Re: [PATCH] sched: Don't call any kfree*() API in do_set_cpus_allowed()

[Peter Zijlstra <peterz@infradead.org>]

On Mon, Oct 30, 2023 at 08:14:18PM -0400, Waiman Long wrote:
> Commit 851a723e45d1 ("sched: Always clear user_cpus_ptr in
> do_set_cpus_allowed()") added a kfree() call to free any user
> provided affinity mask, if present. It was changed later to use
> kfree_rcu() in commit 9a5418bc48ba ("sched/core: Use kfree_rcu()
> in do_set_cpus_allowed()") to avoid a circular locking dependency
> problem.
> 
> It turns out that even kfree_rcu() isn't safe for avoiding
> circular locking problem. As reported by kernel test robot,
> the following circular locking dependency still exists:
> 
>   &rdp->nocb_lock --> rcu_node_0 --> &rq->__lock
> 
> So no kfree*() API can be used in do_set_cpus_allowed(). To prevent
> memory leakage, the unused user provided affinity mask is now saved in a
> lockless list to be reused later by subsequent sched_setaffinity() calls.
> 
> Without kfree_rcu(), the internal cpumask_rcuhead union can be removed
> too as a lockless list entry only holds a single pointer.
> 
> Fixes: 851a723e45d1 ("sched: Always clear user_cpus_ptr in do_set_cpus_allowed()")

Bah, or we fix RCU...  Paul, how insane is the below?

---
 kernel/rcu/tree.c | 31 +++++++++++++++++++++----------
 1 file changed, 21 insertions(+), 10 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index cb1caefa8bd0..4b8e26a028ee 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -754,15 +754,20 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp)
 }
 
 /*
- * Return true if the specified CPU has passed through a quiescent
- * state by virtue of being in or having passed through an dynticks
- * idle state since the last call to dyntick_save_progress_counter()
- * for this same CPU, or by virtue of having been offline.
+ * Returns positive if the specified CPU has passed through a quiescent state
+ * by virtue of being in or having passed through an dynticks idle state since
+ * the last call to dyntick_save_progress_counter() for this same CPU, or by
+ * virtue of having been offline.
+ *
+ * Returns negative if the specified CPU needs a force resched.
+ *
+ * Returns zero otherwise.
  */
 static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 {
-	unsigned long jtsq;
 	struct rcu_node *rnp = rdp->mynode;
+	unsigned long jtsq;
+	int ret = 0;
 
 	/*
 	 * If the CPU passed through or entered a dynticks idle phase with
@@ -847,8 +852,8 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	    (time_after(jiffies, READ_ONCE(rdp->last_fqs_resched) + jtsq * 3) ||
 	     rcu_state.cbovld)) {
 		WRITE_ONCE(rdp->rcu_urgent_qs, true);
-		resched_cpu(rdp->cpu);
 		WRITE_ONCE(rdp->last_fqs_resched, jiffies);
+		ret = -1;
 	}
 
 	/*
@@ -891,7 +896,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 		}
 	}
 
-	return 0;
+	return ret;
 }
 
 /* Trace-event wrapper function for trace_rcu_future_grace_period.  */
@@ -2255,11 +2260,11 @@ void rcu_sched_clock_irq(int user)
  */
 static void force_qs_rnp(int (*f)(struct rcu_data *rdp))
 {
-	int cpu;
+	unsigned long mask, rsmask = 0;
 	unsigned long flags;
-	unsigned long mask;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp;
+	int cpu, ret;
 
 	rcu_state.cbovld = rcu_state.cbovldnext;
 	rcu_state.cbovldnext = false;
@@ -2284,10 +2289,13 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp))
 		}
 		for_each_leaf_node_cpu_mask(rnp, cpu, rnp->qsmask) {
 			rdp = per_cpu_ptr(&rcu_data, cpu);
-			if (f(rdp)) {
+			ret = f(rdp);
+			if (ret > 0) {
 				mask |= rdp->grpmask;
 				rcu_disable_urgency_upon_qs(rdp);
 			}
+			if (ret < 0)
+				rsmask |= 1UL << (cpu - rnp->grplo);
 		}
 		if (mask != 0) {
 			/* Idle/offline CPUs, report (releases rnp->lock). */
@@ -2296,6 +2304,9 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp))
 			/* Nothing to do here, so just drop the lock. */
 			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		}
+
+		for_each_leaf_node_cpu_mask(rnp, cpu, rsmask)
+			resched_cpu(cpu);
 	}
 }