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

Pull networking fixes from David Miller:

 1) Several hash table refcount fixes in batman-adv, from Sven
    Eckelmann.

 2) Use after free in bpf_evict_inode(), from Daniel Borkmann.

 3) Fix mdio bus registration in ixgbe, from Ivan Vecera.

 4) Unbounded loop in __skb_try_recv_datagram(), from Paolo Abeni.

 5) ila rhashtable corruption fix from Herbert Xu.

 6) Don't allow upper-devices to be added to vrf devices, from Sabrina
    Dubroca.

 7) Add qmi_wwan device ID for Olicard 600, from Bjørn Mork.

 8) Don't leave skb->next poisoned in __netif_receive_skb_list_ptype,
    from Alexander Lobakin.

 9) Missing IDR checks in mlx5 driver, from Aditya Pakki.

10) Fix false connection termination in ktls, from Jakub Kicinski.

11) Work around some ASPM issues with r8169 by disabling rx interrupt
    coalescing on certain chips. From Heiner Kallweit.

12) Properly use per-cpu qstat values on NOLOCK qdiscs, from Paolo
    Abeni.

13) Fully initialize sockaddr_in structures in SCTP, from Xin Long.

14) Various BPF flow dissector fixes from Stanislav Fomichev.

15) Divide by zero in act_sample, from Davide Caratti.

16) Fix bridging multicast regression introduced by rhashtable
    conversion, from Nikolay Aleksandrov.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (106 commits)
  ibmvnic: Fix completion structure initialization
  ipv6: sit: reset ip header pointer in ipip6_rcv
  net: bridge: always clear mcast matching struct on reports and leaves
  libcxgb: fix incorrect ppmax calculation
  vlan: conditional inclusion of FCoE hooks to match netdevice.h and bnx2x
  sch_cake: Make sure we can write the IP header before changing DSCP bits
  sch_cake: Use tc_skb_protocol() helper for getting packet protocol
  tcp: Ensure DCTCP reacts to losses
  net/sched: act_sample: fix divide by zero in the traffic path
  net: thunderx: fix NULL pointer dereference in nicvf_open/nicvf_stop
  net: hns: Fix sparse: some warnings in HNS drivers
  net: hns: Fix WARNING when remove HNS driver with SMMU enabled
  net: hns: fix ICMP6 neighbor solicitation messages discard problem
  net: hns: Fix probabilistic memory overwrite when HNS driver initialized
  net: hns: Use NAPI_POLL_WEIGHT for hns driver
  net: hns: fix KASAN: use-after-free in hns_nic_net_xmit_hw()
  flow_dissector: rst'ify documentation
  ipv6: Fix dangling pointer when ipv6 fragment
  net-gro: Fix GRO flush when receiving a GSO packet.
  flow_dissector: document BPF flow dissector environment
  ...

45 files changed, 250 insertions, 189 deletions

diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 15293c2a5dd8..8d77b6ee4477 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -443,27 +443,29 @@ static int vlan_dev_fcoe_disable(struct net_device *dev)
 	return rc;
 }
 
-static int vlan_dev_fcoe_get_wwn(struct net_device *dev, u64 *wwn, int type)
+static int vlan_dev_fcoe_ddp_target(struct net_device *dev, u16 xid,
+				    struct scatterlist *sgl, unsigned int sgc)
 {
 	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
 	const struct net_device_ops *ops = real_dev->netdev_ops;
-	int rc = -EINVAL;
+	int rc = 0;
+
+	if (ops->ndo_fcoe_ddp_target)
+		rc = ops->ndo_fcoe_ddp_target(real_dev, xid, sgl, sgc);
 
-	if (ops->ndo_fcoe_get_wwn)
-		rc = ops->ndo_fcoe_get_wwn(real_dev, wwn, type);
 	return rc;
 }
+#endif
 
-static int vlan_dev_fcoe_ddp_target(struct net_device *dev, u16 xid,
-				    struct scatterlist *sgl, unsigned int sgc)
+#ifdef NETDEV_FCOE_WWNN
+static int vlan_dev_fcoe_get_wwn(struct net_device *dev, u64 *wwn, int type)
 {
 	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
 	const struct net_device_ops *ops = real_dev->netdev_ops;
-	int rc = 0;
-
-	if (ops->ndo_fcoe_ddp_target)
-		rc = ops->ndo_fcoe_ddp_target(real_dev, xid, sgl, sgc);
+	int rc = -EINVAL;
 
+	if (ops->ndo_fcoe_get_wwn)
+		rc = ops->ndo_fcoe_get_wwn(real_dev, wwn, type);
 	return rc;
 }
 #endif
@@ -794,9 +796,11 @@ static const struct net_device_ops vlan_netdev_ops = {
 	.ndo_fcoe_ddp_done	= vlan_dev_fcoe_ddp_done,
 	.ndo_fcoe_enable	= vlan_dev_fcoe_enable,
 	.ndo_fcoe_disable	= vlan_dev_fcoe_disable,
-	.ndo_fcoe_get_wwn	= vlan_dev_fcoe_get_wwn,
 	.ndo_fcoe_ddp_target	= vlan_dev_fcoe_ddp_target,
 #endif
+#ifdef NETDEV_FCOE_WWNN
+	.ndo_fcoe_get_wwn	= vlan_dev_fcoe_get_wwn,
+#endif
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= vlan_dev_poll_controller,
 	.ndo_netpoll_setup	= vlan_dev_netpoll_setup,
diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c
index a9b7919c9de5..d5df0114f08a 100644
--- a/net/batman-adv/bat_v_elp.c
+++ b/net/batman-adv/bat_v_elp.c
@@ -104,8 +104,10 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh)
 
 		ret = cfg80211_get_station(real_netdev, neigh->addr, &sinfo);
 
-		/* free the TID stats immediately */
-		cfg80211_sinfo_release_content(&sinfo);
+		if (!ret) {
+			/* free the TID stats immediately */
+			cfg80211_sinfo_release_content(&sinfo);
+		}
 
 		dev_put(real_netdev);
 		if (ret == -ENOENT) {
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index ef39aabdb694..4fb01108e5f5 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -803,6 +803,8 @@ static void batadv_bla_del_claim(struct batadv_priv *bat_priv,
 				 const u8 *mac, const unsigned short vid)
 {
 	struct batadv_bla_claim search_claim, *claim;
+	struct batadv_bla_claim *claim_removed_entry;
+	struct hlist_node *claim_removed_node;
 
 	ether_addr_copy(search_claim.addr, mac);
 	search_claim.vid = vid;
@@ -813,10 +815,18 @@ static void batadv_bla_del_claim(struct batadv_priv *bat_priv,
 	batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): %pM, vid %d\n", __func__,
 		   mac, batadv_print_vid(vid));
 
-	batadv_hash_remove(bat_priv->bla.claim_hash, batadv_compare_claim,
-			   batadv_choose_claim, claim);
-	batadv_claim_put(claim); /* reference from the hash is gone */
+	claim_removed_node = batadv_hash_remove(bat_priv->bla.claim_hash,
+						batadv_compare_claim,
+						batadv_choose_claim, claim);
+	if (!claim_removed_node)
+		goto free_claim;
 
+	/* reference from the hash is gone */
+	claim_removed_entry = hlist_entry(claim_removed_node,
+					  struct batadv_bla_claim, hash_entry);
+	batadv_claim_put(claim_removed_entry);
+
+free_claim:
 	/* don't need the reference from hash_find() anymore */
 	batadv_claim_put(claim);
 }
diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c
index 0b4b3fb778a6..208655cf6717 100644
--- a/net/batman-adv/sysfs.c
+++ b/net/batman-adv/sysfs.c
@@ -1116,9 +1116,9 @@ static ssize_t batadv_store_throughput_override(struct kobject *kobj,
 						struct attribute *attr,
 						char *buff, size_t count)
 {
-	struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj);
 	struct net_device *net_dev = batadv_kobj_to_netdev(kobj);
 	struct batadv_hard_iface *hard_iface;
+	struct batadv_priv *bat_priv;
 	u32 tp_override;
 	u32 old_tp_override;
 	bool ret;
@@ -1147,7 +1147,10 @@ static ssize_t batadv_store_throughput_override(struct kobject *kobj,
 
 	atomic_set(&hard_iface->bat_v.throughput_override, tp_override);
 
-	batadv_netlink_notify_hardif(bat_priv, hard_iface);
+	if (hard_iface->soft_iface) {
+		bat_priv = netdev_priv(hard_iface->soft_iface);
+		batadv_netlink_notify_hardif(bat_priv, hard_iface);
+	}
 
 out:
 	batadv_hardif_put(hard_iface);
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index f73d79139ae7..26c4e2493ddf 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -616,14 +616,26 @@ static void batadv_tt_global_free(struct batadv_priv *bat_priv,
 				  struct batadv_tt_global_entry *tt_global,
 				  const char *message)
 {
+	struct batadv_tt_global_entry *tt_removed_entry;
+	struct hlist_node *tt_removed_node;
+
 	batadv_dbg(BATADV_DBG_TT, bat_priv,
 		   "Deleting global tt entry %pM (vid: %d): %s\n",
 		   tt_global->common.addr,
 		   batadv_print_vid(tt_global->common.vid), message);
 
-	batadv_hash_remove(bat_priv->tt.global_hash, batadv_compare_tt,
-			   batadv_choose_tt, &tt_global->common);
-	batadv_tt_global_entry_put(tt_global);
+	tt_removed_node = batadv_hash_remove(bat_priv->tt.global_hash,
+					     batadv_compare_tt,
+					     batadv_choose_tt,
+					     &tt_global->common);
+	if (!tt_removed_node)
+		return;
+
+	/* drop reference of remove hash entry */
+	tt_removed_entry = hlist_entry(tt_removed_node,
+				       struct batadv_tt_global_entry,
+				       common.hash_entry);
+	batadv_tt_global_entry_put(tt_removed_entry);
 }
 
 /**
@@ -1337,9 +1349,10 @@ u16 batadv_tt_local_remove(struct batadv_priv *bat_priv, const u8 *addr,
 			   unsigned short vid, const char *message,
 			   bool roaming)
 {
+	struct batadv_tt_local_entry *tt_removed_entry;
 	struct batadv_tt_local_entry *tt_local_entry;
 	u16 flags, curr_flags = BATADV_NO_FLAGS;
-	void *tt_entry_exists;
+	struct hlist_node *tt_removed_node;
 
 	tt_local_entry = batadv_tt_local_hash_find(bat_priv, addr, vid);
 	if (!tt_local_entry)
@@ -1368,15 +1381,18 @@ u16 batadv_tt_local_remove(struct batadv_priv *bat_priv, const u8 *addr,
 	 */
 	batadv_tt_local_event(bat_priv, tt_local_entry, BATADV_TT_CLIENT_DEL);
 
-	tt_entry_exists = batadv_hash_remove(bat_priv->tt.local_hash,
+	tt_removed_node = batadv_hash_remove(bat_priv->tt.local_hash,
 					     batadv_compare_tt,
 					     batadv_choose_tt,
 					     &tt_local_entry->common);
-	if (!tt_entry_exists)
+	if (!tt_removed_node)
 		goto out;
 
-	/* extra call to free the local tt entry */
-	batadv_tt_local_entry_put(tt_local_entry);
+	/* drop reference of remove hash entry */
+	tt_removed_entry = hlist_entry(tt_removed_node,
+				       struct batadv_tt_local_entry,
+				       common.hash_entry);
+	batadv_tt_local_entry_put(tt_removed_entry);
 
 out:
 	if (tt_local_entry)
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index a0e369179f6d..02da21d771c9 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -601,6 +601,7 @@ static int br_ip4_multicast_add_group(struct net_bridge *br,
 	if (ipv4_is_local_multicast(group))
 		return 0;
 
+	memset(&br_group, 0, sizeof(br_group));
 	br_group.u.ip4 = group;
 	br_group.proto = htons(ETH_P_IP);
 	br_group.vid = vid;
@@ -1497,6 +1498,7 @@ static void br_ip4_multicast_leave_group(struct net_bridge *br,
 
 	own_query = port ? &port->ip4_own_query : &br->ip4_own_query;
 
+	memset(&br_group, 0, sizeof(br_group));
 	br_group.u.ip4 = group;
 	br_group.proto = htons(ETH_P_IP);
 	br_group.vid = vid;
@@ -1520,6 +1522,7 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br,
 
 	own_query = port ? &port->ip6_own_query : &br->ip6_own_query;
 
+	memset(&br_group, 0, sizeof(br_group));
 	br_group.u.ip6 = *group;
 	br_group.proto = htons(ETH_P_IPV6);
 	br_group.vid = vid;
diff --git a/net/core/datagram.c b/net/core/datagram.c
index b2651bb6d2a3..e657289db4ac 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -279,7 +279,7 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
 			break;
 
 		sk_busy_loop(sk, flags & MSG_DONTWAIT);
-	} while (!skb_queue_empty(&sk->sk_receive_queue));
+	} while (sk->sk_receive_queue.prev != *last);
 
 	error = -EAGAIN;
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 2b67f2aa59dd..fdcff29df915 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5014,8 +5014,10 @@ static inline void __netif_receive_skb_list_ptype(struct list_head *head,
 	if (pt_prev->list_func != NULL)
 		pt_prev->list_func(head, pt_prev, orig_dev);
 	else
-		list_for_each_entry_safe(skb, next, head, list)
+		list_for_each_entry_safe(skb, next, head, list) {
+			skb_list_del_init(skb);
 			pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
+		}
 }
 
 static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemalloc)
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index b1eb32419732..36ed619faf36 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1797,11 +1797,16 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr)
 	WARN_ON_ONCE(!ret);
 
 	gstrings.len = ret;
-	data = vzalloc(array_size(gstrings.len, ETH_GSTRING_LEN));
-	if (gstrings.len && !data)
-		return -ENOMEM;
 
-	__ethtool_get_strings(dev, gstrings.string_set, data);
+	if (gstrings.len) {
+		data = vzalloc(array_size(gstrings.len, ETH_GSTRING_LEN));
+		if (!data)
+			return -ENOMEM;
+
+		__ethtool_get_strings(dev, gstrings.string_set, data);
+	} else {
+		data = NULL;
+	}
 
 	ret = -EFAULT;
 	if (copy_to_user(useraddr, &gstrings, sizeof(gstrings)))
@@ -1897,11 +1902,15 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr)
 		return -EFAULT;
 
 	stats.n_stats = n_stats;
-	data = vzalloc(array_size(n_stats, sizeof(u64)));
-	if (n_stats && !data)
-		return -ENOMEM;
 
-	ops->get_ethtool_stats(dev, &stats, data);
+	if (n_stats) {
+		data = vzalloc(array_size(n_stats, sizeof(u64)));
+		if (!data)
+			return -ENOMEM;
+		ops->get_ethtool_stats(dev, &stats, data);
+	} else {
+		data = NULL;
+	}
 
 	ret = -EFAULT;
 	if (copy_to_user(useraddr, &stats, sizeof(stats)))
@@ -1941,16 +1950,21 @@ static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr)
 		return -EFAULT;
 
 	stats.n_stats = n_stats;
-	data = vzalloc(array_size(n_stats, sizeof(u64)));
-	if (n_stats && !data)
-		return -ENOMEM;
 
-	if (dev->phydev && !ops->get_ethtool_phy_stats) {
-		ret = phy_ethtool_get_stats(dev->phydev, &stats, data);
-		if (ret < 0)
-			return ret;
+	if (n_stats) {
+		data = vzalloc(array_size(n_stats, sizeof(u64)));
+		if (!data)
+			return -ENOMEM;
+
+		if (dev->phydev && !ops->get_ethtool_phy_stats) {
+			ret = phy_ethtool_get_stats(dev->phydev, &stats, data);
+			if (ret < 0)
+				goto out;
+		} else {
+			ops->get_ethtool_phy_stats(dev, &stats, data);
+		}
 	} else {
-		ops->get_ethtool_phy_stats(dev, &stats, data);
+		data = NULL;
 	}
 
 	ret = -EFAULT;
diff --git a/net/core/filter.c b/net/core/filter.c
index 647c63a7b25b..fc92ebc4e200 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -6613,14 +6613,8 @@ static bool flow_dissector_is_valid_access(int off, int size,
 					   const struct bpf_prog *prog,
 					   struct bpf_insn_access_aux *info)
 {
-	if (type == BPF_WRITE) {
-		switch (off) {
-		case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]):
-			break;
-		default:
-			return false;
-		}
-	}
+	if (type == BPF_WRITE)
+		return false;
 
 	switch (off) {
 	case bpf_ctx_range(struct __sk_buff, data):
@@ -6632,11 +6626,7 @@ static bool flow_dissector_is_valid_access(int off, int size,
 	case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
 		info->reg_type = PTR_TO_FLOW_KEYS;
 		break;
-	case bpf_ctx_range(struct __sk_buff, tc_classid):
-	case bpf_ctx_range(struct __sk_buff, data_meta):
-	case bpf_ctx_range_till(struct __sk_buff, family, local_port):
-	case bpf_ctx_range(struct __sk_buff, tstamp):
-	case bpf_ctx_range(struct __sk_buff, wire_len):
+	default:
 		return false;
 	}
 
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index bb1a54747d64..94a450b2191a 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -707,6 +707,7 @@ bool __skb_flow_bpf_dissect(struct bpf_prog *prog,
 	/* Pass parameters to the BPF program */
 	memset(flow_keys, 0, sizeof(*flow_keys));
 	cb->qdisc_cb.flow_keys = flow_keys;
+	flow_keys->n_proto = skb->protocol;
 	flow_keys->nhoff = skb_network_offset(skb);
 	flow_keys->thoff = flow_keys->nhoff;
 
@@ -716,7 +717,8 @@ bool __skb_flow_bpf_dissect(struct bpf_prog *prog,
 	/* Restore state */
 	memcpy(cb, &cb_saved, sizeof(cb_saved));
 
-	flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff, 0, skb->len);
+	flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff,
+				   skb_network_offset(skb), skb->len);
 	flow_keys->thoff = clamp_t(u16, flow_keys->thoff,
 				   flow_keys->nhoff, skb->len);
 
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 17f36317363d..7e6dcc625701 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -304,6 +304,7 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
 
 	refcount_set(&net->count, 1);
 	refcount_set(&net->passive, 1);
+	get_random_bytes(&net->hash_mix, sizeof(u32));
 	net->dev_base_seq = 1;
 	net->user_ns = user_ns;
 	idr_init(&net->netns_ids);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 2415d9cb9b89..ef2cd5712098 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3801,7 +3801,7 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
 	unsigned int delta_truesize;
 	struct sk_buff *lp;
 
-	if (unlikely(p->len + len >= 65536))
+	if (unlikely(p->len + len >= 65536 || NAPI_GRO_CB(skb)->flush))
 		return -E2BIG;
 
 	lp = NAPI_GRO_CB(p)->last;
diff --git a/net/dccp/feat.c b/net/dccp/feat.c
index f227f002c73d..db87d9f58019 100644
--- a/net/dccp/feat.c
+++ b/net/dccp/feat.c
@@ -738,7 +738,12 @@ static int __feat_register_sp(struct list_head *fn, u8 feat, u8 is_local,
 	if (dccp_feat_clone_sp_val(&fval, sp_val, sp_len))
 		return -ENOMEM;
 
-	return dccp_feat_push_change(fn, feat, is_local, mandatory, &fval);
+	if (dccp_feat_push_change(fn, feat, is_local, mandatory, &fval)) {
+		kfree(fval.sp.vec);
+		return -ENOMEM;
+	}
+
+	return 0;
 }
 
 /**
diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c
index ed4f6dc26365..85c22ada4744 100644
--- a/net/dsa/tag_qca.c
+++ b/net/dsa/tag_qca.c
@@ -98,8 +98,18 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 	return skb;
 }
 
+static int qca_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
+                                int *offset)
+{
+	*offset = QCA_HDR_LEN;
+	*proto = ((__be16 *)skb->data)[0];
+
+	return 0;
+}
+
 const struct dsa_device_ops qca_netdev_ops = {
 	.xmit	= qca_tag_xmit,
 	.rcv	= qca_tag_rcv,
+	.flow_dissect = qca_tag_flow_dissect,
 	.overhead = QCA_HDR_LEN,
 };
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index ecce2dc78f17..1132d6d1796a 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -257,11 +257,10 @@ int ip_local_deliver(struct sk_buff *skb)
 		       ip_local_deliver_finish);
 }
 
-static inline bool ip_rcv_options(struct sk_buff *skb)
+static inline bool ip_rcv_options(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip_options *opt;
 	const struct iphdr *iph;
-	struct net_device *dev = skb->dev;
 
 	/* It looks as overkill, because not all
 	   IP options require packet mangling.
@@ -297,7 +296,7 @@ static inline bool ip_rcv_options(struct sk_buff *skb)
 			}
 		}
 
-		if (ip_options_rcv_srr(skb))
+		if (ip_options_rcv_srr(skb, dev))
 			goto drop;
 	}
 
@@ -353,7 +352,7 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk,
 	}
 #endif
 
-	if (iph->ihl > 5 && ip_rcv_options(skb))
+	if (iph->ihl > 5 && ip_rcv_options(skb, dev))
 		goto drop;
 
 	rt = skb_rtable(skb);
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index 32a35043c9f5..3db31bb9df50 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -612,7 +612,7 @@ void ip_forward_options(struct sk_buff *skb)
 	}
 }
 
-int ip_options_rcv_srr(struct sk_buff *skb)
+int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip_options *opt = &(IPCB(skb)->opt);
 	int srrspace, srrptr;
@@ -647,7 +647,7 @@ int ip_options_rcv_srr(struct sk_buff *skb)
 
 		orefdst = skb->_skb_refdst;
 		skb_dst_set(skb, NULL);
-		err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, skb->dev);
+		err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, dev);
 		rt2 = skb_rtable(skb);
 		if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) {
 			skb_dst_drop(skb);
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index cd4814f7e962..359da68d7c06 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -67,11 +67,6 @@ static unsigned int dctcp_alpha_on_init __read_mostly = DCTCP_MAX_ALPHA;
 module_param(dctcp_alpha_on_init, uint, 0644);
 MODULE_PARM_DESC(dctcp_alpha_on_init, "parameter for initial alpha value");
 
-static unsigned int dctcp_clamp_alpha_on_loss __read_mostly;
-module_param(dctcp_clamp_alpha_on_loss, uint, 0644);
-MODULE_PARM_DESC(dctcp_clamp_alpha_on_loss,
-		 "parameter for clamping alpha on loss");
-
 static struct tcp_congestion_ops dctcp_reno;
 
 static void dctcp_reset(const struct tcp_sock *tp, struct dctcp *ca)
@@ -164,21 +159,23 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags)
 	}
 }
 
-static void dctcp_state(struct sock *sk, u8 new_state)
+static void dctcp_react_to_loss(struct sock *sk)
 {
-	if (dctcp_clamp_alpha_on_loss && new_state == TCP_CA_Loss) {
-		struct dctcp *ca = inet_csk_ca(sk);
+	struct dctcp *ca = inet_csk_ca(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
 
-		/* If this extension is enabled, we clamp dctcp_alpha to
-		 * max on packet loss; the motivation is that dctcp_alpha
-		 * is an indicator to the extend of congestion and packet
-		 * loss is an indicator of extreme congestion; setting
-		 * this in practice turned out to be beneficial, and
-		 * effectively assumes total congestion which reduces the
-		 * window by half.
-		 */
-		ca->dctcp_alpha = DCTCP_MAX_ALPHA;
-	}
+	ca->loss_cwnd = tp->snd_cwnd;
+	tp->snd_ssthresh = max(tp->snd_cwnd >> 1U, 2U);
+}
+
+static void dctcp_state(struct sock *sk, u8 new_state)
+{
+	if (new_state == TCP_CA_Recovery &&
+	    new_state != inet_csk(sk)->icsk_ca_state)
+		dctcp_react_to_loss(sk);
+	/* We handle RTO in dctcp_cwnd_event to ensure that we perform only
+	 * one loss-adjustment per RTT.
+	 */
 }
 
 static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
@@ -190,6 +187,9 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
 	case CA_EVENT_ECN_NO_CE:
 		dctcp_ece_ack_update(sk, ev, &ca->prior_rcv_nxt, &ca->ce_state);
 		break;
+	case CA_EVENT_LOSS:
+		dctcp_react_to_loss(sk);
+		break;
 	default:
 		/* Don't care for the rest. */
 		break;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 277d71239d75..2f8039a26b08 100644
--- a/