From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 7 Jul 2021 18:57:28 +0000 (-0400)
Subject: svcrdma: Fewer calls to wake_up() in Send completion handler
X-Git-Tag: v5.15~119^2~32
X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=6c8c84f525100a1cade5698320b4abe43062e159;p=platform%2Fkernel%2Flinux-starfive.git

svcrdma: Fewer calls to wake_up() in Send completion handler

Because wake_up() takes an IRQ-safe lock, it can be expensive,
especially to call inside of a single-threaded completion handler.
What's more, the Send wait queue almost never has waiters, so
most of the time, this is an expensive no-op.

As always, the goal is to reduce the average overhead of each
completion, because a transport's completion handlers are single-
threaded on one CPU core. This change reduces CPU utilization of
the Send completion thread by 2-3% on my server.

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

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 3184465..57c60ff 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -207,6 +207,7 @@ extern void svc_rdma_send_error_msg(struct svcxprt_rdma *rdma,
 				    struct svc_rdma_send_ctxt *sctxt,
 				    struct svc_rdma_recv_ctxt *rctxt,
 				    int status);
+extern void svc_rdma_wake_send_waiters(struct svcxprt_rdma *rdma, int avail);
 extern int svc_rdma_sendto(struct svc_rqst *);
 extern int svc_rdma_result_payload(struct svc_rqst *rqstp, unsigned int offset,
 				   unsigned int length);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index 1e65144..3d1b119 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -248,8 +248,7 @@ static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc)
 
 	trace_svcrdma_wc_write(wc, &cc->cc_cid);
 
-	atomic_add(cc->cc_sqecount, &rdma->sc_sq_avail);
-	wake_up(&rdma->sc_send_wait);
+	svc_rdma_wake_send_waiters(rdma, cc->cc_sqecount);
 
 	if (unlikely(wc->status != IB_WC_SUCCESS))
 		svc_xprt_deferred_close(&rdma->sc_xprt);
@@ -304,9 +303,7 @@ static void svc_rdma_wc_read_done(struct ib_cq *cq, struct ib_wc *wc)
 
 	trace_svcrdma_wc_read(wc, &cc->cc_cid);
 
-	atomic_add(cc->cc_sqecount, &rdma->sc_sq_avail);
-	wake_up(&rdma->sc_send_wait);
-
+	svc_rdma_wake_send_waiters(rdma, cc->cc_sqecount);
 	cc->cc_status = wc->status;
 	complete(&cc->cc_done);
 	return;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index d6bbafb..fba2ee4 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -259,6 +259,20 @@ void svc_rdma_send_ctxt_put(struct svcxprt_rdma *rdma,
 }
 
 /**
+ * svc_rdma_wake_send_waiters - manage Send Queue accounting
+ * @rdma: controlling transport
+ * @avail: Number of additional SQEs that are now available
+ *
+ */
+void svc_rdma_wake_send_waiters(struct svcxprt_rdma *rdma, int avail)
+{
+	atomic_add(avail, &rdma->sc_sq_avail);
+	smp_mb__after_atomic();
+	if (unlikely(waitqueue_active(&rdma->sc_send_wait)))
+		wake_up(&rdma->sc_send_wait);
+}
+
+/**
  * svc_rdma_wc_send - Invoked by RDMA provider for each polled Send WC
  * @cq: Completion Queue context
  * @wc: Work Completion object
@@ -275,11 +289,9 @@ static void svc_rdma_wc_send(struct ib_cq *cq, struct ib_wc *wc)
 
 	trace_svcrdma_wc_send(wc, &ctxt->sc_cid);
 
+	svc_rdma_wake_send_waiters(rdma, 1);
 	complete(&ctxt->sc_done);
 
-	atomic_inc(&rdma->sc_sq_avail);
-	wake_up(&rdma->sc_send_wait);
-
 	if (unlikely(wc->status != IB_WC_SUCCESS))
 		svc_xprt_deferred_close(&rdma->sc_xprt);
 }