sched/core: Use kfree_rcu() in do_set_cpus_allowed()

Commit 851a723e45d1 ("sched: Always clear user_cpus_ptr in
do_set_cpus_allowed()") may call kfree() if user_cpus_ptr was previously
set. Unfortunately, some of the callers of do_set_cpus_allowed()
may have pi_lock held when calling it. So the following splats may be
printed especially when running with a PREEMPT_RT kernel:

   WARNING: possible circular locking dependency detected
   BUG: sleeping function called from invalid context

To avoid these problems, kfree_rcu() is used instead. An internal
cpumask_rcuhead union is created for the sole purpose of facilitating
the use of kfree_rcu() to free the cpumask.

Since user_cpus_ptr is not being used in non-SMP configs, the newly
introduced alloc_user_cpus_ptr() helper will return NULL in this case
and sched_setaffinity() is modified to handle this special case.

Fixes: 851a723e45d1 ("sched: Always clear user_cpus_ptr in do_set_cpus_allowed()")
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20221231041120.440785-3-longman@redhat.com

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f9f6e5413dcf90df071aad307136e42b129a8183..bb1ee6d7bddea70b11a7aa136b419a153534a056 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2604,9 +2604,29 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
                .user_mask = NULL,
                .flags     = SCA_USER,  /* clear the user requested mask */
        };
+       union cpumask_rcuhead {
+               cpumask_t cpumask;
+               struct rcu_head rcu;
+       };
 
        __do_set_cpus_allowed(p, &ac);
-       kfree(ac.user_mask);
+
+       /*
+        * Because this is called with p->pi_lock held, it is not possible
+        * to use kfree() here (when PREEMPT_RT=y), therefore punt to using
+        * kfree_rcu().
+        */
+       kfree_rcu((union cpumask_rcuhead *)ac.user_mask, rcu);
+}
+
+static cpumask_t *alloc_user_cpus_ptr(int node)
+{
+       /*
+        * See do_set_cpus_allowed() above for the rcu_head usage.
+        */
+       int size = max_t(int, cpumask_size(), sizeof(struct rcu_head));
+
+       return kmalloc_node(size, GFP_KERNEL, node);
 }
 
 int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
@@ -2629,7 +2649,7 @@ int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
        if (data_race(!src->user_cpus_ptr))
                return 0;
 
-       user_mask = kmalloc_node(cpumask_size(), GFP_KERNEL, node);
+       user_mask = alloc_user_cpus_ptr(node);
        if (!user_mask)
                return -ENOMEM;
 
@@ -3605,6 +3625,11 @@ static inline bool rq_has_pinned_tasks(struct rq *rq)
        return false;
 }
 
+static inline cpumask_t *alloc_user_cpus_ptr(int node)
+{
+       return NULL;
+}
+
 #endif /* !CONFIG_SMP */
 
 static void
@@ -8265,8 +8290,8 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
        if (retval)
                goto out_put_task;
 
-       user_mask = kmalloc(cpumask_size(), GFP_KERNEL);
-       if (!user_mask) {
+       user_mask = alloc_user_cpus_ptr(NUMA_NO_NODE);
+       if (IS_ENABLED(CONFIG_SMP) && !user_mask) {
                retval = -ENOMEM;
                goto out_put_task;
        }