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

Pull networking updates from David Millar:
 "Here are some highlights from the 2065 networking commits that
  happened this development cycle:

   1) XDP support for IXGBE (John Fastabend) and thunderx (Sunil Kowuri)

   2) Add a generic XDP driver, so that anyone can test XDP even if they
      lack a networking device whose driver has explicit XDP support
      (me).

   3) Sparc64 now has an eBPF JIT too (me)

   4) Add a BPF program testing framework via BPF_PROG_TEST_RUN (Alexei
      Starovoitov)

   5) Make netfitler network namespace teardown less expensive (Florian
      Westphal)

   6) Add symmetric hashing support to nft_hash (Laura Garcia Liebana)

   7) Implement NAPI and GRO in netvsc driver (Stephen Hemminger)

   8) Support TC flower offload statistics in mlxsw (Arkadi Sharshevsky)

   9) Multiqueue support in stmmac driver (Joao Pinto)

  10) Remove TCP timewait recycling, it never really could possibly work
      well in the real world and timestamp randomization really zaps any
      hint of usability this feature had (Soheil Hassas Yeganeh)

  11) Support level3 vs level4 ECMP route hashing in ipv4 (Nikolay
      Aleksandrov)

  12) Add socket busy poll support to epoll (Sridhar Samudrala)

  13) Netlink extended ACK support (Johannes Berg, Pablo Neira Ayuso,
      and several others)

  14) IPSEC hw offload infrastructure (Steffen Klassert)"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2065 commits)
  tipc: refactor function tipc_sk_recv_stream()
  tipc: refactor function tipc_sk_recvmsg()
  net: thunderx: Optimize page recycling for XDP
  net: thunderx: Support for XDP header adjustment
  net: thunderx: Add support for XDP_TX
  net: thunderx: Add support for XDP_DROP
  net: thunderx: Add basic XDP support
  net: thunderx: Cleanup receive buffer allocation
  net: thunderx: Optimize CQE_TX handling
  net: thunderx: Optimize RBDR descriptor handling
  net: thunderx: Support for page recycling
  ipx: call ipxitf_put() in ioctl error path
  net: sched: add helpers to handle extended actions
  qed*: Fix issues in the ptp filter config implementation.
  qede: Fix concurrency issue in PTP Tx path processing.
  stmmac: Add support for SIMATIC IOT2000 platform
  net: hns: fix ethtool_get_strings overflow in hns driver
  tcp: fix wraparound issue in tcp_lp
  bpf, arm64: fix jit branch offset related to ldimm64
  bpf, arm64: implement jiting of BPF_XADD
  ...

23 files changed, 1735 insertions, 467 deletions

diff --git a/net/core/datagram.c b/net/core/datagram.c
index d797baa69e43..db1866f2ffcf 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -256,8 +256,12 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
 		}
 
 		spin_unlock_irqrestore(&queue->lock, cpu_flags);
-	} while (sk_can_busy_loop(sk) &&
-		 sk_busy_loop(sk, flags & MSG_DONTWAIT));
+
+		if (!sk_can_busy_loop(sk))
+			break;
+
+		sk_busy_loop(sk, flags & MSG_DONTWAIT);
+	} while (!skb_queue_empty(&sk->sk_receive_queue));
 
 	error = -EAGAIN;
 
diff --git a/net/core/dev.c b/net/core/dev.c
index c57878be09d2..d07aa5ffb511 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -95,6 +95,7 @@
 #include <linux/notifier.h>
 #include <linux/skbuff.h>
 #include <linux/bpf.h>
+#include <linux/bpf_trace.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
 #include <net/busy_poll.h>
@@ -2975,6 +2976,9 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device
 		    __skb_linearize(skb))
 			goto out_kfree_skb;
 
+		if (validate_xmit_xfrm(skb, features))
+			goto out_kfree_skb;
+
 		/* If packet is not checksummed and device does not
 		 * support checksumming for this protocol, complete
 		 * checksumming here.
@@ -3444,6 +3448,7 @@ EXPORT_SYMBOL(netdev_max_backlog);
 
 int netdev_tstamp_prequeue __read_mostly = 1;
 int netdev_budget __read_mostly = 300;
+unsigned int __read_mostly netdev_budget_usecs = 2000;
 int weight_p __read_mostly = 64;           /* old backlog weight */
 int dev_weight_rx_bias __read_mostly = 1;  /* bias for backlog weight */
 int dev_weight_tx_bias __read_mostly = 1;  /* bias for output_queue quota */
@@ -4250,6 +4255,125 @@ static int __netif_receive_skb(struct sk_buff *skb)
 	return ret;
 }
 
+static struct static_key generic_xdp_needed __read_mostly;
+
+static int generic_xdp_install(struct net_device *dev, struct netdev_xdp *xdp)
+{
+	struct bpf_prog *new = xdp->prog;
+	int ret = 0;
+
+	switch (xdp->command) {
+	case XDP_SETUP_PROG: {
+		struct bpf_prog *old = rtnl_dereference(dev->xdp_prog);
+
+		rcu_assign_pointer(dev->xdp_prog, new);
+		if (old)
+			bpf_prog_put(old);
+
+		if (old && !new) {
+			static_key_slow_dec(&generic_xdp_needed);
+		} else if (new && !old) {
+			static_key_slow_inc(&generic_xdp_needed);
+			dev_disable_lro(dev);
+		}
+		break;
+	}
+
+	case XDP_QUERY_PROG:
+		xdp->prog_attached = !!rcu_access_pointer(dev->xdp_prog);
+		break;
+
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+static u32 netif_receive_generic_xdp(struct sk_buff *skb,
+				     struct bpf_prog *xdp_prog)
+{
+	struct xdp_buff xdp;
+	u32 act = XDP_DROP;
+	void *orig_data;
+	int hlen, off;
+	u32 mac_len;
+
+	/* Reinjected packets coming from act_mirred or similar should
+	 * not get XDP generic processing.
+	 */
+	if (skb_cloned(skb))
+		return XDP_PASS;
+
+	if (skb_linearize(skb))
+		goto do_drop;
+
+	/* The XDP program wants to see the packet starting at the MAC
+	 * header.
+	 */
+	mac_len = skb->data - skb_mac_header(skb);
+	hlen = skb_headlen(skb) + mac_len;
+	xdp.data = skb->data - mac_len;
+	xdp.data_end = xdp.data + hlen;
+	xdp.data_hard_start = skb->data - skb_headroom(skb);
+	orig_data = xdp.data;
+
+	act = bpf_prog_run_xdp(xdp_prog, &xdp);
+
+	off = xdp.data - orig_data;
+	if (off > 0)
+		__skb_pull(skb, off);
+	else if (off < 0)
+		__skb_push(skb, -off);
+
+	switch (act) {
+	case XDP_TX:
+		__skb_push(skb, mac_len);
+		/* fall through */
+	case XDP_PASS:
+		break;
+
+	default:
+		bpf_warn_invalid_xdp_action(act);
+		/* fall through */
+	case XDP_ABORTED:
+		trace_xdp_exception(skb->dev, xdp_prog, act);
+		/* fall through */
+	case XDP_DROP:
+	do_drop:
+		kfree_skb(skb);
+		break;
+	}
+
+	return act;
+}
+
+/* When doing generic XDP we have to bypass the qdisc layer and the
+ * network taps in order to match in-driver-XDP behavior.
+ */
+static void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog)
+{
+	struct net_device *dev = skb->dev;
+	struct netdev_queue *txq;
+	bool free_skb = true;
+	int cpu, rc;
+
+	txq = netdev_pick_tx(dev, skb, NULL);
+	cpu = smp_processor_id();
+	HARD_TX_LOCK(dev, txq, cpu);
+	if (!netif_xmit_stopped(txq)) {
+		rc = netdev_start_xmit(skb, dev, txq, 0);
+		if (dev_xmit_complete(rc))
+			free_skb = false;
+	}
+	HARD_TX_UNLOCK(dev, txq);
+	if (free_skb) {
+		trace_xdp_exception(dev, xdp_prog, XDP_TX);
+		kfree_skb(skb);
+	}
+}
+
 static int netif_receive_skb_internal(struct sk_buff *skb)
 {
 	int ret;
@@ -4261,6 +4385,21 @@ static int netif_receive_skb_internal(struct sk_buff *skb)
 
 	rcu_read_lock();
 
+	if (static_key_false(&generic_xdp_needed)) {
+		struct bpf_prog *xdp_prog = rcu_dereference(skb->dev->xdp_prog);
+
+		if (xdp_prog) {
+			u32 act = netif_receive_generic_xdp(skb, xdp_prog);
+
+			if (act != XDP_PASS) {
+				rcu_read_unlock();
+				if (act == XDP_TX)
+					generic_xdp_tx(skb, xdp_prog);
+				return NET_RX_DROP;
+			}
+		}
+	}
+
 #ifdef CONFIG_RPS
 	if (static_key_false(&rps_needed)) {
 		struct rps_dev_flow voidflow, *rflow = &voidflow;
@@ -4493,7 +4632,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	enum gro_result ret;
 	int grow;
 
-	if (!(skb->dev->features & NETIF_F_GRO))
+	if (netif_elide_gro(skb->dev))
 		goto normal;
 
 	if (skb->csum_bad)
@@ -5063,27 +5202,28 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock)
 		do_softirq();
 }
 
-bool sk_busy_loop(struct sock *sk, int nonblock)
+void napi_busy_loop(unsigned int napi_id,
+		    bool (*loop_end)(void *, unsigned long),
+		    void *loop_end_arg)
 {
-	unsigned long end_time = !nonblock ? sk_busy_loop_end_time(sk) : 0;
+	unsigned long start_time = loop_end ? busy_loop_current_time() : 0;
 	int (*napi_poll)(struct napi_struct *napi, int budget);
 	void *have_poll_lock = NULL;
 	struct napi_struct *napi;
-	int rc;
 
 restart:
-	rc = false;
 	napi_poll = NULL;
 
 	rcu_read_lock();
 
-	napi = napi_by_id(sk->sk_napi_id);
+	napi = napi_by_id(napi_id);
 	if (!napi)
 		goto out;
 
 	preempt_disable();
 	for (;;) {
-		rc = 0;
+		int work = 0;
+
 		local_bh_disable();
 		if (!napi_poll) {
 			unsigned long val = READ_ONCE(napi->state);
@@ -5101,16 +5241,15 @@ restart:
 			have_poll_lock = netpoll_poll_lock(napi);
 			napi_poll = napi->poll;
 		}
-		rc = napi_poll(napi, BUSY_POLL_BUDGET);
-		trace_napi_poll(napi, rc, BUSY_POLL_BUDGET);
+		work = napi_poll(napi, BUSY_POLL_BUDGET);
+		trace_napi_poll(napi, work, BUSY_POLL_BUDGET);
 count:
-		if (rc > 0)
-			__NET_ADD_STATS(sock_net(sk),
-					LINUX_MIB_BUSYPOLLRXPACKETS, rc);
+		if (work > 0)
+			__NET_ADD_STATS(dev_net(napi->dev),
+					LINUX_MIB_BUSYPOLLRXPACKETS, work);
 		local_bh_enable();
 
-		if (nonblock || !skb_queue_empty(&sk->sk_receive_queue) ||
-		    busy_loop_timeout(end_time))
+		if (!loop_end || loop_end(loop_end_arg, start_time))
 			break;
 
 		if (unlikely(need_resched())) {
@@ -5119,9 +5258,8 @@ count:
 			preempt_enable();
 			rcu_read_unlock();
 			cond_resched();
-			rc = !skb_queue_empty(&sk->sk_receive_queue);
-			if (rc || busy_loop_timeout(end_time))
-				return rc;
+			if (loop_end(loop_end_arg, start_time))
+				return;
 			goto restart;
 		}
 		cpu_relax();
@@ -5129,12 +5267,10 @@ count:
 	if (napi_poll)
 		busy_poll_stop(napi, have_poll_lock);
 	preempt_enable();
-	rc = !skb_queue_empty(&sk->sk_receive_queue);
 out:
 	rcu_read_unlock();
-	return rc;
 }
-EXPORT_SYMBOL(sk_busy_loop);
+EXPORT_SYMBOL(napi_busy_loop);
 
 #endif /* CONFIG_NET_RX_BUSY_POLL */
 
@@ -5146,10 +5282,10 @@ static void napi_hash_add(struct napi_struct *napi)
 
 	spin_lock(&napi_hash_lock);
 
-	/* 0..NR_CPUS+1 range is reserved for sender_cpu use */
+	/* 0..NR_CPUS range is reserved for sender_cpu use */
 	do {
-		if (unlikely(++napi_gen_id < NR_CPUS + 1))
-			napi_gen_id = NR_CPUS + 1;
+		if (unlikely(++napi_gen_id < MIN_NAPI_ID))
+			napi_gen_id = MIN_NAPI_ID;
 	} while (napi_by_id(napi_gen_id));
 	napi->napi_id = napi_gen_id;
 
@@ -5313,7 +5449,8 @@ out_unlock:
 static __latent_entropy void net_rx_action(struct softirq_action *h)
 {
 	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
-	unsigned long time_limit = jiffies + 2;
+	unsigned long time_limit = jiffies +
+		usecs_to_jiffies(netdev_budget_usecs);
 	int budget = netdev_budget;
 	LIST_HEAD(list);
 	LIST_HEAD(repoll);
@@ -6717,13 +6854,16 @@ EXPORT_SYMBOL(dev_change_proto_down);
 /**
  *	dev_change_xdp_fd - set or clear a bpf program for a device rx path
  *	@dev: device
+ *	@extack: netlink extended ack
  *	@fd: new program fd or negative value to clear
  *	@flags: xdp-related flags
  *
  *	Set or clear a bpf program for a device
  */
-int dev_change_xdp_fd(struct net_device *dev, int fd, u32 flags)
+int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
+		      int fd, u32 flags)
 {
+	int (*xdp_op)(struct net_device *dev, struct netdev_xdp *xdp);
 	const struct net_device_ops *ops = dev->netdev_ops;
 	struct bpf_prog *prog = NULL;
 	struct netdev_xdp xdp;
@@ -6731,14 +6871,16 @@ int dev_change_xdp_fd(struct net_device *dev, int fd, u32 flags)
 
 	ASSERT_RTNL();
 
-	if (!ops->ndo_xdp)
-		return -EOPNOTSUPP;
+	xdp_op = ops->ndo_xdp;
+	if (!xdp_op || (flags & XDP_FLAGS_SKB_MODE))
+		xdp_op = generic_xdp_install;
+
 	if (fd >= 0) {
 		if (flags & XDP_FLAGS_UPDATE_IF_NOEXIST) {
 			memset(&xdp, 0, sizeof(xdp));
 			xdp.command = XDP_QUERY_PROG;
 
-			err = ops->ndo_xdp(dev, &xdp);
+			err = xdp_op(dev, &xdp);
 			if (err < 0)
 				return err;
 			if (xdp.prog_attached)
@@ -6752,9 +6894,10 @@ int dev_change_xdp_fd(struct net_device *dev, int fd, u32 flags)
 
 	memset(&xdp, 0, sizeof(xdp));
 	xdp.command = XDP_SETUP_PROG;
+	xdp.extack = extack;
 	xdp.prog = prog;
 
-	err = ops->ndo_xdp(dev, &xdp);
+	err = xdp_op(dev, &xdp);
 	if (err < 0 && prog)
 		bpf_prog_put(prog);
 
@@ -7105,13 +7248,10 @@ void netif_stacked_transfer_operstate(const struct net_device *rootdev,
 	else
 		netif_dormant_off(dev);
 
-	if (netif_carrier_ok(rootdev)) {
-		if (!netif_carrier_ok(dev))
-			netif_carrier_on(dev);
-	} else {
-		if (netif_carrier_ok(dev))
-			netif_carrier_off(dev);
-	}
+	if (netif_carrier_ok(rootdev))
+		netif_carrier_on(dev);
+	else
+		netif_carrier_off(dev);
 }
 EXPORT_SYMBOL(netif_stacked_transfer_operstate);
 
@@ -7794,6 +7934,7 @@ EXPORT_SYMBOL(alloc_netdev_mqs);
 void free_netdev(struct net_device *dev)
 {
 	struct napi_struct *p, *n;
+	struct bpf_prog *prog;
 
 	might_sleep();
 	netif_free_tx_queues(dev);
@@ -7812,6 +7953,12 @@ void free_netdev(struct net_device *dev)
 	free_percpu(dev->pcpu_refcnt);
 	dev->pcpu_refcnt = NULL;
 
+	prog = rcu_dereference_protected(dev->xdp_prog, 1);
+	if (prog) {
+		bpf_prog_put(prog);
+		static_key_slow_dec(&generic_xdp_needed);
+	}
+
 	/*  Compatibility with error handling in drivers */
 	if (dev->reg_state == NETREG_UNINITIALIZED) {
 		netdev_freemem(dev);
diff --git a/net/core/devlink.c b/net/core/devlink.c
index e9c1e6acfb6d..b0b87a292e7c 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -1397,10 +1397,10 @@ static int devlink_nl_eswitch_fill(struct sk_buff *msg, struct devlink *devlink,
 				   u32 seq, int flags)
 {
 	const struct devlink_ops *ops = devlink->ops;
+	u8 inline_mode, encap_mode;
 	void *hdr;
 	int err = 0;
 	u16 mode;
-	u8 inline_mode;
 
 	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
 	if (!hdr)
@@ -1429,6 +1429,15 @@ static int devlink_nl_eswitch_fill(struct sk_buff *msg, struct devlink *devlink,
 			goto nla_put_failure;
 	}
 
+	if (ops->eswitch_encap_mode_get) {
+		err = ops->eswitch_encap_mode_get(devlink, &encap_mode);
+		if (err)
+			goto nla_put_failure;
+		err = nla_put_u8(msg, DEVLINK_ATTR_ESWITCH_ENCAP_MODE, encap_mode);
+		if (err)
+			goto nla_put_failure;
+	}
+
 	genlmsg_end(msg, hdr);
 	return 0;
 
@@ -1468,9 +1477,9 @@ static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb,
 {
 	struct devlink *devlink = info->user_ptr[0];
 	const struct devlink_ops *ops = devlink->ops;
-	u16 mode;
-	u8 inline_mode;
+	u8 inline_mode, encap_mode;
 	int err = 0;
+	u16 mode;
 
 	if (!ops)
 		return -EOPNOTSUPP;
@@ -1494,7 +1503,695 @@ static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb,
 			return err;
 	}
 
+	if (info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]) {
+		if (!ops->eswitch_encap_mode_set)
+			return -EOPNOTSUPP;
+		encap_mode = nla_get_u8(info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]);
+		err = ops->eswitch_encap_mode_set(devlink, encap_mode);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+int devlink_dpipe_match_put(struct sk_buff *skb,
+			    struct devlink_dpipe_match *match)
+{
+	struct devlink_dpipe_header *header = match->header;
+	struct devlink_dpipe_field *field = &header->fields[match->field_id];
+	struct nlattr *match_attr;
+
+	match_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_MATCH);
+	if (!match_attr)
+		return -EMSGSIZE;
+
+	if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_MATCH_TYPE, match->type) ||
+	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_INDEX, match->header_index) ||
+	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) ||
+	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) ||
+	    nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, match_attr);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, match_attr);
+	return -EMSGSIZE;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_match_put);
+
+static int devlink_dpipe_matches_put(struct devlink_dpipe_table *table,
+				     struct sk_buff *skb)
+{
+	struct nlattr *matches_attr;
+
+	matches_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLE_MATCHES);
+	if (!matches_attr)
+		return -EMSGSIZE;
+
+	if (table->table_ops->matches_dump(table->priv, skb))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, matches_attr);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, matches_attr);
+	return -EMSGSIZE;
+}
+
+int devlink_dpipe_action_put(struct sk_buff *skb,
+			     struct devlink_dpipe_action *action)
+{
+	struct devlink_dpipe_header *header = action->header;
+	struct devlink_dpipe_field *field = &header->fields[action->field_id];
+	struct nlattr *action_attr;
+
+	action_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_ACTION);
+	if (!action_attr)
+		return -EMSGSIZE;
+
+	if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_ACTION_TYPE, action->type) ||
+	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_INDEX, action->header_index) ||
+	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) ||
+	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) ||
+	    nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, action_attr);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, action_attr);
+	return -EMSGSIZE;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_action_put);
+
+static int devlink_dpipe_actions_put(struct devlink_dpipe_table *table,
+				     struct sk_buff *skb)
+{
+	struct nlattr *actions_attr;
+
+	actions_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLE_ACTIONS);
+	if (!actions_attr)
+		return -EMSGSIZE;
+
+	if (table->table_ops->actions_dump(table->priv, skb))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, actions_attr);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, actions_attr);
+	return -EMSGSIZE;
+}
+
+static int devlink_dpipe_table_put(struct sk_buff *skb,
+				   struct devlink_dpipe_table *table)
+{
+	struct nlattr *table_attr;
+
+	table_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLE);
+	if (!table_attr)
+		return -EMSGSIZE;
+
+	if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_TABLE_NAME, table->name) ||
+	    nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_SIZE, table->size,
+			      DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+	if (nla_put_u8(skb, DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED,
+		       table->counters_enabled))
+		goto nla_put_failure;
+
+	if (devlink_dpipe_matches_put(table, skb))
+		goto nla_put_failure;
+
+	if (devlink_dpipe_actions_put(table, skb))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, table_attr);
 	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, table_attr);
+	return -EMSGSIZE;
+}
+
+static int devlink_dpipe_send_and_alloc_skb(struct sk_buff **pskb,
+					    struct genl_info *info)
+{
+	int err;
+
+	if (*pskb) {
+		err = genlmsg_reply(*pskb, info);
+		if (err)
+			return err;
+	}
+	*pskb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!*pskb)
+		return -ENOMEM;
+	return 0;
+}
+
+static int devlink_dpipe_tables_fill(struct genl_info *info,
+				     enum devlink_command cmd, int flags,
+				     struct list_head *dpipe_tables,
+				     const char *table_name)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_dpipe_table *table;
+	struct nlattr *tables_attr;
+	struct sk_buff *skb = NULL;
+	struct nlmsghdr *nlh;
+	bool incomplete;
+	void *hdr;
+	int i;
+	int err;
+
+	table = list_first_entry(dpipe_tables,
+				 struct devlink_dpipe_table, list);
+start_again:
+	err = devlink_dpipe_send_and_alloc_skb(&skb, info);
+	if (err)
+		return err;
+
+	hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq,
+			  &devlink_nl_family, NLM_F_MULTI, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(skb, devlink))
+		goto nla_put_failure;
+	tables_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLES);
+	if (!tables_attr)
+		goto nla_put_failure;
+
+	i = 0;
+	incomplete = false;
+	list_for_each_entry_from(table, dpipe_tables, list) {
+		if (!table_name) {
+			err = devlink_dpipe_table_put(skb, table);
+			if (err) {
+				if (!i)
+					goto err_table_put;
+				incomplete = true;
+				break;
+			}
+		} else {
+			if (!strcmp(table->name, table_name)) {
+				err = devlink_dpipe_table_put(skb, table);
+				if (err)
+					break;
+			}
+		}
+		i++;
+	}
+
+	nla_nest_end(skb, tables_attr);
+	genlmsg_end(skb, hdr);
+	if (incomplete)
+		goto start_again;
+
+send_done:
+	nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq,
+			NLMSG_DONE, 0, flags | NLM_F_MULTI);
+	if (!nlh) {
+		err = devlink_dpipe_send_and_alloc_skb(&skb, info);
+		if (err)
+			goto err_skb_send_alloc;
+		goto send_done;
+	}
+
+	return genlmsg_reply(skb, info);
+
+nla_put_failure:
+	err = -EMSGSIZE;
+err_table_put:
+err_skb_send_alloc:
+	genlmsg_cancel(skb, hdr);
+	nlmsg_free(skb);
+	return err;
+}
+
+static int devlink_nl_cmd_dpipe_table_get(struct sk_buff *skb,
+					  struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	const char *table_name =  NULL;
+
+	if (info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME])
+		table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]);
+
+	return devlink_dpipe_tables_fill(info, DEVLINK_CMD_DPIPE_TABLE_GET, 0,
+					 &devlink->dpipe_table_list,
+					 table_name);
+}
+
+static int devlink_dpipe_value_put(struct sk_buff *skb,
+				   struct devlink_dpipe_value *value)
+{
+	if (nla_put(skb, DEVLINK_ATTR_DPIPE_VALUE,
+		    value->value_size, value->value))
+		return -EMSGSIZE;
+	if (value->mask)
+		if (nla_put(skb, DEVLINK_ATTR_DPIPE_VALUE_MASK,
+			    value->value_size, value->mask))
+			return -EMSGSIZE;
+	if (value->mapping_valid)
+		if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_VALUE_MAPPING,
+				value->mapping_value))
+			return -EMSGSIZE;
+	return 0;
+}
+
+static int devlink_dpipe_action_value_put(struct sk_buff *skb,
+					  struct devlink_dpipe_value *value)
+{
+	if (!value->action)
+		return -EINVAL;
+	if (devlink_dpipe_action_put(skb, value->action))
+		return -EMSGSIZE;
+	if (devlink_dpipe_value_put(skb, value))
+		return -EMSGSIZE;
+	return 0;
+}
+
+static int devlink_dpipe_action_values_put(struct sk_buff *skb,
+					   struct devlink_dpipe_value *values,
+					   unsigned int values_count)
+{
+	struct nlattr *action_attr;
+	int i;
+	int err;
+
+	for (i = 0; i < values_count; i++) {
+		action_attr = nla_nest_start(skb,
+					     DEVLINK_ATTR_DPIPE_ACTION_VALUE);
+		if (!action_attr)
+			return -EMSGSIZE;
+		err = devlink_dpipe_action_value_put(skb, &values[i]);
+		if (err)
+			goto err_action_value_put;
+		nla_nest_end(skb, action_attr);
+	}
+	return 0;
+
+err_action_value_put:
+	nla_nest_cancel(skb, action_attr);
+	return err;
+}
+
+static int devlink_dpipe_match_value_put(struct sk_buff *skb,
+					 struct devlink_dpipe_value *value)
+{
+	if (!value->match)
+		return -EINVAL;
+	if (devlink_dpipe_match_put(skb, value->match))
+		return -EMSGSIZE;
+	if (devlink_dpipe_value_put(skb, value))
+		return -EMSGSIZE;
+	return 0;
+}
+
+static int devlink_dpipe_match_values_put(struct sk_buff *skb,
+					  struct devlink_dpipe_value *values,
+					  unsigned int values_count)
+{
+	struct nlattr *match_attr;
+	int i;
+	int err;
+
+	for (i = 0; i < values_count; i++) {
+		match_attr = nla_nest_start(skb,
+					    DEVLINK_ATTR_DPIPE_MATCH_VALUE);
+		if (!match_attr)
+			return -EMSGSIZE;
+		err = devlink_dpipe_match_value_put(skb, &values[i]);
+		if (err)
+			goto err_match_value_put;
+		nla_nest_end(skb, match_attr);
+	}
+	return 0;
+
+err_match_value_put:
+	nla_nest_cancel(skb, match_attr);
+	return err;
+}
+
+static int devlink_dpipe_entry_put(struct sk_buff *skb,
+				   struct devlink_dpipe_entry *entry)
+{
+	struct nlattr *entry_attr, *matches_attr, *actions_attr;
+	int err;
+
+	entry_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_ENTRY);
+	if (!entry_attr)
+		return  -EMSGSIZE;
+
+	if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_ENTRY_INDEX, entry->index,
+			      DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+	if (entry->counter_valid)
+		if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_ENTRY_COUNTER,
+				      entry->counter, DEVLINK_ATTR_PAD))
+			goto nla_put_failure;
+
+	matches_attr = nla_nest_start(skb,
+				      DEVLINK_ATTR_DPIPE_ENTRY_MATCH_VALUES);
+	if (!matches_attr)
+		goto nla_put_failure;
+
+	err = devlink_dpipe_match_values_put(skb, entry->match_values,
+					     entry->match_values_count);
+	if (err) {
+		nla_nest_cancel(skb, matches_attr);
+		goto err_match_values_put;
+	}
+	nla_nest_end(skb, matches_attr);
+
+	actions_attr = nla_nest_start(skb,
+				      DEVLINK_ATTR_DPIPE_ENTRY_ACTION_VALUES);
+	if (!actions_attr)
+		goto nla_put_failure;
+
+	err = devlink_dpipe_action_values_put(skb, entry->action_values,
+					      entry->action_values_count);
+	if (err) {
+		nla_nest_cancel(skb, actions_attr);
+		goto err_action_values_put;
+	}
+	nla_nest_end(skb, actions_attr);
+
+	nla_nest_end(skb, entry_attr);
+	return 0;
+
+nla_put_failure:
+	err = -EMSGSIZE;
+err_match_values_put:
+err_action_values_put:
+	nla_nest_cancel(skb, entry_attr);
+	return err;
+}
+
+static struct devlink_dpipe_table *
+devlink_dpipe_table_find(struct list_head *dpipe_tables,
+			 const char *table_name)
+{
+	struct devlink_dpipe_table *table;
+
+	list_for_each_entry_rcu(table, dpipe_tables, list) {
+		if (!strcmp(table->name, table_name))
+			return table;
+	}
+	return NULL;
+}
+
+int devlink_dpipe_entry_ctx_prepare(struct devlink_dpipe_dump_ctx *dump_ctx)
+{
+	struct devlink *devlink;
+	int err;
+
+	err = devlink_dpipe_send_and_alloc_skb(&dump_ctx->skb,
+					       dump_ctx->info);
+	if (err)
+		return err;
+
+	dump_ctx->hdr = genlmsg_put(dump_ctx->skb,
+				    dump_ctx->info->snd_portid,
+				    dump_ctx->info->snd_seq,
+				    &devlink_nl_family, NLM_F_MULTI,
+				    dump_ctx->cmd);
+	if (!dump_ctx->hdr)
+		goto nla_put_failure;
+
+	devlink = dump_ctx->info->user_ptr[0];
+	if (devlink_nl_put_handle(dump_ctx->skb, devlink))
+		goto nla_put_failure;
+	dump_ctx->nest = nla_nest_start(dump_ctx->skb,
+					DEVLINK_ATTR_DPIPE_ENTRIES);
+	if (!dump_ctx->nest)
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(dump_ctx->skb, dump_ctx->hdr);
+	nlmsg_free(dump_ctx->skb);
+	return -EMSGSIZE;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_prepare);
+
+int devlink_dpipe_entry_ctx_append(struct devlink_dpipe_dump_ctx *dump_ctx,
+				   struct devlink_dpipe_entry *entry)
+{
+	return devlink_dpipe_entry_put(dump_ctx->skb, entry);
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_append);
+
+int devlink_dpipe_entry_ctx_close(struct devlink_dpipe_dump_ctx *dump_ctx)
+{
+	nla_nest_end(dump_ctx->skb, dump_ctx->nest);
+	genlmsg_end(dump_ctx->skb, dump_ctx->hdr);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_close);
+
+static int devlink_dpipe_entries_fill(struct genl_info *info,
+				      enum devlink_command cmd, int flags,
+				      struct devlink_dpipe_table *table)
+{
+	struct devlink_dpipe_dump_ctx dump_ctx;
+	struct nlmsghdr *nlh;
+	int err;
+
+	dump_ctx.skb = NULL;
+	dump_ctx.cmd = cmd;
+	dump_ctx.info = info;
+
+	err = table->table_ops->entries_dump(table->priv,
+					     table->counters_enabled,
+					     &dump_ctx);
+	if (err)
+		goto err_entries_dump;
+
+send_done:
+	nlh = nlmsg_put(dump_ctx.skb, info->snd_portid, info->snd_seq,
+			NLMSG_DONE, 0, flags | NLM_F_MULTI);
+	if (!nlh) {
+		err = devlink_dpipe_send_and_alloc_skb(&dump_ctx.skb, info);
+		if (err)
+			goto err_skb_send_alloc;
+		goto send_done;
+	}
+	return genlmsg_reply(dump_ctx.skb, info);
+
+err_entries_dump:
+err_skb_send_alloc:
+	genlmsg_cancel(dump_ctx.skb, dump_ctx.hdr);
+	nlmsg_free(dump_ctx.skb);
+	return err;
+}
+
+static int devlink_nl_cmd_dpipe_entries_get(struct sk_buff *skb,
+					    struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_dpipe_table *table;
+	const char *table_name;
+
+	if (!info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME])
+		return -EINVAL;
+
+	table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]);
+	table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
+					 table_name);
+	if (!table)
+		return -EINVAL;
+
+	if (!table->table_ops->entries_dump)
+		return -EINVAL;
+
+	return devlink_dpipe_entries_fill(info, DEVLINK_CMD_DPIPE_ENTRIES_GET,
+					  0, table);
+}
+
+static int devlink_dpipe_fields_put(struct sk_buff *skb,
+				    const struct devlink_dpipe_header *header)
+{
+	struct devlink_dpipe_field *field;
+	struct nlattr *field_attr;
+	int i;
+
+	for (i = 0; i < header->fields_count; i++) {
+		field = &header->fields[i];
+		field_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_FIELD);
+		if (!field_attr)
+			return -EMSGSIZE;
+		if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_FIELD_NAME, field->name) ||
+		    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) ||
+		    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_BITWIDTH, field->bitwidth) ||
+		    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_MAPPING_TYPE, field->mapping_type))
+			goto nla_put_failure;
+		nla_nest_end(skb, field_attr);
+	}
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, field_attr);
+	return -EMSGSIZE;
+}
+
+static int devlink_dpipe_header_put(struct sk_buff *skb,
+				    struct devlink_dpipe_header *header)
+{
+	struct nlattr *fields_attr, *header_attr;
+	int err;
+
+	header_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_HEADER);
+	if (!header_attr)
+		return -EMSGSIZE;
+
+	if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_HEADER_NAME, header->name) ||
+	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) ||
+	    nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global))
+		goto nla_put_failure;
+
+	fields_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_HEADER_FIELDS);
+	if (!fields_attr)
+		goto nla_put_failure;
+
+	err = devlink_dpipe_fields_put(skb, header);
+	if (err) {
+		nla_nest_cancel(skb, fields_attr);
+		goto nla_put_failure;
+	}
+	nla_nest_end(skb, fields_attr);
+	nla_nest_end(skb, header_attr);
+	return 0;
+
+nla_put_failure:
+	err = -EMSGSIZE;
+	nla_nest_cancel(skb, header_attr);
+	return err;
+}
+
+static int devlink_dpipe_headers_fill(struct genl_info *info,
+				      enum devlink_command cmd, int flags,
+				      struct devlink_dpipe_headers *
+				      dpipe_headers)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct nlattr *headers_attr;
+	struct sk_buff *skb = NULL;
+	struct nlmsghdr *nlh;
+	void *hdr;
+	int i, j;
+	int err;
+
+	i = 0;
+start_again:
+	err = devlink_dpipe_send_and_alloc_skb(&skb, info);
+	if (err)
+		return err;
+
+	hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq,
+			  &devlink_nl_family, NLM_F_MULTI, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(skb, devlink))
+		goto nla_put_failure;
+	headers_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_HEADERS);
+	if (!headers_attr)
+		goto nla_put_failure;
+
+	j = 0;
+	for (; i < dpipe_headers->headers_count; i++) {
+		err = devlink_dpipe_header_put(skb, dpipe_headers->headers[i]);
+		if (err) {
+			if (!j)
+				goto err_table_put;
+			break;
+		}
+		j++;
+	}
+	nla_nest_end(skb, headers_attr);
+	genlmsg_end(skb, hdr);
+	if (i != dpipe_headers->headers_count)
+		goto start_again;
+
+send_done:
+	nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq,
+			NLMSG_DONE, 0, flags | NLM_F_MULTI);
+	if (!nlh) {
+		err = devlink_dpipe_send_and_alloc_skb(&skb, info);
+		if (err)
+			goto err_skb_send_alloc;
+		goto send_done;
+	}
+	return genlmsg_reply(skb, info);
+
+nla_put_failure:
+	err = -EMSGSIZE;
+err_table_put:
+err_skb_send_alloc:
+	genlmsg_cancel(skb, hdr);
+	nlmsg_free(skb);
+	return err;
+}
+
+static int devlink_nl_cmd_dpipe_headers_get(struct sk_buff *skb,
+					    struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+
+	if (!devlink->dpipe_headers)
+		return -EOPNOTSUPP;
+	return devlink_dpipe_headers_fill(info, DEVLINK_CMD_DPIPE_HEADERS_GET,
+					  0, devlink->dpipe_headers);
+}
+
+static int devlink_dpipe_table_counters_set(struct devlink *devlink,
+					    const char *table_name,
+					    bool enable)
+{
+	struct devlink_dpipe_table *table;
+
+	table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
+					 table_name);
+	if (!table)
+		return -EINVAL;
+
+	if (table->counter_control_extern)
+		return -EOPNOTSUPP;
+
+	if (!(table->counters_enabled ^ enable))
+		return 0;
+
+	table->counters_enabled = enable;
+	if (table->table_ops->counters_set_update)
+		table->table_ops->counters_set_update(table->priv, enable);
+	return 0;
+}
+
+static int devlink_nl_cmd_dpipe_table_counters_set(struct sk_buff *skb,
+						   struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	const char *table_name;
+	bool counters_enable;
+
+	if (!info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME] ||
+	    !info->attrs[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED])
+		return -EINVAL;
+
+	table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]);
+	counters_enable = !!nla_get_u8(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED]);
+
+	return devlink_dpipe_table_counters_set(devlink, table_name,
+						counters_enable);
 }
 
 static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
@@ -1512,6 +2209,9 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16 },
 	[DEVLINK_ATTR_ESWITCH_MODE] = { .type = NLA_U16 },
 	[DEVLINK_ATTR_ESWITCH_INLINE_MODE] = { .type = NLA_U8 },
+	[DEVLINK_ATTR_ESWITCH_ENCAP_MODE] = { .type = NLA_U8 },
+	[DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING },
+	[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED] = { .type = NLA_U8 },
 };
 
 static const struct genl_ops devlink_nl_ops[] = {
@@ -1644,6 +2344,34 @@ static const struct genl_ops devlink_nl_ops[] = {
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 	},
+	{
+		.cmd = DEVLINK_CMD_DPIPE_TABLE_GET,
+		.doit = devlink_nl_cmd_dpipe_table_get,
+		.policy = devlink_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+	},
+	{
+		.cmd = DEVLINK_CMD_DPIPE_ENTRIES_GET,
+		.doit = devlink_nl_cmd_dpipe_entries_get,
+		.policy = devlink_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+	},
+	{
+		.cmd = DEVLINK_CMD_DPIPE_HEADERS_GET,
+		.doit = devlink_nl_cmd_dpipe_headers_get,
+		.policy = devlink_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+	},
+	{
+		.cmd = DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET,
+		.doit = devlink_nl_cmd_dpipe_table_counters_set,
+		.policy = devlink_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+	},
 };
 
 static struct genl_family devlink_nl_family __ro_after_init = {
@@ -1680,6 +2408,7 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size)
 	devlink_net_set(devlink, &init_net);
 	INIT_LIST_HEAD(&devlink->port_list);
 	INIT_LIST_HEAD(&devlink->sb_list);
+	INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list);
 	return devlink;
 }
 EXPORT_SYMBOL_GPL(devlink_alloc);
@@ -1880,6 +2609,133 @@ void devlink_sb_unregister(struct devlink *devlink, unsigned int sb_index)
 }
 EXPORT_SYMBOL_GPL(devlink_sb_unregister);
 
+/**
+ *	devlink_dpipe_headers_register - register dpipe headers
+ *
+ *	@devlink: devlink
+ *	@dpipe_headers: dpipe header array
+ *
+ *	Register the headers supported by hardware.
+ */
+int devlink_dpipe_headers_register(struct devlink *devlink,
+				   struct devlink_dpipe_headers *dpipe_headers)
+{
+	mutex_lock(&devlink_mutex);
+	devlink->dpipe_headers = dpipe_headers;
+	mutex_unlock(&devlink_mutex);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_headers_register);
+
+/**
+ *	devlink_dpipe_headers_unregister - unregister dpipe headers
+ *
+ *	@devlink: devlink
+ *
+ *	Unregister the headers supported by hardware.
+ */
+void devlink_dpipe_headers_unregister(struct devlink *devlink)
+{
+	mutex_lock(&devlink_mutex);
+	devlink->dpipe_headers = NULL;
+	mutex_unlock(&devlink_mutex);
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_headers_unregister);
+
+/**
+ *	devlink_dpipe_table_counter_enabled - check if counter allocation
+ *					      required
+ *	@devlink: devlink
+ *	@table_name: tables name
+ *
+ *	Used by driver to check if counter allocation is required.
+ *	After counter allocation is turned on the table entries
+ *	are updated to include counter statistics.
+ *
+ *	After that point on the driver must respect the counter
+ *	state so that each entry added to the table is added
+ *	with a counter.
+ */
+bool devlink_dpipe_table_counter_enabled(struct devlink *devlink,
+					 const char *table_name)
+{
+	struct devlink_dpipe_table *table;
+	bool enabled;
+
+	rcu_read_lock();
+	table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
+					 table_name);
+	enabled = false;
+	if (table)
+		enabled = table->counters_enabled;
+	rcu_read_unlock();
+	return enabled;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_table_counter_enabled);
+
+/**
+ *	devlink_dpipe_table_register - register dpipe table
+ *
+ *	@devlink: devlink
+ *	@table_name: table name
+ *	@table_ops: table ops
+ *	@priv: priv
+ *	@size: size
+ *	@counter_control_extern: external control for counters
+ */
+int devlink_dpipe_table_register(struct devlink *devlink,
+				 const char *table_name,
+				 struct devlink_dpipe_table_ops *table_ops,
+				 void *priv, u64 size,
+				 bool counter_control_extern)
+{
+	struct devlink_dpipe_table *table;
+
+	if (devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name))
+		return -EEXIST;
+
+	table = kzalloc(sizeof(*table), GFP_KERNEL);
+	if (!table)
+		return -ENOMEM;
+
+	table->name = table_name;
+	table->table_ops = table_ops;
+	table->priv = priv;
+	table->size = size;
+	table->counter_control_extern = counter_control_extern;
+
+	mutex_lock(&devlink_mutex);
+	list_add_tail_rcu(&table->list, &devlink->dpipe_table_list);
+	mutex_unlock(&devlink_mutex);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_table_register);
+
+/**
+ *	devlink_dpipe_table_unregister - unregister dpipe table
+ *
+ *	@devlink: devlink
+ *	@table_name: table name
+ */
+void devlink_dpipe_table_unregister(struct devlink *devlink,
+				    const char *table_name)
+{
+	struct devlink_dpipe_table *table;
+
+	mutex_lock(&devlink_mutex);
+	table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
+					 table_name);
+	if (!table)
+		goto unlock;
+	list_del_rcu(&table->list);
+	mutex_unlock(&devlink_mutex);
+	kfree_rcu(table, rcu);
+	return;
+unlock:
+	mutex_unlock(&devlink_mutex);
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_table_unregister);
+
 static int __init devlink_module_init(void)
 {
 	return genl_register_family(&devlink_nl_family);
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index fb55327dcfea..70ccda233bd1 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -412,9 +412,8 @@ static int __init init_net_drop_monitor(void)
 	for_each_possible_cpu(cpu) {
 		data = &per_cpu(dm_cpu_data, cpu);
 		INIT_WORK(&data->dm_alert_work, send_dm_alert);
-		init_timer(&data->send_timer);
-		data->send_timer.data = (unsigned long)data;
-		data->send_timer.function = sched_send_work;
+		setup_timer(&data->send_timer, sched_send_work,
+			    (unsigned long)data);
 		spin_lock_init(&data->lock);
 		reset_per_cpu_data(data);
 	}
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index aecb2c7241b6..03111a2d6653 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -90,6 +90,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
 	[NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT] = "tx-udp_tnl-csum-segmentation",
 	[NETIF_F_GSO_PARTIAL_BIT] =	 "tx-gso-partial",
 	[NETIF_F_GSO_SCTP_BIT] =	 "tx-sctp-segmentation",
+	[NETIF_F_GSO_ESP_BIT] =		 "tx-esp-segmentation",
 
 	[NETIF_F_FCOE_CRC_BIT] =         "tx-checksum-fcoe-crc",
 	[NETIF_F_SCTP_CRC_BIT] =        "tx-checksum-sctp",
@@ -103,12 +104,15 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
 	[NETIF_F_RXALL_BIT] =            "rx-all",
 	[NETIF_F_HW_L2FW_DOFFLOAD_BIT] = "l2-fwd-offload",
 	[NETIF_F_HW_TC_BIT] =		 "hw-tc-offload",
+	[NETIF_F_HW_ESP_BIT] =		 "esp-hw-offload",
+	[NETIF_F_HW_ESP_TX_CSUM_BIT] =	 "esp-tx-csum-hw-offload",
 };
 
 static const char
 rss_hash_func_strings[ETH_RSS_HASH_FUNCS_COUNT][ETH_GSTRING_LEN] = {
 	[ETH_RSS_HASH_TOP_BIT] =	"toeplitz",
 	[ETH_RSS_HASH_XOR_BIT] =	"xor",
+	[ETH_RSS_HASH_CRC32_BIT] =	"crc32",
 };
 
 static const char
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index b6791d94841d..f21c4d3aeae0 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -23,6 +23,20 @@ static const struct fib_kuid_range fib_kuid_range_unset = {
 	KUIDT_INIT(~0),
 };
 
+bool fib_rule_matchall(const struct fib_rule *rule)
+{
+	if (rule->iifindex || rule->oifindex || rule->mark || rule->tun_id ||
+	    rule->flags)
+		return false;
+	if (rule->suppress_ifgroup != -1 || rule->suppress_prefixlen != -1)
+		return false;
+	if (!uid_eq(rule->uid_range.start, fib_kuid_range_unset.start) ||
+	    !uid_eq(rule->uid_range.end, fib_kuid_range_unset.end))
+		return false;
+	return true;
+}
+EXPORT_SYMBOL_GPL(fib_rule_matchall);
+
 int fib_default_rule_add(struct fib_rules_ops *ops,
 			 u32 pref, u32 table, u32 flags)
 {
@@ -354,7 +368,8 @@ static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh,
 	return 0;
 }
 
-int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh)
+int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
+		   struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct fib_rule_hdr *frh = nlmsg_data(nlh);
@@ -372,7 +387,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh)
 		goto errout;
 	}
 
-	err = nlmsg_parse(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy);
+	err = nlmsg_parse(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy, extack);
 	if (err < 0)
 		goto errout;
 
@@ -425,6 +440,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (tb[FRA_TUN_ID])
 		rule->tun_id = nla_get_be64(tb[FRA_TUN_ID]);
 
+	err = -EINVAL;
 	if (tb[FRA_L3MDEV]) {
 #ifdef CONFIG_NET_L3_MASTER_DEV
 		rule->l3mdev = nla_get_u8(tb[FRA_L3MDEV]);
@@ -446,7 +462,6 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh)
 	else
 		rule->suppress_ifgroup = -1;
 
-	err = -EINVAL;
 	if (tb[FRA_GOTO]) {
 		if (rule->action != FR_ACT_GOTO)
 			goto errout_free;
@@ -547,7 +562,8 @@ errout:
 }
 EXPORT_SYMBOL_GPL(fib_nl_newrule);
 
-int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh)
+int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh,
+		   struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct fib_rule_hdr *frh = nlmsg_data(nlh);
@@ -566,7 +582,7 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh)
 		goto errout;
 	}
 
-	err = nlmsg_parse(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy);
+	err = nlmsg_parse(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy, extack);
 	if (err < 0)
 		goto errout;
 
@@ -576,8 +592,10 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	if (tb[FRA_UID_RANGE]) {
 		range = nla_get_kuid_range(tb);
-		if (!uid_range_set(&range))
+		if (!uid_range_set(&range)) {
+			err = -EINVAL;
 			goto errout;
+		}
 	} else {
 		range = fib_kuid_range_unset;
 	}
diff --git a/net/core/filter.c b/net/core/filter.c
index ebaeaf2e46e8..a253a6197e6b 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -26,6 +26,7 @@
 #include <linux/mm.h>
 #include <linux/fcntl.h>
 #include <linux/socket.h>
+#include <linux/sock_diag.h>
 #include <linux/in.h>
 #include <linux/inet.h>
 #include <linux/netdevice.h>
@@ -52,6 +53,7 @@
 #include <net/dst_metadata.h>
 #include <net/dst.h>
 #include <net/sock_reuseport.h>
+#include <net/busy_poll.h>
 
 /**
  *	sk_filter_trim_cap - run a packet through a socket filter
@@ -91,7 +93,12 @@ int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap)
 	rcu_read_lock();
 	filter = rcu_dereference(sk->sk_filter);
 	if (filter) {
-		unsigned int pkt_len = bpf_prog_run_save_cb(filter->prog, skb);
+		struct sock *save_sk = skb->sk;
+		unsigned int pkt_len;
+
+		skb->sk = sk;
+		pkt_len = bpf_prog_run_save_cb(filter->prog, skb);
+		skb->sk = save_sk;
 		err = pkt_len ? pskb_trim(skb, max(cap, pkt_len)) : -EPERM;
 	}
 	rcu_read_unlock();
@@ -348,7 +355,8 @@ static bool convert_bpf_extensions(struct sock_filter *fp,
  *	@new_prog: buffer where converted program will be stored
  *	@new_len: pointer to store length of converted program
  *
- * Remap 'sock_filter' style BPF instruction set to 'sock_filter_ext' style.
+ * Remap 'sock_filter' style classic BPF (cBPF) instruction set to 'bpf_insn'
+ * style extended BPF (eBPF).
  * Conversion workflow:
  *
  * 1) First pass for calculating the new program length:
@@ -928,7 +936,7 @@ static void sk_filter_release_rcu(struct rcu_head *rcu)
  */
 static void sk_filter_release(struct sk_filter *fp)
 {
-	if (atomic_dec_and_test(&fp->refcnt))
+	if (refcount_dec_and_test(&fp->refcnt))
 		call_rcu(&fp->rcu, sk_filter_release_rcu);
 }
 
@@ -943,20 +951,27 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
 /* try to charge the socket memory if there is space available
  * return true on success
  */
-bool sk_filter_charge(struct sock *sk, struct sk_filter *fp)
+static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp)
 {
 	u32 filter_size = bpf_prog_size(fp->prog->len);
 
 	/* same check as in sock_kmalloc() */
 	if (filter_size <= sysctl_optmem_max &&
 	    atomic_read(&sk->sk_omem_alloc) + filter_size < sysctl_optmem_max) {
-		atomic_inc(&fp->refcnt);
 		atomic_add(filter_size, &sk->sk_omem_alloc);
 		return true;
 	}
 	return false;
 }
 
+bool sk_filter_charge(struct sock *sk, struct sk_filter *fp)
+{
+	bool ret = __sk_filter_charge(sk, fp);
+	if (ret)
+		refcount_inc(&fp->refcnt);
+	return ret;
+}
+
 static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp)
 {
 	struct sock_filter *old_prog;
@@ -1179,12 +1194,12 @@ static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk)
 		return -ENOMEM;
 
 	fp->prog = prog;
-	atomic_set(&fp->refcnt, 0);
 
-	if (!sk_filter_charge(sk, fp)) {
+	if (!__sk_filter_charge(sk, fp)) {
 		kfree(fp);
 		return -ENOMEM;
 	}
+	refcount_set(&fp->refcnt, 1);
 
 	old_fp = rcu_dereference_protected(sk->sk_filter,
 					   lockdep_sock_is_held(sk));
@@ -2599,6 +2614,36 @@ static const struct bpf_func_proto bpf_xdp_event_output_proto = {
 	.arg5_type	= ARG_CONST_SIZE,
 };
 
+BPF_CALL_1(bpf_get_socket_cookie, struct sk_buff *, skb)
+{
+	return skb->sk ? sock_gen_cookie(skb->sk) : 0;
+}
+
+static const struct bpf_func_proto bpf_get_socket_cookie_proto = {
+	.func           = bpf_get_socket_cookie,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_CTX,
+};
+
+BPF_CALL_1(bpf_get_socket_uid, struct sk_buff *, skb)
+{
+	struct sock *sk = sk_to_full_sk(skb->sk);
+	kuid_t kuid;
+
+	if (!sk || !sk_fullsock(sk))
+		return overflowuid;
+	kuid = sock_net_uid(sock_net(sk), sk);
+	return from_kuid_munged(sock_net(sk)->user_ns, kuid);
+}
+
+static const struct bpf_func_proto bpf_get_socket_uid_proto = {
+	.func           = bpf_get_socket_uid,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_CTX,
+};
+
 static const struct bpf_func_proto *
 bpf_base_func_proto(enum bpf_func_id func_id)
 {
@@ -2633,6 +2678,10 @@ sk_filter_func_proto(enum bpf_func_id func_id)
 	switch (func_id) {
 	case BPF_FUNC_skb_load_bytes:
 		return &bpf_skb_load_bytes_proto;
+	case BPF_FUNC_get_socket_cookie:
+		return &bpf_get_socket_cookie_proto;
+	case BPF_FUNC_get_socket_uid:
+		return &bpf_get_socket_uid_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -2692,6 +2741,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id)
 		return &bpf_get_smp_processor_id_proto;
 	case BPF_FUNC_skb_under_cgroup:
 		return &bpf_skb_under_cgroup_proto;
+	case BPF_FUNC_get_socket_cookie:
+		return &bpf_get_socket_cookie_proto;
+	case BPF_FUNC_get_socket_uid:
+		return &bpf_get_socket_uid_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -2715,12 +2768,7 @@ xdp_func_proto(enum bpf_func_id func_id)
 static const struct bpf_func_proto *
 cg_skb_func_proto(enum bpf_func_id func_id)
 {
-	switch (func_id) {
-	case BPF_FUNC_skb_load_bytes:
-		return &bpf_skb_load_bytes_proto;
-	default:
-		return bpf_base_func_proto(func_id);
-	}
+	return sk_filter_func_proto(func_id);
 }
 
 static const struct bpf_func_proto *
@@ -3156,6 +3204,19 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type,
 			*insn++ = BPF_MOV64_IMM(si->dst_reg, 0);
 #endif
 		break;
+
+	case offsetof(struct __sk_buff, napi_id):
+#if defined(CONFIG_NET_RX_BUSY_POLL)
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, napi_id) != 4);
+
+		*insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg,
+				      offsetof(struct sk_buff, napi_id));
+		*insn++ = BPF_JMP_IMM(BPF_JGE, si->dst_reg, MIN_NAPI_ID, 1);
+		*insn++ = BPF_MOV64_IMM(si->dst_reg, 0);
+#else
+		*insn++ = BPF_MOV64_IMM(si->dst_reg, 0);
+#endif
+		break;
 	}
 
 	return insn - insn_buf;
@@ -3252,111 +3313,55 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type,
 	return insn - insn_buf;
 }
 
-static const struct bpf_verifier_ops sk_filter_ops = {
+const struct bpf_verifier_ops sk_filter_prog_ops = {
 	.get_func_proto		= sk_filter_func_proto,
 	.is_valid_access	= sk_filter_is_valid_access,
 	.convert_ctx_access	= bpf_convert_ctx_access,
 };
 
-static const struct bpf_verifier_ops tc_cls_act_ops = {
+const struct bpf_verifier_ops tc_cls_act_prog_ops = {
 	.get_func_proto		= tc_cls_act_func_proto,
 	.is_valid_access	= tc_cls_act_is_valid_access,
 	.convert_ctx_access	= tc_cls_act_convert_ctx_access,
 	.gen_prologue		= tc_cls_act_prologue,
+	.test_run		= bpf_prog_test_run_skb,
 };
 
-static const struct bpf_verifier_ops xdp_ops = {
+const struct bpf_verifier_ops xdp_prog_ops = {
 	.get_func_proto		= xdp_func_proto,
 	.is_valid_access	= xdp_is_valid_access,
 	.convert_ctx_access	= xdp_convert_ctx_access,
+	.test_run		= bpf_prog_test_run_xdp,
 };
 
-static const struct bpf_verifier_ops cg_skb_ops = {
+const struct bpf_verifier_ops cg_skb_prog_ops = {
 	.get_func_proto		= cg_skb_func_proto,
 	.is_valid_access	= sk_filter_is_valid_access,
 	.convert_ctx_access	= bpf_convert_ctx_access,
+	.test_run		= bpf_prog_test_run_skb,
 };
 
-static const struct bpf_verifier_ops lwt_inout_ops = {
+const struct bpf_verifier_ops lwt_inout_prog_ops = {
 	.get_func_proto		= lwt_inout_func_proto,
 	.is_valid_access	= lwt_is_valid_access,
 	.convert_ctx_access	= bpf_convert_ctx_access,
+	.test_run		= bpf_prog_test_run_skb,
 };
 
-static const struct bpf_verifier_ops lwt_xmit_ops = {
+const struct bpf_verifier_ops lwt_xmit_prog_ops = {
 	.get_func_proto		= lwt_xmit_func_proto,
 	.is_valid_access	= lwt_is_valid_access,
 	.convert_ctx_access	= bpf_convert_ctx_access,
 	.gen_prologue		= tc_cls_act_prologue,
+	.test_run		= bpf_prog_test_run_skb,
 };
 
-static const struct bpf_verifier_ops cg_sock_ops = {
+const struct bpf_verifier_ops cg_sock_prog_ops = {
 	.get_func_proto		= bpf_base_func_proto,
 	.is_valid_access	= sock_filter_is_valid_access,
 	.convert_ctx_access	= sock_filter_convert_ctx_access,
 };
 
-static struct bpf_prog_type_list sk_filter_type __ro_after_init = {
-	.ops	= &sk_filter_ops,
-	.type	= BPF_PROG_TYPE_SOCKET_FILTER,
-};
-
-static struct bpf_prog_type_list sched_cls_type __ro_after_init = {
-	.ops	= &tc_cls_act_ops,
-	.type	= BPF_PROG_TYPE_SCHED_CLS,
-};
-
-static struct bpf_prog_type_list sched_act_type __ro_after_init = {
-	.ops	= &tc_cls_act_ops,
-	.type	= BPF_PROG_TYPE_SCHED_ACT,
-};
-
-static struct bpf_prog_type_list xdp_type __ro_after_init = {
-	.ops	= &xdp_ops,
-	.type	= BPF_PROG_TYPE_XDP,
-};
-
-static struct bpf_prog_type_list cg_skb_type __ro_after_init = {
-	.ops	= &cg_skb_ops,
-	.type	= BPF_PROG_TYPE_CGROUP_SKB,
-};
-
-static struct bpf_prog_type_list lwt_in_type __ro_after_init = {
-	.ops	= &lwt_inout_ops,
-	.type	= BPF_PROG_TYPE_LWT_IN,
-};
-
-static struct bpf_prog_type_list lwt_out_type __ro_after_init = {
-	.ops	= &lwt_inout_ops,
-	.type	= BPF_PROG_TYPE_LWT_OUT,
-};
-
-static struct bpf_prog_type_list lwt_xmit_type __ro_after_init = {
-	.ops	= &lwt_xmit_ops,
-	.type	= BPF_PROG_TYPE_LWT_XMIT,
-};
-
-static struct bpf_prog_type_list cg_sock_type __ro_after_init = {
-	.ops	= &cg_sock_ops,
-	.type	= BPF_PROG_TYPE_CGROUP_SOCK
-};
-
-static int __init register_sk_filter_ops(void)
-{
-	bpf_register_prog_type(&sk_filter_type);
-	bpf_register_prog_type(&sched_cls_type);
-	bpf_register_prog_type(&sched_act_type);
-	bpf_register_prog_type(&xdp_type);
-	bpf_register_prog_type(&cg_skb_type);
-	bpf_register_prog_type(&cg_sock_type);
-	bpf_register_prog_type(&lwt_in_type);
-	bpf_register_prog_type(&lwt_out_type);
-	bpf_register_prog_type(&lwt_xmit_type);
-
-	return 0;
-}
-late_initcall(register_sk_filter_ops);
-
 int sk_detach_filter(struct sock *sk)
 {
 	int ret = -ENOENT;
diff --git a/net/core/flow.c b/net/core/flow.c
index f765c11d8df5..f7f5d1932a27 100644
--- a/net/core/flow.c
+++ b/net/core/flow.c
@@ -47,7 +47,7 @@ struct flow_flush_info {
 
 static struct kmem_cache *flow_cachep __read_mostly;
 
-#define flow_cache_hash_size(cache)	(1 << (cache)->hash_shift)
+#define flow_cache_hash_size(cache)	(1U << (cache)->hash_shift)
 #define FLOW_HASH_RND_PERIOD		(10 * 60 * HZ)
 
 static void flow_cache_new_hashrnd(unsigned long arg)
@@ -99,7 +99,8 @@ static void flow_cache_gc_task(struct work_struct *work)
 }
 
 static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp,
-				     int deleted, struct list_head *gc_list,
+				     unsigned int deleted,
+				     struct list_head *gc_list,
 				     struct netns_xfrm *xfrm)
 {
 	if (deleted) {
@@ -114,17 +115,18 @@ static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp,
 
 static void __flow_cache_shrink(struct flow_cache *fc,
 				struct flow_cache_percpu *fcp,
-				int shrink_to)
+				unsigned int shrink_to)
 {
 	struct flow_cache_entry *fle;
 	struct hlist_node *tmp;
 	LIST_HEAD(gc_list);
-	int i, deleted = 0;
+	unsigned int deleted = 0;
 	struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm,
 						flow_cache_global);
+	unsigned int i;
 
 	for (i = 0; i < flow_cache_hash_size(fc); i++) {
-		int saved = 0;
+		unsigned int saved = 0;
 
 		hlist_for_each_entry_safe(fle, tmp,
 					  &fcp->hash_table[i], u.hlist) {
@@ -145,7 +147,7 @@ static void __flow_cache_shrink(struct flow_cache *fc,
 static void flow_cache_shrink(struct flow_cache *fc,
 			      struct flow_cache_percpu *fcp)
 {
-	int shrink_to = fc->low_watermark / flow_cache_hash_size(fc);
+	unsigned int shrink_to = fc->low_watermark / flow_cache_hash_size(fc);
 
 	__flow_cache_shrink(fc, fcp, shrink_to);
 }
@@ -161,7 +163,7 @@ static void flow_new_hash_rnd(struct flow_cache *fc,
 static u32 flow_hash_code(struct flow_cache *fc,
 			  struct flow_cache_percpu *fcp,
 			  const struct flowi *key,
-			  size_t keysize)
+			  unsigned int keysize)
 {
 	const u32 *k = (const u32 *) key;
 	const u32 length = keysize * sizeof(flow_compare_t) / sizeof(u32);
@@ -174,7 +176,7 @@ static u32 flow_hash_code(struct flow_cache *fc,
  * important assumptions that we can here, such as alignment.
  */
 static int flow_key_compare(const struct flowi *key1, const struct flowi *key2,
-			    size_t keysize)
+			    unsigned int keysize)
 {
 	const flow_compare_t *k1, *k1_lim, *k2;
 
@@ -199,7 +201,7 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
 	struct flow_cache_percpu *fcp;
 	struct flow_cache_entry *fle, *tfle;
 	struct flow_cache_object *flo;
-	size_t keysize;
+	unsigned int keysize;
 	unsigned int hash;
 
 	local_bh_disable();
@@ -295,9 +297,10 @@ static void flow_cache_flush_tasklet(unsigned long data)
 	struct flow_cache_entry *fle;
 	struct hlist_node *tmp;
 	LIST_HEAD(gc_list);
-	int i, deleted = 0;
+	unsigned int deleted = 0;
 	struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm,
 						flow_cache_global);
+	unsigned int i;
 
 	fcp = this_cpu_ptr(fc->percpu);
 	for (i = 0; i < flow_cache_hash_size(fc); i++) {
@@ -327,7 +330,7 @@ static void flow_cache_flush_tasklet(unsigned long data)
 static int flow_cache_percpu_empty(struct flow_cache *fc, int cpu)
 {
 	struct flow_cache_percpu *fcp;
-	int i;
+	unsigned int i;
 
 	fcp = per_cpu_ptr(fc->percpu, cpu);
 	for (i = 0; i < flow_cache_hash_size(fc); i++)
@@ -402,12 +405,12 @@ void flow_cache_flush_deferred(struct net *net)
 static int flow_cache_cpu_prepare(struct flow_cache *fc, int cpu)
 {
 	struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu);
-	size_t sz = sizeof(struct hlist_head) * flow_cache_hash_size(fc);
+	unsigned int sz = sizeof(struct hlist_head) * flow_cache_hash_size(fc);
 
 	if (!fcp->hash_table) {
 		fcp->hash_table = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu));
 		if (!fcp->hash_table) {
-			pr_err("NET: failed to allocate flow cache sz %zu\n", sz);
+			pr_err("NET: failed to allocate flow cache sz %u\n", sz);
 			return -ENOMEM;
 		}
 		fcp->hash_rnd_recalc = 1;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index d98d4998213d..28d94bce4df8 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -113,6 +113,235 @@ __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
 }
 EXPORT_SYMBOL(__skb_flow_get_ports);
 
+enum flow_dissect_ret {
+	FLOW_DISSECT_RET_OUT_GOOD,
+	FLOW_DISSECT_RET_OUT_BAD,
+	FLOW_DISSECT_RET_OUT_PROTO_AGAIN,
+};
+
+static enum flow_dissect_ret
+__skb_flow_dissect_mpls(const struct sk_buff *skb,
+			struct flow_dissector *flow_dissector,
+			void *target_container, void *data, int nhoff, int hlen)
+{
+	struct flow_dissector_key_keyid *key_keyid;
+	struct mpls_label *hdr, _hdr[2];
+	u32 entry, label;
+
+	if (!dissector_uses_key(flow_dissector,
+				FLOW_DISSECTOR_KEY_MPLS_ENTROPY) &&
+	    !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS))
+		return FLOW_DISSECT_RET_OUT_GOOD;
+
+	hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data,
+				   hlen, &_hdr);
+	if (!hdr)
+		return FLOW_DISSECT_RET_OUT_BAD;
+
+	entry = ntohl(hdr[0].entry);
+	label = (entry & MPLS_LS_LABEL_MASK) >> MPLS_LS_LABEL_SHIFT;
+
+	if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS)) {
+		struct flow_dissector_key_mpls *key_mpls;
+
+		key_mpls = skb_flow_dissector_target(flow_dissector,
+						     FLOW_DISSECTOR_KEY_MPLS,
+						     target_container);
+		key_mpls->mpls_label = label;
+		key_mpls->mpls_ttl = (entry & MPLS_LS_TTL_MASK)
+					>> MPLS_LS_TTL_SHIFT;
+		key_mpls->mpls_tc = (entry & MPLS_LS_TC_MASK)
+					>> MPLS_LS_TC_SHIFT;
+		key_mpls->mpls_bos = (entry & MPLS_LS_S_MASK)
+					>> MPLS_LS_S_SHIFT;
+	}
+
+	if (label == MPLS_LABEL_ENTROPY) {
+		key_keyid = skb_flow_dissector_target(flow_dissector,
+						      FLOW_DISSECTOR_KEY_MPLS_ENTROPY,
+						      target_container);
+		key_keyid->keyid = hdr[1].entry & htonl(MPLS_LS_LABEL_MASK);
+	}
+	return FLOW_DISSECT_RET_OUT_GOOD;
+}
+
+static enum flow_dissect_ret
+__skb_flow_dissect_arp(const struct sk_buff *skb,
+		       struct flow_dissector *flow_dissector,
+		       void *target_container, void *data, int nhoff, int hlen)
+{
+	struct flow_dissector_key_arp *key_arp;
+	struct {
+		unsigned char ar_sha[ETH_ALEN];
+		unsigned char ar_sip[4];
+		unsigned char ar_tha[ETH_ALEN];
+		unsigned char ar_tip[4];
+	} *arp_eth, _arp_eth;
+	const struct arphdr *arp;
+	struct arphdr _arp;
+
+	if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ARP))
+		return FLOW_DISSECT_RET_OUT_GOOD;
+
+	arp = __skb_header_pointer(skb, nhoff, sizeof(_arp), data,
+				   hlen, &_arp);
+	if (!arp)
+		return FLOW_DISSECT_RET_OUT_BAD;
+
+	if (arp->ar_hrd != htons(ARPHRD_ETHER) ||
+	    arp->ar_pro != htons(ETH_P_IP) ||
+	    arp->ar_hln != ETH_ALEN ||
+	    arp->ar_pln != 4 ||
+	    (arp->ar_op != htons(ARPOP_REPLY) &&
+	     arp->ar_op != htons(ARPOP_REQUEST)))
+		return FLOW_DISSECT_RET_OUT_BAD;
+
+	arp_eth = __skb_header_pointer(skb, nhoff + sizeof(_arp),
+				       sizeof(_arp_eth), data,
+				       hlen, &_arp_eth);
+	if (!arp_eth)
+		return FLOW_DISSECT_RET_OUT_BAD;
+
+	key_arp = skb_flow_dissector_target(flow_dissector,
+					    FLOW_DISSECTOR_KEY_ARP,
+					    target_container);
+
+	memcpy(&key_arp->sip, arp_eth->ar_sip, sizeof(key_arp->sip));
+	memcpy(&key_arp->tip, arp_eth->ar_tip, sizeof(key_arp->tip));
+
+	/* Only store the lower byte of the opcode;
+	 * this covers ARPOP_REPLY and ARPOP_REQUEST.
+	 */
+	key_arp->op = ntohs(arp->ar_op) & 0xff;
+
+	ether_addr_copy(key_arp->sha, arp_eth->ar_sha);
+	ether_addr_copy(key_arp->tha, arp_eth->ar_tha);
+
+	return FLOW_DISSECT_RET_OUT_GOOD;
+}
+
+static enum flow_dissect_ret
+__skb_flow_dissect_gre(const struct sk_buff *skb,
+		       struct flow_dissector_key_control *key_control,
+		       struct flow_dissector *flow_dissector,
+		       void *target_container, void *data,
+		       __be16 *p_proto, int *p_nhoff, int *p_hlen,
+		       unsigned int flags)
+{
+	struct flow_dissector_key_keyid *key_keyid;
+	struct gre_base_hdr *hdr, _hdr;
+	int offset = 0;
+	u16 gre_ver;
+
+	hdr = __skb_header_pointer(skb, *p_nhoff, sizeof(_hdr),
+				   data, *p_hlen, &_hdr);
+	if (!hdr)
+		return FLOW_DISSECT_RET_OUT_BAD;
+
+	/* Only look inside GRE without routing */
+	if (hdr->flags & GRE_ROUTING)
+		return FLOW_DISSECT_RET_OUT_GOOD;
+
+	/* Only look inside GRE for version 0 and 1 */
+	gre_ver = ntohs(hdr->flags & GRE_VERSION);
+	if (gre_ver > 1)
+		return FLOW_DISSECT_RET_OUT_GOOD;
+
+	*p_proto = hdr->protocol;
+	if (gre_ver) {
+		/* Version1 must be PPTP, and check the flags */
+		if (!(*p_proto == GRE_PROTO_PPP && (hdr->flags & GRE_KEY)))
+			return FLOW_DISSECT_RET_OUT_GOOD;
+	}
+
+	offset += sizeof(struct gre_base_hdr);
+
+	if (hdr->flags & GRE_CSUM)
+		offset += sizeof(((struct gre_full_hdr *) 0)->csum) +
+			  sizeof(((struct gre_full_hdr *) 0)->reserved1);
+
+	if (hdr->flags & GRE_KEY) {
+		const __be32 *keyid;
+		__be32 _keyid;
+
+		keyid = __skb_header_pointer(skb, *p_nhoff + offset,
+					     sizeof(_keyid),
+					     data, *p_hlen, &_keyid);
+		if (!keyid)
+			return FLOW_DISSECT_RET_OUT_BAD;
+
+		if (dissector_uses_key(flow_dissector,
+				       FLOW_DISSECTOR_KEY_GRE_KEYID)) {
+			key_keyid = skb_flow_dissector_target(flow_dissector,
+							      FLOW_DISSECTOR_KEY_GRE_KEYID,
+							      target_container);
+			if (gre_ver == 0)
+				key_keyid->keyid = *keyid;
+			else
+				key_keyid->keyid = *keyid & GRE_PPTP_KEY_MASK;
+		}
+		offset += sizeof(((struct gre_full_hdr *) 0)->key);
+	}
+
+	if (hdr->flags & GRE_SEQ)
+		offset += sizeof(((struct pptp_gre_header *) 0)->seq);
+
+	if (gre_ver == 0) {
+		if (*p_proto == htons(ETH_P_TEB)) {
+			const struct ethhdr *eth;
+			struct ethhdr _eth;
+
+			eth = __skb_header_pointer(skb, *p_nhoff + offset,
+						   sizeof(_eth),
+						   data, *p_hlen, &_eth);
+			if (!eth)
+				return FLOW_DISSECT_RET_OUT_BAD;
+			*p_proto = eth->h_proto;
+			offset += sizeof(*eth);
+
+			/* Cap headers that we access via pointers at the
+			 * end of the Ethernet header as our maximum alignment
+			 * at that point is only 2 bytes.
+			 */
+			if (NET_IP_ALIGN)
+				*p_hlen = *p_nhoff + offset;
+		}
+	} else { /* version 1, must be PPTP */
+		u8 _ppp_hdr[PPP_HDRLEN];
+		u8 *ppp_hdr;
+
+		if (hdr->flags & GRE_ACK)
+			offset += sizeof(((struct pptp_gre_header *) 0)->ack);
+
+		ppp_hdr = __skb_header_pointer(skb, *p_nhoff + offset,
+					       sizeof(_ppp_hdr),
+					       data, *p_hlen, _ppp_hdr);
+		if (!ppp_hdr)
+			return FLOW_DISSECT_RET_OUT_BAD;
+
+		switch (PPP_PROTOCOL(ppp_hdr)) {
+		case PPP_IP:
+			*p_proto = htons(ETH_P_IP);
+			break;
+		case PPP_IPV6:
+			*p_proto = htons(ETH_P_IPV6);
+			break;
+		default:
+			/* Could probably catch some more like MPLS */
+			break;
+		}
+
+		offset += PPP_HDRLEN;
+	}
+
+	*p_nhoff += offset;
+	key_control->flags |= FLOW_DIS_ENCAPSULATION;
+	if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP)
+		return FLOW_DISSECT_RET_OUT_GOOD;
+
+	return FLOW_DISSECT_RET_OUT_PROTO_AGAIN;
+}
+
 /**
  * __skb_flow_dissect - extract the flow_keys struct and return it
  * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified
@@ -138,12 +367,10 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
 	struct flow_dissector_key_control *key_control;
 	struct flow_dissector_key_basic *key_basic;
 	struct flow_dissector_key_addrs *key_addrs;
-	struct flow_dissector_key_arp *key_arp;
 	struct flow_dissector_key_ports *key_ports;
 	struct flow_dissector_key_icmp *key_icmp;
 	struct flow_dissector_key_tags *key_tags;
 	struct flow_dissector_key_vlan *key_vlan;
-	struct flow_dissector_key_keyid *key_keyid;
 	bool skip_vlan = false;
 	u8 ip_proto = 0;
 	bool ret;
@@ -181,7 +408,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
 		memcpy(key_eth_addrs, &eth->h_dest, sizeof(*key_eth_addrs));
 	}
 
-again:
+proto_again:
 	switch (proto) {
 	case htons(ETH_P_IP): {
 		const struct iphdr *iph;
@@ -284,7 +511,7 @@ ipv6:
 			proto = vlan->h_vlan_encapsulated_proto;
 			nhoff += sizeof(*vlan);
 			if (skip_vlan)
-				goto again;
+				goto proto_again;
 		}
 
 		skip_vlan = true;
@@ -307,7 +534,7 @@ ipv6:
 			}
 		}
 
-		goto again;
+		goto proto_again;
 	}
 	case htons(ETH_P_PPP_SES): {
 		struct {
@@ -349,31 +576,17 @@ ipv6:
 	}
 
 	case htons(ETH_P_MPLS_UC):
-	case htons(ETH_P_MPLS_MC): {
-		struct mpls_label *hdr, _hdr[2];
+	case htons(ETH_P_MPLS_MC):
 mpls:
-		hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data,
-					   hlen, &_hdr);
-		if (!hdr)
-			goto out_bad;
-
-		if ((ntohl(hdr[0].entry) & MPLS_LS_LABEL_MASK) >>
-		     MPLS_LS_LABEL_SHIFT == MPLS_LABEL_ENTROPY) {
-			if (dissector_uses_key(flow_dissector,
-					       FLOW_DISSECTOR_KEY_MPLS_ENTROPY)) {
-				key_keyid = skb_flow_dissector_target(flow_dissector,
-								      FLOW_DISSECTOR_KEY_MPLS_ENTROPY,
-								      target_container);
-				key_keyid->keyid = hdr[1].entry &
-					htonl(MPLS_LS_LABEL_MASK);
-			}
-
+		switch (__skb_flow_dissect_mpls(skb, flow_dissector,
+						target_container, data,
+						nhoff, hlen)) {
+		case FLOW_DISSECT_RET_OUT_GOOD:
 			goto out_good;
+		case FLOW_DISSECT_RET_OUT_BAD:
+		default:
+			goto out_bad;
 		}
-
-		goto out_good;
-	}
-
 	case htons(ETH_P_FCOE):
 		if ((hlen - nhoff) < FCOE_HEADER_LEN)
 			goto out_bad;
@@ -382,177 +595,33 @@ mpls:
 		goto out_good;
 
 	case htons(ETH_P_ARP):
-	case htons(ETH_P_RARP): {
-		struct {
-			unsigned char ar_sha[ETH_ALEN];
-			unsigned char ar_sip[4];
-			unsigned char ar_tha[ETH_ALEN];
-			unsigned char ar_tip[4];
-		} *arp_eth, _arp_eth;
-		const struct arphdr *arp;
-		struct arphdr _arp;
-
-		arp = __skb_header_pointer(skb, nhoff, sizeof(_arp), data,
-					   hlen, &_arp);
-		if (!arp)
-			goto out_bad;
-
-		if (arp->ar_hrd != htons(ARPHRD_ETHER) ||
-		    arp->ar_pro != htons(ETH_P_IP) ||
-		    arp->ar_hln != ETH_ALEN ||
-		    arp->ar_pln != 4 ||
-		    (arp->ar_op != htons(ARPOP_REPLY) &&
-		     arp->ar_op != htons(ARPOP_REQUEST)))
-			goto out_bad;
-
-		arp_eth = __skb_header_pointer(skb, nhoff + sizeof(_arp),
-					       sizeof(_arp_eth), data,
-					       hlen,
-					       &_arp_eth);
-		if (!arp_eth)
+	case htons(ETH_P_RARP):
+		switch (__skb_flow_dissect_arp(skb, flow_dissector,
+					       target_container, data,
+					       nhoff, hlen)) {
+		case FLOW_DISSECT_RET_OUT_GOOD:
+			goto out_good;
+		case FLOW_DISSECT_RET_OUT_BAD:
+		default:
 			goto out_bad;
-
-		if (dissector_uses_key(flow_dissector,
-				       FLOW_DISSECTOR_KEY_ARP)) {
-
-			key_arp = skb_flow_dissector_target(flow_dissector,
-							    FLOW_DISSECTOR_KEY_ARP,
-							    target_container);
-
-			memcpy(&key_arp->sip, arp_eth->ar_sip,
-			       sizeof(key_arp->sip));
-			memcpy(&key_arp->tip, arp_eth->ar_tip,
-			       sizeof(key_arp->tip));
-
-			/* Only store the lower byte of the opcode;
-			 * this covers ARPOP_REPLY and ARPOP_REQUEST.
-			 */
-			key_arp->op = ntohs(arp->ar_op) & 0xff;
-
-			ether_addr_copy(key_arp->sha, arp_eth->ar_sha);
-			ether_addr_copy(key_arp->tha, arp_eth->ar_tha);
 		}
-
-		goto out_good;
-	}
-
 	default:
 		goto out_bad;
 	}
 
 ip_proto_again:
 	switch (ip_proto) {
-	case IPPROTO_GRE: {
-		struct gre_base_hdr *hdr, _hdr;
-		u16 gre_ver;
-		int offset = 0;
-
-		hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
-		if (!hdr)
+	case IPPROTO_GRE:
+		switch (__skb_flow_dissect_gre(skb, key_control, flow_dissector,
+					       target_container, data,
+					       &proto, &nhoff, &hlen, flags)) {
+		case FLOW_DISSECT_RET_OUT_GOOD:
+			goto out_good;
+		case FLOW_DISSECT_RET_OUT_BAD:
 			goto out_bad;
-
-		/* Only look inside GRE without routing */
-		if (hdr->flags & GRE_ROUTING)
-			break;
-
-		/* Only look inside GRE for version 0 and 1 */
-		gre_ver = ntohs(hdr->flags & GRE_VERSION);
-		if (gre_ver > 1)
-			break;
-
-		proto = hdr->protocol;
-		if (gre_ver) {
-			/* Version1 must be PPTP, and check the flags */
-			if (!(proto == GRE_PROTO_PPP && (hdr->flags & GRE_KEY)))
-				break;
-		}
-
-		offset += sizeof(struct gre_base_hdr);
-
-		if (hdr->flags & GRE_CSUM)
-			offset += sizeof(((struct gre_full_hdr *)0)->csum) +
-				  sizeof(((struct gre_full_hdr *)0)->reserved1);
-
-		if (hdr->flags & GRE_KEY) {
-			const __be32 *keyid;
-			__be32 _keyid;
-
-			keyid = __skb_header_pointer(skb, nhoff + offset, sizeof(_keyid),
-						     data, hlen, &_keyid);
-			if (!keyid)
-				goto out_bad;
-
-			if (dissector_uses_key(flow_dissector,
-					       FLOW_DISSECTOR_KEY_GRE_KEYID)) {
-				key_keyid = skb_flow_dissector_target(flow_dissector,
-								      FLOW_DISSECTOR_KEY_GRE_KEYID,
-								      target_container);
-				if (gre_ver == 0)
-					key_keyid->keyid = *keyid;
-				else
-					key_keyid->keyid = *keyid & GRE_PPTP_KEY_MASK;
-			}
-			offset += sizeof(((struct gre_full_hdr *)0)->key);
-		}
-
-		if (hdr->flags & GRE_SEQ)
-			offset += sizeof(((struct pptp_gre_header *)0)->seq);
-
-		if (gre_ver == 0) {
-			if (proto == htons(ETH_P_TEB)) {
-				const struct ethhdr *eth;
-				struct ethhdr _eth;
-
-				eth = __skb_header_pointer(skb, nhoff + offset,
-							   sizeof(_eth),
-							   data, hlen, &_eth);
-				if (!eth)
-					goto out_bad;
-				proto = eth->h_proto;
-				offset += sizeof(*eth);
-
-				/* Cap headers that we access via pointers at the
-				 * end of the Ethernet header as our maximum alignment
-				 * at that point is only 2 bytes.
-				 */
-				if (NET_IP_ALIGN)
-					hlen = (nhoff + offset);
-			}
-		} else { /* version 1, must be PPTP */
-			u8 _ppp_hdr[PPP_HDRLEN];
-			u8 *ppp_hdr;
-
-			if (hdr->flags & GRE_ACK)
-				offset += sizeof(((struct pptp_gre_header *)0)->ack);
-
-			ppp_hdr = __skb_header_pointer(skb, nhoff + offset,
-						     sizeof(_ppp_hdr),
-						     data, hlen, _ppp_hdr);
-			if (!ppp_hdr)
-				goto out_bad;
-
-			switch (PPP_PROTOCOL(ppp_hdr)) {
-			case PPP_IP:
-				proto = htons(ETH_P_IP);
-				break;
-			case PPP_IPV6:
-				proto = htons(ETH_P_IPV6);
-				break;
-			default:
-				/* Could probably catch some more like MPLS */
-				break;
-			}
-
-			offset += PPP_HDRLEN;
+		case FLOW_DISSECT_RET_OUT_PROTO_AGAIN:
+			goto proto_again;
 		}
-
-		nhoff += offset;
-		key_control->flags |= FLOW_DIS_ENCAPSULATION;
-		if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP)
-			goto out_good;
-
-		goto again;
-	}
 	case NEXTHDR_HOP:
 	case NEXTHDR_ROUTING:
 	case NEXTHDR_DEST: {
diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c
index c98bbfbd26b8..814e58a3ce8b 100644
--- a/net/core/gro_cells.c
+++ b/net/core/gro_cells.c
@@ -13,7 +13,7 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb)
 	struct net_device *dev = skb->dev;
 	struct gro_cell *cell;
 
-	if (!gcells->cells || skb_cloned(skb) || !(dev->features & NETIF_F_GRO))
+	if (!gcells->cells || skb_cloned(skb) || netif_elide_gro(dev))
 		return netif_rx(skb);
 
 	cell = this_cpu_ptr(gcells->cells);
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index 0cfe7b0216c3..b3bc0a31af9f 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -209,7 +209,8 @@ static int bpf_parse_prog(struct nlattr *attr, struct bpf_lwt_prog *prog,
 	int ret;
 	u32 fd;
 
-	ret = nla_parse_nested(tb, LWT_BPF_PROG_MAX, attr, bpf_prog_policy);
+	ret = nla_parse_nested(tb, LWT_BPF_PROG_MAX, attr, bpf_prog_policy,
+			       NULL);
 	if (ret < 0)
 		return ret;
 
@@ -249,7 +250,7 @@ static int bpf_build_state(struct nlattr *nla,
 	if (family != AF_INET && family != AF_INET6)
 		return -EAFNOSUPPORT;
 
-	ret = nla_parse_nested(tb, LWT_BPF_MAX, nla, bpf_nl_policy);
+	ret = nla_parse_nested(tb, LWT_BPF_MAX, nla, bpf_nl_policy, NULL);
 	if (ret < 0)
 		return ret;
 
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index 6df9f8fabf0c..cfae3d5fe11f 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -162,7 +162,6 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining)
 	struct rtnexthop *rtnh = (struct rtnexthop *)attr;
 	struct nlattr *nla_entype;
 	struct nlattr *attrs;
-	struct nlattr *nla;
 	u16 encap_type;
 	int attrlen;
 
@@ -170,7 +169,6 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining)
 		attrlen = rtnh_attrlen(rtnh);
 		if (attrlen > 0) {
 			attrs = rtnh_attrs(rtnh);
-			nla = nla_find(attrs, attrlen, RTA_ENCAP);
 			nla_entype = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);
 
 			if (nla_entype) {
@@ -205,7 +203,7 @@ int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate)
 {
 	const struct lwtunnel_encap_ops *ops;
 	struct nlattr *nest;
-	int ret = -EINVAL;
+	int ret;
 
 	if (!lwtstate)
 		return 0;
@@ -214,8 +212,11 @@ int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate)
 	    lwtstate->type > LWTUNNEL_ENCAP_MAX)
 		return 0;
 
-	ret = -EOPNOTSUPP;
 	nest = nla_nest_start(skb, RTA_ENCAP);
+	if (!nest)
+		return -EMSGSIZE;
+
+	ret = -EOPNOTSUPP;
 	rcu_read_lock();
 	ops = rcu_dereference(lwtun_encaps[lwtstate->type]);
 	if (likely(ops && ops->fill_encap))
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 4526cbd7e28a..58b0bcc125b5 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -52,8 +52,9 @@ do {						\
 #define PNEIGH_HASHMASK		0xF
 
 static void neigh_timer_handler(unsigned long arg);
-static void __neigh_notify(struct neighbour *n, int type, int flags);
-static void neigh_update_notify(struct neighbour *neigh);
+static void __neigh_notify(struct neighbour *n, int type, int flags,
+			   u32 pid);
+static void neigh_update_notify(struct neighbour *neigh, u32 nlmsg_pid);
 static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev);
 
 #ifdef CONFIG_PROC_FS
@@ -99,7 +100,7 @@ static void neigh_cleanup_and_release(struct neighbour *neigh)
 	if (neigh->parms->neigh_cleanup)
 		neigh->parms->neigh_cleanup(neigh);
 
-	__neigh_notify(neigh, RTM_DELNEIGH, 0);
+	__neigh_notify(neigh, RTM_DELNEIGH, 0, 0);
 	call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh);
 	neigh_release(neigh);
 }
@@ -949,7 +950,7 @@ out:
 	}
 
 	if (notify)
-		neigh_update_notify(neigh);
+		neigh_update_notify(neigh, 0);
 
 	neigh_release(neigh);
 }
@@ -1073,7 +1074,7 @@ static void neigh_update_hhs(struct neighbour *neigh)
  */
 
 int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
-		 u32 flags)
+		 u32 flags, u32 nlmsg_pid)
 {
 	u8 old;
 	int err;
@@ -1230,7 +1231,7 @@ out:
 	write_unlock_bh(&neigh->lock);
 
 	if (notify)
-		neigh_update_notify(neigh);
+		neigh_update_notify(neigh, nlmsg_pid);
 
 	return err;
 }
@@ -1261,7 +1262,7 @@ struct neighbour *neigh_event_ns(struct neigh_table *tbl,
 						 lladdr || !dev->addr_len);
 	if (neigh)
 		neigh_update(neigh, lladdr, NUD_STALE,
-			     NEIGH_UPDATE_F_OVERRIDE);
+			     NEIGH_UPDATE_F_OVERRIDE, 0);
 	return neigh;
 }
 EXPORT_SYMBOL(neigh_event_ns);
@@ -1589,7 +1590,8 @@ static struct neigh_table *neigh_find_table(int family)
 	return tbl;
 }
 
-static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh,
+			struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ndmsg *ndm;
@@ -1639,14 +1641,16 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	err = neigh_update(neigh, NULL, NUD_FAILED,
 			   NEIGH_UPDATE_F_OVERRIDE |
-			   NEIGH_UPDATE_F_ADMIN);
+			   NEIGH_UPDATE_F_ADMIN,
+			   NETLINK_CB(skb).portid);
 	neigh_release(neigh);
 
 out:
 	return err;
 }
 
-static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
+		     struct netlink_ext_ack *extack)
 {
 	int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE;
 	struct net *net = sock_net(skb->sk);
@@ -1659,7 +1663,7 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 	int err;
 
 	ASSERT_RTNL();
-	err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL);
+	err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL, extack);
 	if (err < 0)
 		goto out;
 
@@ -1730,7 +1734,8 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 		neigh_event_send(neigh, NULL);
 		err = 0;
 	} else
-		err = neigh_update(neigh, lladdr, ndm->ndm_state, flags);
+		err = neigh_update(neigh, lladdr, ndm->ndm_state, flags,
+				   NETLINK_CB(skb).portid);
 	neigh_release(neigh);
 
 out:
@@ -1933,7 +1938,8 @@ static const struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] = {
 	[NDTPA_LOCKTIME]		= { .type = NLA_U64 },
 };
 
-static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh,
+			struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct neigh_table *tbl;
@@ -1943,7 +1949,7 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
 	int err, tidx;
 
 	err = nlmsg_parse(nlh, sizeof(*ndtmsg), tb, NDTA_MAX,
-			  nl_neightbl_policy);
+			  nl_neightbl_policy, extack);
 	if (err < 0)
 		goto errout;
 
@@ -1981,7 +1987,7 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
 		int i, ifindex = 0;
 
 		err = nla_parse_nested(tbp, NDTPA_MAX, tb[NDTA_PARMS],
-				       nl_ntbl_parm_policy);
+				       nl_ntbl_parm_policy, extack);
 		if (err < 0)
 			goto errout_tbl_lock;
 
@@ -2230,10 +2236,10 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static void neigh_update_notify(struct neighbour *neigh)
+static void neigh_update_notify(struct neighbour *neigh, u32 nlmsg_pid)
 {
 	call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh);
-	__neigh_notify(neigh, RTM_NEWNEIGH, 0);
+	__neigh_notify(neigh, RTM_NEWNEIGH, 0, nlmsg_pid);
 }
 
 static bool neigh_master_filtered(struct net_device *dev, int master_idx)
@@ -2272,7 +2278,7 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
 	unsigned int flags = NLM_F_MULTI;
 	int err;
 
-	err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL);
+	err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL, NULL);
 	if (!err) {
 		if (tb[NDA_IFINDEX])
 			filter_idx = nla_get_u32(tb[NDA_IFINDEX]);
@@ -2831,7 +2837,8 @@ static inline size_t neigh_nlmsg_size(void)
 	       + nla_total_size(4); /* NDA_PROBES */
 }
 
-static void __neigh_notify(struct neighbour *n, int type, int flags)
+static void __neigh_notify(struct neighbour *n, int type, int flags,
+			   u32 pid)
 {
 	struct net *net = dev_net(n->dev);
 	struct sk_buff *skb;
@@ -2841,7 +2848,7 @@ static void __neigh_notify(struct neighbour *n, int type, int flags)
 	if (skb == NULL)
 		goto errout;
 
-	err = neigh_fill_info(skb, n, 0, 0, type, flags);
+	err = neigh_fill_info(skb, n, pid, 0, type, flags);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in neigh_nlmsg_size() */
 		WARN_ON(err == -EMSGSIZE);
@@ -2857,7 +2864,7 @@ errout:
 
 void neigh_app_ns(struct neighbour *n)
 {
-	__neigh_notify(n, RTM_GETNEIGH, NLM_F_REQUEST);
+	__neigh_notify(n, RTM_GETNEIGH, NLM_F_REQUEST, 0);
 }
 EXPORT_SYMBOL(neigh_app_ns);
 
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 652468ff65b7..1934efd4a9d4 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -35,7 +35,8 @@ LIST_HEAD(net_namespace_list);
 EXPORT_SYMBOL_GPL(net_namespace_list);
 
 struct net init_net = {
-	.dev_base_head = LIST_HEAD_INIT(init_net.dev_base_head),
+	.count		= ATOMIC_INIT(1),
+	.dev_base_head	= LIST_HEAD_INIT(init_net.dev_base_head),
 };
 EXPORT_SYMBOL(init_net);
 
@@ -571,7 +572,8 @@ static const struct nla_policy rtnl_net_policy[NETNSA_MAX + 1] = {
 	[NETNSA_FD]		= { .type = NLA_U32 },
 };
 
-static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh,
+			  struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tb[NETNSA_MAX + 1];
@@ -579,7 +581,7 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh)
 	int nsid, err;
 
 	err = nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX,
-			  rtnl_net_policy);
+			  rtnl_net_policy, extack);
 	if (err < 0)
 		return err;
 	if (!tb[NETNSA_NSID])
@@ -644,7 +646,8 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh,
+			  struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tb[NETNSA_MAX + 1];
@@ -653,7 +656,7 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh)
 	int err, id;
 
 	err = nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX,
-			  rtnl_net_policy);
+			  rtnl_net_policy, extack);
 	if (err < 0)
 		return err;
 	if (tb[NETNSA_PID])
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 0f9275ee5595..1c4810919a0a 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -11,6 +11,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/module.h>
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index c4e84c558240..6e67315ec368 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -896,15 +896,13 @@ static size_t rtnl_port_size(const struct net_device *dev,
 		return port_self_size;
 }
 
-static size_t rtnl_xdp_size(const struct net_device *dev)
+static size_t rtnl_xdp_size(void)
 {
 	size_t xdp_size = nla_total_size(0) +	/* nest IFLA_XDP */
-			  nla_total_size(1);	/* XDP_ATTACHED */
+			  nla_total_size(1) +	/* XDP_ATTACHED */
+			  nla_total_size(4);	/* XDP_FLAGS */
 
-	if (!dev->netdev_ops->ndo_xdp)
-		return 0;
-	else
-		return xdp_size;
+	return xdp_size;
 }
 
 static noinline size_t if_nlmsg_size(const struct net_device *dev,
@@ -943,7 +941,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_PORT_ID */
 	       + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_SWITCH_ID */
 	       + nla_total_size(IFNAMSIZ) /* IFLA_PHYS_PORT_NAME */
-	       + rtnl_xdp_size(dev) /* IFLA_XDP */
+	       + rtnl_xdp_size() /* IFLA_XDP */
 	       + nla_total_size(1); /* IFLA_PROTO_DOWN */
 
 }
@@ -1251,23 +1249,35 @@ static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev)
 
 static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev)
 {
-	struct netdev_xdp xdp_op = {};
 	struct nlattr *xdp;
+	u32 xdp_flags = 0;
+	u8 val = 0;
 	int err;
 
-	if (!dev->netdev_ops->ndo_xdp)
-		return 0;
 	xdp = nla_nest_start(skb, IFLA_XDP);
 	if (!xdp)
 		return -EMSGSIZE;
-	xdp_op.command = XDP_QUERY_PROG;
-	err = dev->netdev_ops->ndo_xdp(dev, &xdp_op);
-	if (err)
-		goto err_cancel;
-	err = nla_put_u8(skb, IFLA_XDP_ATTACHED, xdp_op.prog_attached);
+	if (rcu_access_pointer(dev->xdp_prog)) {
+		xdp_flags = XDP_FLAGS_SKB_MODE;
+		val = 1;
+	} else if (dev->netdev_ops->ndo_xdp) {
+		struct netdev_xdp xdp_op = {};
+
+		xdp_op.command = XDP_QUERY_PROG;
+		err = dev->netdev_ops->ndo_xdp(dev, &xdp_op);
+		if (err)
+			goto err_cancel;
+		val = xdp_op.prog_attached;
+	}
+	err = nla_put_u8(skb, IFLA_XDP_ATTACHED, val);
 	if (err)
 		goto err_cancel;
 
+	if (xdp_flags) {
+		err = nla_put_u32(skb, IFLA_XDP_FLAGS, xdp_flags);
+		if (err)
+			goto err_cancel;
+	}
 	nla_nest_end(skb, xdp);
 	return 0;
 
@@ -1515,7 +1525,8 @@ static const struct rtnl_link_ops *linkinfo_to_kind_ops(const struct nlattr *nla
 	const struct rtnl_link_ops *ops = NULL;
 	struct nlattr *linfo[IFLA_INFO_MAX + 1];
 
-	if (nla_parse_nested(linfo, IFLA_INFO_MAX, nla, ifla_info_policy) < 0)
+	if (nla_parse_nested(linfo, IFLA_INFO_MAX, nla,
+			     ifla_info_policy, NULL) < 0)
 		return NULL;
 
 	if (linfo[IFLA_INFO_KIND]) {
@@ -1592,8 +1603,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 	hdrlen = nlmsg_len(cb->nlh) < sizeof(struct ifinfomsg) ?
 		 sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);
 
-	if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) {
-
+	if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX,
+			ifla_policy, NULL) >= 0) {
 		if (tb[IFLA_EXT_MASK])
 			ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
 
@@ -1640,9 +1651,10 @@ out:
 	return skb->len;
 }
 
-int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len)
+int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len,
+			struct netlink_ext_ack *exterr)
 {
-	return nla_parse(tb, IFLA_MAX, head, len, ifla_policy);
+	return nla_parse(tb, IFLA_MAX, head, len, ifla_policy, exterr);
 }
 EXPORT_SYMBOL(rtnl_nla_parse_ifla);
 
@@ -1907,6 +1919,7 @@ static int do_set_master(struct net_device *dev, int ifindex)
 #define DO_SETLINK_NOTIFY	0x03
 static int do_setlink(const struct sk_buff *skb,
 		      struct net_device *dev, struct ifinfomsg *ifm,
+		      struct netlink_ext_ack *extack,
 		      struct nlattr **tb, char *ifname, int status)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
@@ -2078,7 +2091,7 @@ static int do_setlink(const struct sk_buff *skb,
 				goto errout;
 			}
 			err = nla_parse_nested(vfinfo, IFLA_VF_MAX, attr,
-					       ifla_vf_policy);
+					       ifla_vf_policy, NULL);
 			if (err < 0)
 				goto errout;
 			err = do_setvfinfo(dev, vfinfo);
@@ -2106,7 +2119,7 @@ static int do_setlink(const struct sk_buff *skb,
 				goto errout;
 			}
 			err = nla_parse_nested(port, IFLA_PORT_MAX, attr,
-					       ifla_port_policy);
+					       ifla_port_policy, NULL);
 			if (err < 0)
 				goto errout;
 			if (!port[IFLA_PORT_VF]) {
@@ -2126,7 +2139,8 @@ static int do_setlink(const struct sk_buff *skb,
 		struct nlattr *port[IFLA_PORT_MAX+1];
 
 		err = nla_parse_nested(port, IFLA_PORT_MAX,
-			tb[IFLA_PORT_SELF], ifla_port_policy);
+				       tb[IFLA_PORT_SELF], ifla_port_policy,
+				       NULL);
 		if (err < 0)
 			goto errout;
 
@@ -2170,7 +2184,7 @@ static int do_setlink(const struct sk_buff *skb,
 		u32 xdp_flags = 0;
 
 		err = nla_parse_nested(xdp, IFLA_XDP_MAX, tb[IFLA_XDP],
-				       ifla_xdp_policy);
+				       ifla_xdp_policy, NULL);
 		if (err < 0)
 			goto errout;
 
@@ -2188,7 +2202,7 @@ static int do_setlink(const struct sk_buff *skb,
 		}
 
 		if (xdp[IFLA_XDP_FD]) {
-			err = dev_change_xdp_fd(dev,
+			err = dev_change_xdp_fd(dev, extack,
 						nla_get_s32(xdp[IFLA_XDP_FD]),
 						xdp_flags);
 			if (err)
@@ -2210,7 +2224,8 @@ errout:
 	return err;
 }
 
-static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
+			struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ifinfomsg *ifm;
@@ -2219,7 +2234,8 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct nlattr *tb[IFLA_MAX+1];
 	char ifname[IFNAMSIZ];
 
-	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy);
+	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy,
+			  extack);
 	if (err < 0)
 		goto errout;
 
@@ -2246,7 +2262,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (err < 0)
 		goto errout;
 
-	err = do_setlink(skb, dev, ifm, tb, ifname, 0);
+	err = do_setlink(skb, dev, ifm, extack, tb, ifname, 0);
 errout:
 	return err;
 }
@@ -2303,7 +2319,8 @@ int rtnl_delete_link(struct net_device *dev)
 }
 EXPORT_SYMBOL_GPL(rtnl_delete_link);
 
-static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
+			struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct net_device *dev;
@@ -2312,7 +2329,7 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct nlattr *tb[IFLA_MAX+1];
 	int err;
 
-	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy);
+	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -2407,6 +2424,7 @@ EXPORT_SYMBOL(rtnl_create_link);
 static int rtnl_group_changelink(const struct sk_buff *skb,
 		struct net *net, int group,
 		struct ifinfomsg *ifm,
+		struct netlink_ext_ack *extack,
 		struct nlattr **tb)
 {
 	struct net_device *dev, *aux;
@@ -2414,7 +2432,7 @@ static int rtnl_group_changelink(const struct sk_buff *skb,
 
 	for_each_netdev_safe(net, dev, aux) {
 		if (dev->group == group) {
-			err = do_setlink(skb, dev, ifm, tb, NULL, 0);
+			err = do_setlink(skb, dev, ifm, extack, tb, NULL, 0);
 			if (err < 0)
 				return err;
 		}
@@ -2423,7 +2441,8 @@ static int rtnl_group_changelink(const struct sk_buff *skb,
 	return 0;
 }
 
-static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
+			struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	const struct rtnl_link_ops *ops;
@@ -2441,7 +2460,7 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh)
 #ifdef CONFIG_MODULES
 replay:
 #endif
-	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy);
+	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -2472,7 +2491,8 @@ replay:
 
 	if (tb[IFLA_LINKINFO]) {
 		err = nla_parse_nested(linkinfo, IFLA_INFO_MAX,
-				       tb[IFLA_LINKINFO], ifla_info_policy);
+				       tb[IFLA_LINKINFO], ifla_info_policy,
+				       NULL);
 		if (err < 0)
 			return err;
 	} else
@@ -2497,7 +2517,7 @@ replay:
 			if (ops->maxtype && linkinfo[IFLA_INFO_DATA]) {
 				err = nla_parse_nested(attr, ops->maxtype,
 						       linkinfo[IFLA_INFO_DATA],
-						       ops->policy);
+						       ops->policy, NULL);
 				if (err < 0)
 					return err;
 				data = attr;
@@ -2515,7 +2535,8 @@ replay:
 				err = nla_parse_nested(slave_attr,
 						       m_ops->slave_maxtype,
 						       linkinfo[IFLA_INFO_SLAVE_DATA],
-						       m_ops->slave_policy);
+						       m_ops->slave_policy,
+						       NULL);
 				if (err < 0)
 					return err;
 				slave_data = slave_attr;
@@ -2557,14 +2578,15 @@ replay:
 				status |= DO_SETLINK_NOTIFY;
 			}
 
-			return do_setlink(skb, dev, ifm, tb, ifname, status);
+			return do_setlink(skb, dev, ifm, extack, tb, ifname,
+					  status);
 		}
 
 		if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
 			if (ifm->ifi_index == 0 && tb[IFLA_GROUP])
 				return rtnl_group_changelink(skb, net,
 						nla_get_u32(tb[IFLA_GROUP]),
-						ifm, tb);
+						ifm, extack, tb);
 			return -ENODEV;
 		}
 
@@ -2673,7 +2695,8 @@ out_unregister:
 	}
 }
 
-static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh)
+static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
+			struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ifinfomsg *ifm;
@@ -2684,7 +2707,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh)
 	int err;
 	u32 ext_filter_mask = 0;
 
-	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy);
+	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -2734,7 +2757,7 @@ static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh)
 	hdrlen = nlmsg_len(nlh) < sizeof(struct ifinfomsg) ?
 		 sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);
 
-	if (nlmsg_parse(nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) {
+	if (nlmsg_parse(nlh, hdrlen, tb, IFLA_MAX, ifla_policy, NULL) >= 0) {
 		if (tb[IFLA_EXT_MASK])
 			ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
 	}
@@ -2955,7 +2978,8 @@ static int fdb_vid_parse(struct nlattr *vlan_attr, u16 *p_vid)
 	return 0;
 }
 
-static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
+			struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ndmsg *ndm;
@@ -2965,7 +2989,7 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 	u16 vid;
 	int err;
 
-	err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL);
+	err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL, extack);
 	if (err < 0)
 		return err;
 
@@ -3055,7 +3079,8 @@ int ndo_dflt_fdb_del(struct ndmsg *ndm,
 }
 EXPORT_SYMBOL(ndo_dflt_fdb_del);
 
-static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
+			struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ndmsg *ndm;
@@ -3068,7 +3093,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
-	err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL);
+	err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL, extack);
 	if (err < 0)
 		return err;
 
@@ -3203,8 +3228,8 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	int err = 0;
 	int fidx = 0;
 
-	if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX,
-			ifla_policy) == 0) {
+	if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb,
+			IFLA_MAX, ifla_policy, NULL) == 0) {
 		if (tb[IFLA_MASTER])
 			br_idx = nla_get_u32(tb[IFLA_MASTER]);
 	}
@@ -3498,7 +3523,8 @@ errout:
 	return err;
 }
 
-static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
+			       struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ifinfomsg *ifm;
@@ -3572,7 +3598,8 @@ out:
 	return err;
 }
 
-static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
+			       struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ifinfomsg *ifm;
@@ -3940,7 +3967,8 @@ static size_t if_nlmsg_stats_size(const struct net_device *dev,
 	return size;
 }
 
-static int rtnl_stats_get(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int rtnl_stats_get(struct sk_buff *skb, struct nlmsghdr *nlh,
+			  struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct net_device *dev = NULL;
@@ -4046,7 +4074,8 @@ out:
 
 /* Process one rtnetlink message. */
 
-static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	rtnl_doit_func doit;
@@ -4101,7 +4130,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (doit == NULL)
 		return -EOPNOTSUPP;
 
-	return doit(skb, nlh);
+	return doit(skb, nlh, extack);
 }
 
 static void rtnetlink_rcv(struct sk_buff *skb)
@@ -4116,22 +4145,16 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 
 	switch (event) {
-	case NETDEV_UP:
-	case NETDEV_DOWN:
-	case NETDEV_PRE_UP:
-	case NETDEV_POST_INIT:
-	case NETDEV_REGISTER:
-	case NETDEV_CHANGE:
-	case NETDEV_PRE_TYPE_CHANGE:
-	case NETDEV_GOING_DOWN:
-	case NETDEV_UNREGISTER:
-	case NETDEV_UNREGISTER_FINAL:
-	case NETDEV_RELEASE:
-	case NETDEV_JOIN:
-	case NETDEV_BONDING_INFO:
+	case NETDEV_REBOOT:
+	case NETDEV_CHANGENAME:
+	case NETDEV_FEAT_CHANGE:
+	case NETDEV_BONDING_FAILOVER:
+	case NETDEV_NOTIFY_PEERS:
+	case NETDEV_RESEND_IGMP:
+	case NETDEV_CHANGEINFODATA:
+		rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL);
 		break;
 	default:
-		rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL);
 		break;
 	}
 	return NOTIFY_DONE;
@@ -4185,6 +4208,7 @@ void __init rtnetlink_init(void)
 
 	rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all, NULL);
 	rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all, NULL);
+	rtnl_register(PF_UNSPEC, RTM_GETNETCONF, NULL, rtnl_dump_all, NULL);
 
 	rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, rtnl_fdb_add, NULL, NULL);
 	rtnl_register(PF_BRIDGE, RTM_DELNEIGH, rtnl_fdb_del, NULL, NULL);
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index d28da7d363f1..6bd2f8fb0476 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -64,8 +64,8 @@ static u32 secure_tcpv6_ts_off(const __be32 *saddr, const __be32 *daddr)
 		       &ts_secret);
 }
 
-u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
-				 __be16 sport, __be16 dport, u32 *tsoff)
+u32 secure_tcpv6_seq_and_tsoff(const __be32 *saddr, const __be32 *daddr,
+			       __be16 sport, __be16 dport, u32 *tsoff)
 {
 	const struct {
 		struct in6_addr saddr;
@@ -85,7 +85,7 @@ u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
 	*tsoff = secure_tcpv6_ts_off(saddr, daddr);
 	return seq_scale(hash);
 }
-EXPORT_SYMBOL(secure_tcpv6_sequence_number);
+EXPORT_SYMBOL(secure_tcpv6_seq_and_tsoff);
 
 u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
 			       __be16 dport)
@@ -116,14 +116,13 @@ static u32 secure_tcp_ts_off(__be32 saddr, __be32 daddr)
 			    &ts_secret);
 }
 
-/* secure_tcp_sequence_number(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d),
+/* secure_tcp_seq_and_tsoff(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d),
  * but fortunately, `sport' cannot be 0 in any circumstances. If this changes,
  * it would be easy enough to have the former function use siphash_4u32, passing
  * the arguments as separate u32.
  */
-
-u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
-			       __be16 sport, __be16 dport, u32 *tsoff)
+u32 secure_tcp_seq_and_tsoff(__be32 saddr, __be32 daddr,
+			     __be16 sport, __be16 dport, u32 *tsoff)
 {
 	u64 hash;
 	net_secret_init();
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b782b4593f8c..346d3e85dfbc 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3101,7 +3101,7 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 			skb_walk_frags(head_skb, iter) {
 				if (frag_len != iter->len && iter->next)
 					goto normal;
-				if (skb_headlen(iter))
+				if (skb_headlen(iter) && !iter->head_frag)
 					goto normal;
 
 				len -= iter->len;
diff --git a/net/core/sock.c b/net/core/sock.c
index b416a537bd0a..b5baeb9cb0fb 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -247,12 +247,66 @@ static const char *const af_family_kern_slock_key_strings[AF_MAX+1] = {
 static const char *const af_family_kern_clock_key_strings[AF_MAX+1] = {
 	_sock_locks("k-clock-")
 };
+static const char *const af_family_rlock_key_strings[AF_MAX+1] = {
+  "rlock-AF_UNSPEC", "rlock-AF_UNIX"     , "rlock-AF_INET"     ,
+  "rlock-AF_AX25"  , "rlock-AF_IPX"      , "rlock-AF_APPLETALK",
+  "rlock-AF_NETROM", "rlock-AF_BRIDGE"   , "rlock-AF_ATMPVC"   ,
+  "rlock-AF_X25"   , "rlock-AF_INET6"    , "rlock-AF_ROSE"     ,
+  "rlock-AF_DECnet", "rlock-AF_NETBEUI"  , "rlock-AF_SECURITY" ,
+  "rlock-AF_KEY"   , "rlock-AF_NETLINK"  , "rlock-AF_PACKET"   ,
+  "rlock-AF_ASH"   , "rlock-AF_ECONET"   , "rlock-AF_ATMSVC"   ,
+  "rlock-AF_RDS"   , "rlock-AF_SNA"      , "rlock-AF_IRDA"     ,
+  "rlock-AF_PPPOX" , "rlock-AF_WANPIPE"  , "rlock-AF_LLC"      ,
+  "rlock-27"       , "rlock-28"          , "rlock-AF_CAN"      ,
+  "rlock-AF_TIPC"  , "rlock-AF_BLUETOOTH", "rlock-AF_IUCV"     ,
+  "rlock-AF_RXRPC" , "rlock-AF_ISDN"     , "rlock-AF_PHONET"   ,
+  "rlock-AF_IEEE802154", "rlock-AF_CAIF" , "rlock-AF_ALG"      ,
+  "rlock-AF_NFC"   , "rlock-AF_VSOCK"    , "rlock-AF_KCM"      ,
+  "rlock-AF_QIPCRTR", "rlock-AF_SMC"     , "rlock-AF_MAX"
+};
+static const char *const af_family_wlock_key_strings[AF_MAX+1] = {
+  "wlock-AF_UNSPEC", "wlock-AF_UNIX"     , "wlock-AF_INET"     ,
+  "wlock-AF_AX25"  , "wlock-AF_IPX"      , "wlock-AF_APPLETALK",
+  "wlock-AF_NETROM", "wlock-AF_BRIDGE"   , "wlock-AF_ATMPVC"   ,
+  "wlock-AF_X25"   , "wlock-AF_INET6"    , "wlock-AF_ROSE"     ,
+  "wlock-AF_DECnet", "wlock-AF_NETBEUI"  , "wlock-AF_SECURITY" ,
+  "wlock-AF_KEY"   , "wlock-AF_NETLINK"  , "wlock-AF_PACKET"   ,
+  "wlock-AF_ASH"   , "wlock-AF_ECONET"   , "wlock-AF_ATMSVC"   ,
+  "wlock-AF_RDS"   , "wlock-AF_SNA"      , "wlock-AF_IRDA"     ,
+  "wlock-AF_PPPOX" , "wlock-AF_WANPIPE"  , "wlock-AF_LLC"      ,
+  "wlock-27"       , "wlock-28"          , "wlock-AF_CAN"      ,
+  "wlock-AF_TIPC"  , "wlock-AF_BLUETOOTH", "wlock-AF_IUCV"     ,
+  "wlock-AF_RXRPC" , "wlock-AF_ISDN"     , "wlock-AF_PHONET"   ,
+  "wlock-AF_IEEE802154", "wlock-AF_CAIF" , "wlock-AF_ALG"      ,
+  "wlock-AF_NFC"   , "wlock-AF_VSOCK"    , "wlock-AF_KCM"      ,
+  "wlock-AF_QIPCRTR", "wlock-AF_SMC"     , "wlock-AF_MAX"
+};
+static const char *const af_family_elock_key_strings[AF_MAX+1] = {
+  "elock-AF_UNSPEC", "elock-AF_UNIX"     , "elock-AF_INET"     ,
+  "elock-AF_AX25"  , "elock-AF_IPX"      , "elock-AF_APPLETALK",
+  "elock-AF_NETROM", "elock-AF_BRIDGE"   , "elock-AF_ATMPVC"   ,
+  "elock-AF_X25"   , "elock-AF_INET6"    , "elock-AF_ROSE"     ,
+  "elock-AF_DECnet", "elock-AF_NETBEUI"  , "elock-AF_SECURITY" ,
+  "elock-AF_KEY"   , "elock-AF_NETLINK"  , "elock-AF_PACKET"   ,
+  "elock-AF_ASH"   , "elock-AF_ECONET"   , "elock-AF_ATMSVC"   ,
+  "elock-AF_RDS"   , "elock-AF_SNA"      , "elock-AF_IRDA"     ,
+  "elock-AF_PPPOX" , "elock-AF_WANPIPE"  , "elock-AF_LLC"      ,
+  "elock-27"       , "elock-28"          , "elock-AF_CAN"      ,
+  "elock-AF_TIPC"  , "elock-AF_BLUETOOTH", "elock-AF_IUCV"     ,
+  "elock-AF_RXRPC" , "elock-AF_ISDN"     , "elock-AF_PHONET"   ,
+  "elock-AF_IEEE802154", "elock-AF_CAIF" , "elock-AF_ALG"      ,
+  "elock-AF_NFC"   , "elock-AF_VSOCK"    , "elock-AF_KCM"      ,
+  "elock-AF_QIPCRTR", "elock-AF_SMC"     , "elock-AF_MAX"
+};
 
 /*
- * sk_callback_lock locking rules are per-address-family,
+ * sk_callback_lock and sk queues locking rules are per-address-family,
  * so split the lock classes by using a per-AF key:
  */
 static struct lock_class_key af_callback_keys[AF_MAX];
+static struct lock_class_key af_rlock_keys[AF_MAX];
+static struct lock_class_key af_wlock_keys[AF_MAX];
+static struct lock_class_key af_elock_keys[AF_MAX];
 static struct lock_class_key af_kern_callback_keys[AF_MAX];
 
 /* Take into consideration the size of the struct sk_buff overhead in the
@@ -1029,6 +1083,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 
 	union {
 		int val;
+		u64 val64;
 		struct linger ling;
 		struct timeval tm;
 	} v;
@@ -1259,6 +1314,40 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		v.val = sk->sk_incoming_cpu;
 		break;
 
+	case SO_MEMINFO:
+	{
+		u32 meminfo[SK_MEMINFO_VARS];
+
+		if (get_user(len, optlen))
+			return -EFAULT;
+
+		sk_get_meminfo(sk, meminfo);
+
+		len = min_t(unsigned int, len, sizeof(meminfo));
+		if (copy_to_user(optval, &meminfo, len))
+			return -EFAULT;
+
+		goto lenout;
+	}
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	case SO_INCOMING_NAPI_ID:
+		v.val = READ_ONCE(sk->sk_napi_id);
+
+		/* aggregate non-NAPI IDs down to 0 */
+		if (v.val < MIN_NAPI_ID)
+			v.val = 0;
+
+		break;
+#endif
+
+	case SO_COOKIE:
+		lv = sizeof(u64);
+		if (len < lv)
+			return -EINVAL;
+		v.val64 = sock_gen_cookie(sk);
+		break;
+
 	default:
 		/* We implement the SO_SNDLOWAT etc to not be settable
 		 * (1003.1g 7).
@@ -1483,6 +1572,27 @@ void sk_free(struct sock *sk)
 }
 EXPORT_SYMBOL(sk_free);
 
+static void sk_init_common(struct sock *sk)
+{
+	skb_queue_head_init(&sk->sk_receive_queue);
+	skb_queue_head_init(&sk->sk_write_queue);
+	skb_queue_head_init(&sk->sk_error_queue);
+
+	rwlock_init(&sk->sk_callback_lock);
+	lockdep_set_class_and_name(&sk->sk_receive_queue.lock,
+			af_rlock_keys + sk->sk_family,
+			af_family_rlock_key_strings[sk->sk_family]);
+	lockdep_set_class_and_name(&sk->sk_write_queue.lock,
+			af_wlock_keys + sk->sk_family,
+			af_family_wlock_key_strings[sk->sk_family]);
+	lockdep_set_class_and_name(&sk->sk_error_queue.lock,
+			af_elock_keys + sk->sk_family,
+			af_family_elock_key_strings[sk->sk_family]);
+	lockdep_set_class_and_name(&sk->sk_callback_lock,
+			af_callback_keys + sk->sk_family,
+			af_family_clock_key_strings[sk->sk_family]);
+}
+
 /**
  *	sk_clone_lock - clone a socket, and lock its clone
  *	@sk: the socket to clone
@@ -1516,13 +1626,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		 */
 		atomic_set(&newsk->sk_wmem_alloc, 1);
 		atomic_set(&newsk->sk_omem_alloc, 0);
-		skb_queue_head_init(&newsk->sk_receive_queue);
-		skb_queue_head_init(&newsk->sk_write_queue);
-
-		rwlock_init(&newsk->sk_callback_lock);
-		lockdep_set_class_and_name(&newsk->sk_callback_lock,
-				af_callback_keys + newsk->sk_family,
-				af_family_clock_key_strings[newsk->sk_family]);
+		sk_init_common(newsk);
 
 		newsk->sk_dst_cache	= NULL;
 		newsk->sk_dst_pending_confirm = 0;
@@ -1533,7 +1637,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		newsk->sk_userlocks	= sk->sk_userlocks & ~SOCK_BINDPORT_LOCK;
 
 		sock_reset_flag(newsk, SOCK_DONE);
-		skb_queue_head_init(&newsk->sk_error_queue);
 
 		filter = rcu_dereference_protected(newsk->sk_filter, 1);
 		if (filter != NULL)
@@ -2466,10 +2569,7 @@ EXPORT_SYMBOL(sk_stop_timer);
 
 void sock_init_data(struct socket *sock, struct sock *sk)
 {
-	skb_queue_head_init(&sk->sk_receive_queue);
-	skb_queue_head_init(&sk->sk_write_queue);
-	skb_queue_head_init(&sk->sk_error_queue);
-
+	sk_init_common(sk);
 	sk->sk_send_head	=	NULL;
 
 	init_timer(&sk->sk_timer);
@@ -2521,7 +2621,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 	sk->sk_rcvtimeo		=	MAX_SCHEDULE_TIMEOUT;
 	sk->sk_sndtimeo		=	MAX_SCHEDULE_TIMEOUT;
 
-	sk->sk_stamp = ktime_set(-1L, 0);
+	sk->sk_stamp = SK_DEFAULT_STAMP;
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	sk->sk_napi_id		=	0;
@@ -2802,6 +2902,21 @@ void sk_common_release(struct sock *sk)
 }
 EXPORT_SYMBOL(sk_common_release);
 
+void sk_get_meminfo(const struct sock *sk, u32 *mem)
+{
+	memset(mem, 0, sizeof(*mem) * SK_MEMINFO_VARS);
+
+	mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk);
+	mem[SK_MEMINFO_RCVBUF] = sk->sk_rcvbuf;
+	mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk);
+	mem[SK_MEMINFO_SNDBUF] = sk->sk_sndbuf;
+	mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc;
+	mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued;
+	mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
+	mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len;
+	mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops);
+}
+
 #ifdef CONFIG_PROC_FS
 #define PROTO_INUSE_NR	64	/* should be enough for the first time */
 struct prot_inuse {
@@ -3142,3 +3257,14 @@ static int __init proto_init(void)
 subsys_initcall(proto_init);
 
 #endif /* PROC_FS */
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+bool sk_busy_loop_end(void *p, unsigned long start_time)
+{
+	struct sock *sk = p;
+
+	return !skb_queue_empty(&sk->sk_receive_queue) ||
+	       sk_busy_loop_timeout(sk, start_time);
+}
+EXPORT_SYMBOL(sk_busy_loop_end);
+#endif /* CONFIG_NET_RX_BUSY_POLL */
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index 6b10573cc9fa..217f4e3b82f6 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -19,7 +19,7 @@ static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh);
 static DEFINE_MUTEX(sock_diag_table_mutex);
 static struct workqueue_struct *broadcast_wq;
 
-static u64 sock_gen_cookie(struct sock *sk)
+u64 sock_gen_cookie(struct sock *sk)
 {
 	while (1) {
 		u64 res = atomic64_read(&sk->sk_cookie);
@@ -59,15 +59,7 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype)
 {
 	u32 mem[SK_MEMINFO_VARS];
 
-	mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk);
-	mem[SK_MEMINFO_RCVBUF] = sk->sk_rcvbuf;
-	mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk);
-	mem[SK_MEMINFO_SNDBUF] = sk->sk_sndbuf;
-	mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc;
-	mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued;
-	mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
-	mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len;
-	mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops);
+	sk_get_meminfo(sk, mem);
 
 	return nla_put(skb, attrtype, sizeof(mem), &mem);
 }
@@ -246,7 +238,8 @@ static int __sock_diag_cmd(struct sk_buff *skb, struct nlmsghdr *nlh)
 	return err;
 }
 
-static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack)
 {
 	int ret;
 
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index 9a1a352fd1eb..eed1ebf7f29d 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -13,9 +13,9 @@
 
 static DEFINE_SPINLOCK(reuseport_lock);
 
-static struct sock_reuseport *__reuseport_alloc(u16 max_socks)
+static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks)
 {
-	size_t size = sizeof(struct sock_reuseport) +
+	unsigned int size = sizeof(struct sock_reuseport) +
 		      sizeof(struct sock *) * max_socks;
 	struct sock_reuseport *reuse = kzalloc(size, GFP_ATOMIC);
 
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 7f9cc400eca0..ea23254b2457 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -452,6 +452,14 @@ static struct ctl_table net_core_table[] = {
 		.extra1		= &one,
 		.extra2		= &max_skb_frags,
 	},
+	{
+		.procname	= "netdev_budget_usecs",
+		.data		= &netdev_budget_usecs,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+	},
 	{ }
 };
 
diff --git a/net/core/utils.c b/net/core/utils.c
index 32c467cf52d6..93066bd0305a 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -53,7 +53,7 @@ EXPORT_SYMBOL(net_ratelimit);
 
 __be32 in_aton(const char *str)
 {
-	unsigned long l;
+	unsigned int l;
 	unsigned int val;
 	int i;