From mboxrd@z Thu Jan 1 00:00:00 1970 From: Daniel Mack Subject: [PATCH v7 5/6] net: ipv4, ipv6: run cgroup eBPF egress programs Date: Tue, 25 Oct 2016 12:14:13 +0200 Message-ID: <1477390454-12553-6-git-send-email-daniel@zonque.org> References: <1477390454-12553-1-git-send-email-daniel@zonque.org> Cc: davem-fT/PcQaiUtIeIZ0/mPfg9Q@public.gmane.org, kafai-b10kYP2dOMg@public.gmane.org, fw-HFFVJYpyMKqzQB+pC5nmwQ@public.gmane.org, pablo-Cap9r6Oaw4JrovVCs/uTlw@public.gmane.org, harald-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org, netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, sargun-GaZTRHToo+CzQB+pC5nmwQ@public.gmane.org, cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Daniel Mack To: htejun-b10kYP2dOMg@public.gmane.org, daniel-FeC+5ew28dpmcu3hnIyYJQ@public.gmane.org, ast-b10kYP2dOMg@public.gmane.org Return-path: In-Reply-To: <1477390454-12553-1-git-send-email-daniel-cYrQPVfZoowdnm+yROfE0A@public.gmane.org> Sender: cgroups-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org List-Id: netdev.vger.kernel.org If the cgroup associated with the receiving socket has an eBPF programs installed, run them from ip_output(), ip6_output() and ip_mc_output(). eBPF programs used in this context are expected to either return 1 to let the packet pass, or != 1 to drop them. The programs have access to the skb through bpf_skb_load_bytes(), and the payload starts at the network headers (L3). Note that cgroup_bpf_run_filter() is stubbed out as static inline nop for !CONFIG_CGROUP_BPF, and is otherwise guarded by a static key if the feature is unused. Signed-off-by: Daniel Mack Acked-by: Alexei Starovoitov --- net/ipv4/ip_output.c | 17 +++++++++++++++++ net/ipv6/ip6_output.c | 9 +++++++++ 2 files changed, 26 insertions(+) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 05d1058..ee4b249 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -74,6 +74,7 @@ #include #include #include +#include #include #include #include @@ -303,6 +304,7 @@ int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); struct net_device *dev = rt->dst.dev; + int ret; /* * If the indicated interface is up and running, send the packet. @@ -312,6 +314,13 @@ int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb) skb->dev = dev; skb->protocol = htons(ETH_P_IP); + ret = cgroup_bpf_run_filter(sk_to_full_sk(sk), skb, + BPF_CGROUP_INET_EGRESS); + if (ret) { + kfree_skb(skb); + return ret; + } + /* * Multicasts are looped back for other local users */ @@ -364,12 +373,20 @@ int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb) int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev; + int ret; IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); skb->dev = dev; skb->protocol = htons(ETH_P_IP); + ret = cgroup_bpf_run_filter(sk_to_full_sk(sk), skb, + BPF_CGROUP_INET_EGRESS); + if (ret) { + kfree_skb(skb); + return ret; + } + return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, NULL, dev, ip_finish_output, diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 6001e78..1947026 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -39,6 +39,7 @@ #include #include +#include #include #include @@ -143,6 +144,7 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev; struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); + int ret; if (unlikely(idev->cnf.disable_ipv6)) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); @@ -150,6 +152,13 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb) return 0; } + ret = cgroup_bpf_run_filter(sk_to_full_sk(sk), skb, + BPF_CGROUP_INET_EGRESS); + if (ret) { + kfree_skb(skb); + return ret; + } + return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb, NULL, dev, ip6_finish_output, -- 2.7.4