From 8336886f786fdacbc19b719c1f7ea91eb70706d4 Mon Sep 17 00:00:00 2001 From: Jerry Chu Date: Fri, 31 Aug 2012 12:29:12 +0000 Subject: 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 Cc: Yuchung Cheng Cc: Neal Cardwell Cc: Eric Dumazet Cc: Tom Herbert Signed-off-by: David S. Miller --- net/ipv4/tcp_timer.c | 39 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 38 insertions(+), 1 deletion(-) (limited to 'net/ipv4/tcp_timer.c') diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index b774a03bd1dc..fc04711e80c8 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -304,6 +304,35 @@ static void tcp_probe_timer(struct sock *sk) } } +/* + * Timer for Fast Open socket to retransmit SYNACK. Note that the + * sk here is the child socket, not the parent (listener) socket. + */ +static void tcp_fastopen_synack_timer(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + int max_retries = icsk->icsk_syn_retries ? : + sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */ + struct request_sock *req; + + req = tcp_sk(sk)->fastopen_rsk; + req->rsk_ops->syn_ack_timeout(sk, req); + + if (req->retrans >= max_retries) { + tcp_write_err(sk); + return; + } + /* XXX (TFO) - Unlike regular SYN-ACK retransmit, we ignore error + * returned from rtx_syn_ack() to make it more persistent like + * regular retransmit because if the child socket has been accepted + * it's not good to give up too easily. + */ + req->rsk_ops->rtx_syn_ack(sk, req, NULL); + req->retrans++; + inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, + TCP_TIMEOUT_INIT << req->retrans, TCP_RTO_MAX); +} + /* * The TCP retransmit timer. */ @@ -317,7 +346,15 @@ void tcp_retransmit_timer(struct sock *sk) tcp_resume_early_retransmit(sk); return; } - + if (tp->fastopen_rsk) { + BUG_ON(sk->sk_state != TCP_SYN_RECV && + sk->sk_state != TCP_FIN_WAIT1); + tcp_fastopen_synack_timer(sk); + /* Before we receive ACK to our SYN-ACK don't retransmit + * anything else (e.g., data or FIN segments). + */ + return; + } if (!tp->packets_out) goto out; -- cgit v1.2.3 From 37561f68bd527ec39076e32effdc7b1dcdfb17ea Mon Sep 17 00:00:00 2001 From: Jerry Chu Date: Mon, 22 Oct 2012 11:26:36 +0000 Subject: tcp: Reject invalid ack_seq to Fast Open sockets A packet with an invalid ack_seq may cause a TCP Fast Open socket to switch to the unexpected TCP_CLOSING state, triggering a BUG_ON kernel panic. When a FIN packet with an invalid ack_seq# arrives at a socket in the TCP_FIN_WAIT1 state, rather than discarding the packet, the current code will accept the FIN, causing state transition to TCP_CLOSING. This may be a small deviation from RFC793, which seems to say that the packet should be dropped. Unfortunately I did not expect this case for Fast Open hence it will trigger a BUG_ON panic. It turns out there is really nothing bad about a TFO socket going into TCP_CLOSING state so I could just remove the BUG_ON statements. But after some thought I think it's better to treat this case like TCP_SYN_RECV and return a RST to the confused peer who caused the unacceptable ack_seq to be generated in the first place. Signed-off-by: H.K. Jerry Chu Cc: Neal Cardwell Cc: Yuchung Cheng Acked-by: Yuchung Cheng Acked-by: Eric Dumazet Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 12 ++++++++++-- net/ipv4/tcp_timer.c | 4 ++-- 2 files changed, 12 insertions(+), 4 deletions(-) (limited to 'net/ipv4/tcp_timer.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 036f85738141..1db663983587 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5964,7 +5964,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, req = tp->fastopen_rsk; if (req != NULL) { - BUG_ON(sk->sk_state != TCP_SYN_RECV && + WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV && sk->sk_state != TCP_FIN_WAIT1); if (tcp_check_req(sk, skb, req, NULL, true) == NULL) @@ -6053,7 +6053,15 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, * ACK we have received, this would have acknowledged * our SYNACK so stop the SYNACK timer. */ - if (acceptable && req != NULL) { + if (req != NULL) { + /* Return RST if ack_seq is invalid. + * Note that RFC793 only says to generate a + * DUPACK for it but for TCP Fast Open it seems + * better to treat this case like TCP_SYN_RECV + * above. + */ + if (!acceptable) + return 1; /* We no longer need the request sock. */ reqsk_fastopen_remove(sk, req, false); tcp_rearm_rto(sk); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index fc04711e80c8..d47c1b4421a3 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -347,8 +347,8 @@ void tcp_retransmit_timer(struct sock *sk) return; } if (tp->fastopen_rsk) { - BUG_ON(sk->sk_state != TCP_SYN_RECV && - sk->sk_state != TCP_FIN_WAIT1); + WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV && + sk->sk_state != TCP_FIN_WAIT1); tcp_fastopen_synack_timer(sk); /* Before we receive ACK to our SYN-ACK don't retransmit * anything else (e.g., data or FIN segments). -- cgit v1.2.3