[PATCH net-next 0/2] net: vrf: Support for local traffic with sockets bound to enslaved devices

[PATCH net-next 0/2] net: vrf: Support for local traffic with sockets bound to enslaved devices

[David Ahern]

This set gets local traffic working for sockets bound to enslaved
devices. The local rtable and rt6_info added in June 2016 to get
local traffic in VRFs working is no longer needed and actually
keeps local traffic for sockets bound to an enslaved device from
working. Patch 1 removes them.

Patch 2 adds a fix up for IPv4 IP_PKTINFO to return rt_iif for
packets sent over the VRF device. This is similar to the handling
of loopback.

David Ahern (2):
  net: vrf: Drop local rtable and rt6_info
  net: ipv4: add check for l3slave for index returned in IP_PKTINFO

 drivers/net/vrf.c      | 122 ++++---------------------------------------------
 net/ipv4/ip_sockglue.c |   3 +-
 2 files changed, 10 insertions(+), 115 deletions(-)

-- 
2.1.4

[PATCH net-next 1/2] net: vrf: Drop local rtable and rt6_info

[David Ahern]

The VRF cached rtable and rt6_info for local traffic are no longer
needed and actually prevent local traffic through enslaved devices.
Remove them.

Signed-off-by: David Ahern <dsahern@gmail.com>
---
 drivers/net/vrf.c | 122 ++++--------------------------------------------------
 1 file changed, 8 insertions(+), 114 deletions(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index abd2010c48ae..7e19051f3230 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -47,9 +47,7 @@ static unsigned int vrf_net_id;
 
 struct net_vrf {
 	struct rtable __rcu	*rth;
-	struct rtable __rcu	*rth_local;
 	struct rt6_info	__rcu	*rt6;
-	struct rt6_info	__rcu	*rt6_local;
 	u32                     tb_id;
 };
 
@@ -194,42 +192,10 @@ static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
 
 	/* if dst.dev is loopback or the VRF device again this is locally
 	 * originated traffic destined to a local address. Short circuit
-	 * to Rx path using our local dst
+	 * to Rx path
 	 */
-	if (dst->dev == net->loopback_dev || dst->dev == dev) {
-		struct net_vrf *vrf = netdev_priv(dev);
-		struct rt6_info *rt6_local;
-
-		/* release looked up dst and use cached local dst */
-		dst_release(dst);
-
-		rcu_read_lock();
-
-		rt6_local = rcu_dereference(vrf->rt6_local);
-		if (unlikely(!rt6_local)) {
-			rcu_read_unlock();
-			goto err;
-		}
-
-		/* Ordering issue: cached local dst is created on newlink
-		 * before the IPv6 initialization. Using the local dst
-		 * requires rt6i_idev to be set so make sure it is.
-		 */
-		if (unlikely(!rt6_local->rt6i_idev)) {
-			rt6_local->rt6i_idev = in6_dev_get(dev);
-			if (!rt6_local->rt6i_idev) {
-				rcu_read_unlock();
-				goto err;
-			}
-		}
-
-		dst = &rt6_local->dst;
-		dst_hold(dst);
-
-		rcu_read_unlock();
-
-		return vrf_local_xmit(skb, dev, &rt6_local->dst);
-	}
+	if (dst->dev == dev)
+		return vrf_local_xmit(skb, dev, dst);
 
 	skb_dst_set(skb, dst);
 
@@ -296,30 +262,10 @@ static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
 
 	/* if dst.dev is loopback or the VRF device again this is locally
 	 * originated traffic destined to a local address. Short circuit
-	 * to Rx path using our local dst
+	 * to Rx path
 	 */
-	if (rt->dst.dev == net->loopback_dev || rt->dst.dev == vrf_dev) {
-		struct net_vrf *vrf = netdev_priv(vrf_dev);
-		struct rtable *rth_local;
-		struct dst_entry *dst = NULL;
-
-		ip_rt_put(rt);
-
-		rcu_read_lock();
-
-		rth_local = rcu_dereference(vrf->rth_local);
-		if (likely(rth_local)) {
-			dst = &rth_local->dst;
-			dst_hold(dst);
-		}
-
-		rcu_read_unlock();
-
-		if (unlikely(!dst))
-			goto err;
-
-		return vrf_local_xmit(skb, vrf_dev, dst);
-	}
+	if (rt->dst.dev == vrf_dev)
+		return vrf_local_xmit(skb, vrf_dev, &rt->dst);
 
 	skb_dst_set(skb, &rt->dst);
 
@@ -528,12 +474,10 @@ static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev,
 static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf)
 {
 	struct rt6_info *rt6 = rtnl_dereference(vrf->rt6);
-	struct rt6_info *rt6_local = rtnl_dereference(vrf->rt6_local);
 	struct net *net = dev_net(dev);
 	struct dst_entry *dst;
 
 	RCU_INIT_POINTER(vrf->rt6, NULL);
-	RCU_INIT_POINTER(vrf->rt6_local, NULL);
 	synchronize_rcu();
 
 	/* move dev in dst's to loopback so this VRF device can be deleted
@@ -546,19 +490,6 @@ static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf)
 		dev_hold(dst->dev);
 		dst_release(dst);
 	}
-
-	if (rt6_local) {
-		if (rt6_local->rt6i_idev) {
-			in6_dev_put(rt6_local->rt6i_idev);
-			rt6_local->rt6i_idev = NULL;
-		}
-
-		dst = &rt6_local->dst;
-		dev_put(dst->dev);
-		dst->dev = net->loopback_dev;
-		dev_hold(dst->dev);
-		dst_release(dst);
-	}
 }
 
 static int vrf_rt6_create(struct net_device *dev)
@@ -567,7 +498,7 @@ static int vrf_rt6_create(struct net_device *dev)
 	struct net_vrf *vrf = netdev_priv(dev);
 	struct net *net = dev_net(dev);
 	struct fib6_table *rt6i_table;
-	struct rt6_info *rt6, *rt6_local;
+	struct rt6_info *rt6;
 	int rc = -ENOMEM;
 
 	/* IPv6 can be CONFIG enabled and then disabled runtime */
@@ -586,22 +517,7 @@ static int vrf_rt6_create(struct net_device *dev)
 	rt6->rt6i_table = rt6i_table;
 	rt6->dst.output	= vrf_output6;
 
-	/* create a dst for local routing - packets sent locally
-	 * to local address via the VRF device as a loopback
-	 */
-	rt6_local = ip6_dst_alloc(net, dev, flags);
-	if (!rt6_local) {
-		dst_release(&rt6->dst);
-		goto out;
-	}
-
-	rt6_local->rt6i_idev  = in6_dev_get(dev);
-	rt6_local->rt6i_flags = RTF_UP | RTF_NONEXTHOP | RTF_LOCAL;
-	rt6_local->rt6i_table = rt6i_table;
-	rt6_local->dst.input  = ip6_input;
-
 	rcu_assign_pointer(vrf->rt6, rt6);
-	rcu_assign_pointer(vrf->rt6_local, rt6_local);
 
 	rc = 0;
 out:
@@ -788,12 +704,10 @@ static struct sk_buff *vrf_l3_out(struct net_device *vrf_dev,
 static void vrf_rtable_release(struct net_device *dev, struct net_vrf *vrf)
 {
 	struct rtable *rth = rtnl_dereference(vrf->rth);
-	struct rtable *rth_local = rtnl_dereference(vrf->rth_local);
 	struct net *net = dev_net(dev);
 	struct dst_entry *dst;
 
 	RCU_INIT_POINTER(vrf->rth, NULL);
-	RCU_INIT_POINTER(vrf->rth_local, NULL);
 	synchronize_rcu();
 
 	/* move dev in dst's to loopback so this VRF device can be deleted
@@ -806,20 +720,12 @@ static void vrf_rtable_release(struct net_device *dev, struct net_vrf *vrf)
 		dev_hold(dst->dev);
 		dst_release(dst);
 	}
-
-	if (rth_local) {
-		dst = &rth_local->dst;
-		dev_put(dst->dev);
-		dst->dev = net->loopback_dev;
-		dev_hold(dst->dev);
-		dst_release(dst);
-	}
 }
 
 static int vrf_rtable_create(struct net_device *dev)
 {
 	struct net_vrf *vrf = netdev_priv(dev);
-	struct rtable *rth, *rth_local;
+	struct rtable *rth;
 
 	if (!fib_new_table(dev_net(dev), vrf->tb_id))
 		return -ENOMEM;
@@ -829,22 +735,10 @@ static int vrf_rtable_create(struct net_device *dev)
 	if (!rth)
 		return -ENOMEM;
 
-	/* create a dst for local ingress routing - packets sent locally
-	 * to local address via the VRF device as a loopback
-	 */
-	rth_local = rt_dst_alloc(dev, RTCF_LOCAL, RTN_LOCAL, 1, 1, 0);
-	if (!rth_local) {
-		dst_release(&rth->dst);
-		return -ENOMEM;
-	}
-
 	rth->dst.output	= vrf_output;
 	rth->rt_table_id = vrf->tb_id;
 
-	rth_local->rt_table_id = vrf->tb_id;
-
 	rcu_assign_pointer(vrf->rth, rth);
-	rcu_assign_pointer(vrf->rth_local, rth_local);
 
 	return 0;
 }
-- 
2.1.4

[PATCH net-next 2/2] net: ipv4: add check for l3slave for index returned in IP_PKTINFO

[David Ahern]

Similar to the loopback device, for packets sent through a VRF device
the index returned in ipi_ifindex needs to be the saved index in
rt_iif.

Signed-off-by: David Ahern <dsahern@gmail.com>
---
 net/ipv4/ip_sockglue.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index dd68a9ed5e40..e558e4f9597b 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1207,6 +1207,7 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb)
 {
 	struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb);
+	bool l3slave = ipv4_l3mdev_skb(IPCB(skb)->flags);
 	bool prepare = (inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO) ||
 		       ipv6_sk_rxinfo(sk);
 
@@ -1220,7 +1221,7 @@ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb)
 		 * (e.g., process binds socket to eth0 for Tx which is
 		 * redirected to loopback in the rtable/dst).
 		 */
-		if (pktinfo->ipi_ifindex == LOOPBACK_IFINDEX)
+		if (pktinfo->ipi_ifindex == LOOPBACK_IFINDEX || l3slave)
 			pktinfo->ipi_ifindex = inet_iif(skb);
 
 		pktinfo->ipi_spec_dst.s_addr = fib_compute_spec_dst(skb);
-- 
2.1.4

Re: [PATCH net-next 0/2] net: vrf: Support for local traffic with sockets bound to enslaved devices

[David Miller]

From: David Ahern <dsahern@gmail.com>
Date: Fri, 11 Aug 2017 17:11:13 -0700

> This set gets local traffic working for sockets bound to enslaved
> devices. The local rtable and rt6_info added in June 2016 to get
> local traffic in VRFs working is no longer needed and actually
> keeps local traffic for sockets bound to an enslaved device from
> working. Patch 1 removes them.
> 
> Patch 2 adds a fix up for IPv4 IP_PKTINFO to return rt_iif for
> packets sent over the VRF device. This is similar to the handling
> of loopback.

Series applied, thanks David.