From 0536fcc039a8926ec12ec587f41a83f7acafeb82 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Sep 2015 07:42:52 -0700 Subject: tcp: prepare fastopen code for upcoming listener changes While auditing TCP stack for upcoming 'lockless' listener changes, I found I had to change fastopen_init_queue() to properly init the object before publishing it. Otherwise an other cpu could try to lock the spinlock before it gets properly initialized. Instead of adding appropriate barriers, just remove dynamic memory allocations : - Structure is 28 bytes on 64bit arches. Using additional 8 bytes for holding a pointer seems overkill. - Two listeners can share same cache line and performance would suffer. If we really want to save few bytes, we would instead dynamically allocate whole struct request_sock_queue in the future. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) (limited to 'net/ipv4/tcp.c') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b8b8fa184f75..3c96fa87ff9e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2253,13 +2253,6 @@ int tcp_disconnect(struct sock *sk, int flags) } EXPORT_SYMBOL(tcp_disconnect); -void tcp_sock_destruct(struct sock *sk) -{ - inet_sock_destruct(sk); - - kfree(inet_csk(sk)->icsk_accept_queue.fastopenq); -} - static inline bool tcp_can_repair_sock(const struct sock *sk) { return ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN) && @@ -2581,7 +2574,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, TCPF_LISTEN))) { tcp_fastopen_init_key_once(true); - err = fastopen_init_queue(sk, val); + fastopen_queue_tune(sk, val); } else { err = -EINVAL; } @@ -2849,10 +2842,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_FASTOPEN: - if (icsk->icsk_accept_queue.fastopenq) - val = icsk->icsk_accept_queue.fastopenq->max_qlen; - else - val = 0; + val = icsk->icsk_accept_queue.fastopenq.max_qlen; break; case TCP_TIMESTAMP: -- cgit From 686a562449af96a0e8c18c6f1b87b47ff8c36de8 Mon Sep 17 00:00:00 2001 From: Yuvaraja Mariappan Date: Tue, 6 Oct 2015 10:53:29 -0700 Subject: net: ipv4: tcp.c Fixed an assignment coding style issue Fixed an assignment coding style issue Signed-off-by: Yuvaraja Mariappan Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) (limited to 'net/ipv4/tcp.c') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3c96fa87ff9e..ac1bdbb50352 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -900,7 +900,8 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, */ if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) && !tcp_passive_fastopen(sk)) { - if ((err = sk_stream_wait_connect(sk, &timeo)) != 0) + err = sk_stream_wait_connect(sk, &timeo); + if (err != 0) goto out_err; } @@ -967,7 +968,8 @@ new_segment: copied += copy; offset += copy; - if (!(size -= copy)) { + size -= copy; + if (!size) { tcp_tx_timestamp(sk, skb); goto out; } @@ -988,7 +990,8 @@ wait_for_memory: tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH, size_goal); - if ((err = sk_stream_wait_memory(sk, &timeo)) != 0) + err = sk_stream_wait_memory(sk, &timeo); + if (err != 0) goto do_error; mss_now = tcp_send_mss(sk, &size_goal, flags); @@ -1111,7 +1114,8 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) */ if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) && !tcp_passive_fastopen(sk)) { - if ((err = sk_stream_wait_connect(sk, &timeo)) != 0) + err = sk_stream_wait_connect(sk, &timeo); + if (err != 0) goto do_error; } @@ -1267,7 +1271,8 @@ wait_for_memory: tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH, size_goal); - if ((err = sk_stream_wait_memory(sk, &timeo)) != 0) + err = sk_stream_wait_memory(sk, &timeo); + if (err != 0) goto do_error; mss_now = tcp_send_mss(sk, &size_goal, flags); @@ -1767,7 +1772,8 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, /* __ Restore normal policy in scheduler __ */ - if ((chunk = len - tp->ucopy.len) != 0) { + chunk = len - tp->ucopy.len; + if (chunk != 0) { NET_ADD_STATS_USER(sock_net(sk), LINUX_MIB_TCPDIRECTCOPYFROMBACKLOG, chunk); len -= chunk; copied += chunk; @@ -1778,7 +1784,8 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, do_prequeue: tcp_prequeue_process(sk); - if ((chunk = len - tp->ucopy.len) != 0) { + chunk = len - tp->ucopy.len; + if (chunk != 0) { NET_ADD_STATS_USER(sock_net(sk), LINUX_MIB_TCPDIRECTCOPYFROMPREQUEUE, chunk); len -= chunk; copied += chunk; @@ -2230,7 +2237,8 @@ int tcp_disconnect(struct sock *sk, int flags) sk->sk_shutdown = 0; sock_reset_flag(sk, SOCK_DONE); tp->srtt_us = 0; - if ((tp->write_seq += tp->max_window + 2) == 0) + tp->write_seq += tp->max_window + 2; + if (tp->write_seq == 0) tp->write_seq = 1; icsk->icsk_backoff = 0; tp->snd_cwnd = 2; -- cgit From f672258391b42a5c7cc2732c9c063e56a85c8dbe Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Fri, 16 Oct 2015 21:57:42 -0700 Subject: tcp: track min RTT using windowed min-filter Kathleen Nichols' algorithm for tracking the minimum RTT of a data stream over some measurement window. It uses constant space and constant time per update. Yet it almost always delivers the same minimum as an implementation that has to keep all the data in the window. The measurement window is tunable via sysctl.net.ipv4.tcp_min_rtt_wlen with a default value of 5 minutes. The algorithm keeps track of the best, 2nd best & 3rd best min values, maintaining an invariant that the measurement time of the n'th best >= n-1'th best. It also makes sure that the three values are widely separated in the time window since that bounds the worse case error when that data is monotonically increasing over the window. Upon getting a new min, we can forget everything earlier because it has no value - the new min is less than everything else in the window by definition and it's the most recent. So we restart fresh on every new min and overwrites the 2nd & 3rd choices. The same property holds for the 2nd & 3rd best. Therefore we have to maintain two invariants to maximize the information in the samples, one on values (1st.v <= 2nd.v <= 3rd.v) and the other on times (now-win <=1st.t <= 2nd.t <= 3rd.t <= now). These invariants determine the structure of the code The RTT input to the windowed filter is the minimum RTT measured from ACK or SACK, or as the last resort from TCP timestamps. The accessor tcp_min_rtt() returns the minimum RTT seen in the window. ~0U indicates it is not available. The minimum is 1usec even if the true RTT is below that. Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/ipv4/tcp.c') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index ac1bdbb50352..0cfa7c0c1e80 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -388,6 +388,7 @@ void tcp_init_sock(struct sock *sk) icsk->icsk_rto = TCP_TIMEOUT_INIT; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); + tp->rtt_min[0].rtt = ~0U; /* So many TCP implementations out there (incorrectly) count the * initial SYN frame in their delayed-ACK and congestion control -- cgit