_next points to an invalid address. Consider the following
> cgroup and task hierarchy:
>
>          A
>         / \
>        /   \
>       B     E
>      / \    |
>     /   \   t2
>    C     D
>    |     |
>    t0    t1
>
> Here follows a timing sequence that may be responsible for triggering
> the problem:
>
> CPU X                   CPU Y                   CPU Z
> wakeup t0
> set list A->B->C
> traverse A->B->C
> t0 exits
> destroy C
>                         wakeup t2
>                         set list A->E           wakeup t1
>                                                 set list A->B->D
>                         traverse A->B->C
>                         panic
>
> CPU Z sets ->h_load_next list to A->B->D, but due to arm64 weaker memory
> ordering, Y may observe A->B before it sees B->D, then in this time window,
> it can traverse A->B->C and reach an invalid se.
>
> We can avoid stale pointer accesses by clearing ->h_load_next when
> unregistering cgroup.
>
> Suggested-by: Vincent Guittot <vincent.guittot@linaro.org>
> Fixes: 685207963be9 ("sched: Move h_load calculation to task_h_load()")
> Cc: <stable@vger.kernel.org>
> Co-developed-by: Cruz Zhao <CruzZhao@linux.alibaba.com>
> Signed-off-by: Cruz Zhao <CruzZhao@linux.alibaba.com>
> Signed-off-by: Peng Wang <peng_wang@linux.alibaba.com>

Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>

> ---
>  kernel/sched/fair.c | 9 +++++++++
>  1 file changed, 9 insertions(+)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index cee1793e8277..32b466605925 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -13418,6 +13418,8 @@ void unregister_fair_sched_group(struct task_group *tg)
>                 struct rq *rq = cpu_rq(cpu);
>
>                 if (se) {
> +                       struct cfs_rq *parent_cfs_rq = cfs_rq_of(se);
> +
>                         if (se->sched_delayed) {
>                                 guard(rq_lock_irqsave)(rq);
>                                 if (se->sched_delayed) {
> @@ -13427,6 +13429,13 @@ void unregister_fair_sched_group(struct task_group *tg)
>                                 list_del_leaf_cfs_rq(cfs_rq);
>                         }
>                         remove_entity_load_avg(se);
> +
> +                       /*
> +                        * Clear parent's h_load_next if it points to the
> +                        * sched_entity being freed to avoid stale pointer.
> +                        */
> +                       if (READ_ONCE(parent_cfs_rq->h_load_next) == se)
> +                               WRITE_ONCE(parent_cfs_rq->h_load_next, NULL);
>                 }
>
>                 /*
> --
> 2.27.0
>
Re: [PATCH v3] sched/fair: Clear ->h_load_next when unregistering cgroup
Posted by Peng Wang 2 months ago
On Fri, Oct 24, 2025 at 09:52:59AM +0200, Vincent Guittot wrote:
> On Fri, 24 Oct 2025 at 09:24, Peng Wang <peng_wang@linux.alibaba.com> wrote:
> >
> > An invalid pointer dereference bug was reported on arm64 cpu, and has
> > not yet been seen on x86. A partial oops looks like:
> >
> >  Call trace:
> >   update_cfs_rq_h_load+0x80/0xb0
> >   wake_affine+0x158/0x168
> >   select_task_rq_fair+0x364/0x3a8
> >   try_to_wake_up+0x154/0x648
> >   wake_up_q+0x68/0xd0
> >   futex_wake_op+0x280/0x4c8
> >   do_futex+0x198/0x1c0
> >   __arm64_sys_futex+0x11c/0x198
> >
> > Link: https://lore.kernel.org/all/20251013071820.1531295-1-CruzZhao@linux.alibaba.com/
> >
> > We found that the task_group corresponding to the problematic se
> > is not in the parent task_group’s children list, indicating that
> > h_load_next points to an invalid address. Consider the following
> > cgroup and task hierarchy:
> >
> >          A
> >         / \
> >        /   \
> >       B     E
> >      / \    |
> >     /   \   t2
> >    C     D
> >    |     |
> >    t0    t1
> >
> > Here follows a timing sequence that may be responsible for triggering
> > the problem:
> >
> > CPU X                   CPU Y                   CPU Z
> > wakeup t0
> > set list A->B->C
> > traverse A->B->C
> > t0 exits
> > destroy C
> >                         wakeup t2
> >                         set list A->E           wakeup t1
> >                                                 set list A->B->D
> >                         traverse A->B->C
> >                         panic
> >
> > CPU Z sets ->h_load_next list to A->B->D, but due to arm64 weaker memory
> > ordering, Y may observe A->B before it sees B->D, then in this time window,
> > it can traverse A->B->C and reach an invalid se.
> >
> > We can avoid stale pointer accesses by clearing ->h_load_next when
> > unregistering cgroup.
> >
> > Suggested-by: Vincent Guittot <vincent.guittot@linaro.org>
> > Fixes: 685207963be9 ("sched: Move h_load calculation to task_h_load()")
> > Cc: <stable@vger.kernel.org>
> > Co-developed-by: Cruz Zhao <CruzZhao@linux.alibaba.com>
> > Signed-off-by: Cruz Zhao <CruzZhao@linux.alibaba.com>
> > Signed-off-by: Peng Wang <peng_wang@linux.alibaba.com>
> 
> Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>

Gentle Ping

Hi, Peter and Vincent,

after applying this patch, update_cfs_rq_h_load crashing has not occurred for the past two weeks.
The patch has proven to be effective. Would you consider merging it?

> 
> > ---
> >  kernel/sched/fair.c | 9 +++++++++
> >  1 file changed, 9 insertions(+)
> >
> > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> > index cee1793e8277..32b466605925 100644
> > --- a/kernel/sched/fair.c
> > +++ b/kernel/sched/fair.c
> > @@ -13418,6 +13418,8 @@ void unregister_fair_sched_group(struct task_group *tg)
> >                 struct rq *rq = cpu_rq(cpu);
> >
> >                 if (se) {
> > +                       struct cfs_rq *parent_cfs_rq = cfs_rq_of(se);
> > +
> >                         if (se->sched_delayed) {
> >                                 guard(rq_lock_irqsave)(rq);
> >                                 if (se->sched_delayed) {
> > @@ -13427,6 +13429,13 @@ void unregister_fair_sched_group(struct task_group *tg)
> >                                 list_del_leaf_cfs_rq(cfs_rq);
> >                         }
> >                         remove_entity_load_avg(se);
> > +
> > +                       /*
> > +                        * Clear parent's h_load_next if it points to the
> > +                        * sched_entity being freed to avoid stale pointer.
> > +                        */
> > +                       if (READ_ONCE(parent_cfs_rq->h_load_next) == se)
> > +                               WRITE_ONCE(parent_cfs_rq->h_load_next, NULL);
> >                 }
> >
> >                 /*
> > --
> > 2.27.0
> >