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

Pull networking fixes from David Miller:

 1) Fix PCI IDs of 9000 series iwlwifi devices, from Luca Coelho.

 2) bpf offload bug fixes from Jakub Kicinski.

 3) Fix bpf verifier to NOP out code which is dead at run time because
    due to branch pruning the verifier will not explore such
    instructions. From Alexei Starovoitov.

 4) Fix crash when deleting secondary chains in packet scheduler
    classifier. From Roman Kapl.

 5) Fix buffer management bugs in smc, from Ursula Braun.

 6) Fix regression in anycast route handling, from David Ahern.

 7) Fix link settings regression in r8169, from Tobias Jakobi.

 8) Add back enough UFO support so that live migration still works, from
    Willem de Bruijn.

 9) Linearize enough packet data for the full extent to which the ipvlan
    code will inspect the packet headers, from Gao Feng.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (46 commits)
  ipvlan: Fix insufficient skb linear check for ipv6 icmp
  ipvlan: Fix insufficient skb linear check for arp
  geneve: only configure or fill UDP_ZERO_CSUM6_RX/TX info when CONFIG_IPV6
  net: dsa: bcm_sf2: Clear IDDQ_GLOBAL_PWR bit for PHY
  net: accept UFO datagrams from tuntap and packet
  net: realtek: r8169: implement set_link_ksettings()
  net: ipv6: Fixup device for anycast routes during copy
  net/smc: Fix preinitialization of buf_desc in __smc_buf_create()
  net/smc: use sk_rcvbuf as start for rmb creation
  ipv6: Do not consider linkdown nexthops during multipath
  net: sched: fix crash when deleting secondary chains
  net: phy: cortina: add missing MODULE_DESCRIPTION/AUTHOR/LICENSE
  bpf: fix branch pruning logic
  bpf: change bpf_perf_event_output arg5 type to ARG_CONST_SIZE_OR_ZERO
  bpf: change bpf_probe_read_str arg2 type to ARG_CONST_SIZE_OR_ZERO
  bpf: remove explicit handling of 0 for arg2 in bpf_probe_read
  bpf: introduce ARG_PTR_TO_MEM_OR_NULL
  i40evf: Use smp_rmb rather than read_barrier_depends
  fm10k: Use smp_rmb rather than read_barrier_depends
  igb: Use smp_rmb rather than read_barrier_depends
  ...

3 files changed, 119 insertions, 4 deletions

diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index 4a7e5ffa5108..4fe7c90962dd 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -31,6 +31,37 @@ static u32 __ipv6_select_ident(struct net *net, u32 hashrnd,
 	return id;
 }
 
+/* This function exists only for tap drivers that must support broken
+ * clients requesting UFO without specifying an IPv6 fragment ID.
+ *
+ * This is similar to ipv6_select_ident() but we use an independent hash
+ * seed to limit information leakage.
+ *
+ * The network header must be set before calling this.
+ */
+__be32 ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb)
+{
+	static u32 ip6_proxy_idents_hashrnd __read_mostly;
+	struct in6_addr buf[2];
+	struct in6_addr *addrs;
+	u32 id;
+
+	addrs = skb_header_pointer(skb,
+				   skb_network_offset(skb) +
+				   offsetof(struct ipv6hdr, saddr),
+				   sizeof(buf), buf);
+	if (!addrs)
+		return 0;
+
+	net_get_random_once(&ip6_proxy_idents_hashrnd,
+			    sizeof(ip6_proxy_idents_hashrnd));
+
+	id = __ipv6_select_ident(net, ip6_proxy_idents_hashrnd,
+				 &addrs[1], &addrs[0]);
+	return htonl(id);
+}
+EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident);
+
 __be32 ipv6_select_ident(struct net *net,
 			 const struct in6_addr *daddr,
 			 const struct in6_addr *saddr)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 05eb7bc36156..7a8d1500d374 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -472,6 +472,11 @@ static struct rt6_info *rt6_multipath_select(struct rt6_info *match,
 				&match->rt6i_siblings, rt6i_siblings) {
 			route_choosen--;
 			if (route_choosen == 0) {
+				struct inet6_dev *idev = sibling->rt6i_idev;
+
+				if (!netif_carrier_ok(sibling->dst.dev) &&
+				    idev->cnf.ignore_routes_with_linkdown)
+					break;
 				if (rt6_score_route(sibling, oif, strict) < 0)
 					break;
 				match = sibling;
@@ -1019,7 +1024,7 @@ static struct net_device *ip6_rt_get_dev_rcu(struct rt6_info *rt)
 {
 	struct net_device *dev = rt->dst.dev;
 
-	if (rt->rt6i_flags & RTF_LOCAL) {
+	if (rt->rt6i_flags & (RTF_LOCAL | RTF_ANYCAST)) {
 		/* for copies of local routes, dst->dev needs to be the
 		 * device if it is a master device, the master device if
 		 * device is enslaved, and the loopback as the default
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 455fd4e39333..a0f89ad76f9d 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -17,15 +17,94 @@
 #include <net/ip6_checksum.h>
 #include "ip6_offload.h"
 
-static struct sk_buff *udp6_tunnel_segment(struct sk_buff *skb,
-					   netdev_features_t features)
+static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
+					 netdev_features_t features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	unsigned int mss;
+	unsigned int unfrag_ip6hlen, unfrag_len;
+	struct frag_hdr *fptr;
+	u8 *packet_start, *prevhdr;
+	u8 nexthdr;
+	u8 frag_hdr_sz = sizeof(struct frag_hdr);
+	__wsum csum;
+	int tnl_hlen;
+	int err;
+
+	mss = skb_shinfo(skb)->gso_size;
+	if (unlikely(skb->len <= mss))
+		goto out;
 
 	if (skb->encapsulation && skb_shinfo(skb)->gso_type &
 	    (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))
 		segs = skb_udp_tunnel_segment(skb, features, true);
+	else {
+		const struct ipv6hdr *ipv6h;
+		struct udphdr *uh;
+
+		if (!pskb_may_pull(skb, sizeof(struct udphdr)))
+			goto out;
+
+		/* Do software UFO. Complete and fill in the UDP checksum as HW cannot
+		 * do checksum of UDP packets sent as multiple IP fragments.
+		 */
+
+		uh = udp_hdr(skb);
+		ipv6h = ipv6_hdr(skb);
+
+		uh->check = 0;
+		csum = skb_checksum(skb, 0, skb->len, 0);
+		uh->check = udp_v6_check(skb->len, &ipv6h->saddr,
+					  &ipv6h->daddr, csum);
+		if (uh->check == 0)
+			uh->check = CSUM_MANGLED_0;
+
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+		/* If there is no outer header we can fake a checksum offload
+		 * due to the fact that we have already done the checksum in
+		 * software prior to segmenting the frame.
+		 */
+		if (!skb->encap_hdr_csum)
+			features |= NETIF_F_HW_CSUM;
+
+		/* Check if there is enough headroom to insert fragment header. */
+		tnl_hlen = skb_tnl_header_len(skb);
+		if (skb->mac_header < (tnl_hlen + frag_hdr_sz)) {
+			if (gso_pskb_expand_head(skb, tnl_hlen + frag_hdr_sz))
+				goto out;
+		}
+
+		/* Find the unfragmentable header and shift it left by frag_hdr_sz
+		 * bytes to insert fragment header.
+		 */
+		err = ip6_find_1stfragopt(skb, &prevhdr);
+		if (err < 0)
+			return ERR_PTR(err);
+		unfrag_ip6hlen = err;
+		nexthdr = *prevhdr;
+		*prevhdr = NEXTHDR_FRAGMENT;
+		unfrag_len = (skb_network_header(skb) - skb_mac_header(skb)) +
+			     unfrag_ip6hlen + tnl_hlen;
+		packet_start = (u8 *) skb->head + SKB_GSO_CB(skb)->mac_offset;
+		memmove(packet_start-frag_hdr_sz, packet_start, unfrag_len);
+
+		SKB_GSO_CB(skb)->mac_offset -= frag_hdr_sz;
+		skb->mac_header -= frag_hdr_sz;
+		skb->network_header -= frag_hdr_sz;
+
+		fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen);
+		fptr->nexthdr = nexthdr;
+		fptr->reserved = 0;
+		fptr->identification = ipv6_proxy_select_ident(dev_net(skb->dev), skb);
+
+		/* Fragment the skb. ipv6 header and the remaining fields of the
+		 * fragment header are updated in ipv6_gso_segment()
+		 */
+		segs = skb_segment(skb, features);
+	}
 
+out:
 	return segs;
 }
 
@@ -75,7 +154,7 @@ static int udp6_gro_complete(struct sk_buff *skb, int nhoff)
 
 static const struct net_offload udpv6_offload = {
 	.callbacks = {
-		.gso_segment	=	udp6_tunnel_segment,
+		.gso_segment	=	udp6_ufo_fragment,
 		.gro_receive	=	udp6_gro_receive,
 		.gro_complete	=	udp6_gro_complete,
 	},