[RESEND PATCH v2] mm/memcontrol: Avoid stuck FLUSHING_CACHED_CHARGE on isolated CPU

[RESEND PATCH v2] mm/memcontrol: Avoid stuck FLUSHING_CACHED_CHARGE on isolated CPU

[Hui Zhu]

From: Hui Zhu <zhuhui@kylinos.cn>

drain_all_stock() sets FLUSHING_CACHED_CHARGE before calling
schedule_drain_work() to queue per-CPU drain work.  When the target
CPU is isolated (cpu_is_isolated() == true), the work is silently
not queued, but FLUSHING_CACHED_CHARGE stays set.  Every subsequent
drain_all_stock() then sees the bit and skips this stock entirely,
so the entry is effectively pinned until something else on that CPU
runs drain_local_*_stock() and clears the bit -- which on a long-
isolated CPU may never happen.

The original idea was to actually perform the drain from the calling
CPU on behalf of the isolated one, by adding a lock around the
per-CPU stock so that a remote drainer could safely touch it.  In
practice this turned out to be intrusive: the stock data structures
and their fast paths (consume_stock(), refill_stock(), the obj_stock
helpers) are deliberately designed around current-CPU-only access,
and retrofitting cross-CPU serialisation onto them adds non-trivial
locking and PREEMPT_RT concerns for very little gain.

Looking at the actual amount of charge that can accumulate in a
single per-CPU stock, it is bounded and small, so leaving an
isolated CPU's stock undrained for a while is not a real problem.
The only real bug is that the stuck FLUSHING_CACHED_CHARGE bit
prevents future drain_all_stock() callers from re-attempting once
the CPU is no longer isolated.

Fix this minimally by clearing FLUSHING_CACHED_CHARGE when the work
could not be queued because the target CPU is isolated.  The cached
charge itself is left in place; it will be released the next time
the CPU runs drain_local_*_stock() (e.g. after leaving isolation,
or if the isolated CPU itself calls drain_all_stock() -- in that
case cpu == curcpu causes drain_local_memcg_stock() to be invoked
directly), and the next drain_all_stock() call is free to retry
instead of skipping the stock forever.

Fixes: 6a792697a53a ("memcg: do not drain charge pcp caches on remote isolated cpus")
Signed-off-by: Hui Zhu <zhuhui@kylinos.cn>
---
Changelog:
v2:
According to the comments of Waiman Long, updated fixes.

 mm/memcontrol.c | 28 ++++++++++++++++++++++------
 1 file changed, 22 insertions(+), 6 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6dc4888a90f3..2e66b4a2c25d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2256,7 +2256,8 @@ static bool is_memcg_drain_needed(struct memcg_stock_pcp *stock,
 	return flush;
 }
 
-static void schedule_drain_work(int cpu, struct work_struct *work)
+static void
+schedule_drain_work(int cpu, struct work_struct *work, unsigned long *flags)
 {
 	/*
 	 * Protect housekeeping cpumask read and work enqueue together
@@ -2264,9 +2265,22 @@ static void schedule_drain_work(int cpu, struct work_struct *work)
 	 * partition update only need to wait for an RCU GP and flush the
 	 * pending work on newly isolated CPUs.
 	 */
-	guard(rcu)();
-	if (!cpu_is_isolated(cpu))
-		queue_work_on(cpu, memcg_wq, work);
+	scoped_guard(rcu) {
+		if (!cpu_is_isolated(cpu)) {
+			queue_work_on(cpu, memcg_wq, work);
+			return;
+		}
+	}
+
+	/*
+	 * The target CPU is isolated: the drain work was not queued.
+	 * Clear FLUSHING_CACHED_CHARGE so that future drain_all_stock()
+	 * callers can re-attempt instead of skipping this stock forever.
+	 * The cached charge is left in place; it will be released the
+	 * next time the CPU itself runs drain_local_*_stock() (e.g.
+	 * after leaving isolation), or by a follow-up mechanism.
+	 */
+	clear_bit(FLUSHING_CACHED_CHARGE, flags);
 }
 
 /*
@@ -2299,7 +2313,8 @@ void drain_all_stock(struct mem_cgroup *root_memcg)
 			if (cpu == curcpu)
 				drain_local_memcg_stock(&memcg_st->work);
 			else
-				schedule_drain_work(cpu, &memcg_st->work);
+				schedule_drain_work(cpu, &memcg_st->work,
+						    &memcg_st->flags);
 		}
 
 		if (!test_bit(FLUSHING_CACHED_CHARGE, &obj_st->flags) &&
@@ -2309,7 +2324,8 @@ void drain_all_stock(struct mem_cgroup *root_memcg)
 			if (cpu == curcpu)
 				drain_local_obj_stock(&obj_st->work);
 			else
-				schedule_drain_work(cpu, &obj_st->work);
+				schedule_drain_work(cpu, &obj_st->work,
+						    &obj_st->flags);
 		}
 	}
 	migrate_enable();
-- 
2.43.0

Re: [RESEND PATCH v2] mm/memcontrol: Avoid stuck FLUSHING_CACHED_CHARGE on isolated CPU

[Shakeel Butt]

On Tue, Jun 30, 2026 at 03:00:04PM +0800, Hui Zhu wrote:
> From: Hui Zhu <zhuhui@kylinos.cn>
> 
> drain_all_stock() sets FLUSHING_CACHED_CHARGE before calling
> schedule_drain_work() to queue per-CPU drain work.  When the target
> CPU is isolated (cpu_is_isolated() == true), the work is silently
> not queued, but FLUSHING_CACHED_CHARGE stays set.  Every subsequent
> drain_all_stock() then sees the bit and skips this stock entirely,
> so the entry is effectively pinned until something else on that CPU
> runs drain_local_*_stock() and clears the bit -- which on a long-
> isolated CPU may never happen.
> 
> The original idea was to actually perform the drain from the calling
> CPU on behalf of the isolated one, by adding a lock around the
> per-CPU stock so that a remote drainer could safely touch it.  In
> practice this turned out to be intrusive: the stock data structures
> and their fast paths (consume_stock(), refill_stock(), the obj_stock
> helpers) are deliberately designed around current-CPU-only access,
> and retrofitting cross-CPU serialisation onto them adds non-trivial
> locking and PREEMPT_RT concerns for very little gain.
> 
> Looking at the actual amount of charge that can accumulate in a
> single per-CPU stock, it is bounded and small, so leaving an
> isolated CPU's stock undrained for a while is not a real problem.
> The only real bug is that the stuck FLUSHING_CACHED_CHARGE bit
> prevents future drain_all_stock() callers from re-attempting once
> the CPU is no longer isolated.
> 
> Fix this minimally by clearing FLUSHING_CACHED_CHARGE when the work
> could not be queued because the target CPU is isolated.  The cached
> charge itself is left in place; it will be released the next time
> the CPU runs drain_local_*_stock() (e.g. after leaving isolation,
> or if the isolated CPU itself calls drain_all_stock() -- in that
> case cpu == curcpu causes drain_local_memcg_stock() to be invoked
> directly), and the next drain_all_stock() call is free to retry
> instead of skipping the stock forever.
> 
> Fixes: 6a792697a53a ("memcg: do not drain charge pcp caches on remote isolated cpus")
> Signed-off-by: Hui Zhu <zhuhui@kylinos.cn>
> ---
> Changelog:
> v2:
> According to the comments of Waiman Long, updated fixes.
> 
>  mm/memcontrol.c | 28 ++++++++++++++++++++++------
>  1 file changed, 22 insertions(+), 6 deletions(-)
> 
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 6dc4888a90f3..2e66b4a2c25d 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -2256,7 +2256,8 @@ static bool is_memcg_drain_needed(struct memcg_stock_pcp *stock,
>  	return flush;
>  }
>  
> -static void schedule_drain_work(int cpu, struct work_struct *work)
> +static void
> +schedule_drain_work(int cpu, struct work_struct *work, unsigned long *flags)
>  {
>  	/*
>  	 * Protect housekeeping cpumask read and work enqueue together
> @@ -2264,9 +2265,22 @@ static void schedule_drain_work(int cpu, struct work_struct *work)
>  	 * partition update only need to wait for an RCU GP and flush the
>  	 * pending work on newly isolated CPUs.
>  	 */
> -	guard(rcu)();
> -	if (!cpu_is_isolated(cpu))
> -		queue_work_on(cpu, memcg_wq, work);
> +	scoped_guard(rcu) {
> +		if (!cpu_is_isolated(cpu)) {
> +			queue_work_on(cpu, memcg_wq, work);
> +			return;
> +		}
> +	}
> +
> +	/*
> +	 * The target CPU is isolated: the drain work was not queued.
> +	 * Clear FLUSHING_CACHED_CHARGE so that future drain_all_stock()
> +	 * callers can re-attempt instead of skipping this stock forever.
> +	 * The cached charge is left in place; it will be released the
> +	 * next time the CPU itself runs drain_local_*_stock() (e.g.
> +	 * after leaving isolation), or by a follow-up mechanism.
> +	 */
> +	clear_bit(FLUSHING_CACHED_CHARGE, flags);

Let's do something like the following.

	guard(rcu)();
	if (cpu_is_isolated(cpu)) {
		clear_bit(FLUSHING_CACHED_CHARGE, flags);
		return;
	}
	queue_work_on(cpu, memcg_wq, work);

>  }
>  
>  /*
> @@ -2299,7 +2313,8 @@ void drain_all_stock(struct mem_cgroup *root_memcg)
>  			if (cpu == curcpu)
>  				drain_local_memcg_stock(&memcg_st->work);
>  			else
> -				schedule_drain_work(cpu, &memcg_st->work);
> +				schedule_drain_work(cpu, &memcg_st->work,
> +						    &memcg_st->flags);
>  		}
>  
>  		if (!test_bit(FLUSHING_CACHED_CHARGE, &obj_st->flags) &&
> @@ -2309,7 +2324,8 @@ void drain_all_stock(struct mem_cgroup *root_memcg)
>  			if (cpu == curcpu)
>  				drain_local_obj_stock(&obj_st->work);
>  			else
> -				schedule_drain_work(cpu, &obj_st->work);
> +				schedule_drain_work(cpu, &obj_st->work,
> +						    &obj_st->flags);
>  		}
>  	}
>  	migrate_enable();
> -- 
> 2.43.0
> 

Re: [RESEND PATCH v2] mm/memcontrol: Avoid stuck FLUSHING_CACHED_CHARGE on isolated CPU

[Joshua Hahn]

On Tue, 30 Jun 2026 15:00:04 +0800 Hui Zhu <hui.zhu@linux.dev> wrote:

> From: Hui Zhu <zhuhui@kylinos.cn>
> 
> drain_all_stock() sets FLUSHING_CACHED_CHARGE before calling
> schedule_drain_work() to queue per-CPU drain work.  When the target
> CPU is isolated (cpu_is_isolated() == true), the work is silently
> not queued, but FLUSHING_CACHED_CHARGE stays set.  Every subsequent
> drain_all_stock() then sees the bit and skips this stock entirely,
> so the entry is effectively pinned until something else on that CPU
> runs drain_local_*_stock() and clears the bit -- which on a long-
> isolated CPU may never happen.

Hello Hui,

I hope you're doing well! Thank you for the patch. I've also been
thinking about memcg stock and specifically on how the flushing happens.

I haven't been thinking about the issue of isolated work taking a long
time, but I have been reworking memcg stock by getting rid of it and
pushing it down to the page_counter level [1].

I think that this patch is still important because of the obj_stock
portion, which my series doens't touch. I just wanted to bring this
to your attention! I don't think there should be any other problems.

Thank you again, have a great day!
Joshua

[1] https://lore.kernel.org/all/20260623180124.868655-1-joshua.hahnjy@gmail.com/

> The original idea was to actually perform the drain from the calling
> CPU on behalf of the isolated one, by adding a lock around the
> per-CPU stock so that a remote drainer could safely touch it.  In
> practice this turned out to be intrusive: the stock data structures
> and their fast paths (consume_stock(), refill_stock(), the obj_stock
> helpers) are deliberately designed around current-CPU-only access,
> and retrofitting cross-CPU serialisation onto them adds non-trivial
> locking and PREEMPT_RT concerns for very little gain.
> 
> Looking at the actual amount of charge that can accumulate in a
> single per-CPU stock, it is bounded and small, so leaving an
> isolated CPU's stock undrained for a while is not a real problem.
> The only real bug is that the stuck FLUSHING_CACHED_CHARGE bit
> prevents future drain_all_stock() callers from re-attempting once
> the CPU is no longer isolated.
> 
> Fix this minimally by clearing FLUSHING_CACHED_CHARGE when the work
> could not be queued because the target CPU is isolated.  The cached
> charge itself is left in place; it will be released the next time
> the CPU runs drain_local_*_stock() (e.g. after leaving isolation,
> or if the isolated CPU itself calls drain_all_stock() -- in that
> case cpu == curcpu causes drain_local_memcg_stock() to be invoked
> directly), and the next drain_all_stock() call is free to retry
> instead of skipping the stock forever.
> 
> Fixes: 6a792697a53a ("memcg: do not drain charge pcp caches on remote isolated cpus")
> Signed-off-by: Hui Zhu <zhuhui@kylinos.cn>
> ---
> Changelog:
> v2:
> According to the comments of Waiman Long, updated fixes.
> 
>  mm/memcontrol.c | 28 ++++++++++++++++++++++------
>  1 file changed, 22 insertions(+), 6 deletions(-)
> 
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 6dc4888a90f3..2e66b4a2c25d 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -2256,7 +2256,8 @@ static bool is_memcg_drain_needed(struct memcg_stock_pcp *stock,
>  	return flush;
>  }
>  
> -static void schedule_drain_work(int cpu, struct work_struct *work)
> +static void
> +schedule_drain_work(int cpu, struct work_struct *work, unsigned long *flags)
>  {
>  	/*
>  	 * Protect housekeeping cpumask read and work enqueue together
> @@ -2264,9 +2265,22 @@ static void schedule_drain_work(int cpu, struct work_struct *work)
>  	 * partition update only need to wait for an RCU GP and flush the
>  	 * pending work on newly isolated CPUs.
>  	 */
> -	guard(rcu)();
> -	if (!cpu_is_isolated(cpu))
> -		queue_work_on(cpu, memcg_wq, work);
> +	scoped_guard(rcu) {
> +		if (!cpu_is_isolated(cpu)) {
> +			queue_work_on(cpu, memcg_wq, work);
> +			return;
> +		}
> +	}
> +
> +	/*
> +	 * The target CPU is isolated: the drain work was not queued.
> +	 * Clear FLUSHING_CACHED_CHARGE so that future drain_all_stock()
> +	 * callers can re-attempt instead of skipping this stock forever.
> +	 * The cached charge is left in place; it will be released the
> +	 * next time the CPU itself runs drain_local_*_stock() (e.g.
> +	 * after leaving isolation), or by a follow-up mechanism.
> +	 */
> +	clear_bit(FLUSHING_CACHED_CHARGE, flags);
>  }
>  
>  /*
> @@ -2299,7 +2313,8 @@ void drain_all_stock(struct mem_cgroup *root_memcg)
>  			if (cpu == curcpu)
>  				drain_local_memcg_stock(&memcg_st->work);
>  			else
> -				schedule_drain_work(cpu, &memcg_st->work);
> +				schedule_drain_work(cpu, &memcg_st->work,
> +						    &memcg_st->flags);
>  		}
>  
>  		if (!test_bit(FLUSHING_CACHED_CHARGE, &obj_st->flags) &&
> @@ -2309,7 +2324,8 @@ void drain_all_stock(struct mem_cgroup *root_memcg)
>  			if (cpu == curcpu)
>  				drain_local_obj_stock(&obj_st->work);
>  			else
> -				schedule_drain_work(cpu, &obj_st->work);
> +				schedule_drain_work(cpu, &obj_st->work,
> +						    &obj_st->flags);
>  		}
>  	}
>  	migrate_enable();
> -- 
> 2.43.0