netdev - [PATCH v3 bpf-next 4/6] bpf: Update BPF_CGROUP_RUN_PROG_INET

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: <20190528034907.1957536-5-brakmo@fb.com>
Date:   Mon, 27 May 2019 20:49:05 -0700
From:   brakmo <brakmo@...com>
To:     netdev <netdev@...r.kernel.org>
CC:     Martin Lau <kafai@...com>, Alexei Starovoitov <ast@...com>,
        Daniel Borkmann <daniel@...earbox.net>,
        Eric Dumazet <eric.dumazet@...il.com>,
        Kernel Team <Kernel-team@...com>
Subject: [PATCH v3 bpf-next 4/6] bpf: Update BPF_CGROUP_RUN_PROG_INET_EGRESS calls

Update BPF_CGROUP_RUN_PROG_INET_EGRESS() callers to support returning
congestion notifications from the BPF programs.

Signed-off-by: Lawrence Brakmo <brakmo@...com>
Signed-off-by: Alexei Starovoitov <ast@...nel.org>
---
 net/ipv4/ip_output.c  | 34 +++++++++++++++++++++++-----------
 net/ipv6/ip6_output.c | 26 +++++++++++++++++---------
 2 files changed, 40 insertions(+), 20 deletions(-)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index bfd0ca554977..1217a53381c2 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -287,16 +287,9 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk,
 	return ret;
 }
 
-static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+static int __ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	unsigned int mtu;
-	int ret;
-
-	ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
-	if (ret) {
-		kfree_skb(skb);
-		return ret;
-	}
 
 #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
 	/* Policy lookup after SNAT yielded a new policy */
@@ -315,18 +308,37 @@ static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *sk
 	return ip_finish_output2(net, sk, skb);
 }
 
+static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	int ret;
+
+	ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
+	switch (ret) {
+	case NET_XMIT_SUCCESS:
+		return __ip_finish_output(net, sk, skb);
+	case NET_XMIT_CN:
+		return __ip_finish_output(net, sk, skb) ? : ret;
+	default:
+		kfree_skb(skb);
+		return ret;
+	}
+}
+
 static int ip_mc_finish_output(struct net *net, struct sock *sk,
 			       struct sk_buff *skb)
 {
 	int ret;
 
 	ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
-	if (ret) {
+	switch (ret) {
+	case NET_XMIT_SUCCESS:
+		return dev_loopback_xmit(net, sk, skb);
+	case NET_XMIT_CN:
+		return dev_loopback_xmit(net, sk, skb) ? : ret;
+	default:
 		kfree_skb(skb);
 		return ret;
 	}
-
-	return dev_loopback_xmit(net, sk, skb);
 }
 
 int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb)
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index adef2236abe2..a75bc21d8c88 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -128,16 +128,8 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
 	return -EINVAL;
 }
 
-static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
-	int ret;
-
-	ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
-	if (ret) {
-		kfree_skb(skb);
-		return ret;
-	}
-
 #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
 	/* Policy lookup after SNAT yielded a new policy */
 	if (skb_dst(skb)->xfrm) {
@@ -154,6 +146,22 @@ static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *s
 		return ip6_finish_output2(net, sk, skb);
 }
 
+static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	int ret;
+
+	ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
+	switch (ret) {
+	case NET_XMIT_SUCCESS:
+		return __ip6_finish_output(net, sk, skb);
+	case NET_XMIT_CN:
+		return __ip6_finish_output(net, sk, skb) ? : ret;
+	default:
+		kfree_skb(skb);
+		return ret;
+	}
+}
+
 int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	struct net_device *dev = skb_dst(skb)->dev;
-- 
2.17.1