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

Pull networking fixes from David Miller:

 1) Fix OOPS during nf_tables rule dump, from Florian Westphal.

 2) Use after free in ip_vs_in, from Yue Haibing.

 3) Fix various kTLS bugs (NULL deref during device removal resync,
    netdev notification ignoring, etc.) From Jakub Kicinski.

 4) Fix ipv6 redirects with VRF, from David Ahern.

 5) Memory leak fix in igmpv3_del_delrec(), from Eric Dumazet.

 6) Missing memory allocation failure check in ip6_ra_control(), from
    Gen Zhang. And likewise fix ip_ra_control().

 7) TX clean budget logic error in aquantia, from Igor Russkikh.

 8) SKB leak in llc_build_and_send_ui_pkt(), from Eric Dumazet.

 9) Double frees in mlx5, from Parav Pandit.

10) Fix lost MAC address in r8169 during PCI D3, from Heiner Kallweit.

11) Fix botched register access in mvpp2, from Antoine Tenart.

12) Use after free in napi_gro_frags(), from Eric Dumazet.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (89 commits)
  net: correct zerocopy refcnt with udp MSG_MORE
  ethtool: Check for vlan etype or vlan tci when parsing flow_rule
  net: don't clear sock->sk early to avoid trouble in strparser
  net-gro: fix use-after-free read in napi_gro_frags()
  net: dsa: tag_8021q: Create a stable binary format
  net: dsa: tag_8021q: Change order of rx_vid setup
  net: mvpp2: fix bad MVPP2_TXQ_SCHED_TOKEN_CNTR_REG queue value
  ipv4: tcp_input: fix stack out of bounds when parsing TCP options.
  mlxsw: spectrum: Prevent force of 56G
  mlxsw: spectrum_acl: Avoid warning after identical rules insertion
  net: dsa: mv88e6xxx: fix handling of upper half of STATS_TYPE_PORT
  r8169: fix MAC address being lost in PCI D3
  net: core: support XDP generic on stacked devices.
  netvsc: unshare skb in VF rx handler
  udp: Avoid post-GRO UDP checksum recalculation
  net: phy: dp83867: Set up RGMII TX delay
  net: phy: dp83867: do not call config_init twice
  net: phy: dp83867: increase SGMII autoneg timer duration
  net: phy: dp83867: fix speed 10 in sgmii mode
  net: phy: marvell10g: report if the PHY fails to boot firmware
  ...

net/core/dev.c

@@ -4502,23 +4502,6 @@ static int netif_rx_internal(struct sk_buff *skb)
 
 	trace_netif_rx(skb);
 
-	if (static_branch_unlikely(&generic_xdp_needed_key)) {
-		int ret;
-
-		preempt_disable();
-		rcu_read_lock();
-		ret = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), skb);
-		rcu_read_unlock();
-		preempt_enable();
-
-		/* Consider XDP consuming the packet a success from
-		 * the netdev point of view we do not want to count
-		 * this as an error.
-		 */
-		if (ret != XDP_PASS)
-			return NET_RX_SUCCESS;
-	}
-
 #ifdef CONFIG_RPS
 	if (static_branch_unlikely(&rps_needed)) {
 		struct rps_dev_flow voidflow, *rflow = &voidflow;
@@ -4858,6 +4841,18 @@ another_round:
 
 	__this_cpu_inc(softnet_data.processed);
 
+	if (static_branch_unlikely(&generic_xdp_needed_key)) {
+		int ret2;
+
+		preempt_disable();
+		ret2 = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), skb);
+		preempt_enable();
+
+		if (ret2 != XDP_PASS)
+			return NET_RX_DROP;
+		skb_reset_mac_len(skb);
+	}
+
 	if (skb->protocol == cpu_to_be16(ETH_P_8021Q) ||
 	    skb->protocol == cpu_to_be16(ETH_P_8021AD)) {
 		skb = skb_vlan_untag(skb);
@@ -5178,19 +5173,6 @@ static int netif_receive_skb_internal(struct sk_buff *skb)
 	if (skb_defer_rx_timestamp(skb))
 		return NET_RX_SUCCESS;
 
-	if (static_branch_unlikely(&generic_xdp_needed_key)) {
-		int ret;
-
-		preempt_disable();
-		rcu_read_lock();
-		ret = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), skb);
-		rcu_read_unlock();
-		preempt_enable();
-
-		if (ret != XDP_PASS)
-			return NET_RX_DROP;
-	}
-
 	rcu_read_lock();
 #ifdef CONFIG_RPS
 	if (static_branch_unlikely(&rps_needed)) {
@@ -5211,7 +5193,6 @@ static int netif_receive_skb_internal(struct sk_buff *skb)
 
 static void netif_receive_skb_list_internal(struct list_head *head)
 {
-	struct bpf_prog *xdp_prog = NULL;
 	struct sk_buff *skb, *next;
 	struct list_head sublist;
 
@@ -5224,21 +5205,6 @@ static void netif_receive_skb_list_internal(struct list_head *head)
 	}
 	list_splice_init(&sublist, head);
 
-	if (static_branch_unlikely(&generic_xdp_needed_key)) {
-		preempt_disable();
-		rcu_read_lock();
-		list_for_each_entry_safe(skb, next, head, list) {
-			xdp_prog = rcu_dereference(skb->dev->xdp_prog);
-			skb_list_del_init(skb);
-			if (do_xdp_generic(xdp_prog, skb) == XDP_PASS)
-				list_add_tail(&skb->list, &sublist);
-		}
-		rcu_read_unlock();
-		preempt_enable();
-		/* Put passed packets back on main list */
-		list_splice_init(&sublist, head);
-	}
-
 	rcu_read_lock();
 #ifdef CONFIG_RPS
 	if (static_branch_unlikely(&rps_needed)) {
@@ -5809,7 +5775,6 @@ static struct sk_buff *napi_frags_skb(struct napi_struct *napi)
 	skb_reset_mac_header(skb);
 	skb_gro_reset_offset(skb);
 
-	eth = skb_gro_header_fast(skb, 0);
 	if (unlikely(skb_gro_header_hard(skb, hlen))) {
 		eth = skb_gro_header_slow(skb, hlen, 0);
 		if (unlikely(!eth)) {
@@ -5819,6 +5784,7 @@ static struct sk_buff *napi_frags_skb(struct napi_struct *napi)
 			return NULL;
 		}
 	} else {
+		eth = (const struct ethhdr *)skb->data;
 		gro_pull_from_frag0(skb, hlen);
 		NAPI_GRO_CB(skb)->frag0 += hlen;
 		NAPI_GRO_CB(skb)->frag0_len -= hlen;

net/core/ethtool.c

@@ -3010,11 +3010,12 @@ ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input)
 		const struct ethtool_flow_ext *ext_h_spec = &fs->h_ext;
 		const struct ethtool_flow_ext *ext_m_spec = &fs->m_ext;
 
-		if (ext_m_spec->vlan_etype &&
-		    ext_m_spec->vlan_tci) {
+		if (ext_m_spec->vlan_etype) {
 			match->key.vlan.vlan_tpid = ext_h_spec->vlan_etype;
 			match->mask.vlan.vlan_tpid = ext_m_spec->vlan_etype;
+		}
 
+		if (ext_m_spec->vlan_tci) {
 			match->key.vlan.vlan_id =
 				ntohs(ext_h_spec->vlan_tci) & 0x0fff;
 			match->mask.vlan.vlan_id =
@@ -3024,7 +3025,10 @@ ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input)
 				(ntohs(ext_h_spec->vlan_tci) & 0xe000) >> 13;
 			match->mask.vlan.vlan_priority =
 				(ntohs(ext_m_spec->vlan_tci) & 0xe000) >> 13;
+		}
 
+		if (ext_m_spec->vlan_etype ||
+		    ext_m_spec->vlan_tci) {
 			match->dissector.used_keys |=
 				BIT(FLOW_DISSECTOR_KEY_VLAN);
 			match->dissector.offset[FLOW_DISSECTOR_KEY_VLAN] =

net/core/skbuff.c

@@ -1036,7 +1036,11 @@ struct ubuf_info *sock_zerocopy_realloc(struct sock *sk, size_t size,
 			uarg->len++;
 			uarg->bytelen = bytelen;
 			atomic_set(&sk->sk_zckey, ++next);
-			sock_zerocopy_get(uarg);
+
+			/* no extra ref when appending to datagram (MSG_MORE) */
+			if (sk->sk_type == SOCK_STREAM)
+				sock_zerocopy_get(uarg);
+
 			return uarg;
 		}
 	}