From ea84e5555a56e2013687b19b012bcf959d601128 Mon Sep 17 00:00:00 2001 From: Andreas Petlund Date: Tue, 27 Oct 2009 03:27:21 +0000 Subject: net: Corrected spelling error heurestics->heuristics Corrected a spelling error in a function name. Signed-off-by: Andreas Petlund Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index d86784be7ab3..a0c3700bae3a 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2300,7 +2300,7 @@ static inline int tcp_fackets_out(struct tcp_sock *tp) * they differ. Since neither occurs due to loss, TCP should really * ignore them. */ -static inline int tcp_dupack_heurestics(struct tcp_sock *tp) +static inline int tcp_dupack_heuristics(struct tcp_sock *tp) { return tcp_is_fack(tp) ? tp->fackets_out : tp->sacked_out + 1; } @@ -2425,7 +2425,7 @@ static int tcp_time_to_recover(struct sock *sk) return 1; /* Not-A-Trick#2 : Classic rule... */ - if (tcp_dupack_heurestics(tp) > tp->reordering) + if (tcp_dupack_heuristics(tp) > tp->reordering) return 1; /* Trick#3 : when we use RFC2988 timer restart, fast -- cgit v1.2.3 From 022c3f7d82f0f1c68018696f2f027b87b9bb45c2 Mon Sep 17 00:00:00 2001 From: Gilad Ben-Yossef Date: Wed, 28 Oct 2009 04:15:22 +0000 Subject: Allow tcp_parse_options to consult dst entry We need tcp_parse_options to be aware of dst_entry to take into account per dst_entry TCP options settings Signed-off-by: Gilad Ben-Yossef Sigend-off-by: Ori Finkelman Sigend-off-by: Yony Amit Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a0c3700bae3a..c7625005486d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3698,12 +3698,14 @@ 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, struct dst_entry *dst) { unsigned char *ptr; struct tcphdr *th = tcp_hdr(skb); int length = (th->doff * 4) - sizeof(struct tcphdr); + BUG_ON(!estab && !dst); + ptr = (unsigned char *)(th + 1); opt_rx->saw_tstamp = 0; @@ -3820,7 +3822,7 @@ 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, NULL); return 1; } @@ -5364,8 +5366,9 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); int saved_clamp = tp->rx_opt.mss_clamp; + struct dst_entry *dst = __sk_dst_get(sk); - tcp_parse_options(skb, &tp->rx_opt, 0); + tcp_parse_options(skb, &tp->rx_opt, 0, dst); if (th->ack) { /* rfc793: -- cgit v1.2.3 From 1aba721eba1d84a2defce45b950272cee1e6c72a Mon Sep 17 00:00:00 2001 From: Gilad Ben-Yossef Date: Wed, 28 Oct 2009 04:15:24 +0000 Subject: Add the no SACK route option feature Implement querying and acting upon the no sack bit in the features field. Signed-off-by: Gilad Ben-Yossef Sigend-off-by: Ori Finkelman Sigend-off-by: Yony Amit Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index c7625005486d..5fb25f977451 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3763,7 +3763,8 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, break; case TCPOPT_SACK_PERM: if (opsize == TCPOLEN_SACK_PERM && th->syn && - !estab && sysctl_tcp_sack) { + !estab && sysctl_tcp_sack && + !dst_feature(dst, RTAX_FEATURE_NO_SACK)) { opt_rx->sack_ok = 1; tcp_sack_reset(opt_rx); } -- cgit v1.2.3 From cda42ebd67ee5fdf09d7057b5a4584d36fe8a335 Mon Sep 17 00:00:00 2001 From: Gilad Ben-Yossef Date: Wed, 28 Oct 2009 04:15:25 +0000 Subject: Allow disabling TCP timestamp options per route Implement querying and acting upon the no timestamp bit in the feature field. Signed-off-by: Gilad Ben-Yossef Sigend-off-by: Ori Finkelman Sigend-off-by: Yony Amit Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 5fb25f977451..6097491aa9fc 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3755,7 +3755,8 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, case TCPOPT_TIMESTAMP: if ((opsize == TCPOLEN_TIMESTAMP) && ((estab && opt_rx->tstamp_ok) || - (!estab && sysctl_tcp_timestamps))) { + (!estab && sysctl_tcp_timestamps && + !dst_feature(dst, RTAX_FEATURE_NO_TSTAMP)))) { opt_rx->saw_tstamp = 1; opt_rx->rcv_tsval = get_unaligned_be32(ptr); opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4); -- cgit v1.2.3 From 345cda2fd695534be5a4494f1b59da9daed33663 Mon Sep 17 00:00:00 2001 From: Gilad Ben-Yossef Date: Wed, 28 Oct 2009 04:15:26 +0000 Subject: Allow to turn off TCP window scale opt per route Add and use no window scale bit in the features field. Note that this is not the same as setting a window scale of 0 as would happen with window limit on route. Signed-off-by: Gilad Ben-Yossef Sigend-off-by: Ori Finkelman Sigend-off-by: Yony Amit Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 6097491aa9fc..393c56921dcb 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3739,7 +3739,8 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, break; case TCPOPT_WINDOW: if (opsize == TCPOLEN_WINDOW && th->syn && - !estab && sysctl_tcp_window_scaling) { + !estab && sysctl_tcp_window_scaling && + !dst_feature(dst, RTAX_FEATURE_NO_WSCALE)) { __u8 snd_wscale = *(__u8 *)ptr; opt_rx->wscale_ok = 1; if (snd_wscale > 14) { -- cgit v1.2.3 From dc343475ed062e13fc260acccaab91d7d80fd5b2 Mon Sep 17 00:00:00 2001 From: Gilad Ben-Yossef Date: Wed, 28 Oct 2009 04:15:27 +0000 Subject: Allow disabling of DSACK TCP option per route Add and use no DSCAK bit in the features field. Signed-off-by: Gilad Ben-Yossef Sigend-off-by: Ori Finkelman Sigend-off-by: Yony Amit Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 393c56921dcb..ba0eab65fe80 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4080,8 +4080,10 @@ static inline int tcp_sack_extend(struct tcp_sack_block *sp, u32 seq, static void tcp_dsack_set(struct sock *sk, u32 seq, u32 end_seq) { struct tcp_sock *tp = tcp_sk(sk); + struct dst_entry *dst = __sk_dst_get(sk); - if (tcp_is_sack(tp) && sysctl_tcp_dsack) { + if (tcp_is_sack(tp) && sysctl_tcp_dsack && + !dst_feature(dst, RTAX_FEATURE_NO_DSACK)) { int mib_idx; if (before(seq, tp->rcv_nxt)) @@ -4110,13 +4112,15 @@ static void tcp_dsack_extend(struct sock *sk, u32 seq, u32 end_seq) static void tcp_send_dupack(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); + struct dst_entry *dst = __sk_dst_get(sk); if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq && before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKLOST); tcp_enter_quickack_mode(sk); - if (tcp_is_sack(tp) && sysctl_tcp_dsack) { + if (tcp_is_sack(tp) && sysctl_tcp_dsack && + !dst_feature(dst, RTAX_FEATURE_NO_DSACK)) { u32 end_seq = TCP_SKB_CB(skb)->end_seq; if (after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) -- cgit v1.2.3 From 6a2a2d6bf8581216e08be15fcb563cfd6c430e1e Mon Sep 17 00:00:00 2001 From: Gilad Ben-Yossef Date: Wed, 4 Nov 2009 23:23:10 -0800 Subject: tcp: Use defaults when no route options are available Trying to parse the option of a SYN packet that we have no route entry for should just use global wide defaults for route entry options. Signed-off-by: Gilad Ben-Yossef Tested-by: Valdis.Kletnieks@vt.edu Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index ba0eab65fe80..be0c5bf7bfca 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3704,8 +3704,6 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, struct tcphdr *th = tcp_hdr(skb); int length = (th->doff * 4) - sizeof(struct tcphdr); - BUG_ON(!estab && !dst); - ptr = (unsigned char *)(th + 1); opt_rx->saw_tstamp = 0; -- cgit v1.2.3 From bee7ca9ec03a26676ea2b1c28dc4039348eff3e1 Mon Sep 17 00:00:00 2001 From: William Allen Simpson Date: Tue, 10 Nov 2009 09:51:18 +0000 Subject: net: TCP_MSS_DEFAULT, TCP_MSS_DESIRED Define two symbols needed in both kernel and user space. Remove old (somewhat incorrect) kernel variant that wasn't used in most cases. Default should apply to both RMSS and SMSS (RFC2581). Replace numeric constants with defined symbols. Stand-alone patch, originally developed for TCPCT. Signed-off-by: William.Allen.Simpson@gmail.com Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index be0c5bf7bfca..cc306ac6eb51 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -140,7 +140,7 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) * "len" is invariant segment length, including TCP header. */ len += skb->data - skb_transport_header(skb); - if (len >= TCP_MIN_RCVMSS + sizeof(struct tcphdr) || + if (len >= TCP_MSS_DEFAULT + sizeof(struct tcphdr) || /* If PSH is not set, packet should be * full sized, provided peer TCP is not badly broken. * This observation (if it is correct 8)) allows @@ -411,7 +411,7 @@ void tcp_initialize_rcv_mss(struct sock *sk) unsigned int hint = min_t(unsigned int, tp->advmss, tp->mss_cache); hint = min(hint, tp->rcv_wnd / 2); - hint = min(hint, TCP_MIN_RCVMSS); + hint = min(hint, TCP_MSS_DEFAULT); hint = max(hint, TCP_MIN_MSS); inet_csk(sk)->icsk_ack.rcv_mss = hint; -- cgit v1.2.3 From 9d4fb27db90043cd2640e4bc778f9c755d3c17c1 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 23 Nov 2009 10:41:23 -0800 Subject: net/ipv4: Move && and || to end of previous line On Sun, 2009-11-22 at 16:31 -0800, David Miller wrote: > It should be of the form: > if (x && > y) > > or: > if (x && y) > > Fix patches, rather than complaints, for existing cases where things > do not follow this pattern are certainly welcome. Also collapsed some multiple tabs to single space. Signed-off-by: Joe Perches Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index cc306ac6eb51..be166e0e11c5 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4852,11 +4852,11 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible) struct tcp_sock *tp = tcp_sk(sk); /* More than one full frame received... */ - if (((tp->rcv_nxt - tp->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss + if (((tp->rcv_nxt - tp->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss && /* ... and right edge of window advances far enough. * (tcp_recvmsg() will send ACK otherwise). Or... */ - && __tcp_select_window(sk) >= tp->rcv_wnd) || + __tcp_select_window(sk) >= tp->rcv_wnd) || /* We ACK each frame or... */ tcp_in_quickack_mode(sk) || /* We have out of order data. */ -- cgit v1.2.3 From 4957faade11b3a278c3b3cade3411ddc20afa791 Mon Sep 17 00:00:00 2001 From: William Allen Simpson Date: Wed, 2 Dec 2009 18:25:27 +0000 Subject: TCPCT part 1g: Responder Cookie => Initiator Parse incoming TCP_COOKIE option(s). Calculate TCP_COOKIE option. Send optional data. This is a significantly revised implementation of an earlier (year-old) patch that no longer applies cleanly, with permission of the original author (Adam Langley): http://thread.gmane.org/gmane.linux.network/102586 Requires: TCPCT part 1a: add request_values parameter for sending SYNACK TCPCT part 1b: generate Responder Cookie secret TCPCT part 1c: sysctl_tcp_cookie_size, socket option TCP_COOKIE_TRANSACTIONS TCPCT part 1d: define TCP cookie option, extend existing struct's TCPCT part 1e: implement socket option TCP_COOKIE_TRANSACTIONS TCPCT part 1f: Initiator Cookie => Responder Signed-off-by: William.Allen.Simpson@gmail.com Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 75 +++++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 65 insertions(+), 10 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index be166e0e11c5..57ae96a04220 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3698,7 +3698,7 @@ old_ack: * the fast version below fails. */ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, - int estab, struct dst_entry *dst) + u8 **hvpp, int estab, struct dst_entry *dst) { unsigned char *ptr; struct tcphdr *th = tcp_hdr(skb); @@ -3785,7 +3785,30 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, */ break; #endif - } + case TCPOPT_COOKIE: + /* This option is variable length. + */ + switch (opsize) { + case TCPOLEN_COOKIE_BASE: + /* not yet implemented */ + break; + case TCPOLEN_COOKIE_PAIR: + /* not yet implemented */ + break; + case TCPOLEN_COOKIE_MIN+0: + case TCPOLEN_COOKIE_MIN+2: + case TCPOLEN_COOKIE_MIN+4: + case TCPOLEN_COOKIE_MIN+6: + case TCPOLEN_COOKIE_MAX: + /* 16-bit multiple */ + opt_rx->cookie_plus = opsize; + *hvpp = ptr; + default: + /* ignore option */ + break; + }; + break; + }; ptr += opsize-2; length -= opsize; @@ -3813,17 +3836,20 @@ static int tcp_parse_aligned_timestamp(struct tcp_sock *tp, struct tcphdr *th) * If it is wrong it falls back on tcp_parse_options(). */ static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th, - struct tcp_sock *tp) + struct tcp_sock *tp, u8 **hvpp) { - if (th->doff == sizeof(struct tcphdr) >> 2) { + /* In the spirit of fast parsing, compare doff directly to constant + * values. Because equality is used, short doff can be ignored here. + */ + if (th->doff == (sizeof(*th) / 4)) { tp->rx_opt.saw_tstamp = 0; return 0; } else if (tp->rx_opt.tstamp_ok && - th->doff == (sizeof(struct tcphdr)>>2)+(TCPOLEN_TSTAMP_ALIGNED>>2)) { + th->doff == ((sizeof(*th) + TCPOLEN_TSTAMP_ALIGNED) / 4)) { if (tcp_parse_aligned_timestamp(tp, th)) return 1; } - tcp_parse_options(skb, &tp->rx_opt, 1, NULL); + tcp_parse_options(skb, &tp->rx_opt, hvpp, 1, NULL); return 1; } @@ -5077,10 +5103,12 @@ out: static int tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, struct tcphdr *th, int syn_inerr) { + u8 *hash_location; struct tcp_sock *tp = tcp_sk(sk); /* RFC1323: H1. Apply PAWS check first. */ - if (tcp_fast_parse_options(skb, th, tp) && tp->rx_opt.saw_tstamp && + if (tcp_fast_parse_options(skb, th, tp, &hash_location) && + tp->rx_opt.saw_tstamp && tcp_paws_discard(sk, skb)) { if (!th->rst) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED); @@ -5368,12 +5396,14 @@ discard: static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, struct tcphdr *th, unsigned len) { - struct tcp_sock *tp = tcp_sk(sk); + u8 *hash_location; struct inet_connection_sock *icsk = inet_csk(sk); - int saved_clamp = tp->rx_opt.mss_clamp; + struct tcp_sock *tp = tcp_sk(sk); struct dst_entry *dst = __sk_dst_get(sk); + struct tcp_cookie_values *cvp = tp->cookie_values; + int saved_clamp = tp->rx_opt.mss_clamp; - tcp_parse_options(skb, &tp->rx_opt, 0, dst); + tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0, dst); if (th->ack) { /* rfc793: @@ -5470,6 +5500,31 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, * Change state from SYN-SENT only after copied_seq * is initialized. */ tp->copied_seq = tp->rcv_nxt; + + if (cvp != NULL && + cvp->cookie_pair_size > 0 && + tp->rx_opt.cookie_plus > 0) { + int cookie_size = tp->rx_opt.cookie_plus + - TCPOLEN_COOKIE_BASE; + int cookie_pair_size = cookie_size + + cvp->cookie_desired; + + /* A cookie extension option was sent and returned. + * Note that each incoming SYNACK replaces the + * Responder cookie. The initial exchange is most + * fragile, as protection against spoofing relies + * entirely upon the sequence and timestamp (above). + * This replacement strategy allows the correct pair to + * pass through, while any others will be filtered via + * Responder verification later. + */ + if (sizeof(cvp->cookie_pair) >= cookie_pair_size) { + memcpy(&cvp->cookie_pair[cvp->cookie_desired], + hash_location, cookie_size); + cvp->cookie_pair_size = cookie_pair_size; + } + } + smp_mb(); tcp_set_state(sk, TCP_ESTABLISHED); -- cgit v1.2.3