[PATCH 30/33] kthread: Honour kthreads preferred affinity after cpuset changes

[Frederic Weisbecker <frederic@kernel.org>]

When cpuset isolated partitions get updated, unbound kthreads get
indifferently affine to all non isolated CPUs, regardless of their
individual affinity preferences.

For example kswapd is a per-node kthread that prefers to be affine to
the node it refers to. Whenever an isolated partition is created,
updated or deleted, kswapd's node affinity is going to be broken if any
CPU in the related node is not isolated because kswapd will be affine
globally.

Fix this with letting the consolidated kthread managed affinity code do
the affinity update on behalf of cpuset.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
---
 include/linux/kthread.h  |  1 +
 kernel/cgroup/cpuset.c   |  5 ++---
 kernel/kthread.c         | 41 ++++++++++++++++++++++++++++++----------
 kernel/sched/isolation.c |  3 +++
 4 files changed, 37 insertions(+), 13 deletions(-)

diff --git a/include/linux/kthread.h b/include/linux/kthread.h
index 8d27403888ce..c92c1149ee6e 100644
--- a/include/linux/kthread.h
+++ b/include/linux/kthread.h
@@ -100,6 +100,7 @@ void kthread_unpark(struct task_struct *k);
 void kthread_parkme(void);
 void kthread_exit(long result) __noreturn;
 void kthread_complete_and_exit(struct completion *, long) __noreturn;
+int kthreads_update_housekeeping(void);
 
 int kthreadd(void *unused);
 extern struct task_struct *kthreadd_task;
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 1cc83a3c25f6..c8cfaf5cd4a1 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1208,11 +1208,10 @@ void cpuset_update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus)
 
 		if (top_cs) {
 			/*
+			 * PF_KTHREAD tasks are handled by housekeeping.
 			 * PF_NO_SETAFFINITY tasks are ignored.
-			 * All per cpu kthreads should have PF_NO_SETAFFINITY
-			 * flag set, see kthread_set_per_cpu().
 			 */
-			if (task->flags & PF_NO_SETAFFINITY)
+			if (task->flags & (PF_KTHREAD | PF_NO_SETAFFINITY))
 				continue;
 			cpumask_andnot(new_cpus, possible_mask, subpartitions_cpus);
 		} else {
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 968fa5868d21..03008154249c 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -891,14 +891,7 @@ int kthread_affine_preferred(struct task_struct *p, const struct cpumask *mask)
 }
 EXPORT_SYMBOL_GPL(kthread_affine_preferred);
 
-/*
- * Re-affine kthreads according to their preferences
- * and the newly online CPU. The CPU down part is handled
- * by select_fallback_rq() which default re-affines to
- * housekeepers from other nodes in case the preferred
- * affinity doesn't apply anymore.
- */
-static int kthreads_online_cpu(unsigned int cpu)
+static int kthreads_update_affinity(bool force)
 {
 	cpumask_var_t affinity;
 	struct kthread *k;
@@ -924,7 +917,8 @@ static int kthreads_online_cpu(unsigned int cpu)
 		/*
 		 * Unbound kthreads without preferred affinity are already affine
 		 * to housekeeping, whether those CPUs are online or not. So no need
-		 * to handle newly online CPUs for them.
+		 * to handle newly online CPUs for them. However housekeeping changes
+		 * have to be applied.
 		 *
 		 * But kthreads with a preferred affinity or node are different:
 		 * if none of their preferred CPUs are online and part of
@@ -932,7 +926,7 @@ static int kthreads_online_cpu(unsigned int cpu)
 		 * But as soon as one of their preferred CPU becomes online, they must
 		 * be affine to them.
 		 */
-		if (k->preferred_affinity || k->node != NUMA_NO_NODE) {
+		if (force || k->preferred_affinity || k->node != NUMA_NO_NODE) {
 			kthread_fetch_affinity(k, affinity);
 			set_cpus_allowed_ptr(k->task, affinity);
 		}
@@ -943,6 +937,33 @@ static int kthreads_online_cpu(unsigned int cpu)
 	return ret;
 }
 
+/**
+ * kthreads_update_housekeeping - Update kthreads affinity on cpuset change
+ *
+ * When cpuset changes a partition type to/from "isolated" or updates related
+ * cpumasks, propagate the housekeeping cpumask change to preferred kthreads
+ * affinity.
+ *
+ * Returns 0 if successful, -ENOMEM if temporary mask couldn't
+ * be allocated or -EINVAL in case of internal error.
+ */
+int kthreads_update_housekeeping(void)
+{
+	return kthreads_update_affinity(true);
+}
+
+/*
+ * Re-affine kthreads according to their preferences
+ * and the newly online CPU. The CPU down part is handled
+ * by select_fallback_rq() which default re-affines to
+ * housekeepers from other nodes in case the preferred
+ * affinity doesn't apply anymore.
+ */
+static int kthreads_online_cpu(unsigned int cpu)
+{
+	return kthreads_update_affinity(false);
+}
+
 static int kthreads_init(void)
 {
 	return cpuhp_setup_state(CPUHP_AP_KTHREADS_ONLINE, "kthreads:online",
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 84a257d05918..c499474866b8 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -157,6 +157,9 @@ int housekeeping_update(struct cpumask *isol_mask, enum hk_type type)
 	err = tmigr_isolated_exclude_cpumask(isol_mask);
 	WARN_ON_ONCE(err < 0);
 
+	err = kthreads_update_housekeeping();
+	WARN_ON_ONCE(err < 0);
+
 	kfree(old);
 
 	return err;
-- 
2.51.1