rcu: Execute RCU reader shortly after rcu_core for strict GPs

A kernel built with CONFIG_RCU_STRICT_GRACE_PERIOD=y needs a quiescent
state to appear very shortly after a CPU has noticed a new grace period.
Placing an RCU reader immediately after this point is ineffective because
this normally happens in softirq context, which acts as a big RCU reader.
This commit therefore introduces a new per-CPU work_struct, which is
used at the end of rcu_core() processing to schedule an RCU read-side
critical section from within a clean environment.

Reported-by Jann Horn <jannh@google.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

kernel/rcu/tree.c

@@ -2646,6 +2646,14 @@ void rcu_force_quiescent_state(void)
 }
 EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
 
+// Workqueue handler for an RCU reader for kernels enforcing struct RCU
+// grace periods.
+static void strict_work_handler(struct work_struct *work)
+{
+	rcu_read_lock();
+	rcu_read_unlock();
+}
+
 /* Perform RCU core processing work for the current CPU.  */
 static __latent_entropy void rcu_core(void)
 {
@@ -2690,6 +2698,10 @@ static __latent_entropy void rcu_core(void)
 	/* Do any needed deferred wakeups of rcuo kthreads. */
 	do_nocb_deferred_wakeup(rdp);
 	trace_rcu_utilization(TPS("End RCU core"));
+
+	// If strict GPs, schedule an RCU reader in a clean environment.
+	if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD))
+		queue_work_on(rdp->cpu, rcu_gp_wq, &rdp->strict_work);
 }
 
 static void rcu_core_si(struct softirq_action *h)
@@ -3887,6 +3899,7 @@ rcu_boot_init_percpu_data(int cpu)
 
 	/* Set up local state, ensuring consistent view of global state. */
 	rdp->grpmask = leaf_node_cpu_bit(rdp->mynode, cpu);
+	INIT_WORK(&rdp->strict_work, strict_work_handler);
 	WARN_ON_ONCE(rdp->dynticks_nesting != 1);
 	WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp)));
 	rdp->rcu_ofl_gp_seq = rcu_state.gp_seq;

kernel/rcu/tree.h

@@ -164,6 +164,7 @@ struct rcu_data {
 					/* period it is aware of. */
 	struct irq_work defer_qs_iw;	/* Obtain later scheduler attention. */
 	bool defer_qs_iw_pending;	/* Scheduler attention pending? */
+	struct work_struct strict_work;	/* Schedule readers for strict GPs. */
 
 	/* 2) batch handling */
 	struct rcu_segcblist cblist;	/* Segmented callback list, with */