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

Pull networking updates from David Miller:

 1) BBR TCP congestion control, from Neal Cardwell, Yuchung Cheng and
    co. at Google. https://lwn.net/Articles/701165/

 2) Do TCP Small Queues for retransmits, from Eric Dumazet.

 3) Support collect_md mode for all IPV4 and IPV6 tunnels, from Alexei
    Starovoitov.

 4) Allow cls_flower to classify packets in ip tunnels, from Amir Vadai.

 5) Support DSA tagging in older mv88e6xxx switches, from Andrew Lunn.

 6) Support GMAC protocol in iwlwifi mwm, from Ayala Beker.

 7) Support ndo_poll_controller in mlx5, from Calvin Owens.

 8) Move VRF processing to an output hook and allow l3mdev to be
    loopback, from David Ahern.

 9) Support SOCK_DESTROY for UDP sockets. Also from David Ahern.

10) Congestion control in RXRPC, from David Howells.

11) Support geneve RX offload in ixgbe, from Emil Tantilov.

12) When hitting pressure for new incoming TCP data SKBs, perform a
    partial rathern than a full purge of the OFO queue (which could be
    huge). From Eric Dumazet.

13) Convert XFRM state and policy lookups to RCU, from Florian Westphal.

14) Support RX network flow classification to igb, from Gangfeng Huang.

15) Hardware offloading of eBPF in nfp driver, from Jakub Kicinski.

16) New skbmod packet action, from Jamal Hadi Salim.

17) Remove some inefficiencies in snmp proc output, from Jia He.

18) Add FIB notifications to properly propagate route changes to
    hardware which is doing forwarding offloading. From Jiri Pirko.

19) New dsa driver for qca8xxx chips, from John Crispin.

20) Implement RFC7559 ipv6 router solicitation backoff, from Maciej
    Żenczykowski.

21) Add L3 mode to ipvlan, from Mahesh Bandewar.

22) Support 802.1ad in mlx4, from Moshe Shemesh.

23) Support hardware LRO in mediatek driver, from Nelson Chang.

24) Add TC offloading to mlx5, from Or Gerlitz.

25) Convert various drivers to ethtool ksettings interfaces, from
    Philippe Reynes.

26) TX max rate limiting for cxgb4, from Rahul Lakkireddy.

27) NAPI support for ath10k, from Rajkumar Manoharan.

28) Support XDP in mlx5, from Rana Shahout and Saeed Mahameed.

29) UDP replicast support in TIPC, from Richard Alpe.

30) Per-queue statistics for qed driver, from Sudarsana Reddy Kalluru.

31) Support BQL in thunderx driver, from Sunil Goutham.

32) TSO support in alx driver, from Tobias Regnery.

33) Add stream parser engine and use it in kcm.

34) Support async DHCP replies in ipconfig module, from Uwe
    Kleine-König.

35) DSA port fast aging for mv88e6xxx driver, from Vivien Didelot.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1715 commits)
  mlxsw: switchx2: Fix misuse of hard_header_len
  mlxsw: spectrum: Fix misuse of hard_header_len
  net/faraday: Stop NCSI device on shutdown
  net/ncsi: Introduce ncsi_stop_dev()
  net/ncsi: Rework the channel monitoring
  net/ncsi: Allow to extend NCSI request properties
  net/ncsi: Rework request index allocation
  net/ncsi: Don't probe on the reserved channel ID (0x1f)
  net/ncsi: Introduce NCSI_RESERVED_CHANNEL
  net/ncsi: Avoid unused-value build warning from ia64-linux-gcc
  net: Add netdev all_adj_list refcnt propagation to fix panic
  net: phy: Add Edge-rate driver for Microsemi PHYs.
  vmxnet3: Wake queue from reset work
  i40e: avoid NULL pointer dereference and recursive errors on early PCI error
  qed: Add RoCE ll2 & GSI support
  qed: Add support for memory registeration verbs
  qed: Add support for QP verbs
  qed: PD,PKEY and CQ verb support
  qed: Add support for RoCE hw init
  qede: Add qedr framework
  ...

1 files changed, 146 insertions, 148 deletions

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 1ce7420322ee..85c271c70d42 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -37,9 +37,6 @@
 #include <net/l3mdev.h>
 #include <net/fib_rules.h>
 
-#define RT_FL_TOS(oldflp4) \
-	((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))
-
 #define DRV_NAME	"vrf"
 #define DRV_VERSION	"1.0"
 
@@ -137,6 +134,20 @@ static int vrf_local_xmit(struct sk_buff *skb, struct net_device *dev,
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
+static int vrf_ip6_local_out(struct net *net, struct sock *sk,
+			     struct sk_buff *skb)
+{
+	int err;
+
+	err = nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net,
+		      sk, skb, NULL, skb_dst(skb)->dev, dst_output);
+
+	if (likely(err == 1))
+		err = dst_output(net, sk, skb);
+
+	return err;
+}
+
 static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
 					   struct net_device *dev)
 {
@@ -151,7 +162,7 @@ static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
 		.flowlabel = ip6_flowinfo(iph),
 		.flowi6_mark = skb->mark,
 		.flowi6_proto = iph->nexthdr,
-		.flowi6_flags = FLOWI_FLAG_L3MDEV_SRC | FLOWI_FLAG_SKIP_NH_OIF,
+		.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF,
 	};
 	int ret = NET_XMIT_DROP;
 	struct dst_entry *dst;
@@ -207,7 +218,7 @@ static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
 	/* strip the ethernet header added for pass through VRF device */
 	__skb_pull(skb, skb_network_offset(skb));
 
-	ret = ip6_local_out(net, skb->sk, skb);
+	ret = vrf_ip6_local_out(net, skb->sk, skb);
 	if (unlikely(net_xmit_eval(ret)))
 		dev->stats.tx_errors++;
 	else
@@ -227,6 +238,20 @@ static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
 }
 #endif
 
+/* based on ip_local_out; can't use it b/c the dst is switched pointing to us */
+static int vrf_ip_local_out(struct net *net, struct sock *sk,
+			    struct sk_buff *skb)
+{
+	int err;
+
+	err = nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk,
+		      skb, NULL, skb_dst(skb)->dev, dst_output);
+	if (likely(err == 1))
+		err = dst_output(net, sk, skb);
+
+	return err;
+}
+
 static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
 					   struct net_device *vrf_dev)
 {
@@ -237,8 +262,7 @@ static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
 		.flowi4_oif = vrf_dev->ifindex,
 		.flowi4_iif = LOOPBACK_IFINDEX,
 		.flowi4_tos = RT_TOS(ip4h->tos),
-		.flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_L3MDEV_SRC |
-				FLOWI_FLAG_SKIP_NH_OIF,
+		.flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_SKIP_NH_OIF,
 		.daddr = ip4h->daddr,
 	};
 	struct net *net = dev_net(vrf_dev);
@@ -292,7 +316,7 @@ static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
 					       RT_SCOPE_LINK);
 	}
 
-	ret = ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb);
+	ret = vrf_ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb);
 	if (unlikely(net_xmit_eval(ret)))
 		vrf_dev->stats.tx_errors++;
 	else
@@ -377,6 +401,43 @@ static int vrf_output6(struct net *net, struct sock *sk, struct sk_buff *skb)
 			    !(IP6CB(skb)->flags & IP6SKB_REROUTED));
 }
 
+/* set dst on skb to send packet to us via dev_xmit path. Allows
+ * packet to go through device based features such as qdisc, netfilter
+ * hooks and packet sockets with skb->dev set to vrf device.
+ */
+static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev,
+				   struct sock *sk,
+				   struct sk_buff *skb)
+{
+	struct net_vrf *vrf = netdev_priv(vrf_dev);
+	struct dst_entry *dst = NULL;
+	struct rt6_info *rt6;
+
+	/* don't divert link scope packets */
+	if (rt6_need_strict(&ipv6_hdr(skb)->daddr))
+		return skb;
+
+	rcu_read_lock();
+
+	rt6 = rcu_dereference(vrf->rt6);
+	if (likely(rt6)) {
+		dst = &rt6->dst;
+		dst_hold(dst);
+	}
+
+	rcu_read_unlock();
+
+	if (unlikely(!dst)) {
+		vrf_tx_error(vrf_dev, skb);
+		return NULL;
+	}
+
+	skb_dst_drop(skb);
+	skb_dst_set(skb, dst);
+
+	return skb;
+}
+
 /* holding rtnl */
 static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf)
 {
@@ -463,6 +524,13 @@ out:
 	return rc;
 }
 #else
+static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev,
+				   struct sock *sk,
+				   struct sk_buff *skb)
+{
+	return skb;
+}
+
 static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf)
 {
 }
@@ -531,6 +599,55 @@ static int vrf_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 			    !(IPCB(skb)->flags & IPSKB_REROUTED));
 }
 
+/* set dst on skb to send packet to us via dev_xmit path. Allows
+ * packet to go through device based features such as qdisc, netfilter
+ * hooks and packet sockets with skb->dev set to vrf device.
+ */
+static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev,
+				  struct sock *sk,
+				  struct sk_buff *skb)
+{
+	struct net_vrf *vrf = netdev_priv(vrf_dev);
+	struct dst_entry *dst = NULL;
+	struct rtable *rth;
+
+	rcu_read_lock();
+
+	rth = rcu_dereference(vrf->rth);
+	if (likely(rth)) {
+		dst = &rth->dst;
+		dst_hold(dst);
+	}
+
+	rcu_read_unlock();
+
+	if (unlikely(!dst)) {
+		vrf_tx_error(vrf_dev, skb);
+		return NULL;
+	}
+
+	skb_dst_drop(skb);
+	skb_dst_set(skb, dst);
+
+	return skb;
+}
+
+/* called with rcu lock held */
+static struct sk_buff *vrf_l3_out(struct net_device *vrf_dev,
+				  struct sock *sk,
+				  struct sk_buff *skb,
+				  u16 proto)
+{
+	switch (proto) {
+	case AF_INET:
+		return vrf_ip_out(vrf_dev, sk, skb);
+	case AF_INET6:
+		return vrf_ip6_out(vrf_dev, sk, skb);
+	}
+
+	return skb;
+}
+
 /* holding rtnl */
 static void vrf_rtable_release(struct net_device *dev, struct net_vrf *vrf)
 {
@@ -722,63 +839,6 @@ static u32 vrf_fib_table(const struct net_device *dev)
 	return vrf->tb_id;
 }
 
-static struct rtable *vrf_get_rtable(const struct net_device *dev,
-				     const struct flowi4 *fl4)
-{
-	struct rtable *rth = NULL;
-
-	if (!(fl4->flowi4_flags & FLOWI_FLAG_L3MDEV_SRC)) {
-		struct net_vrf *vrf = netdev_priv(dev);
-
-		rcu_read_lock();
-
-		rth = rcu_dereference(vrf->rth);
-		if (likely(rth))
-			dst_hold(&rth->dst);
-
-		rcu_read_unlock();
-	}
-
-	return rth;
-}
-
-/* called under rcu_read_lock */
-static int vrf_get_saddr(struct net_device *dev, struct flowi4 *fl4)
-{
-	struct fib_result res = { .tclassid = 0 };
-	struct net *net = dev_net(dev);
-	u32 orig_tos = fl4->flowi4_tos;
-	u8 flags = fl4->flowi4_flags;
-	u8 scope = fl4->flowi4_scope;
-	u8 tos = RT_FL_TOS(fl4);
-	int rc;
-
-	if (unlikely(!fl4->daddr))
-		return 0;
-
-	fl4->flowi4_flags |= FLOWI_FLAG_SKIP_NH_OIF;
-	fl4->flowi4_iif = LOOPBACK_IFINDEX;
-	/* make sure oif is set to VRF device for lookup */
-	fl4->flowi4_oif = dev->ifindex;
-	fl4->flowi4_tos = tos & IPTOS_RT_MASK;
-	fl4->flowi4_scope = ((tos & RTO_ONLINK) ?
-			     RT_SCOPE_LINK : RT_SCOPE_UNIVERSE);
-
-	rc = fib_lookup(net, fl4, &res, 0);
-	if (!rc) {
-		if (res.type == RTN_LOCAL)
-			fl4->saddr = res.fi->fib_prefsrc ? : fl4->daddr;
-		else
-			fib_select_path(net, &res, fl4, -1);
-	}
-
-	fl4->flowi4_flags = flags;
-	fl4->flowi4_tos = orig_tos;
-	fl4->flowi4_scope = scope;
-
-	return rc;
-}
-
 static int vrf_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	return 0;
@@ -970,106 +1030,44 @@ static struct sk_buff *vrf_l3_rcv(struct net_device *vrf_dev,
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
-static struct dst_entry *vrf_get_rt6_dst(const struct net_device *dev,
-					 struct flowi6 *fl6)
+/* send to link-local or multicast address via interface enslaved to
+ * VRF device. Force lookup to VRF table without changing flow struct
+ */
+static struct dst_entry *vrf_link_scope_lookup(const struct net_device *dev,
+					      struct flowi6 *fl6)
 {
-	bool need_strict = rt6_need_strict(&fl6->daddr);
-	struct net_vrf *vrf = netdev_priv(dev);
 	struct net *net = dev_net(dev);
+	int flags = RT6_LOOKUP_F_IFACE;
 	struct dst_entry *dst = NULL;
 	struct rt6_info *rt;
 
-	/* send to link-local or multicast address */
-	if (need_strict) {
-		int flags = RT6_LOOKUP_F_IFACE;
-
-		/* VRF device does not have a link-local address and
-		 * sending packets to link-local or mcast addresses over
-		 * a VRF device does not make sense
-		 */
-		if (fl6->flowi6_oif == dev->ifindex) {
-			struct dst_entry *dst = &net->ipv6.ip6_null_entry->dst;
-
-			dst_hold(dst);
-			return dst;
-		}
-
-		if (!ipv6_addr_any(&fl6->saddr))
-			flags |= RT6_LOOKUP_F_HAS_SADDR;
-
-		rt = vrf_ip6_route_lookup(net, dev, fl6, fl6->flowi6_oif, flags);
-		if (rt)
-			dst = &rt->dst;
-
-	} else if (!(fl6->flowi6_flags & FLOWI_FLAG_L3MDEV_SRC)) {
-
-		rcu_read_lock();
-
-		rt = rcu_dereference(vrf->rt6);
-		if (likely(rt)) {
-			dst = &rt->dst;
-			dst_hold(dst);
-		}
-
-		rcu_read_unlock();
+	/* VRF device does not have a link-local address and
+	 * sending packets to link-local or mcast addresses over
+	 * a VRF device does not make sense
+	 */
+	if (fl6->flowi6_oif == dev->ifindex) {
+		dst = &net->ipv6.ip6_null_entry->dst;
+		dst_hold(dst);
+		return dst;
 	}
 
-	/* make sure oif is set to VRF device for lookup */
-	if (!need_strict)
-		fl6->flowi6_oif = dev->ifindex;
-
-	return dst;
-}
-
-/* called under rcu_read_lock */
-static int vrf_get_saddr6(struct net_device *dev, const struct sock *sk,
-			  struct flowi6 *fl6)
-{
-	struct net *net = dev_net(dev);
-	struct dst_entry *dst;
-	struct rt6_info *rt;
-	int err;
-
-	if (rt6_need_strict(&fl6->daddr)) {
-		rt = vrf_ip6_route_lookup(net, dev, fl6, fl6->flowi6_oif,
-					  RT6_LOOKUP_F_IFACE);
-		if (unlikely(!rt))
-			return 0;
+	if (!ipv6_addr_any(&fl6->saddr))
+		flags |= RT6_LOOKUP_F_HAS_SADDR;
 
+	rt = vrf_ip6_route_lookup(net, dev, fl6, fl6->flowi6_oif, flags);
+	if (rt)
 		dst = &rt->dst;
-	} else {
-		__u8 flags = fl6->flowi6_flags;
 
-		fl6->flowi6_flags |= FLOWI_FLAG_L3MDEV_SRC;
-		fl6->flowi6_flags |= FLOWI_FLAG_SKIP_NH_OIF;
-
-		dst = ip6_route_output(net, sk, fl6);
-		rt = (struct rt6_info *)dst;
-
-		fl6->flowi6_flags = flags;
-	}
-
-	err = dst->error;
-	if (!err) {
-		err = ip6_route_get_saddr(net, rt, &fl6->daddr,
-					  sk ? inet6_sk(sk)->srcprefs : 0,
-					  &fl6->saddr);
-	}
-
-	dst_release(dst);
-
-	return err;
+	return dst;
 }
 #endif
 
 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,
+	.l3mdev_l3_out		= vrf_l3_out,
 #if IS_ENABLED(CONFIG_IPV6)
-	.l3mdev_get_rt6_dst	= vrf_get_rt6_dst,
-	.l3mdev_get_saddr6	= vrf_get_saddr6,
+	.l3mdev_link_scope_lookup = vrf_link_scope_lookup,
 #endif
 };