rcu: move TREE_RCU from softirq to kthread

If RCU priority boosting is to be meaningful, callback invocation must
be boosted in addition to preempted RCU readers.  Otherwise, in presence
of CPU real-time threads, the grace period ends, but the callbacks don't
get invoked.  If the callbacks don't get invoked, the associated memory
doesn't get freed, so the system is still subject to OOM.

But it is not reasonable to priority-boost RCU_SOFTIRQ, so this commit
moves the callback invocations to a kthread, which can be boosted easily.

Also add comments and properly synchronized all accesses to
rcu_cpu_kthread_task, as suggested by Lai Jiangshan.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>

Documentation/filesystems/proc.txt

@@ -836,7 +836,6 @@ Provides counts of softirq handlers serviced since boot time, for each cpu.
  TASKLET:          0          0          0        290
    SCHED:      27035      26983      26971      26746
  HRTIMER:          0          0          0          0
-     RCU:       1678       1769       2178       2250
 
 
 1.3 IDE devices in /proc/ide

include/linux/interrupt.h

@@ -414,7 +414,6 @@ enum
 	TASKLET_SOFTIRQ,
 	SCHED_SOFTIRQ,
 	HRTIMER_SOFTIRQ,
-	RCU_SOFTIRQ,	/* Preferable RCU should always be the last softirq */
 
 	NR_SOFTIRQS
 };

include/trace/events/irq.h

@@ -20,8 +20,7 @@ struct softirq_action;
 			 softirq_name(BLOCK_IOPOLL),	\
 			 softirq_name(TASKLET),		\
 			 softirq_name(SCHED),		\
-			 softirq_name(HRTIMER),		\
-			 softirq_name(RCU))
+			 softirq_name(HRTIMER))
 
 /**
  * irq_handler_entry - called immediately before the irq action handler

kernel/rcutree.h

@@ -111,6 +111,7 @@ struct rcu_node {
 				/*  elements that need to drain to allow the */
 				/*  current expedited grace period to */
 				/*  complete (only for TREE_PREEMPT_RCU). */
+	unsigned long wakemask; /* CPUs whose kthread needs to be awakened. */
 	unsigned long qsmaskinit;
 				/* Per-GP initial value for qsmask & expmask. */
 	unsigned long grpmask;	/* Mask to apply to parent qsmask. */
@@ -134,6 +135,13 @@ struct rcu_node {
 				/*  if there is no such task.  If there */
 				/*  is no current expedited grace period, */
 				/*  then there can cannot be any such task. */
+	struct task_struct *node_kthread_task;
+				/* kthread that takes care of this rcu_node */
+				/*  structure, for example, awakening the */
+				/*  per-CPU kthreads as needed. */
+	wait_queue_head_t node_wq;
+				/* Wait queue on which to park the per-node */
+				/*  kthread. */
 } ____cacheline_internodealigned_in_smp;
 
 /*

kernel/rcutree_plugin.h

@@ -1206,7 +1206,7 @@ static DEFINE_PER_CPU(unsigned long, rcu_dyntick_holdoff);
  *
  * Because it is not legal to invoke rcu_process_callbacks() with irqs
  * disabled, we do one pass of force_quiescent_state(), then do a
- * raise_softirq() to cause rcu_process_callbacks() to be invoked later.
+ * invoke_rcu_kthread() to cause rcu_process_callbacks() to be invoked later.
  * The per-cpu rcu_dyntick_drain variable controls the sequencing.
  */
 int rcu_needs_cpu(int cpu)
@@ -1257,7 +1257,7 @@ int rcu_needs_cpu(int cpu)
 
 	/* If RCU callbacks are still pending, RCU still needs this CPU. */
 	if (c)
-		raise_softirq(RCU_SOFTIRQ);
+		invoke_rcu_kthread();
 	return c;
 }
 

kernel/softirq.c

@@ -58,7 +58,7 @@ DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
 
 char *softirq_to_name[NR_SOFTIRQS] = {
 	"HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL",
-	"TASKLET", "SCHED", "HRTIMER",	"RCU"
+	"TASKLET", "SCHED", "HRTIMER"
 };
 
 /*

tools/perf/util/trace-event-parse.c

@@ -2187,7 +2187,6 @@ static const struct flag flags[] = {
 	{ "TASKLET_SOFTIRQ", 6 },
 	{ "SCHED_SOFTIRQ", 7 },
 	{ "HRTIMER_SOFTIRQ", 8 },
-	{ "RCU_SOFTIRQ", 9 },
 
 	{ "HRTIMER_NORESTART", 0 },
 	{ "HRTIMER_RESTART", 1 },