From f564650106a6e85702660fefd59fdff0877ab46a Mon Sep 17 00:00:00 2001 From: Flavio Leitner Date: Wed, 27 Jun 2018 10:34:25 -0300 Subject: [PATCH 1/2] netfilter: check if the socket netns is correct. Netfilter assumes that if the socket is present in the skb, then it can be used because that reference is cleaned up while the skb is crossing netns. We want to change that to preserve the socket reference in a future patch, so this is a preparation updating netfilter to check if the socket netns matches before use it. Signed-off-by: Flavio Leitner Acked-by: Florian Westphal Signed-off-by: David S. Miller --- include/net/netfilter/nf_log.h | 3 ++- net/ipv4/netfilter/nf_log_ipv4.c | 8 ++++---- net/ipv6/netfilter/nf_log_ipv6.c | 8 ++++---- net/netfilter/nf_conntrack_broadcast.c | 2 +- net/netfilter/nf_log_common.c | 5 +++-- net/netfilter/nf_nat_core.c | 6 +++++- net/netfilter/nft_meta.c | 9 ++++++--- net/netfilter/nft_socket.c | 5 ++++- net/netfilter/xt_cgroup.c | 6 ++++-- net/netfilter/xt_owner.c | 2 +- net/netfilter/xt_recent.c | 3 ++- net/netfilter/xt_socket.c | 8 ++++++++ 12 files changed, 44 insertions(+), 21 deletions(-) diff --git a/include/net/netfilter/nf_log.h b/include/net/netfilter/nf_log.h index e811ac07ea94..0d3920896d50 100644 --- a/include/net/netfilter/nf_log.h +++ b/include/net/netfilter/nf_log.h @@ -106,7 +106,8 @@ int nf_log_dump_udp_header(struct nf_log_buf *m, const struct sk_buff *skb, int nf_log_dump_tcp_header(struct nf_log_buf *m, const struct sk_buff *skb, u8 proto, int fragment, unsigned int offset, unsigned int logflags); -void nf_log_dump_sk_uid_gid(struct nf_log_buf *m, struct sock *sk); +void nf_log_dump_sk_uid_gid(struct net *net, struct nf_log_buf *m, + struct sock *sk); void nf_log_dump_packet_common(struct nf_log_buf *m, u_int8_t pf, unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, diff --git a/net/ipv4/netfilter/nf_log_ipv4.c b/net/ipv4/netfilter/nf_log_ipv4.c index 4388de0e5380..1e6f28c97d3a 100644 --- a/net/ipv4/netfilter/nf_log_ipv4.c +++ b/net/ipv4/netfilter/nf_log_ipv4.c @@ -35,7 +35,7 @@ static const struct nf_loginfo default_loginfo = { }; /* One level of recursion won't kill us */ -static void dump_ipv4_packet(struct nf_log_buf *m, +static void dump_ipv4_packet(struct net *net, struct nf_log_buf *m, const struct nf_loginfo *info, const struct sk_buff *skb, unsigned int iphoff) { @@ -183,7 +183,7 @@ static void dump_ipv4_packet(struct nf_log_buf *m, /* Max length: 3+maxlen */ if (!iphoff) { /* Only recurse once. */ nf_log_buf_add(m, "["); - dump_ipv4_packet(m, info, skb, + dump_ipv4_packet(net, m, info, skb, iphoff + ih->ihl*4+sizeof(_icmph)); nf_log_buf_add(m, "] "); } @@ -251,7 +251,7 @@ static void dump_ipv4_packet(struct nf_log_buf *m, /* Max length: 15 "UID=4294967295 " */ if ((logflags & NF_LOG_UID) && !iphoff) - nf_log_dump_sk_uid_gid(m, skb->sk); + nf_log_dump_sk_uid_gid(net, m, skb->sk); /* Max length: 16 "MARK=0xFFFFFFFF " */ if (!iphoff && skb->mark) @@ -333,7 +333,7 @@ static void nf_log_ip_packet(struct net *net, u_int8_t pf, if (in != NULL) dump_ipv4_mac_header(m, loginfo, skb); - dump_ipv4_packet(m, loginfo, skb, 0); + dump_ipv4_packet(net, m, loginfo, skb, 0); nf_log_buf_close(m); } diff --git a/net/ipv6/netfilter/nf_log_ipv6.c b/net/ipv6/netfilter/nf_log_ipv6.c index b397a8fe88b9..c6bf580d0f33 100644 --- a/net/ipv6/netfilter/nf_log_ipv6.c +++ b/net/ipv6/netfilter/nf_log_ipv6.c @@ -36,7 +36,7 @@ static const struct nf_loginfo default_loginfo = { }; /* One level of recursion won't kill us */ -static void dump_ipv6_packet(struct nf_log_buf *m, +static void dump_ipv6_packet(struct net *net, struct nf_log_buf *m, const struct nf_loginfo *info, const struct sk_buff *skb, unsigned int ip6hoff, int recurse) @@ -258,7 +258,7 @@ static void dump_ipv6_packet(struct nf_log_buf *m, /* Max length: 3+maxlen */ if (recurse) { nf_log_buf_add(m, "["); - dump_ipv6_packet(m, info, skb, + dump_ipv6_packet(net, m, info, skb, ptr + sizeof(_icmp6h), 0); nf_log_buf_add(m, "] "); } @@ -278,7 +278,7 @@ static void dump_ipv6_packet(struct nf_log_buf *m, /* Max length: 15 "UID=4294967295 " */ if ((logflags & NF_LOG_UID) && recurse) - nf_log_dump_sk_uid_gid(m, skb->sk); + nf_log_dump_sk_uid_gid(net, m, skb->sk); /* Max length: 16 "MARK=0xFFFFFFFF " */ if (recurse && skb->mark) @@ -365,7 +365,7 @@ static void nf_log_ip6_packet(struct net *net, u_int8_t pf, if (in != NULL) dump_ipv6_mac_header(m, loginfo, skb); - dump_ipv6_packet(m, loginfo, skb, skb_network_offset(skb), 1); + dump_ipv6_packet(net, m, loginfo, skb, skb_network_offset(skb), 1); nf_log_buf_close(m); } diff --git a/net/netfilter/nf_conntrack_broadcast.c b/net/netfilter/nf_conntrack_broadcast.c index a1086bdec242..5423b197d98a 100644 --- a/net/netfilter/nf_conntrack_broadcast.c +++ b/net/netfilter/nf_conntrack_broadcast.c @@ -32,7 +32,7 @@ int nf_conntrack_broadcast_help(struct sk_buff *skb, __be32 mask = 0; /* we're only interested in locally generated packets */ - if (skb->sk == NULL) + if (skb->sk == NULL || !net_eq(nf_ct_net(ct), sock_net(skb->sk))) goto out; if (rt == NULL || !(rt->rt_flags & RTCF_BROADCAST)) goto out; diff --git a/net/netfilter/nf_log_common.c b/net/netfilter/nf_log_common.c index dc61399e30be..a8c5c846aec1 100644 --- a/net/netfilter/nf_log_common.c +++ b/net/netfilter/nf_log_common.c @@ -132,9 +132,10 @@ int nf_log_dump_tcp_header(struct nf_log_buf *m, const struct sk_buff *skb, } EXPORT_SYMBOL_GPL(nf_log_dump_tcp_header); -void nf_log_dump_sk_uid_gid(struct nf_log_buf *m, struct sock *sk) +void nf_log_dump_sk_uid_gid(struct net *net, struct nf_log_buf *m, + struct sock *sk) { - if (!sk || !sk_fullsock(sk)) + if (!sk || !sk_fullsock(sk) || !net_eq(net, sock_net(sk))) return; read_lock_bh(&sk->sk_callback_lock); diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 46f9df99d276..86df2a1666fd 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -108,6 +108,7 @@ int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family) struct flowi fl; unsigned int hh_len; struct dst_entry *dst; + struct sock *sk = skb->sk; int err; err = xfrm_decode_session(skb, &fl, family); @@ -119,7 +120,10 @@ int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family) dst = ((struct xfrm_dst *)dst)->route; dst_hold(dst); - dst = xfrm_lookup(net, dst, &fl, skb->sk, 0); + if (sk && !net_eq(net, sock_net(sk))) + sk = NULL; + + dst = xfrm_lookup(net, dst, &fl, sk, 0); if (IS_ERR(dst)) return PTR_ERR(dst); diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 1105a23bda5e..2b94dcc43456 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -107,7 +107,8 @@ static void nft_meta_get_eval(const struct nft_expr *expr, break; case NFT_META_SKUID: sk = skb_to_full_sk(skb); - if (!sk || !sk_fullsock(sk)) + if (!sk || !sk_fullsock(sk) || + !net_eq(nft_net(pkt), sock_net(sk))) goto err; read_lock_bh(&sk->sk_callback_lock); @@ -123,7 +124,8 @@ static void nft_meta_get_eval(const struct nft_expr *expr, break; case NFT_META_SKGID: sk = skb_to_full_sk(skb); - if (!sk || !sk_fullsock(sk)) + if (!sk || !sk_fullsock(sk) || + !net_eq(nft_net(pkt), sock_net(sk))) goto err; read_lock_bh(&sk->sk_callback_lock); @@ -214,7 +216,8 @@ static void nft_meta_get_eval(const struct nft_expr *expr, #ifdef CONFIG_CGROUP_NET_CLASSID case NFT_META_CGROUP: sk = skb_to_full_sk(skb); - if (!sk || !sk_fullsock(sk)) + if (!sk || !sk_fullsock(sk) || + !net_eq(nft_net(pkt), sock_net(sk))) goto err; *dest = sock_cgroup_classid(&sk->sk_cgrp_data); break; diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index 74e1b3bd6954..998c2b546f6d 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -23,6 +23,9 @@ static void nft_socket_eval(const struct nft_expr *expr, struct sock *sk = skb->sk; u32 *dest = ®s->data[priv->dreg]; + if (sk && !net_eq(nft_net(pkt), sock_net(sk))) + sk = NULL; + if (!sk) switch(nft_pf(pkt)) { case NFPROTO_IPV4: @@ -39,7 +42,7 @@ static void nft_socket_eval(const struct nft_expr *expr, return; } - if(!sk) { + if (!sk) { nft_reg_store8(dest, 0); return; } diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c index 7df2dece57d3..5d92e1781980 100644 --- a/net/netfilter/xt_cgroup.c +++ b/net/netfilter/xt_cgroup.c @@ -72,8 +72,9 @@ static bool cgroup_mt_v0(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_cgroup_info_v0 *info = par->matchinfo; + struct sock *sk = skb->sk; - if (skb->sk == NULL || !sk_fullsock(skb->sk)) + if (!sk || !sk_fullsock(sk) || !net_eq(xt_net(par), sock_net(sk))) return false; return (info->id == sock_cgroup_classid(&skb->sk->sk_cgrp_data)) ^ @@ -85,8 +86,9 @@ static bool cgroup_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) const struct xt_cgroup_info_v1 *info = par->matchinfo; struct sock_cgroup_data *skcd = &skb->sk->sk_cgrp_data; struct cgroup *ancestor = info->priv; + struct sock *sk = skb->sk; - if (!skb->sk || !sk_fullsock(skb->sk)) + if (!sk || !sk_fullsock(sk) || !net_eq(xt_net(par), sock_net(sk))) return false; if (ancestor) diff --git a/net/netfilter/xt_owner.c b/net/netfilter/xt_owner.c index 3d705c688a27..46686fb73784 100644 --- a/net/netfilter/xt_owner.c +++ b/net/netfilter/xt_owner.c @@ -67,7 +67,7 @@ owner_mt(const struct sk_buff *skb, struct xt_action_param *par) struct sock *sk = skb_to_full_sk(skb); struct net *net = xt_net(par); - if (sk == NULL || sk->sk_socket == NULL) + if (!sk || !sk->sk_socket || !net_eq(net, sock_net(sk))) return (info->match ^ info->invert) == 0; else if (info->match & info->invert & XT_OWNER_SOCKET) /* diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 07085c22b19c..f44de4bc2100 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -265,7 +265,8 @@ recent_mt(const struct sk_buff *skb, struct xt_action_param *par) } /* use TTL as seen before forwarding */ - if (xt_out(par) != NULL && skb->sk == NULL) + if (xt_out(par) != NULL && + (!skb->sk || !net_eq(net, sock_net(skb->sk)))) ttl++; spin_lock_bh(&recent_lock); diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 5c0779c4fa3c..0472f3472842 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -56,8 +56,12 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, struct sk_buff *pskb = (struct sk_buff *)skb; struct sock *sk = skb->sk; + if (!net_eq(xt_net(par), sock_net(sk))) + sk = NULL; + if (!sk) sk = nf_sk_lookup_slow_v4(xt_net(par), skb, xt_in(par)); + if (sk) { bool wildcard; bool transparent = true; @@ -113,8 +117,12 @@ socket_mt6_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par) struct sk_buff *pskb = (struct sk_buff *)skb; struct sock *sk = skb->sk; + if (!net_eq(xt_net(par), sock_net(sk))) + sk = NULL; + if (!sk) sk = nf_sk_lookup_slow_v6(xt_net(par), skb, xt_in(par)); + if (sk) { bool wildcard; bool transparent = true; From 9c4c325252c54b34d53b3d0ffd535182b744e03d Mon Sep 17 00:00:00 2001 From: Flavio Leitner Date: Wed, 27 Jun 2018 10:34:26 -0300 Subject: [PATCH 2/2] skbuff: preserve sock reference when scrubbing the skb. The sock reference is lost when scrubbing the packet and that breaks TSQ (TCP Small Queues) and XPS (Transmit Packet Steering) causing performance impacts of about 50% in a single TCP stream when crossing network namespaces. XPS breaks because the queue mapping stored in the socket is not available, so another random queue might be selected when the stack needs to transmit something like a TCP ACK, or TCP Retransmissions. That causes packet re-ordering and/or performance issues. TSQ breaks because it orphans the packet while it is still in the host, so packets are queued contributing to the buffer bloat problem. Preserving the sock reference fixes both issues. The socket is orphaned anyways in the receiving path before any relevant action and on TX side the netfilter checks if the reference is local before use it. Signed-off-by: Flavio Leitner Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 10 +++++----- net/core/skbuff.c | 1 - 2 files changed, 5 insertions(+), 6 deletions(-) diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index ce8fbf5aa63c..f4c042be0216 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -733,11 +733,11 @@ tcp_limit_output_bytes - INTEGER Controls TCP Small Queue limit per tcp socket. TCP bulk sender tends to increase packets in flight until it gets losses notifications. With SNDBUF autotuning, this can - result in a large amount of packets queued in qdisc/device - on the local machine, hurting latency of other flows, for - typical pfifo_fast qdiscs. - tcp_limit_output_bytes limits the number of bytes on qdisc - or device to reduce artificial RTT/cwnd and reduce bufferbloat. + result in a large amount of packets queued on the local machine + (e.g.: qdiscs, CPU backlog, or device) hurting latency of other + flows, for typical pfifo_fast qdiscs. tcp_limit_output_bytes + limits the number of bytes on qdisc or device to reduce artificial + RTT/cwnd and reduce bufferbloat. Default: 262144 tcp_challenge_ack_limit - INTEGER diff --git a/net/core/skbuff.c b/net/core/skbuff.c index b1f274f22d85..f59e98ca72c5 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4911,7 +4911,6 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet) return; ipvs_reset(skb); - skb_orphan(skb); skb->mark = 0; } EXPORT_SYMBOL_GPL(skb_scrub_packet);