rcu: Use data_race() for RCU CPU stall-warning prints

Although the accesses used to determine whether or not a stall should
be printed are an integral part of the concurrency algorithm governing
use of the corresponding variables, the values that are simply printed
are ancillary.  As such, it is best to use data_race() for these accesses
in order to provide the greatest latitude in the use of KCSAN for the
other accesses that are an integral part of the algorithm.  This commit
therefore changes the relevant uses of READ_ONCE() to data_race().
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

kernel/rcu/tree_stall.h

@@ -360,7 +360,7 @@ static void rcu_check_gp_kthread_starvation(void)
 		pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
 		       rcu_state.name, j,
 		       (long)rcu_seq_current(&rcu_state.gp_seq),
-		       READ_ONCE(rcu_state.gp_flags),
+		       data_race(rcu_state.gp_flags),
 		       gp_state_getname(rcu_state.gp_state), rcu_state.gp_state,
 		       gpk ? gpk->state : ~0, gpk ? task_cpu(gpk) : -1);
 		if (gpk) {
@@ -421,10 +421,10 @@ static void print_other_cpu_stall(unsigned long gp_seq)
 			pr_err("INFO: Stall ended before state dump start\n");
 		} else {
 			j = jiffies;
-			gpa = READ_ONCE(rcu_state.gp_activity);
+			gpa = data_race(rcu_state.gp_activity);
 			pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld, root ->qsmask %#lx\n",
 			       rcu_state.name, j - gpa, j, gpa,
-			       READ_ONCE(jiffies_till_next_fqs),
+			       data_race(jiffies_till_next_fqs),
 			       rcu_get_root()->qsmask);
 			/* In this case, the current CPU might be at fault. */
 			sched_show_task(current);
@@ -581,23 +581,23 @@ void show_rcu_gp_kthreads(void)
 	struct task_struct *t = READ_ONCE(rcu_state.gp_kthread);
 
 	j = jiffies;
-	ja = j - READ_ONCE(rcu_state.gp_activity);
-	jr = j - READ_ONCE(rcu_state.gp_req_activity);
-	jw = j - READ_ONCE(rcu_state.gp_wake_time);
+	ja = j - data_race(rcu_state.gp_activity);
+	jr = j - data_race(rcu_state.gp_req_activity);
+	jw = j - data_race(rcu_state.gp_wake_time);
 	pr_info("%s: wait state: %s(%d) ->state: %#lx delta ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_flags %#x\n",
 		rcu_state.name, gp_state_getname(rcu_state.gp_state),
 		rcu_state.gp_state, t ? t->state : 0x1ffffL,
-		ja, jr, jw, (long)READ_ONCE(rcu_state.gp_wake_seq),
-		(long)READ_ONCE(rcu_state.gp_seq),
-		(long)READ_ONCE(rcu_get_root()->gp_seq_needed),
-		READ_ONCE(rcu_state.gp_flags));
+		ja, jr, jw, (long)data_race(rcu_state.gp_wake_seq),
+		(long)data_race(rcu_state.gp_seq),
+		(long)data_race(rcu_get_root()->gp_seq_needed),
+		data_race(rcu_state.gp_flags));
 	rcu_for_each_node_breadth_first(rnp) {
 		if (ULONG_CMP_GE(READ_ONCE(rcu_state.gp_seq),
 				 READ_ONCE(rnp->gp_seq_needed)))
 			continue;
 		pr_info("\trcu_node %d:%d ->gp_seq %ld ->gp_seq_needed %ld\n",
-			rnp->grplo, rnp->grphi, (long)READ_ONCE(rnp->gp_seq),
-			(long)READ_ONCE(rnp->gp_seq_needed));
+			rnp->grplo, rnp->grphi, (long)data_race(rnp->gp_seq),
+			(long)data_race(rnp->gp_seq_needed));
 		if (!rcu_is_leaf_node(rnp))
 			continue;
 		for_each_leaf_node_possible_cpu(rnp, cpu) {
@@ -607,7 +607,7 @@ void show_rcu_gp_kthreads(void)
 					 READ_ONCE(rdp->gp_seq_needed)))
 				continue;
 			pr_info("\tcpu %d ->gp_seq_needed %ld\n",
-				cpu, (long)READ_ONCE(rdp->gp_seq_needed));
+				cpu, (long)data_race(rdp->gp_seq_needed));
 		}
 	}
 	for_each_possible_cpu(cpu) {