mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Waiman Long <longman@redhat.com>
To: Ridong <ridong.chen@linux.dev>,
	frederic@kernel.org, tj@kernel.org, peterz@infradead.org,
	mingo@redhat.com, juri.lelli@redhat.com,
	vincent.guittot@linaro.org, dietmar.eggemann@arm.com,
	rostedt@goodmis.org, bsegall@google.com, mgorman@suse.de,
	vschneid@redhat.com, kprateek.nayak@amd.com, hannes@cmpxchg.org,
	mkoutny@suse.com
Cc: linux-kernel@vger.kernel.org, cgroups@vger.kernel.org,
	guopeng.zhang@linux.dev, mathieu.desnoyers@efficios.com,
	Ridong Chen <chenridong@xiaomi.com>
Subject: Re: [PATCH] sched/isolation: Publish new HK_TYPE_DOMAIN cpumask under cpuset_mutex
Date: Tue, 17 Nov 2026 11:15:52 -0500	[thread overview]
Message-ID: <36d49371-31de-4305-89c4-2ce64dd6848c@redhat.com> (raw)
In-Reply-To: <20261117083915.2971979-1-ridong.chen@linux.dev>

On 11/17/26 3:39 AM, Ridong wrote:
> From: Ridong Chen <chenridong@xiaomi.com>
>
> Commit a84097e625f2 ("cgroup/cpuset: Call housekeeping_update() without
> holding cpus_read_lock") calls housekeeping_update() after dropping
> cpus_read_lock and cpuset_mutex, so the HK_TYPE_DOMAIN cpumask is now
> switched and freed outside of those locks. But readers holding either
> lock may still access it without rcu_read_lock() as allowed by
> housekeeping_dereference_check(), and synchronize_rcu() doesn't wait
> for them:
>
>    CPU A                                  CPU B
>    rebuild_sched_domains()                cpuset_update_sd_hk_unlock()
>                                             mutex_unlock(&cpuset_mutex)
>                                             cpus_read_unlock()
>      mutex_lock(&cpuset_mutex)
>      p = housekeeping_cpumask(DOMAIN)
>                                             housekeeping_update()
>                                               rcu_assign_pointer()
>                                               synchronize_rcu()
>                                               kfree(old)
>      access p <- UAF
>
> Fix it by moving the pointer switch into housekeeping_publish(), which
> is called before dropping the locks. Then CPU A either finishes before
> CPU B switches the pointer, or only sees the new cpumask:
>
>    CPU A                                  CPU B
>                                           cpuset_update_sd_hk_unlock()
>                                             housekeeping_publish()
>                                               rcu_assign_pointer()
>      mutex_lock(&cpuset_mutex) <- wait
>                                             mutex_unlock(&cpuset_mutex)
>                                             cpus_read_unlock()
>      p = housekeeping_cpumask(DOMAIN)       housekeeping_update()
>          <- new cpumask                       synchronize_rcu()
>                                               kfree(old)
>
> The rest of housekeeping_update(), including the workqueue flushes,
> still runs without those locks.
>
> Fixes: a84097e625f2 ("cgroup/cpuset: Call housekeeping_update() without holding cpus_read_lock")
> Signed-off-by: Ridong Chen <chenridong@xiaomi.com>
> ---
>   include/linux/sched/isolation.h |  6 ++++--
>   kernel/cgroup/cpuset.c          | 12 ++++++++----
>   kernel/sched/isolation.c        | 23 ++++++++++++++++-------
>   3 files changed, 28 insertions(+), 13 deletions(-)
>
> diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h
> index cf0fd03dd7a24..09fabf42e3224 100644
> --- a/include/linux/sched/isolation.h
> +++ b/include/linux/sched/isolation.h
> @@ -43,7 +43,8 @@ extern const struct cpumask *housekeeping_cpumask(enum hk_type type);
>   extern bool housekeeping_enabled(enum hk_type type);
>   extern void housekeeping_affine(struct task_struct *t, enum hk_type type);
>   extern bool housekeeping_test_cpu(int cpu, enum hk_type type);
> -extern int housekeeping_update(struct cpumask *isol_mask);
> +extern struct cpumask *housekeeping_publish(struct cpumask *isol_mask);
> +extern void housekeeping_update(struct cpumask *isol_mask, struct cpumask *old);
>   extern void __init housekeeping_init(void);
>   
>   #else
> @@ -71,7 +72,8 @@ static inline bool housekeeping_test_cpu(int cpu, enum hk_type type)
>   	return true;
>   }
>   
> -static inline int housekeeping_update(struct cpumask *isol_mask) { return 0; }
> +static inline struct cpumask *housekeeping_publish(struct cpumask *isol_mask) { return NULL; }
> +static inline void housekeeping_update(struct cpumask *isol_mask, struct cpumask *old) { }
>   static inline void housekeeping_init(void) { }
>   #endif /* CONFIG_CPU_ISOLATION */
>   
> diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
> index 8a8a424a389f3..1673bb25a797b 100644
> --- a/kernel/cgroup/cpuset.c
> +++ b/kernel/cgroup/cpuset.c
> @@ -1472,17 +1472,21 @@ static void cpuset_update_sd_hk_unlock(void)
>   		rebuild_sched_domains_locked();
>   
>   	if (update_housekeeping) {
> +		struct cpumask *old;
> +
>   		update_housekeeping = false;
>   		cpumask_copy(isolated_hk_cpus, isolated_cpus);
>   
>   		/*
> -		 * housekeeping_update() is now called without holding
> -		 * cpus_read_lock and cpuset_mutex. Only cpuset_top_mutex
> -		 * is still being held for mutual exclusion.
> +		 * Publish the new cpumask with cpus_read_lock and cpuset_mutex
> +		 * held, but call housekeeping_update() without them. Only
> +		 * cpuset_top_mutex is still being held for mutual exclusion.
>   		 */
> +		old = housekeeping_publish(isolated_hk_cpus);
>   		mutex_unlock(&cpuset_mutex);
>   		cpus_read_unlock();
> -		WARN_ON_ONCE(housekeeping_update(isolated_hk_cpus));
> +		if (!WARN_ON_ONCE(IS_ERR(old)))
> +			housekeeping_update(isolated_hk_cpus, old);
>   		mutex_unlock(&cpuset_top_mutex);
>   	} else {
>   		cpuset_full_unlock();
> diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
> index 156025ef81b75..9e202269e42f6 100644
> --- a/kernel/sched/isolation.c
> +++ b/kernel/sched/isolation.c
> @@ -120,23 +120,26 @@ bool housekeeping_test_cpu(int cpu, enum hk_type type)
>   }
>   EXPORT_SYMBOL_GPL(housekeeping_test_cpu);
>   
> -int housekeeping_update(struct cpumask *isol_mask)
> +/* Called with cpus_read_lock and cpuset_mutex held */
> +struct cpumask *housekeeping_publish(struct cpumask *isol_mask)
>   {
>   	struct cpumask *trial, *old = NULL;
> -	int err;
> +
> +	lockdep_assert_cpus_held();
> +	lockdep_assert_cpuset_lock_held();
>   
>   	trial = kmalloc(cpumask_size(), GFP_KERNEL);
>   	if (!trial)
> -		return -ENOMEM;
> +		return ERR_PTR(-ENOMEM);
>   
>   	cpumask_andnot(trial, housekeeping_cpumask(HK_TYPE_DOMAIN_BOOT), isol_mask);
>   	if (!cpumask_intersects(trial, cpu_online_mask)) {
>   		kfree(trial);
> -		return -EINVAL;
> +		return ERR_PTR(-EINVAL);
>   	}
>   
>   	if (!housekeeping.flags)
> -		static_branch_enable(&housekeeping_overridden);
> +		static_branch_enable_cpuslocked(&housekeeping_overridden);
>   
>   	if (housekeeping.flags & HK_FLAG_DOMAIN)
>   		old = housekeeping_cpumask_dereference(HK_TYPE_DOMAIN);
> @@ -144,6 +147,14 @@ int housekeeping_update(struct cpumask *isol_mask)
>   		WRITE_ONCE(housekeeping.flags, housekeeping.flags | HK_FLAG_DOMAIN);
>   	rcu_assign_pointer(housekeeping.cpumasks[HK_TYPE_DOMAIN], trial);
>   
> +	return old;
> +}
> +
> +/* Called without cpus_read_lock and cpuset_mutex held */
> +void housekeeping_update(struct cpumask *isol_mask, struct cpumask *old)
> +{
> +	int err;
> +
>   	synchronize_rcu();
>   
>   	pci_probe_flush_workqueue();
> @@ -160,8 +171,6 @@ int housekeeping_update(struct cpumask *isol_mask)
>   	WARN_ON_ONCE(err < 0);
>   
>   	kfree(old);
> -
> -	return 0;
>   }
>   
>   void __init housekeeping_init(void)

Yes, that should work too.

Acked-by: Waiman Long <longman@redhat.com>

I will let other decide which one do they want.

Cheers,
Longman


  reply	other threads:[~2026-11-17 16:16 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-17  5:18 [PATCH v2] sched/isolation: Enable cpuset_mutex/cpus_read_lock synchronization before freeing old housekeeping cpumask Waiman Long
2026-11-17  6:43 ` Guopeng Zhang
2026-11-17  8:34 ` Ridong Chen
2026-11-17  8:39   ` [PATCH] sched/isolation: Publish new HK_TYPE_DOMAIN cpumask under cpuset_mutex Ridong
2026-11-17 16:15     ` Waiman Long [this message]
2026-11-17 16:02   ` [PATCH v2] sched/isolation: Enable cpuset_mutex/cpus_read_lock synchronization before freeing old housekeeping cpumask Waiman Long

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=36d49371-31de-4305-89c4-2ce64dd6848c@redhat.com \
    --to=longman@redhat.com \
    --cc=bsegall@google.com \
    --cc=cgroups@vger.kernel.org \
    --cc=chenridong@xiaomi.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=frederic@kernel.org \
    --cc=guopeng.zhang@linux.dev \
    --cc=hannes@cmpxchg.org \
    --cc=juri.lelli@redhat.com \
    --cc=kprateek.nayak@amd.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mathieu.desnoyers@efficios.com \
    --cc=mgorman@suse.de \
    --cc=mingo@redhat.com \
    --cc=mkoutny@suse.com \
    --cc=peterz@infradead.org \
    --cc=ridong.chen@linux.dev \
    --cc=rostedt@goodmis.org \
    --cc=tj@kernel.org \
    --cc=vincent.guittot@linaro.org \
    --cc=vschneid@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®