rcu: Apply rcu_seq operations to _rcu_barrier()

The rcu_seq operations were open-coded in _rcu_barrier(), so this commit
replaces the open-coding with the shiny new rcu_seq operations.

Signed-off-by: Paul E. McKenney <[e-mail]>

include/trace/events/rcu.h

···
  * Tracepoint for _rcu_barrier() execution.  The string "s" describes
  * the _rcu_barrier phase:
  *	"Begin": _rcu_barrier() started.
- *	"Check": _rcu_barrier() checking for piggybacking.
  *	"EarlyExit": _rcu_barrier() piggybacked, thus early exit.
  *	"Inc1": _rcu_barrier() piggyback check counter incremented.
  *	"OfflineNoCB": _rcu_barrier() found callback on never-online CPU

kernel/rcu/tree.c

···
 	struct rcu_state *rsp = rdp->rsp;
 
 	if (atomic_dec_and_test(&rsp->barrier_cpu_count)) {
-		_rcu_barrier_trace(rsp, "LastCB", -1, rsp->n_barrier_done);
+		_rcu_barrier_trace(rsp, "LastCB", -1, rsp->barrier_sequence);
 		complete(&rsp->barrier_completion);
 	} else {
-		_rcu_barrier_trace(rsp, "CB", -1, rsp->n_barrier_done);
+		_rcu_barrier_trace(rsp, "CB", -1, rsp->barrier_sequence);
 	}
 }
 
···
 	struct rcu_state *rsp = type;
 	struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
 
-	_rcu_barrier_trace(rsp, "IRQ", -1, rsp->n_barrier_done);
+	_rcu_barrier_trace(rsp, "IRQ", -1, rsp->barrier_sequence);
 	atomic_inc(&rsp->barrier_cpu_count);
 	rsp->call(&rdp->barrier_head, rcu_barrier_callback);
 }
···
 {
 	int cpu;
 	struct rcu_data *rdp;
-	unsigned long snap = READ_ONCE(rsp->n_barrier_done);
-	unsigned long snap_done;
+	unsigned long s = rcu_seq_snap(&rsp->barrier_sequence);
 
-	_rcu_barrier_trace(rsp, "Begin", -1, snap);
+	_rcu_barrier_trace(rsp, "Begin", -1, s);
 
 	/* Take mutex to serialize concurrent rcu_barrier() requests. */
 	mutex_lock(&rsp->barrier_mutex);
 
-	/*
-	 * Ensure that all prior references, including to ->n_barrier_done,
-	 * are ordered before the _rcu_barrier() machinery.
-	 */
-	smp_mb();  /* See above block comment. */
-
-	/*
-	 * Recheck ->n_barrier_done to see if others did our work for us.
-	 * This means checking ->n_barrier_done for an even-to-odd-to-even
-	 * transition.  The "if" expression below therefore rounds the old
-	 * value up to the next even number and adds two before comparing.
-	 */
-	snap_done = rsp->n_barrier_done;
-	_rcu_barrier_trace(rsp, "Check", -1, snap_done);
-
-	/*
-	 * If the value in snap is odd, we needed to wait for the current
-	 * rcu_barrier() to complete, then wait for the next one, in other
-	 * words, we need the value of snap_done to be three larger than
-	 * the value of snap.  On the other hand, if the value in snap is
-	 * even, we only had to wait for the next rcu_barrier() to complete,
-	 * in other words, we need the value of snap_done to be only two
-	 * greater than the value of snap.  The "(snap + 3) & ~0x1" computes
-	 * this for us (thank you, Linus!).
-	 */
-	if (ULONG_CMP_GE(snap_done, (snap + 3) & ~0x1)) {
-		_rcu_barrier_trace(rsp, "EarlyExit", -1, snap_done);
+	/* Did someone else do our work for us? */
+	if (rcu_seq_done(&rsp->barrier_sequence, s)) {
+		_rcu_barrier_trace(rsp, "EarlyExit", -1, rsp->barrier_sequence);
 		smp_mb(); /* caller's subsequent code after above check. */
 		mutex_unlock(&rsp->barrier_mutex);
 		return;
 	}
 
-	/*
-	 * Increment ->n_barrier_done to avoid duplicate work.  Use
-	 * WRITE_ONCE() to prevent the compiler from speculating
-	 * the increment to precede the early-exit check.
-	 */
-	WRITE_ONCE(rsp->n_barrier_done, rsp->n_barrier_done + 1);
-	WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 1);
-	_rcu_barrier_trace(rsp, "Inc1", -1, rsp->n_barrier_done);
-	smp_mb(); /* Order ->n_barrier_done increment with below mechanism. */
+	/* Mark the start of the barrier operation. */
+	rcu_seq_start(&rsp->barrier_sequence);
+	_rcu_barrier_trace(rsp, "Inc1", -1, rsp->barrier_sequence);
 
 	/*
 	 * Initialize the count to one rather than to zero in order to
···
 		if (rcu_is_nocb_cpu(cpu)) {
 			if (!rcu_nocb_cpu_needs_barrier(rsp, cpu)) {
 				_rcu_barrier_trace(rsp, "OfflineNoCB", cpu,
-						   rsp->n_barrier_done);
+						   rsp->barrier_sequence);
 			} else {
 				_rcu_barrier_trace(rsp, "OnlineNoCB", cpu,
-						   rsp->n_barrier_done);
+						   rsp->barrier_sequence);
 				smp_mb__before_atomic();
 				atomic_inc(&rsp->barrier_cpu_count);
 				__call_rcu(&rdp->barrier_head,
···
 			}
 		} else if (READ_ONCE(rdp->qlen)) {
 			_rcu_barrier_trace(rsp, "OnlineQ", cpu,
-					   rsp->n_barrier_done);
+					   rsp->barrier_sequence);
 			smp_call_function_single(cpu, rcu_barrier_func, rsp, 1);
 		} else {
 			_rcu_barrier_trace(rsp, "OnlineNQ", cpu,
-					   rsp->n_barrier_done);
+					   rsp->barrier_sequence);
 		}
 	}
 	put_online_cpus();
···
 	if (atomic_dec_and_test(&rsp->barrier_cpu_count))
 		complete(&rsp->barrier_completion);
 
-	/* Increment ->n_barrier_done to prevent duplicate work. */
-	smp_mb(); /* Keep increment after above mechanism. */
-	WRITE_ONCE(rsp->n_barrier_done, rsp->n_barrier_done + 1);
-	WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 0);
-	_rcu_barrier_trace(rsp, "Inc2", -1, rsp->n_barrier_done);
-	smp_mb(); /* Keep increment before caller's subsequent code. */
-
 	/* Wait for all rcu_barrier_callback() callbacks to be invoked. */
 	wait_for_completion(&rsp->barrier_completion);
+
+	/* Mark the end of the barrier operation. */
+	_rcu_barrier_trace(rsp, "Inc2", -1, rsp->barrier_sequence);
+	rcu_seq_end(&rsp->barrier_sequence);
 
 	/* Other rcu_barrier() invocations can now safely proceed. */
 	mutex_unlock(&rsp->barrier_mutex);

kernel/rcu/tree.h

···
 	struct mutex barrier_mutex;		/* Guards barrier fields. */
 	atomic_t barrier_cpu_count;		/* # CPUs waiting on. */
 	struct completion barrier_completion;	/* Wake at barrier end. */
-	unsigned long n_barrier_done;		/* ++ at start and end of */
+	unsigned long barrier_sequence;		/* ++ at start and end of */
 						/*  _rcu_barrier(). */
 	/* End of fields guarded by barrier_mutex. */
 

kernel/rcu/tree_trace.c

···
 static int show_rcubarrier(struct seq_file *m, void *v)
 {
 	struct rcu_state *rsp = (struct rcu_state *)m->private;
-	seq_printf(m, "bcc: %d nbd: %lu\n",
+	seq_printf(m, "bcc: %d bseq: %lu\n",
 		   atomic_read(&rsp->barrier_cpu_count),
-		   rsp->n_barrier_done);
+		   rsp->barrier_sequence);
 	return 0;
 }