[PATCH v2 2/3] cgroup/cpuset: Preserve boot-isolated CPUs on partition release

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

From: Guopeng Zhang <zhangguopeng@kylinos.cn>

isolated_cpus tracks CPUs isolated with isolcpus= as well as CPUs in
isolated cpuset partitions. When an isolated partition is released,
isolated_cpus_update() removes its whole CPU mask. This also clears CPUs
which were already isolated at boot.

This can be reproduced on a cgroup v2 system booted with
isolcpus=domain,15:

    cd /sys/fs/cgroup
    echo +cpuset > cgroup.subtree_control
    mkdir cpuset-repro
    echo 15 > cpuset-repro/cpuset.cpus
    echo isolated > cpuset-repro/cpuset.cpus.partition
    echo member > cpuset-repro/cpuset.cpus.partition
    cat cpuset.cpus.isolated

CPU 15 is absent before the change. It must remain in
cpuset.cpus.isolated after the partition is released.

Update isolated_cpus one CPU at a time and keep CPUs outside the
boot-time domain housekeeping mask isolated.

Fixes: c188f33c864e ("cgroup/cpuset: Account for boot time isolated CPUs")
Signed-off-by: Guopeng Zhang <zhangguopeng@kylinos.cn>
---
 kernel/cgroup/cpuset.c | 39 +++++++++++++++++++++++++++++----------
 1 file changed, 29 insertions(+), 10 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index d100634fa12b..2538faac9aba 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1259,6 +1259,28 @@ static void reset_partition_data(struct cpuset *cs)
 		cpumask_copy(cs->effective_cpus, parent->effective_cpus);
 }
 
+/* Return true if isolated_cpus changes. */
+static bool isolated_cpu_update(int new_prs, int cpu)
+{
+	lockdep_assert_held(&callback_lock);
+	lockdep_assert_held(&cpuset_mutex);
+
+	if (new_prs == PRS_ISOLATED) {
+		if (cpumask_test_cpu(cpu, isolated_cpus))
+			return false;
+		cpumask_set_cpu(cpu, isolated_cpus);
+		return true;
+	}
+
+	/* CPUs isolated at boot must remain isolated. */
+	if (!cpumask_test_cpu(cpu,
+			      housekeeping_cpumask(HK_TYPE_DOMAIN_BOOT)) ||
+	    !cpumask_test_cpu(cpu, isolated_cpus))
+		return false;
+	cpumask_clear_cpu(cpu, isolated_cpus);
+	return true;
+}
+
 /*
  * isolated_cpus_update - Update the isolated_cpus mask
  * @old_prs: old partition_root_state
@@ -1267,19 +1289,16 @@ static void reset_partition_data(struct cpuset *cs)
  */
 static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus)
 {
+	bool updated = false;
+	int cpu;
+
 	WARN_ON_ONCE(old_prs == new_prs);
 	lockdep_assert_held(&callback_lock);
 	lockdep_assert_held(&cpuset_mutex);
-	if (new_prs == PRS_ISOLATED) {
-		if (cpumask_subset(xcpus, isolated_cpus))
-			return;
-		cpumask_or(isolated_cpus, isolated_cpus, xcpus);
-	} else {
-		if (!cpumask_intersects(xcpus, isolated_cpus))
-			return;
-		cpumask_andnot(isolated_cpus, isolated_cpus, xcpus);
-	}
-	update_housekeeping = true;
+	for_each_cpu(cpu, xcpus)
+		updated |= isolated_cpu_update(new_prs, cpu);
+	if (updated)
+		update_housekeeping = true;
 }
 
 /*
-- 
2.43.0