On 2025/12/25 15:30, Waiman Long wrote:
> 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.
>
> Signed-off-by: Waiman Long <[email protected]>
> ---
> kernel/cgroup/cpuset.c | 30 +++++++++++++++---------------
> 1 file changed, 15 insertions(+), 15 deletions(-)
>
> diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
> index 850334dbc36a..83bf6b588e5f 100644
> --- 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
> + * @new_xcpus: new exclusive_cpus in trial cpuset
> *
> * 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 new_xcpus)
> {
> /* 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 (new_xcpus && !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 new_xcpus;
> 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;
> + new_xcpus = !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, new_xcpus))
> goto out;
> if (mems_excl_conflict(trial, c))
> goto out;
validate_change() is also called from cpuset_update_flag(), which may not
change any cpus_allowed or
exclusive_cpus. This could lead to incorrect checks.
i.e,
# cd /sys/fs/cgroup/
# mkdir a
# mkdir b
# echo 1-2 > b/cpuset.cpus.exclusive -- no conflict with a
# echo 1 > a/cpuset.cpus
# echo root > b/cpuset.cpus.partition -- b becomes root partition, conflict
with a, but
exclusive_cpus unchanged
# cat b/cpuset.cpus.partition
root
As a result, cpuset a (as a member) contains CPU 1, which is a subset of
partition b's exclusive
CPUs — a conflict that might be missed.
--
Best regards,
Ridong
