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_output.c | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) (limited to 'net/ipv4/tcp_output.c') 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 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)); -- cgit v1.2.3 From 684bad1107571d35610a674c61b3544efb5a5b13 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Sun, 2 Sep 2012 17:38:04 +0000 Subject: tcp: use PRR to reduce cwin in CWR state Use proportional rate reduction (PRR) algorithm to reduce cwnd in CWR state, in addition to Recovery state. Retire the current rate-halving in CWR. When losses are detected via ACKs in CWR state, the sender enters Recovery state but the cwnd reduction continues and does not restart. Rename and refactor cwnd reduction functions since both CWR and Recovery use the same algorithm: tcp_init_cwnd_reduction() is new and initiates reduction state variables. tcp_cwnd_reduction() is previously tcp_update_cwnd_in_recovery(). tcp_ends_cwnd_reduction() is previously tcp_complete_cwr(). The rate halving functions and logic such as tcp_cwnd_down(), tcp_min_cwnd(), and the cwnd moderation inside tcp_enter_cwr() are removed. The unused parameter, flag, in tcp_cwnd_reduction() is also removed. Signed-off-by: Yuchung Cheng Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'net/ipv4/tcp_output.c') diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 9383b51f3efc..cfe6ffe1c177 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2037,10 +2037,10 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (push_one) break; } - if (inet_csk(sk)->icsk_ca_state == TCP_CA_Recovery) - tp->prr_out += sent_pkts; if (likely(sent_pkts)) { + if (tcp_in_cwnd_reduction(sk)) + tp->prr_out += sent_pkts; tcp_cwnd_validate(sk); return false; } @@ -2542,7 +2542,7 @@ begin_fwd: } NET_INC_STATS_BH(sock_net(sk), mib_idx); - if (inet_csk(sk)->icsk_ca_state == TCP_CA_Recovery) + if (tcp_in_cwnd_reduction(sk)) tp->prr_out += tcp_skb_pcount(skb); if (skb == tcp_write_queue_head(sk)) -- cgit v1.2.3