[PATCH tip/core/rcu 19/22] rcu: Allow RCU grace-period initialization to be preempted

[Paul E. McKenney]

From: "Paul E. McKenney" <paulmck@xxxxxxxxxxxxxxxxxx>

RCU grace-period initialization is currently carried out with interrupts
disabled, which can result in 200-microsecond latency spikes on systems
on which RCU has been configured for 4096 CPUs.  This patch therefore
makes the RCU grace-period initialization be preemptible, which should
eliminate those latency spikes.  Similar spikes from grace-period cleanup
and the forcing of quiescent states will be dealt with similarly by later
patches.

Reported-by: Mike Galbraith <mgalbraith@xxxxxxx>
Reported-by: Dimitri Sivanich <sivanich@xxxxxxx>
Signed-off-by: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
---
 kernel/rcutree.c |   17 ++++++++++-------
 1 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index faf4860..e5b4532 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1059,6 +1059,7 @@ static int rcu_gp_kthread(void *arg)
 			 * don't start another one.
 			 */
 			raw_spin_unlock_irqrestore(&rnp->lock, flags);
+			cond_resched();
 			continue;
 		}
 
@@ -1069,6 +1070,7 @@ static int rcu_gp_kthread(void *arg)
 			 */
 			rsp->fqs_need_gp = 1;
 			raw_spin_unlock_irqrestore(&rnp->lock, flags);
+			cond_resched();
 			continue;
 		}
 
@@ -1079,10 +1081,10 @@ static int rcu_gp_kthread(void *arg)
 		rsp->fqs_state = RCU_GP_INIT; /* Stop force_quiescent_state. */
 		rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS;
 		record_gp_stall_check_time(rsp);
-		raw_spin_unlock(&rnp->lock);  /* leave irqs disabled. */
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 
 		/* Exclude any concurrent CPU-hotplug operations. */
-		raw_spin_lock(&rsp->onofflock);  /* irqs already disabled. */
+		get_online_cpus();
 
 		/*
 		 * Set the quiescent-state-needed bits in all the rcu_node
@@ -1102,7 +1104,7 @@ static int rcu_gp_kthread(void *arg)
 		 * due to the fact that we have irqs disabled.
 		 */
 		rcu_for_each_node_breadth_first(rsp, rnp) {
-			raw_spin_lock(&rnp->lock); /* irqs already disabled. */
+			raw_spin_lock_irqsave(&rnp->lock, flags);
 			rcu_preempt_check_blocked_tasks(rnp);
 			rnp->qsmask = rnp->qsmaskinit;
 			rnp->gpnum = rsp->gpnum;
@@ -1113,15 +1115,16 @@ static int rcu_gp_kthread(void *arg)
 			trace_rcu_grace_period_init(rsp->name, rnp->gpnum,
 						    rnp->level, rnp->grplo,
 						    rnp->grphi, rnp->qsmask);
-			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
+			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);
 		/* force_quiescent_state() now OK. */
 		rsp->fqs_state = RCU_SIGNAL_INIT;
-		raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
-		raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		put_online_cpus();
 	}
 	return 0;
 }
-- 
1.7.8

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/