rcu: Add polled expedited grace-period primitives

This commit adds expedited grace-period functionality to RCU's polled
grace-period API, adding start_poll_synchronize_rcu_expedited() and
cond_synchronize_rcu_expedited(), which are similar to the existing
start_poll_synchronize_rcu() and cond_synchronize_rcu() functions,
respectively.

Note that although start_poll_synchronize_rcu_expedited() can be invoked
very early, the resulting expedited grace periods are not guaranteed
to start until after workqueues are fully initialized.  On the other
hand, both synchronize_rcu() and synchronize_rcu_expedited() can also
be invoked very early, and the resulting grace periods will be taken
into account as they occur.

[ paulmck: Apply feedback from Neeraj Upadhyay. ]

Link: https://lore.kernel.org/all/20220121142454.1994916-1-bfoster@redhat.com/
Link: https://docs.google.com/document/d/1RNKWW9jQyfjxw2E8dsXVTdvZYh0HnYeSHDKog9jhdN8/edit?usp=sharing
Cc: Brian Foster <bfoster@redhat.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Ian Kent <raven@themaw.net>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

1 files changed, 12 insertions, 5 deletions

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 1505b02b4e53..6cf5b51622cd 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -4027,20 +4027,20 @@ EXPORT_SYMBOL_GPL(poll_state_synchronize_rcu);
 /**
  * cond_synchronize_rcu - Conditionally wait for an RCU grace period
  *
- * @oldstate: value from get_state_synchronize_rcu() or start_poll_synchronize_rcu()
+ * @oldstate: value from get_state_synchronize_rcu(), start_poll_synchronize_rcu(), or start_poll_synchronize_rcu_expedited()
  *
  * If a full RCU grace period has elapsed since the earlier call to
  * get_state_synchronize_rcu() or start_poll_synchronize_rcu(), just return.
  * Otherwise, invoke synchronize_rcu() to wait for a full grace period.
  *
- * Yes, this function does not take counter wrap into account.  But
- * counter wrap is harmless.  If the counter wraps, we have waited for
+ * Yes, this function does not take counter wrap into account.
+ * But counter wrap is harmless.  If the counter wraps, we have waited for
  * more than 2 billion grace periods (and way more on a 64-bit system!),
- * so waiting for one additional grace period should be just fine.
+ * so waiting for a couple of additional grace periods should be just fine.
  *
  * This function provides the same memory-ordering guarantees that
  * would be provided by a synchronize_rcu() that was invoked at the call
- * to the function that provided @oldstate, and that returned at the end
+ * to the function that provided @oldstate and that returned at the end
  * of this function.
  */
 void cond_synchronize_rcu(unsigned long oldstate)
@@ -4793,6 +4793,9 @@ static void __init rcu_init_one(void)
 			init_waitqueue_head(&rnp->exp_wq[3]);
 			spin_lock_init(&rnp->exp_lock);
 			mutex_init(&rnp->boost_kthread_mutex);
+			raw_spin_lock_init(&rnp->exp_poll_lock);
+			rnp->exp_seq_poll_rq = RCU_GET_STATE_COMPLETED;
+			INIT_WORK(&rnp->exp_poll_wq, sync_rcu_do_polled_gp);
 		}
 	}
 
@@ -5018,6 +5021,10 @@ void __init rcu_init(void)
 		qovld_calc = DEFAULT_RCU_QOVLD_MULT * qhimark;
 	else
 		qovld_calc = qovld;
+
+	// Kick-start any polled grace periods that started early.
+	if (!(per_cpu_ptr(&rcu_data, cpu)->mynode->exp_seq_poll_rq & 0x1))
+		(void)start_poll_synchronize_rcu_expedited();
 }
 
 #include "tree_stall.h"