Re: [PATCH v4 bpf 1/2] bpf: fix skb_do_redirect return values

[Dan Carpenter]

I'm not positive I understand the code in ip_finish_output2().  I think
instead of looking for LWTUNNEL_XMIT_DONE it should instead look for
!= LWTUNNEL_XMIT_CONTINUE.  It's unfortunate that NET_XMIT_DROP and
LWTUNNEL_XMIT_CONTINUE are the both 0x1.  Why don't we just change that
instead?

Also there seems to be a leak in lwtunnel_xmit().  Should that return
LWTUNNEL_XMIT_CONTINUE or should it call kfree_skb() before returning?

Something like the following?

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 11652e464f5d..375790b672bc 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -112,6 +112,9 @@ void netdev_sw_irq_coalesce_default_on(struct net_device *dev);
 #define NET_XMIT_CN		0x02	/* congestion notification	*/
 #define NET_XMIT_MASK		0x0f	/* qdisc flags in net/sch_generic.h */
 
+#define LWTUNNEL_XMIT_DONE NET_XMIT_SUCCESS
+#define LWTUNNEL_XMIT_CONTINUE 0x3
+
 /* NET_XMIT_CN is special. It does not guarantee that this packet is lost. It
  * indicates that the device will soon be dropping packets, or already drops
  * some packets of the same priority; prompting us to send less aggressively. */
diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h
index 6f15e6fa154e..8ab032ee04d0 100644
--- a/include/net/lwtunnel.h
+++ b/include/net/lwtunnel.h
@@ -16,12 +16,6 @@
 #define LWTUNNEL_STATE_INPUT_REDIRECT	BIT(1)
 #define LWTUNNEL_STATE_XMIT_REDIRECT	BIT(2)
 
-enum {
-	LWTUNNEL_XMIT_DONE,
-	LWTUNNEL_XMIT_CONTINUE,
-};
-
-
 struct lwtunnel_state {
 	__u16		type;
 	__u16		flags;
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index 711cd3b4347a..732415d1287d 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -371,7 +371,7 @@ int lwtunnel_xmit(struct sk_buff *skb)
 
 	if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
 	    lwtstate->type > LWTUNNEL_ENCAP_MAX)
-		return 0;
+		return LWTUNNEL_XMIT_CONTINUE;
 
 	ret = -EOPNOTSUPP;
 	rcu_read_lock();
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 6e70839257f7..4be50a211b14 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -216,7 +216,7 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s
 	if (lwtunnel_xmit_redirect(dst->lwtstate)) {
 		int res = lwtunnel_xmit(skb);
 
-		if (res < 0 || res == LWTUNNEL_XMIT_DONE)
+		if (res != LWTUNNEL_XMIT_CONTINUE)
 			return res;
 	}
 
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 1e8c90e97608..016b0a513259 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -113,7 +113,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
 	if (lwtunnel_xmit_redirect(dst->lwtstate)) {
 		int res = lwtunnel_xmit(skb);
 
-		if (res < 0 || res == LWTUNNEL_XMIT_DONE)
+		if (res != LWTUNNEL_XMIT_CONTINUE)
 			return res;
 	}