mptcp: sockopt: add TCP_CONGESTION and TCP_INFO

TCP_CONGESTION is set for all subflows.
The mptcp socket gains icsk_ca_ops too so it can be used to keep the
authoritative state that should be set on new/future subflows.

TCP_INFO will return first subflow only.
The out-of-tree kernel has a MPTCP_INFO getsockopt, this could be added
later on.

Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 5cba90948a7ef7b223230334f294aa807dff737f..073e20078ed0acd943e449212d6c6e95eab18dfe 100644 (file)
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2399,6 +2399,9 @@ static int __mptcp_init_sock(struct sock *sk)
        /* re-use the csk retrans timer for MPTCP-level retrans */
        timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0);
        timer_setup(&sk->sk_timer, mptcp_timeout_timer, 0);
+
+       tcp_assign_congestion_control(sk);
+
        return 0;
 }
 
@@ -2592,6 +2595,8 @@ static void __mptcp_destroy_sock(struct sock *sk)
        WARN_ON_ONCE(msk->rmem_released);
        sk_stream_kill_queues(sk);
        xfrm_sk_free_policy(sk);
+
+       tcp_cleanup_congestion_control(sk);
        sk_refcnt_debug_release(sk);
        mptcp_dispose_initial_subflow(msk);
        sock_put(sk);

diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 390433b7f324bee8add63e0c0e42f0e618153c8a..00d941b66c1e5907906eb1efc1e7aef909b6152d 100644 (file)
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -510,6 +510,62 @@ static bool mptcp_supported_sockopt(int level, int optname)
        return false;
 }
 
+static int mptcp_setsockopt_sol_tcp_congestion(struct mptcp_sock *msk, sockptr_t optval,
+                                              unsigned int optlen)
+{
+       struct mptcp_subflow_context *subflow;
+       struct sock *sk = (struct sock *)msk;
+       char name[TCP_CA_NAME_MAX];
+       bool cap_net_admin;
+       int ret;
+
+       if (optlen < 1)
+               return -EINVAL;
+
+       ret = strncpy_from_sockptr(name, optval,
+                                  min_t(long, TCP_CA_NAME_MAX - 1, optlen));
+       if (ret < 0)
+               return -EFAULT;
+
+       name[ret] = 0;
+
+       cap_net_admin = ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN);
+
+       ret = 0;
+       lock_sock(sk);
+       sockopt_seq_inc(msk);
+       mptcp_for_each_subflow(msk, subflow) {
+               struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+               int err;
+
+               lock_sock(ssk);
+               err = tcp_set_congestion_control(ssk, name, true, cap_net_admin);
+               if (err < 0 && ret == 0)
+                       ret = err;
+               subflow->setsockopt_seq = msk->setsockopt_seq;
+               release_sock(ssk);
+       }
+
+       if (ret == 0)
+               tcp_set_congestion_control(sk, name, false, cap_net_admin);
+
+       release_sock(sk);
+       return ret;
+}
+
+static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
+                                   sockptr_t optval, unsigned int optlen)
+{
+       switch (optname) {
+       case TCP_ULP:
+               return -EOPNOTSUPP;
+       case TCP_CONGESTION:
+               return mptcp_setsockopt_sol_tcp_congestion(msk, optval, optlen);
+       }
+
+       return -EOPNOTSUPP;
+}
+
 int mptcp_setsockopt(struct sock *sk, int level, int optname,
                     sockptr_t optval, unsigned int optlen)
 {
@@ -539,6 +595,49 @@ int mptcp_setsockopt(struct sock *sk, int level, int optname,
        if (level == SOL_IPV6)
                return mptcp_setsockopt_v6(msk, optname, optval, optlen);
 
+       if (level == SOL_TCP)
+               return mptcp_setsockopt_sol_tcp(msk, optname, optval, optlen);
+
+       return -EOPNOTSUPP;
+}
+
+static int mptcp_getsockopt_first_sf_only(struct mptcp_sock *msk, int level, int optname,
+                                         char __user *optval, int __user *optlen)
+{
+       struct sock *sk = (struct sock *)msk;
+       struct socket *ssock;
+       int ret = -EINVAL;
+       struct sock *ssk;
+
+       lock_sock(sk);
+       ssk = msk->first;
+       if (ssk) {
+               ret = tcp_getsockopt(ssk, level, optname, optval, optlen);
+               goto out;
+       }
+
+       ssock = __mptcp_nmpc_socket(msk);
+       if (!ssock)
+               goto out;
+
+       ret = tcp_getsockopt(ssock->sk, level, optname, optval, optlen);
+
+out:
+       release_sock(sk);
+       return ret;
+}
+
+static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
+                                   char __user *optval, int __user *optlen)
+{
+       switch (optname) {
+       case TCP_ULP:
+       case TCP_CONGESTION:
+       case TCP_INFO:
+       case TCP_CC_INFO:
+               return mptcp_getsockopt_first_sf_only(msk, SOL_TCP, optname,
+                                                     optval, optlen);
+       }
        return -EOPNOTSUPP;
 }
 
@@ -562,6 +661,8 @@ int mptcp_getsockopt(struct sock *sk, int level, int optname,
        if (ssk)
                return tcp_getsockopt(ssk, level, optname, optval, option);
 
+       if (level == SOL_TCP)
+               return mptcp_getsockopt_sol_tcp(msk, optname, optval, option);
        return -EOPNOTSUPP;
 }