16 files changed, 324 insertions, 23 deletions

diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h
index a2b953b57689..f291a3b0f9e5 100644
--- a/include/net/dropreason-core.h
+++ b/include/net/dropreason-core.h
@@ -30,6 +30,7 @@
 	FN(TCP_OVERWINDOW)		\
 	FN(TCP_OFOMERGE)		\
 	FN(TCP_RFC7323_PAWS)		\
+	FN(TCP_OLD_SEQUENCE)		\
 	FN(TCP_INVALID_SEQUENCE)	\
 	FN(TCP_RESET)			\
 	FN(TCP_INVALID_SYN)		\
@@ -188,6 +189,8 @@ enum skb_drop_reason {
 	 * LINUX_MIB_PAWSESTABREJECTED
 	 */
 	SKB_DROP_REASON_TCP_RFC7323_PAWS,
+	/** @SKB_DROP_REASON_TCP_OLD_SEQUENCE: Old SEQ field (duplicate packet) */
+	SKB_DROP_REASON_TCP_OLD_SEQUENCE,
 	/** @SKB_DROP_REASON_TCP_INVALID_SEQUENCE: Not acceptable SEQ field */
 	SKB_DROP_REASON_TCP_INVALID_SEQUENCE,
 	/** @SKB_DROP_REASON_TCP_RESET: Invalid RST packet */
diff --git a/include/net/dsa.h b/include/net/dsa.h
index d309ee7ed04b..0b9c6aa27047 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -873,8 +873,6 @@ struct dsa_switch_ops {
 	struct phylink_pcs *(*phylink_mac_select_pcs)(struct dsa_switch *ds,
 						      int port,
 						      phy_interface_t iface);
-	int	(*phylink_mac_link_state)(struct dsa_switch *ds, int port,
-					  struct phylink_link_state *state);
 	int	(*phylink_mac_prepare)(struct dsa_switch *ds, int port,
 				       unsigned int mode,
 				       phy_interface_t interface);
@@ -884,7 +882,6 @@ struct dsa_switch_ops {
 	int	(*phylink_mac_finish)(struct dsa_switch *ds, int port,
 				      unsigned int mode,
 				      phy_interface_t interface);
-	void	(*phylink_mac_an_restart)(struct dsa_switch *ds, int port);
 	void	(*phylink_mac_link_down)(struct dsa_switch *ds, int port,
 					 unsigned int mode,
 					 phy_interface_t interface);
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index ed4b6ad3fcac..e8750b4ef7e1 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -52,6 +52,7 @@ struct ip_tunnel_key {
 	u8			tos;		/* TOS for IPv4, TC for IPv6 */
 	u8			ttl;		/* TTL for IPv4, HL for IPv6 */
 	__be32			label;		/* Flow Label for IPv6 */
+	u32			nhid;
 	__be16			tp_src;
 	__be16			tp_dst;
 	__u8			flow_flags;
diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h
index cf0d81be5a96..165e7a03b8e9 100644
--- a/include/net/netfilter/nf_conntrack_expect.h
+++ b/include/net/netfilter/nf_conntrack_expect.h
@@ -100,7 +100,7 @@ nf_ct_expect_find_get(struct net *net,
 struct nf_conntrack_expect *
 nf_ct_find_expectation(struct net *net,
 		       const struct nf_conntrack_zone *zone,
-		       const struct nf_conntrack_tuple *tuple);
+		       const struct nf_conntrack_tuple *tuple, bool unlink);
 
 void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp,
 				u32 portid, int report);
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index f00374718159..7a41c4791536 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -152,7 +152,7 @@ struct netns_ipv4 {
 	u8 sysctl_tcp_abort_on_overflow;
 	u8 sysctl_tcp_fack; /* obsolete */
 	int sysctl_tcp_max_reordering;
-	int sysctl_tcp_adv_win_scale;
+	int sysctl_tcp_adv_win_scale; /* obsolete */
 	u8 sysctl_tcp_dsack;
 	u8 sysctl_tcp_app_win;
 	u8 sysctl_tcp_frto;
diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index 126f9e294389..f1d5cc1fa13b 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -18,9 +18,8 @@
  *
  * API keeps track of in-flight pages, in-order to let API user know
  * when it is safe to dealloactor page_pool object.  Thus, API users
- * must make sure to call page_pool_release_page() when a page is
- * "leaving" the page_pool.  Or call page_pool_put_page() where
- * appropiate.  For maintaining correct accounting.
+ * must call page_pool_put_page() where appropriate and only attach
+ * the page to a page_pool-aware objects, like skbs marked for recycling.
  *
  * API user must only call page_pool_put_page() once on a page, as it
  * will either recycle the page, or in case of elevated refcnt, it
@@ -251,7 +250,6 @@ void page_pool_unlink_napi(struct page_pool *pool);
 void page_pool_destroy(struct page_pool *pool);
 void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *),
 			   struct xdp_mem_info *mem);
-void page_pool_release_page(struct page_pool *pool, struct page *page);
 void page_pool_put_page_bulk(struct page_pool *pool, void **data,
 			     int count);
 #else
@@ -268,10 +266,6 @@ static inline void page_pool_use_xdp_mem(struct page_pool *pool,
 					 struct xdp_mem_info *mem)
 {
 }
-static inline void page_pool_release_page(struct page_pool *pool,
-					  struct page *page)
-{
-}
 
 static inline void page_pool_put_page_bulk(struct page_pool *pool, void **data,
 					   int count)
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index a2ea45c7b53e..139cd09828af 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -866,6 +866,7 @@ struct tc_htb_qopt_offload {
 	u32 parent_classid;
 	u16 classid;
 	u16 qid;
+	u32 quantum;
 	u64 rate;
 	u64 ceil;
 	u8 prio;
diff --git a/include/net/route.h b/include/net/route.h
index 5a5c726472bd..d8d150155195 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -163,7 +163,7 @@ static inline struct rtable *ip_route_output(struct net *net, __be32 daddr,
 }
 
 static inline struct rtable *ip_route_output_ports(struct net *net, struct flowi4 *fl4,
-						   struct sock *sk,
+						   const struct sock *sk,
 						   __be32 daddr, __be32 saddr,
 						   __be16 dport, __be16 sport,
 						   __u8 proto, __u8 tos, int oif)
@@ -309,7 +309,7 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst,
 static inline struct rtable *ip_route_connect(struct flowi4 *fl4, __be32 dst,
 					      __be32 src, int oif, u8 protocol,
 					      __be16 sport, __be16 dport,
-					      struct sock *sk)
+					      const struct sock *sk)
 {
 	struct net *net = sock_net(sk);
 	struct rtable *rt;
@@ -330,7 +330,7 @@ static inline struct rtable *ip_route_connect(struct flowi4 *fl4, __be32 dst,
 static inline struct rtable *ip_route_newports(struct flowi4 *fl4, struct rtable *rt,
 					       __be16 orig_sport, __be16 orig_dport,
 					       __be16 sport, __be16 dport,
-					       struct sock *sk)
+					       const struct sock *sk)
 {
 	if (sport != orig_sport || dport != orig_dport) {
 		fl4->fl4_dport = dport;
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index e92f73bb3198..15be2d96b06d 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -703,7 +703,7 @@ int skb_do_redirect(struct sk_buff *);
 
 static inline bool skb_at_tc_ingress(const struct sk_buff *skb)
 {
-#ifdef CONFIG_NET_CLS_ACT
+#ifdef CONFIG_NET_XGRESS
 	return skb->tc_at_ingress;
 #else
 	return false;
diff --git a/include/net/sock.h b/include/net/sock.h
index 2eb916d1ff64..7ae44bf866af 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1339,6 +1339,7 @@ struct proto {
 
 	struct kmem_cache	*slab;
 	unsigned int		obj_size;
+	unsigned int		ipv6_pinfo_offset;
 	slab_flags_t		slab_flags;
 	unsigned int		useroffset;	/* Usercopy region offset */
 	unsigned int		usersize;	/* Usercopy region size */
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index ca0312b78294..4d324e2a2eef 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -231,6 +231,7 @@ enum switchdev_notifier_type {
 
 	SWITCHDEV_BRPORT_OFFLOADED,
 	SWITCHDEV_BRPORT_UNOFFLOADED,
+	SWITCHDEV_BRPORT_REPLAY,
 };
 
 struct switchdev_notifier_info {
@@ -299,6 +300,11 @@ void switchdev_bridge_port_unoffload(struct net_device *brport_dev,
 				     const void *ctx,
 				     struct notifier_block *atomic_nb,
 				     struct notifier_block *blocking_nb);
+int switchdev_bridge_port_replay(struct net_device *brport_dev,
+				 struct net_device *dev, const void *ctx,
+				 struct notifier_block *atomic_nb,
+				 struct notifier_block *blocking_nb,
+				 struct netlink_ext_ack *extack);
 
 void switchdev_deferred_process(void);
 int switchdev_port_attr_set(struct net_device *dev,
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 0ca972ebd3dd..6ebf54992ffe 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -350,7 +350,6 @@ ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos,
 struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, gfp_t gfp,
 				     bool force_schedule);
 
-void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks);
 static inline void tcp_dec_quickack_mode(struct sock *sk,
 					 const unsigned int pkts)
 {
@@ -606,7 +605,6 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
 		 unsigned int mss_now, gfp_t gfp);
 
 void tcp_send_probe0(struct sock *);
-void tcp_send_partial(struct sock *);
 int tcp_write_wakeup(struct sock *, int mib);
 void tcp_send_fin(struct sock *sk);
 void tcp_send_active_reset(struct sock *sk, gfp_t priority);
@@ -1432,13 +1430,39 @@ void tcp_select_initial_window(const struct sock *sk, int __space,
 			       __u32 *window_clamp, int wscale_ok,
 			       __u8 *rcv_wscale, __u32 init_rcv_wnd);
 
+static inline int __tcp_win_from_space(u8 scaling_ratio, int space)
+{
+	s64 scaled_space = (s64)space * scaling_ratio;
+
+	return scaled_space >> TCP_RMEM_TO_WIN_SCALE;
+}
+
 static inline int tcp_win_from_space(const struct sock *sk, int space)
 {
-	int tcp_adv_win_scale = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_adv_win_scale);
+	return __tcp_win_from_space(tcp_sk(sk)->scaling_ratio, space);
+}
+
+/* inverse of __tcp_win_from_space() */
+static inline int __tcp_space_from_win(u8 scaling_ratio, int win)
+{
+	u64 val = (u64)win << TCP_RMEM_TO_WIN_SCALE;
 
-	return tcp_adv_win_scale <= 0 ?
-		(space>>(-tcp_adv_win_scale)) :
-		space - (space>>tcp_adv_win_scale);
+	do_div(val, scaling_ratio);
+	return val;
+}
+
+static inline int tcp_space_from_win(const struct sock *sk, int win)
+{
+	return __tcp_space_from_win(tcp_sk(sk)->scaling_ratio, win);
+}
+
+static inline void tcp_scaling_ratio_init(struct sock *sk)
+{
+	/* Assume a conservative default of 1200 bytes of payload per 4K page.
+	 * This may be adjusted later in tcp_measure_rcv_mss().
+	 */
+	tcp_sk(sk)->scaling_ratio = (1200 << TCP_RMEM_TO_WIN_SCALE) /
+				    SKB_TRUESIZE(4096);
 }
 
 /* Note: caller must be prepared to deal with negative returns */
diff --git a/include/net/tcx.h b/include/net/tcx.h
new file mode 100644
index 000000000000..264f147953ba
--- /dev/null
+++ b/include/net/tcx.h
@@ -0,0 +1,206 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2023 Isovalent */
+#ifndef __NET_TCX_H
+#define __NET_TCX_H
+
+#include <linux/bpf.h>
+#include <linux/bpf_mprog.h>
+
+#include <net/sch_generic.h>
+
+struct mini_Qdisc;
+
+struct tcx_entry {
+	struct mini_Qdisc __rcu *miniq;
+	struct bpf_mprog_bundle bundle;
+	bool miniq_active;
+	struct rcu_head rcu;
+};
+
+struct tcx_link {
+	struct bpf_link link;
+	struct net_device *dev;
+	u32 location;
+};
+
+static inline void tcx_set_ingress(struct sk_buff *skb, bool ingress)
+{
+#ifdef CONFIG_NET_XGRESS
+	skb->tc_at_ingress = ingress;
+#endif
+}
+
+#ifdef CONFIG_NET_XGRESS
+static inline struct tcx_entry *tcx_entry(struct bpf_mprog_entry *entry)
+{
+	struct bpf_mprog_bundle *bundle = entry->parent;
+
+	return container_of(bundle, struct tcx_entry, bundle);
+}
+
+static inline struct tcx_link *tcx_link(struct bpf_link *link)
+{
+	return container_of(link, struct tcx_link, link);
+}
+
+static inline const struct tcx_link *tcx_link_const(const struct bpf_link *link)
+{
+	return tcx_link((struct bpf_link *)link);
+}
+
+void tcx_inc(void);
+void tcx_dec(void);
+
+static inline void tcx_entry_sync(void)
+{
+	/* bpf_mprog_entry got a/b swapped, therefore ensure that
+	 * there are no inflight users on the old one anymore.
+	 */
+	synchronize_rcu();
+}
+
+static inline void
+tcx_entry_update(struct net_device *dev, struct bpf_mprog_entry *entry,
+		 bool ingress)
+{
+	ASSERT_RTNL();
+	if (ingress)
+		rcu_assign_pointer(dev->tcx_ingress, entry);
+	else
+		rcu_assign_pointer(dev->tcx_egress, entry);
+}
+
+static inline struct bpf_mprog_entry *
+tcx_entry_fetch(struct net_device *dev, bool ingress)
+{
+	ASSERT_RTNL();
+	if (ingress)
+		return rcu_dereference_rtnl(dev->tcx_ingress);
+	else
+		return rcu_dereference_rtnl(dev->tcx_egress);
+}
+
+static inline struct bpf_mprog_entry *tcx_entry_create(void)
+{
+	struct tcx_entry *tcx = kzalloc(sizeof(*tcx), GFP_KERNEL);
+
+	if (tcx) {
+		bpf_mprog_bundle_init(&tcx->bundle);
+		return &tcx->bundle.a;
+	}
+	return NULL;
+}
+
+static inline void tcx_entry_free(struct bpf_mprog_entry *entry)
+{
+	kfree_rcu(tcx_entry(entry), rcu);
+}
+
+static inline struct bpf_mprog_entry *
+tcx_entry_fetch_or_create(struct net_device *dev, bool ingress, bool *created)
+{
+	struct bpf_mprog_entry *entry = tcx_entry_fetch(dev, ingress);
+
+	*created = false;
+	if (!entry) {
+		entry = tcx_entry_create();
+		if (!entry)
+			return NULL;
+		*created = true;
+	}
+	return entry;
+}
+
+static inline void tcx_skeys_inc(bool ingress)
+{
+	tcx_inc();
+	if (ingress)
+		net_inc_ingress_queue();
+	else
+		net_inc_egress_queue();
+}
+
+static inline void tcx_skeys_dec(bool ingress)
+{
+	if (ingress)
+		net_dec_ingress_queue();
+	else
+		net_dec_egress_queue();
+	tcx_dec();
+}
+
+static inline void tcx_miniq_set_active(struct bpf_mprog_entry *entry,
+					const bool active)
+{
+	ASSERT_RTNL();
+	tcx_entry(entry)->miniq_active = active;
+}
+
+static inline bool tcx_entry_is_active(struct bpf_mprog_entry *entry)
+{
+	ASSERT_RTNL();
+	return bpf_mprog_total(entry) || tcx_entry(entry)->miniq_active;
+}
+
+static inline enum tcx_action_base tcx_action_code(struct sk_buff *skb,
+						   int code)
+{
+	switch (code) {
+	case TCX_PASS:
+		skb->tc_index = qdisc_skb_cb(skb)->tc_classid;
+		fallthrough;
+	case TCX_DROP:
+	case TCX_REDIRECT:
+		return code;
+	case TCX_NEXT:
+	default:
+		return TCX_NEXT;
+	}
+}
+#endif /* CONFIG_NET_XGRESS */
+
+#if defined(CONFIG_NET_XGRESS) && defined(CONFIG_BPF_SYSCALL)
+int tcx_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog);
+int tcx_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
+int tcx_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog);
+void tcx_uninstall(struct net_device *dev, bool ingress);
+
+int tcx_prog_query(const union bpf_attr *attr,
+		   union bpf_attr __user *uattr);
+
+static inline void dev_tcx_uninstall(struct net_device *dev)
+{
+	ASSERT_RTNL();
+	tcx_uninstall(dev, true);
+	tcx_uninstall(dev, false);
+}
+#else
+static inline int tcx_prog_attach(const union bpf_attr *attr,
+				  struct bpf_prog *prog)
+{
+	return -EINVAL;
+}
+
+static inline int tcx_link_attach(const union bpf_attr *attr,
+				  struct bpf_prog *prog)
+{
+	return -EINVAL;
+}
+
+static inline int tcx_prog_detach(const union bpf_attr *attr,
+				  struct bpf_prog *prog)
+{
+	return -EINVAL;
+}
+
+static inline int tcx_prog_query(const union bpf_attr *attr,
+				 union bpf_attr __user *uattr)
+{
+	return -EINVAL;
+}
+
+static inline void dev_tcx_uninstall(struct net_device *dev)
+{
+}
+#endif /* CONFIG_NET_XGRESS && CONFIG_BPF_SYSCALL */
+#endif /* __NET_TCX_H */
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index e96a1151ec75..1617af380162 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -52,6 +52,7 @@ struct xdp_sock {
 	struct xsk_buff_pool *pool;
 	u16 queue_id;
 	bool zc;
+	bool sg;
 	enum {
 		XSK_READY = 0,
 		XSK_BOUND,
@@ -67,6 +68,12 @@ struct xdp_sock {
 	u64 rx_dropped;
 	u64 rx_queue_full;
 
+	/* When __xsk_generic_xmit() must return before it sees the EOP descriptor for the current
+	 * packet, the partially built skb is saved here so that packet building can resume in next
+	 * call of __xsk_generic_xmit().
+	 */
+	struct sk_buff *skb;
+
 	struct list_head map_list;
 	/* Protects map_list */
 	spinlock_t map_list_lock;
diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index c243f906ebed..1f6fc8c7a84c 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -89,6 +89,11 @@ static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool)
 	return xp_alloc(pool);
 }
 
+static inline bool xsk_is_eop_desc(struct xdp_desc *desc)
+{
+	return !xp_mb_desc(desc);
+}
+
 /* Returns as many entries as possible up to max. 0 <= N <= max. */
 static inline u32 xsk_buff_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max)
 {
@@ -103,10 +108,45 @@ static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count)
 static inline void xsk_buff_free(struct xdp_buff *xdp)
 {
 	struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
+	struct list_head *xskb_list = &xskb->pool->xskb_list;
+	struct xdp_buff_xsk *pos, *tmp;
+
+	if (likely(!xdp_buff_has_frags(xdp)))
+		goto out;
 
+	list_for_each_entry_safe(pos, tmp, xskb_list, xskb_list_node) {
+		list_del(&pos->xskb_list_node);
+		xp_free(pos);
+	}
+
+	xdp_get_shared_info_from_buff(xdp)->nr_frags = 0;
+out:
 	xp_free(xskb);
 }
 
+static inline void xsk_buff_add_frag(struct xdp_buff *xdp)
+{
+	struct xdp_buff_xsk *frag = container_of(xdp, struct xdp_buff_xsk, xdp);
+
+	list_add_tail(&frag->xskb_list_node, &frag->pool->xskb_list);
+}
+
+static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first)
+{
+	struct xdp_buff_xsk *xskb = container_of(first, struct xdp_buff_xsk, xdp);
+	struct xdp_buff *ret = NULL;
+	struct xdp_buff_xsk *frag;
+
+	frag = list_first_entry_or_null(&xskb->pool->xskb_list,
+					struct xdp_buff_xsk, xskb_list_node);
+	if (frag) {
+		list_del(&frag->xskb_list_node);
+		ret = &frag->xdp;
+	}
+
+	return ret;
+}
+
 static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size)
 {
 	xdp->data = xdp->data_hard_start + XDP_PACKET_HEADROOM;
@@ -241,6 +281,11 @@ static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool)
 	return NULL;
 }
 
+static inline bool xsk_is_eop_desc(struct xdp_desc *desc)
+{
+	return false;
+}
+
 static inline u32 xsk_buff_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max)
 {
 	return 0;
@@ -255,6 +300,15 @@ static inline void xsk_buff_free(struct xdp_buff *xdp)
 {
 }
 
+static inline void xsk_buff_add_frag(struct xdp_buff *xdp)
+{
+}
+
+static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first)
+{
+	return NULL;
+}
+
 static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size)
 {
 }
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index a8d7b8a3688a..b0bdff26fc88 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -29,6 +29,7 @@ struct xdp_buff_xsk {
 	struct xsk_buff_pool *pool;
 	u64 orig_addr;
 	struct list_head free_list_node;
+	struct list_head xskb_list_node;
 };
 
 #define XSK_CHECK_PRIV_TYPE(t) BUILD_BUG_ON(sizeof(t) > offsetofend(struct xdp_buff_xsk, cb))
@@ -54,6 +55,7 @@ struct xsk_buff_pool {
 	struct xdp_umem *umem;
 	struct work_struct work;
 	struct list_head free_list;
+	struct list_head xskb_list;
 	u32 heads_cnt;
 	u16 queue_id;
 
@@ -184,6 +186,11 @@ static inline bool xp_desc_crosses_non_contig_pg(struct xsk_buff_pool *pool,
 	       !(pool->dma_pages[addr >> PAGE_SHIFT] & XSK_NEXT_PG_CONTIG_MASK);
 }
 
+static inline bool xp_mb_desc(struct xdp_desc *desc)
+{
+	return desc->options & XDP_PKT_CONTD;
+}
+
 static inline u64 xp_aligned_extract_addr(struct xsk_buff_pool *pool, u64 addr)
 {
 	return addr & pool->chunk_mask;