Re: [PATCH-tip] sched: Don't call kfree() in do_set_cpus_allowed()

[Peter Zijlstra]

On Mon, Nov 21, 2022 at 10:04:33AM -0500, Waiman Long wrote:
> 
> On 11/21/22 05:38, Peter Zijlstra wrote:
> > On Fri, Nov 18, 2022 at 02:33:02PM -0500, Waiman Long wrote:
> > > 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()
> > 'some' ? There's only 3 or so, which one triggers this?
> 
> It happenned at __kthread_bind_mask() where do_set_cpus_allowed() is called
> with pi_lock held.
> 
> [ 1084.820105]  <TASK>
> [ 1084.820110]  dump_stack_lvl+0x57/0x81
> [ 1084.820117]  check_noncircular+0x103/0x120
> [ 10[ 1084.820160]  lock_acquire+0xba/0x230
> [ 1084.820164]  ? kfree+0x10f/0x380
> [ 1084.820172]  ? do_set_cpus_allowed+0x40/0x60
> [ 1084.820181]  rt_spin_lock+0x27/0xe0
> [ 1084.820184]  ? kfree+0x10f/0x380
> [ 1084.820188]  kfree+0x10f/0x380
> [ 1084.820195]  do_set_cpus_allowed+0x40/0x60
> [ 1084.820203]  kthread_bind_mask+0x4a/0x70
> [ 1084.820211]  create_worker+0xfb/0x1a0
> [ 1084.820220]  worker_thread+0x2e3/0x3c0
> [ 1084.820226]  ? process_one_work+0x450/0x450
> [ 1084.820230]  kthread+0x111/0x130
> [ 1084.820236]  ? kthread_complete_and_exit+0x20/0x20
> [ 1084.820244]  ret_from_fork+0x22/0x30
> [ 1084.820258]  </TASK>
> [ 1084.820260] BUG: sleeping function called from invalid context at
> kernel/locking/spinlock_rt.c:46
> 
> It shows up with PREEMPT_RT kernel.

Oh, I see ..

> Maybe. One thing that I am not clear about is why user_cpus_ptr is set in
> the first place.

Perhaps someone set an affinity on kthreadd ?

But I'm thinking this exact problem is also possible (rather more likely
even) with select_fallback_rq() that too holds pi_lock (which account
for both other users of this function).

Bah.

And the allocation is just the one long in size (for small configs)
which is just enough space for a single linked list like you had.

Urgh.

The below is yuck too, and I'm not sure Paul wants us to use
kvfree_call_rcu() without its wrapper.

---
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 78b2d5cabcc5..0d0af0fc7fcf 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2606,7 +2606,12 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 	};
 
 	__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().
+	 */
+	kvfree_call_rcu((struct rcu_head *)ac.user_mask, (rcu_callback_t)0);
 }
 
 int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
@@ -8196,7 +8201,7 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 	struct affinity_context ac;
 	struct cpumask *user_mask;
 	struct task_struct *p;
-	int retval;
+	int retval, size;
 
 	rcu_read_lock();
 
@@ -8229,7 +8234,11 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 	if (retval)
 		goto out_put_task;
 
-	user_mask = kmalloc(cpumask_size(), GFP_KERNEL);
+	/*
+	 * See do_set_cpus_allowed() for the rcu_head usage.
+	 */
+	size = max_t(int, cpumask_size(), sizeof(struct rcu_head));
+	user_mask = kmalloc(size, GFP_KERNEL);
 	if (!user_mask) {
 		retval = -ENOMEM;
 		goto out_put_task;