Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Alexei Starovoitov says:

====================
pull-request: bpf-next 2023-07-19

We've added 45 non-merge commits during the last 3 day(s) which contain
a total of 71 files changed, 7808 insertions(+), 592 deletions(-).

The main changes are:

1) multi-buffer support in AF_XDP, from Maciej Fijalkowski,
   Magnus Karlsson, Tirthendu Sarkar.

2) BPF link support for tc BPF programs, from Daniel Borkmann.

3) Enable bpf_map_sum_elem_count kfunc for all program types,
   from Anton Protopopov.

4) Add 'owner' field to bpf_rb_node to fix races in shared ownership,
   Dave Marchevsky.

5) Prevent potential skb_header_pointer() misuse, from Alexei Starovoitov.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (45 commits)
  bpf, net: Introduce skb_pointer_if_linear().
  bpf: sync tools/ uapi header with
  selftests/bpf: Add mprog API tests for BPF tcx links
  selftests/bpf: Add mprog API tests for BPF tcx opts
  bpftool: Extend net dump with tcx progs
  libbpf: Add helper macro to clear opts structs
  libbpf: Add link-based API for tcx
  libbpf: Add opts-based attach/detach/query API for tcx
  bpf: Add fd-based tcx multi-prog infra with link support
  bpf: Add generic attach/detach/query API for multi-progs
  selftests/xsk: reset NIC settings to default after running test suite
  selftests/xsk: add test for too many frags
  selftests/xsk: add metadata copy test for multi-buff
  selftests/xsk: add invalid descriptor test for multi-buffer
  selftests/xsk: add unaligned mode test for multi-buffer
  selftests/xsk: add basic multi-buffer test
  selftests/xsk: transmit and receive multi-buffer packets
  xsk: add multi-buffer documentation
  i40e: xsk: add TX multi-buffer support
  ice: xsk: Tx multi-buffer support
  ...
====================

Link: https://lore.kernel.org/r/20230719175424.75717-1-alexei.starovoitov@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

10 files changed, 592 insertions, 232 deletions

diff --git a/net/Kconfig b/net/Kconfig
index 2fb25b534df5..d532ec33f1fe 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -52,6 +52,11 @@ config NET_INGRESS
 config NET_EGRESS
 	bool
 
+config NET_XGRESS
+	select NET_INGRESS
+	select NET_EGRESS
+	bool
+
 config NET_REDIRECT
 	bool
 
diff --git a/net/core/dev.c b/net/core/dev.c
index d6e1b786c5c5..8e7d0cb540cd 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -107,6 +107,7 @@
 #include <net/pkt_cls.h>
 #include <net/checksum.h>
 #include <net/xfrm.h>
+#include <net/tcx.h>
 #include <linux/highmem.h>
 #include <linux/init.h>
 #include <linux/module.h>
@@ -154,7 +155,6 @@
 #include "dev.h"
 #include "net-sysfs.h"
 
-
 static DEFINE_SPINLOCK(ptype_lock);
 struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;
 struct list_head ptype_all __read_mostly;	/* Taps */
@@ -3882,69 +3882,198 @@ int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
 EXPORT_SYMBOL(dev_loopback_xmit);
 
 #ifdef CONFIG_NET_EGRESS
-static struct sk_buff *
-sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
+static struct netdev_queue *
+netdev_tx_queue_mapping(struct net_device *dev, struct sk_buff *skb)
+{
+	int qm = skb_get_queue_mapping(skb);
+
+	return netdev_get_tx_queue(dev, netdev_cap_txqueue(dev, qm));
+}
+
+static bool netdev_xmit_txqueue_skipped(void)
 {
+	return __this_cpu_read(softnet_data.xmit.skip_txqueue);
+}
+
+void netdev_xmit_skip_txqueue(bool skip)
+{
+	__this_cpu_write(softnet_data.xmit.skip_txqueue, skip);
+}
+EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue);
+#endif /* CONFIG_NET_EGRESS */
+
+#ifdef CONFIG_NET_XGRESS
+static int tc_run(struct tcx_entry *entry, struct sk_buff *skb)
+{
+	int ret = TC_ACT_UNSPEC;
 #ifdef CONFIG_NET_CLS_ACT
-	struct mini_Qdisc *miniq = rcu_dereference_bh(dev->miniq_egress);
-	struct tcf_result cl_res;
+	struct mini_Qdisc *miniq = rcu_dereference_bh(entry->miniq);
+	struct tcf_result res;
 
 	if (!miniq)
-		return skb;
+		return ret;
 
-	/* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */
 	tc_skb_cb(skb)->mru = 0;
 	tc_skb_cb(skb)->post_ct = false;
-	mini_qdisc_bstats_cpu_update(miniq, skb);
 
-	switch (tcf_classify(skb, miniq->block, miniq->filter_list, &cl_res, false)) {
+	mini_qdisc_bstats_cpu_update(miniq, skb);
+	ret = tcf_classify(skb, miniq->block, miniq->filter_list, &res, false);
+	/* Only tcf related quirks below. */
+	switch (ret) {
+	case TC_ACT_SHOT:
+		mini_qdisc_qstats_cpu_drop(miniq);
+		break;
 	case TC_ACT_OK:
 	case TC_ACT_RECLASSIFY:
-		skb->tc_index = TC_H_MIN(cl_res.classid);
+		skb->tc_index = TC_H_MIN(res.classid);
 		break;
+	}
+#endif /* CONFIG_NET_CLS_ACT */
+	return ret;
+}
+
+static DEFINE_STATIC_KEY_FALSE(tcx_needed_key);
+
+void tcx_inc(void)
+{
+	static_branch_inc(&tcx_needed_key);
+}
+
+void tcx_dec(void)
+{
+	static_branch_dec(&tcx_needed_key);
+}
+
+static __always_inline enum tcx_action_base
+tcx_run(const struct bpf_mprog_entry *entry, struct sk_buff *skb,
+	const bool needs_mac)
+{
+	const struct bpf_mprog_fp *fp;
+	const struct bpf_prog *prog;
+	int ret = TCX_NEXT;
+
+	if (needs_mac)
+		__skb_push(skb, skb->mac_len);
+	bpf_mprog_foreach_prog(entry, fp, prog) {
+		bpf_compute_data_pointers(skb);
+		ret = bpf_prog_run(prog, skb);
+		if (ret != TCX_NEXT)
+			break;
+	}
+	if (needs_mac)
+		__skb_pull(skb, skb->mac_len);
+	return tcx_action_code(skb, ret);
+}
+
+static __always_inline struct sk_buff *
+sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
+		   struct net_device *orig_dev, bool *another)
+{
+	struct bpf_mprog_entry *entry = rcu_dereference_bh(skb->dev->tcx_ingress);
+	int sch_ret;
+
+	if (!entry)
+		return skb;
+	if (*pt_prev) {
+		*ret = deliver_skb(skb, *pt_prev, orig_dev);
+		*pt_prev = NULL;
+	}
+
+	qdisc_skb_cb(skb)->pkt_len = skb->len;
+	tcx_set_ingress(skb, true);
+
+	if (static_branch_unlikely(&tcx_needed_key)) {
+		sch_ret = tcx_run(entry, skb, true);
+		if (sch_ret != TC_ACT_UNSPEC)
+			goto ingress_verdict;
+	}
+	sch_ret = tc_run(tcx_entry(entry), skb);
+ingress_verdict:
+	switch (sch_ret) {
+	case TC_ACT_REDIRECT:
+		/* skb_mac_header check was done by BPF, so we can safely
+		 * push the L2 header back before redirecting to another
+		 * netdev.
+		 */
+		__skb_push(skb, skb->mac_len);
+		if (skb_do_redirect(skb) == -EAGAIN) {
+			__skb_pull(skb, skb->mac_len);
+			*another = true;
+			break;
+		}
+		*ret = NET_RX_SUCCESS;
+		return NULL;
 	case TC_ACT_SHOT:
-		mini_qdisc_qstats_cpu_drop(miniq);
-		*ret = NET_XMIT_DROP;
-		kfree_skb_reason(skb, SKB_DROP_REASON_TC_EGRESS);
+		kfree_skb_reason(skb, SKB_DROP_REASON_TC_INGRESS);
+		*ret = NET_RX_DROP;
 		return NULL;
+	/* used by tc_run */
 	case TC_ACT_STOLEN:
 	case TC_ACT_QUEUED:
 	case TC_ACT_TRAP:
-		*ret = NET_XMIT_SUCCESS;
 		consume_skb(skb);
+		fallthrough;
+	case TC_ACT_CONSUMED:
+		*ret = NET_RX_SUCCESS;
 		return NULL;
+	}
+
+	return skb;
+}
+
+static __always_inline struct sk_buff *
+sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
+{
+	struct bpf_mprog_entry *entry = rcu_dereference_bh(dev->tcx_egress);
+	int sch_ret;
+
+	if (!entry)
+		return skb;
+
+	/* qdisc_skb_cb(skb)->pkt_len & tcx_set_ingress() was
+	 * already set by the caller.
+	 */
+	if (static_branch_unlikely(&tcx_needed_key)) {
+		sch_ret = tcx_run(entry, skb, false);
+		if (sch_ret != TC_ACT_UNSPEC)
+			goto egress_verdict;
+	}
+	sch_ret = tc_run(tcx_entry(entry), skb);
+egress_verdict:
+	switch (sch_ret) {
 	case TC_ACT_REDIRECT:
 		/* No need to push/pop skb's mac_header here on egress! */
 		skb_do_redirect(skb);
 		*ret = NET_XMIT_SUCCESS;
 		return NULL;
-	default:
-		break;
+	case TC_ACT_SHOT:
+		kfree_skb_reason(skb, SKB_DROP_REASON_TC_EGRESS);
+		*ret = NET_XMIT_DROP;
+		return NULL;
+	/* used by tc_run */
+	case TC_ACT_STOLEN:
+	case TC_ACT_QUEUED:
+	case TC_ACT_TRAP:
+		*ret = NET_XMIT_SUCCESS;
+		return NULL;
 	}
-#endif /* CONFIG_NET_CLS_ACT */
 
 	return skb;
 }
-
-static struct netdev_queue *
-netdev_tx_queue_mapping(struct net_device *dev, struct sk_buff *skb)
-{
-	int qm = skb_get_queue_mapping(skb);
-
-	return netdev_get_tx_queue(dev, netdev_cap_txqueue(dev, qm));
-}
-
-static bool netdev_xmit_txqueue_skipped(void)
+#else
+static __always_inline struct sk_buff *
+sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
+		   struct net_device *orig_dev, bool *another)
 {
-	return __this_cpu_read(softnet_data.xmit.skip_txqueue);
+	return skb;
 }
 
-void netdev_xmit_skip_txqueue(bool skip)
+static __always_inline struct sk_buff *
+sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
 {
-	__this_cpu_write(softnet_data.xmit.skip_txqueue, skip);
+	return skb;
 }
-EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue);
-#endif /* CONFIG_NET_EGRESS */
+#endif /* CONFIG_NET_XGRESS */
 
 #ifdef CONFIG_XPS
 static int __get_xps_queue_idx(struct net_device *dev, struct sk_buff *skb,
@@ -4128,9 +4257,7 @@ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 	skb_update_prio(skb);
 
 	qdisc_pkt_len_init(skb);
-#ifdef CONFIG_NET_CLS_ACT
-	skb->tc_at_ingress = 0;
-#endif
+	tcx_set_ingress(skb, false);
 #ifdef CONFIG_NET_EGRESS
 	if (static_branch_unlikely(&egress_needed_key)) {
 		if (nf_hook_egress_active()) {
@@ -5064,72 +5191,6 @@ int (*br_fdb_test_addr_hook)(struct net_device *dev,
 EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook);
 #endif
 
-static inline struct sk_buff *
-sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
-		   struct net_device *orig_dev, bool *another)
-{
-#ifdef CONFIG_NET_CLS_ACT
-	struct mini_Qdisc *miniq = rcu_dereference_bh(skb->dev->miniq_ingress);
-	struct tcf_result cl_res;
-
-	/* If there's at least one ingress present somewhere (so
-	 * we get here via enabled static key), remaining devices
-	 * that are not configured with an ingress qdisc will bail
-	 * out here.
-	 */
-	if (!miniq)
-		return skb;
-
-	if (*pt_prev) {
-		*ret = deliver_skb(skb, *pt_prev, orig_dev);
-		*pt_prev = NULL;
-	}
-
-	qdisc_skb_cb(skb)->pkt_len = skb->len;
-	tc_skb_cb(skb)->mru = 0;
-	tc_skb_cb(skb)->post_ct = false;
-	skb->tc_at_ingress = 1;
-	mini_qdisc_bstats_cpu_update(miniq, skb);
-
-	switch (tcf_classify(skb, miniq->block, miniq->filter_list, &cl_res, false)) {
-	case TC_ACT_OK:
-	case TC_ACT_RECLASSIFY:
-		skb->tc_index = TC_H_MIN(cl_res.classid);
-		break;
-	case TC_ACT_SHOT:
-		mini_qdisc_qstats_cpu_drop(miniq);
-		kfree_skb_reason(skb, SKB_DROP_REASON_TC_INGRESS);
-		*ret = NET_RX_DROP;
-		return NULL;
-	case TC_ACT_STOLEN:
-	case TC_ACT_QUEUED:
-	case TC_ACT_TRAP:
-		consume_skb(skb);
-		*ret = NET_RX_SUCCESS;
-		return NULL;
-	case TC_ACT_REDIRECT:
-		/* skb_mac_header check was done by cls/act_bpf, so
-		 * we can safely push the L2 header back before
-		 * redirecting to another netdev
-		 */
-		__skb_push(skb, skb->mac_len);
-		if (skb_do_redirect(skb) == -EAGAIN) {
-			__skb_pull(skb, skb->mac_len);
-			*another = true;
-			break;
-		}
-		*ret = NET_RX_SUCCESS;
-		return NULL;
-	case TC_ACT_CONSUMED:
-		*ret = NET_RX_SUCCESS;
-		return NULL;
-	default:
-		break;
-	}
-#endif /* CONFIG_NET_CLS_ACT */
-	return skb;
-}
-
 /**
  *	netdev_is_rx_handler_busy - check if receive handler is registered
  *	@dev: device to check
@@ -10613,6 +10674,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	dev_net_set(dev, &init_net);
 
 	dev->gso_max_size = GSO_LEGACY_MAX_SIZE;
+	dev->xdp_zc_max_segs = 1;
 	dev->gso_max_segs = GSO_MAX_SEGS;
 	dev->gro_max_size = GRO_LEGACY_MAX_SIZE;
 	dev->gso_ipv4_max_size = GSO_LEGACY_MAX_SIZE;
@@ -10834,7 +10896,7 @@ void unregister_netdevice_many_notify(struct list_head *head,
 
 		/* Shutdown queueing discipline. */
 		dev_shutdown(dev);
-
+		dev_tcx_uninstall(dev);
 		dev_xdp_uninstall(dev);
 		bpf_dev_bound_netdev_unregister(dev);
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 06ba0e56e369..797e8f039696 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4345,13 +4345,8 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 	enum bpf_map_type map_type = ri->map_type;
 
-	if (map_type == BPF_MAP_TYPE_XSKMAP) {
-		/* XDP_REDIRECT is not supported AF_XDP yet. */
-		if (unlikely(xdp_buff_has_frags(xdp)))
-			return -EOPNOTSUPP;
-
+	if (map_type == BPF_MAP_TYPE_XSKMAP)
 		return __xdp_do_redirect_xsk(ri, dev, xdp, xdp_prog);
-	}
 
 	return __xdp_do_redirect_frame(ri, dev, xdp_convert_buff_to_frame(xdp),
 				       xdp_prog);
@@ -9312,7 +9307,7 @@ static struct bpf_insn *bpf_convert_tstamp_read(const struct bpf_prog *prog,
 	__u8 value_reg = si->dst_reg;
 	__u8 skb_reg = si->src_reg;
 
-#ifdef CONFIG_NET_CLS_ACT
+#ifdef CONFIG_NET_XGRESS
 	/* If the tstamp_type is read,
 	 * the bpf prog is aware the tstamp could have delivery time.
 	 * Thus, read skb->tstamp as is if tstamp_type_access is true.
@@ -9346,7 +9341,7 @@ static struct bpf_insn *bpf_convert_tstamp_write(const struct bpf_prog *prog,
 	__u8 value_reg = si->src_reg;
 	__u8 skb_reg = si->dst_reg;
 
-#ifdef CONFIG_NET_CLS_ACT
+#ifdef CONFIG_NET_XGRESS
 	/* If the tstamp_type is read,
 	 * the bpf prog is aware the tstamp could have delivery time.
 	 * Thus, write skb->tstamp as is if tstamp_type_access is true.
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index a4270fafdf11..65ef4867fc49 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -25,6 +25,14 @@ netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp,
 		return -EINVAL;
 	}
 
+	if (netdev->xdp_features & NETDEV_XDP_ACT_XSK_ZEROCOPY) {
+		if (nla_put_u32(rsp, NETDEV_A_DEV_XDP_ZC_MAX_SEGS,
+				netdev->xdp_zc_max_segs)) {
+			genlmsg_cancel(rsp, hdr);
+			return -EINVAL;
+		}
+	}
+
 	genlmsg_end(rsp, hdr);
 
 	return 0;
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index 4406d796cc2f..39dcccf0f174 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -51,8 +51,6 @@ static bool is_unsupported(u32 member_offset)
 	return false;
 }
 
-extern struct btf *btf_vmlinux;
-
 static bool bpf_tcp_ca_is_valid_access(int off, int size,
 				       enum bpf_access_type type,
 				       const struct bpf_prog *prog,
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index 4b95cb1ac435..470c70deffe2 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -347,8 +347,7 @@ config NET_SCH_FQ_PIE
 config NET_SCH_INGRESS
 	tristate "Ingress/classifier-action Qdisc"
 	depends on NET_CLS_ACT
-	select NET_INGRESS
-	select NET_EGRESS
+	select NET_XGRESS
 	help
 	  Say Y here if you want to use classifiers for incoming and/or outgoing
 	  packets. This qdisc doesn't do anything else besides running classifiers,
@@ -679,6 +678,7 @@ config NET_EMATCH_IPT
 config NET_CLS_ACT
 	bool "Actions"
 	select NET_CLS
+	select NET_XGRESS
 	help
 	  Say Y here if you want to use traffic control actions. Actions
 	  get attached to classifiers and are invoked after a successful
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index e43a45499372..04e886f6cee4 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -13,6 +13,7 @@
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
 #include <net/pkt_cls.h>
+#include <net/tcx.h>
 
 struct ingress_sched_data {
 	struct tcf_block *block;
@@ -78,6 +79,8 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt,
 {
 	struct ingress_sched_data *q = qdisc_priv(sch);
 	struct net_device *dev = qdisc_dev(sch);
+	struct bpf_mprog_entry *entry;
+	bool created;
 	int err;
 
 	if (sch->parent != TC_H_INGRESS)
@@ -85,7 +88,13 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt,
 
 	net_inc_ingress_queue();
 
-	mini_qdisc_pair_init(&q->miniqp, sch, &dev->miniq_ingress);
+	entry = tcx_entry_fetch_or_create(dev, true, &created);
+	if (!entry)
+		return -ENOMEM;
+	tcx_miniq_set_active(entry, true);
+	mini_qdisc_pair_init(&q->miniqp, sch, &tcx_entry(entry)->miniq);
+	if (created)
+		tcx_entry_update(dev, entry, true);
 
 	q->block_info.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
 	q->block_info.chain_head_change = clsact_chain_head_change;
@@ -103,11 +112,22 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt,
 static void ingress_destroy(struct Qdisc *sch)
 {
 	struct ingress_sched_data *q = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
+	struct bpf_mprog_entry *entry = rtnl_dereference(dev->tcx_ingress);
 
 	if (sch->parent != TC_H_INGRESS)
 		return;
 
 	tcf_block_put_ext(q->block, sch, &q->block_info);
+
+	if (entry) {
+		tcx_miniq_set_active(entry, false);
+		if (!tcx_entry_is_active(entry)) {
+			tcx_entry_update(dev, NULL, false);
+			tcx_entry_free(entry);
+		}
+	}
+
 	net_dec_ingress_queue();
 }
 
@@ -223,6 +243,8 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt,
 {
 	struct clsact_sched_data *q = qdisc_priv(sch);
 	struct net_device *dev = qdisc_dev(sch);
+	struct bpf_mprog_entry *entry;
+	bool created;
 	int err;
 
 	if (sch->parent != TC_H_CLSACT)
@@ -231,7 +253,13 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt,
 	net_inc_ingress_queue();
 	net_inc_egress_queue();
 
-	mini_qdisc_pair_init(&q->miniqp_ingress, sch, &dev->miniq_ingress);
+	entry = tcx_entry_fetch_or_create(dev, true, &created);
+	if (!entry)
+		return -ENOMEM;
+	tcx_miniq_set_active(entry, true);
+	mini_qdisc_pair_init(&q->miniqp_ingress, sch, &tcx_entry(entry)->miniq);
+	if (created)
+		tcx_entry_update(dev, entry, true);
 
 	q->ingress_block_info.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
 	q->ingress_block_info.chain_head_change = clsact_chain_head_change;
@@ -244,7 +272,13 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt,
 
 	mini_qdisc_pair_block_init(&q->miniqp_ingress, q->ingress_block);
 
-	mini_qdisc_pair_init(&q->miniqp_egress, sch, &dev->miniq_egress);
+	entry = tcx_entry_fetch_or_create(dev, false, &created);
+	if (!entry)
+		return -ENOMEM;
+	tcx_miniq_set_active(entry, true);
+	mini_qdisc_pair_init(&q->miniqp_egress, sch, &tcx_entry(entry)->miniq);
+	if (created)
+		tcx_entry_update(dev, entry, false);
 
 	q->egress_block_info.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS;
 	q->egress_block_info.chain_head_change = clsact_chain_head_change;
@@ -256,12 +290,31 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt,
 static void clsact_destroy(struct Qdisc *sch)
 {
 	struct clsact_sched_data *q = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
+	struct bpf_mprog_entry *ingress_entry = rtnl_dereference(dev->tcx_ingress);
+	struct bpf_mprog_entry *egress_entry = rtnl_dereference(dev->tcx_egress);
 
 	if (sch->parent != TC_H_CLSACT)
 		return;
 
-	tcf_block_put_ext(q->egress_block, sch, &q->egress_block_info);
 	tcf_block_put_ext(q->ingress_block, sch, &q->ingress_block_info);
+	tcf_block_put_ext(q->egress_block, sch, &q->egress_block_info);
+
+	if (ingress_entry) {
+		tcx_miniq_set_active(ingress_entry, false);
+		if (!tcx_entry_is_active(ingress_entry)) {
+			tcx_entry_update(dev, NULL, true);
+			tcx_entry_free(ingress_entry);
+		}
+	}
+
+	if (egress_entry) {
+		tcx_miniq_set_active(egress_entry, false);
+		if (!tcx_entry_is_active(egress_entry)) {
+			tcx_entry_update(dev, NULL, false);
+			tcx_entry_free(egress_entry);
+		}
+	}
 
 	net_dec_ingress_queue();
 	net_dec_egress_queue();
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 31dca4ecb2c5..4f1e0599146e 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -135,14 +135,14 @@ int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool,
 	return 0;
 }
 
-static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
+static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff_xsk *xskb, u32 len,
+			u32 flags)
 {
-	struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
 	u64 addr;
 	int err;
 
 	addr = xp_get_handle(xskb);
-	err = xskq_prod_reserve_desc(xs->rx, addr, len);
+	err = xskq_prod_reserve_desc(xs->rx, addr, len, flags);
 	if (err) {
 		xs->rx_queue_full++;
 		return err;
@@ -152,48 +152,138 @@ static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 	return 0;
 }
 
-static void xsk_copy_xdp(struct xdp_buff *to, struct xdp_buff *from, u32 len)
+static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 {
-	void *from_buf, *to_buf;
-	u32 metalen;
+	struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
+	u32 frags = xdp_buff_has_frags(xdp);
+	struct xdp_buff_xsk *pos, *tmp;
+	struct list_head *xskb_list;
+	u32 contd = 0;
+	int err;
 
-	if (unlikely(xdp_data_meta_unsupported(from))) {
-		from_buf = from->data;
-		to_buf = to->data;
-		metalen = 0;
-	} else {
-		from_buf = from->data_meta;
-		metalen = from->data - from->data_meta;
-		to_buf = to->data - metalen;
+	if (frags)
+		contd = XDP_PKT_CONTD;
+
+	err = __xsk_rcv_zc(xs, xskb, len, contd);
+	if (err || likely(!frags))
+		goto out;
+
+	xskb_list = &xskb->pool->xskb_list;
+	list_for_each_entry_safe(pos, tmp, xskb_list, xskb_list_node) {
+		if (list_is_singular(xskb_list))
+			contd = 0;
+		len = pos->xdp.data_end - pos->xdp.data;
+		err = __xsk_rcv_zc(xs, pos, len, contd);
+		if (err)
+			return err;
+		list_del(&pos->xskb_list_node);
 	}
 
-	memcpy(to_buf, from_buf, len + metalen);
+out:
+	return err;
 }
 
-static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
+static void *xsk_copy_xdp_start(struct xdp_buff *from)
 {
+	if (unlikely(xdp_data_meta_unsupported(from)))
+		return from->data;
+	else
+		return from->data_meta;
+}
+
+static u32 xsk_copy_xdp(void *to, void **from, u32 to_len,
+			u32 *from_len, skb_frag_t **frag, u32 rem)
+{
+	u32 copied = 0;
+
+	while (1) {
+		u32 copy_len = min_t(u32, *from_len, to_len);
+
+		memcpy(to, *from, copy_len);
+		copied += copy_len;
+		if (rem == copied)
+			return copied;
+
+		if (*from_len == copy_len) {
+			*from = skb_frag_address(*frag);
+			*from_len = skb_frag_size((*frag)++);
+		} else {
+			*from += copy_len;
+			*from_len -= copy_len;
+		}
+		if (to_len == copy_len)
+			return copied;
+
+		to_len -= copy_len;
+		to += copy_len;
+	}
+}
+
+static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
+{
+	u32 frame_size = xsk_pool_get_rx_frame_size(xs->pool);
+	void *copy_from = xsk_copy_xdp_start(xdp), *copy_to;
+	u32 from_len, meta_len, rem, num_desc;
+	struct xdp_buff_xsk *xskb;
 	struct xdp_buff *xsk_xdp;
-	int err;
-	u32 len;
+	skb_frag_t *frag;
 
-	len = xdp->data_end - xdp->data;
-	if (len > xsk_pool_get_rx_frame_size(xs->pool)) {
-		xs->rx_dropped++;
-		return -ENOSPC;
+	from_len = xdp->data_end - copy_from;
+	meta_len = xdp->data - copy_from;
+	rem = len + meta_len;
+
+	if (len <= frame_size && !xdp_buff_has_frags(xdp)) {
+		int err;
+
+		xsk_xdp = xsk_buff_alloc(xs->pool);
+		if (!xsk_xdp) {
+			xs->rx_dropped++;
+			return -ENOMEM;
+		}
+		memcpy(xsk_xdp->data - meta_len, copy_from, rem);
+		xskb = container_of(xsk_xdp, struct xdp_buff_xsk, xdp);
+		err = __xsk_rcv_zc(xs, xskb, len, 0);
+		if (err) {
+			xsk_buff_free(xsk_xdp);
+			return err;
+		}
+
+		return 0;
 	}
 
-	xsk_xdp = xsk_buff_alloc(xs->pool);
-	if (!xsk_xdp) {
+	num_desc = (len - 1) / frame_size + 1;
+
+	if (!xsk_buff_can_alloc(xs->pool, num_desc)) {
 		xs->rx_dropped++;
 		return -ENOMEM;
 	}
+	if (xskq_prod_nb_free(xs->rx, num_desc) < num_desc) {
+		xs->rx_queue_full++;
+		return -ENOBUFS;
+	}
 
-	xsk_copy_xdp(xsk_xdp, xdp, len);
-	err = __xsk_rcv_zc(xs, xsk_xdp, len);
-	if (err) {
-		xsk_buff_free(xsk_xdp);
-		return err;
+	if (xdp_buff_has_frags(xdp)) {
+		struct skb_shared_info *sinfo;
+
+		sinfo = xdp_get_shared_info_from_buff(xdp);
+		frag =  &sinfo->frags[0];
 	}
+
+	do {
+		u32 to_len = frame_size + meta_len;
+		u32 copied;
+
+		xsk_xdp = xsk_buff_alloc(xs->pool);
+		copy_to = xsk_xdp->data - meta_len;
+
+		copied = xsk_copy_xdp(copy_to, &copy_from, to_len, &from_len, &frag, rem);
+		rem -= copied;
+
+		xskb = container_of(xsk_xdp, struct xdp_buff_xsk, xdp);
+		__xsk_rcv_zc(xs, xskb, copied - meta_len, rem ? XDP_PKT_CONTD : 0);
+		meta_len = 0;
+	} while (rem);
+
 	return 0;
 }
 
@@ -215,7 +305,7 @@ static bool xsk_is_bound(struct xdp_sock *xs)
 	return false;
 }
 
-static int xsk_rcv_check(struct xdp_sock *xs, struct xdp_buff *xdp)
+static int xsk_rcv_check(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 {
 	if (!xsk_is_bound(xs))
 		return -ENXIO;
@@ -223,6 +313,11 @@ static int xsk_rcv_check(struct xdp_sock *xs, struct xdp_buff *xdp)
 	if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index)
 		return -EINVAL;
 
+	if (len > xsk_pool_get_rx_frame_size(xs->pool) && !xs->sg) {
+		xs->rx_dropped++;
+		return -ENOSPC;
+	}
+
 	sk_mark_napi_id_once_xdp(&xs->sk, xdp);
 	return 0;
 }
@@ -236,12 +331,13 @@ static void xsk_flush(struct xdp_sock *xs)
 
 int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 {
+	u32 len = xdp_get_buff_len(xdp);
 	int err;
 
 	spin_lock_bh(&xs->rx_lock);
-	err = xsk_rcv_check(xs, xdp);
+	err = xsk_rcv_check(xs, xdp, len);
 	if (!err) {
-		err = __xsk_rcv(xs, xdp);
+		err = __xsk_rcv(xs, xdp, len);
 		xsk_flush(xs);
 	}
 	spin_unlock_bh(&xs->rx_lock);
@@ -250,19 +346,19 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 
 static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 {
+	u32 len = xdp_get_buff_len(xdp);
 	int err;
-	u32 len;
 
-	err = xsk_rcv_check(xs, xdp);
+	err = xsk_rcv_check(xs, xdp, len);
 	if (err)
 		return err;
 
 	if (xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL) {
 		len = xdp->data_end - xdp->data;
-		return __xsk_rcv_zc(xs, xdp, len);
+		return xsk_rcv_zc(xs, xdp, len);
 	}
 
-	err = __xsk_rcv(xs, xdp);
+	err = __xsk_rcv(xs, xdp, len);
 	if (!err)
 		xdp_return_buff(xdp);
 	return err;
@@ -321,7 +417,8 @@ bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc)
 	rcu_read_lock();
 	list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) {
 		if (!xskq_cons_peek_desc(xs->tx, desc, pool)) {
-			xs->tx->queue_empty_descs++;
+			if (xskq_has_descs(xs->tx))
+				xskq_cons_release(xs->tx);
 			continue;
 		}
 
@@ -408,37 +505,91 @@ static int xsk_wakeup(struct xdp_sock *xs, u8 flags)
 	return dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, flags);
 }
 
-static void xsk_destruct_skb(struct sk_buff *skb)
+static int xsk_cq_reserve_addr_locked(struct xdp_sock *xs, u64 addr)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&xs->pool->cq_lock, flags);
+	ret = xskq_prod_reserve_addr(xs->pool->cq, addr);
+	spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
+
+	return ret;
+}
+
+static void xsk_cq_submit_locked(struct xdp_sock *xs, u32 n)
 {
-	u64 addr = (u64)(long)skb_shinfo(skb)->destructor_arg;
-	struct xdp_sock *xs = xdp_sk(skb->sk);
 	unsigned long flags;
 
 	spin_lock_irqsave(&xs->pool->cq_lock, flags);
-	xskq_prod_submit_addr(xs->pool->cq, addr);
+	xskq_prod_submit_n(xs->pool->cq, n);
 	spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
+}
+
+static void xsk_cq_cancel_locked(struct xdp_sock *xs, u32 n)
+{
+	unsigned long flags;
 
+	spin_lock_irqsave(&xs->pool->cq_lock, flags);
+	xskq_prod_cancel_n(xs->pool->cq, n);
+	spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
+}
+
+static u32 xsk_get_num_desc(struct sk_buff *skb)
+{
+	return skb ? (long)skb_shinfo(skb)->destructor_arg : 0;
+}
+
+static void xsk_destruct_skb(struct sk_buff *skb)
+{
+	xsk_cq_submit_locked(xdp_sk(skb->sk), xsk_get_num_desc(skb));
 	sock_wfree(skb);
 }
 
+static void xsk_set_destructor_arg(struct sk_buff *skb)
+{
+	long num = xsk_get_num_desc(xdp_sk(skb->sk)->skb) + 1;
+
+	skb_shinfo(skb)->destructor_arg = (void *)num;
+}
+
+static void xsk_consume_skb(struct sk_buff *skb)
+{
+	struct xdp_sock *xs = xdp_sk(skb->sk);
+
+	skb->destructor = sock_wfree;
+	xsk_cq_cancel_locked(xs, xsk_get_num_desc(skb));
+	/* Free skb without triggering the perf drop trace */
+	consume_skb(skb);
+	xs->skb = NULL;
+}
+
+static void xsk_drop_skb(struct sk_buff *skb)
+{
+	xdp_sk(skb->sk)->tx->invalid_descs += xsk_get_num_desc(skb);
+	xsk_consume_skb(skb);
+}
+
 static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs,
 					      struct xdp_desc *desc)
 {
 	struct xsk_buff_pool *pool = xs->pool;
 	u32 hr, len, ts, offset, copy, copied;
-	struct sk_buff *skb;
+	struct sk_buff *skb = xs->skb;
 	struct page *page;
 	void *buffer;
 	int err, i;
 	u64 addr;
 
-	hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(xs->dev->needed_headroom));
+	if (!skb) {
+		hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(xs->dev->needed_headroom));
 
-	skb = sock_alloc_send_skb(&xs->sk, hr, 1, &err);
-	if (unlikely(!skb))
-		return ERR_PTR(err);
+		skb = sock_alloc_send_skb(&xs->sk, hr, 1, &err);
+		if (unlikely(!skb))
+			return ERR_PTR(err);
 
-	skb_reserve(skb, hr);
+		skb_reserve(skb, hr);
+	}
 
 	addr = desc->addr;
 	len = desc->len;
@@ -448,7 +599,10 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs,
 	offset = offset_in_page(buffer);
 	addr = buffer - pool->addrs;
 
-	for (copied = 0, i = 0; copied < len; i++) {
+	for (copied = 0, i = skb_shinfo(skb)->nr_frags; copied < len; i++) {
+		if (unlikely(i >= MAX_SKB_FRAGS))
+			return ERR_PTR(-EFAULT);
+
 		page = pool->umem->pgs[addr >> PAGE_SHIFT];
 		get_page(page);
 
@@ -473,43 +627,77 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 				     struct xdp_desc *desc)
 {
 	struct net_device *dev = xs->dev;
-	struct sk_buff *skb;
+	struct sk_buff *skb = xs->skb;
+	int err;
 
 	if (dev->priv_flags & IFF_TX_SKB_NO_LINEAR) {
 		skb = xsk_build_skb_zerocopy(xs, desc);
-		if (IS_ERR(skb))
-			return skb;
+		if (IS_ERR(skb)) {
+			err = PTR_ERR(skb);
+			goto free_err;
+		}
 	} else {
 		u32 hr, tr, len;
 		void *buffer;
-		int err;
 
-		hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(dev->needed_headroom));
-		tr = dev->needed_tailroom;
+		buffer = xsk_buff_raw_get_data(xs->pool, desc->addr);
 		len = desc->len;
 
-		skb = sock_alloc_send_skb(&xs->sk, hr + len + tr, 1, &err);
-		if (unlikely(!skb))
-			return ERR_PTR(err);
+		if (!skb) {
+			hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(dev->needed_headroom));
+			tr = dev->needed_tailroom;
+			skb = sock_alloc_send_skb(&xs->sk, hr + len + tr, 1, &err);
+			if (unlikely(!skb))
+				goto free_err;
 
-		skb_reserve(skb, hr);
-		skb_put(skb, len);
+			skb_reserve(skb, hr);
+			skb_put(skb, len);
 
-		buffer = xsk_buff_raw_get_data(xs->pool, desc->addr);
-		err = skb_store_bits(skb, 0, buffer, len);
-		if (unlikely(err)) {
-			kfree_skb(skb);
-			return ERR_PTR(err);
+			err = skb_store_bits(skb, 0, buffer, len);
+			if (unlikely(err))
+				goto free_err;
+		} else {
+			int nr_frags = skb_shinfo(skb)->nr_frags;
+			struct page *page;
+			u8 *vaddr;
+
+			if (unlikely(nr_frags == (MAX_SKB_FRAGS - 1) && xp_mb_desc(desc))) {
+				err = -EFAULT;
+				goto free_err;
+			}
+
+			page = alloc_page(xs->sk.sk_allocation);
+			if (unlikely(!page)) {
+				err = -EAGAIN;
+				goto free_err;
+			}
+
+			vaddr = kmap_local_page(page);
+			memcpy(vaddr, buffer, len);
+			kunmap_local(vaddr);
+
+			skb_add_rx_frag(skb, nr_frags, page, 0, len, 0);
 		}
 	}
 
 	skb->dev = dev;
 	skb->priority = xs->sk.sk_priority;
 	skb->mark = xs->sk.sk_mark;
-	skb_shinfo(skb)->destructor_arg = (void *)(long)desc->addr;
 	skb->destructor = xsk_destruct_skb;
+	xsk_set_destructor_arg(skb);
 
 	return skb;
+
+free_err:
+	if (err == -EAGAIN) {
+		xsk_cq_cancel_locked(xs, 1);
+	} else {
+		xsk_set_destructor_arg(skb);
+		xsk_drop_skb(skb);
+		xskq_cons_release(xs->tx);
+	}
+
+	return ERR_PTR(err);
 }
 
 static int __xsk_generic_xmit(struct sock *sk)
@@ -519,7 +707,6 @@ static int __xsk_generic_xmit(struct sock *sk)
 	bool sent_frame = false;
 	struct xdp_desc desc;
 	struct sk_buff *skb;
-	unsigned long flags;
 	int err = 0;
 
 	mutex_lock(&xs->mutex);
@@ -544,47 +731,51 @@ static int __xsk_generic_xmit(struct sock *sk)
 		 * if there is space in it. This avoids having to implement
 		 * any buffering in the Tx path.
 		 */
-		spin_lock_irqsave(&xs->pool->cq_lock, flags);
-		if (xskq_prod_reserve(xs->pool->cq)) {
-			spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
+		if (xsk_cq_reserve_addr_locked(xs, desc.addr))
 			goto out;
-		}
-		spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
 
 		skb = xsk_build_skb(xs, &desc);
 		if (IS_ERR(skb)) {
 			err = PTR_ERR(skb);
-			spin_lock_irqsave(&xs->pool->cq_lock, flags);
-			xskq_prod_cancel(xs->pool->cq);
-			spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
-			goto out;
+			if (err == -EAGAIN)
+				goto out;
+			err = 0;
+			continue;
+		}
+
+		xskq_cons_release(xs->tx);
+
+		if (xp_mb_desc(&desc)) {
+			xs->skb = skb;
+			continue;
 		}
 
 		err = __dev_direct_xmit(skb, xs->queue_id);
 		if  (err == NETDEV_TX_BUSY) {
 			/* Tell user-space to retry the send */
-			skb->destructor = sock_wfree;
-			spin_lock_irqsave(&xs->pool->cq_lock, flags);
-			xskq_prod_cancel(xs->pool->cq);
-			spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
-			/* Free skb without triggering the perf drop trace */
-			consume_skb(skb);
+			xskq_cons_cancel_n(xs->tx, xsk_get_num_desc(skb));
+			xsk_consume_skb(skb);
 			err = -EAGAIN;
 			goto out;
 		}
 
-		xskq_cons_release(xs->tx);
 		/* Ignore NET_XMIT_CN as packet might have been sent */
 		if (err == NET_XMIT_DROP) {
 			/* SKB completed but not sent */
 			err = -EBUSY;
+			xs->skb = NULL;
 			goto out;
 		}
 
 		sent_frame = true;
+		xs->skb = NULL;
 	}
 
-	xs->tx->queue_empty_descs++;
+	if (xskq_has_descs(xs->tx)) {
+		if (xs->skb)
+			xsk_drop_skb(xs->skb);
+		xskq_cons_release(xs->tx);
+	}
 
 out:
 	if (sent_frame)
@@ -834,6 +1025,9 @@ static int xsk_release(struct socket *sock)
 
 	net = sock_net(sk);
 
+	if (xs->skb)
+		xsk_drop_skb(xs->skb);
+
 	mutex_lock(&net->xdp.lock);
 	sk_del_node_init_rcu(sk);
 	mutex_unlock(&net->xdp.lock);
@@ -897,7 +1091,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 
 	flags = sxdp->sxdp_flags;
 	if (flags & ~(XDP_SHARED_UMEM | XDP_COPY | XDP_ZEROCOPY |
-		      XDP_USE_NEED_WAKEUP))
+		      XDP_USE_NEED_WAKEUP | XDP_USE_SG))
 		return -EINVAL;
 
 	bound_dev_if = READ_ONCE(sk->sk_bound_dev_if);
@@ -929,7 +1123,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 		struct socket *sock;
 
 		if ((flags & XDP_COPY) || (flags & XDP_ZEROCOPY) ||
-		    (flags & XDP_USE_NEED_WAKEUP)) {
+		    (flags & XDP_USE_NEED_WAKEUP) || (flags & XDP_USE_SG)) {
 			/* Cannot specify flags for shared sockets. */
 			err = -EINVAL;
 			goto out_unlock;
@@ -1028,6 +1222,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 
 	xs->dev = dev;
 	xs->zc = xs->umem->zc;
+	xs->sg = !!(flags & XDP_USE_SG);
 	xs->queue_id = qid;
 	xp_add_xsk(xs->pool, xs);
 
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 26f6d304451e..b3f7b310811e 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -86,6 +86,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 	pool->umem = umem;
 	pool->addrs = umem->addrs;
 	INIT_LIST_HEAD(&pool->free_list);
+	INIT_LIST_HEAD(&pool->xskb_list);
 	INIT_LIST_HEAD(&pool->xsk_tx_list);
 	spin_lock_init(&pool->xsk_tx_list_lock);
 	spin_lock_init(&pool->cq_lock);
@@ -99,6 +100,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 		xskb->pool = pool;
 		xskb->xdp.frame_sz = umem->chunk_size - umem->headroom;
 		INIT_LIST_HEAD(&xskb->free_list_node);
+		INIT_LIST_HEAD(&xskb->xskb_list_node);
 		if (pool->unaligned)
 			pool->free_heads[i] = xskb;
 		else
@@ -187,6 +189,11 @@ int xp_assign_dev(struct xsk_buff_pool *pool,
 		goto err_unreg_pool;
 	}
 
+	if (netdev->xdp_zc_max_segs == 1 && (flags & XDP_USE_SG)) {
+		err = -EOPNOTSUPP;
+		goto err_unreg_pool;
+	}
+
 	bpf.command = XDP_SETUP_XSK_POOL;
 	bpf.xsk.pool = pool;
 	bpf.xsk.queue_id = queue_id;
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 6d40a77fccbe..13354a1e4280 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -48,6 +48,11 @@ struct xsk_queue {
 	size_t ring_vmalloc_size;
 };
 
+struct parsed_desc {
+	u32 mb;
+	u32 valid;
+};
+
 /* The structure of the shared state of the rings are a simple
  * circular buffer, as outlined in
  * Documentation/core-api/circular-buffers.rst. For the Rx and
@@ -130,18 +135,26 @@ static inline bool xskq_cons_read_addr_unchecked(struct xsk_queue *q, u64 *addr)
 	return false;
 }
 
+static inline bool xp_unused_options_set(u32 options)
+{
+	return options & ~XDP_PKT_CONTD;
+}
+
 static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool,
 					    struct xdp_desc *desc)
 {
 	u64 offset = desc->addr & (pool->chunk_size - 1);
 
+	if (!desc->len)
+		return false;
+
 	if (offset + desc->len > pool->chunk_size)
 		return false;
 
 	if (desc->addr >= pool->addrs_cnt)
 		return false;
 
-	if (desc->options)
+	if (xp_unused_options_set(desc->options))
 		return false;
 	return true;
 }
@@ -151,6 +164,9 @@ static inline bool xp_unaligned_validate_desc(struct xsk_buff_pool *pool,
 {
 	u64 addr = xp_unaligned_add_offset_to_addr(desc->addr);
 
+	if (!desc->len)
+		return false;
+
 	if (desc->len > pool->chunk_size)
 		return false;
 
@@ -158,7 +174,7 @@ static inline bool xp_unaligned_validate_desc(struct xsk_buff_pool *pool,
 	    xp_desc_crosses_non_contig_pg(pool, addr, desc->len))
 		return false;
 
-	if (desc->options)
+	if (xp_unused_options_set(desc->options))
 		return false;
 	return true;
 }
@@ -170,6 +186,11 @@ static inline bool xp_validate_desc(struct xsk_buff_pool *pool,
 		xp_aligned_validate_desc(pool, desc);
 }
 
+static inline bool xskq_has_descs(struct xsk_queue *q)
+{
+	return q->cached_cons != q->cached_prod;
+}
+
 static inline bool xskq_cons_is_valid_desc(struct xsk_queue *q,
 					   struct xdp_desc *d,
 					   struct xsk_buff_pool *pool)
@@ -185,17 +206,15 @@ static inline bool xskq_cons_read_desc(struct xsk_queue *q,
 				       struct xdp_desc *desc,
 				       struct xsk_buff_pool *pool)
 {
-	while (q->cached_cons != q->cached_prod) {
+	if (q->cached_cons != q->cached_prod) {
 		struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring;
 		u32 idx = q->cached_cons & q->ring_mask;
 
 		*desc = ring->desc[idx];
-		if (xskq_cons_is_valid_desc(q, desc, pool))
-			return true;
-
-		q->cached_cons++;
+		return xskq_cons_is_valid_desc(q, desc, pool);
 	}
 
+	q->queue_empty_descs++;
 	return false;
 }
 
@@ -204,30 +223,52 @@ static inline void xskq_cons_release_n(struct xsk_queue *q, u32 cnt)
 	q->cached_cons += cnt;
 }
 
-static inline u32 xskq_cons_read_desc_batch(struct xsk_queue *q, struct xsk_buff_pool *pool,
-					    u32 max)
+static inline void parse_desc(struct xsk_queue *q, struct xsk_buff_pool *pool,
+			      struct xdp_desc *desc, struct parsed_desc *parsed)
+{
+	parsed->valid = xskq_cons_is_valid_desc(q, desc, pool);
+	parsed->mb = xp_mb_desc(desc);
+}
+
+static inline
+u32 xskq_cons_read_desc_batch(struct xsk_queue *q, struct xsk_buff_pool *pool,
+			      u32 max)
 {
 	u32 cached_cons = q->cached_cons, nb_entries = 0;
 	struct xdp_desc *descs = pool->tx_descs;
+	u32 total_descs = 0, nr_frags = 0;
 
+	/* track first entry, if stumble upon *any* invalid descriptor, rewind
+	 * current packet that consists of frags and stop the processing
+	 */
 	while (cached_cons != q->cached_prod && nb_entries < max) {
 		struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring;
 		u32 idx = cached_cons & q->ring_mask;
+		struct parsed_desc parsed;
 
 		descs[nb_entries] = ring->desc[idx];
-		if (unlikely(!xskq_cons_is_valid_desc(q, &descs[nb_entries], pool))) {
-			/* Skip the entry */
-			cached_cons++;
-			continue;
+		cached_cons++;
+		parse_desc(q, pool, &descs[nb_entries], &parsed);
+		if (unlikely(!parsed.valid))
+			break;
+
+		if (likely(!parsed.mb)) {
+			total_descs += (nr_frags + 1);
+			nr_frags = 0;
+		} else {
+			nr_frags++;
+			if (nr_frags == pool->netdev->xdp_zc_max_segs) {
+				nr_frags = 0;
+				break;
+			}
 		}
-
 		nb_entries++;
-		cached_cons++;
 	}
 
+	cached_cons -= nr_frags;
 	/* Release valid plus any invalid entries */
 	xskq_cons_release_n(q, cached_cons - q->cached_cons);
-	return nb_entries;
+	return total_descs;
 }
 
 /* Functions for consumers */
@@ -292,6 +333,11 @@ static inline void xskq_cons_release(struct xsk_queue *q)
 	q->cached_cons++;
 }
 
+static inline void xskq_cons_cancel_n(struct xsk_queue *q, u32 cnt)
+{
+	q->cached_cons -= cnt;
+}
+
 static inline u32 xskq_cons_present_entries(struct xsk_queue *q)
 {
 	/* No barriers needed since data is not accessed */
@@ -319,9 +365,9 @@ static inline bool xskq_prod_is_full(struct xsk_queue *q)
 	return xskq_prod_nb_free(q, 1) ? false : true;
 }
 
-static inline void xskq_prod_cancel(struct xsk_queue *q)
+static inline void xskq_prod_cancel_n(struct xsk_queue *q, u32 cnt)
 {
-	q->cached_prod--;
+	q->cached_prod -= cnt;
 }
 
 static inline int xskq_prod_reserve(struct xsk_queue *q)
@@ -360,7 +406,7 @@ static inline void xskq_prod_write_addr_batch(struct xsk_queue *q, struct xdp_de
 }
 
 static inline int xskq_prod_reserve_desc(struct xsk_queue *q,
-					 u64 addr, u32 len)
+					 u64 addr, u32 len, u32 flags)
 {
 	struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring;
 	u32 idx;
@@ -372,6 +418,7 @@ static inline int xskq_prod_reserve_desc(struct xsk_queue *q,
 	idx = q->cached_prod++ & q->ring_mask;
 	ring->desc[idx].addr = addr;
 	ring->desc[idx].len = len;
+	ring->desc[idx].options = flags;
 
 	return 0;
 }
@@ -386,16 +433,6 @@ static inline void xskq_prod_submit(struct xsk_queue *q)
 	__xskq_prod_submit(q, q->cached_prod);
 }
 
-static inline void xskq_prod_submit_addr(struct xsk_queue *q, u64 addr)
-{
-	struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring;
-	u32 idx = q->ring->producer;
-
-	ring->desc[idx++ & q->ring_mask] = addr;
-
-	__xskq_prod_submit(q, idx);
-}
-
 static inline void xskq_prod_submit_n(struct xsk_queue *q, u32 nb_entries)
 {
 	__xskq_prod_submit(q, q->ring->producer + nb_entries);