rds: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage

When transmitting data, call down into TCP using a single sendmsg with
MSG_SPLICE_PAGES to indicate that content should be spliced.

To make this work, the data is assembled in a bio_vec array and attached to
a BVEC-type iterator.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Santosh Shilimkar <santosh.shilimkar@oracle.com>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
cc: rds-devel@oss.oracle.com
Link: https://lore.kernel.org/r/20230623225513.2732256-6-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c
index 8c4d1d6..7d284ac 100644 (file)
--- a/net/rds/tcp_send.c
+++ b/net/rds/tcp_send.c
@@ -72,9 +72,10 @@ int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm,
 {
        struct rds_conn_path *cp = rm->m_inc.i_conn_path;
        struct rds_tcp_connection *tc = cp->cp_transport_data;
+       struct msghdr msg = {};
+       struct bio_vec bvec;
        int done = 0;
        int ret = 0;
-       int more;
 
        if (hdr_off == 0) {
                /*
@@ -111,15 +112,17 @@ int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm,
                        goto out;
        }
 
-       more = rm->data.op_nents > 1 ? (MSG_MORE | MSG_SENDPAGE_NOTLAST) : 0;
        while (sg < rm->data.op_nents) {
-               int flags = MSG_DONTWAIT | MSG_NOSIGNAL | more;
-
-               ret = tc->t_sock->ops->sendpage(tc->t_sock,
-                                               sg_page(&rm->data.op_sg[sg]),
-                                               rm->data.op_sg[sg].offset + off,
-                                               rm->data.op_sg[sg].length - off,
-                                               flags);
+               msg.msg_flags = MSG_SPLICE_PAGES | MSG_DONTWAIT | MSG_NOSIGNAL;
+               if (sg + 1 < rm->data.op_nents)
+                       msg.msg_flags |= MSG_MORE;
+
+               bvec_set_page(&bvec, sg_page(&rm->data.op_sg[sg]),
+                             rm->data.op_sg[sg].length - off,
+                             rm->data.op_sg[sg].offset + off);
+               iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1,
+                             rm->data.op_sg[sg].length - off);
+               ret = sock_sendmsg(tc->t_sock, &msg);
                rdsdebug("tcp sendpage %p:%u:%u ret %d\n", (void *)sg_page(&rm->data.op_sg[sg]),
                         rm->data.op_sg[sg].offset + off, rm->data.op_sg[sg].length - off,
                         ret);
@@ -132,8 +135,6 @@ int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm,
                        off = 0;
                        sg++;
                }
-               if (sg == rm->data.op_nents - 1)
-                       more = 0;
        }
 
 out: