Merge tag 'sched-core-2020-12-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Thomas Gleixner:

 - migrate_disable/enable() support which originates from the RT tree
   and is now a prerequisite for the new preemptible kmap_local() API
   which aims to replace kmap_atomic().

 - A fair amount of topology and NUMA related improvements

 - Improvements for the frequency invariant calculations

 - Enhanced robustness for the global CPU priority tracking and decision
   making

 - The usual small fixes and enhancements all over the place

* tag 'sched-core-2020-12-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (61 commits)
  sched/fair: Trivial correction of the newidle_balance() comment
  sched/fair: Clear SMT siblings after determining the core is not idle
  sched: Fix kernel-doc markup
  x86: Print ratio freq_max/freq_base used in frequency invariance calculations
  x86, sched: Use midpoint of max_boost and max_P for frequency invariance on AMD EPYC
  x86, sched: Calculate frequency invariance for AMD systems
  irq_work: Optimize irq_work_single()
  smp: Cleanup smp_call_function*()
  irq_work: Cleanup
  sched: Limit the amount of NUMA imbalance that can exist at fork time
  sched/numa: Allow a floating imbalance between NUMA nodes
  sched: Avoid unnecessary calculation of load imbalance at clone time
  sched/numa: Rename nr_running and break out the magic number
  sched: Make migrate_disable/enable() independent of RT
  sched/topology: Condition EAS enablement on FIE support
  arm64: Rebuild sched domains on invariance status changes
  sched/topology,schedutil: Wrap sched domains rebuild
  sched/uclamp: Allow to reset a task uclamp constraint value
  sched/core: Fix typos in comments
  Documentation: scheduler: fix information on arch SD flags, sched_domain and sched_debug
  ...

1 files changed, 28 insertions, 5 deletions

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 57b5b5d0a5fd..53c70c470a38 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -983,25 +983,48 @@ partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
  */
 static 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;
 
 	lockdep_assert_cpus_held();
 	percpu_rwsem_assert_held(&cpuset_rwsem);
 
 	/*
-	 * We have raced with CPU hotplug. Don't do anything to avoid
+	 * If we have raced with CPU hotplug, return early to avoid
 	 * passing doms with offlined cpu to partition_sched_domains().
-	 * Anyways, hotplug work item will rebuild sched domains.
+	 * Anyways, cpuset_hotplug_workfn() 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 (!top_cpuset.nr_subparts_cpus &&
 	    !cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask))
 		return;
 
-	if (top_cpuset.nr_subparts_cpus &&
-	   !cpumask_subset(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 (top_cpuset.nr_subparts_cpus) {
+		rcu_read_lock();
+		cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) {
+			if (!is_partition_root(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);