[PATCH v2 tip/core/rcu 2/3] srcu: Force full grace-period ordering

["Paul E. McKenney" <paulmck@linux.vnet.ibm.com>]

If a process invokes synchronize_srcu(), is delayed just the right amount
of time, and thus does not sleep when waiting for the grace period to
complete, there is no ordering between the end of the grace period and
the code following the synchronize_srcu().  Similarly, there can be a
lack of ordering between the end of the SRCU grace period and callback
invocation.

This commit adds the necessary ordering.

Reported-by: Lance Roy <ldr709@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/rcupdate.h | 12 ++++++++++++
 kernel/rcu/srcu.c        |  5 +++++
 kernel/rcu/tree.h        | 12 ------------
 3 files changed, 17 insertions(+), 12 deletions(-)

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 01f71e1d2e94..6ade6a52d9d4 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -1161,5 +1161,17 @@ do { \
 		ftrace_dump(oops_dump_mode); \
 } while (0)
 
+/*
+ * Place this after a lock-acquisition primitive to guarantee that
+ * an UNLOCK+LOCK pair acts as a full barrier.  This guarantee applies
+ * if the UNLOCK and LOCK are executed by the same CPU or if the
+ * UNLOCK and LOCK operate on the same lock variable.
+ */
+#ifdef CONFIG_PPC
+#define smp_mb__after_unlock_lock()	smp_mb()  /* Full ordering for lock. */
+#else /* #ifdef CONFIG_PPC */
+#define smp_mb__after_unlock_lock()	do { } while (0)
+#endif /* #else #ifdef CONFIG_PPC */
+
 
 #endif /* __LINUX_RCUPDATE_H */
diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index ddabf5fbf562..f2abfbae258c 100644
--- a/kernel/rcu/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -359,6 +359,7 @@ void call_srcu(struct srcu_struct *sp, struct rcu_head *head,
 	head->next = NULL;
 	head->func = func;
 	spin_lock_irqsave(&sp->queue_lock, flags);
+	smp_mb__after_unlock_lock(); /* Caller's prior accesses before GP. */
 	rcu_batch_queue(&sp->batch_queue, head);
 	if (!sp->running) {
 		sp->running = true;
@@ -392,6 +393,7 @@ static void __synchronize_srcu(struct srcu_struct *sp, int trycount)
 	head->next = NULL;
 	head->func = wakeme_after_rcu;
 	spin_lock_irq(&sp->queue_lock);
+	smp_mb__after_unlock_lock(); /* Caller's prior accesses before GP. */
 	if (!sp->running) {
 		/* steal the processing owner */
 		sp->running = true;
@@ -413,6 +415,8 @@ static void __synchronize_srcu(struct srcu_struct *sp, int trycount)
 
 	if (!done)
 		wait_for_completion(&rcu.completion);
+
+	smp_mb(); /* Caller's later accesses after GP. */
 }
 
 /**
@@ -587,6 +591,7 @@ static void srcu_invoke_callbacks(struct srcu_struct *sp)
 	int i;
 	struct rcu_head *head;
 
+	smp_mb(); /* Callback accesses after GP. */
 	for (i = 0; i < SRCU_CALLBACK_BATCH; i++) {
 		head = rcu_batch_dequeue(&sp->batch_done);
 		if (!head)
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index fe98dd24adf8..abcc25bdcb29 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -688,18 +688,6 @@ static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll)
 #endif /* #ifdef CONFIG_RCU_TRACE */
 
 /*
- * Place this after a lock-acquisition primitive to guarantee that
- * an UNLOCK+LOCK pair act as a full barrier.  This guarantee applies
- * if the UNLOCK and LOCK are executed by the same CPU or if the
- * UNLOCK and LOCK operate on the same lock variable.
- */
-#ifdef CONFIG_PPC
-#define smp_mb__after_unlock_lock()	smp_mb()  /* Full ordering for lock. */
-#else /* #ifdef CONFIG_PPC */
-#define smp_mb__after_unlock_lock()	do { } while (0)
-#endif /* #else #ifdef CONFIG_PPC */
-
-/*
  * Wrappers for the rcu_node::lock acquire and release.
  *
  * Because the rcu_nodes form a tree, the tree traversal locking will observe
-- 
2.5.2