tcp: allow zerocopy with fastopen

Accept MSG_ZEROCOPY in all the TCP states that allow sendmsg. Remove
the explicit check for ESTABLISHED and CLOSE_WAIT states.

This requires correctly handling zerocopy state (uarg, sk_zckey) in
all paths reachable from other TCP states. Such as the EPIPE case
in sk_stream_wait_connect, which a sendmsg() in incorrect state will
now hit. Most paths are already safe.

Only extension needed is for TCP Fastopen active open. This can build
an skb with data in tcp_send_syn_data. Pass the uarg along with other
fastopen state, so that this skb also generates a zerocopy
notification on release.

Tested with active and passive tcp fastopen packetdrill scripts at
https://github.com/wdebruij/packetdrill/commit/1747eef03d25a2404e8132817d0f1244fd6f129d

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 5c95018..a6e0355 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1608,6 +1608,7 @@ struct tcp_fastopen_request {
        struct msghdr                   *data;  /* data in MSG_FASTOPEN */
        size_t                          size;
        int                             copied; /* queued in tcp_connect() */
+       struct ubuf_info                *uarg;
 };
 void tcp_free_fastopen_req(struct tcp_sock *tp);
 void tcp_fastopen_destroy_cipher(struct sock *sk);

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 5f099c9..12ba214 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1127,7 +1127,8 @@ void tcp_free_fastopen_req(struct tcp_sock *tp)
 }
 
 static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
-                               int *copied, size_t size)
+                               int *copied, size_t size,
+                               struct ubuf_info *uarg)
 {
        struct tcp_sock *tp = tcp_sk(sk);
        struct inet_sock *inet = inet_sk(sk);
@@ -1147,6 +1148,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
                return -ENOBUFS;
        tp->fastopen_req->data = msg;
        tp->fastopen_req->size = size;
+       tp->fastopen_req->uarg = uarg;
 
        if (inet->defer_connect) {
                err = tcp_connect(sk);
@@ -1186,11 +1188,6 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
        flags = msg->msg_flags;
 
        if (flags & MSG_ZEROCOPY && size && sock_flag(sk, SOCK_ZEROCOPY)) {
-               if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) {
-                       err = -EINVAL;
-                       goto out_err;
-               }
-
                skb = tcp_write_queue_tail(sk);
                uarg = sock_zerocopy_realloc(sk, size, skb_zcopy(skb));
                if (!uarg) {
@@ -1205,7 +1202,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 
        if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) &&
            !tp->repair) {
-               err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size);
+               err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size, uarg);
                if (err == -EINPROGRESS && copied_syn > 0)
                        goto out;
                else if (err)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 6527f61..26a2948 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3455,6 +3455,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
                        skb_trim(syn_data, copied);
                        space = copied;
                }
+               skb_zcopy_set(syn_data, fo->uarg, NULL);
        }
        /* No more data pending in inet_wait_for_connect() */
        if (space == fo->size)