[PATCH v6 4/6] rcu: Support direct wake-up of synchronize_rcu() users

["Uladzislau Rezki (Sony)" <urezki@gmail.com>]

This patch introduces a small enhancement which allows to do a
direct wake-up of synchronize_rcu() callers. It occurs after a
completion of grace period, thus by the gp-kthread.

Number of clients is limited by the hard-coded maximum allowed
threshold. The remaining part, if still exists is deferred to
a main worker.

Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
---
 kernel/rcu/tree.c | 32 ++++++++++++++++++++++++++++++--
 kernel/rcu/tree.h |  6 ++++++
 2 files changed, 36 insertions(+), 2 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index dcc1764e8fad..063200613444 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1672,7 +1672,8 @@ static void rcu_sr_normal_gp_cleanup_work(struct work_struct *work)
  */
 static void rcu_sr_normal_gp_cleanup(void)
 {
-	struct llist_node *wait_tail;
+	struct llist_node *wait_tail, *next, *rcu;
+	int done = 0;
 
 	wait_tail = rcu_state.srs_wait_tail;
 	if (wait_tail == NULL)
@@ -1680,12 +1681,39 @@ static void rcu_sr_normal_gp_cleanup(void)
 
 	rcu_state.srs_wait_tail = NULL;
 	ASSERT_EXCLUSIVE_WRITER(rcu_state.srs_wait_tail);
+	WARN_ON_ONCE(!rcu_sr_is_wait_head(wait_tail));
+
+	/*
+	 * Process (a) and (d) cases. See an illustration. Apart of
+	 * that it handles the scenario when all clients are done,
+	 * wait-head is released if last. The worker is not kicked.
+	 */
+	llist_for_each_safe(rcu, next, wait_tail->next) {
+		if (rcu_sr_is_wait_head(rcu)) {
+			if (!rcu->next) {
+				rcu_sr_put_wait_head(rcu);
+				wait_tail->next = NULL;
+			} else {
+				wait_tail->next = rcu;
+			}
+
+			break;
+		}
+
+		rcu_sr_normal_complete(rcu);
+		// It can be last, update a next on this step.
+		wait_tail->next = next;
+
+		if (++done == SR_MAX_USERS_WAKE_FROM_GP)
+			break;
+	}
 
 	// concurrent sr_normal_gp_cleanup work might observe this update.
 	smp_store_release(&rcu_state.srs_done_tail, wait_tail);
 	ASSERT_EXCLUSIVE_WRITER(rcu_state.srs_done_tail);
 
-	schedule_work(&rcu_state.srs_cleanup_work);
+	if (wait_tail->next)
+		schedule_work(&rcu_state.srs_cleanup_work);
 }
 
 /*
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index b942b9437438..2832787cee1d 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -315,6 +315,12 @@ do {									\
 	__set_current_state(TASK_RUNNING);				\
 } while (0)
 
+/*
+ * A max threshold for synchronize_rcu() users which are
+ * awaken directly by the rcu_gp_kthread(). Left part is
+ * deferred to the main worker.
+ */
+#define SR_MAX_USERS_WAKE_FROM_GP 5
 #define SR_NORMAL_GP_WAIT_HEAD_MAX 5
 
 struct sr_wait_node {
-- 
2.39.2