[v3,48/55] sunrpc: Use sendmsg(MSG_SPLICE_PAGES) rather then sendpage

Commit Message

David Howells March 31, 2023, 4:09 p.m. UTC

When transmitting data, call down into TCP using sendmsg with
MSG_SPLICE_PAGES to indicate that content should be spliced rather than
performing sendpage calls to transmit header, data pages and trailer.

Signed-off-by: David Howells <[e-mail]>
Acked-by: Chuck Lever <[e-mail]>
cc: Trond Myklebust <[e-mail]>
cc: Anna Schumaker <[e-mail]>
cc: Jeff Layton <[e-mail]>
cc: "David S. Miller" <[e-mail]>
cc: Eric Dumazet <[e-mail]>
cc: Jakub Kicinski <[e-mail]>
cc: Paolo Abeni <[e-mail]>
cc: Jens Axboe <[e-mail]>
cc: Matthew Wilcox <[e-mail]>
cc: [e-mail]
cc: [e-mail]
---
 include/linux/sunrpc/svc.h | 11 +++++------
 net/sunrpc/svcsock.c       | 38 ++++++++++++--------------------------
 2 files changed, 17 insertions(+), 32 deletions(-)

Patch

diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 877891536c2f..456ae554aa11 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -161,16 +161,15 @@  static inline bool svc_put_not_last(struct svc_serv *serv)
 extern u32 svc_max_payload(const struct svc_rqst *rqstp);
 
 /*
- * RPC Requsts and replies are stored in one or more pages.
+ * RPC Requests and replies are stored in one or more pages.
  * We maintain an array of pages for each server thread.
  * Requests are copied into these pages as they arrive.  Remaining
  * pages are available to write the reply into.
  *
- * Pages are sent using ->sendpage so each server thread needs to
- * allocate more to replace those used in sending.  To help keep track
- * of these pages we have a receive list where all pages initialy live,
- * and a send list where pages are moved to when there are to be part
- * of a reply.
+ * Pages are sent using ->sendmsg with MSG_SPLICE_PAGES so each server thread
+ * needs to allocate more to replace those used in sending.  To help keep track
+ * of these pages we have a receive list where all pages initialy live, and a
+ * send list where pages are moved to when there are to be part of a reply.
  *
  * We use xdr_buf for holding responses as it fits well with NFS
  * read responses (that have a header, and some data pages, and possibly
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 03a4f5615086..3a015abac5bd 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1063,13 +1063,14 @@  static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
 static int svc_tcp_send_kvec(struct socket *sock, const struct kvec *vec,
 			      int flags)
 {
-	return kernel_sendpage(sock, virt_to_page(vec->iov_base),
-			       offset_in_page(vec->iov_base),
-			       vec->iov_len, flags);
+	struct msghdr msg = { .msg_flags = MSG_SPLICE_PAGES | flags, };
+
+	iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, vec, 1, vec->iov_len);
+	return sock_sendmsg(sock, &msg);
 }
 
 /*
- * kernel_sendpage() is used exclusively to reduce the number of
+ * MSG_SPLICE_PAGES is used exclusively to reduce the number of
  * copy operations in this path. Therefore the caller must ensure
  * that the pages backing @xdr are unchanging.
  *
@@ -1109,28 +1110,13 @@  static int svc_tcp_sendmsg(struct socket *sock, struct xdr_buf *xdr,
 	if (ret != head->iov_len)
 		goto out;
 
-	if (xdr->page_len) {
-		unsigned int offset, len, remaining;
-		struct bio_vec *bvec;
-
-		bvec = xdr->bvec + (xdr->page_base >> PAGE_SHIFT);
-		offset = offset_in_page(xdr->page_base);
-		remaining = xdr->page_len;
-		while (remaining > 0) {
-			len = min(remaining, bvec->bv_len - offset);
-			ret = kernel_sendpage(sock, bvec->bv_page,
-					      bvec->bv_offset + offset,
-					      len, 0);
-			if (ret < 0)
-				return ret;
-			*sentp += ret;
-			if (ret != len)
-				goto out;
-			remaining -= len;
-			offset = 0;
-			bvec++;
-		}
-	}
+	msg.msg_flags = MSG_SPLICE_PAGES;
+	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, xdr->bvec,
+		      xdr_buf_pagecount(xdr), xdr->page_len);
+	ret = sock_sendmsg(sock, &msg);
+	if (ret < 0)
+		return ret;
+	*sentp += ret;
 
 	if (tail->iov_len) {
 		ret = svc_tcp_send_kvec(sock, tail, 0);