summaryrefslogtreecommitdiff
path: root/kernel/cgroup
diff options
context:
space:
mode:
authorWaiman Long <longman@redhat.com>2023-02-05 22:48:53 -0500
committerTejun Heo <tj@kernel.org>2023-02-06 10:15:08 -1000
commit3fb906e7fabbb5b76c3c5256b10dc46ef80a0bfe (patch)
treea54492dba514bcd92b9206ff60e13daecb08984f /kernel/cgroup
parentd2d11f342b179f1894a901f143ec7c008caba43e (diff)
cgroup/cpuset: Don't filter offline CPUs in cpuset_cpus_allowed() for top cpuset tasks
Since commit 8f9ea86fdf99 ("sched: Always preserve the user requested cpumask"), relax_compatible_cpus_allowed_ptr() is calling __sched_setaffinity() unconditionally. This helps to expose a bug in the current cpuset hotplug code where the cpumasks of the tasks in the top cpuset are not updated at all when some CPUs become online or offline. It is likely caused by the fact that some of the tasks in the top cpuset, like percpu kthreads, cannot have their cpu affinity changed. One way to reproduce this as suggested by Peter is: - boot machine - offline all CPUs except one - taskset -p ffffffff $$ - online all CPUs Fix this by allowing cpuset_cpus_allowed() to return a wider mask that includes offline CPUs for those tasks that are in the top cpuset. For tasks not in the top cpuset, the old rule applies and only online CPUs will be returned in the mask since hotplug events will update their cpumasks accordingly. Fixes: 8f9ea86fdf99 ("sched: Always preserve the user requested cpumask") Reported-by: Will Deacon <will@kernel.org> Originally-from: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Will Deacon <will@kernel.org> Signed-off-by: Waiman Long <longman@redhat.com> Signed-off-by: Tejun Heo <tj@kernel.org>
Diffstat (limited to 'kernel/cgroup')
-rw-r--r--kernel/cgroup/cpuset.c27
1 files changed, 25 insertions, 2 deletions
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 205dc9edcaa9..528285a91499 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -3692,15 +3692,38 @@ void __init cpuset_init_smp(void)
* Description: Returns the cpumask_var_t cpus_allowed of the cpuset
* attached to the specified @tsk. Guaranteed to return some non-empty
* subset of cpu_online_mask, even if this means going outside the
- * tasks cpuset.
+ * tasks cpuset, except when the task is in the top cpuset.
**/
void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
{
unsigned long flags;
+ struct cpuset *cs;
spin_lock_irqsave(&callback_lock, flags);
- guarantee_online_cpus(tsk, pmask);
+ rcu_read_lock();
+
+ cs = task_cs(tsk);
+ if (cs != &top_cpuset)
+ guarantee_online_cpus(tsk, pmask);
+ /*
+ * Tasks in the top cpuset won't get update to their cpumasks
+ * when a hotplug online/offline event happens. So we include all
+ * offline cpus in the allowed cpu list.
+ */
+ if ((cs == &top_cpuset) || cpumask_empty(pmask)) {
+ const struct cpumask *possible_mask = task_cpu_possible_mask(tsk);
+
+ /*
+ * We first exclude cpus allocated to partitions. If there is no
+ * allowable online cpu left, we fall back to all possible cpus.
+ */
+ cpumask_andnot(pmask, possible_mask, top_cpuset.subparts_cpus);
+ if (!cpumask_intersects(pmask, cpu_online_mask))
+ cpumask_copy(pmask, possible_mask);
+ }
+
+ rcu_read_unlock();
spin_unlock_irqrestore(&callback_lock, flags);
}