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

Pull networking updates from David Miller:

 1) Missing netlink attribute validation in nft_lookup, from Patrick
    McHardy.

 2) Restrict ipv6 partial checksum handling to UDP, since that's the
    only case it works for.  From Vlad Yasevich.

 3) Clear out silly device table sentinal macros used by SSB and BCMA
    drivers.  From Joe Perches.

 4) Make sure the remote checksum code never creates a situation where
    the remote checksum is applied yet the tunneling metadata describing
    the remote checksum transformation is still present.  Otherwise an
    external entity might see this and apply the checksum again.  From
    Tom Herbert.

 5) Use msecs_to_jiffies() where applicable, from Nicholas Mc Guire.

 6) Don't explicitly initialize timer struct fields, use setup_timer()
    and mod_timer() instead.  From Vaishali Thakkar.

 7) Don't invoke tg3_halt() without the tp->lock held, from Jun'ichi
    Nomura.

 8) Missing __percpu annotation in ipvlan driver, from Eric Dumazet.

 9) Don't potentially perform skb_get() on shared skbs, also from Eric
    Dumazet.

10) Fix COW'ing of metrics for non-DST_HOST routes in ipv6, from Martin
    KaFai Lau.

11) Fix merge resolution error between the iov_iter changes in vhost and
    some bug fixes that occurred at the same time.  From Jason Wang.

12) If rtnl_configure_link() fails we have to perform a call to
    ->dellink() before unregistering the device.  From WANG Cong.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (39 commits)
  net: dsa: Set valid phy interface type
  rtnetlink: call ->dellink on failure when ->newlink exists
  com20020-pci: add support for eae single card
  vhost_net: fix wrong iter offset when setting number of buffers
  net: spelling fixes
  net/core: Fix warning while make xmldocs caused by dev.c
  net: phy: micrel: disable NAND-tree for KSZ8021, KSZ8031, KSZ8051, KSZ8081
  ipv6: fix ipv6_cow_metrics for non DST_HOST case
  openvswitch: Fix key serialization.
  r8152: restore hw settings
  hso: fix rx parsing logic when skb allocation fails
  tcp: make sure skb is not shared before using skb_get()
  bridge: netfilter: Move sysctl-specific error code inside #ifdef
  ipv6: fix possible deadlock in ip6_fl_purge / ip6_fl_gc
  ipvlan: add a missing __percpu pcpu_stats
  tg3: Hold tp->lock before calling tg3_halt() from tg3_init_one()
  bgmac: fix device initialization on Northstar SoCs (condition typo)
  qlcnic: Delete existing multicast MAC list before adding new
  net/mlx5_core: Fix configuration of log_uar_page_sz
  sunvnet: don't change gso data on clones
  ...

4 files changed, 66 insertions, 23 deletions

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index f0b4a31d7bd6..3a8985c94581 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1186,7 +1186,7 @@ __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope)
 no_in_dev:
 
 	/* Not loopback addresses on loopback should be preferred
-	   in this case. It is importnat that lo is the first interface
+	   in this case. It is important that lo is the first interface
 	   in dev_base list.
 	 */
 	for_each_netdev_rcu(net, dev) {
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 92ddea1e6457..ff069f6597ac 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -22,14 +22,18 @@ static LIST_HEAD(fou_list);
 struct fou {
 	struct socket *sock;
 	u8 protocol;
+	u8 flags;
 	u16 port;
 	struct udp_offload udp_offloads;
 	struct list_head list;
 };
 
+#define FOU_F_REMCSUM_NOPARTIAL BIT(0)
+
 struct fou_cfg {
 	u16 type;
 	u8 protocol;
+	u8 flags;
 	struct udp_port_cfg udp_config;
 };
 
@@ -64,24 +68,20 @@ static int fou_udp_recv(struct sock *sk, struct sk_buff *skb)
 }
 
 static struct guehdr *gue_remcsum(struct sk_buff *skb, struct guehdr *guehdr,
-				  void *data, size_t hdrlen, u8 ipproto)
+				  void *data, size_t hdrlen, u8 ipproto,
+				  bool nopartial)
 {
 	__be16 *pd = data;
 	size_t start = ntohs(pd[0]);
 	size_t offset = ntohs(pd[1]);
 	size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start);
 
-	if (skb->remcsum_offload) {
-		/* Already processed in GRO path */
-		skb->remcsum_offload = 0;
-		return guehdr;
-	}
-
 	if (!pskb_may_pull(skb, plen))
 		return NULL;
 	guehdr = (struct guehdr *)&udp_hdr(skb)[1];
 
-	skb_remcsum_process(skb, (void *)guehdr + hdrlen, start, offset);
+	skb_remcsum_process(skb, (void *)guehdr + hdrlen,
+			    start, offset, nopartial);
 
 	return guehdr;
 }
@@ -142,7 +142,9 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
 
 		if (flags & GUE_PFLAG_REMCSUM) {
 			guehdr = gue_remcsum(skb, guehdr, data + doffset,
-					     hdrlen, guehdr->proto_ctype);
+					     hdrlen, guehdr->proto_ctype,
+					     !!(fou->flags &
+						FOU_F_REMCSUM_NOPARTIAL));
 			if (!guehdr)
 				goto drop;
 
@@ -214,7 +216,8 @@ out_unlock:
 
 static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off,
 				      struct guehdr *guehdr, void *data,
-				      size_t hdrlen, u8 ipproto)
+				      size_t hdrlen, u8 ipproto,
+				      struct gro_remcsum *grc, bool nopartial)
 {
 	__be16 *pd = data;
 	size_t start = ntohs(pd[0]);
@@ -222,7 +225,7 @@ static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off,
 	size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start);
 
 	if (skb->remcsum_offload)
-		return guehdr;
+		return NULL;
 
 	if (!NAPI_GRO_CB(skb)->csum_valid)
 		return NULL;
@@ -234,7 +237,8 @@ static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off,
 			return NULL;
 	}
 
-	skb_gro_remcsum_process(skb, (void *)guehdr + hdrlen, start, offset);
+	skb_gro_remcsum_process(skb, (void *)guehdr + hdrlen,
+				start, offset, grc, nopartial);
 
 	skb->remcsum_offload = 1;
 
@@ -254,6 +258,10 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head,
 	void *data;
 	u16 doffset = 0;
 	int flush = 1;
+	struct fou *fou = container_of(uoff, struct fou, udp_offloads);
+	struct gro_remcsum grc;
+
+	skb_gro_remcsum_init(&grc);
 
 	off = skb_gro_offset(skb);
 	len = off + sizeof(*guehdr);
@@ -295,7 +303,9 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head,
 		if (flags & GUE_PFLAG_REMCSUM) {
 			guehdr = gue_gro_remcsum(skb, off, guehdr,
 						 data + doffset, hdrlen,
-						 guehdr->proto_ctype);
+						 guehdr->proto_ctype, &grc,
+						 !!(fou->flags &
+						    FOU_F_REMCSUM_NOPARTIAL));
 			if (!guehdr)
 				goto out;
 
@@ -345,6 +355,7 @@ out_unlock:
 	rcu_read_unlock();
 out:
 	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_gro_remcsum_cleanup(skb, &grc);
 
 	return pp;
 }
@@ -455,6 +466,7 @@ static int fou_create(struct net *net, struct fou_cfg *cfg,
 
 	sk = sock->sk;
 
+	fou->flags = cfg->flags;
 	fou->port = cfg->udp_config.local_udp_port;
 
 	/* Initial for fou type */
@@ -541,6 +553,7 @@ static struct nla_policy fou_nl_policy[FOU_ATTR_MAX + 1] = {
 	[FOU_ATTR_AF] = { .type = NLA_U8, },
 	[FOU_ATTR_IPPROTO] = { .type = NLA_U8, },
 	[FOU_ATTR_TYPE] = { .type = NLA_U8, },
+	[FOU_ATTR_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG, },
 };
 
 static int parse_nl_config(struct genl_info *info,
@@ -571,6 +584,9 @@ static int parse_nl_config(struct genl_info *info,
 	if (info->attrs[FOU_ATTR_TYPE])
 		cfg->type = nla_get_u8(info->attrs[FOU_ATTR_TYPE]);
 
+	if (info->attrs[FOU_ATTR_REMCSUM_NOPARTIAL])
+		cfg->flags |= FOU_F_REMCSUM_NOPARTIAL;
+
 	return 0;
 }
 
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 53db2c309572..ea82fd492c1b 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -134,6 +134,7 @@ static bool tcp_fastopen_create_child(struct sock *sk,
 	struct tcp_sock *tp;
 	struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
 	struct sock *child;
+	u32 end_seq;
 
 	req->num_retrans = 0;
 	req->num_timeout = 0;
@@ -185,20 +186,35 @@ static bool tcp_fastopen_create_child(struct sock *sk,
 
 	/* Queue the data carried in the SYN packet. We need to first
 	 * bump skb's refcnt because the caller will attempt to free it.
+	 * Note that IPv6 might also have used skb_get() trick
+	 * in tcp_v6_conn_request() to keep this SYN around (treq->pktopts)
+	 * So we need to eventually get a clone of the packet,
+	 * before inserting it in sk_receive_queue.
 	 *
 	 * XXX (TFO) - we honor a zero-payload TFO request for now,
 	 * (any reason not to?) but no need to queue the skb since
 	 * there is no data. How about SYN+FIN?
 	 */
-	if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1) {
-		skb = skb_get(skb);
-		skb_dst_drop(skb);
-		__skb_pull(skb, tcp_hdr(skb)->doff * 4);
-		skb_set_owner_r(skb, child);
-		__skb_queue_tail(&child->sk_receive_queue, skb);
-		tp->syn_data_acked = 1;
+	end_seq = TCP_SKB_CB(skb)->end_seq;
+	if (end_seq != TCP_SKB_CB(skb)->seq + 1) {
+		struct sk_buff *skb2;
+
+		if (unlikely(skb_shared(skb)))
+			skb2 = skb_clone(skb, GFP_ATOMIC);
+		else
+			skb2 = skb_get(skb);
+
+		if (likely(skb2)) {
+			skb_dst_drop(skb2);
+			__skb_pull(skb2, tcp_hdrlen(skb));
+			skb_set_owner_r(skb2, child);
+			__skb_queue_tail(&child->sk_receive_queue, skb2);
+			tp->syn_data_acked = 1;
+		} else {
+			end_seq = TCP_SKB_CB(skb)->seq + 1;
+		}
 	}
-	tcp_rsk(req)->rcv_nxt = tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+	tcp_rsk(req)->rcv_nxt = tp->rcv_nxt = end_seq;
 	sk->sk_data_ready(sk);
 	bh_unlock_sock(child);
 	sock_put(child);
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index d10f6f4ead27..4915d8284a86 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -402,6 +402,13 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff)
 	}
 
 	rcu_read_unlock();
+
+	if (skb->remcsum_offload)
+		skb_shinfo(skb)->gso_type |= SKB_GSO_TUNNEL_REMCSUM;
+
+	skb->encapsulation = 1;
+	skb_set_inner_mac_header(skb, nhoff + sizeof(struct udphdr));
+
 	return err;
 }
 
@@ -410,9 +417,13 @@ static int udp4_gro_complete(struct sk_buff *skb, int nhoff)
 	const struct iphdr *iph = ip_hdr(skb);
 	struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
 
-	if (uh->check)
+	if (uh->check) {
+		skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
 		uh->check = ~udp_v4_check(skb->len - nhoff, iph->saddr,
 					  iph->daddr, 0);
+	} else {
+		skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL;
+	}
 
 	return udp_gro_complete(skb, nhoff);
 }