rcu: Add _notrace variation of rcu_dereference_raw() and hlist_for_each_entry_rcu()

As rcu_dereference_raw() under RCU debug config options can add quite a
bit of checks, and that tracing uses rcu_dereference_raw(), these checks
happen with the function tracer. The function tracer also happens to trace
these debug checks too. This added overhead can livelock the system.

Add a new interface to RCU for both rcu_dereference_raw_notrace() as well
as hlist_for_each_entry_rcu_notrace() as the hlist iterator uses the
rcu_dereference_raw() as well, and is used a bit with the function tracer.

Link: http://lkml.kernel.org/r/20130528184209.304356745@goodmis.org

Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

2 files changed, 29 insertions, 0 deletions

diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 8089e35d47ac..f4b1001a4676 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -461,6 +461,26 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev,
                         &(pos)->member)), typeof(*(pos)), member))
 
 /**
+ * hlist_for_each_entry_rcu_notrace - iterate over rcu list of given type (for tracing)
+ * @pos:        the type * to use as a loop cursor.
+ * @head:       the head for your list.
+ * @member:     the name of the hlist_node within the struct.
+ *
+ * This list-traversal primitive may safely run concurrently with
+ * the _rcu list-mutation primitives such as hlist_add_head_rcu()
+ * as long as the traversal is guarded by rcu_read_lock().
+ *
+ * This is the same as hlist_for_each_entry_rcu() except that it does
+ * not do any RCU debugging or tracing.
+ */
+#define hlist_for_each_entry_rcu_notrace(pos, head, member)                     \
+        for (pos = hlist_entry_safe (rcu_dereference_raw_notrace(hlist_first_rcu(head)),\
+                        typeof(*(pos)), member);                        \
+                pos;                                                    \
+                pos = hlist_entry_safe(rcu_dereference_raw_notrace(hlist_next_rcu(\
+                        &(pos)->member)), typeof(*(pos)), member))
+
+/**
  * hlist_for_each_entry_rcu_bh - iterate over rcu list of given type
  * @pos:        the type * to use as a loop cursor.
  * @head:       the head for your list.
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 4ccd68e49b00..ddcc7826d907 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -640,6 +640,15 @@ static inline void rcu_preempt_sleep_check(void)
 
 #define rcu_dereference_raw(p) rcu_dereference_check(p, 1) /*@@@ needed? @@@*/
 
+/*
+ * The tracing infrastructure traces RCU (we want that), but unfortunately
+ * some of the RCU checks causes tracing to lock up the system.
+ *
+ * The tracing version of rcu_dereference_raw() must not call
+ * rcu_read_lock_held().
+ */
+#define rcu_dereference_raw_notrace(p) __rcu_dereference_check((p), 1, __rcu)
+
 /**
  * rcu_access_index() - fetch RCU index with no dereferencing
  * @p: The index to read