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

Pull networking fixes from David Miller:

 1) When we run a tap on netlink sockets, we have to copy mmap'd SKBs
    instead of cloning them.  From Daniel Borkmann.

 2) When converting classical BPF into eBPF, fix the setting of the
    source reg to BPF_REG_X.  From Tycho Andersen.

 3) Fix igmpv3/mldv2 report parsing in the bridge multicast code, from
    Linus Lussing.

 4) Fix dst refcounting for ipv6 tunnels, from Martin KaFai Lau.

 5) Set NLM_F_REPLACE flag properly when replacing ipv6 routes, from
    Roopa Prabhu.

 6) Add some new cxgb4 PCI device IDs, from Hariprasad Shenai.

 7) Fix headroom tests and SKB leaks in ipv6 fragmentation code, from
    Florian Westphal.

 8) Check DMA mapping errors in bna driver, from Ivan Vecera.

 9) Several 8139cp bug fixes (dev_kfree_skb_any in interrupt context,
    misclearing of interrupt status in TX timeout handler, etc.) from
    David Woodhouse.

10) In tipc, reset SKB header pointer after skb_linearize(), from Erik
    Hugne.

11) Fix autobind races et al. in netlink code, from Herbert Xu with
    help from Tejun Heo and others.

12) Missing SET_NETDEV_DEV in sunvnet driver, from Sowmini Varadhan.

13) Fix various races in timewait timer and reqsk_queue_hadh_req, from
    Eric Dumazet.

14) Fix array overruns in mac80211, from Johannes Berg and Dan
    Carpenter.

15) Fix data race in rhashtable_rehash_one(), from Dmitriy Vyukov.

16) Fix race between poll_one_napi and napi_disable, from Neil Horman.

17) Fix byte order in geneve tunnel port config, from John W Linville.

18) Fix handling of ARP replies over lightweight tunnels, from Jiri
    Benc.

19) We can loop when fib rule dumps cross multiple SKBs, fix from Wilson
    Kok and Roopa Prabhu.

20) Several reference count handling bug fixes in the PHY/MDIO layer
    from Russel King.

21) Fix lockdep splat in ppp_dev_uninit(), from Guillaume Nault.

22) Fix crash in icmp_route_lookup(), from David Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (116 commits)
  net: Fix panic in icmp_route_lookup
  net: update docbook comment for __mdiobus_register()
  ppp: fix lockdep splat in ppp_dev_uninit()
  net: via/Kconfig: GENERIC_PCI_IOMAP required if PCI not selected
  phy: marvell: add link partner advertised modes
  net: fix net_device refcounting
  phy: add phy_device_remove()
  phy: fixed-phy: properly validate phy in fixed_phy_update_state()
  net: fix phy refcounting in a bunch of drivers
  of_mdio: fix MDIO phy device refcounting
  phy: add proper phy struct device refcounting
  phy: fix mdiobus module safety
  net: dsa: fix of_mdio_find_bus() device refcount leak
  phy: fix of_mdio_find_bus() device refcount leak
  ip6_tunnel: Reduce log level in ip6_tnl_err() to debug
  ip6_gre: Reduce log level in ip6gre_err() to debug
  fib_rules: fix fib rule dumps across multiple skbs
  bnx2x: byte swap rss_key to comply to Toeplitz specs
  net: revert "net_sched: move tp->root allocation into fw_init()"
  lwtunnel: remove source and destination UDP port config option
  ...

6 files changed, 81 insertions, 41 deletions

diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig
index 2a071f470d57..d143aa9f6654 100644
--- a/net/openvswitch/Kconfig
+++ b/net/openvswitch/Kconfig
@@ -5,7 +5,8 @@
 config OPENVSWITCH
 	tristate "Open vSwitch"
 	depends on INET
-	depends on (!NF_CONNTRACK || NF_CONNTRACK)
+	depends on !NF_CONNTRACK || \
+		   (NF_CONNTRACK && (!NF_DEFRAG_IPV6 || NF_DEFRAG_IPV6))
 	select LIBCRC32C
 	select MPLS
 	select NET_MPLS_GSO
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index e8e524ad8a01..002a755fa07e 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -275,13 +275,15 @@ static int ovs_ct_helper(struct sk_buff *skb, u16 proto)
 	case NFPROTO_IPV6: {
 		u8 nexthdr = ipv6_hdr(skb)->nexthdr;
 		__be16 frag_off;
+		int ofs;
 
-		protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr),
-					   &nexthdr, &frag_off);
-		if (protoff < 0 || (frag_off & htons(~0x7)) != 0) {
+		ofs = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr,
+				       &frag_off);
+		if (ofs < 0 || (frag_off & htons(~0x7)) != 0) {
 			pr_debug("proto header not found\n");
 			return NF_ACCEPT;
 		}
+		protoff = ofs;
 		break;
 	}
 	default:
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 6fbd2decb19e..b816ff871528 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -952,7 +952,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	if (error)
 		goto err_kfree_flow;
 
-	ovs_flow_mask_key(&new_flow->key, &key, &mask);
+	ovs_flow_mask_key(&new_flow->key, &key, true, &mask);
 
 	/* Extract flow identifier. */
 	error = ovs_nla_get_identifier(&new_flow->id, a[OVS_FLOW_ATTR_UFID],
@@ -1080,7 +1080,7 @@ static struct sw_flow_actions *get_flow_actions(struct net *net,
 	struct sw_flow_key masked_key;
 	int error;
 
-	ovs_flow_mask_key(&masked_key, key, mask);
+	ovs_flow_mask_key(&masked_key, key, true, mask);
 	error = ovs_nla_copy_actions(net, a, &masked_key, &acts, log);
 	if (error) {
 		OVS_NLERR(log,
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index c92d6a262bc5..5c030a4d7338 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -57,6 +57,7 @@ struct ovs_len_tbl {
 };
 
 #define OVS_ATTR_NESTED -1
+#define OVS_ATTR_VARIABLE -2
 
 static void update_range(struct sw_flow_match *match,
 			 size_t offset, size_t size, bool is_mask)
@@ -304,6 +305,10 @@ size_t ovs_key_attr_size(void)
 		+ nla_total_size(28); /* OVS_KEY_ATTR_ND */
 }
 
+static const struct ovs_len_tbl ovs_vxlan_ext_key_lens[OVS_VXLAN_EXT_MAX + 1] = {
+	[OVS_VXLAN_EXT_GBP]	    = { .len = sizeof(u32) },
+};
+
 static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] = {
 	[OVS_TUNNEL_KEY_ATTR_ID]	    = { .len = sizeof(u64) },
 	[OVS_TUNNEL_KEY_ATTR_IPV4_SRC]	    = { .len = sizeof(u32) },
@@ -315,8 +320,9 @@ static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1]
 	[OVS_TUNNEL_KEY_ATTR_TP_SRC]	    = { .len = sizeof(u16) },
 	[OVS_TUNNEL_KEY_ATTR_TP_DST]	    = { .len = sizeof(u16) },
 	[OVS_TUNNEL_KEY_ATTR_OAM]	    = { .len = 0 },
-	[OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS]   = { .len = OVS_ATTR_NESTED },
-	[OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS]    = { .len = OVS_ATTR_NESTED },
+	[OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS]   = { .len = OVS_ATTR_VARIABLE },
+	[OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS]    = { .len = OVS_ATTR_NESTED,
+						.next = ovs_vxlan_ext_key_lens },
 };
 
 /* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute.  */
@@ -349,6 +355,13 @@ static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = {
 	[OVS_KEY_ATTR_CT_LABEL]	 = { .len = sizeof(struct ovs_key_ct_label) },
 };
 
+static bool check_attr_len(unsigned int attr_len, unsigned int expected_len)
+{
+	return expected_len == attr_len ||
+	       expected_len == OVS_ATTR_NESTED ||
+	       expected_len == OVS_ATTR_VARIABLE;
+}
+
 static bool is_all_zero(const u8 *fp, size_t size)
 {
 	int i;
@@ -388,7 +401,7 @@ static int __parse_flow_nlattrs(const struct nlattr *attr,
 		}
 
 		expected_len = ovs_key_lens[type].len;
-		if (nla_len(nla) != expected_len && expected_len != OVS_ATTR_NESTED) {
+		if (!check_attr_len(nla_len(nla), expected_len)) {
 			OVS_NLERR(log, "Key %d has unexpected len %d expected %d",
 				  type, nla_len(nla), expected_len);
 			return -EINVAL;
@@ -473,29 +486,50 @@ static int genev_tun_opt_from_nlattr(const struct nlattr *a,
 	return 0;
 }
 
-static const struct nla_policy vxlan_opt_policy[OVS_VXLAN_EXT_MAX + 1] = {
-	[OVS_VXLAN_EXT_GBP]	= { .type = NLA_U32 },
-};
-
-static int vxlan_tun_opt_from_nlattr(const struct nlattr *a,
+static int vxlan_tun_opt_from_nlattr(const struct nlattr *attr,
 				     struct sw_flow_match *match, bool is_mask,
 				     bool log)
 {
-	struct nlattr *tb[OVS_VXLAN_EXT_MAX+1];
+	struct nlattr *a;
+	int rem;
 	unsigned long opt_key_offset;
 	struct vxlan_metadata opts;
-	int err;
 
 	BUILD_BUG_ON(sizeof(opts) > sizeof(match->key->tun_opts));
 
-	err = nla_parse_nested(tb, OVS_VXLAN_EXT_MAX, a, vxlan_opt_policy);
-	if (err < 0)
-		return err;
-
 	memset(&opts, 0, sizeof(opts));
+	nla_for_each_nested(a, attr, rem) {
+		int type = nla_type(a);
 
-	if (tb[OVS_VXLAN_EXT_GBP])
-		opts.gbp = nla_get_u32(tb[OVS_VXLAN_EXT_GBP]);
+		if (type > OVS_VXLAN_EXT_MAX) {
+			OVS_NLERR(log, "VXLAN extension %d out of range max %d",
+				  type, OVS_VXLAN_EXT_MAX);
+			return -EINVAL;
+		}
+
+		if (!check_attr_len(nla_len(a),
+				    ovs_vxlan_ext_key_lens[type].len)) {
+			OVS_NLERR(log, "VXLAN extension %d has unexpected len %d expected %d",
+				  type, nla_len(a),
+				  ovs_vxlan_ext_key_lens[type].len);
+			return -EINVAL;
+		}
+
+		switch (type) {
+		case OVS_VXLAN_EXT_GBP:
+			opts.gbp = nla_get_u32(a);
+			break;
+		default:
+			OVS_NLERR(log, "Unknown VXLAN extension attribute %d",
+				  type);
+			return -EINVAL;
+		}
+	}
+	if (rem) {
+		OVS_NLERR(log, "VXLAN extension message has %d unknown bytes.",
+			  rem);
+		return -EINVAL;
+	}
 
 	if (!is_mask)
 		SW_FLOW_KEY_PUT(match, tun_opts_len, sizeof(opts), false);
@@ -528,8 +562,8 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
 			return -EINVAL;
 		}
 
-		if (ovs_tunnel_key_lens[type].len != nla_len(a) &&
-		    ovs_tunnel_key_lens[type].len != OVS_ATTR_NESTED) {
+		if (!check_attr_len(nla_len(a),
+				    ovs_tunnel_key_lens[type].len)) {
 			OVS_NLERR(log, "Tunnel attr %d has unexpected len %d expected %d",
 				  type, nla_len(a), ovs_tunnel_key_lens[type].len);
 			return -EINVAL;
@@ -1052,10 +1086,13 @@ static void nlattr_set(struct nlattr *attr, u8 val,
 
 	/* The nlattr stream should already have been validated */
 	nla_for_each_nested(nla, attr, rem) {
-		if (tbl && tbl[nla_type(nla)].len == OVS_ATTR_NESTED)
-			nlattr_set(nla, val, tbl[nla_type(nla)].next);
-		else
+		if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED) {
+			if (tbl[nla_type(nla)].next)
+				tbl = tbl[nla_type(nla)].next;
+			nlattr_set(nla, val, tbl);
+		} else {
 			memset(nla_data(nla), val, nla_len(nla));
+		}
 	}
 }
 
@@ -1922,8 +1959,7 @@ static int validate_set(const struct nlattr *a,
 		key_len /= 2;
 
 	if (key_type > OVS_KEY_ATTR_MAX ||
-	    (ovs_key_lens[key_type].len != key_len &&
-	     ovs_key_lens[key_type].len != OVS_ATTR_NESTED))
+	    !check_attr_len(key_len, ovs_key_lens[key_type].len))
 		return -EINVAL;
 
 	if (masked && !validate_masked(nla_data(ovs_key), key_len))
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index d22d8e948d0f..f2ea83ba4763 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -57,20 +57,21 @@ static u16 range_n_bytes(const struct sw_flow_key_range *range)
 }
 
 void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
-		       const struct sw_flow_mask *mask)
+		       bool full, const struct sw_flow_mask *mask)
 {
-	const long *m = (const long *)((const u8 *)&mask->key +
-				mask->range.start);
-	const long *s = (const long *)((const u8 *)src +
-				mask->range.start);
-	long *d = (long *)((u8 *)dst + mask->range.start);
+	int start = full ? 0 : mask->range.start;
+	int len = full ? sizeof *dst : range_n_bytes(&mask->range);
+	const long *m = (const long *)((const u8 *)&mask->key + start);
+	const long *s = (const long *)((const u8 *)src + start);
+	long *d = (long *)((u8 *)dst + start);
 	int i;
 
-	/* The memory outside of the 'mask->range' are not set since
-	 * further operations on 'dst' only uses contents within
-	 * 'mask->range'.
+	/* If 'full' is true then all of 'dst' is fully initialized. Otherwise,
+	 * if 'full' is false the memory outside of the 'mask->range' is left
+	 * uninitialized. This can be used as an optimization when further
+	 * operations on 'dst' only use contents within 'mask->range'.
 	 */
-	for (i = 0; i < range_n_bytes(&mask->range); i += sizeof(long))
+	for (i = 0; i < len; i += sizeof(long))
 		*d++ = *s++ & *m++;
 }
 
@@ -475,7 +476,7 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti,
 	u32 hash;
 	struct sw_flow_key masked_key;
 
-	ovs_flow_mask_key(&masked_key, unmasked, mask);
+	ovs_flow_mask_key(&masked_key, unmasked, false, mask);
 	hash = flow_hash(&masked_key, &mask->range);
 	head = find_bucket(ti, hash);
 	hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver]) {
diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h
index 616eda10d955..2dd9900f533d 100644
--- a/net/openvswitch/flow_table.h
+++ b/net/openvswitch/flow_table.h
@@ -86,5 +86,5 @@ struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *,
 bool ovs_flow_cmp(const struct sw_flow *, const struct sw_flow_match *);
 
 void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
-		       const struct sw_flow_mask *mask);
+		       bool full, const struct sw_flow_mask *mask);
 #endif /* flow_table.h */