[PATCH-next v4 6/6] cgroup/cpuset: Fix lockdep_is_cpuset_held()

From: Waiman Long

Date: Sun Nov 15 2026 - 20:24:21 EST


Commit a84097e625f2 ("cgroup/cpuset: Call housekeeping_update()
without holding cpus_read_lock") changes lockdep_is_cpuset_held()
to return true if either cpuset_mutex or cpuset_top_mutex is held.
lockdep_is_cpuset_held() is used by housekeeping_dereference_check()
as one of the conditions that rcu_read_lock() is not needed to
access HK_TYPE_DOMAIN cpumask that can be changed at run time.
In reality, it should return true only if cpuset_top_mutex is held as
housekeeping_update() is called with only cpuset_top_mutex held.

If only cpuset_mutex is held, it is possible that there can be a parallel
housekeeping_update() call leading to a potential use-after-free situation
when HK_TYPE_DOMAIN housekeeping cpumask is being accessed. It also
means that rcu_read_lock will be required if only cpuset_mutex is being
held like when calling from hotplug, scheduler or cgroup.

Fixes: a84097e625f2 ("cgroup/cpuset: Call housekeeping_update() without holding cpus_read_lock")
Signed-off-by: Waiman Long <longman@xxxxxxxxxx>
---
kernel/cgroup/cpuset-v1.c | 16 ++++++++++------
kernel/cgroup/cpuset.c | 9 +++++++--
2 files changed, 17 insertions(+), 8 deletions(-)

diff --git a/kernel/cgroup/cpuset-v1.c b/kernel/cgroup/cpuset-v1.c
index 7c7f2887dfaf..6bf6da639fec 100644
--- a/kernel/cgroup/cpuset-v1.c
+++ b/kernel/cgroup/cpuset-v1.c
@@ -686,6 +686,7 @@ int cpuset1_generate_sched_domains(cpumask_var_t **domains,
int csn; /* how many cpuset ptrs in csa so far */
int i, j; /* indices for partition finding loops */
cpumask_var_t *doms; /* resulting partition; i.e. sched domains */
+ cpumask_var_t hk_cpus; /* HK_TYPE_DOMAIN housekeeping CPUs */
struct sched_domain_attr *dattr; /* attributes for custom domains */
int ndoms = 0; /* number of sched domains in result */
int nslot; /* next empty doms[] struct cpumask slot */
@@ -698,6 +699,11 @@ int cpuset1_generate_sched_domains(cpumask_var_t **domains,
dattr = NULL;
csa = NULL;

+ alloc_cpumask_var(&hk_cpus, GFP_KERNEL);
+ scoped_guard(rcu) {
+ cpumask_copy(hk_cpus, housekeeping_cpumask(HK_TYPE_DOMAIN));
+ }
+
/* Special case for the 99% of systems with one, full, sched domain */
if (is_sched_load_balance(&top_cpuset)) {
ndoms = 1;
@@ -710,9 +716,7 @@ int cpuset1_generate_sched_domains(cpumask_var_t **domains,
*dattr = SD_ATTR_INIT;
update_domain_attr_tree(dattr, &top_cpuset);
}
- cpumask_and(doms[0], top_cpuset.effective_cpus,
- housekeeping_cpumask(HK_TYPE_DOMAIN));
-
+ cpumask_and(doms[0], top_cpuset.effective_cpus, hk_cpus);
goto done;
}

@@ -736,8 +740,7 @@ int cpuset1_generate_sched_domains(cpumask_var_t **domains,
*/
if (!cpumask_empty(cp->cpus_allowed) &&
!(is_sched_load_balance(cp) &&
- cpumask_intersects(cp->cpus_allowed,
- housekeeping_cpumask(HK_TYPE_DOMAIN))))
+ cpumask_intersects(cp->cpus_allowed, hk_cpus)))
continue;

if (is_sched_load_balance(cp) &&
@@ -794,7 +797,7 @@ int cpuset1_generate_sched_domains(cpumask_var_t **domains,
*(dattr + nslot) = SD_ATTR_INIT;
}
cpumask_or(dp, dp, csa[j]->effective_cpus);
- cpumask_and(dp, dp, housekeeping_cpumask(HK_TYPE_DOMAIN));
+ cpumask_and(dp, dp, hk_cpus);
if (dattr)
update_domain_attr_tree(dattr + nslot, csa[j]);
}
@@ -806,6 +809,7 @@ int cpuset1_generate_sched_domains(cpumask_var_t **domains,

done:
kfree(csa);
+ free_cpumask_var(hk_cpus);

/*
* Fallback to the default domain if kmalloc() failed.
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 64cbcbdbf6da..d18439e13bce 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -343,10 +343,13 @@ void cpuset_full_unlock(void)
}

#ifdef CONFIG_LOCKDEP
+/*
+ * Holding cpuset_top_mutex will guarantee that a parallel
+ * housekeeping_update() call modifying housekeeping cpumasks is not possible.
+ */
bool lockdep_is_cpuset_held(void)
{
- return lockdep_is_held(&cpuset_mutex) ||
- lockdep_is_held(&cpuset_top_mutex);
+ return lockdep_is_held(&cpuset_top_mutex);
}
#endif

@@ -1416,8 +1419,10 @@ static bool prstate_housekeeping_conflict(int new_prs, int parent_prs,
}
}

+ rcu_read_lock();
cpumask_and(full_hk_cpus, housekeeping_cpumask(HK_TYPE_KERNEL_NOISE),
housekeeping_cpumask(HK_TYPE_DOMAIN));
+ rcu_read_unlock();
cpumask_andnot(full_hk_cpus, full_hk_cpus, isolated_cpus);
cpumask_and(full_hk_cpus, full_hk_cpus, cpu_active_mask);
res = !cpumask_weight_andnot(full_hk_cpus, new_cpus);
--
2.56.0