Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Support ipv6 checksum offload in sunvnet driver, from Shannon
    Nelson.

 2) Move to RB-tree instead of custom AVL code in inetpeer, from Eric
    Dumazet.

 3) Allow generic XDP to work on virtual devices, from John Fastabend.

 4) Add bpf device maps and XDP_REDIRECT, which can be used to build
    arbitrary switching frameworks using XDP. From John Fastabend.

 5) Remove UFO offloads from the tree, gave us little other than bugs.

 6) Remove the IPSEC flow cache, from Florian Westphal.

 7) Support ipv6 route offload in mlxsw driver.

 8) Support VF representors in bnxt_en, from Sathya Perla.

 9) Add support for forward error correction modes to ethtool, from
    Vidya Sagar Ravipati.

10) Add time filter for packet scheduler action dumping, from Jamal Hadi
    Salim.

11) Extend the zerocopy sendmsg() used by virtio and tap to regular
    sockets via MSG_ZEROCOPY. From Willem de Bruijn.

12) Significantly rework value tracking in the BPF verifier, from Edward
    Cree.

13) Add new jump instructions to eBPF, from Daniel Borkmann.

14) Rework rtnetlink plumbing so that operations can be run without
    taking the RTNL semaphore. From Florian Westphal.

15) Support XDP in tap driver, from Jason Wang.

16) Add 32-bit eBPF JIT for ARM, from Shubham Bansal.

17) Add Huawei hinic ethernet driver.

18) Allow to report MD5 keys in TCP inet_diag dumps, from Ivan
    Delalande.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1780 commits)
  i40e: point wb_desc at the nvm_wb_desc during i40e_read_nvm_aq
  i40e: avoid NVM acquire deadlock during NVM update
  drivers: net: xgene: Remove return statement from void function
  drivers: net: xgene: Configure tx/rx delay for ACPI
  drivers: net: xgene: Read tx/rx delay for ACPI
  rocker: fix kcalloc parameter order
  rds: Fix non-atomic operation on shared flag variable
  net: sched: don't use GFP_KERNEL under spin lock
  vhost_net: correctly check tx avail during rx busy polling
  net: mdio-mux: add mdio_mux parameter to mdio_mux_init()
  rxrpc: Make service connection lookup always check for retry
  net: stmmac: Delete dead code for MDIO registration
  gianfar: Fix Tx flow control deactivation
  cxgb4: Ignore MPS_TX_INT_CAUSE[Bubble] for T6
  cxgb4: Fix pause frame count in t4_get_port_stats
  cxgb4: fix memory leak
  tun: rename generic_xdp to skb_xdp
  tun: reserve extra headroom only when XDP is set
  net: dsa: bcm_sf2: Configure IMP port TC2QOS mapping
  net: dsa: bcm_sf2: Advertise number of egress queues
  ...

1 files changed, 21 insertions, 118 deletions

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 8a1eaf3..7e19051 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;
 }
@@ -1371,10 +1265,14 @@ static int vrf_validate(struct nlattr *tb[], struct nlattr *data[],
 			struct netlink_ext_ack *extack)
 {
 	if (tb[IFLA_ADDRESS]) {
-		if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN)
+		if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) {
+			NL_SET_ERR_MSG(extack, "Invalid hardware address");
 			return -EINVAL;
-		if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS])))
+		}
+		if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) {
+			NL_SET_ERR_MSG(extack, "Invalid hardware address");
 			return -EADDRNOTAVAIL;
+		}
 	}
 	return 0;
 }
@@ -1399,12 +1297,17 @@ static int vrf_newlink(struct net *src_net, struct net_device *dev,
 	struct net *net;
 	int err;
 
-	if (!data || !data[IFLA_VRF_TABLE])
+	if (!data || !data[IFLA_VRF_TABLE]) {
+		NL_SET_ERR_MSG(extack, "VRF table id is missing");
 		return -EINVAL;
+	}
 
 	vrf->tb_id = nla_get_u32(data[IFLA_VRF_TABLE]);
-	if (vrf->tb_id == RT_TABLE_UNSPEC)
+	if (vrf->tb_id == RT_TABLE_UNSPEC) {
+		NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VRF_TABLE],
+				    "Invalid VRF table id");
 		return -EINVAL;
+	}
 
 	dev->priv_flags |= IFF_L3MDEV_MASTER;