rcu: Switch __rcu_process_callbacks() to rcu_accelerate_cbs()

The __rcu_process_callbacks() function currently checks to see if
the current CPU needs a grace period and also if there is any other
reason to kick off a new grace period.  This is one of the fail-safe
checks that has been rendered unnecessary by the changes that increase
the accuracy of rcu_gp_cleanup()'s estimate as to whether another grace
period is required.  Because this particular fail-safe involved acquiring
the root rcu_node structure's ->lock, which has seen excessive contention
in real life, this fail-safe needs to go.

However, one check must remain, namely the check for newly arrived
RCU callbacks that have not yet been associated with a grace period.
One might hope that the checks in __note_gp_changes(), which is invoked
indirectly from rcu_check_quiescent_state(), would suffice, but this
function won't be invoked at all if RCU is idle.  It is therefore necessary
to replace the fail-safe checks with a simpler check for newly arrived
callbacks during an RCU idle period, which is exactly what this commit
does.  This change removes the final call to rcu_start_gp(), so this
function is removed as well.

Note that lockless use of cpu_needs_another_gp() is racy, but that
these races are harmless in this case.  If RCU really is idle, the
values will not change, so the return value from cpu_needs_another_gp()
will be correct.  If RCU is not idle, the resulting redundant call to
rcu_accelerate_cbs() will be harmless, and might even have the benefit
of reducing grace-period latency a bit.

This commit also moves interrupt disabling into the "if" statement to
improve real-time response a bit.

Reported-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Tested-by: Nicholas Piggin <npiggin@gmail.com>

1 files changed, 15 insertions, 38 deletions

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 6396a3d10be9..fbacc486ed4c 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2335,34 +2335,6 @@ rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
 }
 
 /*
- * Similar to rcu_start_gp_advanced(), but also advance the calling CPU's
- * callbacks.  Note that rcu_start_gp_advanced() cannot do this because it
- * is invoked indirectly from rcu_advance_cbs(), which would result in
- * endless recursion -- or would do so if it wasn't for the self-deadlock
- * that is encountered beforehand.
- *
- * Returns true if the grace-period kthread needs to be awakened.
- */
-static bool rcu_start_gp(struct rcu_state *rsp)
-{
-        struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
-        struct rcu_node *rnp = rcu_get_root(rsp);
-        bool ret = false;
-
-        /*
-         * If there is no grace period in progress right now, any
-         * callbacks we have up to this point will be satisfied by the
-         * next grace period.  Also, advancing the callbacks reduces the
-         * probability of false positives from cpu_needs_another_gp()
-         * resulting in pointless grace periods.  So, advance callbacks
-         * then start the grace period!
-         */
-        ret = rcu_advance_cbs(rsp, rnp, rdp) || ret;
-        ret = rcu_start_gp_advanced(rsp, rnp, rdp) || ret;
-        return ret;
-}
-
-/*
  * Report a full set of quiescent states to the specified rcu_state data
  * structure.  Invoke rcu_gp_kthread_wake() to awaken the grace-period
  * kthread if another grace period is required.  Whether we wake
@@ -2889,22 +2861,27 @@ __rcu_process_callbacks(struct rcu_state *rsp)
         unsigned long flags;
         bool needwake;
         struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
+        struct rcu_node *rnp;
 
         WARN_ON_ONCE(!rdp->beenonline);
 
         /* Update RCU state based on any recent quiescent states. */
         rcu_check_quiescent_state(rsp, rdp);
 
-        /* Does this CPU require a not-yet-started grace period? */
-        local_irq_save(flags);
-        if (cpu_needs_another_gp(rsp, rdp)) {
-                raw_spin_lock_rcu_node(rcu_get_root(rsp)); /* irqs disabled. */
-                needwake = rcu_start_gp(rsp);
-                raw_spin_unlock_irqrestore_rcu_node(rcu_get_root(rsp), flags);
-                if (needwake)
-                        rcu_gp_kthread_wake(rsp);
-        } else {
-                local_irq_restore(flags);
+        /* No grace period and unregistered callbacks? */
+        if (!rcu_gp_in_progress(rsp) &&
+            rcu_segcblist_is_enabled(&rdp->cblist)) {
+                local_irq_save(flags);
+                if (rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) {
+                        local_irq_restore(flags);
+                } else {
+                        rnp = rdp->mynode;
+                        raw_spin_lock_rcu_node(rnp); /* irqs disabled. */
+                        needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
+                        raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+                        if (needwake)
+                                rcu_gp_kthread_wake(rsp);
+                }
         }
 
         /* If there are callbacks ready, invoke them. */