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, 44 insertions, 37 deletions

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 38e795e0c4bf..db1c9e78c83c 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -380,8 +380,8 @@ int udp_v4_get_port(struct sock *sk, unsigned short snum)
 
 static int compute_score(struct sock *sk, struct net *net,
 			 __be32 saddr, __be16 sport,
-			 __be32 daddr, unsigned short hnum, int dif,
-			 bool exact_dif)
+			 __be32 daddr, unsigned short hnum,
+			 int dif, int sdif, bool exact_dif)
 {
 	int score;
 	struct inet_sock *inet;
@@ -413,10 +413,15 @@ static int compute_score(struct sock *sk, struct net *net,
 	}
 
 	if (sk->sk_bound_dev_if || exact_dif) {
-		if (sk->sk_bound_dev_if != dif)
+		bool dev_match = (sk->sk_bound_dev_if == dif ||
+				  sk->sk_bound_dev_if == sdif);
+
+		if (exact_dif && !dev_match)
 			return -1;
-		score += 4;
+		if (sk->sk_bound_dev_if && dev_match)
+			score += 4;
 	}
+
 	if (sk->sk_incoming_cpu == raw_smp_processor_id())
 		score++;
 	return score;
@@ -436,10 +441,11 @@ static u32 udp_ehashfn(const struct net *net, const __be32 laddr,
 
 /* called with rcu_read_lock() */
 static struct sock *udp4_lib_lookup2(struct net *net,
-		__be32 saddr, __be16 sport,
-		__be32 daddr, unsigned int hnum, int dif, bool exact_dif,
-		struct udp_hslot *hslot2,
-		struct sk_buff *skb)
+				     __be32 saddr, __be16 sport,
+				     __be32 daddr, unsigned int hnum,
+				     int dif, int sdif, bool exact_dif,
+				     struct udp_hslot *hslot2,
+				     struct sk_buff *skb)
 {
 	struct sock *sk, *result;
 	int score, badness, matches = 0, reuseport = 0;
@@ -449,7 +455,7 @@ static struct sock *udp4_lib_lookup2(struct net *net,
 	badness = 0;
 	udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
 		score = compute_score(sk, net, saddr, sport,
-				      daddr, hnum, dif, exact_dif);
+				      daddr, hnum, dif, sdif, exact_dif);
 		if (score > badness) {
 			reuseport = sk->sk_reuseport;
 			if (reuseport) {
@@ -477,8 +483,8 @@ static struct sock *udp4_lib_lookup2(struct net *net,
  * harder than this. -DaveM
  */
 struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
-		__be16 sport, __be32 daddr, __be16 dport,
-		int dif, struct udp_table *udptable, struct sk_buff *skb)
+		__be16 sport, __be32 daddr, __be16 dport, int dif,
+		int sdif, struct udp_table *udptable, struct sk_buff *skb)
 {
 	struct sock *sk, *result;
 	unsigned short hnum = ntohs(dport);
@@ -496,7 +502,7 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
 			goto begin;
 
 		result = udp4_lib_lookup2(net, saddr, sport,
-					  daddr, hnum, dif,
+					  daddr, hnum, dif, sdif,
 					  exact_dif, hslot2, skb);
 		if (!result) {
 			unsigned int old_slot2 = slot2;
@@ -511,7 +517,7 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
 				goto begin;
 
 			result = udp4_lib_lookup2(net, saddr, sport,
-						  daddr, hnum, dif,
+						  daddr, hnum, dif, sdif,
 						  exact_dif, hslot2, skb);
 		}
 		return result;
@@ -521,7 +527,7 @@ begin:
 	badness = 0;
 	sk_for_each_rcu(sk, &hslot->head) {
 		score = compute_score(sk, net, saddr, sport,
-				      daddr, hnum, dif, exact_dif);
+				      daddr, hnum, dif, sdif, exact_dif);
 		if (score > badness) {
 			reuseport = sk->sk_reuseport;
 			if (reuseport) {
@@ -554,7 +560,7 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb,
 
 	return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport,
 				 iph->daddr, dport, inet_iif(skb),
-				 udptable, skb);
+				 inet_sdif(skb), udptable, skb);
 }
 
 struct sock *udp4_lib_lookup_skb(struct sk_buff *skb,
@@ -576,7 +582,7 @@ struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
 	struct sock *sk;
 
 	sk = __udp4_lib_lookup(net, saddr, sport, daddr, dport,
-			       dif, &udp_table, NULL);
+			       dif, 0, &udp_table, NULL);
 	if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
 		sk = NULL;
 	return sk;
@@ -587,7 +593,7 @@ EXPORT_SYMBOL_GPL(udp4_lib_lookup);
 static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk,
 				       __be16 loc_port, __be32 loc_addr,
 				       __be16 rmt_port, __be32 rmt_addr,
-				       int dif, unsigned short hnum)
+				       int dif, int sdif, unsigned short hnum)
 {
 	struct inet_sock *inet = inet_sk(sk);
 
@@ -597,9 +603,10 @@ static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk,
 	    (inet->inet_dport != rmt_port && inet->inet_dport) ||
 	    (inet->inet_rcv_saddr && inet->inet_rcv_saddr != loc_addr) ||
 	    ipv6_only_sock(sk) ||
-	    (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif))
+	    (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif &&
+	     sk->sk_bound_dev_if != sdif))
 		return false;
-	if (!ip_mc_sf_allow(sk, loc_addr, rmt_addr, dif))
+	if (!ip_mc_sf_allow(sk, loc_addr, rmt_addr, dif, sdif))
 		return false;
 	return true;
 }
@@ -628,8 +635,8 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 	struct net *net = dev_net(skb->dev);
 
 	sk = __udp4_lib_lookup(net, iph->daddr, uh->dest,
-			iph->saddr, uh->source, skb->dev->ifindex, udptable,
-			NULL);
+			       iph->saddr, uh->source, skb->dev->ifindex, 0,
+			       udptable, NULL);
 	if (!sk) {
 		__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
 		return;	/* No socket for error */
@@ -802,7 +809,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4)
 	if (is_udplite)  				 /*     UDP-Lite      */
 		csum = udplite_csum(skb);
 
-	else if (sk->sk_no_check_tx && !skb_is_gso(skb)) {   /* UDP csum off */
+	else if (sk->sk_no_check_tx) {			 /* UDP csum off */
 
 		skb->ip_summed = CHECKSUM_NONE;
 		goto send;
@@ -1176,7 +1183,11 @@ static void udp_set_dev_scratch(struct sk_buff *skb)
 	scratch->csum_unnecessary = !!skb_csum_unnecessary(skb);
 	scratch->is_linear = !skb_is_nonlinear(skb);
 #endif
-	if (likely(!skb->_skb_refdst && !skb_sec_path(skb)))
+	/* all head states execept sp (dst, sk, nf) are always cleared by
+	 * udp_rcv() and we need to preserve secpath, if present, to eventually
+	 * process IP_CMSG_PASSSEC at recvmsg() time
+	 */
+	if (likely(!skb_sec_path(skb)))
 		scratch->_tsize_state |= UDP_SKB_IS_STATELESS;
 }
 
@@ -1783,13 +1794,6 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		sk_mark_napi_id_once(sk, skb);
 	}
 
-	/* At recvmsg() time we may access skb->dst or skb->sp depending on
-	 * the IP options and the cmsg flags, elsewhere can we clear all
-	 * pending head states while they are hot in the cache
-	 */
-	if (likely(IPCB(skb)->opt.optlen == 0 && !skb_sec_path(skb)))
-		skb_release_head_state(skb);
-
 	rc = __udp_enqueue_schedule_skb(sk, skb);
 	if (rc < 0) {
 		int is_udplite = IS_UDPLITE(sk);
@@ -1958,6 +1962,7 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 	unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10);
 	unsigned int offset = offsetof(typeof(*sk), sk_node);
 	int dif = skb->dev->ifindex;
+	int sdif = inet_sdif(skb);
 	struct hlist_node *node;
 	struct sk_buff *nskb;
 
@@ -1972,7 +1977,7 @@ start_lookup:
 
 	sk_for_each_entry_offset_rcu(sk, node, &hslot->head, offset) {
 		if (!__udp_is_mcast_sock(net, sk, uh->dest, daddr,
-					 uh->source, saddr, dif, hnum))
+					 uh->source, saddr, dif, sdif, hnum))
 			continue;
 
 		if (!first) {
@@ -2162,7 +2167,7 @@ drop:
 static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net,
 						  __be16 loc_port, __be32 loc_addr,
 						  __be16 rmt_port, __be32 rmt_addr,
-						  int dif)
+						  int dif, int sdif)
 {
 	struct sock *sk, *result;
 	unsigned short hnum = ntohs(loc_port);
@@ -2176,7 +2181,7 @@ static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net,
 	result = NULL;
 	sk_for_each_rcu(sk, &hslot->head) {
 		if (__udp_is_mcast_sock(net, sk, loc_port, loc_addr,
-					rmt_port, rmt_addr, dif, hnum)) {
+					rmt_port, rmt_addr, dif, sdif, hnum)) {
 			if (result)
 				return NULL;
 			result = sk;
@@ -2193,7 +2198,7 @@ static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net,
 static struct sock *__udp4_lib_demux_lookup(struct net *net,
 					    __be16 loc_port, __be32 loc_addr,
 					    __be16 rmt_port, __be32 rmt_addr,
-					    int dif)
+					    int dif, int sdif)
 {
 	unsigned short hnum = ntohs(loc_port);
 	unsigned int hash2 = udp4_portaddr_hash(net, loc_addr, hnum);
@@ -2205,7 +2210,7 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net,
 
 	udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
 		if (INET_MATCH(sk, net, acookie, rmt_addr,
-			       loc_addr, ports, dif))
+			       loc_addr, ports, dif, sdif))
 			return sk;
 		/* Only check first socket in chain */
 		break;
@@ -2221,6 +2226,7 @@ void udp_v4_early_demux(struct sk_buff *skb)
 	struct sock *sk = NULL;
 	struct dst_entry *dst;
 	int dif = skb->dev->ifindex;
+	int sdif = inet_sdif(skb);
 	int ours;
 
 	/* validate the packet */
@@ -2246,10 +2252,11 @@ void udp_v4_early_demux(struct sk_buff *skb)
 		}
 
 		sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr,
-						   uh->source, iph->saddr, dif);
+						   uh->source, iph->saddr,
+						   dif, sdif);
 	} else if (skb->pkt_type == PACKET_HOST) {
 		sk = __udp4_lib_demux_lookup(net, uh->dest, iph->daddr,
-					     uh->source, iph->saddr, dif);
+					     uh->source, iph->saddr, dif, sdif);
 	}
 
 	if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt))