[PATCH] mm: memcontrol: fix NULL pointer deref in high_work_func() on dying memcg

[PATCH] mm: memcontrol: fix NULL pointer deref in high_work_func() on dying memcg

[T.J. Mercier]

When memory.high is exceeded in non-task context, try_charge_memcg()
schedules memcg->high_work without taking a CSS reference on the memcg,
and high_work_func() invokes reclaim_high() without pinning the memcg.

Before commit f1cf8d2f36dc ("mm: memcontrol: eliminate the problem of
dying memory cgroup for LRU folios"), memory usage above memory.high
kept the memcg's refcount non-zero. With reparenting, folios and objcgs
charged to a child memcg are reparented to its parent in
mem_cgroup_css_offline(), leaving the offlined child's memory usage
permanently above its memory.high even after its last reference is
dropped.

cancel_work_sync(&memcg->high_work) only runs at the end of teardown in
mem_cgroup_css_free(), so high_work_func() can start or still be running
reclaim_high() after mem_cgroup_css_released() or shrink_many() has
called lru_gen_release_memcg() and unhashed lruvec->lrugen.list. This
causes lru_gen_rotate_memcg() to dereference a NULL pprev pointer.

Fix this by acquiring a reference with css_tryget_online() in
high_work_func() before calling reclaim_high(), and by resetting
memory.high and swap.high to PAGE_COUNTER_MAX in
mem_cgroup_css_offline() so that charges via references on an offlined
memcg do not trigger high_work on the dead child or skip checking live
ancestors in try_charge_memcg().

Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] SMP KASAN NOPTI
KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
CPU: 1 UID: 0 PID: 27 Comm: kworker/1:0 Tainted: G    B   W           7.3.0-rc5-g2bba28e98578 #284 PREEMPT(full) <- Taint from lru_gen_rotate_memcg() VM_WARN_ON_ONCE
Tainted: [B]=BAD_PAGE, [W]=WARN
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014
Workqueue: events high_work_func
RIP: 0010:lru_gen_rotate_memcg+0x1a3/0xe90
Code: fd 7f 09 45 84 ed 0f 85 64 0c 00 00 48 89 cf c6 83 6a 07 00 00 00 48 c1 ef 03 88 83 69 07 00 00 48 b8 00 00 00 00 00 fc ff df <80> 3c 07 00 0f 85 ec 0b 00 00 48 89 31 40 f6 c6 01 0f 85 4e 00
RSP: 0018:ffa00000001ef4c8 EFLAGS: 00010046
RAX: dffffc0000000000 RBX: ff1100000779e440 RCX: 0000000000000000
RDX: 0000000000000001 RSI: ff1100000779b9b0 RDI: 0000000000000000
RBP: ff110000bffd8e40 R08: 0000000000000000 R09: ff1100000779ebb8
R10: ff1100000779ebb0 R11: 0000000000000246 R12: 0000000000000000
R13: 0000000000000000 R14: ffa00000001efb30 R15: 0000000000000002
FS:  0000000000000000(0000) GS:ff1100011c0e7000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000000000251ac88 CR3: 0000000009d6c000 CR4: 0000000000751ef0
PKRU: 55555554
Call Trace:
 <TASK>
 ? read_ctrl_pos+0x22f/0x3f0
 shrink_lruvec+0x16cb/0x1b80
 ? ret_from_fork_asm+0x1a/0x30
 ? lapic_next_event+0x15/0x20
 ? clockevents_program_event+0x2bb/0x6f0
 ? lapic_next_event+0x15/0x20
 ? __pfx_shrink_lruvec+0x10/0x10
 ? __pfx_clockevents_program_event+0x10/0x10
 ? _raw_spin_lock+0x84/0xe0
 ? __pfx__raw_spin_lock+0x10/0x10
 ? kasan_save_stack+0x30/0x50
 ? psi_group_change+0x381/0x740
 ? __pfx_sched_clock_cpu+0x10/0x10
 ? save_fpregs_to_fpstate+0xc4/0x2c0
 ? finish_task_switch.isra.0+0x1de/0xac0
 ? __schedule+0xf62/0x42c0
 ? __pfx___schedule+0x10/0x10
 ? __pfx___irq_work_queue_local+0x10/0x10
 ? shrink_node+0x626/0x31e0
 shrink_node+0x626/0x31e0
 ? ring_buffer_unlock_commit+0x11d/0x5c0
 ? kswapd_clear_hopeless+0xa0/0x150
 ? __pfx_shrink_node+0x10/0x10
 ? 0xffffffffc0000095
 do_try_to_free_pages+0x255/0x13b0
 ? ring_buffer_unlock_commit+0x11d/0x5c0
 ? reclaim_high+0x10a/0x1b0
 try_to_free_mem_cgroup_pages+0x1f9/0x5a0
 ? __pfx_try_to_free_mem_cgroup_pages+0x10/0x10
 ? irqentry_exit+0xc6/0x670
 reclaim_high+0x10a/0x1b0
 ? __pfx_reclaim_high+0x10/0x10
 ? process_one_work+0x5ff/0x1030
 ? __pfx_high_work_func+0x10/0x10
 process_one_work+0x6e2/0x1030
 ? __pfx___schedule+0x10/0x10
 ? __pfx_process_one_work+0x10/0x10
 worker_thread+0x422/0xbb0
 ? __pfx_worker_thread+0x10/0x10
 kthread+0x2cd/0x3a0
 ? recalc_sigpending+0x15c/0x200
 ? __pfx_kthread+0x10/0x10
 ret_from_fork+0x368/0x590
 ? __pfx_ret_from_fork+0x10/0x10
 ? __switch_to+0x588/0xf50
 ? __pfx_kthread+0x10/0x10
 ret_from_fork_asm+0x1a/0x30
 </TASK>

Fixes: f1cf8d2f36dc ("mm: memcontrol: eliminate the problem of dying memory cgroup for LRU folios")
Cc: stable@vger.kernel.org
Signed-off-by: T.J. Mercier <tjmercier@google.com>
---
 mm/memcontrol.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a05d9a8baa1b..84f4a8fd4d16 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2457,7 +2457,10 @@ static void high_work_func(struct work_struct *work)
 	struct mem_cgroup *memcg;
 
 	memcg = container_of(work, struct mem_cgroup, high_work);
+	if (!css_tryget_online(&memcg->css))
+		return;
 	reclaim_high(memcg, MEMCG_CHARGE_BATCH, GFP_KERNEL);
+	css_put(&memcg->css);
 }
 
 static void high_irq_work_func(struct irq_work *work)
@@ -4463,6 +4466,8 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 
 	page_counter_set_min(&memcg->memory, 0);
 	page_counter_set_low(&memcg->memory, 0);
+	page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX);
+	page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX);
 
 	zswap_memcg_offline_cleanup(memcg);
 

base-commit: 2bba28e98578de622ef307d00875aa8f8bca3d10
-- 
2.56.0.257.gf7497c7d27-goog

Re: [PATCH] mm: memcontrol: fix NULL pointer deref in high_work_func() on dying memcg

[Michal Hocko]

On Fri 23-10-26 15:23:13, T.J. Mercier wrote:
[...]
> ---
>  mm/memcontrol.c | 5 +++++
>  1 file changed, 5 insertions(+)
> 
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index a05d9a8baa1b..84f4a8fd4d16 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -2457,7 +2457,10 @@ static void high_work_func(struct work_struct *work)
>  	struct mem_cgroup *memcg;
>  
>  	memcg = container_of(work, struct mem_cgroup, high_work);
> +	if (!css_tryget_online(&memcg->css))
> +		return;
>  	reclaim_high(memcg, MEMCG_CHARGE_BATCH, GFP_KERNEL);
> +	css_put(&memcg->css);
>  }

OK.
  
>  static void high_irq_work_func(struct irq_work *work)
> @@ -4463,6 +4466,8 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
>  
>  	page_counter_set_min(&memcg->memory, 0);
>  	page_counter_set_low(&memcg->memory, 0);
> +	page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX);
> +	page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX);
>  
>  	zswap_memcg_offline_cleanup(memcg);

Should we simply disable_work_sync when the memcg is going to be
released instead (mem_cgroup_css_released)? That should both prevent
the run reclaim_high during the memcg shut down and and also avoid
plaing with limits to work around.

-- 
Michal Hocko
SUSE Labs

Re: [PATCH] mm: memcontrol: fix NULL pointer deref in high_work_func() on dying memcg

[T.J. Mercier]

On Mon, Oct 26, 2026 at 6:25 AM Michal Hocko <mhocko@suse.com> wrote:
>
> On Fri 23-10-26 15:23:13, T.J. Mercier wrote:
> [...]
> > ---
> >  mm/memcontrol.c | 5 +++++
> >  1 file changed, 5 insertions(+)
> >
> > diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> > index a05d9a8baa1b..84f4a8fd4d16 100644
> > --- a/mm/memcontrol.c
> > +++ b/mm/memcontrol.c
> > @@ -2457,7 +2457,10 @@ static void high_work_func(struct work_struct *work)
> >       struct mem_cgroup *memcg;
> >
> >       memcg = container_of(work, struct mem_cgroup, high_work);
> > +     if (!css_tryget_online(&memcg->css))
> > +             return;
> >       reclaim_high(memcg, MEMCG_CHARGE_BATCH, GFP_KERNEL);
> > +     css_put(&memcg->css);
> >  }
>
> OK.
>
> >  static void high_irq_work_func(struct irq_work *work)
> > @@ -4463,6 +4466,8 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
> >
> >       page_counter_set_min(&memcg->memory, 0);
> >       page_counter_set_low(&memcg->memory, 0);
> > +     page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX);
> > +     page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX);
> >
> >       zswap_memcg_offline_cleanup(memcg);
>
> Should we simply disable_work_sync when the memcg is going to be
> released instead (mem_cgroup_css_released)? That should both prevent
> the run reclaim_high during the memcg shut down and and also avoid
> plaing with limits to work around.

Hi Michal,

Unfortunately that won't work for shrink_many() ->
!mem_cgroup_tryget() -> lru_gen_release_memcg() which can occur before
mem_cgroup_css_released() runs. (mem_cgroup_css_released() happens
through the cgroup_release_wq.)

The high limit reset is also needed for targeting live ancestors above
the offlined child in try_charge_memcg(). Without the resets,
high_work is never attempted on them since it gets dropped when
attempted on the offlined child due to the first hunk, and
try_charge_memcg() breaks out of the loop.

Shakeel's remote charging patch
(https://lore.kernel.org/all/20261010210957.1350874-4-shakeel.butt@linux.dev/)
sends remote charges through high_work too, so without the resets
those would lose ancestor reclaim the same way. Before that patch not
performing the resets means reclaim_high() runs unnecesarily against
current's memcg (not the remote memcg above memory.high).

Re: [PATCH] mm: memcontrol: fix NULL pointer deref in high_work_func() on dying memcg

[Michal Hocko]

On Mon 26-10-26 11:01:51, T.J. Mercier wrote:
> On Mon, Oct 26, 2026 at 6:25 AM Michal Hocko <mhocko@suse.com> wrote:
> >
> > On Fri 23-10-26 15:23:13, T.J. Mercier wrote:
> > [...]
> > > ---
> > >  mm/memcontrol.c | 5 +++++
> > >  1 file changed, 5 insertions(+)
> > >
> > > diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> > > index a05d9a8baa1b..84f4a8fd4d16 100644
> > > --- a/mm/memcontrol.c
> > > +++ b/mm/memcontrol.c
> > > @@ -2457,7 +2457,10 @@ static void high_work_func(struct work_struct *work)
> > >       struct mem_cgroup *memcg;
> > >
> > >       memcg = container_of(work, struct mem_cgroup, high_work);
> > > +     if (!css_tryget_online(&memcg->css))
> > > +             return;
> > >       reclaim_high(memcg, MEMCG_CHARGE_BATCH, GFP_KERNEL);
> > > +     css_put(&memcg->css);
> > >  }
> >
> > OK.
> >
> > >  static void high_irq_work_func(struct irq_work *work)
> > > @@ -4463,6 +4466,8 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
> > >
> > >       page_counter_set_min(&memcg->memory, 0);
> > >       page_counter_set_low(&memcg->memory, 0);
> > > +     page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX);
> > > +     page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX);
> > >
> > >       zswap_memcg_offline_cleanup(memcg);
> >
> > Should we simply disable_work_sync when the memcg is going to be
> > released instead (mem_cgroup_css_released)? That should both prevent
> > the run reclaim_high during the memcg shut down and and also avoid
> > plaing with limits to work around.
> 
> Hi Michal,
> 
> Unfortunately that won't work for shrink_many() ->
> !mem_cgroup_tryget() -> lru_gen_release_memcg() which can occur before
> mem_cgroup_css_released() runs. (mem_cgroup_css_released() happens
> through the cgroup_release_wq.)

I do not follow. Could you explain why please?

> The high limit reset is also needed for targeting live ancestors above
> the offlined child in try_charge_memcg(). Without the resets,
> high_work is never attempted on them since it gets dropped when
> attempted on the offlined child due to the first hunk, and
> try_charge_memcg() breaks out of the loop.

I must be missing something really obvious here because I really do not
follow you here too. So we are offlining a memcg. We need to coordinate
memory reclaim with the memcg tear down, right? For the high reclaim we
can achieve this synchronization through disable_work_sync in
mem_cgroup_css_offline. For a synchronous high memory reclaim we do not
have such means but we are keeping a memcg reference which makes the
lifetime well defined. If you reset counter you might help to bail out
early(ier) but that shouldn't be necessary from a correctness POV as it
doesn't provide any explicit synchronization.

> Shakeel's remote charging patch
> (https://lore.kernel.org/all/20261010210957.1350874-4-shakeel.butt@linux.dev/)
> sends remote charges through high_work too, so without the resets
> those would lose ancestor reclaim the same way. Before that patch not
> performing the resets means reclaim_high() runs unnecesarily against
> current's memcg (not the remote memcg above memory.high).

-- 
Michal Hocko
SUSE Labs

Re: [PATCH] mm: memcontrol: fix NULL pointer deref in high_work_func() on dying memcg

[T.J. Mercier]

On Tue, Oct 27, 2026 at 2:41 AM Michal Hocko <mhocko@suse.com> wrote:
>
> On Mon 26-10-26 11:01:51, T.J. Mercier wrote:
> > On Mon, Oct 26, 2026 at 6:25 AM Michal Hocko <mhocko@suse.com> wrote:
> > >
> > > On Fri 23-10-26 15:23:13, T.J. Mercier wrote:
> > > [...]
> > > > ---
> > > >  mm/memcontrol.c | 5 +++++
> > > >  1 file changed, 5 insertions(+)
> > > >
> > > > diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> > > > index a05d9a8baa1b..84f4a8fd4d16 100644
> > > > --- a/mm/memcontrol.c
> > > > +++ b/mm/memcontrol.c
> > > > @@ -2457,7 +2457,10 @@ static void high_work_func(struct work_struct *work)
> > > >       struct mem_cgroup *memcg;
> > > >
> > > >       memcg = container_of(work, struct mem_cgroup, high_work);
> > > > +     if (!css_tryget_online(&memcg->css))
> > > > +             return;
> > > >       reclaim_high(memcg, MEMCG_CHARGE_BATCH, GFP_KERNEL);
> > > > +     css_put(&memcg->css);
> > > >  }
> > >
> > > OK.
> > >
> > > >  static void high_irq_work_func(struct irq_work *work)
> > > > @@ -4463,6 +4466,8 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
> > > >
> > > >       page_counter_set_min(&memcg->memory, 0);
> > > >       page_counter_set_low(&memcg->memory, 0);
> > > > +     page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX);
> > > > +     page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX);
> > > >
> > > >       zswap_memcg_offline_cleanup(memcg);
> > >
> > > Should we simply disable_work_sync when the memcg is going to be
> > > released instead (mem_cgroup_css_released)? That should both prevent
> > > the run reclaim_high during the memcg shut down and and also avoid
> > > plaing with limits to work around.
> >
> > Hi Michal,
> >
> > Unfortunately that won't work for shrink_many() ->
> > !mem_cgroup_tryget() -> lru_gen_release_memcg() which can occur before
> > mem_cgroup_css_released() runs. (mem_cgroup_css_released() happens
> > through the cgroup_release_wq.)
>
> I do not follow. Could you explain why please?

Calling disable_work_sync in mem_cgroup_css_released() is too late. As
soon as the memcg refcount drops to 0, mem_cgroup_tryget() starts
failing, and lru_gen_release_memcg() can run.
mem_cgroup_css_released() runs async via css_release() ->
css_release_work_fn().

high_work_func() doesn't hold a memcg reference, so the memcg refcount
can hit 0 while high_work_func() is already running, or waiting to
run.

high_work_func()                    kswapd
reclaim_high(memcg)
 try_to_free_mem_cgroup_pages()
                                    <memcg refcount hits 0>
                                    shrink_many()
                                     mem_cgroup_tryget() fails
                                     lru_gen_release_memcg()
  shrink_lruvec()
   lru_gen_rotate_memcg()
    NULL pprev deref

... later, on cgroup_release_wq:
css_release_work_fn()
 mem_cgroup_css_released()
  disable_work_sync()   /* too late */

> > The high limit reset is also needed for targeting live ancestors above
> > the offlined child in try_charge_memcg(). Without the resets,
> > high_work is never attempted on them since it gets dropped when
> > attempted on the offlined child due to the first hunk, and
> > try_charge_memcg() breaks out of the loop.
>
> I must be missing something really obvious here because I really do not
> follow you here too. So we are offlining a memcg. We need to coordinate
> memory reclaim with the memcg tear down, right? For the high reclaim we
> can achieve this synchronization through disable_work_sync in
> mem_cgroup_css_offline.

We could call disable_work_sync() in mem_cgroup_css_offline(), but
that waits until high_work_func() is done and it could be performing
reclaim. mem_cgroup_css_offline() runs under the cgroup_mutex, and
cgroup_mutex contention is already bad enough. I don't want to add to
it. It would also block the rest of the cgroup_offline_wq.

Every other caller of try_to_free_mem_cgroup_pages() keeps the memcg
alive. high_work_func() should too.

> For a synchronous high memory reclaim we do not
> have such means but we are keeping a memcg reference which makes the
> lifetime well defined. If you reset counter you might help to bail out
> early(ier) but that shouldn't be necessary from a correctness POV as it
> doesn't provide any explicit synchronization.

The high resets are not for synchronization. They are for performing
high_work on the correct live memcg if necessary.

Even if we take the disable_work_sync() approach, we still need the
high limit resets. Any try_charge_memcg() on that offlined memcg would
break out of this loop too early at schedule_work(&memcg->high_work)
(a no-op), and potentially skip calling it on any of the parents.

do {
        bool mem_high, swap_high;
        mem_high = page_counter_read(&memcg->memory) >
                READ_ONCE(memcg->memory.high);
        swap_high = page_counter_read(&memcg->swap) >
                READ_ONCE(memcg->swap.high);

        /* Don't bother a random interrupted task */
        if (!in_task()) {
                if (mem_high) {
                        if (allow_spinning)
                                schedule_work(&memcg->high_work);
                        else
                                irq_work_queue(&memcg->high_irq_work);
                        break;
                }
                continue;
        }
...
} while ((memcg = parent_mem_cgroup(memcg)));


> > Shakeel's remote charging patch
> > (https://lore.kernel.org/all/20261010210957.1350874-4-shakeel.butt@linux.dev/)
> > sends remote charges through high_work too, so without the resets
> > those would lose ancestor reclaim the same way. Before that patch not
> > performing the resets means reclaim_high() runs unnecesarily against
> > current's memcg (not the remote memcg above memory.high).
>
> --
> Michal Hocko
> SUSE Labs

Re: [PATCH] mm: memcontrol: fix NULL pointer deref in high_work_func() on dying memcg

[Shakeel Butt]

On Tue, Oct 27, 2026 at 10:28:22AM -0700, T.J. Mercier wrote:
> On Tue, Oct 27, 2026 at 2:41 AM Michal Hocko <mhocko@suse.com> wrote:
> >
> > On Mon 26-10-26 11:01:51, T.J. Mercier wrote:
> > > On Mon, Oct 26, 2026 at 6:25 AM Michal Hocko <mhocko@suse.com> wrote:
> > > >
[...]
> > > > On Fri 23-10-26 15:23:13, T.J. Mercier wrote:
> > I must be missing something really obvious here because I really do not
> > follow you here too. So we are offlining a memcg. We need to coordinate
> > memory reclaim with the memcg tear down, right? For the high reclaim we
> > can achieve this synchronization through disable_work_sync in
> > mem_cgroup_css_offline.
> 
> We could call disable_work_sync() in mem_cgroup_css_offline(), but
> that waits until high_work_func() is done and it could be performing
> reclaim. mem_cgroup_css_offline() runs under the cgroup_mutex, and
> cgroup_mutex contention is already bad enough. I don't want to add to
> it. It would also block the rest of the cgroup_offline_wq.

+1, let's not add more potential contention sources for cgroup_mutex.

Re: [PATCH] mm: memcontrol: fix NULL pointer deref in high_work_func() on dying memcg

[Muchun Song]

> On Oct 24, 2026, at 06:23, T.J. Mercier <tjmercier@google.com> wrote:
> 
> When memory.high is exceeded in non-task context, try_charge_memcg()
> schedules memcg->high_work without taking a CSS reference on the memcg,
> and high_work_func() invokes reclaim_high() without pinning the memcg.
> 
> Before commit f1cf8d2f36dc ("mm: memcontrol: eliminate the problem of
> dying memory cgroup for LRU folios"), memory usage above memory.high
> kept the memcg's refcount non-zero. With reparenting, folios and objcgs
> charged to a child memcg are reparented to its parent in
> mem_cgroup_css_offline(), leaving the offlined child's memory usage
> permanently above its memory.high even after its last reference is
> dropped.
> 
> cancel_work_sync(&memcg->high_work) only runs at the end of teardown in
> mem_cgroup_css_free(), so high_work_func() can start or still be running
> reclaim_high() after mem_cgroup_css_released() or shrink_many() has
> called lru_gen_release_memcg() and unhashed lruvec->lrugen.list. This
> causes lru_gen_rotate_memcg() to dereference a NULL pprev pointer.
> 
> Fix this by acquiring a reference with css_tryget_online() in
> high_work_func() before calling reclaim_high(), and by resetting
> memory.high and swap.high to PAGE_COUNTER_MAX in
> mem_cgroup_css_offline() so that charges via references on an offlined
> memcg do not trigger high_work on the dead child or skip checking live
> ancestors in try_charge_memcg().
> 
> Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] SMP KASAN NOPTI
> KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
> CPU: 1 UID: 0 PID: 27 Comm: kworker/1:0 Tainted: G    B   W           7.3.0-rc5-g2bba28e98578 #284 PREEMPT(full) <- Taint from lru_gen_rotate_memcg() VM_WARN_ON_ONCE
> Tainted: [B]=BAD_PAGE, [W]=WARN
> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014
> Workqueue: events high_work_func
> RIP: 0010:lru_gen_rotate_memcg+0x1a3/0xe90
> Code: fd 7f 09 45 84 ed 0f 85 64 0c 00 00 48 89 cf c6 83 6a 07 00 00 00 48 c1 ef 03 88 83 69 07 00 00 48 b8 00 00 00 00 00 fc ff df <80> 3c 07 00 0f 85 ec 0b 00 00 48 89 31 40 f6 c6 01 0f 85 4e 00
> RSP: 0018:ffa00000001ef4c8 EFLAGS: 00010046
> RAX: dffffc0000000000 RBX: ff1100000779e440 RCX: 0000000000000000
> RDX: 0000000000000001 RSI: ff1100000779b9b0 RDI: 0000000000000000
> RBP: ff110000bffd8e40 R08: 0000000000000000 R09: ff1100000779ebb8
> R10: ff1100000779ebb0 R11: 0000000000000246 R12: 0000000000000000
> R13: 0000000000000000 R14: ffa00000001efb30 R15: 0000000000000002
> FS:  0000000000000000(0000) GS:ff1100011c0e7000(0000) knlGS:0000000000000000
> CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> CR2: 000000000251ac88 CR3: 0000000009d6c000 CR4: 0000000000751ef0
> PKRU: 55555554
> Call Trace:
> <TASK>
> ? read_ctrl_pos+0x22f/0x3f0
> shrink_lruvec+0x16cb/0x1b80
> ? ret_from_fork_asm+0x1a/0x30
> ? lapic_next_event+0x15/0x20
> ? clockevents_program_event+0x2bb/0x6f0
> ? lapic_next_event+0x15/0x20
> ? __pfx_shrink_lruvec+0x10/0x10
> ? __pfx_clockevents_program_event+0x10/0x10
> ? _raw_spin_lock+0x84/0xe0
> ? __pfx__raw_spin_lock+0x10/0x10
> ? kasan_save_stack+0x30/0x50
> ? psi_group_change+0x381/0x740
> ? __pfx_sched_clock_cpu+0x10/0x10
> ? save_fpregs_to_fpstate+0xc4/0x2c0
> ? finish_task_switch.isra.0+0x1de/0xac0
> ? __schedule+0xf62/0x42c0
> ? __pfx___schedule+0x10/0x10
> ? __pfx___irq_work_queue_local+0x10/0x10
> ? shrink_node+0x626/0x31e0
> shrink_node+0x626/0x31e0
> ? ring_buffer_unlock_commit+0x11d/0x5c0
> ? kswapd_clear_hopeless+0xa0/0x150
> ? __pfx_shrink_node+0x10/0x10
> ? 0xffffffffc0000095
> do_try_to_free_pages+0x255/0x13b0
> ? ring_buffer_unlock_commit+0x11d/0x5c0
> ? reclaim_high+0x10a/0x1b0
> try_to_free_mem_cgroup_pages+0x1f9/0x5a0
> ? __pfx_try_to_free_mem_cgroup_pages+0x10/0x10
> ? irqentry_exit+0xc6/0x670
> reclaim_high+0x10a/0x1b0
> ? __pfx_reclaim_high+0x10/0x10
> ? process_one_work+0x5ff/0x1030
> ? __pfx_high_work_func+0x10/0x10
> process_one_work+0x6e2/0x1030
> ? __pfx___schedule+0x10/0x10
> ? __pfx_process_one_work+0x10/0x10
> worker_thread+0x422/0xbb0
> ? __pfx_worker_thread+0x10/0x10
> kthread+0x2cd/0x3a0
> ? recalc_sigpending+0x15c/0x200
> ? __pfx_kthread+0x10/0x10
> ret_from_fork+0x368/0x590
> ? __pfx_ret_from_fork+0x10/0x10
> ? __switch_to+0x588/0xf50
> ? __pfx_kthread+0x10/0x10
> ret_from_fork_asm+0x1a/0x30
> </TASK>
> 
> Fixes: f1cf8d2f36dc ("mm: memcontrol: eliminate the problem of dying memory cgroup for LRU folios")

Hi T.J.,

Thanks for fixing this.

I have one question about the Fixes tag.

The changelog says that, before f1cf8d2f36dc, memory usage above
memory.high kept the memcg reference count non-zero. This is true for
LRU folios: before that commit, each charged LRU folio held a CSS
reference until it was uncharged.

However, I wonder whether objcg-based kmem already provided a reachable
path before f1cf8d2f36dc.

In particular, BPF alloc_bulk() mostly runs from irq_work. It obtains a
temporary memcg reference from a persistent objcg, uses set_active_memcg()
while performing __GFP_ACCOUNT allocations, and drops the temporary
reference after the allocation. The charge can therefore queue
memcg->high_work in non-task context without transferring a CSS
reference to the work item.

If this races with memcg offlining, objcg reparenting can redirect the
objcg to the parent while the old child's page-counter usage remains
above memory.high. Once the temporary CSS reference is dropped,
mem_cgroup_css_released() can call lru_gen_release_memcg() before the
queued high_work runs. The worker can then enter reclaim_high() and
rotate an already removed lrugen.list.

This path appears to have all the required pieces after:

  e4dde56cd208 ("mm: multi-gen LRU: per-node lru_gen_folio lists")

Commit 6867c7a33206 later changed the release operation to
hlist_nulls_del_init_rcu(), which explains the exact NULL pprev seen in
the reported crash. Before that, the same invalid second deletion would
instead encounter LIST_POISON2.

So f1cf8d2f36dc clearly broadens the problem to ordinary LRU folios, but
I am not very sure it is the first commit after which the underlying race is
reachable.

Is there an additional lifetime guarantee that prevents the pre-f1cf
objcg/kmem path above? If no, would the following be more appropriate?

Fixes: e4dde56cd208 ("mm: multi-gen LRU: per-node lru_gen_folio lists")

Thanks,
Muchun

Re: [PATCH] mm: memcontrol: fix NULL pointer deref in high_work_func() on dying memcg

[T.J. Mercier]

On Mon, Oct 26, 2026 at 7:42 PM Muchun Song <muchun.song@linux.dev> wrote:
>
>
>
> > On Oct 24, 2026, at 06:23, T.J. Mercier <tjmercier@google.com> wrote:
> >
> > When memory.high is exceeded in non-task context, try_charge_memcg()
> > schedules memcg->high_work without taking a CSS reference on the memcg,
> > and high_work_func() invokes reclaim_high() without pinning the memcg.
> >
> > Before commit f1cf8d2f36dc ("mm: memcontrol: eliminate the problem of
> > dying memory cgroup for LRU folios"), memory usage above memory.high
> > kept the memcg's refcount non-zero. With reparenting, folios and objcgs
> > charged to a child memcg are reparented to its parent in
> > mem_cgroup_css_offline(), leaving the offlined child's memory usage
> > permanently above its memory.high even after its last reference is
> > dropped.
> >
> > cancel_work_sync(&memcg->high_work) only runs at the end of teardown in
> > mem_cgroup_css_free(), so high_work_func() can start or still be running
> > reclaim_high() after mem_cgroup_css_released() or shrink_many() has
> > called lru_gen_release_memcg() and unhashed lruvec->lrugen.list. This
> > causes lru_gen_rotate_memcg() to dereference a NULL pprev pointer.
> >
> > Fix this by acquiring a reference with css_tryget_online() in
> > high_work_func() before calling reclaim_high(), and by resetting
> > memory.high and swap.high to PAGE_COUNTER_MAX in
> > mem_cgroup_css_offline() so that charges via references on an offlined
> > memcg do not trigger high_work on the dead child or skip checking live
> > ancestors in try_charge_memcg().
> >
> > Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] SMP KASAN NOPTI
> > KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
> > CPU: 1 UID: 0 PID: 27 Comm: kworker/1:0 Tainted: G    B   W           7.3.0-rc5-g2bba28e98578 #284 PREEMPT(full) <- Taint from lru_gen_rotate_memcg() VM_WARN_ON_ONCE
> > Tainted: [B]=BAD_PAGE, [W]=WARN
> > Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014
> > Workqueue: events high_work_func
> > RIP: 0010:lru_gen_rotate_memcg+0x1a3/0xe90
> > Code: fd 7f 09 45 84 ed 0f 85 64 0c 00 00 48 89 cf c6 83 6a 07 00 00 00 48 c1 ef 03 88 83 69 07 00 00 48 b8 00 00 00 00 00 fc ff df <80> 3c 07 00 0f 85 ec 0b 00 00 48 89 31 40 f6 c6 01 0f 85 4e 00
> > RSP: 0018:ffa00000001ef4c8 EFLAGS: 00010046
> > RAX: dffffc0000000000 RBX: ff1100000779e440 RCX: 0000000000000000
> > RDX: 0000000000000001 RSI: ff1100000779b9b0 RDI: 0000000000000000
> > RBP: ff110000bffd8e40 R08: 0000000000000000 R09: ff1100000779ebb8
> > R10: ff1100000779ebb0 R11: 0000000000000246 R12: 0000000000000000
> > R13: 0000000000000000 R14: ffa00000001efb30 R15: 0000000000000002
> > FS:  0000000000000000(0000) GS:ff1100011c0e7000(0000) knlGS:0000000000000000
> > CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> > CR2: 000000000251ac88 CR3: 0000000009d6c000 CR4: 0000000000751ef0
> > PKRU: 55555554
> > Call Trace:
> > <TASK>
> > ? read_ctrl_pos+0x22f/0x3f0
> > shrink_lruvec+0x16cb/0x1b80
> > ? ret_from_fork_asm+0x1a/0x30
> > ? lapic_next_event+0x15/0x20
> > ? clockevents_program_event+0x2bb/0x6f0
> > ? lapic_next_event+0x15/0x20
> > ? __pfx_shrink_lruvec+0x10/0x10
> > ? __pfx_clockevents_program_event+0x10/0x10
> > ? _raw_spin_lock+0x84/0xe0
> > ? __pfx__raw_spin_lock+0x10/0x10
> > ? kasan_save_stack+0x30/0x50
> > ? psi_group_change+0x381/0x740
> > ? __pfx_sched_clock_cpu+0x10/0x10
> > ? save_fpregs_to_fpstate+0xc4/0x2c0
> > ? finish_task_switch.isra.0+0x1de/0xac0
> > ? __schedule+0xf62/0x42c0
> > ? __pfx___schedule+0x10/0x10
> > ? __pfx___irq_work_queue_local+0x10/0x10
> > ? shrink_node+0x626/0x31e0
> > shrink_node+0x626/0x31e0
> > ? ring_buffer_unlock_commit+0x11d/0x5c0
> > ? kswapd_clear_hopeless+0xa0/0x150
> > ? __pfx_shrink_node+0x10/0x10
> > ? 0xffffffffc0000095
> > do_try_to_free_pages+0x255/0x13b0
> > ? ring_buffer_unlock_commit+0x11d/0x5c0
> > ? reclaim_high+0x10a/0x1b0
> > try_to_free_mem_cgroup_pages+0x1f9/0x5a0
> > ? __pfx_try_to_free_mem_cgroup_pages+0x10/0x10
> > ? irqentry_exit+0xc6/0x670
> > reclaim_high+0x10a/0x1b0
> > ? __pfx_reclaim_high+0x10/0x10
> > ? process_one_work+0x5ff/0x1030
> > ? __pfx_high_work_func+0x10/0x10
> > process_one_work+0x6e2/0x1030
> > ? __pfx___schedule+0x10/0x10
> > ? __pfx_process_one_work+0x10/0x10
> > worker_thread+0x422/0xbb0
> > ? __pfx_worker_thread+0x10/0x10
> > kthread+0x2cd/0x3a0
> > ? recalc_sigpending+0x15c/0x200
> > ? __pfx_kthread+0x10/0x10
> > ret_from_fork+0x368/0x590
> > ? __pfx_ret_from_fork+0x10/0x10
> > ? __switch_to+0x588/0xf50
> > ? __pfx_kthread+0x10/0x10
> > ret_from_fork_asm+0x1a/0x30
> > </TASK>
> >
> > Fixes: f1cf8d2f36dc ("mm: memcontrol: eliminate the problem of dying memory cgroup for LRU folios")
>
> Hi T.J.,
>
> Thanks for fixing this.
>
> I have one question about the Fixes tag.
>
> The changelog says that, before f1cf8d2f36dc, memory usage above
> memory.high kept the memcg reference count non-zero. This is true for
> LRU folios: before that commit, each charged LRU folio held a CSS
> reference until it was uncharged.
>
> However, I wonder whether objcg-based kmem already provided a reachable
> path before f1cf8d2f36dc.
>
> In particular, BPF alloc_bulk() mostly runs from irq_work. It obtains a
> temporary memcg reference from a persistent objcg, uses set_active_memcg()
> while performing __GFP_ACCOUNT allocations, and drops the temporary
> reference after the allocation. The charge can therefore queue
> memcg->high_work in non-task context without transferring a CSS
> reference to the work item.
>
> If this races with memcg offlining, objcg reparenting can redirect the
> objcg to the parent while the old child's page-counter usage remains
> above memory.high. Once the temporary CSS reference is dropped,
> mem_cgroup_css_released() can call lru_gen_release_memcg() before the
> queued high_work runs. The worker can then enter reclaim_high() and
> rotate an already removed lrugen.list.
>
> This path appears to have all the required pieces after:
>
>   e4dde56cd208 ("mm: multi-gen LRU: per-node lru_gen_folio lists")
>
> Commit 6867c7a33206 later changed the release operation to
> hlist_nulls_del_init_rcu(), which explains the exact NULL pprev seen in
> the reported crash. Before that, the same invalid second deletion would
> instead encounter LIST_POISON2.
>
> So f1cf8d2f36dc clearly broadens the problem to ordinary LRU folios, but
> I am not very sure it is the first commit after which the underlying race is
> reachable.
>
> Is there an additional lifetime guarantee that prevents the pre-f1cf
> objcg/kmem path above? If no, would the following be more appropriate?
>
> Fixes: e4dde56cd208 ("mm: multi-gen LRU: per-node lru_gen_folio lists")
>
> Thanks,
> Muchun

Hi Muchun,

Everything you said sounds correct to me. I don't think there's
anything preventing kmem from keeping the memcg above high while the
refcount hits 0, and hitting the same problem in
lru_gen_rotate_memcg() from lru_gen_shrink_lruvec().

So using Fixes: e4dde56cd208 ("mm: multi-gen LRU: per-node
lru_gen_folio lists") sounds good to me.

Thanks,
T.J.

Re: [PATCH] mm: memcontrol: fix NULL pointer deref in high_work_func() on dying memcg

[T.J. Mercier]

On Tue, Oct 27, 2026 at 10:42 AM T.J. Mercier <tjmercier@google.com> wrote:
>
> On Mon, Oct 26, 2026 at 7:42 PM Muchun Song <muchun.song@linux.dev> wrote:
> >
> >
> >
> > > On Oct 24, 2026, at 06:23, T.J. Mercier <tjmercier@google.com> wrote:
> > >
> > > When memory.high is exceeded in non-task context, try_charge_memcg()
> > > schedules memcg->high_work without taking a CSS reference on the memcg,
> > > and high_work_func() invokes reclaim_high() without pinning the memcg.
> > >
> > > Before commit f1cf8d2f36dc ("mm: memcontrol: eliminate the problem of
> > > dying memory cgroup for LRU folios"), memory usage above memory.high
> > > kept the memcg's refcount non-zero. With reparenting, folios and objcgs
> > > charged to a child memcg are reparented to its parent in
> > > mem_cgroup_css_offline(), leaving the offlined child's memory usage
> > > permanently above its memory.high even after its last reference is
> > > dropped.
> > >
> > > cancel_work_sync(&memcg->high_work) only runs at the end of teardown in
> > > mem_cgroup_css_free(), so high_work_func() can start or still be running
> > > reclaim_high() after mem_cgroup_css_released() or shrink_many() has
> > > called lru_gen_release_memcg() and unhashed lruvec->lrugen.list. This
> > > causes lru_gen_rotate_memcg() to dereference a NULL pprev pointer.
> > >
> > > Fix this by acquiring a reference with css_tryget_online() in
> > > high_work_func() before calling reclaim_high(), and by resetting
> > > memory.high and swap.high to PAGE_COUNTER_MAX in
> > > mem_cgroup_css_offline() so that charges via references on an offlined
> > > memcg do not trigger high_work on the dead child or skip checking live
> > > ancestors in try_charge_memcg().
> > >
> > > Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] SMP KASAN NOPTI
> > > KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
> > > CPU: 1 UID: 0 PID: 27 Comm: kworker/1:0 Tainted: G    B   W           7.3.0-rc5-g2bba28e98578 #284 PREEMPT(full) <- Taint from lru_gen_rotate_memcg() VM_WARN_ON_ONCE
> > > Tainted: [B]=BAD_PAGE, [W]=WARN
> > > Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014
> > > Workqueue: events high_work_func
> > > RIP: 0010:lru_gen_rotate_memcg+0x1a3/0xe90
> > > Code: fd 7f 09 45 84 ed 0f 85 64 0c 00 00 48 89 cf c6 83 6a 07 00 00 00 48 c1 ef 03 88 83 69 07 00 00 48 b8 00 00 00 00 00 fc ff df <80> 3c 07 00 0f 85 ec 0b 00 00 48 89 31 40 f6 c6 01 0f 85 4e 00
> > > RSP: 0018:ffa00000001ef4c8 EFLAGS: 00010046
> > > RAX: dffffc0000000000 RBX: ff1100000779e440 RCX: 0000000000000000
> > > RDX: 0000000000000001 RSI: ff1100000779b9b0 RDI: 0000000000000000
> > > RBP: ff110000bffd8e40 R08: 0000000000000000 R09: ff1100000779ebb8
> > > R10: ff1100000779ebb0 R11: 0000000000000246 R12: 0000000000000000
> > > R13: 0000000000000000 R14: ffa00000001efb30 R15: 0000000000000002
> > > FS:  0000000000000000(0000) GS:ff1100011c0e7000(0000) knlGS:0000000000000000
> > > CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> > > CR2: 000000000251ac88 CR3: 0000000009d6c000 CR4: 0000000000751ef0
> > > PKRU: 55555554
> > > Call Trace:
> > > <TASK>
> > > ? read_ctrl_pos+0x22f/0x3f0
> > > shrink_lruvec+0x16cb/0x1b80
> > > ? ret_from_fork_asm+0x1a/0x30
> > > ? lapic_next_event+0x15/0x20
> > > ? clockevents_program_event+0x2bb/0x6f0
> > > ? lapic_next_event+0x15/0x20
> > > ? __pfx_shrink_lruvec+0x10/0x10
> > > ? __pfx_clockevents_program_event+0x10/0x10
> > > ? _raw_spin_lock+0x84/0xe0
> > > ? __pfx__raw_spin_lock+0x10/0x10
> > > ? kasan_save_stack+0x30/0x50
> > > ? psi_group_change+0x381/0x740
> > > ? __pfx_sched_clock_cpu+0x10/0x10
> > > ? save_fpregs_to_fpstate+0xc4/0x2c0
> > > ? finish_task_switch.isra.0+0x1de/0xac0
> > > ? __schedule+0xf62/0x42c0
> > > ? __pfx___schedule+0x10/0x10
> > > ? __pfx___irq_work_queue_local+0x10/0x10
> > > ? shrink_node+0x626/0x31e0
> > > shrink_node+0x626/0x31e0
> > > ? ring_buffer_unlock_commit+0x11d/0x5c0
> > > ? kswapd_clear_hopeless+0xa0/0x150
> > > ? __pfx_shrink_node+0x10/0x10
> > > ? 0xffffffffc0000095
> > > do_try_to_free_pages+0x255/0x13b0
> > > ? ring_buffer_unlock_commit+0x11d/0x5c0
> > > ? reclaim_high+0x10a/0x1b0
> > > try_to_free_mem_cgroup_pages+0x1f9/0x5a0
> > > ? __pfx_try_to_free_mem_cgroup_pages+0x10/0x10
> > > ? irqentry_exit+0xc6/0x670
> > > reclaim_high+0x10a/0x1b0
> > > ? __pfx_reclaim_high+0x10/0x10
> > > ? process_one_work+0x5ff/0x1030
> > > ? __pfx_high_work_func+0x10/0x10
> > > process_one_work+0x6e2/0x1030
> > > ? __pfx___schedule+0x10/0x10
> > > ? __pfx_process_one_work+0x10/0x10
> > > worker_thread+0x422/0xbb0
> > > ? __pfx_worker_thread+0x10/0x10
> > > kthread+0x2cd/0x3a0
> > > ? recalc_sigpending+0x15c/0x200
> > > ? __pfx_kthread+0x10/0x10
> > > ret_from_fork+0x368/0x590
> > > ? __pfx_ret_from_fork+0x10/0x10
> > > ? __switch_to+0x588/0xf50
> > > ? __pfx_kthread+0x10/0x10
> > > ret_from_fork_asm+0x1a/0x30
> > > </TASK>
> > >
> > > Fixes: f1cf8d2f36dc ("mm: memcontrol: eliminate the problem of dying memory cgroup for LRU folios")
> >
> > Hi T.J.,
> >
> > Thanks for fixing this.
> >
> > I have one question about the Fixes tag.
> >
> > The changelog says that, before f1cf8d2f36dc, memory usage above
> > memory.high kept the memcg reference count non-zero. This is true for
> > LRU folios: before that commit, each charged LRU folio held a CSS
> > reference until it was uncharged.
> >
> > However, I wonder whether objcg-based kmem already provided a reachable
> > path before f1cf8d2f36dc.
> >
> > In particular, BPF alloc_bulk() mostly runs from irq_work. It obtains a
> > temporary memcg reference from a persistent objcg, uses set_active_memcg()
> > while performing __GFP_ACCOUNT allocations, and drops the temporary
> > reference after the allocation. The charge can therefore queue
> > memcg->high_work in non-task context without transferring a CSS
> > reference to the work item.
> >
> > If this races with memcg offlining, objcg reparenting can redirect the
> > objcg to the parent while the old child's page-counter usage remains
> > above memory.high. Once the temporary CSS reference is dropped,
> > mem_cgroup_css_released() can call lru_gen_release_memcg() before the
> > queued high_work runs. The worker can then enter reclaim_high() and
> > rotate an already removed lrugen.list.
> >
> > This path appears to have all the required pieces after:
> >
> >   e4dde56cd208 ("mm: multi-gen LRU: per-node lru_gen_folio lists")
> >
> > Commit 6867c7a33206 later changed the release operation to
> > hlist_nulls_del_init_rcu(), which explains the exact NULL pprev seen in
> > the reported crash. Before that, the same invalid second deletion would
> > instead encounter LIST_POISON2.
> >
> > So f1cf8d2f36dc clearly broadens the problem to ordinary LRU folios, but
> > I am not very sure it is the first commit after which the underlying race is
> > reachable.
> >
> > Is there an additional lifetime guarantee that prevents the pre-f1cf
> > objcg/kmem path above? If no, would the following be more appropriate?
> >
> > Fixes: e4dde56cd208 ("mm: multi-gen LRU: per-node lru_gen_folio lists")
> >
> > Thanks,
> > Muchun
>
> Hi Muchun,
>
> Everything you said sounds correct to me. I don't think there's
> anything preventing kmem from keeping the memcg above high while the
> refcount hits 0, and hitting the same problem in
> lru_gen_rotate_memcg() from lru_gen_shrink_lruvec().
>
> So using Fixes: e4dde56cd208 ("mm: multi-gen LRU: per-node
> lru_gen_folio lists") sounds good to me.
>
> Thanks,
> T.J.

I was able to get a reproduction on e4dde56cd208. Fortunately this
patch applies cleanly on e4dde56cd208, so I expect the stable
backports to be straightforward.

general protection fault, probably for non-canonical address
0xfbd59c0000000024: 0000 [#1] PREEMPT SMP KASAN NOPTI
KASAN: maybe wild-memory-access in range [0xdead000000000120-0xdead000000000127]
CPU: 1 PID: 37 Comm: kworker/1:1 Not tainted 6.2.0-rc4-00108-ge4dde56cd208 #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS
1.17.0-debian-1.17.0-1 04/01/2014
Workqueue: events high_work_func
RIP: 0010:lru_gen_rotate_memcg+0x147/0xef0
Code: 49 c1 ea 03 41 80 3c 3a 00 0f 85 a5 09 00 00 48 89 f7 4c 8b 93
08 07 00 00 48 c1 ef 03 48 89 fa 48 bf 00 00 00 00 00 fc ff df <80> 3c
3a 00 0f 85 2a 07 00 00 4c 89 16 41 f6 c2 01 0f 85 72 00
RSP: 0018:ffa00000002a75e0 EFLAGS: 00010206
RAX: ff11000008d46701 RBX: ff11000008d46000 RCX: 0000000000000000
RDX: 1bd5a00000000024 RSI: dead000000000122 RDI: dffffc0000000000
RBP: ff110000bfe54000 R08: ff11000008d46708 R09: ff11000008d46710
R10: ff11000009a5a708 R11: 0000000000000000 R12: 0000000000000006
R13: 0000000000000004 R14: 1ff4000000054ee4 R15: 0000000000000001
FS:  0000000000000000(0000) GS:ff110000a3480000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000000 CR3: 0000000007d5c000 CR4: 0000000000751ee0
PKRU: 55555554
Call Trace:
 <TASK>
 ? reset_ctrl_pos+0x10f/0x460
 shrink_lruvec+0x19e0/0x2000
 ? kasan_set_track+0x25/0x30
 ? __kasan_slab_alloc+0x66/0x80
 ? kmem_cache_alloc+0x165/0x310
 ? __kernfs_new_node+0xd3/0x590
 ? __kernfs_create_file+0x2d/0x280
 ? sysfs_add_file_mode_ns+0x12b/0x3a0
 ? internal_create_group+0x286/0x940
 ? internal_create_groups+0x84/0x110
 ? really_probe+0x223/0x690
 ? unwind_next_frame+0xa9a/0x2040
 ? arch_stack_walk+0x7a/0x110
 ? unwind_next_frame+0xa9a/0x2040
 ? arch_stack_walk+0x7a/0x110
 ? __pfx_shrink_lruvec+0x10/0x10
 ? preempt_count_add+0x83/0x180
 ? unwind_next_frame+0xb2/0x2040
 ? unwind_next_frame+0x212/0x2040
 ? ret_from_fork+0x2c/0x50
 ? __pfx_stack_trace_consume_entry+0x10/0x10
 ? arch_stack_walk+0xa2/0x110
 ? sched_clock_local+0x132/0x210
 ? __pfx_sched_clock_local+0x10/0x10
 ? unwind_next_frame+0x212/0x2040
 ? __pfx_shrink_slab+0x10/0x10
 ? sched_clock_cpu+0x232/0x2c0
 ? __pfx_sched_clock_local+0x10/0x10
 ? __pfx_sched_clock_cpu+0x10/0x10
 ? mem_cgroup_iter+0x269/0x600
 ? vmpressure+0x30/0x3b0
 shrink_node+0xb39/0x26a0
 ? __pfx_shrink_node+0x10/0x10
 ? kasan_save_stack+0x42/0x60
 ? ring_buffer_lock_reserve+0x2fb/0xe30
 do_try_to_free_pages+0x31a/0x1880
 ? __pfx_do_try_to_free_pages+0x10/0x10
 try_to_free_mem_cgroup_pages+0x282/0x5f0
 ? try_to_free_mem_cgroup_pages+0x4/0x5f0
 ? reclaim_high.constprop.0+0x191/0x250
 ? __pfx_try_to_free_mem_cgroup_pages+0x10/0x10
 ? try_to_free_mem_cgroup_pages+0x9/0x5f0
 reclaim_high.constprop.0+0x191/0x250
 ? __pfx_reclaim_high.constprop.0+0x10/0x10
 ? __pfx_high_work_func+0x10/0x10
 process_one_work+0x641/0x1010
 worker_thread+0x424/0xec0
 ? __kthread_parkme+0x89/0x160
 ? __pfx_worker_thread+0x10/0x10
 kthread+0x26c/0x300
 ? __pfx_kthread+0x10/0x10
 ret_from_fork+0x2c/0x50
 </TASK>

Re: [PATCH] mm: memcontrol: fix NULL pointer deref in high_work_func() on dying memcg

[Muchun Song]

> On Oct 28, 2026, at 07:11, T.J. Mercier <tjmercier@google.com> wrote:
> 
> On Tue, Oct 27, 2026 at 10:42 AM T.J. Mercier <tjmercier@google.com> wrote:
>> 
>> On Mon, Oct 26, 2026 at 7:42 PM Muchun Song <muchun.song@linux.dev> wrote:
>>> 
>>> 
>>> 
>>>> On Oct 24, 2026, at 06:23, T.J. Mercier <tjmercier@google.com> wrote:
>>>> 
>>>> When memory.high is exceeded in non-task context, try_charge_memcg()
>>>> schedules memcg->high_work without taking a CSS reference on the memcg,
>>>> and high_work_func() invokes reclaim_high() without pinning the memcg.
>>>> 
>>>> Before commit f1cf8d2f36dc ("mm: memcontrol: eliminate the problem of
>>>> dying memory cgroup for LRU folios"), memory usage above memory.high
>>>> kept the memcg's refcount non-zero. With reparenting, folios and objcgs
>>>> charged to a child memcg are reparented to its parent in
>>>> mem_cgroup_css_offline(), leaving the offlined child's memory usage
>>>> permanently above its memory.high even after its last reference is
>>>> dropped.
>>>> 
>>>> cancel_work_sync(&memcg->high_work) only runs at the end of teardown in
>>>> mem_cgroup_css_free(), so high_work_func() can start or still be running
>>>> reclaim_high() after mem_cgroup_css_released() or shrink_many() has
>>>> called lru_gen_release_memcg() and unhashed lruvec->lrugen.list. This
>>>> causes lru_gen_rotate_memcg() to dereference a NULL pprev pointer.
>>>> 
>>>> Fix this by acquiring a reference with css_tryget_online() in
>>>> high_work_func() before calling reclaim_high(), and by resetting
>>>> memory.high and swap.high to PAGE_COUNTER_MAX in
>>>> mem_cgroup_css_offline() so that charges via references on an offlined
>>>> memcg do not trigger high_work on the dead child or skip checking live
>>>> ancestors in try_charge_memcg().
>>>> 
>>>> Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] SMP KASAN NOPTI
>>>> KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
>>>> CPU: 1 UID: 0 PID: 27 Comm: kworker/1:0 Tainted: G    B   W           7.3.0-rc5-g2bba28e98578 #284 PREEMPT(full) <- Taint from lru_gen_rotate_memcg() VM_WARN_ON_ONCE
>>>> Tainted: [B]=BAD_PAGE, [W]=WARN
>>>> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014
>>>> Workqueue: events high_work_func
>>>> RIP: 0010:lru_gen_rotate_memcg+0x1a3/0xe90
>>>> Code: fd 7f 09 45 84 ed 0f 85 64 0c 00 00 48 89 cf c6 83 6a 07 00 00 00 48 c1 ef 03 88 83 69 07 00 00 48 b8 00 00 00 00 00 fc ff df <80> 3c 07 00 0f 85 ec 0b 00 00 48 89 31 40 f6 c6 01 0f 85 4e 00
>>>> RSP: 0018:ffa00000001ef4c8 EFLAGS: 00010046
>>>> RAX: dffffc0000000000 RBX: ff1100000779e440 RCX: 0000000000000000
>>>> RDX: 0000000000000001 RSI: ff1100000779b9b0 RDI: 0000000000000000
>>>> RBP: ff110000bffd8e40 R08: 0000000000000000 R09: ff1100000779ebb8
>>>> R10: ff1100000779ebb0 R11: 0000000000000246 R12: 0000000000000000
>>>> R13: 0000000000000000 R14: ffa00000001efb30 R15: 0000000000000002
>>>> FS:  0000000000000000(0000) GS:ff1100011c0e7000(0000) knlGS:0000000000000000
>>>> CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
>>>> CR2: 000000000251ac88 CR3: 0000000009d6c000 CR4: 0000000000751ef0
>>>> PKRU: 55555554
>>>> Call Trace:
>>>> <TASK>
>>>> ? read_ctrl_pos+0x22f/0x3f0
>>>> shrink_lruvec+0x16cb/0x1b80
>>>> ? ret_from_fork_asm+0x1a/0x30
>>>> ? lapic_next_event+0x15/0x20
>>>> ? clockevents_program_event+0x2bb/0x6f0
>>>> ? lapic_next_event+0x15/0x20
>>>> ? __pfx_shrink_lruvec+0x10/0x10
>>>> ? __pfx_clockevents_program_event+0x10/0x10
>>>> ? _raw_spin_lock+0x84/0xe0
>>>> ? __pfx__raw_spin_lock+0x10/0x10
>>>> ? kasan_save_stack+0x30/0x50
>>>> ? psi_group_change+0x381/0x740
>>>> ? __pfx_sched_clock_cpu+0x10/0x10
>>>> ? save_fpregs_to_fpstate+0xc4/0x2c0
>>>> ? finish_task_switch.isra.0+0x1de/0xac0
>>>> ? __schedule+0xf62/0x42c0
>>>> ? __pfx___schedule+0x10/0x10
>>>> ? __pfx___irq_work_queue_local+0x10/0x10
>>>> ? shrink_node+0x626/0x31e0
>>>> shrink_node+0x626/0x31e0
>>>> ? ring_buffer_unlock_commit+0x11d/0x5c0
>>>> ? kswapd_clear_hopeless+0xa0/0x150
>>>> ? __pfx_shrink_node+0x10/0x10
>>>> ? 0xffffffffc0000095
>>>> do_try_to_free_pages+0x255/0x13b0
>>>> ? ring_buffer_unlock_commit+0x11d/0x5c0
>>>> ? reclaim_high+0x10a/0x1b0
>>>> try_to_free_mem_cgroup_pages+0x1f9/0x5a0
>>>> ? __pfx_try_to_free_mem_cgroup_pages+0x10/0x10
>>>> ? irqentry_exit+0xc6/0x670
>>>> reclaim_high+0x10a/0x1b0
>>>> ? __pfx_reclaim_high+0x10/0x10
>>>> ? process_one_work+0x5ff/0x1030
>>>> ? __pfx_high_work_func+0x10/0x10
>>>> process_one_work+0x6e2/0x1030
>>>> ? __pfx___schedule+0x10/0x10
>>>> ? __pfx_process_one_work+0x10/0x10
>>>> worker_thread+0x422/0xbb0
>>>> ? __pfx_worker_thread+0x10/0x10
>>>> kthread+0x2cd/0x3a0
>>>> ? recalc_sigpending+0x15c/0x200
>>>> ? __pfx_kthread+0x10/0x10
>>>> ret_from_fork+0x368/0x590
>>>> ? __pfx_ret_from_fork+0x10/0x10
>>>> ? __switch_to+0x588/0xf50
>>>> ? __pfx_kthread+0x10/0x10
>>>> ret_from_fork_asm+0x1a/0x30
>>>> </TASK>
>>>> 
>>>> Fixes: f1cf8d2f36dc ("mm: memcontrol: eliminate the problem of dying memory cgroup for LRU folios")
>>> 
>>> Hi T.J.,
>>> 
>>> Thanks for fixing this.
>>> 
>>> I have one question about the Fixes tag.
>>> 
>>> The changelog says that, before f1cf8d2f36dc, memory usage above
>>> memory.high kept the memcg reference count non-zero. This is true for
>>> LRU folios: before that commit, each charged LRU folio held a CSS
>>> reference until it was uncharged.
>>> 
>>> However, I wonder whether objcg-based kmem already provided a reachable
>>> path before f1cf8d2f36dc.
>>> 
>>> In particular, BPF alloc_bulk() mostly runs from irq_work. It obtains a
>>> temporary memcg reference from a persistent objcg, uses set_active_memcg()
>>> while performing __GFP_ACCOUNT allocations, and drops the temporary
>>> reference after the allocation. The charge can therefore queue
>>> memcg->high_work in non-task context without transferring a CSS
>>> reference to the work item.
>>> 
>>> If this races with memcg offlining, objcg reparenting can redirect the
>>> objcg to the parent while the old child's page-counter usage remains
>>> above memory.high. Once the temporary CSS reference is dropped,
>>> mem_cgroup_css_released() can call lru_gen_release_memcg() before the
>>> queued high_work runs. The worker can then enter reclaim_high() and
>>> rotate an already removed lrugen.list.
>>> 
>>> This path appears to have all the required pieces after:
>>> 
>>>  e4dde56cd208 ("mm: multi-gen LRU: per-node lru_gen_folio lists")
>>> 
>>> Commit 6867c7a33206 later changed the release operation to
>>> hlist_nulls_del_init_rcu(), which explains the exact NULL pprev seen in
>>> the reported crash. Before that, the same invalid second deletion would
>>> instead encounter LIST_POISON2.
>>> 
>>> So f1cf8d2f36dc clearly broadens the problem to ordinary LRU folios, but
>>> I am not very sure it is the first commit after which the underlying race is
>>> reachable.
>>> 
>>> Is there an additional lifetime guarantee that prevents the pre-f1cf
>>> objcg/kmem path above? If no, would the following be more appropriate?
>>> 
>>> Fixes: e4dde56cd208 ("mm: multi-gen LRU: per-node lru_gen_folio lists")
>>> 
>>> Thanks,
>>> Muchun
>> 
>> Hi Muchun,
>> 
>> Everything you said sounds correct to me. I don't think there's
>> anything preventing kmem from keeping the memcg above high while the
>> refcount hits 0, and hitting the same problem in
>> lru_gen_rotate_memcg() from lru_gen_shrink_lruvec().
>> 
>> So using Fixes: e4dde56cd208 ("mm: multi-gen LRU: per-node
>> lru_gen_folio lists") sounds good to me.
>> 
>> Thanks,
>> T.J.
> 
> I was able to get a reproduction on e4dde56cd208. Fortunately this
> patch applies cleanly on e4dde56cd208, so I expect the stable
> backports to be straightforward.

Excellent job. Yeah, we need this backported.

Thanks,
Muchun

> 
> general protection fault, probably for non-canonical address
> 0xfbd59c0000000024: 0000 [#1] PREEMPT SMP KASAN NOPTI
> KASAN: maybe wild-memory-access in range [0xdead000000000120-0xdead000000000127]
> CPU: 1 PID: 37 Comm: kworker/1:1 Not tainted 6.2.0-rc4-00108-ge4dde56cd208 #1
> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS
> 1.17.0-debian-1.17.0-1 04/01/2014
> Workqueue: events high_work_func
> RIP: 0010:lru_gen_rotate_memcg+0x147/0xef0
> Code: 49 c1 ea 03 41 80 3c 3a 00 0f 85 a5 09 00 00 48 89 f7 4c 8b 93
> 08 07 00 00 48 c1 ef 03 48 89 fa 48 bf 00 00 00 00 00 fc ff df <80> 3c
> 3a 00 0f 85 2a 07 00 00 4c 89 16 41 f6 c2 01 0f 85 72 00
> RSP: 0018:ffa00000002a75e0 EFLAGS: 00010206
> RAX: ff11000008d46701 RBX: ff11000008d46000 RCX: 0000000000000000
> RDX: 1bd5a00000000024 RSI: dead000000000122 RDI: dffffc0000000000
> RBP: ff110000bfe54000 R08: ff11000008d46708 R09: ff11000008d46710
> R10: ff11000009a5a708 R11: 0000000000000000 R12: 0000000000000006
> R13: 0000000000000004 R14: 1ff4000000054ee4 R15: 0000000000000001
> FS:  0000000000000000(0000) GS:ff110000a3480000(0000) knlGS:0000000000000000
> CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> CR2: 0000000000000000 CR3: 0000000007d5c000 CR4: 0000000000751ee0
> PKRU: 55555554
> Call Trace:
> <TASK>
> ? reset_ctrl_pos+0x10f/0x460
> shrink_lruvec+0x19e0/0x2000
> ? kasan_set_track+0x25/0x30
> ? __kasan_slab_alloc+0x66/0x80
> ? kmem_cache_alloc+0x165/0x310
> ? __kernfs_new_node+0xd3/0x590
> ? __kernfs_create_file+0x2d/0x280
> ? sysfs_add_file_mode_ns+0x12b/0x3a0
> ? internal_create_group+0x286/0x940
> ? internal_create_groups+0x84/0x110
> ? really_probe+0x223/0x690
> ? unwind_next_frame+0xa9a/0x2040
> ? arch_stack_walk+0x7a/0x110
> ? unwind_next_frame+0xa9a/0x2040
> ? arch_stack_walk+0x7a/0x110
> ? __pfx_shrink_lruvec+0x10/0x10
> ? preempt_count_add+0x83/0x180
> ? unwind_next_frame+0xb2/0x2040
> ? unwind_next_frame+0x212/0x2040
> ? ret_from_fork+0x2c/0x50
> ? __pfx_stack_trace_consume_entry+0x10/0x10
> ? arch_stack_walk+0xa2/0x110
> ? sched_clock_local+0x132/0x210
> ? __pfx_sched_clock_local+0x10/0x10
> ? unwind_next_frame+0x212/0x2040
> ? __pfx_shrink_slab+0x10/0x10
> ? sched_clock_cpu+0x232/0x2c0
> ? __pfx_sched_clock_local+0x10/0x10
> ? __pfx_sched_clock_cpu+0x10/0x10
> ? mem_cgroup_iter+0x269/0x600
> ? vmpressure+0x30/0x3b0
> shrink_node+0xb39/0x26a0
> ? __pfx_shrink_node+0x10/0x10
> ? kasan_save_stack+0x42/0x60
> ? ring_buffer_lock_reserve+0x2fb/0xe30
> do_try_to_free_pages+0x31a/0x1880
> ? __pfx_do_try_to_free_pages+0x10/0x10
> try_to_free_mem_cgroup_pages+0x282/0x5f0
> ? try_to_free_mem_cgroup_pages+0x4/0x5f0
> ? reclaim_high.constprop.0+0x191/0x250
> ? __pfx_try_to_free_mem_cgroup_pages+0x10/0x10
> ? try_to_free_mem_cgroup_pages+0x9/0x5f0
> reclaim_high.constprop.0+0x191/0x250
> ? __pfx_reclaim_high.constprop.0+0x10/0x10
> ? __pfx_high_work_func+0x10/0x10
> process_one_work+0x641/0x1010
> worker_thread+0x424/0xec0
> ? __kthread_parkme+0x89/0x160
> ? __pfx_worker_thread+0x10/0x10
> kthread+0x26c/0x300
> ? __pfx_kthread+0x10/0x10
> ret_from_fork+0x2c/0x50
> </TASK>