[PATCH] cgroup/cpuset: Properly disable partition when partition state switching fails

[Waiman Long]

Before commit 103b08709e8a ("cgroup/cpuset: Fail if isolated and nohz_full
don't leave any housekeeping"), the partition state can be freely switched
from "root" to "isolated" and vice versa. After that commit, the switch
from "root" to "isolated" can fail if it exhausts all the housekeeping
CPUs. Later on, the switch from "isolated" to "root" can also fail if
some of the partition CPUs are boot-time isolated by "isolcpus".

The partition is made invalid when the switch fails. However, the
remote_partition flag for a remote partition can remain set and the CPUs
from the invalidated partition aren't cleared from subpartitions_cpus.
Fix this by properly disable the partition in this case.

In the case of remote_partition flag, it should be cleared for a
invalidated remote partition. To be safe, the reset_partition_data() is
now enhanced to always clear the remote_partition flag. So there is no
need to explicitly clear remote_partition in remote_partition_disable().

On a x86 test system with boot option "isolcpus=10 cgroup_debug" set
and more than 16 cores, the following commands was executed after boot.

  # cd /sys/fs/cgroup
  # echo +cpuset > cgroup.subtree_control
  # cat cpuset.cpus.isolated
  10
  # mkdir A
  # echo 10-12 > A/cpuset.cpus
  # echo isolated > A/cpuset.cpus.partition
  # cat A/cpuset.cpus.partition
  isolated

Before the patch:

  # echo root > A/cpuset.cpus.partition
  # cat A/cpuset.cpus.partition
  root invalid (partition config conflicts with housekeeping setup)
  # cat cpuset.cpus.isolated .__DEBUG__.cpuset.cpus.subpartitions
  10-12
  10-12

After the patch:

  # echo root > A/cpuset.cpus.partition
  # cat A/cpuset.cpus.partition
  root invalid (partition config conflicts with housekeeping setup)
  # cat cpuset.cpus.isolated .__DEBUG__.cpuset.cpus.subpartitions
  10

Reported-by: Tejun Heo <tj@xxxxxxxxxx>
Link: https://lore.kernel.org/lkml/7f4c57b26ad120ab30adf35653f1dd94@xxxxxxxxxx/
Fixes: 103b08709e8a ("cgroup/cpuset: Fail if isolated and nohz_full don't leave any housekeeping")
Signed-off-by: Waiman Long <longman@xxxxxxxxxx>
---
 kernel/cgroup/cpuset.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 4a915da37bb3..9874c25eb83c 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1229,6 +1229,7 @@ static void reset_partition_data(struct cpuset *cs)
 
 	lockdep_assert_held(&callback_lock);
 
+	cs->remote_partition = false;
 	if (cpumask_empty(cs->exclusive_cpus))
 		cpumask_clear(cs->effective_xcpus);
 
@@ -1615,7 +1616,6 @@ static void remote_partition_disable(struct cpuset *cs, struct tmpmasks *tmp)
 		     !cpumask_empty(subpartitions_cpus));
 
 	spin_lock_irq(&callback_lock);
-	cs->remote_partition = false;
 	partition_xcpus_del(cs->partition_root_state, NULL, cs->effective_xcpus);
 	if (cs->prs_err)
 		cs->partition_root_state = -cs->partition_root_state;
@@ -2892,6 +2892,7 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 	struct cpuset *parent = parent_cs(cs);
 	struct tmpmasks tmpmask;
 	bool isolcpus_updated = false;
+	bool disable_partition = false;
 
 	if (old_prs == new_prs)
 		return 0;
@@ -2946,27 +2947,32 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 		 */
 		if (((new_prs == PRS_ISOLATED) &&
 		     !isolated_cpus_can_update(cs->effective_xcpus, NULL)) ||
-		    prstate_housekeeping_conflict(new_prs, cs->effective_xcpus))
+		    prstate_housekeeping_conflict(new_prs, cs->effective_xcpus)) {
 			err = PERR_HKEEPING;
-		else
+			disable_partition = true;
+		} else {
 			isolcpus_updated = true;
+		}
 	} else {
 		/*
 		 * Switching back to member is always allowed even if it
 		 * disables child partitions.
 		 */
+		disable_partition = true;
+	}
+out:
+	if (disable_partition) {
 		if (is_remote_partition(cs))
 			remote_partition_disable(cs, &tmpmask);
 		else
 			update_parent_effective_cpumask(cs, partcmd_disable,
 							NULL, &tmpmask);
-
 		/*
 		 * Invalidation of child partitions will be done in
-		 * update_cpumasks_hier().
+		 * update_cpumasks_hier() below.
 		 */
 	}
-out:
+
 	/*
 	 * Make partition invalid if an error happens.
 	 */
-- 
2.55.0