rcu: Merge RCU-bh into RCU-preempt

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>

4 files changed, 59 insertions, 2 deletions

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 23c060ae4097..e245e716cd34 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -167,6 +167,9 @@ void call_rcu(struct rcu_head *head,
 
 #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+#define call_rcu_bh	call_rcu
+#else
 /**
  * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period.
  * @head: structure to be used for queueing the RCU updates.
@@ -190,6 +193,7 @@ void call_rcu(struct rcu_head *head,
  */
 void call_rcu_bh(struct rcu_head *head,
 		 void (*func)(struct rcu_head *head));
+#endif
 
 /**
  * call_rcu_sched() - Queue an RCU for invocation after sched grace period.
@@ -296,7 +300,13 @@ static inline int rcu_preempt_depth(void)
 void rcu_init(void);
 void rcu_end_inkernel_boot(void);
 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);
 struct notifier_block;
 void rcu_idle_enter(void);
@@ -470,7 +480,14 @@ 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
 
 /**
  * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section?
@@ -997,10 +1014,14 @@ 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_assert(rcu_is_watching(),
 			   "rcu_read_lock_bh() used illegally while idle");
+#endif
 }
 
 /*
@@ -1010,10 +1031,14 @@ 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_assert(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();
 }
 
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index d2e583a6aaca..0b350893b46a 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -46,7 +46,11 @@ static inline void rcu_virt_note_context_switch(int cpu)
 	rcu_note_context_switch();
 }
 
+#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);
 
@@ -74,7 +78,11 @@ static inline void synchronize_rcu_bh_expedited(void)
 }
 
 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);
@@ -85,12 +93,10 @@ 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);
 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);
 
 void exit_rcu(void);
@@ -100,6 +106,14 @@ extern int rcu_scheduler_active __read_mostly;
 
 bool rcu_is_watching(void);
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+void rcu_bh_force_quiescent_state(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
+#endif
+
 void rcu_all_qs(void);
 
 #endif /* __LINUX_RCUTREE_H */
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 8cf7304b2867..65aecd8681c2 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -220,6 +220,7 @@ void rcu_sched_qs(void)
 	}
 }
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 void rcu_bh_qs(void)
 {
 	if (!__this_cpu_read(rcu_bh_data.passed_quiesce)) {
@@ -229,6 +230,7 @@ void rcu_bh_qs(void)
 		__this_cpu_write(rcu_bh_data.passed_quiesce, 1);
 	}
 }
+#endif
 
 static DEFINE_PER_CPU(int, rcu_sched_qs_mask);
 
@@ -404,6 +406,7 @@ unsigned long rcu_batches_completed_sched(void)
 }
 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.
  */
@@ -431,6 +434,13 @@ 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.
  */
@@ -3040,6 +3050,7 @@ void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
 }
 EXPORT_SYMBOL_GPL(call_rcu_sched);
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /*
  * Queue an RCU callback for invocation after a quicker grace period.
  */
@@ -3048,6 +3059,7 @@ void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
 	__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.
@@ -3139,6 +3151,7 @@ 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.
  *
@@ -3165,6 +3178,7 @@ 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
@@ -3677,6 +3691,7 @@ static void _rcu_barrier(struct rcu_state *rsp)
 	mutex_unlock(&rsp->barrier_mutex);
 }
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /**
  * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete.
  */
@@ -3685,6 +3700,7 @@ 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.
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 1f133350da01..1718c4fe9bce 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -227,6 +227,7 @@ 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?
  *
@@ -253,6 +254,7 @@ 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 */