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

Pull networking fixes from David Miller:

 1) Always validate XFRM esn replay attribute, from Florian Westphal.

 2) Fix RCU read lock imbalance in xfrm_get_tos(), from Xin Long.

 3) Don't try to get firmware dump if not loaded in iwlwifi, from Shaul
    Triebitz.

 4) Fix BPF helpers to deal with SCTP GSO SKBs properly, from Daniel
    Axtens.

 5) Fix some interrupt handling issues in e1000e driver, from Benjamin
    Poitier.

 6) Use strlcpy() in several ethtool get_strings methods, from Florian
    Fainelli.

 7) Fix rhlist dup insertion, from Paul Blakey.

 8) Fix SKB leak in netem packet scheduler, from Alexey Kodanev.

 9) Fix driver unload crash when link is up in smsc911x, from Jeremy
    Linton.

10) Purge out invalid socket types in l2tp_tunnel_create(), from Eric
    Dumazet.

11) Need to purge the write queue when TCP connections are aborted,
    otherwise userspace using MSG_ZEROCOPY can't close the fd. From
    Soheil Hassas Yeganeh.

12) Fix double free in error path of team driver, from Arkadi
    Sharshevsky.

13) Filter fixes for hv_netvsc driver, from Stephen Hemminger.

14) Fix non-linear packet access in ipv6 ndisc code, from Lorenzo
    Bianconi.

15) Properly filter out unsupported feature flags in macvlan driver,
    from Shannon Nelson.

16) Don't request loading the diag module for a protocol if the protocol
    itself is not even registered. From Xin Long.

17) If datagram connect fails in ipv6, make sure the socket state is
    consistent afterwards. From Paolo Abeni.

18) Use after free in qed driver, from Dan Carpenter.

19) If received ipv4 PMTU is less than the min pmtu, lock the mtu in the
    entry. From Sabrina Dubroca.

20) Fix sleep in atomic in tg3 driver, from Jonathan Toppins.

21) Fix vlan in vlan untagging in some situations, from Toshiaki Makita.

22) Fix double SKB free in genlmsg_mcast(). From Nicolas Dichtel.

23) Fix NULL derefs in error paths of tcf_*_init(), from Davide Caratti.

24) Unbalanced PM runtime calls in FEC driver, from Florian Fainelli.

25) Memory leak in gemini driver, from Igor Pylypiv.

26) IDR leaks in error paths of tcf_*_init() functions, from Davide
    Caratti.

27) Need to use GFP_ATOMIC in seg6_build_state(), from David Lebrun.

28) Missing dev_put() in error path of macsec_newlink(), from Dan
    Carpenter.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (201 commits)
  macsec: missing dev_put() on error in macsec_newlink()
  net: dsa: Fix functional dsa-loop dependency on FIXED_PHY
  hv_netvsc: common detach logic
  hv_netvsc: change GPAD teardown order on older versions
  hv_netvsc: use RCU to fix concurrent rx and queue changes
  hv_netvsc: disable NAPI before channel close
  net/ipv6: Handle onlink flag with multipath routes
  ppp: avoid loop in xmit recursion detection code
  ipv6: sr: fix NULL pointer dereference when setting encap source address
  ipv6: sr: fix scheduling in RCU when creating seg6 lwtunnel state
  net: aquantia: driver version bump
  net: aquantia: Implement pci shutdown callback
  net: aquantia: Allow live mac address changes
  net: aquantia: Add tx clean budget and valid budget handling logic
  net: aquantia: Change inefficient wait loop on fw data reads
  net: aquantia: Fix a regression with reset on old firmware
  net: aquantia: Fix hardware reset when SPI may rarely hangup
  s390/qeth: on channel error, reject further cmd requests
  s390/qeth: lock read device while queueing next buffer
  s390/qeth: when thread completes, wake up all waiters
  ...

17 files changed, 158 insertions, 18 deletions

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 9f242b876fde..f8e76d01a5ad 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -755,13 +755,13 @@ struct sock_cgroup_data {
  * updaters and return part of the previous pointer as the prioidx or
  * classid.  Such races are short-lived and the result isn't critical.
  */
-static inline u16 sock_cgroup_prioidx(struct sock_cgroup_data *skcd)
+static inline u16 sock_cgroup_prioidx(const struct sock_cgroup_data *skcd)
 {
 	/* fallback to 1 which is always the ID of the root cgroup */
 	return (skcd->is_data & 1) ? skcd->prioidx : 1;
 }
 
-static inline u32 sock_cgroup_classid(struct sock_cgroup_data *skcd)
+static inline u32 sock_cgroup_classid(const struct sock_cgroup_data *skcd)
 {
 	/* fallback to 0 which is the unconfigured default classid */
 	return (skcd->is_data & 1) ? skcd->classid : 0;
diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h
index c5b0a75a7812..fd00170b494f 100644
--- a/include/linux/if_tun.h
+++ b/include/linux/if_tun.h
@@ -25,6 +25,7 @@ struct ptr_ring *tun_get_tx_ring(struct file *file);
 bool tun_is_xdp_buff(void *ptr);
 void *tun_xdp_to_ptr(void *ptr);
 void *tun_ptr_to_xdp(void *ptr);
+void tun_ptr_free(void *ptr);
 #else
 #include <linux/err.h>
 #include <linux/errno.h>
@@ -50,5 +51,8 @@ static inline void *tun_ptr_to_xdp(void *ptr)
 {
 	return NULL;
 }
+static inline void tun_ptr_free(void *ptr)
+{
+}
 #endif /* CONFIG_TUN */
 #endif /* __IF_TUN_H */
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 5e6a2d4dc366..c4a1cff9c768 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -300,30 +300,34 @@ static inline bool vlan_hw_offload_capable(netdev_features_t features,
 }
 
 /**
- * __vlan_insert_tag - regular VLAN tag inserting
+ * __vlan_insert_inner_tag - inner VLAN tag inserting
  * @skb: skbuff to tag
  * @vlan_proto: VLAN encapsulation protocol
  * @vlan_tci: VLAN TCI to insert
+ * @mac_len: MAC header length including outer vlan headers
  *
- * Inserts the VLAN tag into @skb as part of the payload
+ * Inserts the VLAN tag into @skb as part of the payload at offset mac_len
  * Returns error if skb_cow_head failes.
  *
  * Does not change skb->protocol so this function can be used during receive.
  */
-static inline int __vlan_insert_tag(struct sk_buff *skb,
-				    __be16 vlan_proto, u16 vlan_tci)
+static inline int __vlan_insert_inner_tag(struct sk_buff *skb,
+					  __be16 vlan_proto, u16 vlan_tci,
+					  unsigned int mac_len)
 {
 	struct vlan_ethhdr *veth;
 
 	if (skb_cow_head(skb, VLAN_HLEN) < 0)
 		return -ENOMEM;
 
-	veth = skb_push(skb, VLAN_HLEN);
+	skb_push(skb, VLAN_HLEN);
 
-	/* Move the mac addresses to the beginning of the new header. */
-	memmove(skb->data, skb->data + VLAN_HLEN, 2 * ETH_ALEN);
+	/* Move the mac header sans proto to the beginning of the new header. */
+	memmove(skb->data, skb->data + VLAN_HLEN, mac_len - ETH_TLEN);
 	skb->mac_header -= VLAN_HLEN;
 
+	veth = (struct vlan_ethhdr *)(skb->data + mac_len - ETH_HLEN);
+
 	/* first, the ethernet type */
 	veth->h_vlan_proto = vlan_proto;
 
@@ -334,12 +338,30 @@ static inline int __vlan_insert_tag(struct sk_buff *skb,
 }
 
 /**
- * vlan_insert_tag - regular VLAN tag inserting
+ * __vlan_insert_tag - regular VLAN tag inserting
  * @skb: skbuff to tag
  * @vlan_proto: VLAN encapsulation protocol
  * @vlan_tci: VLAN TCI to insert
  *
  * Inserts the VLAN tag into @skb as part of the payload
+ * Returns error if skb_cow_head failes.
+ *
+ * Does not change skb->protocol so this function can be used during receive.
+ */
+static inline int __vlan_insert_tag(struct sk_buff *skb,
+				    __be16 vlan_proto, u16 vlan_tci)
+{
+	return __vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, ETH_HLEN);
+}
+
+/**
+ * vlan_insert_inner_tag - inner VLAN tag inserting
+ * @skb: skbuff to tag
+ * @vlan_proto: VLAN encapsulation protocol
+ * @vlan_tci: VLAN TCI to insert
+ * @mac_len: MAC header length including outer vlan headers
+ *
+ * Inserts the VLAN tag into @skb as part of the payload at offset mac_len
  * Returns a VLAN tagged skb. If a new skb is created, @skb is freed.
  *
  * Following the skb_unshare() example, in case of error, the calling function
@@ -347,12 +369,14 @@ static inline int __vlan_insert_tag(struct sk_buff *skb,
  *
  * Does not change skb->protocol so this function can be used during receive.
  */
-static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb,
-					      __be16 vlan_proto, u16 vlan_tci)
+static inline struct sk_buff *vlan_insert_inner_tag(struct sk_buff *skb,
+						    __be16 vlan_proto,
+						    u16 vlan_tci,
+						    unsigned int mac_len)
 {
 	int err;
 
-	err = __vlan_insert_tag(skb, vlan_proto, vlan_tci);
+	err = __vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, mac_len);
 	if (err) {
 		dev_kfree_skb_any(skb);
 		return NULL;
@@ -361,6 +385,26 @@ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb,
 }
 
 /**
+ * vlan_insert_tag - regular VLAN tag inserting
+ * @skb: skbuff to tag
+ * @vlan_proto: VLAN encapsulation protocol
+ * @vlan_tci: VLAN TCI to insert
+ *
+ * Inserts the VLAN tag into @skb as part of the payload
+ * Returns a VLAN tagged skb. If a new skb is created, @skb is freed.
+ *
+ * Following the skb_unshare() example, in case of error, the calling function
+ * doesn't have to worry about freeing the original skb.
+ *
+ * Does not change skb->protocol so this function can be used during receive.
+ */
+static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb,
+					      __be16 vlan_proto, u16 vlan_tci)
+{
+	return vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, ETH_HLEN);
+}
+
+/**
  * vlan_insert_tag_set_proto - regular VLAN tag inserting
  * @skb: skbuff to tag
  * @vlan_proto: VLAN encapsulation protocol
diff --git a/include/linux/net.h b/include/linux/net.h
index 91216b16feb7..2a0391eea05c 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -222,6 +222,7 @@ enum {
 int sock_wake_async(struct socket_wq *sk_wq, int how, int band);
 int sock_register(const struct net_proto_family *fam);
 void sock_unregister(int family);
+bool sock_is_registered(int family);
 int __sock_create(struct net *net, int family, int type, int proto,
 		  struct socket **res, int kern);
 int sock_create(int family, int type, int proto, struct socket **res);
diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 1313b35c3ab7..14529511c4b8 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -285,6 +285,8 @@ unsigned int *xt_alloc_entry_offsets(unsigned int size);
 bool xt_find_jump_offset(const unsigned int *offsets,
 			 unsigned int target, unsigned int size);
 
+int xt_check_proc_name(const char *name, unsigned int size);
+
 int xt_check_match(struct xt_mtchk_param *, unsigned int size, u_int8_t proto,
 		   bool inv_proto);
 int xt_check_target(struct xt_tgchk_param *, unsigned int size, u_int8_t proto,
diff --git a/include/linux/phy.h b/include/linux/phy.h
index d7069539f351..7c4c2379e010 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -984,6 +984,10 @@ static inline int genphy_no_soft_reset(struct phy_device *phydev)
 {
 	return 0;
 }
+int genphy_read_mmd_unsupported(struct phy_device *phdev, int devad,
+				u16 regnum);
+int genphy_write_mmd_unsupported(struct phy_device *phdev, int devnum,
+				 u16 regnum, u16 val);
 
 /* Clause 45 PHY */
 int genphy_c45_restart_aneg(struct phy_device *phydev);
@@ -1012,7 +1016,6 @@ int phy_driver_register(struct phy_driver *new_driver, struct module *owner);
 int phy_drivers_register(struct phy_driver *new_driver, int n,
 			 struct module *owner);
 void phy_state_machine(struct work_struct *work);
-void phy_change(struct phy_device *phydev);
 void phy_change_work(struct work_struct *work);
 void phy_mac_interrupt(struct phy_device *phydev);
 void phy_start_machine(struct phy_device *phydev);
diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index c9df2527e0cd..668a21f04b09 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -766,8 +766,10 @@ slow_path:
 		if (!key ||
 		    (params.obj_cmpfn ?
 		     params.obj_cmpfn(&arg, rht_obj(ht, head)) :
-		     rhashtable_compare(&arg, rht_obj(ht, head))))
+		     rhashtable_compare(&arg, rht_obj(ht, head)))) {
+			pprev = &head->next;
 			continue;
+		}
 
 		data = rht_obj(ht, head);
 
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index ddf77cf4ff2d..99df17109e1b 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -4037,6 +4037,12 @@ static inline bool skb_is_gso_v6(const struct sk_buff *skb)
 	return skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6;
 }
 
+/* Note: Should be called only if skb_is_gso(skb) is true */
+static inline bool skb_is_gso_sctp(const struct sk_buff *skb)
+{
+	return skb_shinfo(skb)->gso_type & SKB_GSO_SCTP;
+}
+
 static inline void skb_gso_reset(struct sk_buff *skb)
 {
 	skb_shinfo(skb)->gso_size = 0;
@@ -4044,6 +4050,22 @@ static inline void skb_gso_reset(struct sk_buff *skb)
 	skb_shinfo(skb)->gso_type = 0;
 }
 
+static inline void skb_increase_gso_size(struct skb_shared_info *shinfo,
+					 u16 increment)
+{
+	if (WARN_ON_ONCE(shinfo->gso_size == GSO_BY_FRAGS))
+		return;
+	shinfo->gso_size += increment;
+}
+
+static inline void skb_decrease_gso_size(struct skb_shared_info *shinfo,
+					 u16 decrement)
+{
+	if (WARN_ON_ONCE(shinfo->gso_size == GSO_BY_FRAGS))
+		return;
+	shinfo->gso_size -= decrement;
+}
+
 void __skb_warn_lro_forwarding(const struct sk_buff *skb);
 
 static inline bool skb_warn_if_lro(const struct sk_buff *skb)
diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h
index 5bdbd9f49395..07ee0f84a46c 100644
--- a/include/linux/u64_stats_sync.h
+++ b/include/linux/u64_stats_sync.h
@@ -90,6 +90,28 @@ static inline void u64_stats_update_end(struct u64_stats_sync *syncp)
 #endif
 }
 
+static inline unsigned long
+u64_stats_update_begin_irqsave(struct u64_stats_sync *syncp)
+{
+	unsigned long flags = 0;
+
+#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
+	local_irq_save(flags);
+	write_seqcount_begin(&syncp->seq);
+#endif
+	return flags;
+}
+
+static inline void
+u64_stats_update_end_irqrestore(struct u64_stats_sync *syncp,
+				unsigned long flags)
+{
+#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
+	write_seqcount_end(&syncp->seq);
+	local_irq_restore(flags);
+#endif
+}
+
 static inline void u64_stats_update_begin_raw(struct u64_stats_sync *syncp)
 {
 #if BITS_PER_LONG==32 && defined(CONFIG_SMP)
diff --git a/include/net/ip.h b/include/net/ip.h
index 746abff9ce51..f49b3a576bec 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -328,6 +328,13 @@ int ip_decrease_ttl(struct iphdr *iph)
 	return --iph->ttl;
 }
 
+static inline int ip_mtu_locked(const struct dst_entry *dst)
+{
+	const struct rtable *rt = (const struct rtable *)dst;
+
+	return rt->rt_mtu_locked || dst_metric_locked(dst, RTAX_MTU);
+}
+
 static inline
 int ip_dont_fragment(const struct sock *sk, const struct dst_entry *dst)
 {
@@ -335,7 +342,7 @@ int ip_dont_fragment(const struct sock *sk, const struct dst_entry *dst)
 
 	return  pmtudisc == IP_PMTUDISC_DO ||
 		(pmtudisc == IP_PMTUDISC_WANT &&
-		 !(dst_metric_locked(dst, RTAX_MTU)));
+		 !ip_mtu_locked(dst));
 }
 
 static inline bool ip_sk_accept_pmtu(const struct sock *sk)
@@ -361,7 +368,7 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,
 	struct net *net = dev_net(dst->dev);
 
 	if (net->ipv4.sysctl_ip_fwd_use_pmtu ||
-	    dst_metric_locked(dst, RTAX_MTU) ||
+	    ip_mtu_locked(dst) ||
 	    !forwarding)
 		return dst_mtu(dst);
 
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 27d23a65f3cd..ac0866bb9e93 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -179,6 +179,9 @@ void rt6_disable_ip(struct net_device *dev, unsigned long event);
 void rt6_sync_down_dev(struct net_device *dev, unsigned long event);
 void rt6_multipath_rebalance(struct rt6_info *rt);
 
+void rt6_uncached_list_add(struct rt6_info *rt);
+void rt6_uncached_list_del(struct rt6_info *rt);
+
 static inline const struct rt6_info *skb_rt6_info(const struct sk_buff *skb)
 {
 	const struct dst_entry *dst = skb_dst(skb);
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index f80524396c06..77d0a78cf7d2 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -59,6 +59,7 @@ struct fib_nh_exception {
 	int				fnhe_genid;
 	__be32				fnhe_daddr;
 	u32				fnhe_pmtu;
+	bool				fnhe_mtu_locked;
 	__be32				fnhe_gw;
 	unsigned long			fnhe_expires;
 	struct rtable __rcu		*fnhe_rth_input;
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index c96511fa9198..2b581bd93812 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -2063,6 +2063,9 @@ struct ieee80211_txq {
  * @IEEE80211_HW_SUPPORTS_TDLS_BUFFER_STA: Hardware supports buffer STA on
  *	TDLS links.
  *
+ * @IEEE80211_HW_DOESNT_SUPPORT_QOS_NDP: The driver (or firmware) doesn't
+ *	support QoS NDP for AP probing - that's most likely a driver bug.
+ *
  * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays
  */
 enum ieee80211_hw_flags {
@@ -2106,6 +2109,7 @@ enum ieee80211_hw_flags {
 	IEEE80211_HW_REPORTS_LOW_ACK,
 	IEEE80211_HW_SUPPORTS_TX_FRAG,
 	IEEE80211_HW_SUPPORTS_TDLS_BUFFER_STA,
+	IEEE80211_HW_DOESNT_SUPPORT_QOS_NDP,
 
 	/* keep last, obviously */
 	NUM_IEEE80211_HW_FLAGS
diff --git a/include/net/route.h b/include/net/route.h
index 1eb9ce470e25..20a92ca9e115 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -63,7 +63,8 @@ struct rtable {
 	__be32			rt_gateway;
 
 	/* Miscellaneous cached information */
-	u32			rt_pmtu;
+	u32			rt_mtu_locked:1,
+				rt_pmtu:31;
 
 	u32			rt_table_id;
 
@@ -227,6 +228,9 @@ struct in_ifaddr;
 void fib_add_ifaddr(struct in_ifaddr *);
 void fib_del_ifaddr(struct in_ifaddr *, struct in_ifaddr *);
 
+void rt_add_uncached_list(struct rtable *rt);
+void rt_del_uncached_list(struct rtable *rt);
+
 static inline void ip_rt_put(struct rtable *rt)
 {
 	/* dst_release() accepts a NULL parameter.
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index e2ab13687fb9..2092d33194dd 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -824,6 +824,16 @@ static inline void __qdisc_drop(struct sk_buff *skb, struct sk_buff **to_free)
 	*to_free = skb;
 }
 
+static inline void __qdisc_drop_all(struct sk_buff *skb,
+				    struct sk_buff **to_free)
+{
+	if (skb->prev)
+		skb->prev->next = *to_free;
+	else
+		skb->next = *to_free;
+	*to_free = skb;
+}
+
 static inline unsigned int __qdisc_queue_drop_head(struct Qdisc *sch,
 						   struct qdisc_skb_head *qh,
 						   struct sk_buff **to_free)
@@ -956,6 +966,15 @@ static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch,
 	return NET_XMIT_DROP;
 }
 
+static inline int qdisc_drop_all(struct sk_buff *skb, struct Qdisc *sch,
+				 struct sk_buff **to_free)
+{
+	__qdisc_drop_all(skb, to_free);
+	qdisc_qstats_drop(sch);
+
+	return NET_XMIT_DROP;
+}
+
 /* Length to Time (L2T) lookup in a qdisc_rate_table, to determine how
    long it will take to send a packet given its size.
  */
diff --git a/include/net/sock.h b/include/net/sock.h
index 169c92afcafa..ae23f3b389ca 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1137,6 +1137,7 @@ struct proto {
 
 int proto_register(struct proto *prot, int alloc_slab);
 void proto_unregister(struct proto *prot);
+int sock_load_diag_module(int family, int protocol);
 
 #ifdef SOCK_REFCNT_DEBUG
 static inline void sk_refcnt_debug_inc(struct sock *sk)
diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h
index 8bbbcb5cd94b..820de5d222d2 100644
--- a/include/uapi/linux/if_ether.h
+++ b/include/uapi/linux/if_ether.h
@@ -30,6 +30,7 @@
  */
 
 #define ETH_ALEN	6		/* Octets in one ethernet addr	 */
+#define ETH_TLEN	2		/* Octets in ethernet type field */
 #define ETH_HLEN	14		/* Total octets in header.	 */
 #define ETH_ZLEN	60		/* Min. octets in frame sans FCS */
 #define ETH_DATA_LEN	1500		/* Max. octets in payload	 */