[PATCH v3 3/3] cgroup/cpuset: Keep the top sched domain non-empty on CPU hotplug

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

From: Guopeng Zhang <zhangguopeng@kylinos.cn>

In cpuset_hotplug_update_tasks(), the local partition check passes only
the partition's own effective CPUs to tasks_nocpu_error(). For a
top-level partition with children, top_cpuset_sd_nocpu() treats the
children's CPUs as being returned, although hotplug does not return
them. This can leave the top sched domain empty when its last boot
domain housekeeping CPU goes offline.

For example, on a 32-CPU system with isolcpus=domain,10-31:

  echo 0,2-9 > A/cpuset.cpus
  echo root > A/cpuset.cpus.partition
  echo 5-9 > A/B/cpuset.cpus
  echo root > A/B/cpuset.cpus.partition
  echo 0 > /sys/devices/system/cpu/cpu1/online
  Oops: general protection fault
  RIP: 0010:build_perf_domains+...

The remote hotplug path does not check whether the top sched domain
is empty.

Check the full effective_xcpus of top-level local and remote partitions
without assuming any CPUs have been returned. Only invalidate a
partition to restore the top domain if it can return an active boot
domain housekeeping CPU. Partitions holding only boot-isolated or
offline housekeeping CPUs cannot do that.

Add hotplug regression tests.

Fixes: 9b496a8bbed9 ("cgroup/cpuset: Prevent leakage of isolated CPUs into sched domains")
Signed-off-by: Guopeng Zhang <zhangguopeng@kylinos.cn>
---
 kernel/cgroup/cpuset.c                        | 23 ++++++++++++++++---
 .../selftests/cgroup/test_cpuset_prs.sh       | 19 +++++++++++++++
 2 files changed, 39 insertions(+), 3 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 8b6831983803..0b392d50df27 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -4043,6 +4043,7 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
 	static nodemask_t new_mems;
 	bool cpus_updated;
 	bool mems_updated;
+	bool nocpu;
 	int partcmd = -1;
 	struct cpuset *parent;
 
@@ -4054,9 +4055,24 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
 	if (!tmp || !cs->partition_root_state)
 		goto update_tasks;
 
+	if (parent == &top_cpuset || is_remote_partition(cs)) {
+		/*
+		 * Hotplug does not return CPUs held by child partitions. Only
+		 * invalidate a partition for an empty top sched domain if it
+		 * can return an active boot domain housekeeping CPU.
+		 */
+		cpumask_and(tmp->addmask, cs->effective_xcpus,
+			    housekeeping_cpumask(HK_TYPE_DOMAIN_BOOT));
+		nocpu = cpumask_intersects(tmp->addmask, cpu_active_mask) &&
+			top_cpuset_sd_nocpu(cs->effective_xcpus, NULL);
+		nocpu |= cpumask_empty(&new_cpus) &&
+			 partition_is_populated(cs, NULL);
+	} else {
+		nocpu = tasks_nocpu_error(parent, cs, &new_cpus);
+	}
+
 	if (is_remote_partition(cs) && (cpumask_empty(subpartitions_cpus) ||
-				       (cpumask_empty(&new_cpus) &&
-					partition_is_populated(cs, NULL)))) {
+				       nocpu)) {
 		WRITE_ONCE(cs->prs_err, PERR_HOTPLUG);
 		remote_partition_disable(cs, tmp);
 		compute_effective_cpumask(&new_cpus, cs, parent);
@@ -4069,10 +4085,11 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
 	 * 2) parent is invalid or doesn't grant any cpus to child
 	 *    partitions.
 	 * 3) subpartitions_cpus is empty.
+	 * 4) top_cpuset needs an active boot domain housekeeping CPU from cs.
 	 */
 	if (is_local_partition(cs) &&
 	    (!is_partition_valid(parent) ||
-	     tasks_nocpu_error(parent, cs, &new_cpus) ||
+	     nocpu ||
 	     cpumask_empty(subpartitions_cpus)))
 		partcmd = partcmd_invalidate;
 	/*
diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
index ee4d57b7e35b..f345696e5b53 100755
--- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh
+++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
@@ -648,8 +648,27 @@ ISOLCPUS_DOMAIN_TEST_MATRIX=(
 
 	# An invalid partition can recover once it leaves a top-level HK CPU.
 	" C0-9:P1   .      .      .    C0-6,8-9 .      .      .     0 A1:0-6,8-9 A1:P1 7|"
+
+	# A local root must not count its child's CPUs as already returned.
+	" C0,2-9:P1 C5-9:P1 . . O1=0 . . . 0 A1:0,2-9|A2:5-9 A1:P-1|A2:P-1 1|"
+
+	# A remote root must return CPUs when the top domain loses its last HK CPU.
+	" X0,2-9 CX0,2-9:P1 . . O1=0 . . . 0 A2:0,2-9 A2:P-1 1|"
 )
 
+# Keep an online boot-isolated CPU at the top so hotplug does not
+# clear subpartitions_cpus before checking the individual partitions.
+if [[ "$ONLINE_LAST" -gt 10 ]]; then
+	ISOLCPUS_DOMAIN_TEST_MATRIX+=(
+		# An offline HK CPU cannot restore the top domain. Keep this local
+		# partition valid while its sibling returns active HK CPUs.
+		" O2=0:C2,10:P2 . . C0,3-9:P1 O1=0 . . . 0 A1:10|B1:0,3-9 A1:P2|B1:P-1 1-2|2"
+
+		# Check the same active-CPU rule for a remote partition.
+		" O2=0:X2,10 CX2,10:P2 . C0,3-9:P1 O1=0 . . . 0 A2:10|B1:0,3-9 A2:P2|B1:P-1 1-2|2"
+	)
+fi
+
 # Test matrix to be run when boot time nohz_full CPUs cover all CPUs except CPUs 0-7
 # This also means that CPU 8 is available and is a nohz_full CPU.
 NOHZ_FULL_TEST_MATRIX=(
-- 
2.43.0