From: Paolo Abeni <pab...@redhat.com>
This makes mptcp sendmsg() behaviour more consistent and
improves xmit performances.
Signed-off-by: Paolo Abeni <pab...@redhat.com>
---
net/mptcp/protocol.c | 126 ++++++++++++++++++++++++-------------------
1 file changed, 71 insertions(+), 55 deletions(-)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index da983ea4fb5e..758369256f9b 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -58,71 +58,37 @@ static struct sock *mptcp_subflow_get_ref(const struct
mptcp_sock *msk)
return NULL;
}
-static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
+static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
+ struct msghdr *msg, long *timeo)
{
int mss_now = 0, size_goal = 0, ret = 0;
struct mptcp_sock *msk = mptcp_sk(sk);
- struct socket *ssock;
- struct sock *ssk;
struct mptcp_ext *mpext = NULL;
struct page_frag *pfrag;
struct sk_buff *skb;
size_t psize;
- int poffset;
- long timeo;
-
- lock_sock(sk);
- ssock = __mptcp_fallback_get_ref(msk);
- if (ssock) {
- release_sock(sk);
- pr_debug("fallback passthrough");
- ret = sock_sendmsg(ssock, msg);
- sock_put(ssock->sk);
- return ret;
- }
-
- ssk = mptcp_subflow_get_ref(msk);
- if (!ssk) {
- release_sock(sk);
- return -ENOTCONN;
- }
-
- if (!msg_data_left(msg)) {
- pr_debug("empty send");
- ret = sock_sendmsg(ssk->sk_socket, msg);
- goto put_out;
- }
-
- if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL)) {
- ret = -ENOTSUPP;
- goto put_out;
- }
-
- lock_sock(ssk);
- timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
/* use the mptcp page cache so that we can easily move the data
* from one substream to another, but do per subflow memory accounting
*/
pfrag = sk_page_frag(sk);
while (!sk_page_frag_refill(ssk, pfrag)) {
- ret = sk_stream_wait_memory(ssk, &timeo);
+ ret = sk_stream_wait_memory(ssk, timeo);
if (ret)
- goto put_out;
+ return ret;
}
- /* Copy to page */
- poffset = pfrag->offset;
+ /* compute copy limit */
+ mss_now = tcp_send_mss(ssk, &size_goal, msg->msg_flags);
+ psize = min_t(int, pfrag->size - pfrag->offset, size_goal);
+
pr_debug("left=%zu", msg_data_left(msg));
- psize = copy_page_from_iter(pfrag->page, poffset,
- min_t(size_t, msg_data_left(msg),
- pfrag->size - poffset),
+ psize = copy_page_from_iter(pfrag->page, pfrag->offset,
+ min_t(size_t, msg_data_left(msg), psize),
&msg->msg_iter);
pr_debug("left=%zu", msg_data_left(msg));
- if (!psize) {
- ret = -EINVAL;
- goto put_out;
- }
+ if (!psize)
+ return -EINVAL;
/* Mark the end of the previous write so the beginning of the
* next write (with its own mptcp skb extension data) is not
@@ -132,20 +98,15 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr
*msg, size_t len)
if (skb)
TCP_SKB_CB(skb)->eor = 1;
- mss_now = tcp_send_mss(ssk, &size_goal, msg->msg_flags);
- psize = min_t(int, size_goal, psize);
- ret = do_tcp_sendpages(ssk, pfrag->page, poffset, psize,
+ ret = do_tcp_sendpages(ssk, pfrag->page, pfrag->offset, psize,
msg->msg_flags | MSG_SENDPAGE_NOTLAST);
if (ret <= 0)
- goto put_out;
-
- if (skb == tcp_write_queue_tail(ssk))
- pr_err("no new skb %p/%p", sk, ssk);
+ return ret;
+ if (unlikely(ret < psize))
+ iov_iter_revert(&msg->msg_iter, psize - ret);
skb = tcp_write_queue_tail(ssk);
-
mpext = skb_ext_add(skb, SKB_EXT_MPTCP);
-
if (mpext) {
memset(mpext, 0, sizeof(*mpext));
mpext->data_seq = msk->write_seq;
@@ -165,6 +126,61 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr
*msg, size_t len)
mptcp_subflow_ctx(ssk)->rel_write_seq += ret;
tcp_push(ssk, msg->msg_flags, mss_now, tcp_sk(ssk)->nonagle, size_goal);
+ return ret;
+}
+
+static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ struct socket *ssock;
+ size_t copied = 0;
+ struct sock *ssk;
+ int ret = 0;
+ long timeo;
+
+ lock_sock(sk);
+ ssock = __mptcp_fallback_get_ref(msk);
+ if (ssock) {
+ release_sock(sk);
+ pr_debug("fallback passthrough");
+ ret = sock_sendmsg(ssock, msg);
+ sock_put(ssock->sk);
+ return ret;
+ }
+
+ ssk = mptcp_subflow_get_ref(msk);
+ if (!ssk) {
+ release_sock(sk);
+ return -ENOTCONN;
+ }
+
+ if (!msg_data_left(msg)) {
+ pr_debug("empty send");
+ ret = sock_sendmsg(ssk->sk_socket, msg);
+ goto put_out;
+ }
+
+ pr_debug("conn_list->subflow=%p", ssk);
+
+ if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL)) {
+ ret = -ENOTSUPP;
+ goto put_out;
+ }
+
+ lock_sock(ssk);
+ timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
+ while (msg_data_left(msg)) {
+ ret = mptcp_sendmsg_frag(sk, ssk, msg, &timeo);
+ if (ret < 0)
+ break;
+
+ copied += ret;
+ }
+
+ if (copied > 0)
+ ret = copied;
+
+ release_sock(ssk);
put_out:
release_sock(sk);
--
2.23.0
