rcu: Make ksoftirqd do RCU quiescent states

Implementing RCU-bh in terms of RCU-preempt makes the system vulnerable
to network-based denial-of-service attacks.  This patch therefore
makes __do_softirq() invoke rcu_bh_qs(), but only when __do_softirq()
is running in ksoftirqd context.  A wrapper layer in interposed so that
other calls to __do_softirq() avoid invoking rcu_bh_qs().  The underlying
function __do_softirq_common() does the actual work.

The reason that rcu_bh_qs() is bad in these non-ksoftirqd contexts is
that there might be a local_bh_enable() inside an RCU-preempt read-side
critical section.  This local_bh_enable() can invoke __do_softirq()
directly, so if __do_softirq() were to invoke rcu_bh_qs() (which just
calls rcu_preempt_qs() in the PREEMPT_RT_FULL case), there would be
an illegal RCU-preempt quiescent state in the middle of an RCU-preempt
read-side critical section.  Therefore, quiescent states can only happen
in cases where __do_softirq() is invoked directly from ksoftirqd.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/20111005184518.GA21601@linux.vnet.ibm.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

3 files changed, 15 insertions, 6 deletions

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index ddacc7e629111..c2f5f955163d7 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -334,11 +334,7 @@ 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;
 int rcu_cpu_notify(struct notifier_block *self,
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index d52db2c442e3e..eadbeb631f55d 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -266,7 +266,14 @@ void rcu_sched_qs(void)
 	}
 }
 
-#ifndef CONFIG_PREEMPT_RT_FULL
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void rcu_preempt_qs(void);
+
+void rcu_bh_qs(void)
+{
+	rcu_preempt_qs();
+}
+#else
 void rcu_bh_qs(void)
 {
 	if (__this_cpu_read(rcu_bh_data.cpu_no_qs.s)) {
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index ccac43b7170c8..13ce51b08de0b 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -28,6 +28,7 @@
 #include <linux/gfp.h>
 #include <linux/oom.h>
 #include <linux/smpboot.h>
+#include <linux/jiffies.h>
 #include "../time/tick-internal.h"
 
 #ifdef CONFIG_RCU_BOOST
@@ -1346,7 +1347,7 @@ static void rcu_prepare_kthreads(int cpu)
 
 #endif /* #else #ifdef CONFIG_RCU_BOOST */
 
-#if !defined(CONFIG_RCU_FAST_NO_HZ)
+#if !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL)
 
 /*
  * Check to see if any future RCU-related work will need to be done
@@ -1363,7 +1364,9 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt)
 	return IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL)
 	       ? 0 : rcu_cpu_has_callbacks(NULL);
 }
+#endif /* !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL) */
 
+#if !defined(CONFIG_RCU_FAST_NO_HZ)
 /*
  * Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up
  * after it.
@@ -1459,6 +1462,8 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void)
 	return cbs_ready;
 }
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+
 /*
  * Allow the CPU to enter dyntick-idle mode unless it has callbacks ready
  * to invoke.  If the CPU has callbacks, try to advance them.  Tell the
@@ -1504,6 +1509,7 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt)
 	*nextevt = basemono + dj * TICK_NSEC;
 	return 0;
 }
+#endif /* #ifndef CONFIG_PREEMPT_RT_FULL */
 
 /*
  * Prepare a CPU for idle from an RCU perspective.  The first major task