rcu/nocb: Remove needless full barrier after callback advancing

A full barrier is issued from nocb_gp_wait() upon callbacks advancing
to order grace period completion with callbacks execution.

However these two events are already ordered by the
smp_mb__after_unlock_lock() barrier within the call to
raw_spin_lock_rcu_node() that is necessary for callbacks advancing to
happen.

The following litmus test shows the kind of guarantee that this barrier
provides:

	C smp_mb__after_unlock_lock

	{}

	// rcu_gp_cleanup()
	P0(spinlock_t *rnp_lock, int *gpnum)
	{
		// Grace period cleanup increase gp sequence number
		spin_lock(rnp_lock);
		WRITE_ONCE(*gpnum, 1);
		spin_unlock(rnp_lock);
	}

	// nocb_gp_wait()
	P1(spinlock_t *rnp_lock, spinlock_t *nocb_lock, int *gpnum, int *cb_ready)
	{
		int r1;

		// Call rcu_advance_cbs() from nocb_gp_wait()
		spin_lock(nocb_lock);
		spin_lock(rnp_lock);
		smp_mb__after_unlock_lock();
		r1 = READ_ONCE(*gpnum);
		WRITE_ONCE(*cb_ready, 1);
		spin_unlock(rnp_lock);
		spin_unlock(nocb_lock);
	}

	// nocb_cb_wait()
	P2(spinlock_t *nocb_lock, int *cb_ready, int *cb_executed)
	{
		int r2;

		// rcu_do_batch() -> rcu_segcblist_extract_done_cbs()
		spin_lock(nocb_lock);
		r2 = READ_ONCE(*cb_ready);
		spin_unlock(nocb_lock);

		// Actual callback execution
		WRITE_ONCE(*cb_executed, 1);
	}

	P3(int *cb_executed, int *gpnum)
	{
		int r3;

		WRITE_ONCE(*cb_executed, 2);
		smp_mb();
		r3 = READ_ONCE(*gpnum);
	}

	exists (1:r1=1 /\ 2:r2=1 /\ cb_executed=2 /\ 3:r3=0) (* Bad outcome. *)

Here the bad outcome only occurs if the smp_mb__after_unlock_lock() is
removed. This barrier orders the grace period completion against
callbacks advancing and even later callbacks invocation, thanks to the
opportunistic propagation via the ->nocb_lock to nocb_cb_wait().

Therefore the smp_mb() placed after callbacks advancing can be safely
removed.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Reviewed-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Boqun Feng <boqun.feng@gmail.com>

kernel/rcu/tree.c

@@ -2145,6 +2145,12 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	 * Extract the list of ready callbacks, disabling IRQs to prevent
 	 * races with call_rcu() from interrupt handlers.  Leave the
 	 * callback counts, as rcu_barrier() needs to be conservative.
+	 *
+	 * Callbacks execution is fully ordered against preceding grace period
+	 * completion (materialized by rnp->gp_seq update) thanks to the
+	 * smp_mb__after_unlock_lock() upon node locking required for callbacks
+	 * advancing. In NOCB mode this ordering is then further relayed through
+	 * the nocb locking that protects both callbacks advancing and extraction.
 	 */
 	rcu_nocb_lock_irqsave(rdp, flags);
 	WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));

kernel/rcu/tree_nocb.h

@@ -779,7 +779,6 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
 		if (rcu_segcblist_ready_cbs(&rdp->cblist)) {
 			needwake = rdp->nocb_cb_sleep;
 			WRITE_ONCE(rdp->nocb_cb_sleep, false);
-			smp_mb(); /* CB invocation -after- GP end. */
 		} else {
 			needwake = false;
 		}