Merge tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Don't destroy user event fields when removal fails

   User event fields are destroyed before the event is removed from
   visibility. But that can fail leaving the still visible event with no
   fields. Move the destroying of the fields to after the event is
   successfully removed from visibility.

 - Initialize function graph state is fork before calling
   copy_exec_state()

   For non-CLONE_VM forks, copy_exec_state() allocates a new
   task_exec_state. If that allocation fails, ftrace_graph_exit_task()
   will free the tasks ret_stack pointer. Since that pointer is still
   using the parent's ret_stack, it mistakenly frees the parent's
   pointer too.

   Call ftrace_graph_init() on the task first which will NULL out the
   new tasks's ret_stack and if the copy fails, it will not free
   anything.

 - Remove FGRAPH_MAX_INDEX

   The macro FGRAPH_MAX_INDEX was added but never used. Remove it.

 - Save ent_size in function graph printing of nested functions

   The function graph tracer needs to look at the next event to see if
   the next event is the return of the current function entry. If it is,
   it prints a single line:

	ktime_get();

   Otherwise it prints it like a nested function:

	tick_nohz_irq_exit() {
	    ktime_get();
	    kcpustat_irq_exit();
	}

   In order to look at the next event, it must save the current event so
   that it has the information to print from it. It saves the event in
   the iterator descriptor called "ent". What it doesn't save is the
   ent_size of the event which is now used to know if the function graph
   arguments are to be printed. The peek doesn't save the size so the
   size used happens to be that of the size of the last event that was
   seen.

   Save the entry event size in the iterator descriptor so that the
   correct size is used.

 - Fix several errors with freeing data in the histogram code

   The histogram code had a lot of leaked or or incorrect accounting
   when failures happen. Correct them.

 - Fix histogram regression of .percent and .graph modifiers

   Up until 6.3 histogram values could have "percent" or "graph"
   modifiers that changed how they were printed. But a change that added
   restricting histograms values from being strings, stack traces and
   other modifiers inadvertently prevented them from using the percent
   and graph modifiers, which were legal use cases for values.

   Put back the percent and graph modifiers.

 - Fix various typos in the comments

 - Set the trace_clock before initializing a histogram with clock
   argument

   The histogram API allows the user to specific which trace clock to
   use via a "clock=" string. The histogram is set up first before the
   clock is checked. If the passed in clock is not valid, it exits
   without fully fixing up the histogram leaving it on the list and a
   use-after-free can trigger.

   Update the clock argument first and if it fails then exit gracefully
   before the histogram trigger is placed on any lists.

 - Restore :mod: trailer after parsing in ftrace_set_clr_event

   The function ftrace_set_clr_event() modifies the parse string and
   needs to put it back to what was passed in. It searches for ":mod:"
   via a strsep() but fails to put back the first ':' in the string.

   Add back the ':' in the passed in string.

 - Take trace_array reference when opening a tracer options file

   The options files are dynamically created and some tracers add their
   own options. When a tracer adds their own list of options, the
   trace_array holding them has an array to hold the list of options for
   each tracer. This array increases in size via a krealloc(), and the
   new entry gets a newly allocated array to hold the options of the new
   tracer being added.

   The element in each entry of the tracer's option array holds a
   pointer back to the trace_array, a pointer to the tracer it is
   associated to, a pointer to the flags of the option.

   The issue is that these arrays are freed when the trace_array is
   freed when its instance it represents is removed from the instances
   directory. There's a race that an open of one of these options files
   can happen when the instance is being removed.

   Add a new helper function to be called by the open function of the
   options file to iterate all existing trace_arrays under a lock and
   find the one that has the given option element in one of it's tracer
   arrays. If found, then update the associated trace_array's reference
   counter to keep it from being freed. If not found, have the open call
   return -ENODEV.

 - Disable interrupts when acquiring the lock in rb_wake_up_waiters()

   The function rb_wake_up_waiters() assumes it will be called in
   interrupt context and does not disable irqs when taking
   cpu_buffer->reader_lock, which can be called in hard interrupt
   context. The issue is in PREEMPT_RT, this function is called in
   thread context leaving this lock open to a deadlock.

   Take the lock with interrupts disabled.

 - Use rcu_assign_pointer() for tmp_ops filter hash

   The tmp_ops used in update_ftrace_direct_mod() assigns its
   filter_hash field directly, but that field is annotated as __rcu and
   sparse complains. Assign it with rcu_assign_pointer()

 - Fix use-after-free in enable_trigger_private_data_free()

   The trace_event_call is accessed through the event_trigger_data's
   trace_event_file pointer to put the trace_event_call on freeing. The
   issue is that the trace_event_file data may have been freed already
   causing a use-after-free. Add a field to the event_trigger_data that
   points directly to the trace_event_call so that it can decrement its
   reference directly without needing to go through the
   trace_event_file.

 - Fix accounting of buffer data remote headers

   trace_buffer_desc_size() and trace_remote_alloc_buffer() undercount
   the number of pages is needed for the asked for size as it doesn't
   take into account the meta data on each page. Add a helper function
   to do the calculation properly and use that in these functions.

 - Catch nr_page_va overflow in ring_buffer_desc sizing

   The number of pages per remote ring buffer is capped by
   ring_buffer_desc::nr_page_va (32 bits). A buffer_size large enough to
   overflow that field would silently allocate a descriptor smaller than
   what was asked for.

 - Do not resize the subbuf order if any per_cpu buffer is disabled

   The mmapping of ring buffers disables resizing the subbuffers, but it
   is done per-cpu whereas the subbuf size change is done for all the
   per_cpu buffers under the buffer->mutex. It could change the size of
   some while the mapping is happening on others. Have the resize of the
   subbuf order check all the per_cpu buffers under the lock to see if
   any of them is disabled before starting and causing an inconsistency
   between buffers that are being mapped.

* tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (25 commits)
  ring-buffer: Check resize_disabled before publishing the new subbuf order
  tracing/remotes: Catch nr_page_va overflow in ring_buffer_desc sizing
  tracing/remotes: Account for ring buffer page header in size calculation
  tracing: Don't dereference trace_event_file in deferred trigger free
  ftrace: Use rcu_assign_pointer() for tmp_ops filter hash
  ring-buffer: Acquire the lock with irqsave in rb_wake_up_waiters()
  tracing: Take trace_array reference when opening a tracer options file
  tracing: Fix ring_buffer_read_page_size() kernel-doc
  tracing: Restore :mod: trailer after parsing in ftrace_set_clr_event()
  tracing: Fix memory corruption from a "STACKTRACE" histogram key
  tracing: Fix memory corruption from the histogram stacktrace modifier
  tracing: Undo the registration when enabling the histogram trigger fails
  tracing: Take the reference before publishing the named histogram trigger
  tracing: Set the trace clock before registering the histogram trigger
  tracing: Fix typo "preceeded" in comment
  tracing: Fix typo "availabe" in comment
  tracing: Let histogram values keep the percent and graph modifiers
  tracing: Keep the entry count when the histogram stats allocation fails
  tracing: Free histogram the field rejected for a bad modifier
  tracing: Free histogram the var ref when its initialization fails
  ...

1 files changed, 2026 insertions, 0 deletions

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
new file mode 100644
index 000000000..6ed3ee811
--- /dev/null
+++ b/drivers/net/veth.c
@@ -0,0 +1,2026 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  drivers/net/veth.c
+ *
+ *  Copyright (C) 2007 OpenVZ http://openvz.org, SWsoft Inc
+ *
+ * Author: Pavel Emelianov <xemul@openvz.org>
+ * Ethtool interface from: Eric W. Biederman <ebiederm@xmission.com>
+ *
+ */
+
+#include <linux/netdevice.h>
+#include <linux/slab.h>
+#include <linux/ethtool.h>
+#include <linux/etherdevice.h>
+#include <linux/u64_stats_sync.h>
+
+#include <net/rtnetlink.h>
+#include <net/dst.h>
+#include <net/netdev_lock.h>
+#include <net/xfrm.h>
+#include <net/xdp.h>
+#include <linux/veth.h>
+#include <linux/module.h>
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <linux/ptr_ring.h>
+#include <linux/bpf_trace.h>
+#include <linux/net_tstamp.h>
+#include <linux/skbuff_ref.h>
+#include <net/page_pool/helpers.h>
+
+#define DRV_NAME	"veth"
+#define DRV_VERSION	"1.0"
+
+#define VETH_XDP_FLAG		BIT(0)
+#define VETH_RING_SIZE		256
+#define VETH_XDP_HEADROOM	(XDP_PACKET_HEADROOM + NET_IP_ALIGN)
+
+#define VETH_XDP_TX_BULK_SIZE	16
+#define VETH_XDP_BATCH		16
+
+struct veth_stats {
+	u64	rx_drops;
+	/* xdp */
+	u64	xdp_packets;
+	u64	xdp_bytes;
+	u64	xdp_redirect;
+	u64	xdp_drops;
+	u64	xdp_tx;
+	u64	xdp_tx_err;
+	u64	peer_tq_xdp_xmit;
+	u64	peer_tq_xdp_xmit_err;
+};
+
+struct veth_rq_stats {
+	struct veth_stats	vs;
+	struct u64_stats_sync	syncp;
+};
+
+struct veth_rq {
+	struct napi_struct	xdp_napi;
+	struct napi_struct __rcu *napi; /* points to xdp_napi when the latter is initialized */
+	struct net_device	*dev;
+	struct bpf_prog __rcu	*xdp_prog;
+	struct xdp_mem_info	xdp_mem;
+	struct veth_rq_stats	stats;
+	bool			rx_notify_masked;
+	struct ptr_ring		xdp_ring;
+	struct xdp_rxq_info	xdp_rxq;
+	struct page_pool	*page_pool;
+};
+
+struct veth_priv {
+	struct net_device __rcu	*peer;
+	atomic64_t		dropped;
+	struct bpf_prog		*_xdp_prog;
+	struct veth_rq		*rq;
+	unsigned int		requested_headroom;
+	netdevice_tracker	peer_tracker;
+};
+
+struct veth_xdp_tx_bq {
+	struct xdp_frame *q[VETH_XDP_TX_BULK_SIZE];
+	unsigned int count;
+};
+
+/*
+ * ethtool interface
+ */
+
+struct veth_q_stat_desc {
+	char	desc[ETH_GSTRING_LEN];
+	size_t	offset;
+};
+
+#define VETH_RQ_STAT(m)	offsetof(struct veth_stats, m)
+
+static const struct veth_q_stat_desc veth_rq_stats_desc[] = {
+	{ "xdp_packets",	VETH_RQ_STAT(xdp_packets) },
+	{ "xdp_bytes",		VETH_RQ_STAT(xdp_bytes) },
+	{ "drops",		VETH_RQ_STAT(rx_drops) },
+	{ "xdp_redirect",	VETH_RQ_STAT(xdp_redirect) },
+	{ "xdp_drops",		VETH_RQ_STAT(xdp_drops) },
+	{ "xdp_tx",		VETH_RQ_STAT(xdp_tx) },
+	{ "xdp_tx_errors",	VETH_RQ_STAT(xdp_tx_err) },
+};
+
+#define VETH_RQ_STATS_LEN	ARRAY_SIZE(veth_rq_stats_desc)
+
+static const struct veth_q_stat_desc veth_tq_stats_desc[] = {
+	{ "xdp_xmit",		VETH_RQ_STAT(peer_tq_xdp_xmit) },
+	{ "xdp_xmit_errors",	VETH_RQ_STAT(peer_tq_xdp_xmit_err) },
+};
+
+#define VETH_TQ_STATS_LEN	ARRAY_SIZE(veth_tq_stats_desc)
+
+static struct {
+	const char string[ETH_GSTRING_LEN];
+} ethtool_stats_keys[] = {
+	{ "peer_ifindex" },
+};
+
+struct veth_xdp_buff {
+	struct xdp_buff xdp;
+	struct sk_buff *skb;
+};
+
+static int veth_get_link_ksettings(struct net_device *dev,
+				   struct ethtool_link_ksettings *cmd)
+{
+	cmd->base.speed		= SPEED_10000;
+	cmd->base.duplex	= DUPLEX_FULL;
+	cmd->base.port		= PORT_TP;
+	cmd->base.autoneg	= AUTONEG_DISABLE;
+	return 0;
+}
+
+static void veth_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
+{
+	strscpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strscpy(info->version, DRV_VERSION, sizeof(info->version));
+}
+
+static void veth_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
+{
+	u8 *p = buf;
+	int i, j;
+
+	switch(stringset) {
+	case ETH_SS_STATS:
+		memcpy(p, &ethtool_stats_keys, sizeof(ethtool_stats_keys));
+		p += sizeof(ethtool_stats_keys);
+		for (i = 0; i < dev->real_num_rx_queues; i++)
+			for (j = 0; j < VETH_RQ_STATS_LEN; j++)
+				ethtool_sprintf(&p, "rx_queue_%u_%.18s",
+						i, veth_rq_stats_desc[j].desc);
+
+		for (i = 0; i < dev->real_num_tx_queues; i++)
+			for (j = 0; j < VETH_TQ_STATS_LEN; j++)
+				ethtool_sprintf(&p, "tx_queue_%u_%.18s",
+						i, veth_tq_stats_desc[j].desc);
+
+		page_pool_ethtool_stats_get_strings(p);
+		break;
+	}
+}
+
+static int veth_get_sset_count(struct net_device *dev, int sset)
+{
+	switch (sset) {
+	case ETH_SS_STATS:
+		return ARRAY_SIZE(ethtool_stats_keys) +
+		       VETH_RQ_STATS_LEN * dev->real_num_rx_queues +
+		       VETH_TQ_STATS_LEN * dev->real_num_tx_queues +
+		       page_pool_ethtool_stats_get_count();
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static void veth_get_page_pool_stats(struct net_device *dev, u64 *data)
+{
+#ifdef CONFIG_PAGE_POOL_STATS
+	struct veth_priv *priv = netdev_priv(dev);
+	struct page_pool_stats pp_stats = {};
+	int i;
+
+	for (i = 0; i < dev->real_num_rx_queues; i++) {
+		if (!priv->rq[i].page_pool)
+			continue;
+		page_pool_get_stats(priv->rq[i].page_pool, &pp_stats);
+	}
+	page_pool_ethtool_stats_get(data, &pp_stats);
+#endif /* CONFIG_PAGE_POOL_STATS */
+}
+
+static void veth_get_ethtool_stats(struct net_device *dev,
+		struct ethtool_stats *stats, u64 *data)
+{
+	struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
+	struct net_device *peer = rtnl_dereference(priv->peer);
+	int i, j, idx, pp_idx;
+
+	data[0] = peer ? peer->ifindex : 0;
+	idx = 1;
+	for (i = 0; i < dev->real_num_rx_queues; i++) {
+		const struct veth_rq_stats *rq_stats = &priv->rq[i].stats;
+		const void *stats_base = (void *)&rq_stats->vs;
+		unsigned int start;
+		size_t offset;
+
+		do {
+			start = u64_stats_fetch_begin(&rq_stats->syncp);
+			for (j = 0; j < VETH_RQ_STATS_LEN; j++) {
+				offset = veth_rq_stats_desc[j].offset;
+				data[idx + j] = *(u64 *)(stats_base + offset);
+			}
+		} while (u64_stats_fetch_retry(&rq_stats->syncp, start));
+		idx += VETH_RQ_STATS_LEN;
+	}
+	pp_idx = idx;
+
+	if (!peer)
+		goto page_pool_stats;
+
+	rcv_priv = netdev_priv(peer);
+	for (i = 0; i < peer->real_num_rx_queues; i++) {
+		const struct veth_rq_stats *rq_stats = &rcv_priv->rq[i].stats;
+		const void *base = (void *)&rq_stats->vs;
+		unsigned int start, tx_idx = idx;
+		u64 buf[VETH_TQ_STATS_LEN];
+		size_t offset;
+
+		do {
+			start = u64_stats_fetch_begin(&rq_stats->syncp);
+			for (j = 0; j < VETH_TQ_STATS_LEN; j++) {
+				offset = veth_tq_stats_desc[j].offset;
+				buf[j] = *(u64 *)(base + offset);
+			}
+		} while (u64_stats_fetch_retry(&rq_stats->syncp, start));
+
+		tx_idx += (i % dev->real_num_tx_queues) * VETH_TQ_STATS_LEN;
+		for (j = 0; j < VETH_TQ_STATS_LEN; j++)
+			data[tx_idx + j] += buf[j];
+	}
+	pp_idx = idx + dev->real_num_tx_queues * VETH_TQ_STATS_LEN;
+
+page_pool_stats:
+	veth_get_page_pool_stats(dev, &data[pp_idx]);
+}
+
+static void veth_get_channels(struct net_device *dev,
+			      struct ethtool_channels *channels)
+{
+	channels->tx_count = dev->real_num_tx_queues;
+	channels->rx_count = dev->real_num_rx_queues;
+	channels->max_tx = dev->num_tx_queues;
+	channels->max_rx = dev->num_rx_queues;
+}
+
+static int veth_set_channels(struct net_device *dev,
+			     struct ethtool_channels *ch);
+
+static const struct ethtool_ops veth_ethtool_ops = {
+	.get_drvinfo		= veth_get_drvinfo,
+	.get_link		= ethtool_op_get_link,
+	.get_strings		= veth_get_strings,
+	.get_sset_count		= veth_get_sset_count,
+	.get_ethtool_stats	= veth_get_ethtool_stats,
+	.get_link_ksettings	= veth_get_link_ksettings,
+	.get_ts_info		= ethtool_op_get_ts_info,
+	.get_channels		= veth_get_channels,
+	.set_channels		= veth_set_channels,
+};
+
+/* general routines */
+
+static bool veth_is_xdp_frame(void *ptr)
+{
+	return (unsigned long)ptr & VETH_XDP_FLAG;
+}
+
+static struct xdp_frame *veth_ptr_to_xdp(void *ptr)
+{
+	return (void *)((unsigned long)ptr & ~VETH_XDP_FLAG);
+}
+
+static void *veth_xdp_to_ptr(struct xdp_frame *xdp)
+{
+	return (void *)((unsigned long)xdp | VETH_XDP_FLAG);
+}
+
+static void veth_ptr_free(void *ptr)
+{
+	if (veth_is_xdp_frame(ptr))
+		xdp_return_frame(veth_ptr_to_xdp(ptr));
+	else
+		kfree_skb(ptr);
+}
+
+static void __veth_xdp_flush(struct veth_rq *rq)
+{
+	/* Write ptr_ring before reading rx_notify_masked */
+	smp_mb();
+	if (!READ_ONCE(rq->rx_notify_masked) &&
+	    napi_schedule_prep(&rq->xdp_napi)) {
+		WRITE_ONCE(rq->rx_notify_masked, true);
+		__napi_schedule(&rq->xdp_napi);
+	}
+}
+
+static int veth_xdp_rx(struct veth_rq *rq, struct sk_buff *skb)
+{
+	if (unlikely(ptr_ring_produce(&rq->xdp_ring, skb)))
+		return NETDEV_TX_BUSY; /* signal qdisc layer */
+
+	return NET_RX_SUCCESS; /* same as NETDEV_TX_OK */
+}
+
+static int veth_forward_skb(struct net_device *dev, struct sk_buff *skb,
+			    struct veth_rq *rq, bool xdp)
+{
+	return __dev_forward_skb(dev, skb) ?: xdp ?
+		veth_xdp_rx(rq, skb) :
+		__netif_rx(skb);
+}
+
+/* return true if the specified skb has chances of GRO aggregation
+ * Don't strive for accuracy, but try to avoid GRO overhead in the most
+ * common scenarios.
+ * When XDP is enabled, all traffic is considered eligible, as the xmit
+ * device has TSO off.
+ * When TSO is enabled on the xmit device, we are likely interested only
+ * in UDP aggregation, explicitly check for that if the skb is suspected
+ * - the sock_wfree destructor is used by UDP, ICMP and XDP sockets -
+ * to belong to locally generated UDP traffic.
+ */
+static bool veth_skb_is_eligible_for_gro(const struct net_device *dev,
+					 const struct net_device *rcv,
+					 const struct sk_buff *skb)
+{
+	return !(dev->features & NETIF_F_ALL_TSO) ||
+		(skb->destructor == sock_wfree &&
+		 rcv->features & (NETIF_F_GRO_FRAGLIST | NETIF_F_GRO_UDP_FWD));
+}
+
+static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
+	struct veth_rq *rq = NULL;
+	struct netdev_queue *txq;
+	struct net_device *rcv;
+	int length = skb->len;
+	bool use_napi = false;
+	int ret, rxq;
+
+	rcu_read_lock();
+	rcv = rcu_dereference(priv->peer);
+	if (unlikely(!rcv) || !pskb_may_pull(skb, ETH_HLEN)) {
+		kfree_skb(skb);
+		goto drop;
+	}
+
+	rcv_priv = netdev_priv(rcv);
+	rxq = skb_get_queue_mapping(skb);
+	if (rxq < rcv->real_num_rx_queues) {
+		rq = &rcv_priv->rq[rxq];
+
+		/* The napi pointer is available when an XDP program is
+		 * attached or when GRO is enabled
+		 * Don't bother with napi/GRO if the skb can't be aggregated
+		 */
+		use_napi = rcu_access_pointer(rq->napi) &&
+			   veth_skb_is_eligible_for_gro(dev, rcv, skb);
+	}
+
+	skb_tx_timestamp(skb);
+
+	ret = veth_forward_skb(rcv, skb, rq, use_napi);
+	switch (ret) {
+	case NET_RX_SUCCESS: /* same as NETDEV_TX_OK */
+		if (!use_napi)
+			dev_sw_netstats_tx_add(dev, 1, length);
+		else
+			__veth_xdp_flush(rq);
+		break;
+	case NETDEV_TX_BUSY:
+		/* If a qdisc is attached to our virtual device, returning
+		 * NETDEV_TX_BUSY is allowed.
+		 */
+		txq = netdev_get_tx_queue(dev, rxq);
+
+		if (qdisc_txq_has_no_queue(txq)) {
+			dev_kfree_skb_any(skb);
+			goto drop;
+		}
+		/* Restore Eth hdr pulled by dev_forward_skb/eth_type_trans */
+		__skb_push(skb, ETH_HLEN);
+		netif_tx_stop_queue(txq);
+		/* Makes sure NAPI peer consumer runs. Consumer is responsible
+		 * for starting txq again, until then ndo_start_xmit (this
+		 * function) will not be invoked by the netstack again.
+		 */
+		__veth_xdp_flush(rq);
+		break;
+	case NET_RX_DROP: /* same as NET_XMIT_DROP */
+drop:
+		atomic64_inc(&priv->dropped);
+		ret = NET_XMIT_DROP;
+		break;
+	default:
+		net_crit_ratelimited("%s(%s): Invalid return code(%d)",
+				     __func__, dev->name, ret);
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static void veth_stats_rx(struct veth_stats *result, struct net_device *dev)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	int i;
+
+	result->peer_tq_xdp_xmit_err = 0;
+	result->xdp_packets = 0;
+	result->xdp_tx_err = 0;
+	result->xdp_bytes = 0;
+	result->rx_drops = 0;
+	for (i = 0; i < dev->num_rx_queues; i++) {
+		u64 packets, bytes, drops, xdp_tx_err, peer_tq_xdp_xmit_err;
+		struct veth_rq_stats *stats = &priv->rq[i].stats;
+		unsigned int start;
+
+		do {
+			start = u64_stats_fetch_begin(&stats->syncp);
+			peer_tq_xdp_xmit_err = stats->vs.peer_tq_xdp_xmit_err;
+			xdp_tx_err = stats->vs.xdp_tx_err;
+			packets = stats->vs.xdp_packets;
+			bytes = stats->vs.xdp_bytes;
+			drops = stats->vs.rx_drops;
+		} while (u64_stats_fetch_retry(&stats->syncp, start));
+		result->peer_tq_xdp_xmit_err += peer_tq_xdp_xmit_err;
+		result->xdp_tx_err += xdp_tx_err;
+		result->xdp_packets += packets;
+		result->xdp_bytes += bytes;
+		result->rx_drops += drops;
+	}
+}
+
+static void veth_get_stats64(struct net_device *dev,
+			     struct rtnl_link_stats64 *tot)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	struct net_device *peer;
+	struct veth_stats rx;
+
+	tot->tx_dropped = atomic64_read(&priv->dropped);
+	dev_fetch_sw_netstats(tot, dev->tstats);
+
+	veth_stats_rx(&rx, dev);
+	tot->tx_dropped += rx.xdp_tx_err;
+	tot->rx_dropped = rx.rx_drops + rx.peer_tq_xdp_xmit_err;
+	tot->rx_bytes += rx.xdp_bytes;
+	tot->rx_packets += rx.xdp_packets;
+
+	rcu_read_lock();
+	peer = rcu_dereference(priv->peer);
+	if (peer) {
+		struct rtnl_link_stats64 tot_peer = {};
+
+		dev_fetch_sw_netstats(&tot_peer, peer->tstats);
+		tot->rx_bytes += tot_peer.tx_bytes;
+		tot->rx_packets += tot_peer.tx_packets;
+
+		veth_stats_rx(&rx, peer);
+		tot->tx_dropped += rx.peer_tq_xdp_xmit_err;
+		tot->rx_dropped += rx.xdp_tx_err;
+		tot->tx_bytes += rx.xdp_bytes;
+		tot->tx_packets += rx.xdp_packets;
+	}
+	rcu_read_unlock();
+}
+
+/* fake multicast ability */
+static void veth_set_multicast_list(struct net_device *dev)
+{
+}
+
+static int veth_select_rxq(struct net_device *dev)
+{
+	return smp_processor_id() % dev->real_num_rx_queues;
+}
+
+static struct net_device *veth_peer_dev(struct net_device *dev)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+
+	/* Callers must be under RCU read side. */
+	return rcu_dereference(priv->peer);
+}
+
+static int veth_xdp_xmit(struct net_device *dev, int n,
+			 struct xdp_frame **frames,
+			 u32 flags, bool ndo_xmit)
+{
+	struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
+	int i, ret = -ENXIO, nxmit = 0;
+	struct net_device *rcv;
+	unsigned int max_len;
+	struct veth_rq *rq;
+
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+		return -EINVAL;
+
+	rcu_read_lock();
+	rcv = rcu_dereference(priv->peer);
+	if (unlikely(!rcv))
+		goto out;
+
+	rcv_priv = netdev_priv(rcv);
+	rq = &rcv_priv->rq[veth_select_rxq(rcv)];
+	/* The napi pointer is set if NAPI is enabled, which ensures that
+	 * xdp_ring is initialized on receive side and the peer device is up.
+	 */
+	if (!rcu_access_pointer(rq->napi))
+		goto out;
+
+	max_len = rcv->mtu + rcv->hard_header_len + VLAN_HLEN;
+
+	spin_lock(&rq->xdp_ring.producer_lock);
+	for (i = 0; i < n; i++) {
+		struct xdp_frame *frame = frames[i];
+		void *ptr = veth_xdp_to_ptr(frame);
+
+		if (unlikely(xdp_get_frame_len(frame) > max_len ||
+			     __ptr_ring_produce(&rq->xdp_ring, ptr)))
+			break;
+		nxmit++;
+	}
+	spin_unlock(&rq->xdp_ring.producer_lock);
+
+	if (flags & XDP_XMIT_FLUSH)
+		__veth_xdp_flush(rq);
+
+	ret = nxmit;
+	if (ndo_xmit) {
+		u64_stats_update_begin(&rq->stats.syncp);
+		rq->stats.vs.peer_tq_xdp_xmit += nxmit;
+		rq->stats.vs.peer_tq_xdp_xmit_err += n - nxmit;
+		u64_stats_update_end(&rq->stats.syncp);
+	}
+
+out:
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static int veth_ndo_xdp_xmit(struct net_device *dev, int n,
+			     struct xdp_frame **frames, u32 flags)
+{
+	int err;
+
+	err = veth_xdp_xmit(dev, n, frames, flags, true);
+	if (err < 0) {
+		struct veth_priv *priv = netdev_priv(dev);
+
+		atomic64_add(n, &priv->dropped);
+	}
+
+	return err;
+}
+
+static void veth_xdp_flush_bq(struct veth_rq *rq, struct veth_xdp_tx_bq *bq)
+{
+	int sent, i, err = 0, drops;
+
+	sent = veth_xdp_xmit(rq->dev, bq->count, bq->q, 0, false);
+	if (sent < 0) {
+		err = sent;
+		sent = 0;
+	}
+
+	for (i = sent; unlikely(i < bq->count); i++)
+		xdp_return_frame(bq->q[i]);
+
+	drops = bq->count - sent;
+	trace_xdp_bulk_tx(rq->dev, sent, drops, err);
+
+	u64_stats_update_begin(&rq->stats.syncp);
+	rq->stats.vs.xdp_tx += sent;
+	rq->stats.vs.xdp_tx_err += drops;
+	u64_stats_update_end(&rq->stats.syncp);
+
+	bq->count = 0;
+}
+
+static void veth_xdp_flush(struct veth_rq *rq, struct veth_xdp_tx_bq *bq)
+{
+	struct veth_priv *rcv_priv, *priv = netdev_priv(rq->dev);
+	struct net_device *rcv;
+	struct veth_rq *rcv_rq;
+
+	rcu_read_lock();
+	veth_xdp_flush_bq(rq, bq);
+	rcv = rcu_dereference(priv->peer);
+	if (unlikely(!rcv))
+		goto out;
+
+	rcv_priv = netdev_priv(rcv);
+	rcv_rq = &rcv_priv->rq[veth_select_rxq(rcv)];
+	/* xdp_ring is initialized on receive side? */
+	if (unlikely(!rcu_access_pointer(rcv_rq->xdp_prog)))
+		goto out;
+
+	__veth_xdp_flush(rcv_rq);
+out:
+	rcu_read_unlock();
+}
+
+static int veth_xdp_tx(struct veth_rq *rq, struct xdp_buff *xdp,
+		       struct veth_xdp_tx_bq *bq)
+{
+	struct xdp_frame *frame = xdp_convert_buff_to_frame(xdp);
+
+	if (unlikely(!frame))
+		return -EOVERFLOW;
+
+	if (unlikely(bq->count == VETH_XDP_TX_BULK_SIZE))
+		veth_xdp_flush_bq(rq, bq);
+
+	bq->q[bq->count++] = frame;
+
+	return 0;
+}
+
+static struct xdp_frame *veth_xdp_rcv_one(struct veth_rq *rq,
+					  struct xdp_frame *frame,
+					  struct veth_xdp_tx_bq *bq,
+					  struct veth_stats *stats)
+{
+	struct xdp_frame orig_frame;
+	struct bpf_prog *xdp_prog;
+
+	rcu_read_lock();
+	xdp_prog = rcu_dereference(rq->xdp_prog);
+	if (likely(xdp_prog)) {
+		struct veth_xdp_buff vxbuf;
+		struct xdp_buff *xdp = &vxbuf.xdp;
+		u32 act;
+
+		xdp_convert_frame_to_buff(frame, xdp);
+		xdp->rxq = &rq->xdp_rxq;
+		vxbuf.skb = NULL;
+
+		act = bpf_prog_run_xdp(xdp_prog, xdp);
+
+		switch (act) {
+		case XDP_PASS:
+			if (xdp_update_frame_from_buff(xdp, frame))
+				goto err_xdp;
+			break;
+		case XDP_TX:
+			orig_frame = *frame;
+			xdp->rxq->mem.type = frame->mem_type;
+			if (unlikely(veth_xdp_tx(rq, xdp, bq) < 0)) {
+				trace_xdp_exception(rq->dev, xdp_prog, act);
+				frame = &orig_frame;
+				stats->rx_drops++;
+				goto err_xdp;
+			}
+			stats->xdp_tx++;
+			rcu_read_unlock();
+			goto xdp_xmit;
+		case XDP_REDIRECT:
+			orig_frame = *frame;
+			xdp->rxq->mem.type = frame->mem_type;
+			if (xdp_do_redirect(rq->dev, xdp, xdp_prog)) {
+				frame = &orig_frame;
+				stats->rx_drops++;
+				goto err_xdp;
+			}
+			stats->xdp_redirect++;
+			rcu_read_unlock();
+			goto xdp_xmit;
+		default:
+			bpf_warn_invalid_xdp_action(rq->dev, xdp_prog, act);
+			fallthrough;
+		case XDP_ABORTED:
+			trace_xdp_exception(rq->dev, xdp_prog, act);
+			fallthrough;
+		case XDP_DROP:
+			stats->xdp_drops++;
+			goto err_xdp;
+		}
+	}
+	rcu_read_unlock();
+
+	return frame;
+err_xdp:
+	rcu_read_unlock();
+	xdp_return_frame(frame);
+xdp_xmit:
+	return NULL;
+}
+
+/* frames array contains VETH_XDP_BATCH at most */
+static void veth_xdp_rcv_bulk_skb(struct veth_rq *rq, void **frames,
+				  int n_xdpf, struct veth_xdp_tx_bq *bq,
+				  struct veth_stats *stats)
+{
+	void *skbs[VETH_XDP_BATCH];
+	int i;
+
+	if (unlikely(!napi_skb_cache_get_bulk(skbs, n_xdpf))) {
+		for (i = 0; i < n_xdpf; i++)
+			xdp_return_frame(frames[i]);
+		stats->rx_drops += n_xdpf;
+
+		return;
+	}
+
+	for (i = 0; i < n_xdpf; i++) {
+		struct sk_buff *skb = skbs[i];
+
+		skb = __xdp_build_skb_from_frame(frames[i], skb,
+						 rq->dev);
+		if (!skb) {
+			xdp_return_frame(frames[i]);
+			stats->rx_drops++;
+			continue;
+		}
+		napi_gro_receive(&rq->xdp_napi, skb);
+	}
+}
+
+static void veth_xdp_get(struct xdp_buff *xdp)
+{
+	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
+	int i;
+
+	get_page(virt_to_page(xdp->data));
+	if (likely(!xdp_buff_has_frags(xdp)))
+		return;
+
+	for (i = 0; i < sinfo->nr_frags; i++)
+		__skb_frag_ref(&sinfo->frags[i]);
+}
+
+static int veth_convert_skb_to_xdp_buff(struct veth_rq *rq,
+					struct xdp_buff *xdp,
+					struct sk_buff **pskb)
+{
+	struct sk_buff *skb = *pskb;
+	u32 frame_sz;
+
+	if (skb_shared(skb) || skb_head_is_locked(skb) ||
+	    skb_is_nonlinear(skb) ||
+	    skb_headroom(skb) < XDP_PACKET_HEADROOM) {
+		if (skb_pp_cow_data(rq->page_pool, pskb, XDP_PACKET_HEADROOM))
+			goto drop;
+
+		skb = *pskb;
+	}
+
+	/* SKB "head" area always have tailroom for skb_shared_info */
+	frame_sz = skb_end_pointer(skb) - skb->head;
+	frame_sz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+	xdp_init_buff(xdp, frame_sz, &rq->xdp_rxq);
+	xdp_prepare_buff(xdp, skb->head, skb_headroom(skb),
+			 skb_headlen(skb), true);
+
+	if (skb_shinfo(skb)->nr_frags) {
+		skb_shinfo(skb)->xdp_frags_size = skb->data_len;
+		xdp_buff_set_frags_flag(xdp);
+	} else {
+		xdp_buff_clear_frags_flag(xdp);
+	}
+	*pskb = skb;
+
+	return 0;
+drop:
+	consume_skb(skb);
+	*pskb = NULL;
+
+	return -ENOMEM;
+}
+
+static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq,
+					struct sk_buff *skb,
+					struct veth_xdp_tx_bq *bq,
+					struct veth_stats *stats)
+{
+	void *orig_data, *orig_data_end;
+	struct bpf_prog *xdp_prog;
+	struct veth_xdp_buff vxbuf;
+	struct xdp_buff *xdp = &vxbuf.xdp;
+	u32 act, metalen;
+	int off;
+
+	skb_prepare_for_gro(skb);
+
+	rcu_read_lock();
+	xdp_prog = rcu_dereference(rq->xdp_prog);
+	if (unlikely(!xdp_prog)) {
+		rcu_read_unlock();
+		goto out;
+	}
+
+	__skb_push(skb, skb->data - skb_mac_header(skb));
+	if (veth_convert_skb_to_xdp_buff(rq, xdp, &skb))
+		goto drop;
+	vxbuf.skb = skb;
+
+	orig_data = xdp->data;
+	orig_data_end = xdp->data_end;
+
+	act = bpf_prog_run_xdp(xdp_prog, xdp);
+
+	switch (act) {
+	case XDP_PASS:
+		break;
+	case XDP_TX:
+		veth_xdp_get(xdp);
+		consume_skb(skb);
+		xdp->rxq->mem = rq->xdp_mem;
+		if (unlikely(veth_xdp_tx(rq, xdp, bq) < 0)) {
+			trace_xdp_exception(rq->dev, xdp_prog, act);
+			stats->rx_drops++;
+			goto err_xdp;
+		}
+		stats->xdp_tx++;
+		rcu_read_unlock();
+		goto xdp_xmit;
+	case XDP_REDIRECT:
+		veth_xdp_get(xdp);
+		consume_skb(skb);
+		xdp->rxq->mem = rq->xdp_mem;
+		if (xdp_do_redirect(rq->dev, xdp, xdp_prog)) {
+			stats->rx_drops++;
+			goto err_xdp;
+		}
+		stats->xdp_redirect++;
+		rcu_read_unlock();
+		goto xdp_xmit;
+	default:
+		bpf_warn_invalid_xdp_action(rq->dev, xdp_prog, act);
+		fallthrough;
+	case XDP_ABORTED:
+		trace_xdp_exception(rq->dev, xdp_prog, act);
+		fallthrough;
+	case XDP_DROP:
+		stats->xdp_drops++;
+		goto xdp_drop;
+	}
+	rcu_read_unlock();
+
+	/* check if bpf_xdp_adjust_head was used */
+	off = orig_data - xdp->data;
+	if (off > 0)
+		__skb_push(skb, off);
+	else if (off < 0)
+		__skb_pull(skb, -off);
+
+	skb_reset_mac_header(skb);
+
+	/* XDP frag metadata (e.g. nr_frags) are updated in eBPF helpers
+	 * (e.g. bpf_xdp_adjust_tail). Remove the old fragment contribution
+	 * from skb->len before updating data_len, then add the new one back.
+	 */
+	skb->len -= skb->data_len;
+	if (xdp_buff_has_frags(xdp)) {
+		skb->data_len = skb_shinfo(skb)->xdp_frags_size;
+		skb->len += skb->data_len;
+	} else {
+		skb->data_len = 0;
+	}
+
+	/* Synchronize the skb tail with XDP's updated linear area. */
+	off = xdp->data_end - orig_data_end;
+	if (off != 0) {
+		skb_set_tail_pointer(skb, xdp->data_end - xdp->data);
+		skb->len += off; /* positive on grow, negative on shrink */
+	}
+
+	skb->protocol = eth_type_trans(skb, rq->dev);
+
+	metalen = xdp->data - xdp->data_meta;
+	if (metalen)
+		skb_metadata_set(skb, metalen);
+out:
+	return skb;
+drop:
+	stats->rx_drops++;
+xdp_drop:
+	rcu_read_unlock();
+	kfree_skb(skb);
+	return NULL;
+err_xdp:
+	rcu_read_unlock();
+	xdp_return_buff(xdp);
+xdp_xmit:
+	return NULL;
+}
+
+static int veth_xdp_rcv(struct veth_rq *rq, int budget,
+			struct veth_xdp_tx_bq *bq,
+			struct veth_stats *stats)
+{
+	int i, done = 0, n_xdpf = 0;
+	void *xdpf[VETH_XDP_BATCH];
+
+	for (i = 0; i < budget; i++) {
+		void *ptr = __ptr_ring_consume(&rq->xdp_ring);
+
+		if (!ptr)
+			break;
+
+		if (veth_is_xdp_frame(ptr)) {
+			/* ndo_xdp_xmit */
+			struct xdp_frame *frame = veth_ptr_to_xdp(ptr);
+
+			stats->xdp_bytes += xdp_get_frame_len(frame);
+			frame = veth_xdp_rcv_one(rq, frame, bq, stats);
+			if (frame) {
+				/* XDP_PASS */
+				xdpf[n_xdpf++] = frame;
+				if (n_xdpf == VETH_XDP_BATCH) {
+					veth_xdp_rcv_bulk_skb(rq, xdpf, n_xdpf,
+							      bq, stats);
+					n_xdpf = 0;
+				}
+			}
+		} else {
+			/* ndo_start_xmit */
+			struct sk_buff *skb = ptr;
+
+			stats->xdp_bytes += skb->len;
+			skb = veth_xdp_rcv_skb(rq, skb, bq, stats);
+			if (skb) {
+				if (skb_shared(skb) || skb_unclone(skb, GFP_ATOMIC))
+					netif_receive_skb(skb);
+				else
+					napi_gro_receive(&rq->xdp_napi, skb);
+			}
+		}
+		done++;
+	}
+
+	if (n_xdpf)
+		veth_xdp_rcv_bulk_skb(rq, xdpf, n_xdpf, bq, stats);
+
+	u64_stats_update_begin(&rq->stats.syncp);
+	rq->stats.vs.xdp_redirect += stats->xdp_redirect;
+	rq->stats.vs.xdp_bytes += stats->xdp_bytes;
+	rq->stats.vs.xdp_drops += stats->xdp_drops;
+	rq->stats.vs.rx_drops += stats->rx_drops;
+	rq->stats.vs.xdp_packets += done;
+	u64_stats_update_end(&rq->stats.syncp);
+
+	return done;
+}
+
+static int veth_poll(struct napi_struct *napi, int budget)
+{
+	struct veth_rq *rq =
+		container_of(napi, struct veth_rq, xdp_napi);
+	struct veth_priv *priv = netdev_priv(rq->dev);
+	int queue_idx = rq - priv->rq;
+	struct netdev_queue *peer_txq;
+	struct veth_stats stats = {};
+	struct net_device *peer_dev;
+	struct veth_xdp_tx_bq bq;
+	int done;
+
+	bq.count = 0;
+
+	/* NAPI functions as RCU section */
+	peer_dev = rcu_dereference_check(priv->peer, rcu_read_lock_bh_held());
+	peer_txq = (peer_dev && queue_idx < peer_dev->real_num_tx_queues) ?
+		   netdev_get_tx_queue(peer_dev, queue_idx) : NULL;
+
+	xdp_set_return_frame_no_direct();
+	done = veth_xdp_rcv(rq, budget, &bq, &stats);
+
+	if (stats.xdp_redirect > 0)
+		xdp_do_flush();
+	if (stats.xdp_tx > 0)
+		veth_xdp_flush(rq, &bq);
+	xdp_clear_return_frame_no_direct();
+
+	if (done < budget && napi_complete_done(napi, done)) {
+		/* Write rx_notify_masked before reading ptr_ring */
+		smp_store_mb(rq->rx_notify_masked, false);
+		if (unlikely(!__ptr_ring_empty(&rq->xdp_ring))) {
+			if (napi_schedule_prep(&rq->xdp_napi)) {
+				WRITE_ONCE(rq->rx_notify_masked, true);
+				__napi_schedule(&rq->xdp_napi);
+			}
+		}
+	}
+
+	/* Release backpressure per NAPI poll */
+	smp_rmb(); /* Paired with netif_tx_stop_queue set_bit */
+	if (peer_txq && netif_tx_queue_stopped(peer_txq)) {
+		txq_trans_cond_update(peer_txq);
+		netif_tx_wake_queue(peer_txq);
+	}
+
+	return done;
+}
+
+static int veth_create_page_pool(struct veth_rq *rq)
+{
+	struct page_pool_params pp_params = {
+		.order = 0,
+		.pool_size = VETH_RING_SIZE,
+		.nid = NUMA_NO_NODE,
+		.dev = &rq->dev->dev,
+	};
+
+	rq->page_pool = page_pool_create(&pp_params);
+	if (IS_ERR(rq->page_pool)) {
+		int err = PTR_ERR(rq->page_pool);
+
+		rq->page_pool = NULL;
+		return err;
+	}
+
+	return 0;
+}
+
+static int __veth_napi_enable_range(struct net_device *dev, int start, int end)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	int err, i;
+
+	for (i = start; i < end; i++) {
+		err = veth_create_page_pool(&priv->rq[i]);
+		if (err)
+			goto err_page_pool;
+	}
+
+	for (i = start; i < end; i++) {
+		struct veth_rq *rq = &priv->rq[i];
+
+		err = ptr_ring_init(&rq->xdp_ring, VETH_RING_SIZE, GFP_KERNEL);
+		if (err)
+			goto err_xdp_ring;
+	}
+
+	for (i = start; i < end; i++) {
+		struct veth_rq *rq = &priv->rq[i];
+
+		napi_enable(&rq->xdp_napi);
+		rcu_assign_pointer(priv->rq[i].napi, &priv->rq[i].xdp_napi);
+	}
+
+	return 0;
+
+err_xdp_ring:
+	for (i--; i >= start; i--)
+		ptr_ring_cleanup(&priv->rq[i].xdp_ring, veth_ptr_free);
+	i = end;
+err_page_pool:
+	for (i--; i >= start; i--) {
+		page_pool_destroy(priv->rq[i].page_pool);
+		priv->rq[i].page_pool = NULL;
+	}
+
+	return err;
+}
+
+static int __veth_napi_enable(struct net_device *dev)
+{
+	return __veth_napi_enable_range(dev, 0, dev->real_num_rx_queues);
+}
+
+static void veth_napi_del_range(struct net_device *dev, int start, int end)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	int i;
+
+	for (i = start; i < end; i++) {
+		struct veth_rq *rq = &priv->rq[i];
+
+		rcu_assign_pointer(priv->rq[i].napi, NULL);
+		napi_disable(&rq->xdp_napi);
+		__netif_napi_del(&rq->xdp_napi);
+	}
+	synchronize_net();
+
+	for (i = start; i < end; i++) {
+		struct veth_rq *rq = &priv->rq[i];
+
+		rq->rx_notify_masked = false;
+		ptr_ring_cleanup(&rq->xdp_ring, veth_ptr_free);
+	}
+
+	for (i = start; i < end; i++) {
+		page_pool_destroy(priv->rq[i].page_pool);
+		priv->rq[i].page_pool = NULL;
+	}
+}
+
+static void veth_napi_del(struct net_device *dev)
+{
+	veth_napi_del_range(dev, 0, dev->real_num_rx_queues);
+}
+
+static bool veth_gro_requested(const struct net_device *dev)
+{
+	return !!(dev->wanted_features & NETIF_F_GRO);
+}
+
+static int veth_enable_xdp_range(struct net_device *dev, int start, int end,
+				 bool napi_already_on)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	int err, i;
+
+	for (i = start; i < end; i++) {
+		struct veth_rq *rq = &priv->rq[i];
+
+		if (!napi_already_on)
+			netif_napi_add(dev, &rq->xdp_napi, veth_poll);
+		err = xdp_rxq_info_reg(&rq->xdp_rxq, dev, i, rq->xdp_napi.napi_id);
+		if (err < 0)
+			goto err_rxq_reg;
+
+		err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
+						 MEM_TYPE_PAGE_SHARED,
+						 NULL);
+		if (err < 0)
+			goto err_reg_mem;
+
+		/* Save original mem info as it can be overwritten */
+		rq->xdp_mem = rq->xdp_rxq.mem;
+	}
+	return 0;
+
+err_reg_mem:
+	xdp_rxq_info_unreg(&priv->rq[i].xdp_rxq);
+err_rxq_reg:
+	if (!napi_already_on)
+		netif_napi_del(&priv->rq[i].xdp_napi);
+	for (i--; i >= start; i--) {
+		struct veth_rq *rq = &priv->rq[i];
+
+		xdp_rxq_info_unreg(&rq->xdp_rxq);
+		if (!napi_already_on)
+			netif_napi_del(&rq->xdp_napi);
+	}
+
+	return err;
+}
+
+static void veth_disable_xdp_range(struct net_device *dev, int start, int end,
+				   bool delete_napi)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	int i;
+
+	for (i = start; i < end; i++) {
+		struct veth_rq *rq = &priv->rq[i];
+
+		rq->xdp_rxq.mem = rq->xdp_mem;
+		xdp_rxq_info_unreg(&rq->xdp_rxq);
+
+		if (delete_napi)
+			netif_napi_del(&rq->xdp_napi);
+	}
+}
+
+static int veth_enable_xdp(struct net_device *dev)
+{
+	bool napi_already_on = veth_gro_requested(dev) && (dev->flags & IFF_UP);
+	struct veth_priv *priv = netdev_priv(dev);
+	int err, i;
+
+	if (!xdp_rxq_info_is_reg(&priv->rq[0].xdp_rxq)) {
+		err = veth_enable_xdp_range(dev, 0, dev->real_num_rx_queues, napi_already_on);
+		if (err)
+			return err;
+
+		if (!napi_already_on) {
+			err = __veth_napi_enable(dev);
+			if (err) {
+				veth_disable_xdp_range(dev, 0, dev->real_num_rx_queues, true);
+				return err;
+			}
+		}
+	}
+
+	for (i = 0; i < dev->real_num_rx_queues; i++) {
+		rcu_assign_pointer(priv->rq[i].xdp_prog, priv->_xdp_prog);
+		rcu_assign_pointer(priv->rq[i].napi, &priv->rq[i].xdp_napi);
+	}
+
+	return 0;
+}
+
+static void veth_disable_xdp(struct net_device *dev)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	int i;
+
+	for (i = 0; i < dev->real_num_rx_queues; i++)
+		rcu_assign_pointer(priv->rq[i].xdp_prog, NULL);
+
+	if (!netif_running(dev) || !veth_gro_requested(dev))
+		veth_napi_del(dev);
+
+	veth_disable_xdp_range(dev, 0, dev->real_num_rx_queues, false);
+}
+
+static int veth_napi_enable_range(struct net_device *dev, int start, int end)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	int err, i;
+
+	for (i = start; i < end; i++) {
+		struct veth_rq *rq = &priv->rq[i];
+
+		netif_napi_add(dev, &rq->xdp_napi, veth_poll);
+	}
+
+	err = __veth_napi_enable_range(dev, start, end);
+	if (err) {
+		for (i = start; i < end; i++) {
+			struct veth_rq *rq = &priv->rq[i];
+
+			netif_napi_del(&rq->xdp_napi);
+		}
+		return err;
+	}
+	return err;
+}
+
+static int veth_napi_enable(struct net_device *dev)
+{
+	return veth_napi_enable_range(dev, 0, dev->real_num_rx_queues);
+}
+
+static void veth_disable_range_safe(struct net_device *dev, int start, int end)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+
+	if (start >= end)
+		return;
+
+	if (priv->_xdp_prog) {
+		veth_napi_del_range(dev, start, end);
+		veth_disable_xdp_range(dev, start, end, false);
+	} else if (veth_gro_requested(dev)) {
+		veth_napi_del_range(dev, start, end);
+	}
+}
+
+static int veth_enable_range_safe(struct net_device *dev, int start, int end)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	int err;
+
+	if (start >= end)
+		return 0;
+
+	if (priv->_xdp_prog) {
+		/* these channels are freshly initialized, napi is not on there even
+		 * when GRO is requeste
+		 */
+		err = veth_enable_xdp_range(dev, start, end, false);
+		if (err)
+			return err;
+
+		err = __veth_napi_enable_range(dev, start, end);
+		if (err) {
+			/* on error always delete the newly added napis */
+			veth_disable_xdp_range(dev, start, end, true);
+			return err;
+		}
+	} else if (veth_gro_requested(dev)) {
+		return veth_napi_enable_range(dev, start, end);
+	}
+	return 0;
+}
+
+static void veth_set_xdp_features(struct net_device *dev)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	struct net_device *peer;
+
+	peer = rtnl_dereference(priv->peer);
+	if (peer && peer->real_num_tx_queues <= dev->real_num_rx_queues) {
+		struct veth_priv *priv_peer = netdev_priv(peer);
+		xdp_features_t val = NETDEV_XDP_ACT_BASIC |
+				     NETDEV_XDP_ACT_REDIRECT |
+				     NETDEV_XDP_ACT_RX_SG;
+
+		if (priv_peer->_xdp_prog || veth_gro_requested(peer))
+			val |= NETDEV_XDP_ACT_NDO_XMIT |
+			       NETDEV_XDP_ACT_NDO_XMIT_SG;
+		xdp_set_features_flag(dev, val);
+	} else {
+		xdp_clear_features_flag(dev);
+	}
+}
+
+static int veth_set_channels(struct net_device *dev,
+			     struct ethtool_channels *ch)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	unsigned int old_rx_count, new_rx_count;
+	struct veth_priv *peer_priv;
+	struct net_device *peer;
+	int err;
+
+	/* sanity check. Upper bounds are already enforced by the caller */
+	if (!ch->rx_count || !ch->tx_count)
+		return -EINVAL;
+
+	/* avoid braking XDP, if that is enabled */
+	peer = rtnl_dereference(priv->peer);
+	peer_priv = peer ? netdev_priv(peer) : NULL;
+	if (priv->_xdp_prog && peer && ch->rx_count < peer->real_num_tx_queues)
+		return -EINVAL;
+
+	if (peer && peer_priv && peer_priv->_xdp_prog && ch->tx_count > peer->real_num_rx_queues)
+		return -EINVAL;
+
+	old_rx_count = dev->real_num_rx_queues;
+	new_rx_count = ch->rx_count;
+	if (netif_running(dev)) {
+		/* turn device off */
+		netif_carrier_off(dev);
+		if (peer)
+			netif_carrier_off(peer);
+
+		/* try to allocate new resources, as needed*/
+		err = veth_enable_range_safe(dev, old_rx_count, new_rx_count);
+		if (err)
+			goto out;
+	}
+
+	err = netif_set_real_num_rx_queues(dev, ch->rx_count);
+	if (err)
+		goto revert;
+
+	err = netif_set_real_num_tx_queues(dev, ch->tx_count);
+	if (err) {
+		int err2 = netif_set_real_num_rx_queues(dev, old_rx_count);
+
+		/* this error condition could happen only if rx and tx change
+		 * in opposite directions (e.g. tx nr raises, rx nr decreases)
+		 * and we can't do anything to fully restore the original
+		 * status
+		 */
+		if (err2)
+			pr_warn("Can't restore rx queues config %d -> %d %d",
+				new_rx_count, old_rx_count, err2);
+		else
+			goto revert;
+	}
+
+out:
+	if (netif_running(dev)) {
+		/* note that we need to swap the arguments WRT the enable part
+		 * to identify the range we have to disable
+		 */
+		veth_disable_range_safe(dev, new_rx_count, old_rx_count);
+		netif_carrier_on(dev);
+		if (peer)
+			netif_carrier_on(peer);
+	}
+
+	/* update XDP supported features */
+	veth_set_xdp_features(dev);
+	if (peer)
+		veth_set_xdp_features(peer);
+
+	return err;
+
+revert:
+	new_rx_count = old_rx_count;
+	old_rx_count = ch->rx_count;
+	goto out;
+}
+
+static int veth_open(struct net_device *dev)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	struct net_device *peer = rtnl_dereference(priv->peer);
+	int err;
+
+	if (!peer)
+		return -ENOTCONN;
+
+	if (priv->_xdp_prog) {
+		err = veth_enable_xdp(dev);
+		if (err)
+			return err;
+	} else if (veth_gro_requested(dev)) {
+		err = veth_napi_enable(dev);
+		if (err)
+			return err;
+	}
+
+	if (peer->flags & IFF_UP) {
+		netif_carrier_on(dev);
+		netif_carrier_on(peer);
+	}
+
+	veth_set_xdp_features(dev);
+
+	return 0;
+}
+
+static int veth_close(struct net_device *dev)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	struct net_device *peer = rtnl_dereference(priv->peer);
+
+	netif_carrier_off(dev);
+	if (peer)
+		netif_carrier_off(peer);
+
+	if (priv->_xdp_prog)
+		veth_disable_xdp(dev);
+	else if (veth_gro_requested(dev))
+		veth_napi_del(dev);
+
+	return 0;
+}
+
+static int is_valid_veth_mtu(int mtu)
+{
+	return mtu >= ETH_MIN_MTU && mtu <= ETH_MAX_MTU;
+}
+
+static int veth_alloc_queues(struct net_device *dev)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	int i;
+
+	priv->rq = kvzalloc_objs(*priv->rq, dev->num_rx_queues,
+				 GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL);
+	if (!priv->rq)
+		return -ENOMEM;
+
+	for (i = 0; i < dev->num_rx_queues; i++) {
+		priv->rq[i].dev = dev;
+		u64_stats_init(&priv->rq[i].stats.syncp);
+	}
+
+	return 0;
+}
+
+static void veth_free_queues(struct net_device *dev)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+
+	kvfree(priv->rq);
+}
+
+static int veth_dev_init(struct net_device *dev)
+{
+	netdev_lockdep_set_classes(dev);
+	return veth_alloc_queues(dev);
+}
+
+static void veth_dev_free(struct net_device *dev)
+{
+	veth_free_queues(dev);
+}
+
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void veth_poll_controller(struct net_device *dev)
+{
+	/* veth only receives frames when its peer sends one
+	 * Since it has nothing to do with disabling irqs, we are guaranteed
+	 * never to have pending data when we poll for it so
+	 * there is nothing to do here.
+	 *
+	 * We need this though so netpoll recognizes us as an interface that
+	 * supports polling, which enables bridge devices in virt setups to
+	 * still use netconsole
+	 */
+}
+#endif	/* CONFIG_NET_POLL_CONTROLLER */
+
+static int veth_get_iflink(const struct net_device *dev)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	struct net_device *peer;
+	int iflink;
+
+	rcu_read_lock();
+	peer = rcu_dereference(priv->peer);
+	iflink = peer ? READ_ONCE(peer->ifindex) : 0;
+	rcu_read_unlock();
+
+	return iflink;
+}
+
+static netdev_features_t veth_fix_features(struct net_device *dev,
+					   netdev_features_t features)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	struct net_device *peer;
+
+	peer = rtnl_dereference(priv->peer);
+	if (peer) {
+		struct veth_priv *peer_priv = netdev_priv(peer);
+
+		if (peer_priv->_xdp_prog)
+			features &= ~NETIF_F_GSO_SOFTWARE;
+	}
+
+	return features;
+}
+
+static int veth_set_features(struct net_device *dev,
+			     netdev_features_t features)
+{
+	netdev_features_t changed = features ^ dev->features;
+	struct veth_priv *priv = netdev_priv(dev);
+	struct net_device *peer;
+	int err;
+
+	if (!(changed & NETIF_F_GRO) || !(dev->flags & IFF_UP) || priv->_xdp_prog)
+		return 0;
+
+	peer = rtnl_dereference(priv->peer);
+	if (features & NETIF_F_GRO) {
+		err = veth_napi_enable(dev);
+		if (err)
+			return err;
+
+		if (peer)
+			xdp_features_set_redirect_target(peer, true);
+	} else {
+		if (peer)
+			xdp_features_clear_redirect_target(peer);
+		veth_napi_del(dev);
+	}
+	return 0;
+}
+
+static void veth_set_rx_headroom(struct net_device *dev, int new_hr)
+{
+	struct veth_priv *peer_priv, *priv = netdev_priv(dev);
+	struct net_device *peer;
+
+	if (new_hr < 0)
+		new_hr = 0;
+
+	rcu_read_lock();
+	peer = rcu_dereference(priv->peer);
+	if (unlikely(!peer))
+		goto out;
+
+	peer_priv = netdev_priv(peer);
+	priv->requested_headroom = new_hr;
+	new_hr = max(priv->requested_headroom, peer_priv->requested_headroom);
+	dev->needed_headroom = new_hr;
+	peer->needed_headroom = new_hr;
+
+out:
+	rcu_read_unlock();
+}
+
+static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog,
+			struct netlink_ext_ack *extack)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	struct bpf_prog *old_prog;
+	struct net_device *peer;
+	unsigned int max_mtu;
+	int err;
+
+	old_prog = priv->_xdp_prog;
+	priv->_xdp_prog = prog;
+	peer = rtnl_dereference(priv->peer);
+
+	if (prog) {
+		if (!peer) {
+			NL_SET_ERR_MSG_MOD(extack, "Cannot set XDP when peer is detached");
+			err = -ENOTCONN;
+			goto err;
+		}
+
+		max_mtu = SKB_WITH_OVERHEAD(PAGE_SIZE - VETH_XDP_HEADROOM) -
+			  peer->hard_header_len;
+		/* Allow increasing the max_mtu if the program supports
+		 * XDP fragments.
+		 */
+		if (prog->aux->xdp_has_frags)
+			max_mtu += PAGE_SIZE * MAX_SKB_FRAGS;
+
+		if (peer->mtu > max_mtu) {
+			NL_SET_ERR_MSG_MOD(extack, "Peer MTU is too large to set XDP");
+			err = -ERANGE;
+			goto err;
+		}
+
+		if (dev->real_num_rx_queues < peer->real_num_tx_queues) {
+			NL_SET_ERR_MSG_MOD(extack, "XDP expects number of rx queues not less than peer tx queues");
+			err = -ENOSPC;
+			goto err;
+		}
+
+		if (dev->flags & IFF_UP) {
+			err = veth_enable_xdp(dev);
+			if (err) {
+				NL_SET_ERR_MSG_MOD(extack, "Setup for XDP failed");
+				goto err;
+			}
+		}
+
+		if (!old_prog) {
+			peer->hw_features &= ~NETIF_F_GSO_SOFTWARE;
+			peer->max_mtu = max_mtu;
+		}
+
+		xdp_features_set_redirect_target(peer, true);
+	}
+
+	if (old_prog) {
+		if (!prog) {
+			if (peer && !veth_gro_requested(dev))
+				xdp_features_clear_redirect_target(peer);
+
+			if (dev->flags & IFF_UP)
+				veth_disable_xdp(dev);
+
+			if (peer) {
+				peer->hw_features |= NETIF_F_GSO_SOFTWARE;
+				peer->max_mtu = ETH_MAX_MTU;
+			}
+		}
+		bpf_prog_put(old_prog);
+	}
+
+	if ((!!old_prog ^ !!prog) && peer)
+		netdev_update_features(peer);
+
+	return 0;
+err:
+	priv->_xdp_prog = old_prog;
+
+	return err;
+}
+
+static int veth_xdp(struct net_device *dev, struct netdev_bpf *xdp)
+{
+	switch (xdp->command) {
+	case XDP_SETUP_PROG:
+		return veth_xdp_set(dev, xdp->prog, xdp->extack);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int veth_xdp_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp)
+{
+	struct veth_xdp_buff *_ctx = (void *)ctx;
+
+	if (!_ctx->skb)
+		return -ENODATA;
+
+	*timestamp = skb_hwtstamps(_ctx->skb)->hwtstamp;
+	return 0;
+}
+
+static int veth_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash,
+			    enum xdp_rss_hash_type *rss_type)
+{
+	struct veth_xdp_buff *_ctx = (void *)ctx;
+	struct sk_buff *skb = _ctx->skb;
+
+	if (!skb)
+		return -ENODATA;
+
+	*hash = skb_get_hash(skb);
+	*rss_type = skb->l4_hash ? XDP_RSS_TYPE_L4_ANY : XDP_RSS_TYPE_NONE;
+
+	return 0;
+}
+
+static int veth_xdp_rx_vlan_tag(const struct xdp_md *ctx, __be16 *vlan_proto,
+				u16 *vlan_tci)
+{
+	const struct veth_xdp_buff *_ctx = (void *)ctx;
+	const struct sk_buff *skb = _ctx->skb;
+	int err;
+
+	if (!skb)
+		return -ENODATA;
+
+	err = __vlan_hwaccel_get_tag(skb, vlan_tci);
+	if (err)
+		return err;
+
+	*vlan_proto = skb->vlan_proto;
+	return err;
+}
+
+static const struct net_device_ops veth_netdev_ops = {
+	.ndo_init            = veth_dev_init,
+	.ndo_open            = veth_open,
+	.ndo_stop            = veth_close,
+	.ndo_start_xmit      = veth_xmit,
+	.ndo_get_stats64     = veth_get_stats64,
+	.ndo_set_rx_mode     = veth_set_multicast_list,
+	.ndo_set_mac_address = eth_mac_addr,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller	= veth_poll_controller,
+#endif
+	.ndo_get_iflink		= veth_get_iflink,
+	.ndo_fix_features	= veth_fix_features,
+	.ndo_set_features	= veth_set_features,
+	.ndo_features_check	= passthru_features_check,
+	.ndo_set_rx_headroom	= veth_set_rx_headroom,
+	.ndo_bpf		= veth_xdp,
+	.ndo_xdp_xmit		= veth_ndo_xdp_xmit,
+	.ndo_get_peer_dev	= veth_peer_dev,
+};
+
+static const struct xdp_metadata_ops veth_xdp_metadata_ops = {
+	.xmo_rx_timestamp		= veth_xdp_rx_timestamp,
+	.xmo_rx_hash			= veth_xdp_rx_hash,
+	.xmo_rx_vlan_tag		= veth_xdp_rx_vlan_tag,
+};
+
+#define VETH_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | \
+		       NETIF_F_RXCSUM | NETIF_F_SCTP_CRC | NETIF_F_HIGHDMA | \
+		       NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL | \
+		       NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | \
+		       NETIF_F_HW_VLAN_STAG_TX | NETIF_F_HW_VLAN_STAG_RX )
+
+static void veth_setup(struct net_device *dev)
+{
+	ether_setup(dev);
+
+	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
+	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+	dev->priv_flags |= IFF_NO_QUEUE;
+	dev->priv_flags |= IFF_PHONY_HEADROOM;
+	dev->priv_flags |= IFF_DISABLE_NETPOLL;
+	dev->lltx = true;
+
+	dev->netdev_ops = &veth_netdev_ops;
+	dev->xdp_metadata_ops = &veth_xdp_metadata_ops;
+	dev->ethtool_ops = &veth_ethtool_ops;
+	dev->features |= VETH_FEATURES;
+	dev->vlan_features = dev->features &
+			     ~(NETIF_F_HW_VLAN_CTAG_TX |
+			       NETIF_F_HW_VLAN_STAG_TX |
+			       NETIF_F_HW_VLAN_CTAG_RX |
+			       NETIF_F_HW_VLAN_STAG_RX);
+	dev->needs_free_netdev = true;
+	dev->priv_destructor = veth_dev_free;
+	dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS;
+	dev->max_mtu = ETH_MAX_MTU;
+
+	dev->hw_features = VETH_FEATURES;
+	dev->hw_enc_features = VETH_FEATURES;
+	dev->mpls_features = NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE;
+	netif_set_tso_max_size(dev, GSO_MAX_SIZE);
+}
+
+/*
+ * netlink interface
+ */
+
+static int veth_validate(struct nlattr *tb[], struct nlattr *data[],
+			 struct netlink_ext_ack *extack)
+{
+	if (tb[IFLA_ADDRESS]) {
+		if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN)
+			return -EINVAL;
+		if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS])))
+			return -EADDRNOTAVAIL;
+	}
+	if (tb[IFLA_MTU]) {
+		if (!is_valid_veth_mtu(nla_get_u32(tb[IFLA_MTU])))
+			return -EINVAL;
+	}
+	return 0;
+}
+
+static struct rtnl_link_ops veth_link_ops;
+
+static void veth_disable_gro(struct net_device *dev)
+{
+	dev->features &= ~NETIF_F_GRO;
+	dev->wanted_features &= ~NETIF_F_GRO;
+	netdev_update_features(dev);
+}
+
+static int veth_init_queues(struct net_device *dev, struct nlattr *tb[])
+{
+	int err;
+
+	if (!tb[IFLA_NUM_TX_QUEUES] && dev->num_tx_queues > 1) {
+		err = netif_set_real_num_tx_queues(dev, 1);
+		if (err)
+			return err;
+	}
+	if (!tb[IFLA_NUM_RX_QUEUES] && dev->num_rx_queues > 1) {
+		err = netif_set_real_num_rx_queues(dev, 1);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+static int veth_newlink(struct net_device *dev,
+			struct rtnl_newlink_params *params,
+			struct netlink_ext_ack *extack)
+{
+	struct net *peer_net = rtnl_newlink_peer_net(params);
+	struct nlattr **data = params->data;
+	struct nlattr **tb = params->tb;
+	int err;
+	struct net_device *peer;
+	struct veth_priv *priv;
+	char ifname[IFNAMSIZ];
+	struct nlattr *peer_tb[IFLA_MAX + 1], **tbp;
+	unsigned char name_assign_type;
+	struct ifinfomsg *ifmp;
+
+	/*
+	 * create and register peer first
+	 */
+	if (data && data[VETH_INFO_PEER]) {
+		struct nlattr *nla_peer = data[VETH_INFO_PEER];
+
+		ifmp = nla_data(nla_peer);
+		rtnl_nla_parse_ifinfomsg(peer_tb, nla_peer, extack);
+		tbp = peer_tb;
+	} else {
+		ifmp = NULL;
+		tbp = tb;
+	}
+
+	if (ifmp && tbp[IFLA_IFNAME]) {
+		nla_strscpy(ifname, tbp[IFLA_IFNAME], IFNAMSIZ);
+		name_assign_type = NET_NAME_USER;
+	} else {
+		snprintf(ifname, IFNAMSIZ, DRV_NAME "%%d");
+		name_assign_type = NET_NAME_ENUM;
+	}
+
+	peer = rtnl_create_link(peer_net, ifname, name_assign_type,
+				&veth_link_ops, tbp, extack);
+	if (IS_ERR(peer))
+		return PTR_ERR(peer);
+
+	if (!ifmp || !tbp[IFLA_ADDRESS])
+		eth_hw_addr_random(peer);
+
+	if (ifmp && (dev->ifindex != 0))
+		peer->ifindex = ifmp->ifi_index;
+
+	netif_inherit_tso_max(peer, dev);
+
+	err = register_netdevice(peer);
+	if (err < 0)
+		goto err_register_peer;
+
+	/* keep GRO disabled by default to be consistent with the established
+	 * veth behavior
+	 */
+	veth_disable_gro(peer);
+	netif_carrier_off(peer);
+
+	err = rtnl_configure_link(peer, ifmp, 0, NULL);
+	if (err < 0)
+		goto err_configure_peer;
+
+	/*
+	 * register dev last
+	 *
+	 * note, that since we've registered new device the dev's name
+	 * should be re-allocated
+	 */
+
+	if (tb[IFLA_ADDRESS] == NULL)
+		eth_hw_addr_random(dev);
+
+	if (tb[IFLA_IFNAME])
+		nla_strscpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ);
+	else
+		snprintf(dev->name, IFNAMSIZ, DRV_NAME "%%d");
+
+	err = register_netdevice(dev);
+	if (err < 0)
+		goto err_register_dev;
+
+	netif_carrier_off(dev);
+
+	/*
+	 * tie the deviced together
+	 */
+
+	priv = netdev_priv(dev);
+	rcu_assign_pointer(priv->peer, peer);
+	netdev_hold(peer, &priv->peer_tracker, GFP_KERNEL);
+	err = veth_init_queues(dev, tb);
+	if (err)
+		goto err_queues;
+
+	priv = netdev_priv(peer);
+	rcu_assign_pointer(priv->peer, dev);
+	netdev_hold(dev, &priv->peer_tracker, GFP_KERNEL);
+	err = veth_init_queues(peer, tb);
+	if (err)
+		goto err_peer_queues;
+
+	veth_disable_gro(dev);
+	/* update XDP supported features */
+	veth_set_xdp_features(dev);
+	veth_set_xdp_features(peer);
+
+	return 0;
+
+err_peer_queues:
+	netdev_put(dev, &priv->peer_tracker);
+	priv = netdev_priv(dev);
+err_queues:
+	netdev_put(peer, &priv->peer_tracker);
+	unregister_netdevice(dev);
+err_register_dev:
+	/* nothing to do */
+err_configure_peer:
+	unregister_netdevice(peer);
+	return err;
+
+err_register_peer:
+	free_netdev(peer);
+	return err;
+}
+
+static void veth_dellink(struct net_device *dev, struct list_head *head)
+{
+	netdevice_tracker *peer_tracker;
+	struct net_device *peer;
+	struct veth_priv *priv;
+
+	priv = netdev_priv(dev);
+	peer_tracker = &priv->peer_tracker;
+	peer = unrcu_pointer(xchg(&priv->peer, NULL));
+	if (!peer)
+		return;
+
+	unregister_netdevice_queue(dev, head);
+
+	priv = netdev_priv(peer);
+	dev = unrcu_pointer(xchg(&priv->peer, NULL));
+	if (dev)
+		unregister_netdevice_queue_net(dev_net(dev), peer, head);
+
+	netdev_put(peer, peer_tracker);
+	netdev_put(dev, &priv->peer_tracker);
+}
+
+static const struct nla_policy veth_policy[VETH_INFO_MAX + 1] = {
+	[VETH_INFO_PEER]	= { .len = sizeof(struct ifinfomsg) },
+};
+
+static struct net *veth_get_link_net(const struct net_device *dev)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	struct net_device *peer = rtnl_dereference(priv->peer);
+
+	return peer ? dev_net(peer) : dev_net(dev);
+}
+
+static unsigned int veth_get_num_queues(void)
+{
+	/* enforce the same queue limit as rtnl_create_link */
+	int queues = num_possible_cpus();
+
+	if (queues > 4096)
+		queues = 4096;
+	return queues;
+}
+
+static struct rtnl_link_ops veth_link_ops = {
+	.kind		= DRV_NAME,
+	.priv_size	= sizeof(struct veth_priv),
+	.setup		= veth_setup,
+	.validate	= veth_validate,
+	.newlink	= veth_newlink,
+	.dellink	= veth_dellink,
+	.policy		= veth_policy,
+	.peer_type	= VETH_INFO_PEER,
+	.maxtype	= VETH_INFO_MAX,
+	.get_link_net	= veth_get_link_net,
+	.get_num_tx_queues	= veth_get_num_queues,
+	.get_num_rx_queues	= veth_get_num_queues,
+};
+
+/*
+ * init/fini
+ */
+
+static __init int veth_init(void)
+{
+	return rtnl_link_register(&veth_link_ops);
+}
+
+static __exit void veth_exit(void)
+{
+	rtnl_link_unregister(&veth_link_ops);
+}
+
+module_init(veth_init);
+module_exit(veth_exit);
+
+MODULE_DESCRIPTION("Virtual Ethernet Tunnel");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_RTNL_LINK(DRV_NAME);