leandrof/linux
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

net: mptcp: improve fallback to TCP

Browse Source 
Keep using MPTCP sockets and a use "dummy mapping" in case of fallback
to regular TCP. When fallback is triggered, skip addition of the MPTCP
option on send.

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/11
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/22
Co-developed-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Davide Caratti
2020-06-29 22:26:20 +02:00
committed by David S. Miller
parent e11703330a
commit e1ff9e82e2
4 changed files with 98 additions and 89 deletions
Download Patch File Download Diff File Expand all files Collapse all files

98
net/mptcp/protocol.c
View File

@@ -52,11 +52,6 @@ static struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk)
return msk->subflow;
}
static bool __mptcp_needs_tcp_fallback(const struct mptcp_sock *msk)
{
return msk->first && !sk_is_mptcp(msk->first);
}
static struct socket *mptcp_is_tcpsk(struct sock *sk)
{
struct socket *sock = sk->sk_socket;
@@ -94,7 +89,7 @@ static struct socket *__mptcp_tcp_fallback(struct mptcp_sock *msk)
if (unlikely(sock))
return sock;
if (likely(!__mptcp_needs_tcp_fallback(msk)))
if (likely(!__mptcp_check_fallback(msk)))
return NULL;
return msk->subflow;
@@ -133,6 +128,11 @@ static struct socket *__mptcp_socket_create(struct mptcp_sock *msk, int state)
list_add(&subflow->node, &msk->conn_list);
subflow->request_mptcp = 1;
/* accept() will wait on first subflow sk_wq, and we always wakes up
* via msk->sk_socket
*/
RCU_INIT_POINTER(msk->first->sk_wq, &sk->sk_socket->wq);
set_state:
if (state != MPTCP_SAME_STATE)
inet_sk_state_store(sk, state);
@@ -229,6 +229,15 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
if (!skb)
break;
if (__mptcp_check_fallback(msk)) {
/* if we are running under the workqueue, TCP could have
* collapsed skbs between dummy map creation and now
* be sure to adjust the size
*/
map_remaining = skb->len;
subflow->map_data_len = skb->len;
}
offset = seq - TCP_SKB_CB(skb)->seq;
fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
if (fin) {
@@ -466,8 +475,15 @@ static void mptcp_clean_una(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
struct mptcp_data_frag *dtmp, *dfrag;
u64 snd_una = atomic64_read(&msk->snd_una);
bool cleaned = false;
u64 snd_una;
/* on fallback we just need to ignore snd_una, as this is really
* plain TCP
*/
if (__mptcp_check_fallback(msk))
atomic64_set(&msk->snd_una, msk->write_seq);
snd_una = atomic64_read(&msk->snd_una);
list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list) {
if (after64(dfrag->data_seq + dfrag->data_len, snd_una))
@@ -740,7 +756,6 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
int mss_now = 0, size_goal = 0, ret = 0;
struct mptcp_sock *msk = mptcp_sk(sk);
struct page_frag *pfrag;
struct socket *ssock;
size_t copied = 0;
struct sock *ssk;
bool tx_ok;
@@ -759,15 +774,6 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
goto out;
}
fallback:
ssock = __mptcp_tcp_fallback(msk);
if (unlikely(ssock)) {
release_sock(sk);
pr_debug("fallback passthrough");
ret = sock_sendmsg(ssock, msg);
return ret >= 0 ? ret + copied : (copied ? copied : ret);
}
pfrag = sk_page_frag(sk);
restart:
mptcp_clean_una(sk);
@@ -819,17 +825,6 @@ wait_for_sndbuf:
}
break;
}
if (ret == 0 && unlikely(__mptcp_needs_tcp_fallback(msk))) {
/* Can happen for passive sockets:
* 3WHS negotiated MPTCP, but first packet after is
* plain TCP (e.g. due to middlebox filtering unknown
* options).
*
* Fall back to TCP.
*/
release_sock(ssk);
goto fallback;
}
copied += ret;
@@ -972,7 +967,6 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
int nonblock, int flags, int *addr_len)
{
struct mptcp_sock *msk = mptcp_sk(sk);
struct socket *ssock;
int copied = 0;
int target;
long timeo;
@@ -981,16 +975,6 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
return -EOPNOTSUPP;
lock_sock(sk);
ssock = __mptcp_tcp_fallback(msk);
if (unlikely(ssock)) {
fallback:
release_sock(sk);
pr_debug("fallback-read subflow=%p",
mptcp_subflow_ctx(ssock->sk));
copied = sock_recvmsg(ssock, msg, flags);
return copied;
}
timeo = sock_rcvtimeo(sk, nonblock);
len = min_t(size_t, len, INT_MAX);
@@ -1056,9 +1040,6 @@ fallback:
pr_debug("block timeout %ld", timeo);
mptcp_wait_data(sk, &timeo);
ssock = __mptcp_tcp_fallback(msk);
if (unlikely(ssock))
goto fallback;
}
if (skb_queue_empty(&sk->sk_receive_queue)) {
@@ -1335,8 +1316,6 @@ static void mptcp_subflow_shutdown(struct sock *ssk, int how,
break;
}
/* Wake up anyone sleeping in poll. */
ssk->sk_state_change(ssk);
release_sock(ssk);
}
@@ -1660,12 +1639,6 @@ void mptcp_finish_connect(struct sock *ssk)
sk = subflow->conn;
msk = mptcp_sk(sk);
if (!subflow->mp_capable) {
MPTCP_INC_STATS(sock_net(sk),
MPTCP_MIB_MPCAPABLEACTIVEFALLBACK);
return;
}
pr_debug("msk=%p, token=%u", sk, subflow->token);
mptcp_crypto_key_sha(subflow->remote_key, NULL, &ack_seq);
@@ -1971,23 +1944,10 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
{
struct sock *sk = sock->sk;
struct mptcp_sock *msk;
struct socket *ssock;
__poll_t mask = 0;
msk = mptcp_sk(sk);
lock_sock(sk);
ssock = __mptcp_tcp_fallback(msk);
if (!ssock)
ssock = __mptcp_nmpc_socket(msk);
if (ssock) {
mask = ssock->ops->poll(file, ssock, wait);
release_sock(sk);
return mask;
}
release_sock(sk);
sock_poll_wait(file, sock, wait);
lock_sock(sk);
if (test_bit(MPTCP_DATA_READY, &msk->flags))
mask = EPOLLIN | EPOLLRDNORM;
@@ -1997,8 +1957,6 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
if (sk->sk_shutdown & RCV_SHUTDOWN)
mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
release_sock(sk);
return mask;
}
@@ -2006,18 +1964,11 @@ static int mptcp_shutdown(struct socket *sock, int how)
{
struct mptcp_sock *msk = mptcp_sk(sock->sk);
struct mptcp_subflow_context *subflow;
struct socket *ssock;
int ret = 0;
pr_debug("sk=%p, how=%d", msk, how);
lock_sock(sock->sk);
ssock = __mptcp_tcp_fallback(msk);
if (ssock) {
release_sock(sock->sk);
return inet_shutdown(ssock, how);
}
if (how == SHUT_WR || how == SHUT_RDWR)
inet_sk_state_store(sock->sk, TCP_FIN_WAIT1);
@@ -2043,6 +1994,9 @@ static int mptcp_shutdown(struct socket *sock, int how)
mptcp_subflow_shutdown(tcp_sk, how, 1, msk->write_seq);
}
/* Wake up anyone sleeping in poll. */
sock->sk->sk_state_change(sock->sk);
out_unlock:
release_sock(sock->sk);