rcu: Make NOCB CPUs migrate CBs directly from outgoing CPU

RCU's CPU-hotplug callback-migration code first moves the outgoing
CPU's callbacks to ->orphan_done and ->orphan_pend, and only then
moves them to the NOCB callback list.  This commit avoids the
extra step (and simplifies the code) by moving the callbacks directly
from the outgoing CPU's callback list to the NOCB callback list.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

kernel/rcu/tree.c

@@ -3899,11 +3899,6 @@ static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags)
 
 	lockdep_assert_held(&rsp->orphan_lock);
 
-	/* No-CBs CPUs are handled specially. */
-	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) ||
-	    rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags))
-		return;
-
 	/* Do the accounting first. */
 	if (rsp->orphan_done.len_lazy != rsp->orphan_done.len)
 		rcu_idle_count_callbacks_posted();
@@ -3928,13 +3923,20 @@ static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags)
 static void rcu_migrate_callbacks(int cpu, struct rcu_state *rsp)
 {
 	unsigned long flags;
+	struct rcu_data *my_rdp;
 	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 	struct rcu_node *rnp = rdp->mynode;  /* Outgoing CPU's rdp & rnp. */
 
 	if (rcu_is_nocb_cpu(cpu) || rcu_segcblist_empty(&rdp->cblist))
 		return;  /* No callbacks to migrate. */
 
-	raw_spin_lock_irqsave(&rsp->orphan_lock, flags);
+	local_irq_save(flags);
+	my_rdp = this_cpu_ptr(rsp->rda);
+	if (rcu_nocb_adopt_orphan_cbs(my_rdp, rdp, flags)) {
+		local_irq_restore(flags);
+		return;
+	}
+	raw_spin_lock(&rsp->orphan_lock); /* irqs already disabled. */
 	rcu_send_cbs_to_orphanage(cpu, rsp, rnp, rdp);
 	rcu_adopt_orphan_cbs(rsp, flags);
 	raw_spin_unlock_irqrestore(&rsp->orphan_lock, flags);

kernel/rcu/tree.h

@@ -493,7 +493,7 @@ static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq);
 static void rcu_init_one_nocb(struct rcu_node *rnp);
 static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
 			    bool lazy, unsigned long flags);
-static bool rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
+static bool rcu_nocb_adopt_orphan_cbs(struct rcu_data *my_rdp,
 				      struct rcu_data *rdp,
 				      unsigned long flags);
 static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp);

kernel/rcu/tree_plugin.h

@@ -1961,30 +1961,19 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
  * Adopt orphaned callbacks on a no-CBs CPU, or return 0 if this is
  * not a no-CBs CPU.
  */
-static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
+static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_data *my_rdp,
 						     struct rcu_data *rdp,
 						     unsigned long flags)
 {
-	long ql = rsp->orphan_done.len;
-	long qll = rsp->orphan_done.len_lazy;
-
-	/* If this is not a no-CBs CPU, tell the caller to do it the old way. */
+	RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_nocb_adopt_orphan_cbs() invoked with irqs enabled!!!");
 	if (!rcu_is_nocb_cpu(smp_processor_id()))
-		return false;
-
-	/* First, enqueue the donelist, if any.  This preserves CB ordering. */
-	if (rsp->orphan_done.head) {
-		__call_rcu_nocb_enqueue(rdp, rcu_cblist_head(&rsp->orphan_done),
-					rcu_cblist_tail(&rsp->orphan_done),
-					ql, qll, flags);
-	}
-	if (rsp->orphan_pend.head) {
-		__call_rcu_nocb_enqueue(rdp, rcu_cblist_head(&rsp->orphan_pend),
-					rcu_cblist_tail(&rsp->orphan_pend),
-					ql, qll, flags);
-	}
-	rcu_cblist_init(&rsp->orphan_done);
-	rcu_cblist_init(&rsp->orphan_pend);
+		return false; /* Not NOCBs CPU, caller must migrate CBs. */
+	__call_rcu_nocb_enqueue(my_rdp, rcu_segcblist_head(&rdp->cblist),
+				rcu_segcblist_tail(&rdp->cblist),
+				rcu_segcblist_n_cbs(&rdp->cblist),
+				rcu_segcblist_n_lazy_cbs(&rdp->cblist), flags);
+	rcu_segcblist_init(&rdp->cblist);
+	rcu_segcblist_disable(&rdp->cblist);
 	return true;
 }
 
@@ -2459,7 +2448,7 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
 	return false;
 }
 
-static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
+static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_data *my_rdp,
 						     struct rcu_data *rdp,
 						     unsigned long flags)
 {