rcu: Provide exact CPU-online tracking for RCU

Up to now, RCU has assumed that the CPU-online process makes it from
CPU_UP_PREPARE to set_cpu_online() within one jiffy.  Given the recent
rise of virtualized environments, this assumption is very clearly
obsolete.  Failing to meet this deadline can result in RCU paying
attention to an incoming CPU for one jiffy, then ignoring it until the
grace period following the one in which that CPU sets itself online.
This situation might prove to be fatally disappointing to any RCU
read-side critical sections that had the misfortune to execute during
the time in which RCU was ignoring the slow-to-come-online CPU.

This commit therefore updates RCU's internal CPU state-tracking
information at notify_cpu_starting() time, thus providing RCU with
an exact transition of the CPU's state from offline to online.

Note that this means that incoming CPUs must not use RCU read-side
critical section (other than those of SRCU) until notify_cpu_starting()
time.  Note also that the CPU_STARTING notifiers -are- allowed to use
RCU read-side critical sections.  (Of course, CPU-hotplug notifiers are
rapidly becoming obsolete, so you need to act fast!)

If a given architecture or CPU family needs to use RCU read-side
critical sections earlier, the call to rcu_cpu_starting() from
notify_cpu_starting() will need to be architecture-specific, with
architectures that need early use being required to hand-place
the call to rcu_cpu_starting() at some point preceding the call to
notify_cpu_starting().
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

include/linux/rcupdate.h

@@ -334,6 +334,7 @@ void rcu_sched_qs(void);
 void rcu_bh_qs(void);
 void rcu_check_callbacks(int user);
 void rcu_report_dead(unsigned int cpu);
+void rcu_cpu_starting(unsigned int cpu);
 
 #ifndef CONFIG_TINY_RCU
 void rcu_end_inkernel_boot(void);

kernel/cpu.c

@@ -889,6 +889,7 @@ void notify_cpu_starting(unsigned int cpu)
 	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
 	enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE);
 
+	rcu_cpu_starting(cpu);  /* All CPU_STARTING notifiers can use RCU. */
 	while (st->state < target) {
 		struct cpuhp_step *step;
 

kernel/rcu/tree.c

@@ -3792,8 +3792,6 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rnp = rdp->mynode;
 	mask = rdp->grpmask;
 	raw_spin_lock_rcu_node(rnp);		/* irqs already disabled. */
-	rnp->qsmaskinitnext |= mask;
-	rnp->expmaskinitnext |= mask;
 	if (!rdp->beenonline)
 		WRITE_ONCE(rsp->ncpus, READ_ONCE(rsp->ncpus) + 1);
 	rdp->beenonline = true;	 /* We have now been online. */
@@ -3860,6 +3858,32 @@ int rcutree_dead_cpu(unsigned int cpu)
 	return 0;
 }
 
+/*
+ * Mark the specified CPU as being online so that subsequent grace periods
+ * (both expedited and normal) will wait on it.  Note that this means that
+ * incoming CPUs are not allowed to use RCU read-side critical sections
+ * until this function is called.  Failing to observe this restriction
+ * will result in lockdep splats.
+ */
+void rcu_cpu_starting(unsigned int cpu)
+{
+	unsigned long flags;
+	unsigned long mask;
+	struct rcu_data *rdp;
+	struct rcu_node *rnp;
+	struct rcu_state *rsp;
+
+	for_each_rcu_flavor(rsp) {
+		rdp = this_cpu_ptr(rsp->rda);
+		rnp = rdp->mynode;
+		mask = rdp->grpmask;
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
+		rnp->qsmaskinitnext |= mask;
+		rnp->expmaskinitnext |= mask;
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+	}
+}
+
 #ifdef CONFIG_HOTPLUG_CPU
 /*
  * The CPU is exiting the idle loop into the arch_cpu_idle_dead()
@@ -4209,8 +4233,10 @@ void __init rcu_init(void)
 	 * or the scheduler are operational.
 	 */
 	pm_notifier(rcu_pm_notify, 0);
-	for_each_online_cpu(cpu)
+	for_each_online_cpu(cpu) {
 		rcutree_prepare_cpu(cpu);
+		rcu_cpu_starting(cpu);
+	}
 }
 
 #include "tree_exp.h"