From e06b678e3b4e12fdaa0b51a7a5a54abc5dbd6469 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Tue, 29 Sep 2026 23:18:33 -0400 Subject: [PATCH 1/3] cgroup/cpuset: Don't access cpuset_cgrp_subsys.root in is_in_v2_mode() After seeing the patch [1] to guard is_in_v2_mode() with RCU, it makes me realize that is_in_v2_mode() may be called in a context where a new cgroup filesystem is being rebound with stale cpuset_cgrp_subsys.root pointer. Avoid this potential UaF situation by adding a new cpuset_v2_mode flag which is set when the cpuset_v2_mode mount option is used. This flag is written into only when cpuset_bind() is being called with a stable cpuset_cgrp_subsys.root value. The is_in_v2_mode() helper is modified to read the new cpuset_v2_mode flag instead of accessing cpuset_cgrp_subsys.root directly. [1] https://lore.kernel.org/lkml/20260929084124.626693-2-arighi@nvidia.com Fixes: b8d1b8ee93df ("cpuset: Allow v2 behavior in v1 cgroup") Signed-off-by: Waiman Long Reviewed-by: Ridong Chen Reviewed-by: Andrea Righi Signed-off-by: Tejun Heo --- kernel/cgroup/cpuset.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 1fcec89a28b9..98af44a7f399 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -152,6 +152,12 @@ static cpumask_var_t isolated_cpus; /* CSCB */ */ static bool update_housekeeping; /* RWCS */ +/* + * Set if "cpuset_v2_mode" mount option is used + * Cached at bind time and not lock protected; accessed via {READ,WRITE}_ONCE + */ +static bool cpuset_v2_mode; + /* * Copy of isolated_cpus to be passed to housekeeping_update() */ @@ -439,8 +445,7 @@ static inline bool cpuset_v2(void) */ static inline bool is_in_v2_mode(void) { - return cpuset_v2() || - (cpuset_cgrp_subsys.root->flags & CGRP_ROOT_CPUSET_V2_MODE); + return cpuset_v2() || READ_ONCE(cpuset_v2_mode); } /** @@ -3727,6 +3732,8 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css) mutex_lock(&cpuset_mutex); spin_lock_irq(&callback_lock); + WRITE_ONCE(cpuset_v2_mode, + !!(cpuset_cgrp_subsys.root->flags & CGRP_ROOT_CPUSET_V2_MODE)); if (is_in_v2_mode()) { cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask); cpumask_copy(top_cpuset.effective_xcpus, cpu_possible_mask); From 23b1ab15ca91f2cffaf149d9bb0fafeb700c7db2 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Fri, 2 Oct 2026 12:54:38 -0400 Subject: [PATCH 2/3] cgroup/cpuset: Handle cpu hotplug race in guarantee_active_cpus() With commit 2125c0034c5d ("cgroup/cpuset: Make cpuset hotplug processing synchronous"), the cpuset hotplug operation becomes synchronous. That commit also removes the code that handles race between cpuset_hotplug_work and cpu hotplug notifier with the assumption that race is now gone. Later commit 7a0aabd9ce69 ("cgroup/cpuset: Always use cpu_active_mask") updates the cpuset code to always use cpu_active_mask instead of cpu_online_mask in some places including guarantee_online_cpus() which is renamed to guarantee_active_cpus() in that commit. In the case of CPU offline operation, cpu_active_mask is updated first in sched_cpu_deactivate() to remove the offline CPU before cpuset_handle_hotplug() is called to update the effective_cpus of the affected cpusets. The cpu_online_mask is updated after that near the end of the offline operation to remove the offline CPU. As a result, the race comes back and the top cpuset may not have any active CPU leading to NULL pointer dereference during the race window when guarantee_active_cpus() is called after cpu_active_mask is updated to remove the CPU to be torn down but before cpuset_handle_hotplug() is able to properly update the effective_cpus of the top cpuset. Fix this by adding back the NULL cs check to avoid this problem. Fixes: 7a0aabd9ce69 ("cgroup/cpuset: Always use cpu_active_mask") Cc: stable@vger.kernel.org # v6.16+ Reported-by: Farhad Alemi Link: https://lore.kernel.org/lkml/CA+0ovChh3VjsKN1g+ZGjwwY2fGTpP7uD+aCCByLj5Qbymw=bfQ@mail.gmail.com Signed-off-by: Waiman Long Tested-by: Farhad Alemi Signed-off-by: Tejun Heo --- kernel/cgroup/cpuset.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 98af44a7f399..d2ec7b128960 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -518,10 +518,26 @@ static void guarantee_active_cpus(struct task_struct *tsk, rcu_read_lock(); cs = task_cs(tsk); - while (!cpumask_intersects(cs->effective_cpus, pmask)) + while (!cpumask_intersects(cs->effective_cpus, pmask)) { cs = parent_cs(cs); - + if (unlikely(!cs)) { + /* + * The top cpuset doesn't have any active cpu as a + * consequence of a race between its caller and the cpu + * hotplug operation where cpu_active_mask is updated + * asynchronously before cpuset_handle_hotplug() is + * being called to adjust the effective_cpus of the + * affected cpusets. But we know the top cpuset's + * effective_cpus is on its way to be identical to + * cpu_active_mask minus the exclusive CPUs dedicated + * to other valid cpuset partitions. Just pass back + * the filtered cpu_active_mask in this case. + */ + goto out_unlock; + } + } cpumask_and(pmask, pmask, cs->effective_cpus); +out_unlock: rcu_read_unlock(); } From b8eb5fd5bdb4c03758b056c70e5e1d962ca89757 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Mon, 5 Oct 2026 06:43:10 -0400 Subject: [PATCH 3/3] cgroup/cpuset: Call is_in_v2_mode() after acquiring cpuset_mutex in cpuset_handle_hotplug() It is reported by sashiko that calling is_in_v2_mode() outside of cpuset_mutex critical section in cpuset_handle_hotplug() can introduce a TOCTOU race where cgroup hierarchy may have changed from v1 to v2 or vice versa after is_in_v2_mode() is called leading to erroneously skip the allocation of tmpmasks or incorrectly modify cpus_allowed masks, resulting in cpuset state corruption. Fix that by calling is_in_v2_mode() after acquiring the cpuset_mutex. Fixes: b8d1b8ee93df ("cpuset: Allow v2 behavior in v1 cgroup") Signed-off-by: Waiman Long Signed-off-by: Tejun Heo --- kernel/cgroup/cpuset.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index d2ec7b128960..b61bc3ed1037 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -4062,15 +4062,16 @@ static void cpuset_handle_hotplug(void) static cpumask_t new_cpus; static nodemask_t new_mems; bool cpus_updated, mems_updated; - bool on_dfl = is_in_v2_mode(); + bool on_dfl; struct tmpmasks tmp, *ptmp = NULL; - if (on_dfl && !alloc_tmpmasks(&tmp)) - ptmp = &tmp; - lockdep_assert_cpus_held(); mutex_lock(&cpuset_mutex); + on_dfl = is_in_v2_mode(); + if (on_dfl && !alloc_tmpmasks(&tmp)) + ptmp = &tmp; + /* fetch the available cpus/mems and find out which changed how */ cpumask_copy(&new_cpus, cpu_active_mask); new_mems = node_states[N_MEMORY];