[PATCH v6 7/8] cgroup/cpuset: Defer housekeeping_update() calls from CPU hotplug to workqueue

[Waiman Long <longman@redhat.com>]

The cpuset_handle_hotplug() may need to invoke housekeeping_update(),
for instance, when an isolated partition is invalidated because its
last active CPU has been put offline.

As we are going to enable dynamic update to the nozh_full housekeeping
cpumask (HK_TYPE_KERNEL_NOISE) soon with the help of CPU hotplug,
allowing the CPU hotplug path to call into housekeeping_update() directly
from update_isolation_cpumasks() will likely cause deadlock. So we
have to defer any call to housekeeping_update() after the CPU hotplug
operation has finished. This is now done via the workqueue where
the update_hk_sched_domains() function will be invoked via the
hk_sd_workfn().

An concurrent cpuset control file write may have executed the required
update_hk_sched_domains() function before the work function is called. So
the work function call may become a no-op when it is invoked.

Signed-off-by: Waiman Long <longman@redhat.com>
---
 kernel/cgroup/cpuset.c                        | 31 ++++++++++++++++---
 .../selftests/cgroup/test_cpuset_prs.sh       | 11 ++++++-
 2 files changed, 36 insertions(+), 6 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 3d0d18bf182f..2c80bfc30bbc 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1323,6 +1323,16 @@ static void update_hk_sched_domains(void)
 		rebuild_sched_domains_locked();
 }
 
+/*
+ * Work function to invoke update_hk_sched_domains()
+ */
+static void hk_sd_workfn(struct work_struct *work)
+{
+	cpuset_full_lock();
+	update_hk_sched_domains();
+	cpuset_full_unlock();
+}
+
 /**
  * rm_siblings_excl_cpus - Remove exclusive CPUs that are used by sibling cpusets
  * @parent: Parent cpuset containing all siblings
@@ -3795,6 +3805,7 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
  */
 static void cpuset_handle_hotplug(void)
 {
+	static DECLARE_WORK(hk_sd_work, hk_sd_workfn);
 	static cpumask_t new_cpus;
 	static nodemask_t new_mems;
 	bool cpus_updated, mems_updated;
@@ -3877,11 +3888,21 @@ static void cpuset_handle_hotplug(void)
 	}
 
 
-	if (update_housekeeping || force_sd_rebuild) {
-		mutex_lock(&cpuset_mutex);
-		update_hk_sched_domains();
-		mutex_unlock(&cpuset_mutex);
-	}
+	/*
+	 * Queue a work to call housekeeping_update() & rebuild_sched_domains()
+	 * There will be a slight delay before the HK_TYPE_DOMAIN housekeeping
+	 * cpumask can correctly reflect what is in isolated_cpus.
+	 *
+	 * We rely on WORK_STRUCT_PENDING_BIT to not requeue a work item that
+	 * is still pending. Before the pending bit is cleared, the work data
+	 * is copied out and work item dequeued. So it is possible to queue
+	 * the work again before the hk_sd_workfn() is invoked to process the
+	 * previously queued work. Since hk_sd_workfn() doesn't use the work
+	 * item at all, this is not a problem.
+	 */
+	if (update_housekeeping || force_sd_rebuild)
+		queue_work(system_unbound_wq, &hk_sd_work);
+
 	free_tmpmasks(ptmp);
 }
 
diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
index 0c5db118f2d1..dc2dff361ec6 100755
--- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh
+++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
@@ -246,6 +246,9 @@ TEST_MATRIX=(
 	"  C2-3:P1  C3:P1   .      .     O3=0    .      .      .     0 A1:2|A2: A1:P1|A2:P1"
 	"  C2-3:P1  C3:P1   .      .    T:O2=0   .      .      .     0 A1:3|A2:3 A1:P1|A2:P-1"
 	"  C2-3:P1  C3:P1   .      .      .    T:O3=0   .      .     0 A1:2|A2:2 A1:P1|A2:P-1"
+	"  C2-3:P1  C3:P2   .      .    T:O2=0   .      .      .     0 A1:3|A2:3 A1:P1|A2:P-2"
+	"  C1-3:P1  C3:P2   .      .      .    T:O3=0   .      .     0 A1:1-2|A2:1-2 A1:P1|A2:P-2 3|"
+	"  C1-3:P1  C3:P2   .      .      .    T:O3=0  O3=1    .     0 A1:1-2|A2:3 A1:P1|A2:P2  3"
 	"$SETUP_A123_PARTITIONS    .     O1=0    .      .      .     0 A1:|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
 	"$SETUP_A123_PARTITIONS    .     O2=0    .      .      .     0 A1:1|A2:|A3:3 A1:P1|A2:P1|A3:P1"
 	"$SETUP_A123_PARTITIONS    .     O3=0    .      .      .     0 A1:1|A2:2|A3: A1:P1|A2:P1|A3:P1"
@@ -762,7 +765,7 @@ check_cgroup_states()
 # only CPUs in isolated partitions as well as those that are isolated at
 # boot time.
 #
-# $1 - expected isolated cpu list(s) <isolcpus1>{,<isolcpus2>}
+# $1 - expected isolated cpu list(s) <isolcpus1>{|<isolcpus2>}
 # <isolcpus1> - expected sched/domains value
 # <isolcpus2> - cpuset.cpus.isolated value = <isolcpus1> if not defined
 #
@@ -771,6 +774,7 @@ check_isolcpus()
 	EXPECTED_ISOLCPUS=$1
 	ISCPUS=${CGROUP2}/cpuset.cpus.isolated
 	ISOLCPUS=$(cat $ISCPUS)
+	HKICPUS=$(cat /sys/devices/system/cpu/isolated)
 	LASTISOLCPU=
 	SCHED_DOMAINS=/sys/kernel/debug/sched/domains
 	if [[ $EXPECTED_ISOLCPUS = . ]]
@@ -808,6 +812,11 @@ check_isolcpus()
 	ISOLCPUS=
 	EXPECTED_ISOLCPUS=$EXPECTED_SDOMAIN
 
+	#
+	# The inverse of HK_TYPE_DOMAIN cpumask in $HKICPUS should match $ISOLCPUS
+	#
+	[[ "$ISOLCPUS" != "$HKICPUS" ]] && return 1
+
 	#
 	# Use the sched domain in debugfs to check isolated CPUs, if available
 	#
-- 
2.53.0