rcu: Make ->cpu_no_qs be a union for aggregate OR

This commit converts the rcu_data structure's ->cpu_no_qs field
to a union.  The bytewise side of this union allows individual access
to indications as to whether this CPU needs to find a quiescent state
for a normal (.norm) and/or expedited (.exp) grace period.  The setwise
side of the union allows testing whether or not a quiescent state is
needed at all, for either type of grace period.

For now, only .norm is used.  A later commit will introduce the expedited
usage.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

kernel/rcu/tree.c

@@ -245,21 +245,21 @@ static int rcu_gp_in_progress(struct rcu_state *rsp)
  */
 void rcu_sched_qs(void)
 {
-	if (__this_cpu_read(rcu_sched_data.cpu_no_qs)) {
+	if (__this_cpu_read(rcu_sched_data.cpu_no_qs.s)) {
 		trace_rcu_grace_period(TPS("rcu_sched"),
 				       __this_cpu_read(rcu_sched_data.gpnum),
 				       TPS("cpuqs"));
-		__this_cpu_write(rcu_sched_data.cpu_no_qs, false);
+		__this_cpu_write(rcu_sched_data.cpu_no_qs.b.norm, false);
 	}
 }
 
 void rcu_bh_qs(void)
 {
-	if (__this_cpu_read(rcu_bh_data.cpu_no_qs)) {
+	if (__this_cpu_read(rcu_bh_data.cpu_no_qs.s)) {
 		trace_rcu_grace_period(TPS("rcu_bh"),
 				       __this_cpu_read(rcu_bh_data.gpnum),
 				       TPS("cpuqs"));
-		__this_cpu_write(rcu_bh_data.cpu_no_qs, false);
+		__this_cpu_write(rcu_bh_data.cpu_no_qs.b.norm, false);
 	}
 }
 
@@ -1744,7 +1744,7 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp,
 		 */
 		rdp->gpnum = rnp->gpnum;
 		trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpustart"));
-		rdp->cpu_no_qs = true;
+		rdp->cpu_no_qs.b.norm = true;
 		rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
 		rdp->core_needs_qs = !!(rnp->qsmask & rdp->grpmask);
 		zero_cpu_stall_ticks(rdp);
@@ -2337,7 +2337,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
 	rnp = rdp->mynode;
 	raw_spin_lock_irqsave(&rnp->lock, flags);
 	smp_mb__after_unlock_lock();
-	if ((rdp->cpu_no_qs &&
+	if ((rdp->cpu_no_qs.b.norm &&
 	     rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) ||
 	    rdp->gpnum != rnp->gpnum || rnp->completed == rnp->gpnum ||
 	    rdp->gpwrap) {
@@ -2348,7 +2348,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
 		 * We will instead need a new quiescent state that lies
 		 * within the current grace period.
 		 */
-		rdp->cpu_no_qs = true;	/* need qs for new gp. */
+		rdp->cpu_no_qs.b.norm = true;	/* need qs for new gp. */
 		rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		return;
@@ -2395,7 +2395,7 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
 	 * Was there a quiescent state since the beginning of the grace
 	 * period? If no, then exit and wait for the next call.
 	 */
-	if (rdp->cpu_no_qs &&
+	if (rdp->cpu_no_qs.b.norm &&
 	    rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr))
 		return;
 
@@ -3828,11 +3828,11 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 
 	/* Is the RCU core waiting for a quiescent state from this CPU? */
 	if (rcu_scheduler_fully_active &&
-	    rdp->core_needs_qs && rdp->cpu_no_qs &&
+	    rdp->core_needs_qs && rdp->cpu_no_qs.b.norm &&
 	    rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) {
 		rdp->n_rp_core_needs_qs++;
 	} else if (rdp->core_needs_qs &&
-		   (!rdp->cpu_no_qs ||
+		   (!rdp->cpu_no_qs.b.norm ||
 		    rdp->rcu_qs_ctr_snap != __this_cpu_read(rcu_qs_ctr))) {
 		rdp->n_rp_report_qs++;
 		return 1;
@@ -4155,7 +4155,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rdp->beenonline = true;	 /* We have now been online. */
 	rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */
 	rdp->completed = rnp->completed;
-	rdp->cpu_no_qs = true;
+	rdp->cpu_no_qs.b.norm = true;
 	rdp->rcu_qs_ctr_snap = per_cpu(rcu_qs_ctr, cpu);
 	rdp->core_needs_qs = false;
 	trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl"));

kernel/rcu/tree.h

@@ -286,6 +286,18 @@ struct rcu_node {
 	for ((rnp) = (rsp)->level[rcu_num_lvls - 1]; \
 	     (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++)
 
+/*
+ * Union to allow "aggregate OR" operation on the need for a quiescent
+ * state by the normal and expedited grace periods.
+ */
+union rcu_noqs {
+	struct {
+		u8 norm;
+		u8 exp;
+	} b; /* Bits. */
+	u16 s; /* Set of bits, aggregate OR here. */
+};
+
 /* Index values for nxttail array in struct rcu_data. */
 #define RCU_DONE_TAIL		0	/* Also RCU_WAIT head. */
 #define RCU_WAIT_TAIL		1	/* Also RCU_NEXT_READY head. */
@@ -302,7 +314,7 @@ struct rcu_data {
 					/*  is aware of having started. */
 	unsigned long	rcu_qs_ctr_snap;/* Snapshot of rcu_qs_ctr to check */
 					/*  for rcu_all_qs() invocations. */
-	bool		cpu_no_qs;	/* No QS yet for this CPU. */
+	union rcu_noqs	cpu_no_qs;	/* No QSes yet for this CPU. */
 	bool		core_needs_qs;	/* Core waits for quiesc state. */
 	bool		beenonline;	/* CPU online at least once. */
 	bool		gpwrap;		/* Possible gpnum/completed wrap. */

kernel/rcu/tree_plugin.h

@@ -265,11 +265,11 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp,
  */
 static void rcu_preempt_qs(void)
 {
-	if (__this_cpu_read(rcu_data_p->cpu_no_qs)) {
+	if (__this_cpu_read(rcu_data_p->cpu_no_qs.s)) {
 		trace_rcu_grace_period(TPS("rcu_preempt"),
 				       __this_cpu_read(rcu_data_p->gpnum),
 				       TPS("cpuqs"));
-		__this_cpu_write(rcu_data_p->cpu_no_qs, false);
+		__this_cpu_write(rcu_data_p->cpu_no_qs.b.norm, false);
 		barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */
 		current->rcu_read_unlock_special.b.need_qs = false;
 	}
@@ -620,7 +620,7 @@ static void rcu_preempt_check_callbacks(void)
 	}
 	if (t->rcu_read_lock_nesting > 0 &&
 	    __this_cpu_read(rcu_data_p->core_needs_qs) &&
-	    __this_cpu_read(rcu_data_p->cpu_no_qs))
+	    __this_cpu_read(rcu_data_p->cpu_no_qs.b.norm))
 		t->rcu_read_unlock_special.b.need_qs = true;
 }
 

kernel/rcu/tree_trace.c

@@ -121,7 +121,7 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 		   rdp->cpu,
 		   cpu_is_offline(rdp->cpu) ? '!' : ' ',
 		   ulong2long(rdp->completed), ulong2long(rdp->gpnum),
-		   rdp->cpu_no_qs,
+		   rdp->cpu_no_qs.b.norm,
 		   rdp->rcu_qs_ctr_snap == per_cpu(rcu_qs_ctr, rdp->cpu),
 		   rdp->core_needs_qs);
 	seq_printf(m, " dt=%d/%llx/%d df=%lu",