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

Pull networking updates from David Miller:
 "Another merge window, another pull full of stuff:

   1) Support alternative names for network devices, from Jiri Pirko.

   2) Introduce per-netns netdev notifiers, also from Jiri Pirko.

   3) Support MSG_PEEK in vsock/virtio, from Matias Ezequiel Vara
      Larsen.

   4) Allow compiling out the TLS TOE code, from Jakub Kicinski.

   5) Add several new tracepoints to the kTLS code, also from Jakub.

   6) Support set channels ethtool callback in ena driver, from Sameeh
      Jubran.

   7) New SCTP events SCTP_ADDR_ADDED, SCTP_ADDR_REMOVED,
      SCTP_ADDR_MADE_PRIM, and SCTP_SEND_FAILED_EVENT. From Xin Long.

   8) Add XDP support to mvneta driver, from Lorenzo Bianconi.

   9) Lots of netfilter hw offload fixes, cleanups and enhancements,
      from Pablo Neira Ayuso.

  10) PTP support for aquantia chips, from Egor Pomozov.

  11) Add UDP segmentation offload support to igb, ixgbe, and i40e. From
      Josh Hunt.

  12) Add smart nagle to tipc, from Jon Maloy.

  13) Support L2 field rewrite by TC offloads in bnxt_en, from Venkat
      Duvvuru.

  14) Add a flow mask cache to OVS, from Tonghao Zhang.

  15) Add XDP support to ice driver, from Maciej Fijalkowski.

  16) Add AF_XDP support to ice driver, from Krzysztof Kazimierczak.

  17) Support UDP GSO offload in atlantic driver, from Igor Russkikh.

  18) Support it in stmmac driver too, from Jose Abreu.

  19) Support TIPC encryption and auth, from Tuong Lien.

  20) Introduce BPF trampolines, from Alexei Starovoitov.

  21) Make page_pool API more numa friendly, from Saeed Mahameed.

  22) Introduce route hints to ipv4 and ipv6, from Paolo Abeni.

  23) Add UDP segmentation offload to cxgb4, Rahul Lakkireddy"

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1857 commits)
  libbpf: Fix usage of u32 in userspace code
  mm: Implement no-MMU variant of vmalloc_user_node_flags
  slip: Fix use-after-free Read in slip_open
  net: dsa: sja1105: fix sja1105_parse_rgmii_delays()
  macvlan: schedule bc_work even if error
  enetc: add support Credit Based Shaper(CBS) for hardware offload
  net: phy: add helpers phy_(un)lock_mdio_bus
  mdio_bus: don't use managed reset-controller
  ax88179_178a: add ethtool_op_get_ts_info()
  mlxsw: spectrum_router: Fix use of uninitialized adjacency index
  mlxsw: spectrum_router: After underlay moves, demote conflicting tunnels
  bpf: Simplify __bpf_arch_text_poke poke type handling
  bpf: Introduce BPF_TRACE_x helper for the tracing tests
  bpf: Add bpf_jit_blinding_enabled for !CONFIG_BPF_JIT
  bpf, testing: Add various tail call test cases
  bpf, x86: Emit patchable direct jump as tail call
  bpf: Constant map key tracking for prog array pokes
  bpf: Add poke dependency tracking for prog array maps
  bpf: Add initial poke descriptor table for jit images
  bpf: Move owner type, jited info into array auxiliary data
  ...

26 files changed, 698 insertions, 137 deletions

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 69d4676a402f..7fc1e2c1b656 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -188,6 +188,8 @@ static size_t tcf_action_shared_attrs_size(const struct tc_action *act)
 		+ nla_total_size(0) /* TCA_ACT_STATS nested */
 		/* TCA_STATS_BASIC */
 		+ nla_total_size_64bit(sizeof(struct gnet_stats_basic))
+		/* TCA_STATS_PKT64 */
+		+ nla_total_size_64bit(sizeof(u64))
 		/* TCA_STATS_QUEUE */
 		+ nla_total_size_64bit(sizeof(struct gnet_stats_queue))
 		+ nla_total_size(0) /* TCA_OPTIONS nested */
@@ -399,7 +401,7 @@ static int tcf_idr_delete_index(struct tcf_idrinfo *idrinfo, u32 index)
 
 int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
 		   struct tc_action **a, const struct tc_action_ops *ops,
-		   int bind, bool cpustats)
+		   int bind, bool cpustats, u32 flags)
 {
 	struct tc_action *p = kzalloc(ops->size, GFP_KERNEL);
 	struct tcf_idrinfo *idrinfo = tn->idrinfo;
@@ -427,6 +429,7 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
 	p->tcfa_tm.install = jiffies;
 	p->tcfa_tm.lastuse = jiffies;
 	p->tcfa_tm.firstuse = 0;
+	p->tcfa_flags = flags;
 	if (est) {
 		err = gen_new_estimator(&p->tcfa_bstats, p->cpu_bstats,
 					&p->tcfa_rate_est,
@@ -451,6 +454,17 @@ err1:
 }
 EXPORT_SYMBOL(tcf_idr_create);
 
+int tcf_idr_create_from_flags(struct tc_action_net *tn, u32 index,
+			      struct nlattr *est, struct tc_action **a,
+			      const struct tc_action_ops *ops, int bind,
+			      u32 flags)
+{
+	/* Set cpustats according to actions flags. */
+	return tcf_idr_create(tn, index, est, a, ops, bind,
+			      !(flags & TCA_ACT_FLAGS_NO_PERCPU_STATS), flags);
+}
+EXPORT_SYMBOL(tcf_idr_create_from_flags);
+
 void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a)
 {
 	struct tcf_idrinfo *idrinfo = tn->idrinfo;
@@ -773,6 +787,14 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
 	}
 	rcu_read_unlock();
 
+	if (a->tcfa_flags) {
+		struct nla_bitfield32 flags = { a->tcfa_flags,
+						a->tcfa_flags, };
+
+		if (nla_put(skb, TCA_ACT_FLAGS, sizeof(flags), &flags))
+			goto nla_put_failure;
+	}
+
 	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (nest == NULL)
 		goto nla_put_failure;
@@ -831,12 +853,15 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb)
 	return c;
 }
 
+static const u32 tca_act_flags_allowed = TCA_ACT_FLAGS_NO_PERCPU_STATS;
 static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = {
 	[TCA_ACT_KIND]		= { .type = NLA_STRING },
 	[TCA_ACT_INDEX]		= { .type = NLA_U32 },
 	[TCA_ACT_COOKIE]	= { .type = NLA_BINARY,
 				    .len = TC_COOKIE_MAX_SIZE },
 	[TCA_ACT_OPTIONS]	= { .type = NLA_NESTED },
+	[TCA_ACT_FLAGS]		= { .type = NLA_BITFIELD32,
+				    .validation_data = &tca_act_flags_allowed },
 };
 
 struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
@@ -845,6 +870,7 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 				    bool rtnl_held,
 				    struct netlink_ext_ack *extack)
 {
+	struct nla_bitfield32 flags = { 0, 0 };
 	struct tc_action *a;
 	struct tc_action_ops *a_o;
 	struct tc_cookie *cookie = NULL;
@@ -876,6 +902,8 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 				goto err_out;
 			}
 		}
+		if (tb[TCA_ACT_FLAGS])
+			flags = nla_get_bitfield32(tb[TCA_ACT_FLAGS]);
 	} else {
 		if (strlcpy(act_name, name, IFNAMSIZ) >= IFNAMSIZ) {
 			NL_SET_ERR_MSG(extack, "TC action name too long");
@@ -914,10 +942,10 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 	/* backward compatibility for policer */
 	if (name == NULL)
 		err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, &a, ovr, bind,
-				rtnl_held, tp, extack);
+				rtnl_held, tp, flags.value, extack);
 	else
 		err = a_o->init(net, nla, est, &a, ovr, bind, rtnl_held,
-				tp, extack);
+				tp, flags.value, extack);
 	if (err < 0)
 		goto err_mod;
 
@@ -975,7 +1003,6 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 			err = PTR_ERR(act);
 			goto err;
 		}
-		act->order = i;
 		sz += tcf_action_fill_size(act);
 		/* Start from index 0 */
 		actions[i - 1] = act;
@@ -989,6 +1016,29 @@ err:
 	return err;
 }
 
+void tcf_action_update_stats(struct tc_action *a, u64 bytes, u32 packets,
+			     bool drop, bool hw)
+{
+	if (a->cpu_bstats) {
+		_bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets);
+
+		if (drop)
+			this_cpu_ptr(a->cpu_qstats)->drops += packets;
+
+		if (hw)
+			_bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw),
+					   bytes, packets);
+		return;
+	}
+
+	_bstats_update(&a->tcfa_bstats, bytes, packets);
+	if (drop)
+		a->tcfa_qstats.drops += packets;
+	if (hw)
+		_bstats_update(&a->tcfa_bstats_hw, bytes, packets);
+}
+EXPORT_SYMBOL(tcf_action_update_stats);
+
 int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *p,
 			  int compat_mode)
 {
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 04b7bd4ec751..46f47e58b3be 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -275,7 +275,8 @@ static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog,
 static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 			struct nlattr *est, struct tc_action **act,
 			int replace, int bind, bool rtnl_held,
-			struct tcf_proto *tp, struct netlink_ext_ack *extack)
+			struct tcf_proto *tp, u32 flags,
+			struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, bpf_net_id);
 	struct nlattr *tb[TCA_ACT_BPF_MAX + 1];
@@ -303,7 +304,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 	ret = tcf_idr_check_alloc(tn, &index, act, bind);
 	if (!ret) {
 		ret = tcf_idr_create(tn, index, est, act,
-				     &act_bpf_ops, bind, true);
+				     &act_bpf_ops, bind, true, 0);
 		if (ret < 0) {
 			tcf_idr_cleanup(tn, index);
 			return ret;
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 2b43cacf82af..43a243081e7d 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -94,7 +94,7 @@ static const struct nla_policy connmark_policy[TCA_CONNMARK_MAX + 1] = {
 static int tcf_connmark_init(struct net *net, struct nlattr *nla,
 			     struct nlattr *est, struct tc_action **a,
 			     int ovr, int bind, bool rtnl_held,
-			     struct tcf_proto *tp,
+			     struct tcf_proto *tp, u32 flags,
 			     struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, connmark_net_id);
@@ -121,7 +121,7 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
 	ret = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!ret) {
 		ret = tcf_idr_create(tn, index, est, a,
-				     &act_connmark_ops, bind, false);
+				     &act_connmark_ops, bind, false, 0);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			return ret;
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index d3cfad88dc3a..16e67e1c1db1 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -43,7 +43,7 @@ static struct tc_action_ops act_csum_ops;
 static int tcf_csum_init(struct net *net, struct nlattr *nla,
 			 struct nlattr *est, struct tc_action **a, int ovr,
 			 int bind, bool rtnl_held, struct tcf_proto *tp,
-			 struct netlink_ext_ack *extack)
+			 u32 flags, struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, csum_net_id);
 	struct tcf_csum_params *params_new;
@@ -68,8 +68,8 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
 	index = parm->index;
 	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!err) {
-		ret = tcf_idr_create(tn, index, est, a,
-				     &act_csum_ops, bind, true);
+		ret = tcf_idr_create_from_flags(tn, index, est, a,
+						&act_csum_ops, bind, flags);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			return ret;
@@ -580,7 +580,7 @@ static int tcf_csum_act(struct sk_buff *skb, const struct tc_action *a,
 	params = rcu_dereference_bh(p->params);
 
 	tcf_lastuse_update(&p->tcf_tm);
-	bstats_cpu_update(this_cpu_ptr(p->common.cpu_bstats), skb);
+	tcf_action_update_bstats(&p->common, skb);
 
 	action = READ_ONCE(p->tcf_action);
 	if (unlikely(action == TC_ACT_SHOT))
@@ -624,7 +624,7 @@ out:
 	return action;
 
 drop:
-	qstats_drop_inc(this_cpu_ptr(p->common.cpu_qstats));
+	tcf_action_inc_drop_qstats(&p->common);
 	action = TC_ACT_SHOT;
 	goto out;
 }
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index fcc46025e790..c13638aeef46 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -465,16 +465,15 @@ out_push:
 	skb_push_rcsum(skb, nh_ofs);
 
 out:
-	bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), skb);
+	tcf_action_update_bstats(&c->common, skb);
 	return retval;
 
 drop:
-	qstats_drop_inc(this_cpu_ptr(a->cpu_qstats));
+	tcf_action_inc_drop_qstats(&c->common);
 	return TC_ACT_SHOT;
 }
 
 static const struct nla_policy ct_policy[TCA_CT_MAX + 1] = {
-	[TCA_CT_UNSPEC] = { .strict_start_type = TCA_CT_UNSPEC + 1 },
 	[TCA_CT_ACTION] = { .type = NLA_U16 },
 	[TCA_CT_PARMS] = { .type = NLA_EXACT_LEN, .len = sizeof(struct tc_ct) },
 	[TCA_CT_ZONE] = { .type = NLA_U16 },
@@ -656,7 +655,7 @@ static int tcf_ct_fill_params(struct net *net,
 static int tcf_ct_init(struct net *net, struct nlattr *nla,
 		       struct nlattr *est, struct tc_action **a,
 		       int replace, int bind, bool rtnl_held,
-		       struct tcf_proto *tp,
+		       struct tcf_proto *tp, u32 flags,
 		       struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, ct_net_id);
@@ -688,8 +687,8 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla,
 		return err;
 
 	if (!err) {
-		err = tcf_idr_create(tn, index, est, a,
-				     &act_ct_ops, bind, true);
+		err = tcf_idr_create_from_flags(tn, index, est, a,
+						&act_ct_ops, bind, flags);
 		if (err) {
 			tcf_idr_cleanup(tn, index);
 			return err;
@@ -905,11 +904,7 @@ static void tcf_stats_update(struct tc_action *a, u64 bytes, u32 packets,
 {
 	struct tcf_ct *c = to_ct(a);
 
-	_bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets);
-
-	if (hw)
-		_bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw),
-				   bytes, packets);
+	tcf_action_update_stats(a, bytes, packets, false, hw);
 	c->tcf_tm.lastuse = max_t(u64, c->tcf_tm.lastuse, lastuse);
 }
 
diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c
index 0dbcfd1dca7b..b1e601007242 100644
--- a/net/sched/act_ctinfo.c
+++ b/net/sched/act_ctinfo.c
@@ -153,7 +153,7 @@ static const struct nla_policy ctinfo_policy[TCA_CTINFO_MAX + 1] = {
 static int tcf_ctinfo_init(struct net *net, struct nlattr *nla,
 			   struct nlattr *est, struct tc_action **a,
 			   int ovr, int bind, bool rtnl_held,
-			   struct tcf_proto *tp,
+			   struct tcf_proto *tp, u32 flags,
 			   struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, ctinfo_net_id);
@@ -210,7 +210,7 @@ static int tcf_ctinfo_init(struct net *net, struct nlattr *nla,
 	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!err) {
 		ret = tcf_idr_create(tn, index, est, a,
-				     &act_ctinfo_ops, bind, false);
+				     &act_ctinfo_ops, bind, false, 0);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			return ret;
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index 324f1d1f6d47..416065772719 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -53,7 +53,8 @@ static const struct nla_policy gact_policy[TCA_GACT_MAX + 1] = {
 static int tcf_gact_init(struct net *net, struct nlattr *nla,
 			 struct nlattr *est, struct tc_action **a,
 			 int ovr, int bind, bool rtnl_held,
-			 struct tcf_proto *tp, struct netlink_ext_ack *extack)
+			 struct tcf_proto *tp, u32 flags,
+			 struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, gact_net_id);
 	struct nlattr *tb[TCA_GACT_MAX + 1];
@@ -98,8 +99,8 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
 
 	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!err) {
-		ret = tcf_idr_create(tn, index, est, a,
-				     &act_gact_ops, bind, true);
+		ret = tcf_idr_create_from_flags(tn, index, est, a,
+						&act_gact_ops, bind, flags);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			return ret;
@@ -161,9 +162,9 @@ static int tcf_gact_act(struct sk_buff *skb, const struct tc_action *a,
 		action = gact_rand[ptype](gact);
 	}
 #endif
-	bstats_cpu_update(this_cpu_ptr(gact->common.cpu_bstats), skb);
+	tcf_action_update_bstats(&gact->common, skb);
 	if (action == TC_ACT_SHOT)
-		qstats_drop_inc(this_cpu_ptr(gact->common.cpu_qstats));
+		tcf_action_inc_drop_qstats(&gact->common);
 
 	tcf_lastuse_update(&gact->tcf_tm);
 
@@ -177,15 +178,7 @@ static void tcf_gact_stats_update(struct tc_action *a, u64 bytes, u32 packets,
 	int action = READ_ONCE(gact->tcf_action);
 	struct tcf_t *tm = &gact->tcf_tm;
 
-	_bstats_cpu_update(this_cpu_ptr(gact->common.cpu_bstats), bytes,
-			   packets);
-	if (action == TC_ACT_SHOT)
-		this_cpu_ptr(gact->common.cpu_qstats)->drops += packets;
-
-	if (hw)
-		_bstats_cpu_update(this_cpu_ptr(gact->common.cpu_bstats_hw),
-				   bytes, packets);
-
+	tcf_action_update_stats(a, bytes, packets, action == TC_ACT_SHOT, hw);
 	tm->lastuse = max_t(u64, tm->lastuse, lastuse);
 }
 
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 3a31e241c647..d562c88cccbe 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -465,7 +465,8 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
 static int tcf_ife_init(struct net *net, struct nlattr *nla,
 			struct nlattr *est, struct tc_action **a,
 			int ovr, int bind, bool rtnl_held,
-			struct tcf_proto *tp, struct netlink_ext_ack *extack)
+			struct tcf_proto *tp, u32 flags,
+			struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, ife_net_id);
 	struct nlattr *tb[TCA_IFE_MAX + 1];
@@ -522,7 +523,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, index, est, a, &act_ife_ops,
-				     bind, true);
+				     bind, true, 0);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			kfree(p);
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 214a03d405cf..400a2cfe8452 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -95,7 +95,7 @@ static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = {
 static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla,
 			  struct nlattr *est, struct tc_action **a,
 			  const struct tc_action_ops *ops, int ovr, int bind,
-			  struct tcf_proto *tp)
+			  struct tcf_proto *tp, u32 flags)
 {
 	struct tc_action_net *tn = net_generic(net, id);
 	struct nlattr *tb[TCA_IPT_MAX + 1];
@@ -144,7 +144,7 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla,
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, index, est, a, ops, bind,
-				     false);
+				     false, 0);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			return ret;
@@ -205,19 +205,19 @@ err1:
 static int tcf_ipt_init(struct net *net, struct nlattr *nla,
 			struct nlattr *est, struct tc_action **a, int ovr,
 			int bind, bool rtnl_held, struct tcf_proto *tp,
-			struct netlink_ext_ack *extack)
+			u32 flags, struct netlink_ext_ack *extack)
 {
 	return __tcf_ipt_init(net, ipt_net_id, nla, est, a, &act_ipt_ops, ovr,
-			      bind, tp);
+			      bind, tp, flags);
 }
 
 static int tcf_xt_init(struct net *net, struct nlattr *nla,
 		       struct nlattr *est, struct tc_action **a, int ovr,
 		       int bind, bool unlocked, struct tcf_proto *tp,
-		       struct netlink_ext_ack *extack)
+		       u32 flags, struct netlink_ext_ack *extack)
 {
 	return __tcf_ipt_init(net, xt_net_id, nla, est, a, &act_xt_ops, ovr,
-			      bind, tp);
+			      bind, tp, flags);
 }
 
 static int tcf_ipt_act(struct sk_buff *skb, const struct tc_action *a,
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 08923b21e566..b6e1b5bbb4da 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -93,7 +93,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 			   struct nlattr *est, struct tc_action **a,
 			   int ovr, int bind, bool rtnl_held,
 			   struct tcf_proto *tp,
-			   struct netlink_ext_ack *extack)
+			   u32 flags, struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, mirred_net_id);
 	struct nlattr *tb[TCA_MIRRED_MAX + 1];
@@ -148,8 +148,8 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 			NL_SET_ERR_MSG_MOD(extack, "Specified device does not exist");
 			return -EINVAL;
 		}
-		ret = tcf_idr_create(tn, index, est, a,
-				     &act_mirred_ops, bind, true);
+		ret = tcf_idr_create_from_flags(tn, index, est, a,
+						&act_mirred_ops, bind, flags);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			return ret;
@@ -231,7 +231,7 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a,
 	}
 
 	tcf_lastuse_update(&m->tcf_tm);
-	bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb);
+	tcf_action_update_bstats(&m->common, skb);
 
 	m_mac_header_xmit = READ_ONCE(m->tcfm_mac_header_xmit);
 	m_eaction = READ_ONCE(m->tcfm_eaction);
@@ -289,8 +289,8 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a,
 		/* let's the caller reinsert the packet, if possible */
 		if (use_reinsert) {
 			res->ingress = want_ingress;
-			res->qstats = this_cpu_ptr(m->common.cpu_qstats);
-			skb_tc_reinsert(skb, res);
+			if (skb_tc_reinsert(skb, res))
+				tcf_action_inc_overlimit_qstats(&m->common);
 			__this_cpu_dec(mirred_rec_level);
 			return TC_ACT_CONSUMED;
 		}
@@ -303,7 +303,7 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a,
 
 	if (err) {
 out:
-		qstats_overlimit_inc(this_cpu_ptr(m->common.cpu_qstats));
+		tcf_action_inc_overlimit_qstats(&m->common);
 		if (tcf_mirred_is_act_redirect(m_eaction))
 			retval = TC_ACT_SHOT;
 	}
@@ -318,10 +318,7 @@ static void tcf_stats_update(struct tc_action *a, u64 bytes, u32 packets,
 	struct tcf_mirred *m = to_mirred(a);
 	struct tcf_t *tm = &m->tcf_tm;
 
-	_bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets);
-	if (hw)
-		_bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw),
-				   bytes, packets);
+	tcf_action_update_stats(a, bytes, packets, false, hw);
 	tm->lastuse = max_t(u64, tm->lastuse, lastuse);
 }
 
diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c
index 4cf6c553bb0b..c7d5e12ee919 100644
--- a/net/sched/act_mpls.c
+++ b/net/sched/act_mpls.c
@@ -119,7 +119,6 @@ static int valid_label(const struct nlattr *attr,
 }
 
 static const struct nla_policy mpls_policy[TCA_MPLS_MAX + 1] = {
-	[TCA_MPLS_UNSPEC]	= { .strict_start_type = TCA_MPLS_UNSPEC + 1 },
 	[TCA_MPLS_PARMS]	= NLA_POLICY_EXACT_LEN(sizeof(struct tc_mpls)),
 	[TCA_MPLS_PROTO]	= { .type = NLA_U16 },
 	[TCA_MPLS_LABEL]	= NLA_POLICY_VALIDATE_FN(NLA_U32, valid_label),
@@ -131,7 +130,8 @@ static const struct nla_policy mpls_policy[TCA_MPLS_MAX + 1] = {
 static int tcf_mpls_init(struct net *net, struct nlattr *nla,
 			 struct nlattr *est, struct tc_action **a,
 			 int ovr, int bind, bool rtnl_held,
-			 struct tcf_proto *tp, struct netlink_ext_ack *extack)
+			 struct tcf_proto *tp, u32 flags,
+			 struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, mpls_net_id);
 	struct nlattr *tb[TCA_MPLS_MAX + 1];
@@ -224,7 +224,7 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla,
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, index, est, a,
-				     &act_mpls_ops, bind, true);
+				     &act_mpls_ops, bind, true, 0);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			return ret;
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index ea4c5359e7df..855a6fa16a62 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -36,7 +36,7 @@ static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = {
 static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 			struct tc_action **a, int ovr, int bind,
 			bool rtnl_held,	struct tcf_proto *tp,
-			struct netlink_ext_ack *extack)
+			u32 flags, struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, nat_net_id);
 	struct nlattr *tb[TCA_NAT_MAX + 1];
@@ -61,7 +61,7 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!err) {
 		ret = tcf_idr_create(tn, index, est, a,
-				     &act_nat_ops, bind, false);
+				     &act_nat_ops, bind, false, 0);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			return ret;
@@ -206,9 +206,7 @@ static int tcf_nat_act(struct sk_buff *skb, const struct tc_action *a,
 
 		icmph = (void *)(skb_network_header(skb) + ihl);
 
-		if ((icmph->type != ICMP_DEST_UNREACH) &&
-		    (icmph->type != ICMP_TIME_EXCEEDED) &&
-		    (icmph->type != ICMP_PARAMETERPROB))
+		if (!icmp_is_err(icmph->type))
 			break;
 
 		if (!pskb_may_pull(skb, ihl + sizeof(*icmph) + sizeof(*iph) +
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index b5bc631b96b7..3ad718576304 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -137,7 +137,8 @@ nla_failure:
 static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 			  struct nlattr *est, struct tc_action **a,
 			  int ovr, int bind, bool rtnl_held,
-			  struct tcf_proto *tp, struct netlink_ext_ack *extack)
+			  struct tcf_proto *tp, u32 flags,
+			  struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, pedit_net_id);
 	struct nlattr *tb[TCA_PEDIT_MAX + 1];
@@ -188,7 +189,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!err) {
 		ret = tcf_idr_create(tn, index, est, a,
-				     &act_pedit_ops, bind, false);
+				     &act_pedit_ops, bind, false, 0);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			goto out_free;
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 89c04c52af3d..d96271590268 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -47,7 +47,7 @@ static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = {
 static int tcf_police_init(struct net *net, struct nlattr *nla,
 			       struct nlattr *est, struct tc_action **a,
 			       int ovr, int bind, bool rtnl_held,
-			       struct tcf_proto *tp,
+			       struct tcf_proto *tp, u32 flags,
 			       struct netlink_ext_ack *extack)
 {
 	int ret = 0, tcfp_result = TC_ACT_OK, err, size;
@@ -87,7 +87,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, index, NULL, a,
-				     &act_police_ops, bind, true);
+				     &act_police_ops, bind, true, 0);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			return ret;
@@ -294,10 +294,7 @@ static void tcf_police_stats_update(struct tc_action *a,
 	struct tcf_police *police = to_police(a);
 	struct tcf_t *tm = &police->tcf_tm;
 
-	_bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets);
-	if (hw)
-		_bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw),
-				   bytes, packets);
+	tcf_action_update_stats(a, bytes, packets, false, hw);
 	tm->lastuse = max_t(u64, tm->lastuse, lastuse);
 }
 
@@ -345,10 +342,7 @@ static int tcf_police_dump(struct sk_buff *skb, struct tc_action *a,
 	    nla_put_u32(skb, TCA_POLICE_AVRATE, p->tcfp_ewma_rate))
 		goto nla_put_failure;
 
-	t.install = jiffies_to_clock_t(jiffies - police->tcf_tm.install);
-	t.lastuse = jiffies_to_clock_t(jiffies - police->tcf_tm.lastuse);
-	t.firstuse = jiffies_to_clock_t(jiffies - police->tcf_tm.firstuse);
-	t.expires = jiffies_to_clock_t(police->tcf_tm.expires);
+	tcf_tm_dump(&t, &police->tcf_tm);
 	if (nla_put_64bit(skb, TCA_POLICE_TM, sizeof(t), &t, TCA_POLICE_PAD))
 		goto nla_put_failure;
 	spin_unlock_bh(&police->tcf_lock);
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 514456a0b9a8..29b23bfaf10d 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -36,7 +36,7 @@ static const struct nla_policy sample_policy[TCA_SAMPLE_MAX + 1] = {
 static int tcf_sample_init(struct net *net, struct nlattr *nla,
 			   struct nlattr *est, struct tc_action **a, int ovr,
 			   int bind, bool rtnl_held, struct tcf_proto *tp,
-			   struct netlink_ext_ack *extack)
+			   u32 flags, struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, sample_net_id);
 	struct nlattr *tb[TCA_SAMPLE_MAX + 1];
@@ -69,7 +69,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, index, est, a,
-				     &act_sample_ops, bind, true);
+				     &act_sample_ops, bind, true, 0);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			return ret;
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 6120e56117ca..9813ca4006dd 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -35,7 +35,7 @@ static int tcf_simp_act(struct sk_buff *skb, const struct tc_action *a,
 	 * Example if this was the 3rd packet and the string was "hello"
 	 * then it would look like "hello_3" (without quotes)
 	 */
-	pr_info("simple: %s_%d\n",
+	pr_info("simple: %s_%llu\n",
 	       (char *)d->tcfd_defdata, d->tcf_bstats.packets);
 	spin_unlock(&d->tcf_lock);
 	return d->tcf_action;
@@ -86,7 +86,8 @@ static const struct nla_policy simple_policy[TCA_DEF_MAX + 1] = {
 static int tcf_simp_init(struct net *net, struct nlattr *nla,
 			 struct nlattr *est, struct tc_action **a,
 			 int ovr, int bind, bool rtnl_held,
-			 struct tcf_proto *tp, struct netlink_ext_ack *extack)
+			 struct tcf_proto *tp, u32 flags,
+			 struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, simp_net_id);
 	struct nlattr *tb[TCA_DEF_MAX + 1];
@@ -127,7 +128,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, index, est, a,
-				     &act_simp_ops, bind, false);
+				     &act_simp_ops, bind, false, 0);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			return ret;
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 6a8d3337c577..5f7ca7f89ca2 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -86,7 +86,7 @@ static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = {
 static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 			    struct nlattr *est, struct tc_action **a,
 			    int ovr, int bind, bool rtnl_held,
-			    struct tcf_proto *tp,
+			    struct tcf_proto *tp, u32 act_flags,
 			    struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, skbedit_net_id);
@@ -165,7 +165,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, index, est, a,
-				     &act_skbedit_ops, bind, true);
+				     &act_skbedit_ops, bind, true, 0);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			return ret;
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index 888437f97ba6..39e6d94cfafb 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -79,7 +79,7 @@ static const struct nla_policy skbmod_policy[TCA_SKBMOD_MAX + 1] = {
 static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 			   struct nlattr *est, struct tc_action **a,
 			   int ovr, int bind, bool rtnl_held,
-			   struct tcf_proto *tp,
+			   struct tcf_proto *tp, u32 flags,
 			   struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, skbmod_net_id);
@@ -143,7 +143,7 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, index, est, a,
-				     &act_skbmod_ops, bind, true);
+				     &act_skbmod_ops, bind, true, 0);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			return ret;
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index d55669e14741..6379f9568ab8 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -10,6 +10,8 @@
 #include <linux/skbuff.h>
 #include <linux/rtnetlink.h>
 #include <net/geneve.h>
+#include <net/vxlan.h>
+#include <net/erspan.h>
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
 #include <net/dst.h>
@@ -31,7 +33,7 @@ static int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a,
 	params = rcu_dereference_bh(t->params);
 
 	tcf_lastuse_update(&t->tcf_tm);
-	bstats_cpu_update(this_cpu_ptr(t->common.cpu_bstats), skb);
+	tcf_action_update_bstats(&t->common, skb);
 	action = READ_ONCE(t->tcf_action);
 
 	switch (params->tcft_action) {
@@ -53,7 +55,11 @@ static int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a,
 
 static const struct nla_policy
 enc_opts_policy[TCA_TUNNEL_KEY_ENC_OPTS_MAX + 1] = {
+	[TCA_TUNNEL_KEY_ENC_OPTS_UNSPEC]	= {
+		.strict_start_type = TCA_TUNNEL_KEY_ENC_OPTS_VXLAN },
 	[TCA_TUNNEL_KEY_ENC_OPTS_GENEVE]	= { .type = NLA_NESTED },
+	[TCA_TUNNEL_KEY_ENC_OPTS_VXLAN]		= { .type = NLA_NESTED },
+	[TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN]	= { .type = NLA_NESTED },
 };
 
 static const struct nla_policy
@@ -64,6 +70,19 @@ geneve_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX + 1] = {
 						       .len = 128 },
 };
 
+static const struct nla_policy
+vxlan_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX + 1] = {
+	[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP]	   = { .type = NLA_U32 },
+};
+
+static const struct nla_policy
+erspan_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX + 1] = {
+	[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER]	   = { .type = NLA_U8 },
+	[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX]	   = { .type = NLA_U32 },
+	[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR]	   = { .type = NLA_U8 },
+	[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID]	   = { .type = NLA_U8 },
+};
+
 static int
 tunnel_key_copy_geneve_opt(const struct nlattr *nla, void *dst, int dst_len,
 			   struct netlink_ext_ack *extack)
@@ -116,10 +135,89 @@ tunnel_key_copy_geneve_opt(const struct nlattr *nla, void *dst, int dst_len,
 	return opt_len;
 }
 
+static int
+tunnel_key_copy_vxlan_opt(const struct nlattr *nla, void *dst, int dst_len,
+			  struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX + 1];
+	int err;
+
+	err = nla_parse_nested(tb, TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX, nla,
+			       vxlan_opt_policy, extack);
+	if (err < 0)
+		return err;
+
+	if (!tb[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP]) {
+		NL_SET_ERR_MSG(extack, "Missing tunnel key vxlan option gbp");
+		return -EINVAL;
+	}
+
+	if (dst) {
+		struct vxlan_metadata *md = dst;
+
+		md->gbp = nla_get_u32(tb[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP]);
+	}
+
+	return sizeof(struct vxlan_metadata);
+}
+
+static int
+tunnel_key_copy_erspan_opt(const struct nlattr *nla, void *dst, int dst_len,
+			   struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX + 1];
+	int err;
+	u8 ver;
+
+	err = nla_parse_nested(tb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX, nla,
+			       erspan_opt_policy, extack);
+	if (err < 0)
+		return err;
+
+	if (!tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER]) {
+		NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option ver");
+		return -EINVAL;
+	}
+
+	ver = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER]);
+	if (ver == 1) {
+		if (!tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX]) {
+			NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option index");
+			return -EINVAL;
+		}
+	} else if (ver == 2) {
+		if (!tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR] ||
+		    !tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID]) {
+			NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option dir or hwid");
+			return -EINVAL;
+		}
+	} else {
+		NL_SET_ERR_MSG(extack, "Tunnel key erspan option ver is incorrect");
+		return -EINVAL;
+	}
+
+	if (dst) {
+		struct erspan_metadata *md = dst;
+
+		md->version = ver;
+		if (ver == 1) {
+			nla = tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX];
+			md->u.index = nla_get_be32(nla);
+		} else {
+			nla = tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR];
+			md->u.md2.dir = nla_get_u8(nla);
+			nla = tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID];
+			set_hwid(&md->u.md2, nla_get_u8(nla));
+		}
+	}
+
+	return sizeof(struct erspan_metadata);
+}
+
 static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst,
 				int dst_len, struct netlink_ext_ack *extack)
 {
-	int err, rem, opt_len, len = nla_len(nla), opts_len = 0;
+	int err, rem, opt_len, len = nla_len(nla), opts_len = 0, type = 0;
 	const struct nlattr *attr, *head = nla_data(nla);
 
 	err = nla_validate_deprecated(head, len, TCA_TUNNEL_KEY_ENC_OPTS_MAX,
@@ -130,6 +228,10 @@ static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst,
 	nla_for_each_attr(attr, head, len, rem) {
 		switch (nla_type(attr)) {
 		case TCA_TUNNEL_KEY_ENC_OPTS_GENEVE:
+			if (type && type != TUNNEL_GENEVE_OPT) {
+				NL_SET_ERR_MSG(extack, "Duplicate type for geneve options");
+				return -EINVAL;
+			}
 			opt_len = tunnel_key_copy_geneve_opt(attr, dst,
 							     dst_len, extack);
 			if (opt_len < 0)
@@ -143,6 +245,31 @@ static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst,
 				dst_len -= opt_len;
 				dst += opt_len;
 			}
+			type = TUNNEL_GENEVE_OPT;
+			break;
+		case TCA_TUNNEL_KEY_ENC_OPTS_VXLAN:
+			if (type) {
+				NL_SET_ERR_MSG(extack, "Duplicate type for vxlan options");
+				return -EINVAL;
+			}
+			opt_len = tunnel_key_copy_vxlan_opt(attr, dst,
+							    dst_len, extack);
+			if (opt_len < 0)
+				return opt_len;
+			opts_len += opt_len;
+			type = TUNNEL_VXLAN_OPT;
+			break;
+		case TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN:
+			if (type) {
+				NL_SET_ERR_MSG(extack, "Duplicate type for erspan options");
+				return -EINVAL;
+			}
+			opt_len = tunnel_key_copy_erspan_opt(attr, dst,
+							     dst_len, extack);
+			if (opt_len < 0)
+				return opt_len;
+			opts_len += opt_len;
+			type = TUNNEL_ERSPAN_OPT;
 			break;
 		}
 	}
@@ -179,6 +306,22 @@ static int tunnel_key_opts_set(struct nlattr *nla, struct ip_tunnel_info *info,
 #else
 		return -EAFNOSUPPORT;
 #endif
+	case TCA_TUNNEL_KEY_ENC_OPTS_VXLAN:
+#if IS_ENABLED(CONFIG_INET)
+		info->key.tun_flags |= TUNNEL_VXLAN_OPT;
+		return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info),
+					    opts_len, extack);
+#else
+		return -EAFNOSUPPORT;
+#endif
+	case TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN:
+#if IS_ENABLED(CONFIG_INET)
+		info->key.tun_flags |= TUNNEL_ERSPAN_OPT;
+		return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info),
+					    opts_len, extack);
+#else
+		return -EAFNOSUPPORT;
+#endif
 	default:
 		NL_SET_ERR_MSG(extack, "Cannot set tunnel options for unknown tunnel type");
 		return -EINVAL;
@@ -212,7 +355,7 @@ static void tunnel_key_release_params(struct tcf_tunnel_key_params *p)
 static int tunnel_key_init(struct net *net, struct nlattr *nla,
 			   struct nlattr *est, struct tc_action **a,
 			   int ovr, int bind, bool rtnl_held,
-			   struct tcf_proto *tp,
+			   struct tcf_proto *tp, u32 act_flags,
 			   struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
@@ -351,8 +494,9 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 	}
 
 	if (!exists) {
-		ret = tcf_idr_create(tn, index, est, a,
-				     &act_tunnel_key_ops, bind, true);
+		ret = tcf_idr_create_from_flags(tn, index, est, a,
+						&act_tunnel_key_ops, bind,
+						act_flags);
 		if (ret) {
 			NL_SET_ERR_MSG(extack, "Cannot create TC IDR");
 			goto release_tun_meta;
@@ -454,6 +598,56 @@ static int tunnel_key_geneve_opts_dump(struct sk_buff *skb,
 	return 0;
 }
 
+static int tunnel_key_vxlan_opts_dump(struct sk_buff *skb,
+				      const struct ip_tunnel_info *info)
+{
+	struct vxlan_metadata *md = (struct vxlan_metadata *)(info + 1);
+	struct nlattr *start;
+
+	start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_VXLAN);
+	if (!start)
+		return -EMSGSIZE;
+
+	if (nla_put_u32(skb, TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP, md->gbp)) {
+		nla_nest_cancel(skb, start);
+		return -EMSGSIZE;
+	}
+
+	nla_nest_end(skb, start);
+	return 0;
+}
+
+static int tunnel_key_erspan_opts_dump(struct sk_buff *skb,
+				       const struct ip_tunnel_info *info)
+{
+	struct erspan_metadata *md = (struct erspan_metadata *)(info + 1);
+	struct nlattr *start;
+
+	start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN);
+	if (!start)
+		return -EMSGSIZE;
+
+	if (nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER, md->version))
+		goto err;
+
+	if (md->version == 1 &&
+	    nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX, md->u.index))
+		goto err;
+
+	if (md->version == 2 &&
+	    (nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR,
+			md->u.md2.dir) ||
+	     nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID,
+			get_hwid(&md->u.md2))))
+		goto err;
+
+	nla_nest_end(skb, start);
+	return 0;
+err:
+	nla_nest_cancel(skb, start);
+	return -EMSGSIZE;
+}
+
 static int tunnel_key_opts_dump(struct sk_buff *skb,
 				const struct ip_tunnel_info *info)
 {
@@ -471,6 +665,14 @@ static int tunnel_key_opts_dump(struct sk_buff *skb,
 		err = tunnel_key_geneve_opts_dump(skb, info);
 		if (err)
 			goto err_out;
+	} else if (info->key.tun_flags & TUNNEL_VXLAN_OPT) {
+		err = tunnel_key_vxlan_opts_dump(skb, info);
+		if (err)
+			goto err_out;
+	} else if (info->key.tun_flags & TUNNEL_ERSPAN_OPT) {
+		err = tunnel_key_erspan_opts_dump(skb, info);
+		if (err)
+			goto err_out;
 	} else {
 err_out:
 		nla_nest_cancel(skb, start);
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 08aaf719a70f..b6939abc61eb 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -29,7 +29,7 @@ static int tcf_vlan_act(struct sk_buff *skb, const struct tc_action *a,
 	u16 tci;
 
 	tcf_lastuse_update(&v->tcf_tm);
-	bstats_cpu_update(this_cpu_ptr(v->common.cpu_bstats), skb);
+	tcf_action_update_bstats(&v->common, skb);
 
 	/* Ensure 'data' points at mac_header prior calling vlan manipulating
 	 * functions.
@@ -88,7 +88,7 @@ out:
 	return action;
 
 drop:
-	qstats_drop_inc(this_cpu_ptr(v->common.cpu_qstats));
+	tcf_action_inc_drop_qstats(&v->common);
 	return TC_ACT_SHOT;
 }
 
@@ -102,7 +102,8 @@ static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = {
 static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 			 struct nlattr *est, struct tc_action **a,
 			 int ovr, int bind, bool rtnl_held,
-			 struct tcf_proto *tp, struct netlink_ext_ack *extack)
+			 struct tcf_proto *tp, u32 flags,
+			 struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, vlan_net_id);
 	struct nlattr *tb[TCA_VLAN_MAX + 1];
@@ -188,8 +189,8 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 	action = parm->v_action;
 
 	if (!exists) {
-		ret = tcf_idr_create(tn, index, est, a,
-				     &act_vlan_ops, bind, true);
+		ret = tcf_idr_create_from_flags(tn, index, est, a,
+						&act_vlan_ops, bind, flags);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			return ret;
@@ -307,10 +308,7 @@ static void tcf_vlan_stats_update(struct tc_action *a, u64 bytes, u32 packets,
 	struct tcf_vlan *v = to_vlan(a);
 	struct tcf_t *tm = &v->tcf_tm;
 
-	_bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets);
-	if (hw)
-		_bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw),
-				   bytes, packets);
+	tcf_action_update_stats(a, bytes, packets, false, hw);
 	tm->lastuse = max_t(u64, tm->lastuse, lastuse);
 }
 
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 74221e3351c3..c307ee1d6ca6 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -22,6 +22,8 @@
 #include <net/ip.h>
 #include <net/flow_dissector.h>
 #include <net/geneve.h>
+#include <net/vxlan.h>
+#include <net/erspan.h>
 
 #include <net/dst.h>
 #include <net/dst_metadata.h>
@@ -688,7 +690,11 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
 
 static const struct nla_policy
 enc_opts_policy[TCA_FLOWER_KEY_ENC_OPTS_MAX + 1] = {
+	[TCA_FLOWER_KEY_ENC_OPTS_UNSPEC]        = {
+		.strict_start_type = TCA_FLOWER_KEY_ENC_OPTS_VXLAN },
 	[TCA_FLOWER_KEY_ENC_OPTS_GENEVE]        = { .type = NLA_NESTED },
+	[TCA_FLOWER_KEY_ENC_OPTS_VXLAN]         = { .type = NLA_NESTED },
+	[TCA_FLOWER_KEY_ENC_OPTS_ERSPAN]        = { .type = NLA_NESTED },
 };
 
 static const struct nla_policy
@@ -699,6 +705,19 @@ geneve_opt_policy[TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX + 1] = {
 						       .len = 128 },
 };
 
+static const struct nla_policy
+vxlan_opt_policy[TCA_FLOWER_KEY_ENC_OPT_VXLAN_MAX + 1] = {
+	[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]         = { .type = NLA_U32 },
+};
+
+static const struct nla_policy
+erspan_opt_policy[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX + 1] = {
+	[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_VER]        = { .type = NLA_U8 },
+	[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX]      = { .type = NLA_U32 },
+	[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_DIR]        = { .type = NLA_U8 },
+	[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID]       = { .type = NLA_U8 },
+};
+
 static void fl_set_key_val(struct nlattr **tb,
 			   void *val, int val_type,
 			   void *mask, int mask_type, int len)
@@ -928,6 +947,105 @@ static int fl_set_geneve_opt(const struct nlattr *nla, struct fl_flow_key *key,
 	return sizeof(struct geneve_opt) + data_len;
 }
 
+static int fl_set_vxlan_opt(const struct nlattr *nla, struct fl_flow_key *key,
+			    int depth, int option_len,
+			    struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_MAX + 1];
+	struct vxlan_metadata *md;
+	int err;
+
+	md = (struct vxlan_metadata *)&key->enc_opts.data[key->enc_opts.len];
+	memset(md, 0xff, sizeof(*md));
+
+	if (!depth)
+		return sizeof(*md);
+
+	if (nla_type(nla) != TCA_FLOWER_KEY_ENC_OPTS_VXLAN) {
+		NL_SET_ERR_MSG(extack, "Non-vxlan option type for mask");
+		return -EINVAL;
+	}
+
+	err = nla_parse_nested(tb, TCA_FLOWER_KEY_ENC_OPT_VXLAN_MAX, nla,
+			       vxlan_opt_policy, extack);
+	if (err < 0)
+		return err;
+
+	if (!option_len && !tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]) {
+		NL_SET_ERR_MSG(extack, "Missing tunnel key vxlan option gbp");
+		return -EINVAL;
+	}
+
+	if (tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP])
+		md->gbp = nla_get_u32(tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]);
+
+	return sizeof(*md);
+}
+
+static int fl_set_erspan_opt(const struct nlattr *nla, struct fl_flow_key *key,
+			     int depth, int option_len,
+			     struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX + 1];
+	struct erspan_metadata *md;
+	int err;
+
+	md = (struct erspan_metadata *)&key->enc_opts.data[key->enc_opts.len];
+	memset(md, 0xff, sizeof(*md));
+	md->version = 1;
+
+	if (!depth)
+		return sizeof(*md);
+
+	if (nla_type(nla) != TCA_FLOWER_KEY_ENC_OPTS_ERSPAN) {
+		NL_SET_ERR_MSG(extack, "Non-erspan option type for mask");
+		return -EINVAL;
+	}
+
+	err = nla_parse_nested(tb, TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX, nla,
+			       erspan_opt_policy, extack);
+	if (err < 0)
+		return err;
+
+	if (!option_len && !tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_VER]) {
+		NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option ver");
+		return -EINVAL;
+	}
+
+	if (tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_VER])
+		md->version = nla_get_u8(tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_VER]);
+
+	if (md->version == 1) {
+		if (!option_len && !tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX]) {
+			NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option index");
+			return -EINVAL;
+		}
+		if (tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX]) {
+			nla = tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX];
+			md->u.index = nla_get_be32(nla);
+		}
+	} else if (md->version == 2) {
+		if (!option_len && (!tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_DIR] ||
+				    !tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID])) {
+			NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option dir or hwid");
+			return -EINVAL;
+		}
+		if (tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_DIR]) {
+			nla = tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_DIR];
+			md->u.md2.dir = nla_get_u8(nla);
+		}
+		if (tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID]) {
+			nla = tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID];
+			set_hwid(&md->u.md2, nla_get_u8(nla));
+		}
+	} else {
+		NL_SET_ERR_MSG(extack, "Tunnel key erspan option ver is incorrect");
+		return -EINVAL;
+	}
+
+	return sizeof(*md);
+}
+
 static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key,
 			  struct fl_flow_key *mask,
 			  struct netlink_ext_ack *extack)
@@ -958,6 +1076,11 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key,
 			  nla_len(tb[TCA_FLOWER_KEY_ENC_OPTS]), key_depth) {
 		switch (nla_type(nla_opt_key)) {
 		case TCA_FLOWER_KEY_ENC_OPTS_GENEVE:
+			if (key->enc_opts.dst_opt_type &&
+			    key->enc_opts.dst_opt_type != TUNNEL_GENEVE_OPT) {
+				NL_SET_ERR_MSG(extack, "Duplicate type for geneve options");
+				return -EINVAL;
+			}
 			option_len = 0;
 			key->enc_opts.dst_opt_type = TUNNEL_GENEVE_OPT;
 			option_len = fl_set_geneve_opt(nla_opt_key, key,
@@ -986,6 +1109,72 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key,
 			if (msk_depth)
 				nla_opt_msk = nla_next(nla_opt_msk, &msk_depth);
 			break;
+		case TCA_FLOWER_KEY_ENC_OPTS_VXLAN:
+			if (key->enc_opts.dst_opt_type) {
+				NL_SET_ERR_MSG(extack, "Duplicate type for vxlan options");
+				return -EINVAL;
+			}
+			option_len = 0;
+			key->enc_opts.dst_opt_type = TUNNEL_VXLAN_OPT;
+			option_len = fl_set_vxlan_opt(nla_opt_key, key,
+						      key_depth, option_len,
+						      extack);
+			if (option_len < 0)
+				return option_len;
+
+			key->enc_opts.len += option_len;
+			/* At the same time we need to parse through the mask
+			 * in order to verify exact and mask attribute lengths.
+			 */
+			mask->enc_opts.dst_opt_type = TUNNEL_VXLAN_OPT;
+			option_len = fl_set_vxlan_opt(nla_opt_msk, mask,
+						      msk_depth, option_len,
+						      extack);
+			if (option_len < 0)
+				return option_len;
+
+			mask->enc_opts.len += option_len;
+			if (key->enc_opts.len != mask->enc_opts.len) {
+				NL_SET_ERR_MSG(extack, "Key and mask miss aligned");
+				return -EINVAL;
+			}
+
+			if (msk_depth)
+				nla_opt_msk = nla_next(nla_opt_msk, &msk_depth);
+			break;
+		case TCA_FLOWER_KEY_ENC_OPTS_ERSPAN:
+			if (key->enc_opts.dst_opt_type) {
+				NL_SET_ERR_MSG(extack, "Duplicate type for erspan options");
+				return -EINVAL;
+			}
+			option_len = 0;
+			key->enc_opts.dst_opt_type = TUNNEL_ERSPAN_OPT;
+			option_len = fl_set_erspan_opt(nla_opt_key, key,
+						       key_depth, option_len,
+						       extack);
+			if (option_len < 0)
+				return option_len;
+
+			key->enc_opts.len += option_len;
+			/* At the same time we need to parse through the mask
+			 * in order to verify exact and mask attribute lengths.
+			 */
+			mask->enc_opts.dst_opt_type = TUNNEL_ERSPAN_OPT;
+			option_len = fl_set_erspan_opt(nla_opt_msk, mask,
+						       msk_depth, option_len,
+						       extack);
+			if (option_len < 0)
+				return option_len;
+
+			mask->enc_opts.len += option_len;
+			if (key->enc_opts.len != mask->enc_opts.len) {
+				NL_SET_ERR_MSG(extack, "Key and mask miss aligned");
+				return -EINVAL;
+			}
+
+			if (msk_depth)
+				nla_opt_msk = nla_next(nla_opt_msk, &msk_depth);
+			break;
 		default:
 			NL_SET_ERR_MSG(extack, "Unknown tunnel option type");
 			return -EINVAL;
@@ -2135,6 +2324,61 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
+static int fl_dump_key_vxlan_opt(struct sk_buff *skb,
+				 struct flow_dissector_key_enc_opts *enc_opts)
+{
+	struct vxlan_metadata *md;
+	struct nlattr *nest;
+
+	nest = nla_nest_start_noflag(skb, TCA_FLOWER_KEY_ENC_OPTS_VXLAN);
+	if (!nest)
+		goto nla_put_failure;
+
+	md = (struct vxlan_metadata *)&enc_opts->data[0];
+	if (nla_put_u32(skb, TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP, md->gbp))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, nest);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, nest);
+	return -EMSGSIZE;
+}
+
+static int fl_dump_key_erspan_opt(struct sk_buff *skb,
+				  struct flow_dissector_key_enc_opts *enc_opts)
+{
+	struct erspan_metadata *md;
+	struct nlattr *nest;
+
+	nest = nla_nest_start_noflag(skb, TCA_FLOWER_KEY_ENC_OPTS_ERSPAN);
+	if (!nest)
+		goto nla_put_failure;
+
+	md = (struct erspan_metadata *)&enc_opts->data[0];
+	if (nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_ERSPAN_VER, md->version))
+		goto nla_put_failure;
+
+	if (md->version == 1 &&
+	    nla_put_be32(skb, TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX, md->u.index))
+		goto nla_put_failure;
+
+	if (md->version == 2 &&
+	    (nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_ERSPAN_DIR,
+			md->u.md2.dir) ||
+	     nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID,
+			get_hwid(&md->u.md2))))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, nest);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, nest);
+	return -EMSGSIZE;
+}
+
 static int fl_dump_key_ct(struct sk_buff *skb,
 			  struct flow_dissector_key_ct *key,
 			  struct flow_dissector_key_ct *mask)
@@ -2188,6 +2432,16 @@ static int fl_dump_key_options(struct sk_buff *skb, int enc_opt_type,
 		if (err)
 			goto nla_put_failure;
 		break;
+	case TUNNEL_VXLAN_OPT:
+		err = fl_dump_key_vxlan_opt(skb, enc_opts);
+		if (err)
+			goto nla_put_failure;
+		break;
+	case TUNNEL_ERSPAN_OPT:
+		err = fl_dump_key_erspan_opt(skb, enc_opts);
+		if (err)
+			goto nla_put_failure;
+		break;
 	default:
 		goto nla_put_failure;
 	}
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index 3177dcb17316..d99966a55c84 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -521,7 +521,7 @@ META_COLLECTOR(int_sk_ack_bl)
 		*err = -1;
 		return;
 	}
-	dst->value = sk->sk_ack_backlog;
+	dst->value = READ_ONCE(sk->sk_ack_backlog);
 }
 
 META_COLLECTOR(int_sk_max_ack_bl)
@@ -532,7 +532,7 @@ META_COLLECTOR(int_sk_max_ack_bl)
 		*err = -1;
 		return;
 	}
-	dst->value = sk->sk_max_ack_backlog;
+	dst->value = READ_ONCE(sk->sk_max_ack_backlog);
 }
 
 META_COLLECTOR(int_sk_prio)
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 98dd87ce1510..b1c7e726ce5d 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -530,8 +530,7 @@ begin:
 			fq_flow_set_throttled(q, f);
 			goto begin;
 		}
-		if (time_next_packet &&
-		    (s64)(now - time_next_packet - q->ce_threshold) > 0) {
+		if ((s64)(now - time_next_packet - q->ce_threshold) > 0) {
 			INET_ECN_set_ce(skb);
 			q->stat_ce_mark++;
 		}
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index c261c0a18868..968519ff36e9 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -14,7 +14,6 @@
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/skbuff.h>
-#include <linux/jhash.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <net/netlink.h>
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 8769b4b8807d..5ab696efca95 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -382,13 +382,8 @@ void __qdisc_run(struct Qdisc *q)
 	int packets;
 
 	while (qdisc_restart(q, &packets)) {
-		/*
-		 * Ordered by possible occurrence: Postpone processing if
-		 * 1. we've exceeded packet quota
-		 * 2. another process needs the CPU;
-		 */
 		quota -= packets;
-		if (quota <= 0 || need_resched()) {
+		if (quota <= 0) {
 			__netif_schedule(q);
 			break;
 		}
@@ -657,7 +652,7 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc)
 	if (likely(skb)) {
 		qdisc_update_stats_at_dequeue(qdisc, skb);
 	} else {
-		qdisc->empty = true;
+		WRITE_ONCE(qdisc->empty, true);
 	}
 
 	return skb;
@@ -1214,8 +1209,13 @@ void dev_deactivate_many(struct list_head *head)
 
 	/* Wait for outstanding qdisc_run calls. */
 	list_for_each_entry(dev, head, close_list) {
-		while (some_qdisc_is_busy(dev))
-			yield();
+		while (some_qdisc_is_busy(dev)) {
+			/* wait_event() would avoid this sleep-loop but would
+			 * require expensive checks in the fast paths of packet
+			 * processing which isn't worth it.
+			 */
+			schedule_timeout_uninterruptible(1);
+		}
 		/* The new qdisc is assigned at this point so we can safely
 		 * unwind stale skb lists and qdisc statistics
 		 */
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
index df98a887eb89..b0b0dc46af61 100644
--- a/net/sched/sch_pie.c
+++ b/net/sched/sch_pie.c
@@ -22,6 +22,7 @@
 
 #define QUEUE_THRESHOLD 16384
 #define DQCOUNT_INVALID -1
+#define DTIME_INVALID 0xffffffffffffffff
 #define MAX_PROB 0xffffffffffffffff
 #define PIE_SCALE 8
 
@@ -34,6 +35,7 @@ struct pie_params {
 	u32 beta;		/* and are used for shift relative to 1 */
 	bool ecn;		/* true if ecn is enabled */
 	bool bytemode;		/* to scale drop early prob based on pkt size */
+	u8 dq_rate_estimator;	/* to calculate delay using Little's law */
 };
 
 /* variables used */
@@ -77,11 +79,34 @@ static void pie_params_init(struct pie_params *params)
 	params->target = PSCHED_NS2TICKS(15 * NSEC_PER_MSEC);	/* 15 ms */
 	params->ecn = false;
 	params->bytemode = false;
+	params->dq_rate_estimator = false;
+}
+
+/* private skb vars */
+struct pie_skb_cb {
+	psched_time_t enqueue_time;
+};
+
+static struct pie_skb_cb *get_pie_cb(const struct sk_buff *skb)
+{
+	qdisc_cb_private_validate(skb, sizeof(struct pie_skb_cb));
+	return (struct pie_skb_cb *)qdisc_skb_cb(skb)->data;
+}
+
+static psched_time_t pie_get_enqueue_time(const struct sk_buff *skb)
+{
+	return get_pie_cb(skb)->enqueue_time;
+}
+
+static void pie_set_enqueue_time(struct sk_buff *skb)
+{
+	get_pie_cb(skb)->enqueue_time = psched_get_time();
 }
 
 static void pie_vars_init(struct pie_vars *vars)
 {
 	vars->dq_count = DQCOUNT_INVALID;
+	vars->dq_tstamp = DTIME_INVALID;
 	vars->accu_prob = 0;
 	vars->avg_dq_rate = 0;
 	/* default of 150 ms in pschedtime */
@@ -172,6 +197,10 @@ static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 
 	/* we can enqueue the packet */
 	if (enqueue) {
+		/* Set enqueue time only when dq_rate_estimator is disabled. */
+		if (!q->params.dq_rate_estimator)
+			pie_set_enqueue_time(skb);
+
 		q->stats.packets_in++;
 		if (qdisc_qlen(sch) > q->stats.maxq)
 			q->stats.maxq = qdisc_qlen(sch);
@@ -194,6 +223,7 @@ static const struct nla_policy pie_policy[TCA_PIE_MAX + 1] = {
 	[TCA_PIE_BETA] = {.type = NLA_U32},
 	[TCA_PIE_ECN] = {.type = NLA_U32},
 	[TCA_PIE_BYTEMODE] = {.type = NLA_U32},
+	[TCA_PIE_DQ_RATE_ESTIMATOR] = {.type = NLA_U32},
 };
 
 static int pie_change(struct Qdisc *sch, struct nlattr *opt,
@@ -247,6 +277,10 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt,
 	if (tb[TCA_PIE_BYTEMODE])
 		q->params.bytemode = nla_get_u32(tb[TCA_PIE_BYTEMODE]);
 
+	if (tb[TCA_PIE_DQ_RATE_ESTIMATOR])
+		q->params.dq_rate_estimator =
+				nla_get_u32(tb[TCA_PIE_DQ_RATE_ESTIMATOR]);
+
 	/* Drop excess packets if new limit is lower */
 	qlen = sch->q.qlen;
 	while (sch->q.qlen > sch->limit) {
@@ -266,6 +300,28 @@ static void pie_process_dequeue(struct Qdisc *sch, struct sk_buff *skb)
 {
 	struct pie_sched_data *q = qdisc_priv(sch);
 	int qlen = sch->qstats.backlog;	/* current queue size in bytes */
+	psched_time_t now = psched_get_time();
+	u32 dtime = 0;
+
+	/* If dq_rate_estimator is disabled, calculate qdelay using the
+	 * packet timestamp.
+	 */
+	if (!q->params.dq_rate_estimator) {
+		q->vars.qdelay = now - pie_get_enqueue_time(skb);
+
+		if (q->vars.dq_tstamp != DTIME_INVALID)
+			dtime = now - q->vars.dq_tstamp;
+
+		q->vars.dq_tstamp = now;
+
+		if (qlen == 0)
+			q->vars.qdelay = 0;
+
+		if (dtime == 0)
+			return;
+
+		goto burst_allowance_reduction;
+	}
 
 	/* If current queue is about 10 packets or more and dq_count is unset
 	 * we have enough packets to calculate the drain rate. Save
@@ -289,10 +345,10 @@ static void pie_process_dequeue(struct Qdisc *sch, struct sk_buff *skb)
 		q->vars.dq_count += skb->len;
 
 		if (q->vars.dq_count >= QUEUE_THRESHOLD) {
-			psched_time_t now = psched_get_time();
-			u32 dtime = now - q->vars.dq_tstamp;
 			u32 count = q->vars.dq_count << PIE_SCALE;
 
+			dtime = now - q->vars.dq_tstamp;
+
 			if (dtime == 0)
 				return;
 
@@ -317,14 +373,19 @@ static void pie_process_dequeue(struct Qdisc *sch, struct sk_buff *skb)
 				q->vars.dq_tstamp = psched_get_time();
 			}
 
-			if (q->vars.burst_time > 0) {
-				if (q->vars.burst_time > dtime)
-					q->vars.burst_time -= dtime;
-				else
-					q->vars.burst_time = 0;
-			}
+			goto burst_allowance_reduction;
 		}
 	}
+
+	return;
+
+burst_allowance_reduction:
+	if (q->vars.burst_time > 0) {
+		if (q->vars.burst_time > dtime)
+			q->vars.burst_time -= dtime;
+		else
+			q->vars.burst_time = 0;
+	}
 }
 
 static void calculate_probability(struct Qdisc *sch)
@@ -332,19 +393,25 @@ static void calculate_probability(struct Qdisc *sch)
 	struct pie_sched_data *q = qdisc_priv(sch);
 	u32 qlen = sch->qstats.backlog;	/* queue size in bytes */
 	psched_time_t qdelay = 0;	/* in pschedtime */
-	psched_time_t qdelay_old = q->vars.qdelay;	/* in pschedtime */
+	psched_time_t qdelay_old = 0;	/* in pschedtime */
 	s64 delta = 0;		/* determines the change in probability */
 	u64 oldprob;
 	u64 alpha, beta;
 	u32 power;
 	bool update_prob = true;
 
-	q->vars.qdelay_old = q->vars.qdelay;
+	if (q->params.dq_rate_estimator) {
+		qdelay_old = q->vars.qdelay;
+		q->vars.qdelay_old = q->vars.qdelay;
 
-	if (q->vars.avg_dq_rate > 0)
-		qdelay = (qlen << PIE_SCALE) / q->vars.avg_dq_rate;
-	else
-		qdelay = 0;
+		if (q->vars.avg_dq_rate > 0)
+			qdelay = (qlen << PIE_SCALE) / q->vars.avg_dq_rate;
+		else
+			qdelay = 0;
+	} else {
+		qdelay = q->vars.qdelay;
+		qdelay_old = q->vars.qdelay_old;
+	}
 
 	/* If qdelay is zero and qlen is not, it means qlen is very small, less
 	 * than dequeue_rate, so we do not update probabilty in this round
@@ -430,14 +497,18 @@ static void calculate_probability(struct Qdisc *sch)
 	/* We restart the measurement cycle if the following conditions are met
 	 * 1. If the delay has been low for 2 consecutive Tupdate periods
 	 * 2. Calculated drop probability is zero
-	 * 3. We have atleast one estimate for the avg_dq_rate ie.,
-	 *    is a non-zero value
+	 * 3. If average dq_rate_estimator is enabled, we have atleast one
+	 *    estimate for the avg_dq_rate ie., is a non-zero value
 	 */
 	if ((q->vars.qdelay < q->params.target / 2) &&
 	    (q->vars.qdelay_old < q->params.target / 2) &&
 	    q->vars.prob == 0 &&
-	    q->vars.avg_dq_rate > 0)
+	    (!q->params.dq_rate_estimator || q->vars.avg_dq_rate > 0)) {
 		pie_vars_init(&q->vars);
+	}
+
+	if (!q->params.dq_rate_estimator)
+		q->vars.qdelay_old = qdelay;
 }
 
 static void pie_timer(struct timer_list *t)
@@ -497,7 +568,9 @@ static int pie_dump(struct Qdisc *sch, struct sk_buff *skb)
 	    nla_put_u32(skb, TCA_PIE_ALPHA, q->params.alpha) ||
 	    nla_put_u32(skb, TCA_PIE_BETA, q->params.beta) ||
 	    nla_put_u32(skb, TCA_PIE_ECN, q->params.ecn) ||
-	    nla_put_u32(skb, TCA_PIE_BYTEMODE, q->params.bytemode))
+	    nla_put_u32(skb, TCA_PIE_BYTEMODE, q->params.bytemode) ||
+	    nla_put_u32(skb, TCA_PIE_DQ_RATE_ESTIMATOR,
+			q->params.dq_rate_estimator))
 		goto nla_put_failure;
 
 	return nla_nest_end(skb, opts);
@@ -514,9 +587,6 @@ static int pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
 		.prob		= q->vars.prob,
 		.delay		= ((u32)PSCHED_TICKS2NS(q->vars.qdelay)) /
 				   NSEC_PER_USEC,
-		/* unscale and return dq_rate in bytes per sec */
-		.avg_dq_rate	= q->vars.avg_dq_rate *
-				  (PSCHED_TICKS_PER_SEC) >> PIE_SCALE,
 		.packets_in	= q->stats.packets_in,
 		.overlimit	= q->stats.overlimit,
 		.maxq		= q->stats.maxq,
@@ -524,6 +594,14 @@ static int pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
 		.ecn_mark	= q->stats.ecn_mark,
 	};
 
+	/* avg_dq_rate is only valid if dq_rate_estimator is enabled */
+	st.dq_rate_estimating = q->params.dq_rate_estimator;
+
+	/* unscale and return dq_rate in bytes per sec */
+	if (q->params.dq_rate_estimator)
+		st.avg_dq_rate = q->vars.avg_dq_rate *
+				 (PSCHED_TICKS_PER_SEC) >> PIE_SCALE;
+
 	return gnet_stats_copy_app(d, &st, sizeof(st));
 }