[PATCH v5 09/12] cpuset: Add dhm_cycling_cpus mask to suppress transient invalidation

[Qiliang Yuan]

When the cpuset code cycles a CPU through hotplug to apply kernel-noise
isolation (remove_cpu followed by add_cpu), the CPU disappears from
cpu_active_mask temporarily. cpuset_hotplug_update_tasks() sees an
empty effective CPU set on the isolated partition and issues
partcmd_invalidate, tearing down the partition. The subsequent add_cpu
brings the CPU back online, but the partition has already been marked
invalid and requires manual user intervention to restore.

Add a global dhm_cycling_cpus cpumask protected by dhm_cycling_lock.
The isolation cycling path sets the bits for CPUs being cycled before
calling remove_cpu(), clears them after add_cpu() completes.
cpuset_hotplug_update_tasks() checks whether any of the cpuset's
effective exclusive CPUs are in dhm_cycling_cpus and skips the
invalidation command when they are, treating the transient empty-CPU
state as expected rather than an error.

A global cpumask avoids the need to walk the cpuset tree to find the
owning cpuset during the cycling loop which runs without cpuset locks.

Signed-off-by: Qiliang Yuan <odys.yuan@xxxxxxxxx>
---
 kernel/cgroup/cpuset.c | 40 ++++++++++++++++++++++++++++++++++++++--
 1 file changed, 38 insertions(+), 2 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 8b3bb034adf62..6213e63cf348d 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -157,6 +157,14 @@ static bool		update_housekeeping;	/* RWCS */
  */
 static cpumask_var_t	isolated_hk_cpus;	/* T */
 
+/*
+ * CPUs currently being cycled through hotplug for kernel-noise isolation.
+ * Protected by dhm_cycling_lock; read in cpuset_hotplug_update_tasks() to
+ * suppress transient partition invalidation during the offline step.
+ */
+static DEFINE_SPINLOCK(dhm_cycling_lock);
+static cpumask_var_t	dhm_cycling_cpus;
+
 /*
  * A flag to force sched domain rebuild at the end of an operation.
  * It can be set in
@@ -3906,6 +3914,7 @@ int __init cpuset_init(void)
 	BUG_ON(!zalloc_cpumask_var(&subpartitions_cpus, GFP_KERNEL));
 	BUG_ON(!zalloc_cpumask_var(&isolated_cpus, GFP_KERNEL));
 	BUG_ON(!zalloc_cpumask_var(&isolated_hk_cpus, GFP_KERNEL));
+	BUG_ON(!zalloc_cpumask_var(&dhm_cycling_cpus, GFP_KERNEL));
 
 	cpumask_setall(top_cpuset.cpus_allowed);
 	nodes_setall(top_cpuset.mems_allowed);
@@ -3991,6 +4000,20 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
 	if (remote && (cpumask_empty(subpartitions_cpus) ||
 			(cpumask_empty(&new_cpus) &&
 			 partition_is_populated(cs, NULL)))) {
+		bool cycling;
+
+		/*
+		 * Suppress transient invalidation when the offline is part
+		 * of a hotplug cycling step for kernel-noise isolation.
+		 */
+		spin_lock(&dhm_cycling_lock);
+		cycling = cpumask_available(dhm_cycling_cpus) &&
+			  cpumask_intersects(cs->effective_xcpus,
+					     dhm_cycling_cpus);
+		spin_unlock(&dhm_cycling_lock);
+		if (cycling)
+			goto unlock;
+
 		WRITE_ONCE(cs->prs_err, PERR_HOTPLUG);
 		remote_partition_disable(cs, tmp);
 		compute_effective_cpumask(&new_cpus, cs, parent);
@@ -4008,8 +4031,21 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
 	if (is_local_partition(cs) &&
 	    (!is_partition_valid(parent) ||
 	     tasks_nocpu_error(parent, cs, &new_cpus) ||
-	     cpumask_empty(subpartitions_cpus)))
-		partcmd = partcmd_invalidate;
+	     cpumask_empty(subpartitions_cpus))) {
+		bool cycling;
+
+		/*
+		 * Suppress transient invalidation when the offline is part
+		 * of a hotplug cycling step for kernel-noise isolation.
+		 */
+		spin_lock(&dhm_cycling_lock);
+		cycling = cpumask_available(dhm_cycling_cpus) &&
+			  cpumask_intersects(cs->effective_xcpus,
+					     dhm_cycling_cpus);
+		spin_unlock(&dhm_cycling_lock);
+		if (!cycling)
+			partcmd = partcmd_invalidate;
+	}
 	/*
 	 * On the other hand, an invalid partition root may be transitioned
 	 * back to a regular one with a non-empty effective xcpus.

-- 
2.43.0