net: l3mdev: Add hook in ip and ipv6

Currently the VRF driver uses the rx_handler to switch the skb device
to the VRF device. Switching the dev prior to the ip / ipv6 layer
means the VRF driver has to duplicate IP/IPv6 processing which adds
overhead and makes features such as retaining the ingress device index
more complicated than necessary.

This patch moves the hook to the L3 layer just after the first NF_HOOK
for PRE_ROUTING. This location makes exposing the original ingress device
trivial (next patch) and allows adding other NF_HOOKs to the VRF driver
in the future.

dev_queue_xmit_nit is exported so that the VRF driver can cycle the skb
with the switched device through the packet taps to maintain current
behavior (tcpdump can be used on either the vrf device or the enslaved
devices).

Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 91 insertions, 98 deletions

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index c8db55aa8280..0ea29345eb2e 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -42,9 +42,6 @@
 #define DRV_NAME	"vrf"
 #define DRV_VERSION	"1.0"
 
-#define vrf_master_get_rcu(dev) \
-	((struct net_device *)rcu_dereference(dev->rx_handler_data))
-
 struct net_vrf {
 	struct rtable           *rth;
 	struct rt6_info		*rt6;
@@ -60,90 +57,12 @@ struct pcpu_dstats {
 	struct u64_stats_sync	syncp;
 };
 
-/* neighbor handling is done with actual device; do not want
- * to flip skb->dev for those ndisc packets. This really fails
- * for multiple next protocols (e.g., NEXTHDR_HOP). But it is
- * a start.
- */
-#if IS_ENABLED(CONFIG_IPV6)
-static bool check_ipv6_frame(const struct sk_buff *skb)
-{
-	const struct ipv6hdr *ipv6h;
-	struct ipv6hdr _ipv6h;
-	bool rc = true;
-
-	ipv6h = skb_header_pointer(skb, 0, sizeof(_ipv6h), &_ipv6h);
-	if (!ipv6h)
-		goto out;
-
-	if (ipv6h->nexthdr == NEXTHDR_ICMP) {
-		const struct icmp6hdr *icmph;
-		struct icmp6hdr _icmph;
-
-		icmph = skb_header_pointer(skb, sizeof(_ipv6h),
-					   sizeof(_icmph), &_icmph);
-		if (!icmph)
-			goto out;
-
-		switch (icmph->icmp6_type) {
-		case NDISC_ROUTER_SOLICITATION:
-		case NDISC_ROUTER_ADVERTISEMENT:
-		case NDISC_NEIGHBOUR_SOLICITATION:
-		case NDISC_NEIGHBOUR_ADVERTISEMENT:
-		case NDISC_REDIRECT:
-			rc = false;
-			break;
-		}
-	}
-
-out:
-	return rc;
-}
-#else
-static bool check_ipv6_frame(const struct sk_buff *skb)
-{
-	return false;
-}
-#endif
-
-static bool is_ip_rx_frame(struct sk_buff *skb)
-{
-	switch (skb->protocol) {
-	case htons(ETH_P_IP):
-		return true;
-	case htons(ETH_P_IPV6):
-		return check_ipv6_frame(skb);
-	}
-	return false;
-}
-
 static void vrf_tx_error(struct net_device *vrf_dev, struct sk_buff *skb)
 {
 	vrf_dev->stats.tx_errors++;
 	kfree_skb(skb);
 }
 
-/* note: already called with rcu_read_lock */
-static rx_handler_result_t vrf_handle_frame(struct sk_buff **pskb)
-{
-	struct sk_buff *skb = *pskb;
-
-	if (is_ip_rx_frame(skb)) {
-		struct net_device *dev = vrf_master_get_rcu(skb->dev);
-		struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats);
-
-		u64_stats_update_begin(&dstats->syncp);
-		dstats->rx_pkts++;
-		dstats->rx_bytes += skb->len;
-		u64_stats_update_end(&dstats->syncp);
-
-		skb->dev = dev;
-
-		return RX_HANDLER_ANOTHER;
-	}
-	return RX_HANDLER_PASS;
-}
-
 static struct rtnl_link_stats64 *vrf_get_stats64(struct net_device *dev,
 						 struct rtnl_link_stats64 *stats)
 {
@@ -506,28 +425,14 @@ static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev)
 {
 	int ret;
 
-	/* register the packet handler for slave ports */
-	ret = netdev_rx_handler_register(port_dev, vrf_handle_frame, dev);
-	if (ret) {
-		netdev_err(port_dev,
-			   "Device %s failed to register rx_handler\n",
-			   port_dev->name);
-		goto out_fail;
-	}
-
 	ret = netdev_master_upper_dev_link(port_dev, dev, NULL, NULL);
 	if (ret < 0)
-		goto out_unregister;
+		return ret;
 
 	port_dev->priv_flags |= IFF_L3MDEV_SLAVE;
 	cycle_netdev(port_dev);
 
 	return 0;
-
-out_unregister:
-	netdev_rx_handler_unregister(port_dev);
-out_fail:
-	return ret;
 }
 
 static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev)
@@ -544,8 +449,6 @@ static int do_vrf_del_slave(struct net_device *dev, struct net_device *port_dev)
 	netdev_upper_dev_unlink(port_dev, dev);
 	port_dev->priv_flags &= ~IFF_L3MDEV_SLAVE;
 
-	netdev_rx_handler_unregister(port_dev);
-
 	cycle_netdev(port_dev);
 
 	return 0;
@@ -670,6 +573,95 @@ static int vrf_get_saddr(struct net_device *dev, struct flowi4 *fl4)
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
+/* neighbor handling is done with actual device; do not want
+ * to flip skb->dev for those ndisc packets. This really fails
+ * for multiple next protocols (e.g., NEXTHDR_HOP). But it is
+ * a start.
+ */
+static bool ipv6_ndisc_frame(const struct sk_buff *skb)
+{
+	const struct ipv6hdr *iph = ipv6_hdr(skb);
+	bool rc = false;
+
+	if (iph->nexthdr == NEXTHDR_ICMP) {
+		const struct icmp6hdr *icmph;
+		struct icmp6hdr _icmph;
+
+		icmph = skb_header_pointer(skb, sizeof(*iph),
+					   sizeof(_icmph), &_icmph);
+		if (!icmph)
+			goto out;
+
+		switch (icmph->icmp6_type) {
+		case NDISC_ROUTER_SOLICITATION:
+		case NDISC_ROUTER_ADVERTISEMENT:
+		case NDISC_NEIGHBOUR_SOLICITATION:
+		case NDISC_NEIGHBOUR_ADVERTISEMENT:
+		case NDISC_REDIRECT:
+			rc = true;
+			break;
+		}
+	}
+
+out:
+	return rc;
+}
+
+static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
+				   struct sk_buff *skb)
+{
+	/* if packet is NDISC keep the ingress interface */
+	if (!ipv6_ndisc_frame(skb)) {
+		skb->dev = vrf_dev;
+		skb->skb_iif = vrf_dev->ifindex;
+
+		skb_push(skb, skb->mac_len);
+		dev_queue_xmit_nit(skb, vrf_dev);
+		skb_pull(skb, skb->mac_len);
+
+		IP6CB(skb)->flags |= IP6SKB_L3SLAVE;
+	}
+
+	return skb;
+}
+
+#else
+static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
+				   struct sk_buff *skb)
+{
+	return skb;
+}
+#endif
+
+static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev,
+				  struct sk_buff *skb)
+{
+	skb->dev = vrf_dev;
+	skb->skb_iif = vrf_dev->ifindex;
+
+	skb_push(skb, skb->mac_len);
+	dev_queue_xmit_nit(skb, vrf_dev);
+	skb_pull(skb, skb->mac_len);
+
+	return skb;
+}
+
+/* called with rcu lock held */
+static struct sk_buff *vrf_l3_rcv(struct net_device *vrf_dev,
+				  struct sk_buff *skb,
+				  u16 proto)
+{
+	switch (proto) {
+	case AF_INET:
+		return vrf_ip_rcv(vrf_dev, skb);
+	case AF_INET6:
+		return vrf_ip6_rcv(vrf_dev, skb);
+	}
+
+	return skb;
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
 static struct dst_entry *vrf_get_rt6_dst(const struct net_device *dev,
 					 const struct flowi6 *fl6)
 {
@@ -690,6 +682,7 @@ static const struct l3mdev_ops vrf_l3mdev_ops = {
 	.l3mdev_fib_table	= vrf_fib_table,
 	.l3mdev_get_rtable	= vrf_get_rtable,
 	.l3mdev_get_saddr	= vrf_get_saddr,
+	.l3mdev_l3_rcv		= vrf_l3_rcv,
 #if IS_ENABLED(CONFIG_IPV6)
 	.l3mdev_get_rt6_dst	= vrf_get_rt6_dst,
 #endif