From 6ee43047e8ada63c4dfee01e2ea7e7eadfcda2ab Mon Sep 17 00:00:00 2001 From: Chen Ridong Date: Wed, 26 Nov 2025 09:11:58 +0000 Subject: [PATCH] cpuset: Remove unnecessary checks in rebuild_sched_domains_locked Commit 406100f3da08 ("cpuset: fix race between hotplug work and later CPU offline") added a check for empty effective_cpus in partitions for cgroup v2. However, this check did not account for remote partitions, which were introduced later. After commit 2125c0034c5d ("cgroup/cpuset: Make cpuset hotplug processing synchronous"), cpuset hotplug handling is now synchronous. This eliminates the race condition with subsequent CPU offline operations that the original check aimed to fix. Instead of extending the check to support remote partitions, this patch removes all the redundant effective_cpus check. Additionally, it adds a check and warning to verify that all generated sched domains consist of active CPUs, preventing partition_sched_domains from being invoked with offline CPUs. Signed-off-by: Chen Ridong Reviewed-by: Waiman Long Signed-off-by: Tejun Heo --- kernel/cgroup/cpuset.c | 52 +++++++++++++----------------------------- 1 file changed, 16 insertions(+), 36 deletions(-) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 6e6eb09b8db6..fea577b4016a 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1103,53 +1103,33 @@ void dl_rebuild_rd_accounting(void) */ void rebuild_sched_domains_locked(void) { - struct cgroup_subsys_state *pos_css; struct sched_domain_attr *attr; cpumask_var_t *doms; - struct cpuset *cs; int ndoms; + int i; lockdep_assert_cpus_held(); lockdep_assert_held(&cpuset_mutex); force_sd_rebuild = false; - /* - * If we have raced with CPU hotplug, return early to avoid - * passing doms with offlined cpu to partition_sched_domains(). - * Anyways, cpuset_handle_hotplug() will rebuild sched domains. - * - * With no CPUs in any subpartitions, top_cpuset's effective CPUs - * should be the same as the active CPUs, so checking only top_cpuset - * is enough to detect racing CPU offlines. - */ - if (cpumask_empty(subpartitions_cpus) && - !cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask)) - return; - - /* - * With subpartition CPUs, however, the effective CPUs of a partition - * root should be only a subset of the active CPUs. Since a CPU in any - * partition root could be offlined, all must be checked. - */ - if (!cpumask_empty(subpartitions_cpus)) { - rcu_read_lock(); - cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { - if (!is_partition_valid(cs)) { - pos_css = css_rightmost_descendant(pos_css); - continue; - } - if (!cpumask_subset(cs->effective_cpus, - cpu_active_mask)) { - rcu_read_unlock(); - return; - } - } - rcu_read_unlock(); - } - /* Generate domain masks and attrs */ ndoms = generate_sched_domains(&doms, &attr); + /* + * cpuset_hotplug_workfn is invoked synchronously now, thus this + * function should not race with CPU hotplug. And the effective CPUs + * must not include any offline CPUs. Passing an offline CPU in the + * doms to partition_sched_domains() will trigger a kernel panic. + * + * We perform a final check here: if the doms contains any + * offline CPUs, a warning is emitted and we return directly to + * prevent the panic. + */ + for (i = 0; i < ndoms; ++i) { + if (WARN_ON_ONCE(!cpumask_subset(doms[i], cpu_active_mask))) + return; + } + /* Have scheduler rebuild the domains */ partition_sched_domains(ndoms, doms, attr); }