rcu: Enable elimination of Tree-RCU softirq processing

Some workloads need to change kthread priority for RCU core processing
without affecting other softirq work.  This commit therefore introduces
the rcutree.use_softirq kernel boot parameter, which moves the RCU core
work from softirq to a per-CPU SCHED_OTHER kthread named rcuc.  Use of
SCHED_OTHER approach avoids the scalability problems that appeared
with the earlier attempt to move RCU core processing to from softirq
to kthreads.  That said, kernels built with RCU_BOOST=y will run the
rcuc kthreads at the RCU-boosting priority.

Note that rcutree.use_softirq=0 must be specified to move RCU core
processing to the rcuc kthreads: rcutree.use_softirq=1 is the default.

Reported-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
[ paulmck: Adjust for invoke_rcu_callbacks() only ever being invoked
  from RCU core processing, in contrast to softirq->rcuc transition
  in old mainline RCU priority boosting. ]
[ paulmck: Avoid wakeups when scheduler might have invoked rcu_read_unlock()
  while holding rq or pi locks, also possibly fixing a pre-existing latent
  bug involving raise_softirq()-induced wakeups. ]
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 980ca3c..8e29016 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -51,6 +51,12 @@
 #include <linux/tick.h>
 #include <linux/sysrq.h>
 #include <linux/kprobes.h>
+#include <linux/gfp.h>
+#include <linux/oom.h>
+#include <linux/smpboot.h>
+#include <linux/jiffies.h>
+#include <linux/sched/isolation.h>
+#include "../time/tick-internal.h"
 
 #include "tree.h"
 #include "rcu.h"
@@ -92,6 +98,9 @@ struct rcu_state rcu_state = {
 /* Dump rcu_node combining tree at boot to verify correct setup. */
 static bool dump_tree;
 module_param(dump_tree, bool, 0444);
+/* By default, use RCU_SOFTIRQ instead of rcuc kthreads. */
+static bool use_softirq = 1;
+module_param(use_softirq, bool, 0444);
 /* Control rcu_node-tree auto-balancing at boot time. */
 static bool rcu_fanout_exact;
 module_param(rcu_fanout_exact, bool, 0444);
@@ -2253,7 +2262,7 @@ void rcu_force_quiescent_state(void)
 EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
 
 /* Perform RCU core processing work for the current CPU.  */
-static __latent_entropy void rcu_core(struct softirq_action *unused)
+static __latent_entropy void rcu_core(void)
 {
 	unsigned long flags;
 	struct rcu_data *rdp = raw_cpu_ptr(&rcu_data);
@@ -2295,30 +2304,132 @@ static __latent_entropy void rcu_core(struct softirq_action *unused)
 	trace_rcu_utilization(TPS("End RCU core"));
 }
 
+static void rcu_core_si(struct softirq_action *h)
+{
+	rcu_core();
+}
+
+static void rcu_wake_cond(struct task_struct *t, int status)
+{
+	/*
+	 * If the thread is yielding, only wake it when this
+	 * is invoked from idle
+	 */
+	if (t && (status != RCU_KTHREAD_YIELDING || is_idle_task(current)))
+		wake_up_process(t);
+}
+
+static void invoke_rcu_core_kthread(void)
+{
+	struct task_struct *t;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__this_cpu_write(rcu_data.rcu_cpu_has_work, 1);
+	t = __this_cpu_read(rcu_data.rcu_cpu_kthread_task);
+	if (t != NULL && t != current)
+		rcu_wake_cond(t, __this_cpu_read(rcu_data.rcu_cpu_kthread_status));
+	local_irq_restore(flags);
+}
+
 /*
- * Schedule RCU callback invocation.  If the running implementation of RCU
- * does not support RCU priority boosting, just do a direct call, otherwise
- * wake up the per-CPU kernel kthread.  Note that because we are running
- * on the current CPU with softirqs disabled, the rcu_cpu_kthread_task
- * cannot disappear out from under us.
+ * Do RCU callback invocation.  Not that if we are running !use_softirq,
+ * we are already in the rcuc kthread.  If callbacks are offloaded, then
+ * ->cblist is always empty, so we don't get here.  Therefore, we only
+ * ever need to check for the scheduler being operational (some callbacks
+ * do wakeups, so we do need the scheduler).
  */
 static void invoke_rcu_callbacks(struct rcu_data *rdp)
 {
 	if (unlikely(!READ_ONCE(rcu_scheduler_fully_active)))
 		return;
-	if (likely(!rcu_state.boost)) {
-		rcu_do_batch(rdp);
-		return;
-	}
-	invoke_rcu_callbacks_kthread();
+	rcu_do_batch(rdp);
 }
 
+/*
+ * Wake up this CPU's rcuc kthread to do RCU core processing.
+ */
 static void invoke_rcu_core(void)
 {
-	if (cpu_online(smp_processor_id()))
+	if (!cpu_online(smp_processor_id()))
+		return;
+	if (use_softirq)
 		raise_softirq(RCU_SOFTIRQ);
+	else
+		invoke_rcu_core_kthread();
 }
 
+static void rcu_cpu_kthread_park(unsigned int cpu)
+{
+	per_cpu(rcu_data.rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU;
+}
+
+static int rcu_cpu_kthread_should_run(unsigned int cpu)
+{
+	return __this_cpu_read(rcu_data.rcu_cpu_has_work);
+}
+
+/*
+ * Per-CPU kernel thread that invokes RCU callbacks.  This replaces
+ * the RCU softirq used in configurations of RCU that do not support RCU
+ * priority boosting.
+ */
+static void rcu_cpu_kthread(unsigned int cpu)
+{
+	unsigned int *statusp = this_cpu_ptr(&rcu_data.rcu_cpu_kthread_status);
+	char work, *workp = this_cpu_ptr(&rcu_data.rcu_cpu_has_work);
+	int spincnt;
+
+	for (spincnt = 0; spincnt < 10; spincnt++) {
+		trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait"));
+		local_bh_disable();
+		*statusp = RCU_KTHREAD_RUNNING;
+		local_irq_disable();
+		work = *workp;
+		*workp = 0;
+		local_irq_enable();
+		if (work)
+			rcu_core();
+		local_bh_enable();
+		if (*workp == 0) {
+			trace_rcu_utilization(TPS("End CPU kthread@rcu_wait"));
+			*statusp = RCU_KTHREAD_WAITING;
+			return;
+		}
+	}
+	*statusp = RCU_KTHREAD_YIELDING;
+	trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield"));
+	schedule_timeout_interruptible(2);
+	trace_rcu_utilization(TPS("End CPU kthread@rcu_yield"));
+	*statusp = RCU_KTHREAD_WAITING;
+}
+
+static struct smp_hotplug_thread rcu_cpu_thread_spec = {
+	.store			= &rcu_data.rcu_cpu_kthread_task,
+	.thread_should_run	= rcu_cpu_kthread_should_run,
+	.thread_fn		= rcu_cpu_kthread,
+	.thread_comm		= "rcuc/%u",
+	.setup			= rcu_cpu_kthread_setup,
+	.park			= rcu_cpu_kthread_park,
+};
+
+/*
+ * Spawn per-CPU RCU core processing kthreads.
+ */
+static int __init rcu_spawn_core_kthreads(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		per_cpu(rcu_data.rcu_cpu_has_work, cpu) = 0;
+	if (!IS_ENABLED(CONFIG_RCU_BOOST) && use_softirq)
+		return 0;
+	WARN_ONCE(smpboot_register_percpu_thread(&rcu_cpu_thread_spec),
+		  "%s: Could not start rcuc kthread, OOM is now expected behavior\n", __func__);
+	return 0;
+}
+early_initcall(rcu_spawn_core_kthreads);
+
 /*
  * Handle any core-RCU processing required by a call_rcu() invocation.
  */
@@ -3355,7 +3466,8 @@ void __init rcu_init(void)
 	rcu_init_one();
 	if (dump_tree)
 		rcu_dump_rcu_node_tree();
-	open_softirq(RCU_SOFTIRQ, rcu_core);
+	if (use_softirq)
+		open_softirq(RCU_SOFTIRQ, rcu_core_si);
 
 	/*
 	 * We don't need protection against CPU-hotplug here because