cgroup/cpuset: Use effective_xcpus in partcmd_update add/del mask calculation

When sibling CPU exclusion occurs, a partition's user_xcpus may contain
CPUs that were never actually granted to it. These CPUs are present in
user_xcpus(cs) but not in cs->effective_xcpus.

The partcmd_update path in update_parent_effective_cpumask() uses
user_xcpus(cs) (via the local variable xcpus) to compute the addmask
(CPUs to return to parent) and delmask (CPUs to request from parent).
This is incorrect:

 1) When newmask removes a CPU that was previously excluded by a
    sibling, addmask incorrectly includes that CPU and tries to return
    it to the parent even though the partition never actually owned it,
    causing CPU overlap with sibling partitions and triggering warnings
    in generate_sched_domains().

 2) When newmask adds a previously excluded CPU that is now available,
    delmask fails to request it from the parent because user_xcpus(cs)
    already includes it.

Fix this by using cs->effective_xcpus instead of user_xcpus(cs) in all
partcmd_update paths that calculate addmask or delmask, including the
PERR_NOCPUS error handling paths.

Reproducers:

  Example 1 - Removing a sibling-excluded CPU incorrectly returns it:

    # cd /sys/fs/cgroup
    # echo "0-1" > a1/cpuset.cpus
    # echo "root" > a1/cpuset.cpus.partition
    # echo "0-2" > b1/cpuset.cpus
    # echo "root" > b1/cpuset.cpus.partition
    # echo "2" > b1/cpuset.cpus
    # cat cpuset.cpus.effective
    # Actual: 0-1,3    Expected: 3

  Example 2 - Expanding to a previously excluded CPU fails to request it:

    # cd /sys/fs/cgroup
    # echo "0-1" > a1/cpuset.cpus
    # echo "root" > a1/cpuset.cpus.partition
    # echo "0-2" > b1/cpuset.cpus
    # echo "root" > b1/cpuset.cpus.partition
    # echo "member" > a1/cpuset.cpus.partition
    # echo "1-2" > b1/cpuset.cpus
    # cat cpuset.cpus.effective
    # Actual: 0-1,3    Expected: 0,3

Fixes: 2a3602030d80 ("cgroup/cpuset: Don't invalidate sibling partitions on cpuset.cpus conflict")
Cc: stable@vger.kernel.org # v7.0+
Suggested-by: Zhang Guopeng <zhangguopeng@kylinos.cn>
Signed-off-by: Sun Shaojie <sunshaojie@kylinos.cn>
Reviewed-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 5c33ab20cc208b9cd06cc42be278ffc42de4df8f..c9e14fda3d6fdcdcb2f58a418afd45a6233ceacd 100644 (file)
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1811,9 +1811,9 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
                 * Compute add/delete mask to/from effective_cpus
                 *
                 * For valid partition:
-                *   addmask = exclusive_cpus & ~newmask
+                *   addmask = effective_xcpus & ~newmask
                 *                            & parent->effective_xcpus
-                *   delmask = newmask & ~exclusive_cpus
+                *   delmask = newmask & ~effective_xcpus
                 *                     & parent->effective_xcpus
                 *
                 * For invalid partition:
@@ -1825,11 +1825,11 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
                        deleting = cpumask_and(tmp->delmask,
                                        newmask, parent->effective_xcpus);
                } else {
-                       cpumask_andnot(tmp->addmask, xcpus, newmask);
+                       cpumask_andnot(tmp->addmask, cs->effective_xcpus, newmask);
                        adding = cpumask_and(tmp->addmask, tmp->addmask,
                                             parent->effective_xcpus);
 
-                       cpumask_andnot(tmp->delmask, newmask, xcpus);
+                       cpumask_andnot(tmp->delmask, newmask, cs->effective_xcpus);
                        deleting = cpumask_and(tmp->delmask, tmp->delmask,
                                               parent->effective_xcpus);
                }
@@ -1868,7 +1868,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
                        part_error = PERR_NOCPUS;
                        deleting = false;
                        adding = cpumask_and(tmp->addmask,
-                                            xcpus, parent->effective_xcpus);
+                                            cs->effective_xcpus, parent->effective_xcpus);
                }
        } else {
                /*
@@ -1890,7 +1890,8 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
                        part_error = PERR_NOCPUS;
                        if (is_partition_valid(cs))
                                adding = cpumask_and(tmp->addmask,
-                                               xcpus, parent->effective_xcpus);
+                                                    cs->effective_xcpus,
+                                                    parent->effective_xcpus);
                } else if (is_partition_invalid(cs) && !cpumask_empty(xcpus) &&
                           cpumask_subset(xcpus, parent->effective_xcpus)) {
                        struct cgroup_subsys_state *css;