[PATCH-next v3 3/3] cgroup/cpuset: Check remote partition underneath before making an invalid partition valid

[Waiman Long]

When re-evaluating an invalid local partition via partcmd_update,
update_parent_effective_cpumask() does not check whether a descendant
remote partition is using its exclusive CPUs, promoting the cpuset to a
valid partition root over the remote partition. This condition should only
be possible if parent is the top_cpuset and exclusive_cpus isn't empty.

This leaves an active remote partition underneath a valid
local partition root with overlapping exclusive CPUs, breaking
scheduler domain partitioning and triggering warnings in
compute_partition_effective_cpumask() and generate_sched_domains().

Fix that by checking the effective_xcpus against subpartitions_cpus
when an underneath remote partition is possible to make sure that all
the exclusive CPUs are available before allowing the invalid partition
to be switched back to valid.

Also make sure that effective_xcpus is non-empty before swtiching an
invalid partition back to valid.

Add a test case in test_cpuset_prs.sh to verify that an invalid partition
with a remote partition underneath cannot be switched back to valid
with a hotplug event.

Fixes: 181c8e091aae ("cgroup/cpuset: Introduce remote partition")
Reported-by: Sashiko <sashiko-bot@xxxxxxxxxx>
Link: https://sashiko.dev/#/bug/linux-47715b89-d5fb-4731-b7c9-070773c6ff75
Signed-off-by: Waiman Long <longman@xxxxxxxxxx>
---
 kernel/cgroup/cpuset.c                        | 42 ++++++++++++-------
 .../selftests/cgroup/test_cpuset_prs.sh       |  4 ++
 2 files changed, 30 insertions(+), 16 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 8b684361c94e..af5fd543fe88 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -2034,11 +2034,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 		 * tasks_nocpu_error() with this very mask, and a failing
 		 * write is routed to partcmd_invalidate instead.
 		 */
-		if (is_partition_invalid(cs)) {
-			adding = false;
-			deleting = cpumask_and(tmp->delmask,
-					newmask, parent->effective_xcpus);
-		} else {
+		if (is_partition_valid(cs)) {
 			cpumask_andnot(tmp->addmask, cs->effective_xcpus, newmask);
 			adding = cpumask_and(tmp->addmask, tmp->addmask,
 					     parent->effective_xcpus);
@@ -2046,6 +2042,17 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 			cpumask_andnot(tmp->delmask, newmask, cs->effective_xcpus);
 			deleting = cpumask_and(tmp->delmask, tmp->delmask,
 					       parent->effective_xcpus);
+		} else {
+			deleting = cpumask_and(tmp->delmask,
+					newmask, parent->effective_xcpus);
+
+			/* Check if a remote partition may be underneath */
+			if ((parent == &top_cpuset) &&
+			    !cpumask_empty(cs->exclusive_cpus) &&
+			    cpumask_intersects(tmp->delmask, subpartitions_cpus)) {
+				part_error = PERR_REMOTE;
+				deleting = false;
+			}
 		}
 
 		/*
@@ -2126,34 +2133,37 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 		} else if (is_partition_invalid(cs)) {
 			struct cgroup_subsys_state *css;
 			struct cpuset *child;
-			bool exclusive = true;
 
 			/*
 			 * Convert invalid partition to valid has to pass the
-			 * cpu exclusivity test when cpuset.cpus.exclusive is
-			 * empty as well as the housekeeping check.
+			 * following tests:
+			 * 1) housekeeping CPU conflict check
+			 * 2) cpu exclusivity test when cpuset.cpus.exclusive is
+			 *    empty.
+			 * 3) if parent is top_cpuset, none of the effective_xcpus
+			 *    (tmp->delmask) are in subpartitions_cpus, if not a
+			 *    remote partition may be underneath.
 			 */
 			if (prstate_housekeeping_conflict(cs->partition_root_state,
 							  parent_prs, tmp->delmask, NULL)) {
 				part_error = PERR_HKEEPING;
-				goto write_error;
-			}
-			if (cpumask_empty(cs->exclusive_cpus)) {
+			} else if (cpumask_empty(cs->exclusive_cpus)) {
 				rcu_read_lock();
 				cpuset_for_each_child(child, css, parent) {
 					if (child == cs)
 						continue;
 					if (!cpusets_are_exclusive(cs, child)) {
-						exclusive = false;
+						part_error = PERR_NOTEXCL;
 						break;
 					}
 				}
 				rcu_read_unlock();
+			} else if ((parent == &top_cpuset) &&
+				   cpumask_intersects(tmp->delmask, subpartitions_cpus)) {
+				part_error = PERR_REMOTE;
 			}
-			if (exclusive)
+			if (!part_error)
 				deleting = !cpumask_empty(tmp->delmask);
-			else
-				part_error = PERR_NOTEXCL;
 		}
 	}
 
@@ -2174,7 +2184,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 			break;
 		case PRS_INVALID_ROOT:
 		case PRS_INVALID_ISOLATED:
-			if (!part_error)
+			if (!part_error && deleting)
 				new_prs = -old_prs;
 			break;
 		}
diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
index 1e9e6b4c6f7b..3d873804abc2 100755
--- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh
+++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
@@ -563,6 +563,10 @@ TEST_MATRIX=(
 	" C1-6:P1 C3-6:P2 C5-6:P2  .       .    P1      .      .     0 A1:1-2|A2:3-4|A3:5-6 \
 								       A1:P1|A2:P1|A3:P2 5-6"
 
+	# A hotplug event will not incorrectly activate an invalid partition with
+	# a remote partition underneath.
+	"  CX1-4  C3-4:P1   .      .      P1   O1=0     .      .     0 A1:2|A2:3-4 A1:P-1|A2:P1"
+
 	#
 	#  old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
 	#  ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
-- 
2.56.0