From ee58681195bf243bafc44ca53f3c24429d096cce Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Tue, 16 Nov 2010 11:52:49 +0000 Subject: network: tcp_connect should return certain errors up the stack The current tcp_connect code completely ignores errors from sending an skb. This makes sense in many situations (like -ENOBUFFS) but I want to be able to immediately fail connections if they are denied by the SELinux netfilter hook. Netfilter does not normally return ECONNREFUSED when it drops a packet so we respect that error code as a final and fatal error that can not be recovered. Based-on-patch-by: Patrick McHardy Signed-off-by: Eric Paris Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'net/ipv4/tcp_output.c') diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 05b1ecf36763..bb8f547fc7d2 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2592,6 +2592,7 @@ int tcp_connect(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *buff; + int err; tcp_connect_init(sk); @@ -2614,7 +2615,9 @@ int tcp_connect(struct sock *sk) sk->sk_wmem_queued += buff->truesize; sk_mem_charge(sk, buff->truesize); tp->packets_out += tcp_skb_pcount(buff); - tcp_transmit_skb(sk, buff, 1, sk->sk_allocation); + err = tcp_transmit_skb(sk, buff, 1, sk->sk_allocation); + if (err == -ECONNREFUSED) + return err; /* We change tp->snd_nxt after the tcp_transmit_skb() call * in order to make this packet get counted in tcpOutSegs. -- cgit v1.2.3 From 3853b5841c01a3f492fe137afaad9c209e5162c6 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Sun, 21 Nov 2010 13:17:29 +0000 Subject: xps: Improvements in TX queue selection In dev_pick_tx, don't do work in calculating queue index or setting the index in the sock unless the device has more than one queue. This allows the sock to be set only with a queue index of a multi-queue device which is desirable if device are stacked like in a tunnel. We also allow the mapping of a socket to queue to be changed. To maintain in order packet transmission a flag (ooo_okay) has been added to the sk_buff structure. If a transport layer sets this flag on a packet, the transmit queue can be changed for the socket. Presumably, the transport would set this if there was no possbility of creating OOO packets (for instance, there are no packets in flight for the socket). This patch includes the modification in TCP output for setting this flag. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'net/ipv4/tcp_output.c') diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index bb8f547fc7d2..5f29b2e20e23 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -822,8 +822,11 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, &md5); tcp_header_size = tcp_options_size + sizeof(struct tcphdr); - if (tcp_packets_in_flight(tp) == 0) + if (tcp_packets_in_flight(tp) == 0) { tcp_ca_event(sk, CA_EVENT_TX_START); + skb->ooo_okay = 1; + } else + skb->ooo_okay = 0; skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); -- cgit v1.2.3 From 97b1ce25e8fc27f74703537ec09d4996c7a6e38a Mon Sep 17 00:00:00 2001 From: Shan Wei Date: Wed, 1 Dec 2010 18:04:50 +0000 Subject: tcp: use TCP_BASE_MSS to set basic mss value TCP_BASE_MSS is defined, but not used. commit 5d424d5a introduce this macro, so use it to initial sysctl_tcp_base_mss. commit 5d424d5a674f782d0659a3b66d951f412901faee Author: John Heffner Date: Mon Mar 20 17:53:41 2006 -0800 [TCP]: MTU probing Signed-off-by: Shan Wei Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv4/tcp_output.c') diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 5f29b2e20e23..749b6498588e 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -55,7 +55,7 @@ int sysctl_tcp_workaround_signed_windows __read_mostly = 0; int sysctl_tcp_tso_win_divisor __read_mostly = 3; int sysctl_tcp_mtu_probing __read_mostly = 0; -int sysctl_tcp_base_mss __read_mostly = 512; +int sysctl_tcp_base_mss __read_mostly = TCP_BASE_MSS; /* By default, RFC2861 behavior. */ int sysctl_tcp_slow_start_after_idle __read_mostly = 1; -- cgit v1.2.3 From 0dbaee3b37e118a96bb7b8eb0d9bbaeeb46264be Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 13 Dec 2010 12:52:14 -0800 Subject: net: Abstract default ADVMSS behind an accessor. Make all RTAX_ADVMSS metric accesses go through a new helper function, dst_metric_advmss(). Leave the actual default metric as "zero" in the real metric slot, and compute the actual default value dynamically via a new dst_ops AF specific callback. For stacked IPSEC routes, we use the advmss of the path which preserves existing behavior. Unlike ipv4/ipv6, DecNET ties the advmss to the mtu and thus updates advmss on pmtu updates. This inconsistency in advmss handling results in more raw metric accesses than I wish we ended up with. Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 14 +++++++++----- 1 file changed, 9 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 97041f24cd27..2d390669d406 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -119,9 +119,13 @@ static __u16 tcp_advertise_mss(struct sock *sk) struct dst_entry *dst = __sk_dst_get(sk); int mss = tp->advmss; - if (dst && dst_metric(dst, RTAX_ADVMSS) < mss) { - mss = dst_metric(dst, RTAX_ADVMSS); - tp->advmss = mss; + if (dst) { + unsigned int metric = dst_metric_advmss(dst); + + if (metric < mss) { + mss = metric; + tp->advmss = mss; + } } return (__u16)mss; @@ -2422,7 +2426,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, skb_dst_set(skb, dst_clone(dst)); - mss = dst_metric(dst, RTAX_ADVMSS); + mss = dst_metric_advmss(dst); if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss) mss = tp->rx_opt.user_mss; @@ -2556,7 +2560,7 @@ static void tcp_connect_init(struct sock *sk) if (!tp->window_clamp) tp->window_clamp = dst_metric(dst, RTAX_WINDOW); - tp->advmss = dst_metric(dst, RTAX_ADVMSS); + tp->advmss = dst_metric_advmss(dst); if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < tp->advmss) tp->advmss = tp->rx_opt.user_mss; -- cgit v1.2.3 From 356f039822b8d802138f7121c80d2a9286976dbd Mon Sep 17 00:00:00 2001 From: Nandita Dukkipati Date: Mon, 20 Dec 2010 14:15:56 +0000 Subject: TCP: increase default initial receive window. This patch changes the default initial receive window to 10 mss (defined constant). The default window is limited to the maximum of 10*1460 and 2*mss (when mss > 1460). draft-ietf-tcpm-initcwnd-00 is a proposal to the IETF that recommends increasing TCP's initial congestion window to 10 mss or about 15KB. Leading up to this proposal were several large-scale live Internet experiments with an initial congestion window of 10 mss (IW10), where we showed that the average latency of HTTP responses improved by approximately 10%. This was accompanied by a slight increase in retransmission rate (0.5%), most of which is coming from applications opening multiple simultaneous connections. To understand the extreme worst case scenarios, and fairness issues (IW10 versus IW3), we further conducted controlled testbed experiments. We came away finding minimal negative impact even under low link bandwidths (dial-ups) and small buffers. These results are extremely encouraging to adopting IW10. However, an initial congestion window of 10 mss is useless unless a TCP receiver advertises an initial receive window of at least 10 mss. Fortunately, in the large-scale Internet experiments we found that most widely used operating systems advertised large initial receive windows of 64KB, allowing us to experiment with a wide range of initial congestion windows. Linux systems were among the few exceptions that advertised a small receive window of 6KB. The purpose of this patch is to fix this shortcoming. References: 1. A comprehensive list of all IW10 references to date. http://code.google.com/speed/protocols/tcpm-IW10.html 2. Paper describing results from large-scale Internet experiments with IW10. http://ccr.sigcomm.org/drupal/?q=node/621 3. Controlled testbed experiments under worst case scenarios and a fairness study. http://www.ietf.org/proceedings/79/slides/tcpm-0.pdf 4. Raw test data from testbed experiments (Linux senders/receivers) with initial congestion and receive windows of both 10 mss. http://research.csc.ncsu.edu/netsrv/?q=content/iw10 5. Internet-Draft. Increasing TCP's Initial Window. https://datatracker.ietf.org/doc/draft-ietf-tcpm-initcwnd/ Signed-off-by: Nandita Dukkipati Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 11 ++++++++--- 1 file changed, 8 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 2d390669d406..dc7c096ddfef 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -228,10 +228,15 @@ void tcp_select_initial_window(int __space, __u32 mss, } } - /* Set initial window to value enough for senders, following RFC5681. */ + /* Set initial window to a value enough for senders starting with + * initial congestion window of TCP_DEFAULT_INIT_RCVWND. Place + * a limit on the initial window when mss is larger than 1460. + */ if (mss > (1 << *rcv_wscale)) { - int init_cwnd = rfc3390_bytes_to_packets(mss); - + int init_cwnd = TCP_DEFAULT_INIT_RCVWND; + if (mss > 1460) + init_cwnd = + max_t(u32, (1460 * TCP_DEFAULT_INIT_RCVWND) / mss, 2); /* when initializing use the value from init_rcv_wnd * rather than the default from above */ -- cgit v1.2.3