[RFC PATCH 3/3] sched/topology: Tear down domains without active domain housekeeping CPUs

[Guopeng Zhang <guopeng.zhang@linux.dev>]

From: Guopeng Zhang <zhangguopeng@kylinos.cn>

During suspend, freeze_secondary_cpus() takes every CPU except the primary
offline. If the primary CPU is excluded from HK_TYPE_DOMAIN, offlining the
last domain housekeeping CPU leaves no active CPU from which to build the
fallback scheduler domain.

The frozen CPU-hotplug callback nevertheless requests one domain by
passing a non-zero domain count with a NULL domain array.
partition_sched_domains_locked() then constructs the fallback span from
cpu_active_mask and housekeeping_cpumask(HK_TYPE_DOMAIN), which is empty.
build_sched_domains() warns about the empty span, followed by a general
protection fault in build_perf_domains().

Make cpuset_reset_sched_domains(), including its !CONFIG_CPUSETS stub,
request zero domains when no active HK_TYPE_DOMAIN CPU remains.
Distinguish that explicit zero-domain request from a non-zero request with
a NULL domain array, for which the existing fallback-domain behavior must
be retained.

Fixes: d35be8bab9b0 ("CPU hotplug, cpusets, suspend: Don't modify cpusets during suspend/resume")
Signed-off-by: Guopeng Zhang <zhangguopeng@kylinos.cn>
---
 include/linux/cpuset.h  | 7 ++++++-
 kernel/cgroup/cpuset.c  | 6 +++++-
 kernel/sched/topology.c | 9 ++++-----
 3 files changed, 15 insertions(+), 7 deletions(-)

diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index a67ba1b32d16..461ba4876a8e 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -10,6 +10,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/isolation.h>
 #include <linux/sched/topology.h>
 #include <linux/sched/task.h>
 #include <linux/cpumask.h>
@@ -284,7 +285,11 @@ static inline void rebuild_sched_domains(void)
 
 static inline void cpuset_reset_sched_domains(void)
 {
-	partition_sched_domains(1, NULL, NULL);
+	if (cpumask_intersects(cpu_active_mask,
+			       housekeeping_cpumask(HK_TYPE_DOMAIN)))
+		partition_sched_domains(1, NULL, NULL);
+	else
+		partition_sched_domains(0, NULL, NULL);
 }
 
 static inline void cpuset_print_current_mems_allowed(void)
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 03e82d6026f5..1e66723e01b4 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1076,7 +1076,11 @@ void rebuild_sched_domains(void)
 void cpuset_reset_sched_domains(void)
 {
 	mutex_lock(&cpuset_mutex);
-	partition_sched_domains(1, NULL, NULL);
+	if (cpumask_intersects(cpu_active_mask,
+			       housekeeping_cpumask(HK_TYPE_DOMAIN)))
+		partition_sched_domains(1, NULL, NULL);
+	else
+		partition_sched_domains(0, NULL, NULL);
 	mutex_unlock(&cpuset_mutex);
 }
 
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 622e2e01974c..e8d34cb1ed84 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -3365,9 +3365,8 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
  * and partition_sched_domains() will fallback to the single partition
  * 'fallback_doms', it also forces the domains to be rebuilt.
  *
- * If doms_new == NULL it will be replaced with cpu_online_mask.
- * ndoms_new == 0 is a special case for destroying existing domains,
- * and it will not create the default domain.
+ * ndoms_new == 0 and doms_new == NULL is a special case for destroying
+ * existing domains, and it will not create the default domain.
  *
  * Call with hotplug lock and sched_domains_mutex held
  */
@@ -3387,7 +3386,7 @@ static void partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new
 	if (new_topology)
 		asym_cpu_capacity_scan();
 
-	if (!doms_new) {
+	if (ndoms_new && !doms_new) {
 		WARN_ON_ONCE(dattr_new);
 		n = 0;
 		doms_new = alloc_sched_domains(1);
@@ -3414,7 +3413,7 @@ static void partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new
 	}
 
 	n = ndoms_cur;
-	if (!doms_new) {
+	if (ndoms_new && !doms_new) {
 		n = 0;
 		doms_new = &fallback_doms;
 		cpumask_and(doms_new[0], cpu_active_mask,
-- 
2.43.0