bpf: Drop MTU check when doing TC-BPF redirect to ingress

The use-case for dropping the MTU check when TC-BPF does redirect to
ingress, is described by Eyal Birger in email[0]. The summary is the
ability to increase packet size (e.g. with IPv6 headers for NAT64) and
ingress redirect packet and let normal netstack fragment packet as needed.

[0] https://lore.kernel.org/netdev/CAHsH6Gug-hsLGHQ6N0wtixdOa85LDZ3HNRHVd0opR=19Qo4W4Q@mail.gmail.com/

V15:
 - missing static for function declaration

V9:
 - Make net_device "up" (IFF_UP) check explicit in skb_do_redirect

V4:
 - Keep net_device "up" (IFF_UP) check.
 - Adjustment to handle bpf_redirect_peer() helper

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/161287790971.790810.11785274340154740591.stgit@firesoul

3 files changed, 47 insertions, 23 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ef517254367d..b9bcbfde7849 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3931,14 +3931,42 @@ int xdp_umem_query(struct net_device *dev, u16 queue_id);
 
 int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
 int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
+int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb);
 bool is_skb_forwardable(const struct net_device *dev,
 			const struct sk_buff *skb);
 
+static __always_inline bool __is_skb_forwardable(const struct net_device *dev,
+						 const struct sk_buff *skb,
+						 const bool check_mtu)
+{
+	const u32 vlan_hdr_len = 4; /* VLAN_HLEN */
+	unsigned int len;
+
+	if (!(dev->flags & IFF_UP))
+		return false;
+
+	if (!check_mtu)
+		return true;
+
+	len = dev->mtu + dev->hard_header_len + vlan_hdr_len;
+	if (skb->len <= len)
+		return true;
+
+	/* if TSO is enabled, we don't care about the length as the packet
+	 * could be forwarded without being segmented before
+	 */
+	if (skb_is_gso(skb))
+		return true;
+
+	return false;
+}
+
 static __always_inline int ____dev_forward_skb(struct net_device *dev,
-					       struct sk_buff *skb)
+					       struct sk_buff *skb,
+					       const bool check_mtu)
 {
 	if (skb_orphan_frags(skb, GFP_ATOMIC) ||
-	    unlikely(!is_skb_forwardable(dev, skb))) {
+	    unlikely(!__is_skb_forwardable(dev, skb, check_mtu))) {
 		atomic_long_inc(&dev->rx_dropped);
 		kfree_skb(skb);
 		return NET_RX_DROP;
diff --git a/net/core/dev.c b/net/core/dev.c
index 07a0347c33fb..8c820fe0eff3 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2194,28 +2194,14 @@ static inline void net_timestamp_set(struct sk_buff *skb)
 
 bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb)
 {
-	unsigned int len;
-
-	if (!(dev->flags & IFF_UP))
-		return false;
-
-	len = dev->mtu + dev->hard_header_len + VLAN_HLEN;
-	if (skb->len <= len)
-		return true;
-
-	/* if TSO is enabled, we don't care about the length as the packet
-	 * could be forwarded without being segmented before
-	 */
-	if (skb_is_gso(skb))
-		return true;
-
-	return false;
+	return __is_skb_forwardable(dev, skb, true);
 }
 EXPORT_SYMBOL_GPL(is_skb_forwardable);
 
-int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
+static int __dev_forward_skb2(struct net_device *dev, struct sk_buff *skb,
+			      bool check_mtu)
 {
-	int ret = ____dev_forward_skb(dev, skb);
+	int ret = ____dev_forward_skb(dev, skb, check_mtu);
 
 	if (likely(!ret)) {
 		skb->protocol = eth_type_trans(skb, dev);
@@ -2224,6 +2210,11 @@ int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 
 	return ret;
 }
+
+int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
+{
+	return __dev_forward_skb2(dev, skb, true);
+}
 EXPORT_SYMBOL_GPL(__dev_forward_skb);
 
 /**
@@ -2250,6 +2241,11 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 }
 EXPORT_SYMBOL_GPL(dev_forward_skb);
 
+int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb)
+{
+	return __dev_forward_skb2(dev, skb, false) ?: netif_rx_internal(skb);
+}
+
 static inline int deliver_skb(struct sk_buff *skb,
 			      struct packet_type *pt_prev,
 			      struct net_device *orig_dev)
diff --git a/net/core/filter.c b/net/core/filter.c
index 439f43f00483..7059cf604d94 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2083,13 +2083,13 @@ static const struct bpf_func_proto bpf_csum_level_proto = {
 
 static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb)
 {
-	return dev_forward_skb(dev, skb);
+	return dev_forward_skb_nomtu(dev, skb);
 }
 
 static inline int __bpf_rx_skb_no_mac(struct net_device *dev,
 				      struct sk_buff *skb)
 {
-	int ret = ____dev_forward_skb(dev, skb);
+	int ret = ____dev_forward_skb(dev, skb, false);
 
 	if (likely(!ret)) {
 		skb->dev = dev;
@@ -2480,7 +2480,7 @@ int skb_do_redirect(struct sk_buff *skb)
 			goto out_drop;
 		dev = ops->ndo_get_peer_dev(dev);
 		if (unlikely(!dev ||
-			     !is_skb_forwardable(dev, skb) ||
+			     !(dev->flags & IFF_UP) ||
 			     net_eq(net, dev_net(dev))))
 			goto out_drop;
 		skb->dev = dev;