[PATCH 6.1 12/16] rcu: Fix missing nocb gp wake on rcu_barrier()

[Alexey Nepomnyashih <sdl@nppct.ru>]

From: Frederic Weisbecker <frederic@kernel.org>

commit b8f7aca3f0e0e6223094ba2662bac90353674b04 upstream.

In preparation for RCU lazy changes, wake up the RCU nocb gp thread if
needed after an entrain.  This change prevents the RCU barrier callback
from waiting in the queue for several seconds before the lazy callbacks
in front of it are serviced.

Reported-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Alexey Nepomnyashih <sdl@nppct.ru>
---
 kernel/rcu/tree.c      | 11 +++++++++++
 kernel/rcu/tree.h      |  1 +
 kernel/rcu/tree_nocb.h |  5 +++++
 3 files changed, 17 insertions(+)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index dd6e15ca63b0..664ebd2da252 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3962,6 +3962,8 @@ static void rcu_barrier_entrain(struct rcu_data *rdp)
 {
 	unsigned long gseq = READ_ONCE(rcu_state.barrier_sequence);
 	unsigned long lseq = READ_ONCE(rdp->barrier_seq_snap);
+	bool wake_nocb = false;
+	bool was_alldone = false;
 
 	lockdep_assert_held(&rcu_state.barrier_lock);
 	if (rcu_seq_state(lseq) || !rcu_seq_state(gseq) || rcu_seq_ctr(lseq) != rcu_seq_ctr(gseq))
@@ -3970,7 +3972,14 @@ static void rcu_barrier_entrain(struct rcu_data *rdp)
 	rdp->barrier_head.func = rcu_barrier_callback;
 	debug_rcu_head_queue(&rdp->barrier_head);
 	rcu_nocb_lock(rdp);
+	/*
+	 * Flush bypass and wakeup rcuog if we add callbacks to an empty regular
+	 * queue. This way we don't wait for bypass timer that can reach seconds
+	 * if it's fully lazy.
+	 */
+	was_alldone = rcu_rdp_is_offloaded(rdp) && !rcu_segcblist_pend_cbs(&rdp->cblist);
 	WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies));
+	wake_nocb = was_alldone && rcu_segcblist_pend_cbs(&rdp->cblist);
 	if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head)) {
 		atomic_inc(&rcu_state.barrier_cpu_count);
 	} else {
@@ -3978,6 +3987,8 @@ static void rcu_barrier_entrain(struct rcu_data *rdp)
 		rcu_barrier_trace(TPS("IRQNQ"), -1, rcu_state.barrier_sequence);
 	}
 	rcu_nocb_unlock(rdp);
+	if (wake_nocb)
+		wake_nocb_gp(rdp, false);
 	smp_store_release(&rdp->barrier_seq_snap, gseq);
 }
 
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index aa16d3cd62ba..43babe7b1fbf 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -442,6 +442,7 @@ static void zero_cpu_stall_ticks(struct rcu_data *rdp);
 static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp);
 static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq);
 static void rcu_init_one_nocb(struct rcu_node *rnp);
+static bool wake_nocb_gp(struct rcu_data *rdp, bool force);
 static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
 				  unsigned long j);
 static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index 7c28d154b094..e8027f4d441c 100644
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -1547,6 +1547,11 @@ static void rcu_init_one_nocb(struct rcu_node *rnp)
 {
 }
 
+static bool wake_nocb_gp(struct rcu_data *rdp, bool force)
+{
+	return false;
+}
+
 static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
 				  unsigned long j)
 {
-- 
2.43.0