[PATCH v2 3/3] cgroup/cpuset: Do housekeeping check when isolated child with root parent may get more xcpus

[Waiman Long]

It is reported by sashiko and Guopeng that when an isolated child with
root parent gets more isolated CPUs from the expansion of the parent's
effective_xcpus, it is possible that all the active housekeeping CPUs
may be gone. So a prstate_housekeeping_conflict() should be performed
when that happens. Add the check to make sure that we can't exhaust
all the active housekeeping CPUs.

Test cases are added to the NOHZ_FULL_TEST_MATRIX of test_cpuset_prs.sh
to test that.

Reported-by: Guopeng Zhang <guopeng.zhang@xxxxxxxxx>
Link: https://lore.kernel.org/lkml/ed6fecb4-38e9-4a73-8c1a-7bdd80175a69@xxxxxxxxx
Fixes: e2ffe502ba45 ("cgroup/cpuset: Add cpuset.cpus.exclusive for v2")
Signed-off-by: Waiman Long <longman@xxxxxxxxxx>
---
 kernel/cgroup/cpuset.c                         | 18 +++++++++++++++---
 .../selftests/cgroup/test_cpuset_prs.sh        | 10 ++++++++--
 2 files changed, 23 insertions(+), 5 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index ed014ecb770c..6e136888fc8e 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -2119,10 +2119,22 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 			 * If there is an expansion of parent's effective_xcpus,
 			 * we may take more xcpus from parent. The parent's
 			 * effective_cpus should still have active CPUs or nocpu
-			 * should have been set.
+			 * should have been set. We also need to do a
+			 * housekeeping check for an isolated child with root
+			 * parent to make sure that it won't exhaust all the
+			 * active housekeeping CPUs.
 			 */
-			deleting = cpumask_andnot(tmp->delmask, tmp->delmask,
-						  cs->effective_xcpus);
+			cpumask_andnot(tmp->addmask, cs->effective_xcpus, tmp->delmask);
+			if ((parent_prs == PRS_ROOT) && (old_prs == PRS_ISOLATED) &&
+			    prstate_housekeeping_conflict(old_prs, parent_prs,
+							  tmp->delmask, tmp->addmask)) {
+				adding = cpumask_and(tmp->addmask, cs->effective_xcpus,
+						     tmp->delmask);
+				part_error = PERR_HKEEPING;
+			} else {
+				deleting = cpumask_andnot(tmp->delmask, tmp->delmask,
+							  cs->effective_xcpus);
+			}
 		} else if (is_partition_invalid(cs)) {
 			struct cgroup_subsys_state *css;
 			struct cpuset *child;
diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
index 844efdf029cd..bdca6c471f87 100755
--- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh
+++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
@@ -137,7 +137,8 @@ LAST_PRESENT_CPU=$(cat /sys/devices/system/cpu/present | sed -e "s/.*[,-]//")
 # If isolated CPUs have been reserved at boot time (as shown in
 # /sys/devices/system/cpu/isolated), these isolated CPUs should be outside of
 # CPUs 0-8 that will be used by this script for testing purpose. If not, some
-# of the tests may fail incorrectly.
+# of the tests may fail incorrectly. The first boot isolated CPU should be
+# 10 or above.
 #
 # The current set of isolated CPUs (as shown in cpuset.cpus.isolated) should
 # be the same as the boot value. If not, wait a bit and retry again just in
@@ -156,7 +157,7 @@ TEST_ISOLCPUS=
 [[ -n "$BOOT_ISOLCPUS" ]] && {
 	FIRST_ISOLCPUS=$(echo $BOOT_ISOLCPUS | sed -e "s/[,-].*//")
 	echo "Boot isolated CPUs: $BOOT_ISOLCPUS"
-	[[ $FIRST_ISOLCPUS -le 8 ]] &&
+	[[ $FIRST_ISOLCPUS -le 9 ]] &&
 		skip_test "Boot isolated CPUs overlap CPUs to be tested"
 }
 
@@ -602,6 +603,7 @@ ISOLCPUS_TEST_MATRIX=(
 )
 
 # 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=(
 	#  old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
 	#  ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
@@ -610,6 +612,10 @@ NOHZ_FULL_TEST_MATRIX=(
 	" C2-7:P2    .      .      .     C0-4    .      .      .     0 A1:0-4 A1:P2 0-4"
 	" C1-7:P2 C5-7:P2   .      .       .     .      .    C0:P2   0 A1:1-4|A2:5-7|B1:0
 								       A1:P2|A2:P2|B1:P-2 1-7"
+	# An isolated child partition cannot grow to take over the last
+	# housekeeping CPU when its parent expands the exclusive CPUs.
+	" C0-8:X1-8:P1 CX0-8:P2 .  .     X0-7    .      .      .     0 A1:0-7|A2:0-7 A1:P1|A2:P-2 ."
+	" C0-8:X0-6:P1 CX0-8:P2 .  .     X2-8    .      .      .     0 A1:|A2:2-8 A1:P1|A2:P2 2-8"
 )
 
 #
-- 
2.56.0