tcp: TCP Fast Open Server - support TFO listeners

This patch builds on top of the previous patch to add the support
for TFO listeners. This includes -

1. allocating, properly initializing, and managing the per listener
fastopen_queue structure when TFO is enabled

2. changes to the inet_csk_accept code to support TFO. E.g., the
request_sock can no longer be freed upon accept(), not until 3WHS
finishes

3. allowing a TCP_SYN_RECV socket to properly poll() and sendmsg()
if it's a TFO socket

4. properly closing a TFO listener, and a TFO socket before 3WHS
finishes

5. supporting TCP_FASTOPEN socket option

6. modifying tcp_check_req() to use to check a TFO socket as well
as request_sock

7. supporting TCP's TFO cookie option

8. adding a new SYN-ACK retransmit handler to use the timer directly
off the TFO socket rather than the listener socket. Note that TFO
server side will not retransmit anything other than SYN-ACK until
the 3WHS is completed.

The patch also contains an important function
"reqsk_fastopen_remove()" to manage the somewhat complex relation
between a listener, its request_sock, and the corresponding child
socket. See the comment above the function for the detail.

Signed-off-by: H.K. Jerry Chu <hkchu@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 16 insertions, 5 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index d04632673a9e..9383b51f3efc 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -702,7 +702,8 @@ static unsigned int tcp_synack_options(struct sock *sk,
                                    unsigned int mss, struct sk_buff *skb,
                                    struct tcp_out_options *opts,
                                    struct tcp_md5sig_key **md5,
-                                   struct tcp_extend_values *xvp)
+                                   struct tcp_extend_values *xvp,
+                                   struct tcp_fastopen_cookie *foc)
 {
         struct inet_request_sock *ireq = inet_rsk(req);
         unsigned int remaining = MAX_TCP_OPTION_SPACE;
@@ -747,7 +748,15 @@ static unsigned int tcp_synack_options(struct sock *sk,
                 if (unlikely(!ireq->tstamp_ok))
                         remaining -= TCPOLEN_SACKPERM_ALIGNED;
         }
-
+        if (foc != NULL) {
+                u32 need = TCPOLEN_EXP_FASTOPEN_BASE + foc->len;
+                need = (need + 3) & ~3U;  /* Align to 32 bits */
+                if (remaining >= need) {
+                        opts->options |= OPTION_FAST_OPEN_COOKIE;
+                        opts->fastopen_cookie = foc;
+                        remaining -= need;
+                }
+        }
         /* Similar rationale to tcp_syn_options() applies here, too.
          * If the <SYN> options fit, the same options should fit now!
          */
@@ -2658,7 +2667,8 @@ int tcp_send_synack(struct sock *sk)
  */
 struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
                                 struct request_sock *req,
-                                struct request_values *rvp)
+                                struct request_values *rvp,
+                                struct tcp_fastopen_cookie *foc)
 {
         struct tcp_out_options opts;
         struct tcp_extend_values *xvp = tcp_xv(rvp);
@@ -2718,7 +2728,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 #endif
         TCP_SKB_CB(skb)->when = tcp_time_stamp;
         tcp_header_size = tcp_synack_options(sk, req, mss,
-                                             skb, &opts, &md5, xvp)
+                                             skb, &opts, &md5, xvp, foc)
                         + sizeof(*th);
 
         skb_push(skb, tcp_header_size);
@@ -2772,7 +2782,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
         }
 
         th->seq = htonl(TCP_SKB_CB(skb)->seq);
-        th->ack_seq = htonl(tcp_rsk(req)->rcv_isn + 1);
+        /* XXX data is queued and acked as is. No buffer/window check */
+        th->ack_seq = htonl(tcp_rsk(req)->rcv_nxt);
 
         /* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */
         th->window = htons(min(req->rcv_wnd, 65535U));