rcu: Allow RCU grace-period cleanup to be preempted

RCU grace-period cleanup is currently carried out with interrupts
disabled, which can result in excessive latency spikes on large systems
(many hundreds or thousands of CPUs).  This patch therefore makes the
RCU grace-period cleanup be preemptible, including voluntary preemption
points, which should eliminate those latency spikes.  Similar spikes from
forcing of quiescent states will be dealt with similarly by later patches.

Reported-by: Mike Galbraith <mgalbraith@suse.de>
Reported-by: Dimitri Sivanich <sivanich@sgi.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 9fad21c86e78ae4f354abed3419e677ff21c278b..300aba6926928dc75f80102e16ceab5e7c4d02ee 100644 (file)
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1170,7 +1170,7 @@ static int rcu_gp_kthread(void *arg)
                 * completed.
                 */
                if (*rdp->nxttail[RCU_WAIT_TAIL] == NULL) {
-                       raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
+                       raw_spin_unlock_irqrestore(&rnp->lock, flags);
 
                        /*
                         * Propagate new ->completed value to rcu_node
@@ -1179,14 +1179,13 @@ static int rcu_gp_kthread(void *arg)
                         * to process their callbacks.
                         */
                        rcu_for_each_node_breadth_first(rsp, rnp) {
-                               /* irqs already disabled. */
-                               raw_spin_lock(&rnp->lock);
+                               raw_spin_lock_irqsave(&rnp->lock, flags);
                                rnp->completed = rsp->gpnum;
-                               /* irqs remain disabled. */
-                               raw_spin_unlock(&rnp->lock);
+                               raw_spin_unlock_irqrestore(&rnp->lock, flags);
+                               cond_resched();
                        }
                        rnp = rcu_get_root(rsp);
-                       raw_spin_lock(&rnp->lock); /* irqs already disabled. */
+                       raw_spin_lock_irqsave(&rnp->lock, flags);
                }
 
                rsp->completed = rsp->gpnum; /* Declare grace period done. */