Use sendmsg() and MSG_SPLICE_PAGES rather than sendpage in ceph when
transmitting data. For the moment, this can only transmit one page at a
time because of the architecture of net/ceph/, but if
write_partial_message_data() can be given a bvec[] at a time by the
iteration code, this would allow pages to be sent in a batch.
Signed-off-by: David Howells <[email protected]>
cc: Ilya Dryomov <[email protected]>
cc: Xiubo Li <[email protected]>
cc: Jeff Layton <[email protected]>
cc: "David S. Miller" <[email protected]>
cc: Eric Dumazet <[email protected]>
cc: Jakub Kicinski <[email protected]>
cc: Paolo Abeni <[email protected]>
cc: Jens Axboe <[email protected]>
cc: Matthew Wilcox <[email protected]>
cc: [email protected]
cc: [email protected]
---
net/ceph/messenger_v2.c | 91 +++++++++--------------------------------
1 file changed, 19 insertions(+), 72 deletions(-)
diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index 301a991dc6a6..87ac97073e75 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -117,91 +117,38 @@ static int ceph_tcp_recv(struct ceph_connection *con)
return ret;
}
-static int do_sendmsg(struct socket *sock, struct iov_iter *it)
-{
- struct msghdr msg = { .msg_flags = CEPH_MSG_FLAGS };
- int ret;
-
- msg.msg_iter = *it;
- while (iov_iter_count(it)) {
- ret = sock_sendmsg(sock, &msg);
- if (ret <= 0) {
- if (ret == -EAGAIN)
- ret = 0;
- return ret;
- }
-
- iov_iter_advance(it, ret);
- }
-
- WARN_ON(msg_data_left(&msg));
- return 1;
-}
-
-static int do_try_sendpage(struct socket *sock, struct iov_iter *it)
-{
- struct msghdr msg = { .msg_flags = CEPH_MSG_FLAGS };
- struct bio_vec bv;
- int ret;
-
- if (WARN_ON(!iov_iter_is_bvec(it)))
- return -EINVAL;
-
- while (iov_iter_count(it)) {
- /* iov_iter_iovec() for ITER_BVEC */
- bvec_set_page(&bv, it->bvec->bv_page,
- min(iov_iter_count(it),
- it->bvec->bv_len - it->iov_offset),
- it->bvec->bv_offset + it->iov_offset);
-
- /*
- * sendpage cannot properly handle pages with
- * page_count == 0, we need to fall back to sendmsg if
- * that's the case.
- *
- * Same goes for slab pages: skb_can_coalesce() allows
- * coalescing neighboring slab objects into a single frag
- * which triggers one of hardened usercopy checks.
- */
- if (sendpage_ok(bv.bv_page)) {
- ret = sock->ops->sendpage(sock, bv.bv_page,
- bv.bv_offset, bv.bv_len,
- CEPH_MSG_FLAGS);
- } else {
- iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bv, 1, bv.bv_len);
- ret = sock_sendmsg(sock, &msg);
- }
- if (ret <= 0) {
- if (ret == -EAGAIN)
- ret = 0;
- return ret;
- }
-
- iov_iter_advance(it, ret);
- }
-
- return 1;
-}
-
/*
* Write as much as possible. The socket is expected to be corked,
- * so we don't bother with MSG_MORE/MSG_SENDPAGE_NOTLAST here.
+ * so we don't bother with MSG_MORE here.
*
* Return:
- * 1 - done, nothing (else) to write
+ * >0 - done, nothing (else) to write
* 0 - socket is full, need to wait
* <0 - error
*/
static int ceph_tcp_send(struct ceph_connection *con)
{
+ struct msghdr msg = {
+ .msg_iter = con->v2.out_iter,
+ .msg_flags = CEPH_MSG_FLAGS,
+ };
int ret;
+ if (WARN_ON(!iov_iter_is_bvec(&con->v2.out_iter)))
+ return -EINVAL;
+
+ if (con->v2.out_iter_sendpage)
+ msg.msg_flags |= MSG_SPLICE_PAGES;
+
dout("%s con %p have %zu try_sendpage %d\n", __func__, con,
iov_iter_count(&con->v2.out_iter), con->v2.out_iter_sendpage);
- if (con->v2.out_iter_sendpage)
- ret = do_try_sendpage(con->sock, &con->v2.out_iter);
- else
- ret = do_sendmsg(con->sock, &con->v2.out_iter);
+
+ ret = sock_sendmsg(con->sock, &msg);
+ if (ret > 0)
+ iov_iter_advance(&con->v2.out_iter, ret);
+ else if (ret == -EAGAIN)
+ ret = 0;
+
dout("%s con %p ret %d left %zu\n", __func__, con, ret,
iov_iter_count(&con->v2.out_iter));
return ret;