Subject: rcu: Merge RCU-bh into RCU-preempt
Date: Wed, 5 Oct 2011 11:59:38 -0700
From: Thomas Gleixner <tglx@linutronix.de>

The Linux kernel has long RCU-bh read-side critical sections that
intolerably increase scheduling latency under mainline's RCU-bh rules,
which include RCU-bh read-side critical sections being non-preemptible.
This patch therefore arranges for RCU-bh to be implemented in terms of
RCU-preempt for CONFIG_PREEMPT_RT_FULL=y.

This has the downside of defeating the purpose of RCU-bh, namely,
handling the case where the system is subjected to a network-based
denial-of-service attack that keeps at least one CPU doing full-time
softirq processing.  This issue will be fixed by a later commit.

The current commit will need some work to make it appropriate for
mainline use, for example, it needs to be extended to cover Tiny RCU.

[ paulmck: Added a useful changelog ]

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/20111005185938.GA20403@linux.vnet.ibm.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 include/linux/rcupdate.h |   23 +++++++++++++++++++++++
 include/linux/rcutree.h  |    8 ++++++++
 kernel/rcu/rcu.h         |   14 +++++++++++---
 kernel/rcu/rcutorture.c  |    7 +++++++
 kernel/rcu/tree.c        |   24 ++++++++++++++++++++++++
 kernel/rcu/tree.h        |    2 ++
 kernel/rcu/update.c      |    2 ++
 7 files changed, 77 insertions(+), 3 deletions(-)

--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -56,7 +56,11 @@ void call_rcu(struct rcu_head *head, rcu
 #define	call_rcu	call_rcu_sched
 #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+#define call_rcu_bh	call_rcu
+#else
 void call_rcu_bh(struct rcu_head *head, rcu_callback_t func);
+#endif
 void call_rcu_sched(struct rcu_head *head, rcu_callback_t func);
 void synchronize_sched(void);
 void rcu_barrier_tasks(void);
@@ -113,7 +117,11 @@ static inline int rcu_preempt_depth(void
 void rcu_init(void);
 extern int rcu_scheduler_active __read_mostly;
 void rcu_sched_qs(void);
+#ifdef CONFIG_PREEMPT_RT_FULL
+static inline void rcu_bh_qs(void) { }
+#else
 void rcu_bh_qs(void);
+#endif
 void rcu_check_callbacks(int user);
 void rcu_report_dead(unsigned int cpu);
 void rcu_cpu_starting(unsigned int cpu);
@@ -263,7 +271,14 @@ extern struct lockdep_map rcu_sched_lock
 extern struct lockdep_map rcu_callback_map;
 int debug_lockdep_rcu_enabled(void);
 int rcu_read_lock_held(void);
+#ifdef CONFIG_PREEMPT_RT_FULL
+static inline int rcu_read_lock_bh_held(void)
+{
+	return rcu_read_lock_held();
+}
+#else
 int rcu_read_lock_bh_held(void);
+#endif
 int rcu_read_lock_sched_held(void);
 
 #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
@@ -667,10 +682,14 @@ static inline void rcu_read_unlock(void)
 static inline void rcu_read_lock_bh(void)
 {
 	local_bh_disable();
+#ifdef CONFIG_PREEMPT_RT_FULL
+	rcu_read_lock();
+#else
 	__acquire(RCU_BH);
 	rcu_lock_acquire(&rcu_bh_lock_map);
 	RCU_LOCKDEP_WARN(!rcu_is_watching(),
 			 "rcu_read_lock_bh() used illegally while idle");
+#endif
 }
 
 /*
@@ -680,10 +699,14 @@ static inline void rcu_read_lock_bh(void
  */
 static inline void rcu_read_unlock_bh(void)
 {
+#ifdef CONFIG_PREEMPT_RT_FULL
+	rcu_read_unlock();
+#else
 	RCU_LOCKDEP_WARN(!rcu_is_watching(),
 			 "rcu_read_unlock_bh() used illegally while idle");
 	rcu_lock_release(&rcu_bh_lock_map);
 	__release(RCU_BH);
+#endif
 	local_bh_enable();
 }
 
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -44,7 +44,11 @@ static inline void rcu_virt_note_context
 	rcu_note_context_switch(false);
 }
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+# define synchronize_rcu_bh	synchronize_rcu
+#else
 void synchronize_rcu_bh(void);
+#endif
 void synchronize_sched_expedited(void);
 void synchronize_rcu_expedited(void);
 
@@ -72,7 +76,11 @@ static inline void synchronize_rcu_bh_ex
 }
 
 void rcu_barrier(void);
+#ifdef CONFIG_PREEMPT_RT_FULL
+# define rcu_barrier_bh                rcu_barrier
+#else
 void rcu_barrier_bh(void);
+#endif
 void rcu_barrier_sched(void);
 unsigned long get_state_synchronize_rcu(void);
 void cond_synchronize_rcu(unsigned long oldstate);
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -462,18 +462,26 @@ static inline void show_rcu_gp_kthreads(
 extern unsigned long rcutorture_testseq;
 extern unsigned long rcutorture_vernum;
 unsigned long rcu_batches_started(void);
-unsigned long rcu_batches_started_bh(void);
 unsigned long rcu_batches_started_sched(void);
 unsigned long rcu_batches_completed(void);
-unsigned long rcu_batches_completed_bh(void);
 unsigned long rcu_batches_completed_sched(void);
 unsigned long rcu_exp_batches_completed(void);
 unsigned long rcu_exp_batches_completed_sched(void);
 unsigned long srcu_batches_completed(struct srcu_struct *sp);
 void show_rcu_gp_kthreads(void);
 void rcu_force_quiescent_state(void);
-void rcu_bh_force_quiescent_state(void);
 void rcu_sched_force_quiescent_state(void);
+
+#ifndef CONFIG_PREEMPT_RT_FULL
+void rcu_bh_force_quiescent_state(void);
+unsigned long rcu_batches_started_bh(void);
+unsigned long rcu_batches_completed_bh(void);
+#else
+# define rcu_bh_force_quiescent_state	rcu_force_quiescent_state
+# define rcu_batches_completed_bh	rcu_batches_completed
+# define rcu_batches_started_bh		rcu_batches_completed
+#endif
+
 #endif /* #else #ifdef CONFIG_TINY_RCU */
 
 #ifdef CONFIG_RCU_NOCB_CPU
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -417,6 +417,7 @@ static struct rcu_torture_ops rcu_ops =
 	.name		= "rcu"
 };
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /*
  * Definitions for rcu_bh torture testing.
  */
@@ -456,6 +457,12 @@ static struct rcu_torture_ops rcu_bh_ops
 	.name		= "rcu_bh"
 };
 
+#else
+static struct rcu_torture_ops rcu_bh_ops = {
+	.ttype		= INVALID_RCU_FLAVOR,
+};
+#endif
+
 /*
  * Don't even think about trying any of these in real life!!!
  * The names includes "busted", and they really means it!
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -243,6 +243,7 @@ void rcu_sched_qs(void)
 			   this_cpu_ptr(&rcu_sched_data), true);
 }
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 void rcu_bh_qs(void)
 {
 	RCU_LOCKDEP_WARN(preemptible(), "rcu_bh_qs() invoked with preemption enabled!!!");
@@ -253,6 +254,7 @@ void rcu_bh_qs(void)
 		__this_cpu_write(rcu_bh_data.cpu_no_qs.b.norm, false);
 	}
 }
+#endif
 
 /*
  * Steal a bit from the bottom of ->dynticks for idle entry/exit
@@ -564,11 +566,13 @@ EXPORT_SYMBOL_GPL(rcu_batches_started_sc
 /*
  * Return the number of RCU BH batches started thus far for debug & stats.
  */
+#ifndef CONFIG_PREEMPT_RT_FULL
 unsigned long rcu_batches_started_bh(void)
 {
 	return rcu_bh_state.gpnum;
 }
 EXPORT_SYMBOL_GPL(rcu_batches_started_bh);
+#endif
 
 /*
  * Return the number of RCU batches completed thus far for debug & stats.
@@ -588,6 +592,7 @@ unsigned long rcu_batches_completed_sche
 }
 EXPORT_SYMBOL_GPL(rcu_batches_completed_sched);
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /*
  * Return the number of RCU BH batches completed thus far for debug & stats.
  */
@@ -596,6 +601,7 @@ unsigned long rcu_batches_completed_bh(v
 	return rcu_bh_state.completed;
 }
 EXPORT_SYMBOL_GPL(rcu_batches_completed_bh);
+#endif
 
 /*
  * Return the number of RCU expedited batches completed thus far for
@@ -619,6 +625,7 @@ unsigned long rcu_exp_batches_completed_
 }
 EXPORT_SYMBOL_GPL(rcu_exp_batches_completed_sched);
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /*
  * Force a quiescent state.
  */
@@ -637,6 +644,13 @@ void rcu_bh_force_quiescent_state(void)
 }
 EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state);
 
+#else
+void rcu_force_quiescent_state(void)
+{
+}
+EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
+#endif
+
 /*
  * Force a quiescent state for RCU-sched.
  */
@@ -687,9 +701,11 @@ void rcutorture_get_gp_data(enum rcutort
 	case RCU_FLAVOR:
 		rsp = rcu_state_p;
 		break;
+#ifndef CONFIG_PREEMPT_RT_FULL
 	case RCU_BH_FLAVOR:
 		rsp = &rcu_bh_state;
 		break;
+#endif
 	case RCU_SCHED_FLAVOR:
 		rsp = &rcu_sched_state;
 		break;
@@ -3113,6 +3129,7 @@ void call_rcu_sched(struct rcu_head *hea
 }
 EXPORT_SYMBOL_GPL(call_rcu_sched);
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /**
  * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period.
  * @head: structure to be used for queueing the RCU updates.
@@ -3140,6 +3157,7 @@ void call_rcu_bh(struct rcu_head *head,
 	__call_rcu(head, func, &rcu_bh_state, -1, 0);
 }
 EXPORT_SYMBOL_GPL(call_rcu_bh);
+#endif
 
 /*
  * Queue an RCU callback for lazy invocation after a grace period.
@@ -3225,6 +3243,7 @@ void synchronize_sched(void)
 }
 EXPORT_SYMBOL_GPL(synchronize_sched);
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /**
  * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed.
  *
@@ -3251,6 +3270,7 @@ void synchronize_rcu_bh(void)
 		wait_rcu_gp(call_rcu_bh);
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
+#endif
 
 /**
  * get_state_synchronize_rcu - Snapshot current RCU state
@@ -3601,6 +3621,7 @@ static void _rcu_barrier(struct rcu_stat
 	mutex_unlock(&rsp->barrier_mutex);
 }
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /**
  * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete.
  */
@@ -3609,6 +3630,7 @@ void rcu_barrier_bh(void)
 	_rcu_barrier(&rcu_bh_state);
 }
 EXPORT_SYMBOL_GPL(rcu_barrier_bh);
+#endif
 
 /**
  * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks.
@@ -4184,7 +4206,9 @@ void __init rcu_init(void)
 
 	rcu_bootup_announce();
 	rcu_init_geometry();
+#ifndef CONFIG_PREEMPT_RT_FULL
 	rcu_init_one(&rcu_bh_state);
+#endif
 	rcu_init_one(&rcu_sched_state);
 	if (dump_tree)
 		rcu_dump_rcu_node_tree(&rcu_sched_state);
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -427,7 +427,9 @@ extern struct list_head rcu_struct_flavo
  */
 extern struct rcu_state rcu_sched_state;
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 extern struct rcu_state rcu_bh_state;
+#endif
 
 #ifdef CONFIG_PREEMPT_RCU
 extern struct rcu_state rcu_preempt_state;
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -333,6 +333,7 @@ int rcu_read_lock_held(void)
 }
 EXPORT_SYMBOL_GPL(rcu_read_lock_held);
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /**
  * rcu_read_lock_bh_held() - might we be in RCU-bh read-side critical section?
  *
@@ -359,6 +360,7 @@ int rcu_read_lock_bh_held(void)
 	return in_softirq() || irqs_disabled();
 }
 EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held);
+#endif
 
 #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */