svcrdma: Relieve contention on sc_send_lock.

/proc/lock_stat indicates the the sc_send_lock is heavily
contended when the server is under load from a single client.

To address this, convert the send_ctxt free list to an llist.
Returning an item to the send_ctxt cache is now waitless, which
reduces the instruction path length in the single-threaded Send
handler (svc_rdma_wc_send).

The goal is to enable the ib_comp_wq worker to handle a higher
RPC/RDMA Send completion rate given the same CPU resources. This
change reduces CPU utilization of Send completion by 2-3% on my
server.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-By: Tom Talpey <tom@talpey.com>

1 files changed, 2 insertions, 2 deletions

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 57c60ffe76dd..5f8d5af6556c 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -90,7 +90,7 @@ struct svcxprt_rdma {
 	struct ib_pd         *sc_pd;
 
 	spinlock_t	     sc_send_lock;
-	struct list_head     sc_send_ctxts;
+	struct llist_head    sc_send_ctxts;
 	spinlock_t	     sc_rw_ctxt_lock;
 	struct list_head     sc_rw_ctxts;
 
@@ -150,7 +150,7 @@ struct svc_rdma_recv_ctxt {
 };
 
 struct svc_rdma_send_ctxt {
-	struct list_head	sc_list;
+	struct llist_node	sc_node;
 	struct rpc_rdma_cid	sc_cid;
 
 	struct ib_send_wr	sc_send_wr;