cgroup/cpuset: Don't fail cpuset.cpus change in v2

Commit fe8cd2736e75 ("cgroup/cpuset: Delay setting of CS_CPU_EXCLUSIVE
until valid partition") introduced a new check to disallow the setting
of a new cpuset.cpus.exclusive value that is a superset of a sibling's
cpuset.cpus value so that there will at least be one CPU left in the
sibling in case the cpuset becomes a valid partition root. This new
check does have the side effect of failing a cpuset.cpus change that
make it a subset of a sibling's cpuset.cpus.exclusive value.

With v2, users are supposed to be allowed to set whatever value they
want in cpuset.cpus without failure. To maintain this rule, the check
is now restricted to only when cpuset.cpus.exclusive is being changed
not when cpuset.cpus is changed.

The cgroup-v2.rst doc file is also updated to reflect this change.

Signed-off-by: Waiman Long <longman@redhat.com>
Reviewed-by: Chen Ridong <chenridong@huawei.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 7f5b59d95fce5c42cc04ad7a4b9f1123858e4628..510df2461aff234810a4971369ca8e310ee0ab80 100644 (file)
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -2561,10 +2561,10 @@ Cpuset Interface Files
        Users can manually set it to a value that is different from
        "cpuset.cpus".  One constraint in setting it is that the list of
        CPUs must be exclusive with respect to "cpuset.cpus.exclusive"
-       of its sibling.  If "cpuset.cpus.exclusive" of a sibling cgroup
-       isn't set, its "cpuset.cpus" value, if set, cannot be a subset
-       of it to leave at least one CPU available when the exclusive
-       CPUs are taken away.
+       and "cpuset.cpus.exclusive.effective" of its siblings.  Another
+       constraint is that it cannot be a superset of "cpuset.cpus"
+       of its sibling in order to leave at least one CPU available to
+       that sibling when the exclusive CPUs are taken away.
 
        For a parent cgroup, any one of its exclusive CPUs can only
        be distributed to at most one of its child cgroups.  Having an

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 894131f47f78aa891bbe44445d6f86aed9b4faea..4819ab429771d284bacc9c1620cc89bd7e431b96 100644 (file)
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -609,33 +609,31 @@ static inline bool cpusets_are_exclusive(struct cpuset *cs1, struct cpuset *cs2)
 
 /**
  * cpus_excl_conflict - Check if two cpusets have exclusive CPU conflicts
- * @cs1: first cpuset to check
- * @cs2: second cpuset to check
+ * @trial:     the trial cpuset to be checked
+ * @sibling:   a sibling cpuset to be checked against
+ * @xcpus_changed: set if exclusive_cpus has been set
  *
  * Returns: true if CPU exclusivity conflict exists, false otherwise
  *
  * Conflict detection rules:
  * 1. If either cpuset is CPU exclusive, they must be mutually exclusive
  * 2. exclusive_cpus masks cannot intersect between cpusets
- * 3. The allowed CPUs of one cpuset cannot be a subset of another's exclusive CPUs
+ * 3. The allowed CPUs of a sibling cpuset cannot be a subset of the new exclusive CPUs
  */
-static inline bool cpus_excl_conflict(struct cpuset *cs1, struct cpuset *cs2)
+static inline bool cpus_excl_conflict(struct cpuset *trial, struct cpuset *sibling,
+                                     bool xcpus_changed)
 {
        /* If either cpuset is exclusive, check if they are mutually exclusive */
-       if (is_cpu_exclusive(cs1) || is_cpu_exclusive(cs2))
-               return !cpusets_are_exclusive(cs1, cs2);
+       if (is_cpu_exclusive(trial) || is_cpu_exclusive(sibling))
+               return !cpusets_are_exclusive(trial, sibling);
 
        /* Exclusive_cpus cannot intersect */
-       if (cpumask_intersects(cs1->exclusive_cpus, cs2->exclusive_cpus))
+       if (cpumask_intersects(trial->exclusive_cpus, sibling->exclusive_cpus))
                return true;
 
-       /* The cpus_allowed of one cpuset cannot be a subset of another cpuset's exclusive_cpus */
-       if (!cpumask_empty(cs1->cpus_allowed) &&
-           cpumask_subset(cs1->cpus_allowed, cs2->exclusive_cpus))
-               return true;
-
-       if (!cpumask_empty(cs2->cpus_allowed) &&
-           cpumask_subset(cs2->cpus_allowed, cs1->exclusive_cpus))
+       /* The cpus_allowed of a sibling cpuset cannot be a subset of the new exclusive_cpus */
+       if (xcpus_changed && !cpumask_empty(sibling->cpus_allowed) &&
+           cpumask_subset(sibling->cpus_allowed, trial->exclusive_cpus))
                return true;
 
        return false;
@@ -672,6 +670,7 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
 {
        struct cgroup_subsys_state *css;
        struct cpuset *c, *par;
+       bool xcpus_changed;
        int ret = 0;
 
        rcu_read_lock();
@@ -728,10 +727,11 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
         * overlap. exclusive_cpus cannot overlap with each other if set.
         */
        ret = -EINVAL;
+       xcpus_changed = !cpumask_equal(cur->exclusive_cpus, trial->exclusive_cpus);
        cpuset_for_each_child(c, css, par) {
                if (c == cur)
                        continue;
-               if (cpus_excl_conflict(trial, c))
+               if (cpus_excl_conflict(trial, c, xcpus_changed))
                        goto out;
                if (mems_excl_conflict(trial, c))
                        goto out;