From e42e24c3cc072088756d84ef07b492ac2a3ae2e5 Mon Sep 17 00:00:00 2001 From: Matvejchikov Ilya Date: Mon, 24 Jul 2017 16:02:12 +0400 Subject: tcp: remove redundant argument from tcp_rcv_established() The last (4th) argument of tcp_rcv_established() is redundant as it always equals to skb->len and the skb itself is always passed as 2th agrument. There is no reason to have it. Signed-off-by: Ilya V. Matveychikov Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a20e7f03d5f7..3a19ea28339f 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1458,7 +1458,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) sk->sk_rx_dst = NULL; } } - tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len); + tcp_rcv_established(sk, skb, tcp_hdr(skb)); return 0; } -- cgit From e7942d0633c47c791ece6afa038be9cf977226de Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sun, 30 Jul 2017 03:57:18 +0200 Subject: tcp: remove prequeue support prequeue is a tcp receive optimization that moves part of rx processing from bh to process context. This only works if the socket being processed belongs to a process that is blocked in recv on that socket. In practice, this doesn't happen anymore that often because nowadays servers tend to use an event driven (epoll) model. Even normal client applications (web browsers) commonly use many tcp connections in parallel. This has measureable impact only in netperf (which uses plain recv and thus allows prequeue use) from host to locally running vm (~4%), however, there were no changes when using netperf between two physical hosts with ixgbe interfaces. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 61 +---------------------------------------------------- 1 file changed, 1 insertion(+), 60 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 3a19ea28339f..a68eb4577d36 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1541,61 +1541,6 @@ void tcp_v4_early_demux(struct sk_buff *skb) } } -/* Packet is added to VJ-style prequeue for processing in process - * context, if a reader task is waiting. Apparently, this exciting - * idea (VJ's mail "Re: query about TCP header on tcp-ip" of 07 Sep 93) - * failed somewhere. Latency? Burstiness? Well, at least now we will - * see, why it failed. 8)8) --ANK - * - */ -bool tcp_prequeue(struct sock *sk, struct sk_buff *skb) -{ - struct tcp_sock *tp = tcp_sk(sk); - - if (sysctl_tcp_low_latency || !tp->ucopy.task) - return false; - - if (skb->len <= tcp_hdrlen(skb) && - skb_queue_len(&tp->ucopy.prequeue) == 0) - return false; - - /* Before escaping RCU protected region, we need to take care of skb - * dst. Prequeue is only enabled for established sockets. - * For such sockets, we might need the skb dst only to set sk->sk_rx_dst - * Instead of doing full sk_rx_dst validity here, let's perform - * an optimistic check. - */ - if (likely(sk->sk_rx_dst)) - skb_dst_drop(skb); - else - skb_dst_force_safe(skb); - - __skb_queue_tail(&tp->ucopy.prequeue, skb); - tp->ucopy.memory += skb->truesize; - if (skb_queue_len(&tp->ucopy.prequeue) >= 32 || - tp->ucopy.memory + atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) { - struct sk_buff *skb1; - - BUG_ON(sock_owned_by_user(sk)); - __NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPPREQUEUEDROPPED, - skb_queue_len(&tp->ucopy.prequeue)); - - while ((skb1 = __skb_dequeue(&tp->ucopy.prequeue)) != NULL) - sk_backlog_rcv(sk, skb1); - - tp->ucopy.memory = 0; - } else if (skb_queue_len(&tp->ucopy.prequeue) == 1) { - wake_up_interruptible_sync_poll(sk_sleep(sk), - POLLIN | POLLRDNORM | POLLRDBAND); - if (!inet_csk_ack_scheduled(sk)) - inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, - (3 * tcp_rto_min(sk)) / 4, - TCP_RTO_MAX); - } - return true; -} -EXPORT_SYMBOL(tcp_prequeue); - bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) { u32 limit = sk->sk_rcvbuf + sk->sk_sndbuf; @@ -1770,8 +1715,7 @@ process: tcp_segs_in(tcp_sk(sk), skb); ret = 0; if (!sock_owned_by_user(sk)) { - if (!tcp_prequeue(sk, skb)) - ret = tcp_v4_do_rcv(sk, skb); + ret = tcp_v4_do_rcv(sk, skb); } else if (tcp_add_backlog(sk, skb)) { goto discard_and_relse; } @@ -1936,9 +1880,6 @@ void tcp_v4_destroy_sock(struct sock *sk) } #endif - /* Clean prequeue, it must be empty really */ - __skb_queue_purge(&tp->ucopy.prequeue); - /* Clean up a referenced TCP bind bucket. */ if (inet_csk(sk)->icsk_bind_hash) inet_put_port(sk); -- cgit From b6690b14386698ce2c19309abad3f17656bdfaea Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sun, 30 Jul 2017 03:57:20 +0200 Subject: tcp: remove low_latency sysctl Was only checked by the removed prequeue code. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a68eb4577d36..9b51663cd5a4 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -85,8 +85,6 @@ #include #include -int sysctl_tcp_low_latency __read_mostly; - #ifdef CONFIG_TCP_MD5SIG static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, __be32 daddr, __be32 saddr, const struct tcphdr *th); -- cgit From 91ed1e666a4ea2e260452a7d7d311ac5ae852cba Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 3 Aug 2017 18:07:06 +0200 Subject: ip/options: explicitly provide net ns to __ip_options_echo() __ip_options_echo() uses the current network namespace, and currently retrives it via skb->dst->dev. This commit adds an explicit 'net' argument to __ip_options_echo() and update all the call sites to provide it, usually via a simpler sock_net(). After this change, __ip_options_echo() no more needs to access skb->dst and we can drop a couple of hack to preserve such info in the rx path. Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 9b51663cd5a4..5f708c85110e 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1267,7 +1267,7 @@ static void tcp_v4_init_req(struct request_sock *req, sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr); sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr); - ireq->opt = tcp_v4_save_options(skb); + ireq->opt = tcp_v4_save_options(sock_net(sk_listener), skb); } static struct dst_entry *tcp_v4_route_req(const struct sock *sk, -- cgit From 3fa6f616a7a4d0bdf4d877d530456d8a5c3b109b Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 7 Aug 2017 08:44:17 -0700 Subject: net: ipv4: add second dif to inet socket lookups Add a second device index, sdif, to inet socket lookups. sdif is the index for ingress devices enslaved to an l3mdev. It allows the lookups to consider the enslaved device as well as the L3 domain when searching for a socket. TCP moves the data in the cb. Prior to tcp_v4_rcv (e.g., early demux) the ingress index is obtained from IPCB using inet_sdif and after the cb move in tcp_v4_rcv the tcp_v4_sdif helper is used. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 5f708c85110e..c8784ab37852 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -383,7 +383,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) sk = __inet_lookup_established(net, &tcp_hashinfo, iph->daddr, th->dest, iph->saddr, ntohs(th->source), - inet_iif(icmp_skb)); + inet_iif(icmp_skb), 0); if (!sk) { __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); return; @@ -659,7 +659,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) sk1 = __inet_lookup_listener(net, &tcp_hashinfo, NULL, 0, ip_hdr(skb)->saddr, th->source, ip_hdr(skb)->daddr, - ntohs(th->source), inet_iif(skb)); + ntohs(th->source), inet_iif(skb), + tcp_v4_sdif(skb)); /* don't send rst if it can't find key */ if (!sk1) goto out; @@ -1523,7 +1524,7 @@ void tcp_v4_early_demux(struct sk_buff *skb) sk = __inet_lookup_established(dev_net(skb->dev), &tcp_hashinfo, iph->saddr, th->source, iph->daddr, ntohs(th->dest), - skb->skb_iif); + skb->skb_iif, inet_sdif(skb)); if (sk) { skb->sk = sk; skb->destructor = sock_edemux; @@ -1588,6 +1589,7 @@ EXPORT_SYMBOL(tcp_filter); int tcp_v4_rcv(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); + int sdif = inet_sdif(skb); const struct iphdr *iph; const struct tcphdr *th; bool refcounted; @@ -1638,7 +1640,7 @@ int tcp_v4_rcv(struct sk_buff *skb) lookup: sk = __inet_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th), th->source, - th->dest, &refcounted); + th->dest, sdif, &refcounted); if (!sk) goto no_tcp_socket; @@ -1766,7 +1768,8 @@ do_time_wait: __tcp_hdrlen(th), iph->saddr, th->source, iph->daddr, th->dest, - inet_iif(skb)); + inet_iif(skb), + sdif); if (sk2) { inet_twsk_deschedule_put(inet_twsk(sk)); sk = sk2; -- cgit From 98aaa913b4ed250324429f0a9e6d5f77a3b5276c Mon Sep 17 00:00:00 2001 From: Mike Maloney Date: Tue, 22 Aug 2017 17:08:48 -0400 Subject: tcp: Extend SOF_TIMESTAMPING_RX_SOFTWARE to TCP recvmsg When SOF_TIMESTAMPING_RX_SOFTWARE is enabled for tcp sockets, return the timestamp corresponding to the highest sequence number data returned. Previously the skb->tstamp is overwritten when a TCP packet is placed in the out of order queue. While the packet is in the ooo queue, save the timestamp in the TCB_SKB_CB. This space is shared with the gso_* options which are only used on the tx path, and a previously unused 4 byte hole. When skbs are coalesced either in the sk_receive_queue or the out_of_order_queue always choose the timestamp of the appended skb to maintain the invariant of returning the timestamp of the last byte in the recvmsg buffer. Signed-off-by: Mike Maloney Acked-by: Willem de Bruijn Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 5af8b809dfbc..a63486afa7a7 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1637,6 +1637,8 @@ int tcp_v4_rcv(struct sk_buff *skb) TCP_SKB_CB(skb)->tcp_tw_isn = 0; TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph); TCP_SKB_CB(skb)->sacked = 0; + TCP_SKB_CB(skb)->has_rxtstamp = + skb->tstamp || skb_hwtstamps(skb)->hwtstamp; lookup: sk = __inet_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th), th->source, -- cgit