diff mbox series

[04/13] mptcp: basic sndbuf autotuning

Message ID bf9d95f3ed58d0ce68c507fe3808f5120e12c62d.1596649926.git.pabeni@redhat.com
State Accepted, archived
Delegated to: Matthieu Baerts
Headers show
Series mptcp: multiple xmit substreams support | expand

Commit Message

Paolo Abeni Aug. 5, 2020, 5:57 p.m. UTC 
Let the msk sendbuf track the size of the larger subflow's
send window, so that we ensure mptcp_sendmsg() does not
exceed MPTCP-level send window.

The update is performed just before try to send any data.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
RFC -> v1:
 - SOCK_RCVBUF_LOCK -> SOCK_SNDBUF_LOCK
 - track snd_wnd instead of subflows sndbuf
---
 net/mptcp/protocol.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)
diff mbox series

Patch

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index e74a27581c73..9d7b75b4611d 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -854,7 +854,8 @@  static void mptcp_nospace(struct mptcp_sock *msk)
 	}
 }
 
-static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
+static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk,
+					   u32 *sndbuf)
 {
 	struct mptcp_subflow_context *subflow;
 	struct sock *sk = (struct sock *)msk;
@@ -862,6 +863,7 @@  static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 
 	sock_owned_by_me(sk);
 
+	*sndbuf = 0;
 	if (!mptcp_ext_cache_refill(msk))
 		return NULL;
 
@@ -873,6 +875,7 @@  static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 			return NULL;
 		}
 
+		*sndbuf = max(tcp_sk(ssk)->snd_wnd, *sndbuf);
 		if (subflow->backup) {
 			if (!backup)
 				backup = ssk;
@@ -899,6 +902,7 @@  static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	struct page_frag *pfrag;
 	size_t copied = 0;
 	struct sock *ssk;
+	u32 sndbuf;
 	bool tx_ok;
 	long timeo;
 
@@ -926,7 +930,7 @@  static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 wait_for_sndbuf:
 	__mptcp_flush_join_list(msk);
-	ssk = mptcp_subflow_get_send(msk);
+	ssk = mptcp_subflow_get_send(msk, &sndbuf);
 	while (!sk_stream_memory_free(sk) ||
 	       !ssk ||
 	       !mptcp_page_frag_refill(ssk, pfrag)) {
@@ -950,13 +954,18 @@  static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 		mptcp_clean_una(sk);
 
-		ssk = mptcp_subflow_get_send(msk);
+		ssk = mptcp_subflow_get_send(msk, &sndbuf);
 		if (list_empty(&msk->conn_list)) {
 			ret = -ENOTCONN;
 			goto out;
 		}
 	}
 
+	/* do auto tuning */
+	if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK) &&
+	    sndbuf > READ_ONCE(sk->sk_sndbuf))
+		WRITE_ONCE(sk->sk_sndbuf, sndbuf);
+
 	pr_debug("conn_list->subflow=%p", ssk);
 
 	lock_sock(ssk);
@@ -1546,7 +1555,7 @@  static int mptcp_init_sock(struct sock *sk)
 
 	sk_sockets_allocated_inc(sk);
 	sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1];
-	sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[2];
+	sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1];
 
 	return 0;
 }