mptcp: add TCP_INQ cmsg support

Support the TCP_INQ setsockopt.

This is a boolean that tells recvmsg path to include the remaining
in-sequence bytes in the cmsg data.

v2: do not use CB(skb)->offset, increment map_seq instead (Paolo Abeni)
v3: adjust CB(skb)->map_seq when taking skb from ofo queue (Paolo Abeni)

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/224
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index b100048..ffc8068 100644 (file)
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -46,6 +46,7 @@ struct mptcp_skb_cb {
 
 enum {
        MPTCP_CMSG_TS = BIT(0),
+       MPTCP_CMSG_INQ = BIT(1),
 };
 
 static struct percpu_counter mptcp_sockets_allocated ____cacheline_aligned_in_smp;
@@ -738,6 +739,7 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk)
                                 MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq,
                                 delta);
                        MPTCP_SKB_CB(skb)->offset += delta;
+                       MPTCP_SKB_CB(skb)->map_seq += delta;
                        __skb_queue_tail(&sk->sk_receive_queue, skb);
                }
                msk->ack_seq = end_seq;
@@ -1784,8 +1786,10 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
                copied += count;
 
                if (count < data_len) {
-                       if (!(flags & MSG_PEEK))
+                       if (!(flags & MSG_PEEK)) {
                                MPTCP_SKB_CB(skb)->offset += count;
+                               MPTCP_SKB_CB(skb)->map_seq += count;
+                       }
                        break;
                }
 
@@ -1965,6 +1969,27 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk)
        return !skb_queue_empty(&msk->receive_queue);
 }
 
+static unsigned int mptcp_inq_hint(const struct sock *sk)
+{
+       const struct mptcp_sock *msk = mptcp_sk(sk);
+       const struct sk_buff *skb;
+
+       skb = skb_peek(&msk->receive_queue);
+       if (skb) {
+               u64 hint_val = msk->ack_seq - MPTCP_SKB_CB(skb)->map_seq;
+
+               if (hint_val >= INT_MAX)
+                       return INT_MAX;
+
+               return (unsigned int)hint_val;
+       }
+
+       if (sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN))
+               return 1;
+
+       return 0;
+}
+
 static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
                         int nonblock, int flags, int *addr_len)
 {
@@ -1989,6 +2014,9 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
        len = min_t(size_t, len, INT_MAX);
        target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
 
+       if (unlikely(msk->recvmsg_inq))
+               cmsg_flags = MPTCP_CMSG_INQ;
+
        while (copied < len) {
                int bytes_read;
 
@@ -2062,6 +2090,12 @@ out_err:
        if (cmsg_flags && copied >= 0) {
                if (cmsg_flags & MPTCP_CMSG_TS)
                        tcp_recv_timestamp(msg, sk, &tss);
+
+               if (cmsg_flags & MPTCP_CMSG_INQ) {
+                       unsigned int inq = mptcp_inq_hint(sk);
+
+                       put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq);
+               }
        }
 
        pr_debug("msk=%p rx queue empty=%d:%d copied=%d",

diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index d87cc04..bb51fa7 100644 (file)
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -249,6 +249,7 @@ struct mptcp_sock {
        bool            rcv_fastclose;
        bool            use_64bit_ack; /* Set when we received a 64-bit DSN */
        bool            csum_enabled;
+       u8              recvmsg_inq:1;
        spinlock_t      join_list_lock;
        struct work_struct work;
        struct sk_buff  *ooo_last_skb;

diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index fb43e14..11cda86 100644 (file)
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -557,6 +557,7 @@ static bool mptcp_supported_sockopt(int level, int optname)
                case TCP_TIMESTAMP:
                case TCP_NOTSENT_LOWAT:
                case TCP_TX_DELAY:
+               case TCP_INQ:
                        return true;
                }
 
@@ -568,7 +569,6 @@ static bool mptcp_supported_sockopt(int level, int optname)
                /* TCP_FASTOPEN_KEY, TCP_FASTOPEN TCP_FASTOPEN_CONNECT, TCP_FASTOPEN_NO_COOKIE,
                 * are not supported fastopen is currently unsupported
                 */
-               /* TCP_INQ is currently unsupported, needs some recvmsg work */
        }
        return false;
 }
@@ -698,7 +698,21 @@ static int mptcp_setsockopt_v4(struct mptcp_sock *msk, int optname,
 static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
                                    sockptr_t optval, unsigned int optlen)
 {
+       struct sock *sk = (void *)msk;
+       int ret, val;
+
        switch (optname) {
+       case TCP_INQ:
+               ret = mptcp_get_int_option(msk, optval, optlen, &val);
+               if (ret)
+                       return ret;
+               if (val < 0 || val > 1)
+                       return -EINVAL;
+
+               lock_sock(sk);
+               msk->recvmsg_inq = !!val;
+               release_sock(sk);
+               return 0;
        case TCP_ULP:
                return -EOPNOTSUPP;
        case TCP_CONGESTION:
@@ -1032,6 +1046,26 @@ static int mptcp_getsockopt_subflow_addrs(struct mptcp_sock *msk, char __user *o
        return 0;
 }
 
+static int mptcp_put_int_option(struct mptcp_sock *msk, char __user *optval,
+                               int __user *optlen, int val)
+{
+       int len;
+
+       if (get_user(len, optlen))
+               return -EFAULT;
+
+       len = min_t(unsigned int, len, sizeof(int));
+       if (len < 0)
+               return -EINVAL;
+
+       if (put_user(len, optlen))
+               return -EFAULT;
+       if (copy_to_user(optval, &val, len))
+               return -EFAULT;
+
+       return 0;
+}
+
 static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
                                    char __user *optval, int __user *optlen)
 {
@@ -1042,6 +1076,8 @@ static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
        case TCP_CC_INFO:
                return mptcp_getsockopt_first_sf_only(msk, SOL_TCP, optname,
                                                      optval, optlen);
+       case TCP_INQ:
+               return mptcp_put_int_option(msk, optval, optlen, msk->recvmsg_inq);
        }
        return -EOPNOTSUPP;
 }