1 files changed, 18 insertions, 84 deletions

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index e73be8539978..62d05413b7ba 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -536,86 +536,28 @@ void synchronize_rcu(void)
 EXPORT_SYMBOL_GPL(synchronize_rcu);
 
 /*
- * Snapshot the tasks blocking the newly started preemptible-RCU expedited
- * grace period for the specified rcu_node structure, phase 1.  If there
- * are such tasks, set the ->expmask bits up the rcu_node tree and also
- * set the ->expmask bits on the leaf rcu_node structures to tell phase 2
- * that work is needed here.
- *
- * Caller must hold the root rcu_node's exp_funnel_mutex.
+ * Select the nodes that the upcoming expedited grace period needs
+ * to wait for.
  */
-static void
-sync_rcu_preempt_exp_init1(struct rcu_state *rsp, struct rcu_node *rnp)
+static void sync_rcu_exp_select_nodes(struct rcu_state *rsp)
 {
 	unsigned long flags;
-	unsigned long mask;
-	struct rcu_node *rnp_up;
+	struct rcu_node *rnp;
 
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	smp_mb__after_unlock_lock();
-	WARN_ON_ONCE(rnp->expmask);
-	WARN_ON_ONCE(rnp->exp_tasks);
-	if (!rcu_preempt_has_tasks(rnp)) {
-		/* No blocked tasks, nothing to do. */
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
-		return;
-	}
-	/* Call for Phase 2 and propagate ->expmask bits up the tree. */
-	rnp->expmask = 1;
-	rnp_up = rnp;
-	while (rnp_up->parent) {
-		mask = rnp_up->grpmask;
-		rnp_up = rnp_up->parent;
-		if (rnp_up->expmask & mask)
-			break;
-		raw_spin_lock(&rnp_up->lock); /* irqs already off */
+	sync_exp_reset_tree(rsp);
+	rcu_for_each_leaf_node(rsp, rnp) {
+		raw_spin_lock_irqsave(&rnp->lock, flags);
 		smp_mb__after_unlock_lock();
-		rnp_up->expmask |= mask;
-		raw_spin_unlock(&rnp_up->lock); /* irqs still off */
-	}
-	raw_spin_unlock_irqrestore(&rnp->lock, flags);
-}
-
-/*
- * Snapshot the tasks blocking the newly started preemptible-RCU expedited
- * grace period for the specified rcu_node structure, phase 2.  If the
- * leaf rcu_node structure has its ->expmask field set, check for tasks.
- * If there are some, clear ->expmask and set ->exp_tasks accordingly,
- * then initiate RCU priority boosting.  Otherwise, clear ->expmask and
- * invoke rcu_report_exp_rnp() to clear out the upper-level ->expmask bits,
- * enabling rcu_read_unlock_special() to do the bit-clearing.
- *
- * Caller must hold the root rcu_node's exp_funnel_mutex.
- */
-static void
-sync_rcu_preempt_exp_init2(struct rcu_state *rsp, struct rcu_node *rnp)
-{
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	smp_mb__after_unlock_lock();
-	if (!rnp->expmask) {
-		/* Phase 1 didn't do anything, so Phase 2 doesn't either. */
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
-		return;
-	}
-
-	/* Phase 1 is over. */
-	rnp->expmask = 0;
-
-	/*
-	 * If there are still blocked tasks, set up ->exp_tasks so that
-	 * rcu_read_unlock_special() will wake us and then boost them.
-	 */
-	if (rcu_preempt_has_tasks(rnp)) {
-		rnp->exp_tasks = rnp->blkd_tasks.next;
-		rcu_initiate_boost(rnp, flags);  /* releases rnp->lock */
-		return;
+		rnp->expmask = 0; /* No per-CPU component yet. */
+		if (!rcu_preempt_has_tasks(rnp)) {
+			/* FIXME: Want __rcu_report_exp_rnp() here. */
+			raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		} else {
+			rnp->exp_tasks = rnp->blkd_tasks.next;
+			rcu_initiate_boost(rnp, flags);
+		}
+		rcu_report_exp_rnp(rsp, rnp, false);
 	}
-
-	/* No longer any blocked tasks, so undo bit setting. */
-	raw_spin_unlock_irqrestore(&rnp->lock, flags);
-	rcu_report_exp_rnp(rsp, rnp, false);
 }
 
 /**
@@ -648,16 +590,8 @@ void synchronize_rcu_expedited(void)
 	/* force all RCU readers onto ->blkd_tasks lists. */
 	synchronize_sched_expedited();
 
-	/*
-	 * Snapshot current state of ->blkd_tasks lists into ->expmask.
-	 * Phase 1 sets bits and phase 2 permits rcu_read_unlock_special()
-	 * to start clearing them.  Doing this in one phase leads to
-	 * strange races between setting and clearing bits, so just say "no"!
-	 */
-	rcu_for_each_leaf_node(rsp, rnp)
-		sync_rcu_preempt_exp_init1(rsp, rnp);
-	rcu_for_each_leaf_node(rsp, rnp)
-		sync_rcu_preempt_exp_init2(rsp, rnp);
+	/* Initialize the rcu_node tree in preparation for the wait. */
+	sync_rcu_exp_select_nodes(rsp);
 
 	/* Wait for snapshotted ->blkd_tasks lists to drain. */
 	rnp = rcu_get_root(rsp);