Merge tag 'cgroup-for-7.3-rc1-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup fixes from Tejun Heo:

 - After cgroup.kill was written to a cgroup, every child cloned into it
   with CLONE_INTO_CGROUP was spuriously killed because the fork path
   snapshotted the kill counter before resolving the target cgroup

 - Releasing an isolated cpuset partition dropped the isolation of CPUs
   isolated on the kernel command line

 - Selftest and documentation fixes

* tag 'cgroup-for-7.3-rc1-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  selftests/cgroup: test clone3() into a previously killed cgroup
  cgroup: fix spurious SIGKILL of CLONE_INTO_CGROUP children
  selftests/cgroup: Add test for preserving boot-isolated CPUs
  cgroup/cpuset: Preserve boot-isolated CPUs on partition release
  selftests/cgroup: Drop invalid boot isolation comparison
  docs: cgroup-v2: fix misc.events key format description
  selftests/cgroup: Fix cg_run_in_subcgroups ignoring arg parameter
  selftests/cgroup: set the test plan after the setup checks

2 files changed, 31 insertions, 14 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index c3a12fee7528..2d532bf2c0c7 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -6873,10 +6873,7 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs)
 	spin_lock_irq(&css_set_lock);
 	cset = task_css_set(current);
 	get_css_set(cset);
-	if (kargs->cgrp)
-		kargs->kill_seq = kargs->cgrp->kill_seq;
-	else
-		kargs->kill_seq = cset->dfl_cgrp->kill_seq;
+	kargs->kill_seq = cset->dfl_cgrp->kill_seq;
 	spin_unlock_irq(&css_set_lock);
 
 	if (!(kargs->flags & CLONE_INTO_CGROUP)) {
@@ -6940,6 +6937,7 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs)
 
 	put_css_set(cset);
 	kargs->cgrp = dst_cgrp;
+	kargs->kill_seq = dst_cgrp->kill_seq;
 	return ret;
 
 err:
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;
 }
 
 /*