From 8ef9ba4d666614497a057d09b0a6eafc1e34eadf Mon Sep 17 00:00:00 2001 From: Oliver Herms Date: Tue, 3 Nov 2020 11:41:33 +0100 Subject: IPv6: Set SIT tunnel hard_header_len to zero Due to the legacy usage of hard_header_len for SIT tunnels while already using infrastructure from net/ipv4/ip_tunnel.c the calculation of the path MTU in tnl_update_pmtu is incorrect. This leads to unnecessary creation of MTU exceptions for any flow going over a SIT tunnel. As SIT tunnels do not have a header themsevles other than their transport (L3, L2) headers we're leaving hard_header_len set to zero as tnl_update_pmtu is already taking care of the transport headers sizes. This will also help avoiding unnecessary IPv6 GC runs and spinlock contention seen when using SIT tunnels and for more than net.ipv6.route.gc_thresh flows. Fixes: c54419321455 ("GRE: Refactor GRE tunneling code.") Signed-off-by: Oliver Herms Acked-by: Willem de Bruijn Link: https://lore.kernel.org/r/20201103104133.GA1573211@tws Signed-off-by: Jakub Kicinski --- net/ipv6/sit.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 5e2c34c0ac97..5e7983cb6154 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1128,7 +1128,6 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev) if (tdev && !netif_is_l3_master(tdev)) { int t_hlen = tunnel->hlen + sizeof(struct iphdr); - dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr); dev->mtu = tdev->mtu - t_hlen; if (dev->mtu < IPV6_MIN_MTU) dev->mtu = IPV6_MIN_MTU; @@ -1426,7 +1425,6 @@ static void ipip6_tunnel_setup(struct net_device *dev) dev->priv_destructor = ipip6_dev_free; dev->type = ARPHRD_SIT; - dev->hard_header_len = LL_MAX_HEADER + t_hlen; dev->mtu = ETH_DATA_LEN - t_hlen; dev->min_mtu = IPV6_MIN_MTU; dev->max_mtu = IP6_MAX_MTU - t_hlen; -- cgit v1.2.3 From 909172a149749242990a6e64cb55d55460d4e417 Mon Sep 17 00:00:00 2001 From: Mao Wenan Date: Tue, 10 Nov 2020 08:16:31 +0800 Subject: net: Update window_clamp if SOCK_RCVBUF is set When net.ipv4.tcp_syncookies=1 and syn flood is happened, cookie_v4_check or cookie_v6_check tries to redo what tcp_v4_send_synack or tcp_v6_send_synack did, rsk_window_clamp will be changed if SOCK_RCVBUF is set, which will make rcv_wscale is different, the client still operates with initial window scale and can overshot granted window, the client use the initial scale but local server use new scale to advertise window value, and session work abnormally. Fixes: e88c64f0a425 ("tcp: allow effective reduction of TCP's rcv-buffer via setsockopt") Signed-off-by: Mao Wenan Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/1604967391-123737-1-git-send-email-wenan.mao@linux.alibaba.com Signed-off-by: Jakub Kicinski --- net/ipv4/syncookies.c | 9 +++++++-- net/ipv6/syncookies.c | 10 ++++++++-- 2 files changed, 15 insertions(+), 4 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 6ac473b47f30..00dc3f943c80 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -331,7 +331,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) __u32 cookie = ntohl(th->ack_seq) - 1; struct sock *ret = sk; struct request_sock *req; - int mss; + int full_space, mss; struct rtable *rt; __u8 rcv_wscale; struct flowi4 fl4; @@ -427,8 +427,13 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) /* Try to redo what tcp_v4_send_synack did. */ req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW); + /* limit the window selection if the user enforce a smaller rx buffer */ + full_space = tcp_full_space(sk); + if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && + (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0)) + req->rsk_window_clamp = full_space; - tcp_select_initial_window(sk, tcp_full_space(sk), req->mss, + tcp_select_initial_window(sk, full_space, req->mss, &req->rsk_rcv_wnd, &req->rsk_window_clamp, ireq->wscale_ok, &rcv_wscale, dst_metric(&rt->dst, RTAX_INITRWND)); diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index e796a64be308..9b6cae1e49d9 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -136,7 +136,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) __u32 cookie = ntohl(th->ack_seq) - 1; struct sock *ret = sk; struct request_sock *req; - int mss; + int full_space, mss; struct dst_entry *dst; __u8 rcv_wscale; u32 tsoff = 0; @@ -241,7 +241,13 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) } req->rsk_window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW); - tcp_select_initial_window(sk, tcp_full_space(sk), req->mss, + /* limit the window selection if the user enforce a smaller rx buffer */ + full_space = tcp_full_space(sk); + if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && + (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0)) + req->rsk_window_clamp = full_space; + + tcp_select_initial_window(sk, full_space, req->mss, &req->rsk_rcv_wnd, &req->rsk_window_clamp, ireq->wscale_ok, &rcv_wscale, dst_metric(dst, RTAX_INITRWND)); -- cgit v1.2.3 From 55e729889bb07d68ab071660ce3f5e7a7872ebe8 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Wed, 11 Nov 2020 20:45:38 +0000 Subject: net: udp: fix IP header access and skb lookup on Fast/frag0 UDP GRO udp{4,6}_lib_lookup_skb() use ip{,v6}_hdr() to get IP header of the packet. While it's probably OK for non-frag0 paths, this helpers will also point to junk on Fast/frag0 GRO when all headers are located in frags. As a result, sk/skb lookup may fail or give wrong results. To support both GRO modes, skb_gro_network_header() might be used. To not modify original functions, add private versions of udp{4,6}_lib_lookup_skb() only to perform correct sk lookups on GRO. Present since the introduction of "application-level" UDP GRO in 4.7-rc1. Misc: replace totally unneeded ternaries with plain ifs. Fixes: a6024562ffd7 ("udp: Add GRO functions to UDP socket") Suggested-by: Willem de Bruijn Cc: Eric Dumazet Signed-off-by: Alexander Lobakin Acked-by: Willem de Bruijn Signed-off-by: Jakub Kicinski --- net/ipv4/udp_offload.c | 17 +++++++++++++++-- net/ipv6/udp_offload.c | 17 +++++++++++++++-- 2 files changed, 30 insertions(+), 4 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 13740e9fe6ec..c62805cd3131 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -500,12 +500,22 @@ out: } EXPORT_SYMBOL(udp_gro_receive); +static struct sock *udp4_gro_lookup_skb(struct sk_buff *skb, __be16 sport, + __be16 dport) +{ + const struct iphdr *iph = skb_gro_network_header(skb); + + return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport, + iph->daddr, dport, inet_iif(skb), + inet_sdif(skb), &udp_table, NULL); +} + INDIRECT_CALLABLE_SCOPE struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); + struct sock *sk = NULL; struct sk_buff *pp; - struct sock *sk; if (unlikely(!uh)) goto flush; @@ -523,7 +533,10 @@ struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb) skip: NAPI_GRO_CB(skb)->is_ipv6 = 0; rcu_read_lock(); - sk = static_branch_unlikely(&udp_encap_needed_key) ? udp4_lib_lookup_skb(skb, uh->source, uh->dest) : NULL; + + if (static_branch_unlikely(&udp_encap_needed_key)) + sk = udp4_gro_lookup_skb(skb, uh->source, uh->dest); + pp = udp_gro_receive(head, skb, uh, sk); rcu_read_unlock(); return pp; diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 584157a07759..f9e888d1b9af 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -111,12 +111,22 @@ out: return segs; } +static struct sock *udp6_gro_lookup_skb(struct sk_buff *skb, __be16 sport, + __be16 dport) +{ + const struct ipv6hdr *iph = skb_gro_network_header(skb); + + return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport, + &iph->daddr, dport, inet6_iif(skb), + inet6_sdif(skb), &udp_table, NULL); +} + INDIRECT_CALLABLE_SCOPE struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); + struct sock *sk = NULL; struct sk_buff *pp; - struct sock *sk; if (unlikely(!uh)) goto flush; @@ -135,7 +145,10 @@ struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb) skip: NAPI_GRO_CB(skb)->is_ipv6 = 1; rcu_read_lock(); - sk = static_branch_unlikely(&udpv6_encap_needed_key) ? udp6_lib_lookup_skb(skb, uh->source, uh->dest) : NULL; + + if (static_branch_unlikely(&udpv6_encap_needed_key)) + sk = udp6_gro_lookup_skb(skb, uh->source, uh->dest); + pp = udp_gro_receive(head, skb, uh, sk); rcu_read_unlock(); return pp; -- cgit v1.2.3