Adjust the sent and received TCP timestamp value by a scalar value in the tcp_sock structure. This will be zero most of the time, except when the socket has been migrated with c/r. If a socket is re-migrated, we take the new adjusted value as the saved value so that on restart it can be re-adjusted. Also, copy this into the timewait sock so that timestamps can continue to be adjusted in timewait state in the minisocks code.
Note that TCP timestamps are just a jiffies stamp, which means they have no relation to wall-clock time and thus a simple correction factor should be enough to ensure correctness. Signed-off-by: Dan Smith <[email protected]> --- include/linux/checkpoint_hdr.h | 2 ++ include/linux/tcp.h | 3 +++ include/net/tcp.h | 3 ++- net/ipv4/checkpoint.c | 8 ++++++++ net/ipv4/syncookies.c | 2 +- net/ipv4/tcp_input.c | 14 +++++++------- net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/tcp_minisocks.c | 8 ++++++-- net/ipv4/tcp_output.c | 20 ++++++++++---------- net/ipv6/syncookies.c | 2 +- net/ipv6/tcp_ipv6.c | 2 +- 11 files changed, 42 insertions(+), 24 deletions(-) diff --git a/include/linux/checkpoint_hdr.h b/include/linux/checkpoint_hdr.h index 0c10657..9c2f13d 100644 --- a/include/linux/checkpoint_hdr.h +++ b/include/linux/checkpoint_hdr.h @@ -649,6 +649,8 @@ struct ckpt_hdr_socket_inet { __u32 keepalive_time; __u32 keepalive_intvl; + __s32 tcp_ts; + __u16 urg_data; __u16 advmss; __u8 frto_counter; diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 8afac76..b845e21 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -399,6 +399,8 @@ struct tcp_sock { u32 probe_seq_end; } mtu_probe; + s32 ts_adjust; /* tcp_time_stamp adjustment factor */ + #ifdef CONFIG_TCP_MD5SIG /* TCP AF-Specific parts; only used by MD5 Signature support so far */ struct tcp_sock_af_ops *af_specific; @@ -420,6 +422,7 @@ struct tcp_timewait_sock { u32 tw_rcv_wnd; u32 tw_ts_recent; long tw_ts_recent_stamp; + s32 tw_ts_adjust; #ifdef CONFIG_TCP_MD5SIG u16 tw_md5_keylen; u8 tw_md5_key[TCP_MD5SIG_MAXKEYLEN]; diff --git a/include/net/tcp.h b/include/net/tcp.h index 88af843..96b4b27 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -409,7 +409,8 @@ extern int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, extern void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, - int estab); + int estab, + s32 ts_adjust); extern u8 *tcp_parse_md5sig_option(struct tcphdr *th); diff --git a/net/ipv4/checkpoint.c b/net/ipv4/checkpoint.c index 5913652..f858dbc 100644 --- a/net/ipv4/checkpoint.c +++ b/net/ipv4/checkpoint.c @@ -178,6 +178,14 @@ static int sock_inet_tcp_cptrst(struct ckpt_ctx *ctx, CKPT_COPY(op, hh->tcp.keepalive_time, sk->keepalive_time); CKPT_COPY(op, hh->tcp.keepalive_intvl, sk->keepalive_intvl); + if (op == CKPT_CPT) + hh->tcp.tcp_ts = tcp_time_stamp + sk->ts_adjust; + else + sk->ts_adjust = hh->tcp.tcp_ts - tcp_time_stamp; + + ckpt_debug("TCP tcp_ts %i ts_adjust %i\n", + hh->tcp.tcp_ts, sk->ts_adjust); + return 0; } diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index cd2b97f..31eafef 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -277,7 +277,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, /* check for timestamp cookie support */ memset(&tcp_opt, 0, sizeof(tcp_opt)); - tcp_parse_options(skb, &tcp_opt, 0); + tcp_parse_options(skb, &tcp_opt, 0, tp->ts_adjust); if (tcp_opt.saw_tstamp) cookie_check_timestamp(&tcp_opt); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2bdb0da..63cac78 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3699,7 +3699,7 @@ old_ack: * the fast version below fails. */ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, - int estab) + int estab, s32 ts_adjust) { unsigned char *ptr; struct tcphdr *th = tcp_hdr(skb); @@ -3756,8 +3756,8 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, ((estab && opt_rx->tstamp_ok) || (!estab && sysctl_tcp_timestamps))) { opt_rx->saw_tstamp = 1; - opt_rx->rcv_tsval = get_unaligned_be32(ptr); - opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4); + opt_rx->rcv_tsval = get_unaligned_be32(ptr) + ts_adjust; + opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4) + ts_adjust; } break; case TCPOPT_SACK_PERM: @@ -3799,9 +3799,9 @@ static int tcp_parse_aligned_timestamp(struct tcp_sock *tp, struct tcphdr *th) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP)) { tp->rx_opt.saw_tstamp = 1; ++ptr; - tp->rx_opt.rcv_tsval = ntohl(*ptr); + tp->rx_opt.rcv_tsval = ntohl(*ptr) + tp->ts_adjust; ++ptr; - tp->rx_opt.rcv_tsecr = ntohl(*ptr); + tp->rx_opt.rcv_tsecr = ntohl(*ptr) + tp->ts_adjust; return 1; } return 0; @@ -3821,7 +3821,7 @@ static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th, if (tcp_parse_aligned_timestamp(tp, th)) return 1; } - tcp_parse_options(skb, &tp->rx_opt, 1); + tcp_parse_options(skb, &tp->rx_opt, 1, tp->ts_adjust); return 1; } @@ -5366,7 +5366,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, struct inet_connection_sock *icsk = inet_csk(sk); int saved_clamp = tp->rx_opt.mss_clamp; - tcp_parse_options(skb, &tp->rx_opt, 0); + tcp_parse_options(skb, &tp->rx_opt, 0, tp->ts_adjust); if (th->ack) { /* rfc793: diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 6d88219..e8efe7f 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1222,7 +1222,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) tmp_opt.mss_clamp = 536; tmp_opt.user_mss = tcp_sk(sk)->rx_opt.user_mss; - tcp_parse_options(skb, &tmp_opt, 0); + tcp_parse_options(skb, &tmp_opt, 0, 0); if (want_cookie && !tmp_opt.saw_tstamp) tcp_clear_options(&tmp_opt); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index f8d67cc..4c72954 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -102,7 +102,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, tmp_opt.saw_tstamp = 0; if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) { - tcp_parse_options(skb, &tmp_opt, 0); + tcp_parse_options(skb, &tmp_opt, 0, tcptw->tw_ts_adjust); if (tmp_opt.saw_tstamp) { tmp_opt.ts_recent = tcptw->tw_ts_recent; @@ -292,6 +292,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) tcptw->tw_snd_nxt = tp->snd_nxt; tcptw->tw_rcv_wnd = tcp_receive_window(tp); tcptw->tw_ts_recent = tp->rx_opt.ts_recent; + tcptw->tw_ts_adjust = tp->ts_adjust; tcptw->tw_ts_recent_stamp = tp->rx_opt.ts_recent_stamp; #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) @@ -503,7 +504,10 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, tmp_opt.saw_tstamp = 0; if (th->doff > (sizeof(struct tcphdr)>>2)) { - tcp_parse_options(skb, &tmp_opt, 0); + /* C/R doesn't support request sockets yet, so we + * don't need to worry about passing a ts_adjust here + */ + tcp_parse_options(skb, &tmp_opt, 0, 0); if (tmp_opt.saw_tstamp) { tmp_opt.ts_recent = req->ts_recent; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index bd62712..38c165e 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1487,7 +1487,7 @@ static int tcp_mtu_probe(struct sock *sk) /* We're ready to send. If this fails, the probe will * be resegmented into mss-sized pieces by tcp_write_xmit(). */ - TCP_SKB_CB(nskb)->when = tcp_time_stamp; + TCP_SKB_CB(nskb)->when = tcp_time_stamp + tp->ts_adjust; if (!tcp_transmit_skb(sk, nskb, 1, GFP_ATOMIC)) { /* Decrement cwnd here because we are sending * effectively two packets. */ @@ -1568,7 +1568,7 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, unlikely(tso_fragment(sk, skb, limit, mss_now))) break; - TCP_SKB_CB(skb)->when = tcp_time_stamp; + TCP_SKB_CB(skb)->when = tcp_time_stamp + tp->ts_adjust; if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp))) break; @@ -1922,7 +1922,7 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) /* Make a copy, if the first transmission SKB clone we made * is still in somebody's hands, else make a clone. */ - TCP_SKB_CB(skb)->when = tcp_time_stamp; + TCP_SKB_CB(skb)->when = tcp_time_stamp + tp->ts_adjust; err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); @@ -2138,7 +2138,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority) tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk), TCPCB_FLAG_ACK | TCPCB_FLAG_RST); /* Send it off. */ - TCP_SKB_CB(skb)->when = tcp_time_stamp; + TCP_SKB_CB(skb)->when = tcp_time_stamp + tcp_sk(sk)->ts_adjust; if (tcp_transmit_skb(sk, skb, 0, priority)) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED); @@ -2176,7 +2176,7 @@ int tcp_send_synack(struct sock *sk) TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_ACK; TCP_ECN_send_synack(tcp_sk(sk), skb); } - TCP_SKB_CB(skb)->when = tcp_time_stamp; + TCP_SKB_CB(skb)->when = tcp_time_stamp + tcp_sk(sk)->ts_adjust; return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } @@ -2229,7 +2229,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, TCP_SKB_CB(skb)->when = cookie_init_timestamp(req); else #endif - TCP_SKB_CB(skb)->when = tcp_time_stamp; + TCP_SKB_CB(skb)->when = tcp_time_stamp + tp->ts_adjust; tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, &md5) + sizeof(struct tcphdr); @@ -2352,7 +2352,7 @@ int tcp_connect(struct sock *sk) TCP_ECN_send_syn(sk, buff); /* Send it off. */ - TCP_SKB_CB(buff)->when = tcp_time_stamp; + TCP_SKB_CB(buff)->when = tcp_time_stamp + tp->ts_adjust; tp->retrans_stamp = TCP_SKB_CB(buff)->when; skb_header_release(buff); __tcp_add_write_queue_tail(sk, buff); @@ -2457,7 +2457,7 @@ void tcp_send_ack(struct sock *sk) tcp_init_nondata_skb(buff, tcp_acceptable_seq(sk), TCPCB_FLAG_ACK); /* Send it off, this clears delayed acks for us. */ - TCP_SKB_CB(buff)->when = tcp_time_stamp; + TCP_SKB_CB(buff)->when = tcp_time_stamp + tcp_sk(sk)->ts_adjust; tcp_transmit_skb(sk, buff, 0, GFP_ATOMIC); } @@ -2489,7 +2489,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent) * send it. */ tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPCB_FLAG_ACK); - TCP_SKB_CB(skb)->when = tcp_time_stamp; + TCP_SKB_CB(skb)->when = tcp_time_stamp + tp->ts_adjust; return tcp_transmit_skb(sk, skb, 0, GFP_ATOMIC); } @@ -2524,7 +2524,7 @@ int tcp_write_wakeup(struct sock *sk) tcp_set_skb_tso_segs(sk, skb, mss); TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_PSH; - TCP_SKB_CB(skb)->when = tcp_time_stamp; + TCP_SKB_CB(skb)->when = tcp_time_stamp + tp->ts_adjust; err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); if (!err) tcp_event_new_data_sent(sk, skb); diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 8c25139..9337ec6 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -185,7 +185,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) /* check for timestamp cookie support */ memset(&tcp_opt, 0, sizeof(tcp_opt)); - tcp_parse_options(skb, &tcp_opt, 0); + tcp_parse_options(skb, &tcp_opt, 0, tp->ts_adjust); if (tcp_opt.saw_tstamp) cookie_check_timestamp(&tcp_opt); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index d849dd5..3a83570 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1202,7 +1202,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); tmp_opt.user_mss = tp->rx_opt.user_mss; - tcp_parse_options(skb, &tmp_opt, 0); + tcp_parse_options(skb, &tmp_opt, 0, 0); if (want_cookie && !tmp_opt.saw_tstamp) tcp_clear_options(&tmp_opt); -- 1.6.2.5 _______________________________________________ Containers mailing list [email protected] https://lists.linux-foundation.org/mailman/listinfo/containers _______________________________________________ Devel mailing list [email protected] https://openvz.org/mailman/listinfo/devel
