rcu: Make rcu_barrier() less disruptive

The rcu_barrier() primitive interrupts each and every CPU, registering
a callback on every CPU.  Once all of these callbacks have been invoked,
rcu_barrier() knows that every callback that was registered before
the call to rcu_barrier() has also been invoked.

However, there is no point in registering a callback on a CPU that
currently has no callbacks, most especially if that CPU is in a
deep idle state.  This commit therefore makes rcu_barrier() avoid
interrupting CPUs that have no callbacks.  Doing this requires reworking
the handling of orphaned callbacks, otherwise callbacks could slip through
rcu_barrier()'s net by being orphaned from a CPU that rcu_barrier() had
not yet interrupted to a CPU that rcu_barrier() had already interrupted.
This reworking was needed anyway to take a first step towards weaning
RCU from the CPU_DYING notifier's use of stop_cpu().
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

kernel/rcutree.h

@@ -371,6 +371,17 @@ struct rcu_state {
 
 	raw_spinlock_t onofflock;		/* exclude on/offline and */
 						/*  starting new GP. */
+	struct rcu_head *orphan_nxtlist;	/* Orphaned callbacks that */
+						/*  need a grace period. */
+	struct rcu_head **orphan_nxttail;	/* Tail of above. */
+	struct rcu_head *orphan_donelist;	/* Orphaned callbacks that */
+						/*  are ready to invoke. */
+	struct rcu_head **orphan_donetail;	/* Tail of above. */
+	long qlen_lazy;				/* Number of lazy callbacks. */
+	long qlen;				/* Total number of callbacks. */
+	struct task_struct *rcu_barrier_in_progress;
+						/* Task doing rcu_barrier(), */
+						/*  or NULL if no barrier. */
 	raw_spinlock_t fqslock;			/* Only one task forcing */
 						/*  quiescent states. */
 	unsigned long jiffies_force_qs;		/* Time at which to invoke */

kernel/rcutree_trace.c

@@ -271,13 +271,13 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
 
 	gpnum = rsp->gpnum;
 	seq_printf(m, "c=%lu g=%lu s=%d jfq=%ld j=%x "
-		      "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu\n",
+		      "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n",
 		   rsp->completed, gpnum, rsp->fqs_state,
 		   (long)(rsp->jiffies_force_qs - jiffies),
 		   (int)(jiffies & 0xffff),
 		   rsp->n_force_qs, rsp->n_force_qs_ngp,
 		   rsp->n_force_qs - rsp->n_force_qs_ngp,
-		   rsp->n_force_qs_lh);
+		   rsp->n_force_qs_lh, rsp->qlen_lazy, rsp->qlen);
 	for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < NUM_RCU_NODES; rnp++) {
 		if (rnp->level != level) {
 			seq_puts(m, "\n");