cgroups.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [PATCH] sched/isolation: Publish new HK_TYPE_DOMAIN cpumask under cpuset_mutex
       [not found] <054a53a3-c038-48fe-ac01-fc24fd8065d0@linux.dev>
@ 2026-11-17  8:39 ` Ridong
  2026-11-17 16:15   ` Waiman Long
  2026-11-17 21:18   ` Tejun Heo
  0 siblings, 2 replies; 3+ messages in thread
From: Ridong @ 2026-11-17  8:39 UTC (permalink / raw)
  To: longman, frederic, tj, peterz, mingo, juri.lelli, vincent.guittot,
	dietmar.eggemann, rostedt, bsegall, mgorman, vschneid,
	kprateek.nayak, hannes, mkoutny
  Cc: linux-kernel, cgroups, guopeng.zhang, mathieu.desnoyers,
	Ridong Chen

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)
-- 
2.34.1


^ permalink raw reply related	[flat|nested] 3+ messages in thread

* Re: [PATCH] sched/isolation: Publish new HK_TYPE_DOMAIN cpumask under cpuset_mutex
  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
  2026-11-17 21:18   ` Tejun Heo
  1 sibling, 0 replies; 3+ messages in thread
From: Waiman Long @ 2026-11-17 16:15 UTC (permalink / raw)
  To: Ridong, frederic, tj, peterz, mingo, juri.lelli, vincent.guittot,
	dietmar.eggemann, rostedt, bsegall, mgorman, vschneid,
	kprateek.nayak, hannes, mkoutny
  Cc: linux-kernel, cgroups, guopeng.zhang, mathieu.desnoyers,
	Ridong Chen

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


^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [PATCH] sched/isolation: Publish new HK_TYPE_DOMAIN cpumask under cpuset_mutex
  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
@ 2026-11-17 21:18   ` Tejun Heo
  1 sibling, 0 replies; 3+ messages in thread
From: Tejun Heo @ 2026-11-17 21:18 UTC (permalink / raw)
  To: Ridong
  Cc: longman, frederic, peterz, mingo, juri.lelli, vincent.guittot,
	dietmar.eggemann, rostedt, bsegall, mgorman, vschneid,
	kprateek.nayak, hannes, mkoutny, linux-kernel, cgroups,
	guopeng.zhang, mathieu.desnoyers, Ridong Chen

On Tue, Nov 17, 2026 at 04:39:15PM +0800, Ridong wrote:
> 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>

Acked-by: Tejun Heo <tj@kernel.org>

Thanks.

--
tejun

^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2026-11-17 21:18 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
     [not found] <054a53a3-c038-48fe-ac01-fc24fd8065d0@linux.dev>
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
2026-11-17 21:18   ` Tejun Heo

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).