netdev - [RFC PATCH 4/5] net: filter: run cgroup eBPF programs

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1471442448-1248-5-git-send-email-daniel@zonque.org>
Date:	Wed, 17 Aug 2016 16:00:47 +0200
From:	Daniel Mack <daniel@...que.org>
To:	htejun@...com, daniel@...earbox.net, ast@...com
Cc:	davem@...emloft.net, kafai@...com, fw@...len.de,
	pablo@...filter.org, harald@...hat.com, netdev@...r.kernel.org,
	Daniel Mack <daniel@...que.org>
Subject: [RFC PATCH 4/5] net: filter: run cgroup eBPF programs

If CONFIG_CGROUP_BPF is enabled, and the cgroup associated with the
receiving socket has an eBPF programs installed, run them from
sk_filter_trim_cap().

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 full skb, including the MAC headers.

This patch only implements the call site for ingress packets.

Signed-off-by: Daniel Mack <daniel@...que.org>
---
 net/core/filter.c | 44 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/net/core/filter.c b/net/core/filter.c
index c5d8332..a1dd94b 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -52,6 +52,44 @@
 #include <net/dst.h>
 #include <net/sock_reuseport.h>
 
+#ifdef CONFIG_CGROUP_BPF
+static int sk_filter_cgroup_bpf(struct sock *sk, struct sk_buff *skb,
+				enum bpf_attach_type type)
+{
+	struct sock_cgroup_data *skcd = &sk->sk_cgrp_data;
+	struct cgroup *cgrp = sock_cgroup_ptr(skcd);
+	struct bpf_prog *prog;
+	int ret = 0;
+
+	rcu_read_lock();
+
+	switch (type) {
+	case BPF_ATTACH_TYPE_CGROUP_EGRESS:
+		prog = rcu_dereference(cgrp->bpf_egress);
+		break;
+	case BPF_ATTACH_TYPE_CGROUP_INGRESS:
+		prog = rcu_dereference(cgrp->bpf_ingress);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		ret = -EINVAL;
+		break;
+	}
+
+	if (prog) {
+		unsigned int offset = skb->data - skb_mac_header(skb);
+
+		__skb_push(skb, offset);
+		ret = bpf_prog_run_clear_cb(prog, skb) > 0 ? 0 : -EPERM;
+		__skb_pull(skb, offset);
+	}
+
+	rcu_read_unlock();
+
+	return ret;
+}
+#endif /* !CONFIG_CGROUP_BPF */
+
 /**
  *	sk_filter_trim_cap - run a packet through a socket filter
  *	@sk: sock associated with &sk_buff
@@ -78,6 +116,12 @@ int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap)
 	if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC))
 		return -ENOMEM;
 
+#ifdef CONFIG_CGROUP_BPF
+	err = sk_filter_cgroup_bpf(sk, skb, BPF_ATTACH_TYPE_CGROUP_INGRESS);
+	if (err)
+		return err;
+#endif
+
 	err = security_sock_rcv_skb(sk, skb);
 	if (err)
 		return err;
-- 
2.5.5