[PATCH 01/11] rcu: avoid leaking exp_deferred_qs into next GP

[Lai Jiangshan]

If exp_deferred_qs is incorrectly set and leaked to the next
exp GP, it may cause the next GP to be incorrectly prematurely
completed.

Signed-off-by: Lai Jiangshan <laijs@xxxxxxxxxxxxxxxxx>
---
 kernel/rcu/tree_exp.h | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index a0e1e51c51c2..6dec21909b30 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -603,6 +603,18 @@ static void rcu_exp_handler(void *unused)
 	struct rcu_node *rnp = rdp->mynode;
 	struct task_struct *t = current;
 
+	/*
+	 * Note that there is a large group of race conditions that
+	 * can have caused this quiescent state to already have been
+	 * reported, so we really do need to check ->expmask first.
+	 */
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
+	if (!(rnp->expmask & rdp->grpmask)) {
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		return;
+	}
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+
 	/*
 	 * First, the common case of not being in an RCU read-side
 	 * critical section.  If also enabled or idle, immediately
@@ -628,17 +640,10 @@ static void rcu_exp_handler(void *unused)
 	 * a future context switch.  Either way, if the expedited
 	 * grace period is still waiting on this CPU, set ->deferred_qs
 	 * so that the eventual quiescent state will be reported.
-	 * Note that there is a large group of race conditions that
-	 * can have caused this quiescent state to already have been
-	 * reported, so we really do need to check ->expmask.
 	 */
 	if (t->rcu_read_lock_nesting > 0) {
-		raw_spin_lock_irqsave_rcu_node(rnp, flags);
-		if (rnp->expmask & rdp->grpmask) {
-			rdp->exp_deferred_qs = true;
-			t->rcu_read_unlock_special.b.exp_hint = true;
-		}
-		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		rdp->exp_deferred_qs = true;
+		WRITE_ONCE(t->rcu_read_unlock_special.b.exp_hint, true);
 		return;
 	}
 
-- 
2.20.1