Add a call to rcu_promote_blocked_tasks() in sync_exp_reset_tree()
before checking for blocked tasks. This ensures that expedited grace
periods properly wait for tasks that were blocked on per-CPU lists
before the expedited GP was initiated.

Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
 kernel/rcu/tree.h        | 1 +
 kernel/rcu/tree_exp.h    | 5 +++++
 kernel/rcu/tree_plugin.h | 8 +++++---
 3 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 13d5649a80fb..b71c6c1de8d3 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -501,6 +501,7 @@ static bool rcu_is_callbacks_kthread(struct rcu_data *rdp);
 static void rcu_cpu_kthread_setup(unsigned int cpu);
 static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp);
 static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
+static void rcu_promote_blocked_tasks(struct rcu_node *rnp);
 static bool rcu_preempt_need_deferred_qs(struct task_struct *t);
 static void zero_cpu_stall_ticks(struct rcu_data *rdp);
 static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp);
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 96c49c56fc14..f6cb0e3147c4 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -141,6 +141,11 @@ static void __maybe_unused sync_exp_reset_tree(void)
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		WARN_ON_ONCE(rnp->expmask);
 		WRITE_ONCE(rnp->expmask, rnp->expmaskinit);
+		/*
+		 * Promote tasks from per-CPU lists before checking blkd_tasks.
+		 * This ensures expedited GPs see tasks blocked.
+		 */
+		rcu_promote_blocked_tasks(rnp);
 		/*
 		 * Need to wait for any blocked tasks as well.	Note that
 		 * additional blocking tasks will also block the expedited GP
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 6810f1b72d2a..ad33fdd0efe8 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -810,8 +810,8 @@ static void rcu_read_unlock_special(struct task_struct *t)
 /*
  * Promote blocked tasks from a single CPU's per-CPU list to the rnp list.
  *
- * If there are no tracked blockers (gp_tasks NULL) and this CPU
- * is still blocking the corresponding GP (bit set in qsmask), set
+ * If there are no tracked blockers (gp_tasks/exp_tasks NULL) and this CPU
+ * is still blocking the corresponding GP (bit set in qsmask/expmask), set
  * the pointer to ensure the GP machinery knows about the blocking task.
  * This handles late promotion during QS reporting, where tasks may have
  * blocked after rcu_gp_init() or sync_exp_reset_tree() ran their scans.
@@ -844,11 +844,13 @@ static void rcu_promote_blocked_tasks_rdp(struct rcu_data *rdp,
 		t->rcu_blocked_cpu = -1;
 
 		/*
-		 * Set gp_tasks if this is the first blocker and
+		 * Set gp_tasks/exp_tasks if this is the first blocker and
 		 * this CPU is still blocking the corresponding GP.
 		 */
 		if (!rnp->gp_tasks && (rnp->qsmask & rdp->grpmask))
 			WRITE_ONCE(rnp->gp_tasks, &t->rcu_node_entry);
+		if (!rnp->exp_tasks && (rnp->expmask & rdp->grpmask))
+			WRITE_ONCE(rnp->exp_tasks, &t->rcu_node_entry);
 	}
 	raw_spin_unlock(&rdp->blkd_lock);
 }
-- 
2.34.1