[PATCH net-next v2 04/13] mptcp: basic sndbuf autotuning

[Paolo Abeni]

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 <pab...@redhat.com>
---
 net/mptcp/protocol.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 95573c6f7762..4f12a8ce0ddd 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -856,7 +856,8 @@ 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;
@@ -865,6 +866,7 @@ 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;
 
@@ -877,6 +879,7 @@ 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;
@@ -903,6 +906,7 @@ 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;
 
@@ -929,7 +933,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr 
*msg, size_t len)
        }
 
        __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)) {
@@ -953,13 +957,18 @@ 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);
@@ -1547,7 +1556,7 @@ 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;
 }
-- 
2.26.2