[PATCH v2] wfcqueue: functions for local append and enqueue

[Eric Wong <normalperson@yhbt.net>]

With level-triggered epoll, append/enqueue operations to the
local/locked queues increase performance by avoiding unnecessary atomic
operations and barriers.  These are necessary to avoid performance
regressions when looping through ep_send_events and appending many
items to a local queue.

Signed-off-by: Eric Wong <normalperson@yhbt.net>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Stephen Hemminger <shemminger@vyatta.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
---
 I noticed the original __wfcq_append function was not in the
 synchronization table, so I left out ___wfcq_append from the table
 as well.

 include/linux/wfcqueue.h | 59 ++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 52 insertions(+), 7 deletions(-)

diff --git a/include/linux/wfcqueue.h b/include/linux/wfcqueue.h
index 9464a0c..800b1dd 100644
--- a/include/linux/wfcqueue.h
+++ b/include/linux/wfcqueue.h
@@ -55,14 +55,16 @@
  * [4] __wfcq_splice (source queue)
  * [5] __wfcq_first
  * [6] __wfcq_next
+ * [7] __wfcq_enqueue
  *
- *     [1] [2] [3] [4] [5] [6]
- * [1]  -   -   -   -   -   -
- * [2]  -   -   -   -   -   -
- * [3]  -   -   X   X   X   X
- * [4]  -   -   X   -   X   X
- * [5]  -   -   X   X   -   -
- * [6]  -   -   X   X   -   -
+ *     [1] [2] [3] [4] [5] [6] [7]
+ * [1]  -   -   -   -   -   -   X
+ * [2]  -   -   -   -   -   -   X
+ * [3]  -   -   X   X   X   X   X
+ * [4]  -   -   X   -   X   X   X
+ * [5]  -   -   X   X   -   -   X
+ * [6]  -   -   X   X   -   -   X
+ * [7]  X   X   X   X   X   X   X
  *
  * Besides locking, mutual exclusion of dequeue, splice and iteration
  * can be ensured by performing all of those operations from a single
@@ -205,6 +207,49 @@ static inline bool wfcq_enqueue(struct wfcq_head *head,
 }
 
 /*
+ * ___wfcq_append: append one local queue to another local queue
+ *
+ * No memory barriers are issued.  Mutual exclusion is the responsibility
+ * of the caller.
+ *
+ * Returns false if the queue was empty prior to adding the node.
+ * Returns true otherwise.
+ */
+static inline bool ___wfcq_append(struct wfcq_head *head,
+		struct wfcq_tail *tail,
+		struct wfcq_node *new_head,
+		struct wfcq_node *new_tail)
+{
+	struct wfcq_node *old_tail;
+
+	old_tail = tail->p;
+	tail->p = new_tail;
+	old_tail->next = new_head;
+
+	/*
+	 * Return false if queue was empty prior to adding the node,
+	 * else return true.
+	 */
+	return old_tail != &head->node;
+}
+
+/*
+ * __wfcq_enqueue: enqueue a node into a local queue
+ *
+ * No memory barriers are issued.  Mutual exclusion is the responsibility
+ * of the caller.
+ *
+ * Returns false if the queue was empty prior to adding the node.
+ * Returns true otherwise.
+ */
+static inline bool __wfcq_enqueue(struct wfcq_head *head,
+		struct wfcq_tail *tail,
+		struct wfcq_node *new_tail)
+{
+	return ___wfcq_append(head, tail, new_tail, new_tail);
+}
+
+/*
  * ___wfcq_busy_wait: busy-wait.
  */
 static inline void ___wfcq_busy_wait(void)
-- 
1.8.2.rc3.2.geae6cf5