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

Pull networking updates from David Miller:

 1) BBR TCP congestion control, from Neal Cardwell, Yuchung Cheng and
    co. at Google. https://lwn.net/Articles/701165/

 2) Do TCP Small Queues for retransmits, from Eric Dumazet.

 3) Support collect_md mode for all IPV4 and IPV6 tunnels, from Alexei
    Starovoitov.

 4) Allow cls_flower to classify packets in ip tunnels, from Amir Vadai.

 5) Support DSA tagging in older mv88e6xxx switches, from Andrew Lunn.

 6) Support GMAC protocol in iwlwifi mwm, from Ayala Beker.

 7) Support ndo_poll_controller in mlx5, from Calvin Owens.

 8) Move VRF processing to an output hook and allow l3mdev to be
    loopback, from David Ahern.

 9) Support SOCK_DESTROY for UDP sockets. Also from David Ahern.

10) Congestion control in RXRPC, from David Howells.

11) Support geneve RX offload in ixgbe, from Emil Tantilov.

12) When hitting pressure for new incoming TCP data SKBs, perform a
    partial rathern than a full purge of the OFO queue (which could be
    huge). From Eric Dumazet.

13) Convert XFRM state and policy lookups to RCU, from Florian Westphal.

14) Support RX network flow classification to igb, from Gangfeng Huang.

15) Hardware offloading of eBPF in nfp driver, from Jakub Kicinski.

16) New skbmod packet action, from Jamal Hadi Salim.

17) Remove some inefficiencies in snmp proc output, from Jia He.

18) Add FIB notifications to properly propagate route changes to
    hardware which is doing forwarding offloading. From Jiri Pirko.

19) New dsa driver for qca8xxx chips, from John Crispin.

20) Implement RFC7559 ipv6 router solicitation backoff, from Maciej
    Żenczykowski.

21) Add L3 mode to ipvlan, from Mahesh Bandewar.

22) Support 802.1ad in mlx4, from Moshe Shemesh.

23) Support hardware LRO in mediatek driver, from Nelson Chang.

24) Add TC offloading to mlx5, from Or Gerlitz.

25) Convert various drivers to ethtool ksettings interfaces, from
    Philippe Reynes.

26) TX max rate limiting for cxgb4, from Rahul Lakkireddy.

27) NAPI support for ath10k, from Rajkumar Manoharan.

28) Support XDP in mlx5, from Rana Shahout and Saeed Mahameed.

29) UDP replicast support in TIPC, from Richard Alpe.

30) Per-queue statistics for qed driver, from Sudarsana Reddy Kalluru.

31) Support BQL in thunderx driver, from Sunil Goutham.

32) TSO support in alx driver, from Tobias Regnery.

33) Add stream parser engine and use it in kcm.

34) Support async DHCP replies in ipconfig module, from Uwe
    Kleine-König.

35) DSA port fast aging for mv88e6xxx driver, from Vivien Didelot.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1715 commits)
  mlxsw: switchx2: Fix misuse of hard_header_len
  mlxsw: spectrum: Fix misuse of hard_header_len
  net/faraday: Stop NCSI device on shutdown
  net/ncsi: Introduce ncsi_stop_dev()
  net/ncsi: Rework the channel monitoring
  net/ncsi: Allow to extend NCSI request properties
  net/ncsi: Rework request index allocation
  net/ncsi: Don't probe on the reserved channel ID (0x1f)
  net/ncsi: Introduce NCSI_RESERVED_CHANNEL
  net/ncsi: Avoid unused-value build warning from ia64-linux-gcc
  net: Add netdev all_adj_list refcnt propagation to fix panic
  net: phy: Add Edge-rate driver for Microsemi PHYs.
  vmxnet3: Wake queue from reset work
  i40e: avoid NULL pointer dereference and recursive errors on early PCI error
  qed: Add RoCE ll2 & GSI support
  qed: Add support for memory registeration verbs
  qed: Add support for QP verbs
  qed: PD,PKEY and CQ verb support
  qed: Add support for RoCE hw init
  qede: Add qedr framework
  ...

1 files changed, 57 insertions, 22 deletions

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 1ecbd7715f6d..4e03f64709bc 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -71,6 +71,8 @@ struct ovs_frag_data {
 static DEFINE_PER_CPU(struct ovs_frag_data, ovs_frag_data_storage);
 
 #define DEFERRED_ACTION_FIFO_SIZE 10
+#define OVS_RECURSION_LIMIT 5
+#define OVS_DEFERRED_ACTION_THRESHOLD (OVS_RECURSION_LIMIT - 2)
 struct action_fifo {
 	int head;
 	int tail;
@@ -78,7 +80,12 @@ struct action_fifo {
 	struct deferred_action fifo[DEFERRED_ACTION_FIFO_SIZE];
 };
 
+struct recirc_keys {
+	struct sw_flow_key key[OVS_DEFERRED_ACTION_THRESHOLD];
+};
+
 static struct action_fifo __percpu *action_fifos;
+static struct recirc_keys __percpu *recirc_keys;
 static DEFINE_PER_CPU(int, exec_actions_level);
 
 static void action_fifo_init(struct action_fifo *fifo)
@@ -153,7 +160,7 @@ static void update_ethertype(struct sk_buff *skb, struct ethhdr *hdr,
 static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key,
 		     const struct ovs_action_push_mpls *mpls)
 {
-	__be32 *new_mpls_lse;
+	struct mpls_shim_hdr *new_mpls_lse;
 
 	/* Networking stack do not allow simultaneous Tunnel and MPLS GSO. */
 	if (skb->encapsulation)
@@ -162,19 +169,23 @@ static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key,
 	if (skb_cow_head(skb, MPLS_HLEN) < 0)
 		return -ENOMEM;
 
+	if (!skb->inner_protocol) {
+		skb_set_inner_network_header(skb, skb->mac_len);
+		skb_set_inner_protocol(skb, skb->protocol);
+	}
+
 	skb_push(skb, MPLS_HLEN);
 	memmove(skb_mac_header(skb) - MPLS_HLEN, skb_mac_header(skb),
 		skb->mac_len);
 	skb_reset_mac_header(skb);
+	skb_set_network_header(skb, skb->mac_len);
 
-	new_mpls_lse = (__be32 *)skb_mpls_header(skb);
-	*new_mpls_lse = mpls->mpls_lse;
+	new_mpls_lse = mpls_hdr(skb);
+	new_mpls_lse->label_stack_entry = mpls->mpls_lse;
 
 	skb_postpush_rcsum(skb, new_mpls_lse, MPLS_HLEN);
 
 	update_ethertype(skb, eth_hdr(skb), mpls->mpls_ethertype);
-	if (!skb->inner_protocol)
-		skb_set_inner_protocol(skb, skb->protocol);
 	skb->protocol = mpls->mpls_ethertype;
 
 	invalidate_flow_key(key);
@@ -191,18 +202,19 @@ static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key,
 	if (unlikely(err))
 		return err;
 
-	skb_postpull_rcsum(skb, skb_mpls_header(skb), MPLS_HLEN);
+	skb_postpull_rcsum(skb, mpls_hdr(skb), MPLS_HLEN);
 
 	memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb),
 		skb->mac_len);
 
 	__skb_pull(skb, MPLS_HLEN);
 	skb_reset_mac_header(skb);
+	skb_set_network_header(skb, skb->mac_len);
 
-	/* skb_mpls_header() is used to locate the ethertype
-	 * field correctly in the presence of VLAN tags.
+	/* mpls_hdr() is used to locate the ethertype field correctly in the
+	 * presence of VLAN tags.
 	 */
-	hdr = (struct ethhdr *)(skb_mpls_header(skb) - ETH_HLEN);
+	hdr = (struct ethhdr *)((void *)mpls_hdr(skb) - ETH_HLEN);
 	update_ethertype(skb, hdr, ethertype);
 	if (eth_p_mpls(skb->protocol))
 		skb->protocol = ethertype;
@@ -214,7 +226,7 @@ static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key,
 static int set_mpls(struct sk_buff *skb, struct sw_flow_key *flow_key,
 		    const __be32 *mpls_lse, const __be32 *mask)
 {
-	__be32 *stack;
+	struct mpls_shim_hdr *stack;
 	__be32 lse;
 	int err;
 
@@ -222,16 +234,16 @@ static int set_mpls(struct sk_buff *skb, struct sw_flow_key *flow_key,
 	if (unlikely(err))
 		return err;
 
-	stack = (__be32 *)skb_mpls_header(skb);
-	lse = OVS_MASKED(*stack, *mpls_lse, *mask);
+	stack = mpls_hdr(skb);
+	lse = OVS_MASKED(stack->label_stack_entry, *mpls_lse, *mask);
 	if (skb->ip_summed == CHECKSUM_COMPLETE) {
-		__be32 diff[] = { ~(*stack), lse };
+		__be32 diff[] = { ~(stack->label_stack_entry), lse };
 
 		skb->csum = ~csum_partial((char *)diff, sizeof(diff),
 					  ~skb->csum);
 	}
 
-	*stack = lse;
+	stack->label_stack_entry = lse;
 	flow_key->mpls.top_lse = lse;
 	return 0;
 }
@@ -241,20 +253,24 @@ static int pop_vlan(struct sk_buff *skb, struct sw_flow_key *key)
 	int err;
 
 	err = skb_vlan_pop(skb);
-	if (skb_vlan_tag_present(skb))
+	if (skb_vlan_tag_present(skb)) {
 		invalidate_flow_key(key);
-	else
-		key->eth.tci = 0;
+	} else {
+		key->eth.vlan.tci = 0;
+		key->eth.vlan.tpid = 0;
+	}
 	return err;
 }
 
 static int push_vlan(struct sk_buff *skb, struct sw_flow_key *key,
 		     const struct ovs_action_push_vlan *vlan)
 {
-	if (skb_vlan_tag_present(skb))
+	if (skb_vlan_tag_present(skb)) {
 		invalidate_flow_key(key);
-	else
-		key->eth.tci = vlan->vlan_tci;
+	} else {
+		key->eth.vlan.tci = vlan->vlan_tci;
+		key->eth.vlan.tpid = vlan->vlan_tpid;
+	}
 	return skb_vlan_push(skb, vlan->vlan_tpid,
 			     ntohs(vlan->vlan_tci) & ~VLAN_TAG_PRESENT);
 }
@@ -1011,6 +1027,7 @@ static int execute_recirc(struct datapath *dp, struct sk_buff *skb,
 			  const struct nlattr *a, int rem)
 {
 	struct deferred_action *da;
+	int level;
 
 	if (!is_flow_key_valid(key)) {
 		int err;
@@ -1034,6 +1051,18 @@ static int execute_recirc(struct datapath *dp, struct sk_buff *skb,
 			return 0;
 	}
 
+	level = this_cpu_read(exec_actions_level);
+	if (level <= OVS_DEFERRED_ACTION_THRESHOLD) {
+		struct recirc_keys *rks = this_cpu_ptr(recirc_keys);
+		struct sw_flow_key *recirc_key = &rks->key[level - 1];
+
+		*recirc_key = *key;
+		recirc_key->recirc_id = nla_get_u32(a);
+		ovs_dp_process_packet(skb, recirc_key);
+
+		return 0;
+	}
+
 	da = add_deferred_actions(skb, key, NULL);
 	if (da) {
 		da->pkt_key.recirc_id = nla_get_u32(a);
@@ -1200,11 +1229,10 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			const struct sw_flow_actions *acts,
 			struct sw_flow_key *key)
 {
-	static const int ovs_recursion_limit = 5;
 	int err, level;
 
 	level = __this_cpu_inc_return(exec_actions_level);
-	if (unlikely(level > ovs_recursion_limit)) {
+	if (unlikely(level > OVS_RECURSION_LIMIT)) {
 		net_crit_ratelimited("ovs: recursion limit reached on datapath %s, probable configuration error\n",
 				     ovs_dp_name(dp));
 		kfree_skb(skb);
@@ -1229,10 +1257,17 @@ int action_fifos_init(void)
 	if (!action_fifos)
 		return -ENOMEM;
 
+	recirc_keys = alloc_percpu(struct recirc_keys);
+	if (!recirc_keys) {
+		free_percpu(action_fifos);
+		return -ENOMEM;
+	}
+
 	return 0;
 }
 
 void action_fifos_exit(void)
 {
 	free_percpu(action_fifos);
+	free_percpu(recirc_keys);
 }