Merge branch 'virtio_udp_tunnel_08_07_2025' of https://github.com/pabeni/linux-devel

Paolo Abeni says:

====================
virtio: introduce GSO over UDP tunnel

Some virtualized deployments use UDP tunnel pervasively and are impacted
negatively by the lack of GSO support for such kind of traffic in the
virtual NIC driver.

The virtio_net specification recently introduced support for GSO over
UDP tunnel, this series updates the virtio implementation to support
such a feature.

Currently the kernel virtio support limits the feature space to 64,
while the virtio specification allows for a larger number of features.
Specifically the GSO-over-UDP-tunnel-related virtio features use bits
65-69.

The first four patches in this series rework the virtio and vhost
feature support to cope with up to 128 bits. The limit is set by
a define and could be easily raised in future, as needed.

This implementation choice is aimed at keeping the code churn as
limited as possible. For the same reason, only the virtio_net driver is
reworked to leverage the extended feature space; all other
virtio/vhost drivers are unaffected, but could be upgraded to support
the extended features space in a later time.

The last four patches bring in the actual GSO over UDP tunnel support.
As per specification, some additional fields are introduced into the
virtio net header to support the new offload. The presence of such
fields depends on the negotiated features.

New helpers are introduced to convert the UDP-tunneled skb metadata to
an extended virtio net header and vice versa. Such helpers are used by
the tun and virtio_net driver to cope with the newly supported offloads.

Tested with basic stream transfer with all the possible permutations of
host kernel/qemu/guest kernel with/without GSO over UDP tunnel support.
====================

Link: https://patch.msgid.link/cover.1751874094.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

20 files changed, 790 insertions, 164 deletions

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 447c37959504..49bcd12a4ac8 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -186,7 +186,8 @@ struct tun_struct {
 	struct net_device	*dev;
 	netdev_features_t	set_features;
 #define TUN_USER_FEATURES (NETIF_F_HW_CSUM|NETIF_F_TSO_ECN|NETIF_F_TSO| \
-			  NETIF_F_TSO6 | NETIF_F_GSO_UDP_L4)
+			  NETIF_F_TSO6 | NETIF_F_GSO_UDP_L4 | \
+			  NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM)
 
 	int			align;
 	int			vnet_hdr_sz;
@@ -925,6 +926,7 @@ static int tun_net_init(struct net_device *dev)
 	dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST |
 			   TUN_USER_FEATURES | NETIF_F_HW_VLAN_CTAG_TX |
 			   NETIF_F_HW_VLAN_STAG_TX;
+	dev->hw_enc_features = dev->hw_features;
 	dev->features = dev->hw_features;
 	dev->vlan_features = dev->features &
 			     ~(NETIF_F_HW_VLAN_CTAG_TX |
@@ -1698,7 +1700,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	struct sk_buff *skb;
 	size_t total_len = iov_iter_count(from);
 	size_t len = total_len, align = tun->align, linear;
-	struct virtio_net_hdr gso = { 0 };
+	struct virtio_net_hdr_v1_hash_tunnel hdr;
+	struct virtio_net_hdr *gso;
 	int good_linear;
 	int copylen;
 	int hdr_len = 0;
@@ -1708,6 +1711,15 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	int skb_xdp = 1;
 	bool frags = tun_napi_frags_enabled(tfile);
 	enum skb_drop_reason drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
+	netdev_features_t features = 0;
+
+	/*
+	 * Keep it easy and always zero the whole buffer, even if the
+	 * tunnel-related field will be touched only when the feature
+	 * is enabled and the hdr size id compatible.
+	 */
+	memset(&hdr, 0, sizeof(hdr));
+	gso = (struct virtio_net_hdr *)&hdr;
 
 	if (!(tun->flags & IFF_NO_PI)) {
 		if (len < sizeof(pi))
@@ -1721,7 +1733,9 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	if (tun->flags & IFF_VNET_HDR) {
 		int vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz);
 
-		hdr_len = tun_vnet_hdr_get(vnet_hdr_sz, tun->flags, from, &gso);
+		features = tun_vnet_hdr_guest_features(vnet_hdr_sz);
+		hdr_len = __tun_vnet_hdr_get(vnet_hdr_sz, tun->flags,
+					     features, from, gso);
 		if (hdr_len < 0)
 			return hdr_len;
 
@@ -1755,7 +1769,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		 * (e.g gso or jumbo packet), we will do it at after
 		 * skb was created with generic XDP routine.
 		 */
-		skb = tun_build_skb(tun, tfile, from, &gso, len, &skb_xdp);
+		skb = tun_build_skb(tun, tfile, from, gso, len, &skb_xdp);
 		err = PTR_ERR_OR_ZERO(skb);
 		if (err)
 			goto drop;
@@ -1799,7 +1813,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		}
 	}
 
-	if (tun_vnet_hdr_to_skb(tun->flags, skb, &gso)) {
+	if (tun_vnet_hdr_tnl_to_skb(tun->flags, features, skb, &hdr)) {
 		atomic_long_inc(&tun->rx_frame_errors);
 		err = -EINVAL;
 		goto free_skb;
@@ -2050,13 +2064,21 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 	}
 
 	if (vnet_hdr_sz) {
-		struct virtio_net_hdr gso;
+		struct virtio_net_hdr_v1_hash_tunnel hdr;
+		struct virtio_net_hdr *gso;
 
-		ret = tun_vnet_hdr_from_skb(tun->flags, tun->dev, skb, &gso);
+		ret = tun_vnet_hdr_tnl_from_skb(tun->flags, tun->dev, skb,
+						&hdr);
 		if (ret)
 			return ret;
 
-		ret = tun_vnet_hdr_put(vnet_hdr_sz, iter, &gso);
+		/*
+		 * Drop the packet if the configured header size is too small
+		 * WRT the enabled offloads.
+		 */
+		gso = (struct virtio_net_hdr *)&hdr;
+		ret = __tun_vnet_hdr_put(vnet_hdr_sz, tun->dev->features,
+					 iter, gso);
 		if (ret)
 			return ret;
 	}
@@ -2357,9 +2379,11 @@ static int tun_xdp_one(struct tun_struct *tun,
 {
 	unsigned int datasize = xdp->data_end - xdp->data;
 	struct virtio_net_hdr *gso = xdp->data_hard_start;
+	struct virtio_net_hdr_v1_hash_tunnel *tnl_hdr;
 	struct bpf_prog *xdp_prog;
 	struct sk_buff *skb = NULL;
 	struct sk_buff_head *queue;
+	netdev_features_t features;
 	u32 rxhash = 0, act;
 	int buflen = xdp->frame_sz;
 	int metasize = 0;
@@ -2425,7 +2449,9 @@ build:
 	if (metasize > 0)
 		skb_metadata_set(skb, metasize);
 
-	if (tun_vnet_hdr_to_skb(tun->flags, skb, gso)) {
+	features = tun_vnet_hdr_guest_features(READ_ONCE(tun->vnet_hdr_sz));
+	tnl_hdr = (struct virtio_net_hdr_v1_hash_tunnel *)gso;
+	if (tun_vnet_hdr_tnl_to_skb(tun->flags, features, skb, tnl_hdr)) {
 		atomic_long_inc(&tun->rx_frame_errors);
 		kfree_skb(skb);
 		ret = -EINVAL;
@@ -2811,6 +2837,8 @@ static void tun_get_iff(struct tun_struct *tun, struct ifreq *ifr)
 
 }
 
+#define PLAIN_GSO (NETIF_F_GSO_UDP_L4 | NETIF_F_TSO | NETIF_F_TSO6)
+
 /* This is like a cut-down ethtool ops, except done via tun fd so no
  * privs required. */
 static int set_offload(struct tun_struct *tun, unsigned long arg)
@@ -2840,6 +2868,18 @@ static int set_offload(struct tun_struct *tun, unsigned long arg)
 			features |= NETIF_F_GSO_UDP_L4;
 			arg &= ~(TUN_F_USO4 | TUN_F_USO6);
 		}
+
+		/*
+		 * Tunnel offload is allowed only if some plain offload is
+		 * available, too.
+		 */
+		if (features & PLAIN_GSO && arg & TUN_F_UDP_TUNNEL_GSO) {
+			features |= NETIF_F_GSO_UDP_TUNNEL;
+			if (arg & TUN_F_UDP_TUNNEL_GSO_CSUM)
+				features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
+			arg &= ~(TUN_F_UDP_TUNNEL_GSO |
+				 TUN_F_UDP_TUNNEL_GSO_CSUM);
+		}
 	}
 
 	/* This gives the user a way to test for new features in future by
diff --git a/drivers/net/tun_vnet.h b/drivers/net/tun_vnet.h
index 58b9ac7a5fc4..81662328b2c7 100644
--- a/drivers/net/tun_vnet.h
+++ b/drivers/net/tun_vnet.h
@@ -6,6 +6,8 @@
 #define TUN_VNET_LE     0x80000000
 #define TUN_VNET_BE     0x40000000
 
+#define TUN_VNET_TNL_SIZE	sizeof(struct virtio_net_hdr_v1_hash_tunnel)
+
 static inline bool tun_vnet_legacy_is_little_endian(unsigned int flags)
 {
 	bool be = IS_ENABLED(CONFIG_TUN_VNET_CROSS_LE) &&
@@ -107,16 +109,26 @@ static inline long tun_vnet_ioctl(int *vnet_hdr_sz, unsigned int *flags,
 	}
 }
 
-static inline int tun_vnet_hdr_get(int sz, unsigned int flags,
-				   struct iov_iter *from,
-				   struct virtio_net_hdr *hdr)
+static inline unsigned int tun_vnet_parse_size(netdev_features_t features)
+{
+	if (!(features & NETIF_F_GSO_UDP_TUNNEL))
+		return sizeof(struct virtio_net_hdr);
+
+	return TUN_VNET_TNL_SIZE;
+}
+
+static inline int __tun_vnet_hdr_get(int sz, unsigned int flags,
+				     netdev_features_t features,
+				     struct iov_iter *from,
+				     struct virtio_net_hdr *hdr)
 {
+	unsigned int parsed_size = tun_vnet_parse_size(features);
 	u16 hdr_len;
 
 	if (iov_iter_count(from) < sz)
 		return -EINVAL;
 
-	if (!copy_from_iter_full(hdr, sizeof(*hdr), from))
+	if (!copy_from_iter_full(hdr, parsed_size, from))
 		return -EFAULT;
 
 	hdr_len = tun_vnet16_to_cpu(flags, hdr->hdr_len);
@@ -129,32 +141,70 @@ static inline int tun_vnet_hdr_get(int sz, unsigned int flags,
 	if (hdr_len > iov_iter_count(from))
 		return -EINVAL;
 
-	iov_iter_advance(from, sz - sizeof(*hdr));
+	iov_iter_advance(from, sz - parsed_size);
 
 	return hdr_len;
 }
 
-static inline int tun_vnet_hdr_put(int sz, struct iov_iter *iter,
-				   const struct virtio_net_hdr *hdr)
+static inline int tun_vnet_hdr_get(int sz, unsigned int flags,
+				   struct iov_iter *from,
+				   struct virtio_net_hdr *hdr)
+{
+	return __tun_vnet_hdr_get(sz, flags, 0, from, hdr);
+}
+
+static inline int __tun_vnet_hdr_put(int sz, netdev_features_t features,
+				     struct iov_iter *iter,
+				     const struct virtio_net_hdr *hdr)
 {
+	unsigned int parsed_size = tun_vnet_parse_size(features);
+
 	if (unlikely(iov_iter_count(iter) < sz))
 		return -EINVAL;
 
-	if (unlikely(copy_to_iter(hdr, sizeof(*hdr), iter) != sizeof(*hdr)))
+	if (unlikely(copy_to_iter(hdr, parsed_size, iter) != parsed_size))
 		return -EFAULT;
 
-	if (iov_iter_zero(sz - sizeof(*hdr), iter) != sz - sizeof(*hdr))
+	if (iov_iter_zero(sz - parsed_size, iter) != sz - parsed_size)
 		return -EFAULT;
 
 	return 0;
 }
 
+static inline int tun_vnet_hdr_put(int sz, struct iov_iter *iter,
+				   const struct virtio_net_hdr *hdr)
+{
+	return __tun_vnet_hdr_put(sz, 0, iter, hdr);
+}
+
 static inline int tun_vnet_hdr_to_skb(unsigned int flags, struct sk_buff *skb,
 				      const struct virtio_net_hdr *hdr)
 {
 	return virtio_net_hdr_to_skb(skb, hdr, tun_vnet_is_little_endian(flags));
 }
 
+/*
+ * Tun is not aware of the negotiated guest features, guess them from the
+ * virtio net hdr size
+ */
+static inline netdev_features_t tun_vnet_hdr_guest_features(int vnet_hdr_sz)
+{
+	if (vnet_hdr_sz >= TUN_VNET_TNL_SIZE)
+		return NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM;
+	return 0;
+}
+
+static inline int
+tun_vnet_hdr_tnl_to_skb(unsigned int flags, netdev_features_t features,
+			struct sk_buff *skb,
+			const struct virtio_net_hdr_v1_hash_tunnel *hdr)
+{
+	return virtio_net_hdr_tnl_to_skb(skb, hdr,
+				features & NETIF_F_GSO_UDP_TUNNEL,
+				features & NETIF_F_GSO_UDP_TUNNEL_CSUM,
+				tun_vnet_is_little_endian(flags));
+}
+
 static inline int tun_vnet_hdr_from_skb(unsigned int flags,
 					const struct net_device *dev,
 					const struct sk_buff *skb,
@@ -183,4 +233,37 @@ static inline int tun_vnet_hdr_from_skb(unsigned int flags,
 	return 0;
 }
 
+static inline int
+tun_vnet_hdr_tnl_from_skb(unsigned int flags,
+			  const struct net_device *dev,
+			  const struct sk_buff *skb,
+			  struct virtio_net_hdr_v1_hash_tunnel *tnl_hdr)
+{
+	bool has_tnl_offload = !!(dev->features & NETIF_F_GSO_UDP_TUNNEL);
+	int vlan_hlen = skb_vlan_tag_present(skb) ? VLAN_HLEN : 0;
+
+	if (virtio_net_hdr_tnl_from_skb(skb, tnl_hdr, has_tnl_offload,
+					tun_vnet_is_little_endian(flags),
+					vlan_hlen)) {
+		struct virtio_net_hdr_v1 *hdr = &tnl_hdr->hash_hdr.hdr;
+		struct skb_shared_info *sinfo = skb_shinfo(skb);
+
+		if (net_ratelimit()) {
+			int hdr_len = tun_vnet16_to_cpu(flags, hdr->hdr_len);
+
+			netdev_err(dev, "unexpected GSO type: 0x%x, gso_size %d, hdr_len %d\n",
+				   sinfo->gso_type,
+				   tun_vnet16_to_cpu(flags, hdr->gso_size),
+				   tun_vnet16_to_cpu(flags, hdr->hdr_len));
+			print_hex_dump(KERN_ERR, "tun: ", DUMP_PREFIX_NONE,
+				       16, 1, skb->head, min(hdr_len, 64),
+				       true);
+		}
+		WARN_ON_ONCE(1);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 #endif /* TUN_VNET_H */
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 4d995a47a116..64453f4da825 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -35,6 +35,23 @@ module_param(csum, bool, 0444);
 module_param(gso, bool, 0444);
 module_param(napi_tx, bool, 0644);
 
+#define VIRTIO_OFFLOAD_MAP_MIN	46
+#define VIRTIO_OFFLOAD_MAP_MAX	47
+#define VIRTIO_FEATURES_MAP_MIN	65
+#define VIRTIO_O2F_DELTA	(VIRTIO_FEATURES_MAP_MIN - \
+				 VIRTIO_OFFLOAD_MAP_MIN)
+
+static bool virtio_is_mapped_offload(unsigned int obit)
+{
+	return obit >= VIRTIO_OFFLOAD_MAP_MIN &&
+	       obit <= VIRTIO_OFFLOAD_MAP_MAX;
+}
+
+static unsigned int virtio_offload_to_feature(unsigned int obit)
+{
+	return virtio_is_mapped_offload(obit) ? obit + VIRTIO_O2F_DELTA : obit;
+}
+
 /* FIXME: MTU in config. */
 #define GOOD_PACKET_LEN (ETH_HLEN + VLAN_HLEN + ETH_DATA_LEN)
 #define GOOD_COPY_LEN	128
@@ -62,15 +79,19 @@ static const unsigned long guest_offloads[] = {
 	VIRTIO_NET_F_GUEST_CSUM,
 	VIRTIO_NET_F_GUEST_USO4,
 	VIRTIO_NET_F_GUEST_USO6,
-	VIRTIO_NET_F_GUEST_HDRLEN
+	VIRTIO_NET_F_GUEST_HDRLEN,
+	VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_MAPPED,
+	VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_CSUM_MAPPED,
 };
 
 #define GUEST_OFFLOAD_GRO_HW_MASK ((1ULL << VIRTIO_NET_F_GUEST_TSO4) | \
-				(1ULL << VIRTIO_NET_F_GUEST_TSO6) | \
-				(1ULL << VIRTIO_NET_F_GUEST_ECN)  | \
-				(1ULL << VIRTIO_NET_F_GUEST_UFO)  | \
-				(1ULL << VIRTIO_NET_F_GUEST_USO4) | \
-				(1ULL << VIRTIO_NET_F_GUEST_USO6))
+			(1ULL << VIRTIO_NET_F_GUEST_TSO6) | \
+			(1ULL << VIRTIO_NET_F_GUEST_ECN)  | \
+			(1ULL << VIRTIO_NET_F_GUEST_UFO)  | \
+			(1ULL << VIRTIO_NET_F_GUEST_USO4) | \
+			(1ULL << VIRTIO_NET_F_GUEST_USO6) | \
+			(1ULL << VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_MAPPED) | \
+			(1ULL << VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_CSUM_MAPPED))
 
 struct virtnet_stat_desc {
 	char desc[ETH_GSTRING_LEN];
@@ -423,6 +444,13 @@ struct virtnet_info {
 	/* Work struct for delayed refilling if we run low on memory. */
 	struct delayed_work refill;
 
+	/* UDP tunnel support */
+	bool tx_tnl;
+
+	bool rx_tnl;
+
+	bool rx_tnl_csum;
+
 	/* Is delayed refill enabled? */
 	bool refill_enabled;
 
@@ -482,6 +510,7 @@ struct virtio_net_common_hdr {
 		struct virtio_net_hdr hdr;
 		struct virtio_net_hdr_mrg_rxbuf	mrg_hdr;
 		struct virtio_net_hdr_v1_hash hash_v1_hdr;
+		struct virtio_net_hdr_v1_hash_tunnel tnl_hdr;
 	};
 };
 
@@ -2545,14 +2574,21 @@ static void virtnet_receive_done(struct virtnet_info *vi, struct receive_queue *
 	if (dev->features & NETIF_F_RXHASH && vi->has_rss_hash_report)
 		virtio_skb_set_hash(&hdr->hash_v1_hdr, skb);
 
-	if (flags & VIRTIO_NET_HDR_F_DATA_VALID)
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
+	hdr->hdr.flags = flags;
+	if (virtio_net_handle_csum_offload(skb, &hdr->hdr, vi->rx_tnl_csum)) {
+		net_warn_ratelimited("%s: bad csum: flags: %x, gso_type: %x rx_tnl_csum %d\n",
+				     dev->name, hdr->hdr.flags,
+				     hdr->hdr.gso_type, vi->rx_tnl_csum);
+		goto frame_err;
+	}
 
-	if (virtio_net_hdr_to_skb(skb, &hdr->hdr,
-				  virtio_is_little_endian(vi->vdev))) {
-		net_warn_ratelimited("%s: bad gso: type: %u, size: %u\n",
+	if (virtio_net_hdr_tnl_to_skb(skb, &hdr->tnl_hdr, vi->rx_tnl,
+				      vi->rx_tnl_csum,
+				      virtio_is_little_endian(vi->vdev))) {
+		net_warn_ratelimited("%s: bad gso: type: %x, size: %u, flags %x tunnel %d tnl csum %d\n",
 				     dev->name, hdr->hdr.gso_type,
-				     hdr->hdr.gso_size);
+				     hdr->hdr.gso_size, hdr->hdr.flags,
+				     vi->rx_tnl, vi->rx_tnl_csum);
 		goto frame_err;
 	}
 
@@ -3264,9 +3300,9 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget)
 
 static int xmit_skb(struct send_queue *sq, struct sk_buff *skb, bool orphan)
 {
-	struct virtio_net_hdr_mrg_rxbuf *hdr;
 	const unsigned char *dest = ((struct ethhdr *)skb->data)->h_dest;
 	struct virtnet_info *vi = sq->vq->vdev->priv;
+	struct virtio_net_hdr_v1_hash_tunnel *hdr;
 	int num_sg;
 	unsigned hdr_len = vi->hdr_len;
 	bool can_push;
@@ -3279,17 +3315,17 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb, bool orphan)
 	/* Even if we can, don't push here yet as this would skew
 	 * csum_start offset below. */
 	if (can_push)
-		hdr = (struct virtio_net_hdr_mrg_rxbuf *)(skb->data - hdr_len);
+		hdr = (struct virtio_net_hdr_v1_hash_tunnel *)(skb->data -
+							       hdr_len);
 	else
-		hdr = &skb_vnet_common_hdr(skb)->mrg_hdr;
+		hdr = &skb_vnet_common_hdr(skb)->tnl_hdr;
 
-	if (virtio_net_hdr_from_skb(skb, &hdr->hdr,
-				    virtio_is_little_endian(vi->vdev), false,
-				    0))
+	if (virtio_net_hdr_tnl_from_skb(skb, hdr, vi->tx_tnl,
+					virtio_is_little_endian(vi->vdev), 0))
 		return -EPROTO;
 
 	if (vi->mergeable_rx_bufs)
-		hdr->num_buffers = 0;
+		hdr->hash_hdr.hdr.num_buffers = 0;
 
 	sg_init_table(sq->sg, skb_shinfo(skb)->nr_frags + (can_push ? 1 : 2));
 	if (can_push) {
@@ -6784,10 +6820,20 @@ static int virtnet_probe(struct virtio_device *vdev)
 		if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_USO))
 			dev->hw_features |= NETIF_F_GSO_UDP_L4;
 
+		if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO)) {
+			dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL;
+			dev->hw_enc_features = dev->hw_features;
+		}
+		if (dev->hw_features & NETIF_F_GSO_UDP_TUNNEL &&
+		    virtio_has_feature(vdev, VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO_CSUM)) {
+			dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
+			dev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
+		}
+
 		dev->features |= NETIF_F_GSO_ROBUST;
 
 		if (gso)
-			dev->features |= dev->hw_features & NETIF_F_ALL_TSO;
+			dev->features |= dev->hw_features;
 		/* (!csum && gso) case will be fixed by register_netdev() */
 	}
 
@@ -6880,7 +6926,10 @@ static int virtnet_probe(struct virtio_device *vdev)
 		dev->xdp_metadata_ops = &virtnet_xdp_metadata_ops;
 	}
 
-	if (vi->has_rss_hash_report)
+	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO) ||
+	    virtio_has_feature(vdev, VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO))
+		vi->hdr_len = sizeof(struct virtio_net_hdr_v1_hash_tunnel);
+	else if (vi->has_rss_hash_report)
 		vi->hdr_len = sizeof(struct virtio_net_hdr_v1_hash);
 	else if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF) ||
 		 virtio_has_feature(vdev, VIRTIO_F_VERSION_1))
@@ -6888,6 +6937,13 @@ static int virtnet_probe(struct virtio_device *vdev)
 	else
 		vi->hdr_len = sizeof(struct virtio_net_hdr);
 
+	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_CSUM))
+		vi->rx_tnl_csum = true;
+	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO))
+		vi->rx_tnl = true;
+	if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO))
+		vi->tx_tnl = true;
+
 	if (virtio_has_feature(vdev, VIRTIO_F_ANY_LAYOUT) ||
 	    virtio_has_feature(vdev, VIRTIO_F_VERSION_1))
 		vi->any_header_sg = true;
@@ -7062,9 +7118,13 @@ static int virtnet_probe(struct virtio_device *vdev)
 		netif_carrier_on(dev);
 	}
 
-	for (i = 0; i < ARRAY_SIZE(guest_offloads); i++)
-		if (virtio_has_feature(vi->vdev, guest_offloads[i]))
+	for (i = 0; i < ARRAY_SIZE(guest_offloads); i++) {
+		unsigned int fbit;
+
+		fbit = virtio_offload_to_feature(guest_offloads[i]);
+		if (virtio_has_feature(vi->vdev, fbit))
 			set_bit(guest_offloads[i], &vi->guest_offloads);
+	}
 	vi->guest_offloads_capable = vi->guest_offloads;
 
 	rtnl_unlock();
@@ -7194,6 +7254,10 @@ static struct virtio_device_id id_table[] = {
 
 static unsigned int features[] = {
 	VIRTNET_FEATURES,
+	VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO,
+	VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_CSUM,
+	VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO,
+	VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO_CSUM,
 };
 
 static unsigned int features_legacy[] = {
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 9dbd88eb9ff4..bfb774c273ea 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -69,12 +69,14 @@ MODULE_PARM_DESC(experimental_zcopytx, "Enable Zero Copy TX;"
 
 #define VHOST_DMA_IS_DONE(len) ((__force u32)(len) >= (__force u32)VHOST_DMA_DONE_LEN)
 
-enum {
-	VHOST_NET_FEATURES = VHOST_FEATURES |
-			 (1ULL << VHOST_NET_F_VIRTIO_NET_HDR) |
-			 (1ULL << VIRTIO_NET_F_MRG_RXBUF) |
-			 (1ULL << VIRTIO_F_ACCESS_PLATFORM) |
-			 (1ULL << VIRTIO_F_RING_RESET)
+static const u64 vhost_net_features[VIRTIO_FEATURES_DWORDS] = {
+	VHOST_FEATURES |
+	(1ULL << VHOST_NET_F_VIRTIO_NET_HDR) |
+	(1ULL << VIRTIO_NET_F_MRG_RXBUF) |
+	(1ULL << VIRTIO_F_ACCESS_PLATFORM) |
+	(1ULL << VIRTIO_F_RING_RESET),
+	VIRTIO_BIT(VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO) |
+	VIRTIO_BIT(VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO),
 };
 
 enum {
@@ -1606,16 +1608,23 @@ done:
 	return err;
 }
 
-static int vhost_net_set_features(struct vhost_net *n, u64 features)
+static int vhost_net_set_features(struct vhost_net *n, const u64 *features)
 {
 	size_t vhost_hlen, sock_hlen, hdr_len;
 	int i;
 
-	hdr_len = (features & ((1ULL << VIRTIO_NET_F_MRG_RXBUF) |
-			       (1ULL << VIRTIO_F_VERSION_1))) ?
-			sizeof(struct virtio_net_hdr_mrg_rxbuf) :
-			sizeof(struct virtio_net_hdr);
-	if (features & (1 << VHOST_NET_F_VIRTIO_NET_HDR)) {
+	hdr_len = virtio_features_test_bit(features, VIRTIO_NET_F_MRG_RXBUF) ||
+		  virtio_features_test_bit(features, VIRTIO_F_VERSION_1) ?
+		  sizeof(struct virtio_net_hdr_mrg_rxbuf) :
+		  sizeof(struct virtio_net_hdr);
+
+	if (virtio_features_test_bit(features,
+				     VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO) ||
+	    virtio_features_test_bit(features,
+				     VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO))
+		hdr_len = sizeof(struct virtio_net_hdr_v1_hash_tunnel);
+
+	if (virtio_features_test_bit(features, VHOST_NET_F_VIRTIO_NET_HDR)) {
 		/* vhost provides vnet_hdr */
 		vhost_hlen = hdr_len;
 		sock_hlen = 0;
@@ -1625,18 +1634,19 @@ static int vhost_net_set_features(struct vhost_net *n, u64 features)
 		sock_hlen = hdr_len;
 	}
 	mutex_lock(&n->dev.mutex);
-	if ((features & (1 << VHOST_F_LOG_ALL)) &&
+	if (virtio_features_test_bit(features, VHOST_F_LOG_ALL) &&
 	    !vhost_log_access_ok(&n->dev))
 		goto out_unlock;
 
-	if ((features & (1ULL << VIRTIO_F_ACCESS_PLATFORM))) {
+	if (virtio_features_test_bit(features, VIRTIO_F_ACCESS_PLATFORM)) {
 		if (vhost_init_device_iotlb(&n->dev))
 			goto out_unlock;
 	}
 
 	for (i = 0; i < VHOST_NET_VQ_MAX; ++i) {
 		mutex_lock(&n->vqs[i].vq.mutex);
-		n->vqs[i].vq.acked_features = features;
+		virtio_features_copy(n->vqs[i].vq.acked_features_array,
+				     features);
 		n->vqs[i].vhost_hlen = vhost_hlen;
 		n->vqs[i].sock_hlen = sock_hlen;
 		mutex_unlock(&n->vqs[i].vq.mutex);
@@ -1673,12 +1683,13 @@ out:
 static long vhost_net_ioctl(struct file *f, unsigned int ioctl,
 			    unsigned long arg)
 {
+	u64 all_features[VIRTIO_FEATURES_DWORDS];
 	struct vhost_net *n = f->private_data;
 	void __user *argp = (void __user *)arg;
 	u64 __user *featurep = argp;
 	struct vhost_vring_file backend;
-	u64 features;
-	int r;
+	u64 features, count, copied;
+	int r, i;
 
 	switch (ioctl) {
 	case VHOST_NET_SET_BACKEND:
@@ -1686,16 +1697,60 @@ static long vhost_net_ioctl(struct file *f, unsigned int ioctl,
 			return -EFAULT;
 		return vhost_net_set_backend(n, backend.index, backend.fd);
 	case VHOST_GET_FEATURES:
-		features = VHOST_NET_FEATURES;
+		features = vhost_net_features[0];
 		if (copy_to_user(featurep, &features, sizeof features))
 			return -EFAULT;
 		return 0;
 	case VHOST_SET_FEATURES:
 		if (copy_from_user(&features, featurep, sizeof features))
 			return -EFAULT;
-		if (features & ~VHOST_NET_FEATURES)
+		if (features & ~vhost_net_features[0])
 			return -EOPNOTSUPP;
-		return vhost_net_set_features(n, features);
+
+		virtio_features_from_u64(all_features, features);
+		return vhost_net_set_features(n, all_features);
+	case VHOST_GET_FEATURES_ARRAY:
+		if (copy_from_user(&count, featurep, sizeof(count)))
+			return -EFAULT;
+
+		/* Copy the net features, up to the user-provided buffer size */
+		argp += sizeof(u64);
+		copied = min(count, VIRTIO_FEATURES_DWORDS);
+		if (copy_to_user(argp, vhost_net_features,
+				 copied * sizeof(u64)))
+			return -EFAULT;
+
+		/* Zero the trailing space provided by user-space, if any */
+		if (clear_user(argp, size_mul(count - copied, sizeof(u64))))
+			return -EFAULT;
+		return 0;
+	case VHOST_SET_FEATURES_ARRAY:
+		if (copy_from_user(&count, featurep, sizeof(count)))
+			return -EFAULT;
+
+		virtio_features_zero(all_features);
+		argp += sizeof(u64);
+		copied = min(count, VIRTIO_FEATURES_DWORDS);
+		if (copy_from_user(all_features, argp, copied * sizeof(u64)))
+			return -EFAULT;
+
+		/*
+		 * Any feature specified by user-space above
+		 * VIRTIO_FEATURES_MAX is not supported by definition.
+		 */
+		for (i = copied; i < count; ++i) {
+			if (copy_from_user(&features, featurep + 1 + i,
+					   sizeof(features)))
+				return -EFAULT;
+			if (features)
+				return -EOPNOTSUPP;
+		}
+
+		for (i = 0; i < VIRTIO_FEATURES_DWORDS; i++)
+			if (all_features[i] & ~vhost_net_features[i])
+				return -EOPNOTSUPP;
+
+		return vhost_net_set_features(n, all_features);
 	case VHOST_GET_BACKEND_FEATURES:
 		features = VHOST_NET_BACKEND_FEATURES;
 		if (copy_to_user(featurep, &features, sizeof(features)))
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 3a5ebb973dba..1094256a943c 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -372,7 +372,7 @@ static void vhost_vq_reset(struct vhost_dev *dev,
 	vq->log_used = false;
 	vq->log_addr = -1ull;
 	vq->private_data = NULL;
-	vq->acked_features = 0;
+	virtio_features_zero(vq->acked_features_array);
 	vq->acked_backend_features = 0;
 	vq->log_base = NULL;
 	vq->error_ctx = NULL;
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index bb75a292d50c..d1aed35c4b07 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -133,7 +133,7 @@ struct vhost_virtqueue {
 	struct vhost_iotlb *umem;
 	struct vhost_iotlb *iotlb;
 	void *private_data;
-	u64 acked_features;
+	VIRTIO_DECLARE_FEATURES(acked_features);
 	u64 acked_backend_features;
 	/* Log write descriptors */
 	void __user *log_base;
@@ -291,7 +291,7 @@ static inline void *vhost_vq_get_backend(struct vhost_virtqueue *vq)
 
 static inline bool vhost_has_feature(struct vhost_virtqueue *vq, int bit)
 {
-	return vq->acked_features & (1ULL << bit);
+	return virtio_features_test_bit(vq->acked_features_array, bit);
 }
 
 static inline bool vhost_backend_has_feature(struct vhost_virtqueue *vq, int bit)
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 95d5d7993e5b..5c48788cdbec 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -53,7 +53,7 @@ static ssize_t features_show(struct device *_d,
 
 	/* We actually represent this as a bitstring, as it could be
 	 * arbitrary length in future. */
-	for (i = 0; i < sizeof(dev->features)*8; i++)
+	for (i = 0; i < VIRTIO_FEATURES_MAX; i++)
 		len += sysfs_emit_at(buf, len, "%c",
 			       __virtio_test_bit(dev, i) ? '1' : '0');
 	len += sysfs_emit_at(buf, len, "\n");
@@ -272,22 +272,22 @@ static int virtio_dev_probe(struct device *_d)
 	int err, i;
 	struct virtio_device *dev = dev_to_virtio(_d);
 	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
-	u64 device_features;
-	u64 driver_features;
+	u64 device_features[VIRTIO_FEATURES_DWORDS];
+	u64 driver_features[VIRTIO_FEATURES_DWORDS];
 	u64 driver_features_legacy;
 
 	/* We have a driver! */
 	virtio_add_status(dev, VIRTIO_CONFIG_S_DRIVER);
 
 	/* Figure out what features the device supports. */
-	device_features = dev->config->get_features(dev);
+	virtio_get_features(dev, device_features);
 
 	/* Figure out what features the driver supports. */
-	driver_features = 0;
+	virtio_features_zero(driver_features);
 	for (i = 0; i < drv->feature_table_size; i++) {
 		unsigned int f = drv->feature_table[i];
-		BUG_ON(f >= 64);
-		driver_features |= (1ULL << f);
+		if (!WARN_ON_ONCE(f >= VIRTIO_FEATURES_MAX))
+			virtio_features_set_bit(driver_features, f);
 	}
 
 	/* Some drivers have a separate feature table for virtio v1.0 */
@@ -295,24 +295,29 @@ static int virtio_dev_probe(struct device *_d)
 		driver_features_legacy = 0;
 		for (i = 0; i < drv->feature_table_size_legacy; i++) {
 			unsigned int f = drv->feature_table_legacy[i];
-			BUG_ON(f >= 64);
-			driver_features_legacy |= (1ULL << f);
+			if (!WARN_ON_ONCE(f >= 64))
+				driver_features_legacy |= (1ULL << f);
 		}
 	} else {
-		driver_features_legacy = driver_features;
+		driver_features_legacy = driver_features[0];
 	}
 
-	if (device_features & (1ULL << VIRTIO_F_VERSION_1))
-		dev->features = driver_features & device_features;
-	else
-		dev->features = driver_features_legacy & device_features;
+	if (virtio_features_test_bit(device_features, VIRTIO_F_VERSION_1)) {
+		for (i = 0; i < VIRTIO_FEATURES_DWORDS; ++i)
+			dev->features_array[i] = driver_features[i] &
+						 device_features[i];
+	} else {
+		virtio_features_from_u64(dev->features_array,
+					 driver_features_legacy &
+					 device_features[0]);
+	}
 
 	/* When debugging, user may filter some features by hand. */
 	virtio_debug_device_filter_features(dev);
 
 	/* Transport features always preserved to pass to finalize_features. */
 	for (i = VIRTIO_TRANSPORT_F_START; i < VIRTIO_TRANSPORT_F_END; i++)
-		if (device_features & (1ULL << i))
+		if (virtio_features_test_bit(device_features, i))
 			__virtio_set_bit(dev, i);
 
 	err = dev->config->finalize_features(dev);
@@ -320,14 +325,15 @@ static int virtio_dev_probe(struct device *_d)
 		goto err;
 
 	if (drv->validate) {
-		u64 features = dev->features;
+		u64 features[VIRTIO_FEATURES_DWORDS];
 
+		virtio_features_copy(features, dev->features_array);
 		err = drv->validate(dev);
 		if (err)
 			goto err;
 
 		/* Did validation change any features? Then write them again. */
-		if (features != dev->features) {
+		if (!virtio_features_equal(features, dev->features_array)) {
 			err = dev->config->finalize_features(dev);
 			if (err)
 				goto err;
@@ -701,6 +707,9 @@ EXPORT_SYMBOL_GPL(virtio_device_reset_done);
 
 static int virtio_init(void)
 {
+	BUILD_BUG_ON(offsetof(struct virtio_device, features) !=
+		     offsetof(struct virtio_device, features_array[0]));
+
 	if (bus_register(&virtio_bus) != 0)
 		panic("virtio bus registration failed");
 	virtio_debug_init();
diff --git a/drivers/virtio/virtio_debug.c b/drivers/virtio/virtio_debug.c
index 95c8fc7705bb..d58713ddf2e5 100644
--- a/drivers/virtio/virtio_debug.c
+++ b/drivers/virtio/virtio_debug.c
@@ -8,13 +8,13 @@ static struct dentry *virtio_debugfs_dir;
 
 static int virtio_debug_device_features_show(struct seq_file *s, void *data)
 {
+	u64 device_features[VIRTIO_FEATURES_DWORDS];
 	struct virtio_device *dev = s->private;
-	u64 device_features;
 	unsigned int i;
 
-	device_features = dev->config->get_features(dev);
-	for (i = 0; i < BITS_PER_LONG_LONG; i++) {
-		if (device_features & (1ULL << i))
+	virtio_get_features(dev, device_features);
+	for (i = 0; i < VIRTIO_FEATURES_MAX; i++) {
+		if (virtio_features_test_bit(device_features, i))
 			seq_printf(s, "%u\n", i);
 	}
 	return 0;
@@ -26,8 +26,8 @@ static int virtio_debug_filter_features_show(struct seq_file *s, void *data)
 	struct virtio_device *dev = s->private;
 	unsigned int i;
 
-	for (i = 0; i < BITS_PER_LONG_LONG; i++) {
-		if (dev->debugfs_filter_features & (1ULL << i))
+	for (i = 0; i < VIRTIO_FEATURES_MAX; i++) {
+		if (virtio_features_test_bit(dev->debugfs_filter_features, i))
 			seq_printf(s, "%u\n", i);
 	}
 	return 0;
@@ -39,7 +39,7 @@ static int virtio_debug_filter_features_clear(void *data, u64 val)
 	struct virtio_device *dev = data;
 
 	if (val == 1)
-		dev->debugfs_filter_features = 0;
+		virtio_features_zero(dev->debugfs_filter_features);
 	return 0;
 }
 
@@ -50,9 +50,10 @@ static int virtio_debug_filter_feature_add(void *data, u64 val)
 {
 	struct virtio_device *dev = data;
 
-	if (val >= BITS_PER_LONG_LONG)
+	if (val >= VIRTIO_FEATURES_MAX)
 		return -EINVAL;
-	dev->debugfs_filter_features |= BIT_ULL_MASK(val);
+
+	virtio_features_set_bit(dev->debugfs_filter_features, val);
 	return 0;
 }
 
@@ -63,9 +64,10 @@ static int virtio_debug_filter_feature_del(void *data, u64 val)
 {
 	struct virtio_device *dev = data;
 
-	if (val >= BITS_PER_LONG_LONG)
+	if (val >= VIRTIO_FEATURES_MAX)
 		return -EINVAL;
-	dev->debugfs_filter_features &= ~BIT_ULL_MASK(val);
+
+	virtio_features_clear_bit(dev->debugfs_filter_features, val);
 	return 0;
 }
 
@@ -91,7 +93,8 @@ EXPORT_SYMBOL_GPL(virtio_debug_device_init);
 
 void virtio_debug_device_filter_features(struct virtio_device *dev)
 {
-	dev->features &= ~dev->debugfs_filter_features;
+	virtio_features_andnot(dev->features_array, dev->features_array,
+			       dev->debugfs_filter_features);
 }
 EXPORT_SYMBOL_GPL(virtio_debug_device_filter_features);
 
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 7182f43ed055..dd0e65f71d41 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -22,11 +22,11 @@
 
 #define VIRTIO_AVQ_SGS_MAX	4
 
-static u64 vp_get_features(struct virtio_device *vdev)
+static void vp_get_features(struct virtio_device *vdev, u64 *features)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 
-	return vp_modern_get_features(&vp_dev->mdev);
+	vp_modern_get_extended_features(&vp_dev->mdev, features);
 }
 
 static int vp_avq_index(struct virtio_device *vdev, u16 *index, u16 *num)
@@ -437,7 +437,7 @@ static int vp_finalize_features(struct virtio_device *vdev)
 	if (vp_check_common_size(vdev))
 		return -EINVAL;
 
-	vp_modern_set_features(&vp_dev->mdev, vdev->features);
+	vp_modern_set_extended_features(&vp_dev->mdev, vdev->features_array);
 
 	return 0;
 }
@@ -1234,7 +1234,7 @@ static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
 	.find_vqs	= vp_modern_find_vqs,
 	.del_vqs	= vp_del_vqs,
 	.synchronize_cbs = vp_synchronize_vectors,
-	.get_features	= vp_get_features,
+	.get_extended_features = vp_get_features,
 	.finalize_features = vp_finalize_features,
 	.bus_name	= vp_bus_name,
 	.set_vq_affinity = vp_set_vq_affinity,
@@ -1254,7 +1254,7 @@ static const struct virtio_config_ops virtio_pci_config_ops = {
 	.find_vqs	= vp_modern_find_vqs,
 	.del_vqs	= vp_del_vqs,
 	.synchronize_cbs = vp_synchronize_vectors,
-	.get_features	= vp_get_features,
+	.get_extended_features = vp_get_features,
 	.finalize_features = vp_finalize_features,
 	.bus_name	= vp_bus_name,
 	.set_vq_affinity = vp_set_vq_affinity,
diff --git a/drivers/virtio/virtio_pci_modern_dev.c b/drivers/virtio/virtio_pci_modern_dev.c
index 0d3dbfaf4b23..d665f8f73ea8 100644
--- a/drivers/virtio/virtio_pci_modern_dev.c
+++ b/drivers/virtio/virtio_pci_modern_dev.c
@@ -388,63 +388,74 @@ void vp_modern_remove(struct virtio_pci_modern_device *mdev)
 EXPORT_SYMBOL_GPL(vp_modern_remove);
 
 /*
- * vp_modern_get_features - get features from device
+ * vp_modern_get_extended_features - get features from device
  * @mdev: the modern virtio-pci device
+ * @features: the features array to be filled
  *
- * Returns the features read from the device
+ * Fill the specified features array with the features read from the device
  */
-u64 vp_modern_get_features(struct virtio_pci_modern_device *mdev)
+void vp_modern_get_extended_features(struct virtio_pci_modern_device *mdev,
+				     u64 *features)
 {
 	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+	int i;
 
-	u64 features;
+	virtio_features_zero(features);
+	for (i = 0; i < VIRTIO_FEATURES_WORDS; i++) {
+		u64 cur;
 
-	vp_iowrite32(0, &cfg->device_feature_select);
-	features = vp_ioread32(&cfg->device_feature);
-	vp_iowrite32(1, &cfg->device_feature_select);
-	features |= ((u64)vp_ioread32(&cfg->device_feature) << 32);
-
-	return features;
+		vp_iowrite32(i, &cfg->device_feature_select);
+		cur = vp_ioread32(&cfg->device_feature);
+		features[i >> 1] |= cur << (32 * (i & 1));
+	}
 }
-EXPORT_SYMBOL_GPL(vp_modern_get_features);
+EXPORT_SYMBOL_GPL(vp_modern_get_extended_features);
 
 /*
  * vp_modern_get_driver_features - get driver features from device
  * @mdev: the modern virtio-pci device
+ * @features: the features array to be filled
  *
- * Returns the driver features read from the device
+ * Fill the specified features array with the driver features read from the
+ * device
  */
-u64 vp_modern_get_driver_features(struct virtio_pci_modern_device *mdev)
+void
+vp_modern_get_driver_extended_features(struct virtio_pci_modern_device *mdev,
+				       u64 *features)
 {
 	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+	int i;
 
-	u64 features;
-
-	vp_iowrite32(0, &cfg->guest_feature_select);
-	features = vp_ioread32(&cfg->guest_feature);
-	vp_iowrite32(1, &cfg->guest_feature_select);
-	features |= ((u64)vp_ioread32(&cfg->guest_feature) << 32);
+	virtio_features_zero(features);
+	for (i = 0; i < VIRTIO_FEATURES_WORDS; i++) {
+		u64 cur;
 
-	return features;
+		vp_iowrite32(i, &cfg->guest_feature_select);
+		cur = vp_ioread32(&cfg->guest_feature);
+		features[i >> 1] |= cur << (32 * (i & 1));
+	}
 }
-EXPORT_SYMBOL_GPL(vp_modern_get_driver_features);
+EXPORT_SYMBOL_GPL(vp_modern_get_driver_extended_features);
 
 /*
- * vp_modern_set_features - set features to device
+ * vp_modern_set_extended_features - set features to device
  * @mdev: the modern virtio-pci device
  * @features: the features set to device
  */
-void vp_modern_set_features(struct virtio_pci_modern_device *mdev,
-			    u64 features)
+void vp_modern_set_extended_features(struct virtio_pci_modern_device *mdev,
+				     const u64 *features)
 {
 	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+	int i;
+
+	for (i = 0; i < VIRTIO_FEATURES_WORDS; i++) {
+		u32 cur = features[i >> 1] >> (32 * (i & 1));
 
-	vp_iowrite32(0, &cfg->guest_feature_select);
-	vp_iowrite32((u32)features, &cfg->guest_feature);
-	vp_iowrite32(1, &cfg->guest_feature_select);
-	vp_iowrite32(features >> 32, &cfg->guest_feature);
+		vp_iowrite32(i, &cfg->guest_feature_select);
+		vp_iowrite32(cur, &cfg->guest_feature);
+	}
 }
-EXPORT_SYMBOL_GPL(vp_modern_set_features);
+EXPORT_SYMBOL_GPL(vp_modern_set_extended_features);
 
 /*
  * vp_modern_generation - get the device genreation
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 64cb4b04be7a..04b90c88d164 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -11,6 +11,7 @@
 #include <linux/gfp.h>
 #include <linux/dma-mapping.h>
 #include <linux/completion.h>
+#include <linux/virtio_features.h>
 
 /**
  * struct virtqueue - a queue to register buffers for sending or receiving.
@@ -141,7 +142,9 @@ struct virtio_admin_cmd {
  * @config: the configuration ops for this device.
  * @vringh_config: configuration ops for host vrings.
  * @vqs: the list of virtqueues for this device.
- * @features: the features supported by both driver and device.
+ * @features: the 64 lower features supported by both driver and device.
+ * @features_array: the full features space supported by both driver and
+ *		    device.
  * @priv: private pointer for the driver's use.
  * @debugfs_dir: debugfs directory entry.
  * @debugfs_filter_features: features to be filtered set by debugfs.
@@ -159,11 +162,11 @@ struct virtio_device {
 	const struct virtio_config_ops *config;
 	const struct vringh_config_ops *vringh_config;
 	struct list_head vqs;
-	u64 features;
+	VIRTIO_DECLARE_FEATURES(features);
 	void *priv;
 #ifdef CONFIG_VIRTIO_DEBUG
 	struct dentry *debugfs_dir;
-	u64 debugfs_filter_features;
+	u64 debugfs_filter_features[VIRTIO_FEATURES_DWORDS];
 #endif
 };
 
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index b3e1d30c765b..918cf25cd3c6 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -77,7 +77,11 @@ struct virtqueue_info {
  *      vdev: the virtio_device
  * @get_features: get the array of feature bits for this device.
  *	vdev: the virtio_device
- *	Returns the first 64 feature bits (all we currently need).
+ *	Returns the first 64 feature bits.
+ * @get_extended_features:
+ *      vdev: the virtio_device
+ *      Returns the first VIRTIO_FEATURES_MAX feature bits (all we currently
+ *      need).
  * @finalize_features: confirm what device features we'll be using.
  *	vdev: the virtio_device
  *	This sends the driver feature bits to the device: it can change
@@ -121,6 +125,8 @@ struct virtio_config_ops {
 	void (*del_vqs)(struct virtio_device *);
 	void (*synchronize_cbs)(struct virtio_device *);
 	u64 (*get_features)(struct virtio_device *vdev);
+	void (*get_extended_features)(struct virtio_device *vdev,
+				      u64 *features);
 	int (*finalize_features)(struct virtio_device *vdev);
 	const char *(*bus_name)(struct virtio_device *vdev);
 	int (*set_vq_affinity)(struct virtqueue *vq,
@@ -147,13 +153,7 @@ void virtio_check_driver_offered_feature(const struct virtio_device *vdev,
 static inline bool __virtio_test_bit(const struct virtio_device *vdev,
 				     unsigned int fbit)
 {
-	/* Did you forget to fix assumptions on max features? */
-	if (__builtin_constant_p(fbit))
-		BUILD_BUG_ON(fbit >= 64);
-	else
-		BUG_ON(fbit >= 64);
-
-	return vdev->features & BIT_ULL(fbit);
+	return virtio_features_test_bit(vdev->features_array, fbit);
 }
 
 /**
@@ -164,13 +164,7 @@ static inline bool __virtio_test_bit(const struct virtio_device *vdev,
 static inline void __virtio_set_bit(struct virtio_device *vdev,
 				    unsigned int fbit)
 {
-	/* Did you forget to fix assumptions on max features? */
-	if (__builtin_constant_p(fbit))
-		BUILD_BUG_ON(fbit >= 64);
-	else
-		BUG_ON(fbit >= 64);
-
-	vdev->features |= BIT_ULL(fbit);
+	virtio_features_set_bit(vdev->features_array, fbit);
 }
 
 /**
@@ -181,13 +175,7 @@ static inline void __virtio_set_bit(struct virtio_device *vdev,
 static inline void __virtio_clear_bit(struct virtio_device *vdev,
 				      unsigned int fbit)
 {
-	/* Did you forget to fix assumptions on max features? */
-	if (__builtin_constant_p(fbit))
-		BUILD_BUG_ON(fbit >= 64);
-	else
-		BUG_ON(fbit >= 64);
-
-	vdev->features &= ~BIT_ULL(fbit);
+	virtio_features_clear_bit(vdev->features_array, fbit);
 }
 
 /**
@@ -204,6 +192,17 @@ static inline bool virtio_has_feature(const struct virtio_device *vdev,
 	return __virtio_test_bit(vdev, fbit);
 }
 
+static inline void virtio_get_features(struct virtio_device *vdev,
+				       u64 *features)
+{
+	if (vdev->config->get_extended_features) {
+		vdev->config->get_extended_features(vdev, features);
+		return;
+	}
+
+	virtio_features_from_u64(features, vdev->config->get_features(vdev));
+}
+
 /**
  * virtio_has_dma_quirk - determine whether this device has the DMA quirk
  * @vdev: the device
diff --git a/include/linux/virtio_features.h b/include/linux/virtio_features.h
new file mode 100644
index 000000000000..f748f2f87de8
--- /dev/null
+++ b/include/linux/virtio_features.h
@@ -0,0 +1,88 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_VIRTIO_FEATURES_H
+#define _LINUX_VIRTIO_FEATURES_H
+
+#include <linux/bits.h>
+
+#define VIRTIO_FEATURES_DWORDS	2
+#define VIRTIO_FEATURES_MAX	(VIRTIO_FEATURES_DWORDS * 64)
+#define VIRTIO_FEATURES_WORDS	(VIRTIO_FEATURES_DWORDS * 2)
+#define VIRTIO_BIT(b)		BIT_ULL((b) & 0x3f)
+#define VIRTIO_DWORD(b)		((b) >> 6)
+#define VIRTIO_DECLARE_FEATURES(name)			\
+	union {						\
+		u64 name;				\
+		u64 name##_array[VIRTIO_FEATURES_DWORDS];\
+	}
+
+static inline bool virtio_features_chk_bit(unsigned int bit)
+{
+	if (__builtin_constant_p(bit)) {
+		/*
+		 * Don't care returning the correct value: the build
+		 * will fail before any bad features access
+		 */
+		BUILD_BUG_ON(bit >= VIRTIO_FEATURES_MAX);
+	} else {
+		if (WARN_ON_ONCE(bit >= VIRTIO_FEATURES_MAX))
+			return false;
+	}
+	return true;
+}
+
+static inline bool virtio_features_test_bit(const u64 *features,
+					    unsigned int bit)
+{
+	return virtio_features_chk_bit(bit) &&
+	       !!(features[VIRTIO_DWORD(bit)] & VIRTIO_BIT(bit));
+}
+
+static inline void virtio_features_set_bit(u64 *features,
+					   unsigned int bit)
+{
+	if (virtio_features_chk_bit(bit))
+		features[VIRTIO_DWORD(bit)] |= VIRTIO_BIT(bit);
+}
+
+static inline void virtio_features_clear_bit(u64 *features,
+					     unsigned int bit)
+{
+	if (virtio_features_chk_bit(bit))
+		features[VIRTIO_DWORD(bit)] &= ~VIRTIO_BIT(bit);
+}
+
+static inline void virtio_features_zero(u64 *features)
+{
+	memset(features, 0, sizeof(features[0]) * VIRTIO_FEATURES_DWORDS);
+}
+
+static inline void virtio_features_from_u64(u64 *features, u64 from)
+{
+	virtio_features_zero(features);
+	features[0] = from;
+}
+
+static inline bool virtio_features_equal(const u64 *f1, const u64 *f2)
+{
+	int i;
+
+	for (i = 0; i < VIRTIO_FEATURES_DWORDS; ++i)
+		if (f1[i] != f2[i])
+			return false;
+	return true;
+}
+
+static inline void virtio_features_copy(u64 *to, const u64 *from)
+{
+	memcpy(to, from, sizeof(to[0]) * VIRTIO_FEATURES_DWORDS);
+}
+
+static inline void virtio_features_andnot(u64 *to, const u64 *f1, const u64 *f2)
+{
+	int i;
+
+	for (i = 0; i < VIRTIO_FEATURES_DWORDS; i++)
+		to[i] = f1[i] & ~f2[i];
+}
+
+#endif
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 02a9f4dc594d..20e0584db1dd 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -47,9 +47,9 @@ static inline int virtio_net_hdr_set_proto(struct sk_buff *skb,
 	return 0;
 }
 
-static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
-					const struct virtio_net_hdr *hdr,
-					bool little_endian)
+static inline int __virtio_net_hdr_to_skb(struct sk_buff *skb,
+					  const struct virtio_net_hdr *hdr,
+					  bool little_endian, u8 hdr_gso_type)
 {
 	unsigned int nh_min_len = sizeof(struct iphdr);
 	unsigned int gso_type = 0;
@@ -57,8 +57,8 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 	unsigned int p_off = 0;
 	unsigned int ip_proto;
 
-	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
-		switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
+	if (hdr_gso_type != VIRTIO_NET_HDR_GSO_NONE) {
+		switch (hdr_gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
 		case VIRTIO_NET_HDR_GSO_TCPV4:
 			gso_type = SKB_GSO_TCPV4;
 			ip_proto = IPPROTO_TCP;
@@ -84,7 +84,7 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 			return -EINVAL;
 		}
 
-		if (hdr->gso_type & VIRTIO_NET_HDR_GSO_ECN)
+		if (hdr_gso_type & VIRTIO_NET_HDR_GSO_ECN)
 			gso_type |= SKB_GSO_TCP_ECN;
 
 		if (hdr->gso_size == 0)
@@ -122,7 +122,8 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 
 				if (!protocol)
 					virtio_net_hdr_set_proto(skb, hdr);
-				else if (!virtio_net_hdr_match_proto(protocol, hdr->gso_type))
+				else if (!virtio_net_hdr_match_proto(protocol,
+								 hdr_gso_type))
 					return -EINVAL;
 				else
 					skb->protocol = protocol;
@@ -153,7 +154,7 @@ retry:
 		}
 	}
 
-	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
+	if (hdr_gso_type != VIRTIO_NET_HDR_GSO_NONE) {
 		u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size);
 		unsigned int nh_off = p_off;
 		struct skb_shared_info *shinfo = skb_shinfo(skb);
@@ -199,6 +200,13 @@ retry:
 	return 0;
 }
 
+static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
+					const struct virtio_net_hdr *hdr,
+					bool little_endian)
+{
+	return __virtio_net_hdr_to_skb(skb, hdr, little_endian, hdr->gso_type);
+}
+
 static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb,
 					  struct virtio_net_hdr *hdr,
 					  bool little_endian,
@@ -242,4 +250,177 @@ static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb,
 	return 0;
 }
 
+static inline unsigned int virtio_l3min(bool is_ipv6)
+{
+	return is_ipv6 ? sizeof(struct ipv6hdr) : sizeof(struct iphdr);
+}
+
+static inline int
+virtio_net_hdr_tnl_to_skb(struct sk_buff *skb,
+			  const struct virtio_net_hdr_v1_hash_tunnel *vhdr,
+			  bool tnl_hdr_negotiated,
+			  bool tnl_csum_negotiated,
+			  bool little_endian)
+{
+	const struct virtio_net_hdr *hdr = (const struct virtio_net_hdr *)vhdr;
+	unsigned int inner_nh, outer_th, inner_th;
+	unsigned int inner_l3min, outer_l3min;
+	u8 gso_inner_type, gso_tunnel_type;
+	bool outer_isv6, inner_isv6;
+	int ret;
+
+	gso_tunnel_type = hdr->gso_type & VIRTIO_NET_HDR_GSO_UDP_TUNNEL;
+	if (!gso_tunnel_type)
+		return virtio_net_hdr_to_skb(skb, hdr, little_endian);
+
+	/* Tunnel not supported/negotiated, but the hdr asks for it. */
+	if (!tnl_hdr_negotiated)
+		return -EINVAL;
+
+	/* Either ipv4 or ipv6. */
+	if (gso_tunnel_type == VIRTIO_NET_HDR_GSO_UDP_TUNNEL)
+		return -EINVAL;
+
+	/* The UDP tunnel must carry a GSO packet, but no UFO. */
+	gso_inner_type = hdr->gso_type & ~(VIRTIO_NET_HDR_GSO_ECN |
+					   VIRTIO_NET_HDR_GSO_UDP_TUNNEL);
+	if (!gso_inner_type || gso_inner_type == VIRTIO_NET_HDR_GSO_UDP)
+		return -EINVAL;
+
+	/* Rely on csum being present. */
+	if (!(hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM))
+		return -EINVAL;
+
+	/* Validate offsets. */
+	outer_isv6 = gso_tunnel_type & VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6;
+	inner_isv6 = gso_inner_type == VIRTIO_NET_HDR_GSO_TCPV6;
+	inner_l3min = virtio_l3min(inner_isv6);
+	outer_l3min = ETH_HLEN + virtio_l3min(outer_isv6);
+
+	inner_th = __virtio16_to_cpu(little_endian, hdr->csum_start);
+	inner_nh = le16_to_cpu(vhdr->inner_nh_offset);
+	outer_th = le16_to_cpu(vhdr->outer_th_offset);
+	if (outer_th < outer_l3min ||
+	    inner_nh < outer_th + sizeof(struct udphdr) ||
+	    inner_th < inner_nh + inner_l3min)
+		return -EINVAL;
+
+	/* Let the basic parsing deal with plain GSO features. */
+	ret = __virtio_net_hdr_to_skb(skb, hdr, true,
+				      hdr->gso_type & ~gso_tunnel_type);
+	if (ret)
+		return ret;
+
+	/* In case of USO, the inner protocol is still unknown and
+	 * `inner_isv6` is just a guess, additional parsing is needed.
+	 * The previous validation ensures that accessing an ipv4 inner
+	 * network header is safe.
+	 */
+	if (gso_inner_type == VIRTIO_NET_HDR_GSO_UDP_L4) {
+		struct iphdr *iphdr = (struct iphdr *)(skb->data + inner_nh);
+
+		inner_isv6 = iphdr->version == 6;
+		inner_l3min = virtio_l3min(inner_isv6);
+		if (inner_th < inner_nh + inner_l3min)
+			return -EINVAL;
+	}
+
+	skb_set_inner_protocol(skb, inner_isv6 ? htons(ETH_P_IPV6) :
+						 htons(ETH_P_IP));
+	if (hdr->flags & VIRTIO_NET_HDR_F_UDP_TUNNEL_CSUM) {
+		if (!tnl_csum_negotiated)
+			return -EINVAL;
+
+		skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
+	} else {
+		skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL;
+	}
+
+	skb->inner_transport_header = inner_th + skb_headroom(skb);
+	skb->inner_network_header = inner_nh + skb_headroom(skb);
+	skb->inner_mac_header = inner_nh + skb_headroom(skb);
+	skb->transport_header = outer_th + skb_headroom(skb);
+	skb->encapsulation = 1;
+	return 0;
+}
+
+/* Checksum-related fields validation for the driver */
+static inline int virtio_net_handle_csum_offload(struct sk_buff *skb,
+						 struct virtio_net_hdr *hdr,
+						 bool tnl_csum_negotiated)
+{
+	if (!(hdr->gso_type & VIRTIO_NET_HDR_GSO_UDP_TUNNEL)) {
+		if (!(hdr->flags & VIRTIO_NET_HDR_F_DATA_VALID))
+			return 0;
+
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		if (!(hdr->flags & VIRTIO_NET_HDR_F_UDP_TUNNEL_CSUM))
+			return 0;
+
+		/* tunnel csum packets are invalid when the related
+		 * feature has not been negotiated
+		 */
+		if (!tnl_csum_negotiated)
+			return -EINVAL;
+		skb->csum_level = 1;
+		return 0;
+	}
+
+	/* DATA_VALID is mutually exclusive with NEEDS_CSUM, and GSO
+	 * over UDP tunnel requires the latter
+	 */
+	if (hdr->flags & VIRTIO_NET_HDR_F_DATA_VALID)
+		return -EINVAL;
+	return 0;
+}
+
+/*
+ * vlan_hlen always refers to the outermost MAC header. That also
+ * means it refers to the only MAC header, if the packet does not carry
+ * any encapsulation.
+ */
+static inline int
+virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb,
+			    struct virtio_net_hdr_v1_hash_tunnel *vhdr,
+			    bool tnl_hdr_negotiated,
+			    bool little_endian,
+			    int vlan_hlen)
+{
+	struct virtio_net_hdr *hdr = (struct virtio_net_hdr *)vhdr;
+	unsigned int inner_nh, outer_th;
+	int tnl_gso_type;
+	int ret;
+
+	tnl_gso_type = skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL |
+						    SKB_GSO_UDP_TUNNEL_CSUM);
+	if (!tnl_gso_type)
+		return virtio_net_hdr_from_skb(skb, hdr, little_endian, false,
+					       vlan_hlen);
+
+	/* Tunnel support not negotiated but skb ask for it. */
+	if (!tnl_hdr_negotiated)
+		return -EINVAL;
+
+	/* Let the basic parsing deal with plain GSO features. */
+	skb_shinfo(skb)->gso_type &= ~tnl_gso_type;
+	ret = virtio_net_hdr_from_skb(skb, hdr, true, false, vlan_hlen);
+	skb_shinfo(skb)->gso_type |= tnl_gso_type;
+	if (ret)
+		return ret;
+
+	if (skb->protocol == htons(ETH_P_IPV6))
+		hdr->gso_type |= VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6;
+	else
+		hdr->gso_type |= VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV4;
+
+	if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM)
+		hdr->flags |= VIRTIO_NET_HDR_F_UDP_TUNNEL_CSUM;
+
+	inner_nh = skb->inner_network_header - skb_headroom(skb);
+	outer_th = skb->transport_header - skb_headroom(skb);
+	vhdr->inner_nh_offset = cpu_to_le16(inner_nh);
+	vhdr->outer_th_offset = cpu_to_le16(outer_th);
+	return 0;
+}
+
 #endif /* _LINUX_VIRTIO_NET_H */
diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h
index c0b1b1ca1163..48bc12d1045b 100644
--- a/include/linux/virtio_pci_modern.h
+++ b/include/linux/virtio_pci_modern.h
@@ -3,6 +3,7 @@
 #define _LINUX_VIRTIO_PCI_MODERN_H
 
 #include <linux/pci.h>
+#include <linux/virtio_config.h>
 #include <linux/virtio_pci.h>
 
 /**
@@ -95,10 +96,44 @@ static inline void vp_iowrite64_twopart(u64 val,
 	vp_iowrite32(val >> 32, hi);
 }
 
-u64 vp_modern_get_features(struct virtio_pci_modern_device *mdev);
-u64 vp_modern_get_driver_features(struct virtio_pci_modern_device *mdev);
-void vp_modern_set_features(struct virtio_pci_modern_device *mdev,
-		     u64 features);
+void
+vp_modern_get_driver_extended_features(struct virtio_pci_modern_device *mdev,
+				       u64 *features);
+void vp_modern_get_extended_features(struct virtio_pci_modern_device *mdev,
+				     u64 *features);
+void vp_modern_set_extended_features(struct virtio_pci_modern_device *mdev,
+				     const u64 *features);
+
+static inline u64
+vp_modern_get_features(struct virtio_pci_modern_device *mdev)
+{
+	u64 features_array[VIRTIO_FEATURES_DWORDS];
+
+	vp_modern_get_extended_features(mdev, features_array);
+	return features_array[0];
+}
+
+static inline u64
+vp_modern_get_driver_features(struct virtio_pci_modern_device *mdev)
+{
+	u64 features_array[VIRTIO_FEATURES_DWORDS];
+	int i;
+
+	vp_modern_get_driver_extended_features(mdev, features_array);
+	for (i = 1; i < VIRTIO_FEATURES_DWORDS; ++i)
+		WARN_ON_ONCE(features_array[i]);
+	return features_array[0];
+}
+
+static inline void
+vp_modern_set_features(struct virtio_pci_modern_device *mdev, u64 features)
+{
+	u64 features_array[VIRTIO_FEATURES_DWORDS];
+
+	virtio_features_from_u64(features_array, features);
+	vp_modern_set_extended_features(mdev, features_array);
+}
+
 u32 vp_modern_generation(struct virtio_pci_modern_device *mdev);
 u8 vp_modern_get_status(struct virtio_pci_modern_device *mdev);
 void vp_modern_set_status(struct virtio_pci_modern_device *mdev,
diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h
index 287cdc81c939..79d53c7a1ebd 100644
--- a/include/uapi/linux/if_tun.h
+++ b/include/uapi/linux/if_tun.h
@@ -93,6 +93,15 @@
 #define TUN_F_USO4	0x20	/* I can handle USO for IPv4 packets */
 #define TUN_F_USO6	0x40	/* I can handle USO for IPv6 packets */
 
+/* I can handle TSO/USO for UDP tunneled packets */
+#define TUN_F_UDP_TUNNEL_GSO		0x080
+
+/*
+ * I can handle TSO/USO for UDP tunneled packets requiring csum offload for
+ * the outer header
+ */
+#define TUN_F_UDP_TUNNEL_GSO_CSUM	0x100
+
 /* Protocol info prepended to the packets (when IFF_NO_PI is not set) */
 #define TUN_PKT_STRIP	0x0001
 struct tun_pi {
diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h
index d4b3e2ae1314..d6ad01fbb8d2 100644
--- a/include/uapi/linux/vhost.h
+++ b/include/uapi/linux/vhost.h
@@ -235,4 +235,11 @@
  */
 #define VHOST_VDPA_GET_VRING_SIZE	_IOWR(VHOST_VIRTIO, 0x82,	\
 					      struct vhost_vring_state)
+
+/* Extended features manipulation */
+#define VHOST_GET_FEATURES_ARRAY _IOR(VHOST_VIRTIO, 0x83, \
+				       struct vhost_features_array)
+#define VHOST_SET_FEATURES_ARRAY _IOW(VHOST_VIRTIO, 0x83, \
+				       struct vhost_features_array)
+
 #endif
diff --git a/include/uapi/linux/vhost_types.h b/include/uapi/linux/vhost_types.h
index d7656908f730..1c39cc5f5a31 100644
--- a/include/uapi/linux/vhost_types.h
+++ b/include/uapi/linux/vhost_types.h
@@ -110,6 +110,11 @@ struct vhost_msg_v2 {
 	};
 };
 
+struct vhost_features_array {
+	__u64 count; /* number of entries present in features array */
+	__u64 features[] __counted_by(count);
+};
+
 struct vhost_memory_region {
 	__u64 guest_phys_addr;
 	__u64 memory_size; /* bytes */
diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h
index 963540deae66..8bf27ab8bcb4 100644
--- a/include/uapi/linux/virtio_net.h
+++ b/include/uapi/linux/virtio_net.h
@@ -70,6 +70,28 @@
 					 * with the same MAC.
 					 */
 #define VIRTIO_NET_F_SPEED_DUPLEX 63	/* Device set linkspeed and duplex */
+#define VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO 65 /* Driver can receive
+					      * GSO-over-UDP-tunnel packets
+					      */
+#define VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_CSUM 66 /* Driver handles
+						   * GSO-over-UDP-tunnel
+						   * packets with partial csum
+						   * for the outer header
+						   */
+#define VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO 67 /* Device can receive
+					     * GSO-over-UDP-tunnel packets
+					     */
+#define VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO_CSUM 68 /* Device handles
+						  * GSO-over-UDP-tunnel
+						  * packets with partial csum
+						  * for the outer header
+						  */
+
+/* Offloads bits corresponding to VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO{,_CSUM}
+ * features
+ */
+#define VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_MAPPED	46
+#define VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_CSUM_MAPPED	47
 
 #ifndef VIRTIO_NET_NO_LEGACY
 #define VIRTIO_NET_F_GSO	6	/* Host handles pkts w/ any GSO type */
@@ -131,12 +153,17 @@ struct virtio_net_hdr_v1 {
 #define VIRTIO_NET_HDR_F_NEEDS_CSUM	1	/* Use csum_start, csum_offset */
 #define VIRTIO_NET_HDR_F_DATA_VALID	2	/* Csum is valid */
 #define VIRTIO_NET_HDR_F_RSC_INFO	4	/* rsc info in csum_ fields */
+#define VIRTIO_NET_HDR_F_UDP_TUNNEL_CSUM 8	/* UDP tunnel csum offload */
 	__u8 flags;
 #define VIRTIO_NET_HDR_GSO_NONE		0	/* Not a GSO frame */
 #define VIRTIO_NET_HDR_GSO_TCPV4	1	/* GSO frame, IPv4 TCP (TSO) */
 #define VIRTIO_NET_HDR_GSO_UDP		3	/* GSO frame, IPv4 UDP (UFO) */
 #define VIRTIO_NET_HDR_GSO_TCPV6	4	/* GSO frame, IPv6 TCP */
 #define VIRTIO_NET_HDR_GSO_UDP_L4	5	/* GSO frame, IPv4& IPv6 UDP (USO) */
+#define VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV4 0x20 /* UDPv4 tunnel present */
+#define VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6 0x40 /* UDPv6 tunnel present */
+#define VIRTIO_NET_HDR_GSO_UDP_TUNNEL (VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV4 | \
+				       VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6)
 #define VIRTIO_NET_HDR_GSO_ECN		0x80	/* TCP has ECN set */
 	__u8 gso_type;
 	__virtio16 hdr_len;	/* Ethernet + IP + tcp/udp hdrs */
@@ -181,6 +208,12 @@ struct virtio_net_hdr_v1_hash {
 	__le16 padding;
 };
 
+struct virtio_net_hdr_v1_hash_tunnel {
+	struct virtio_net_hdr_v1_hash hash_hdr;
+	__le16 outer_th_offset;
+	__le16 inner_nh_offset;
+};
+
 #ifndef VIRTIO_NET_NO_LEGACY
 /* This header comes first in the scatter-gather list.
  * For legacy virtio, if VIRTIO_F_ANY_LAYOUT is not negotiated, it must
diff --git a/scripts/lib/kdoc/kdoc_parser.py b/scripts/lib/kdoc/kdoc_parser.py
index 062453eefc7a..3115558925ac 100644
--- a/scripts/lib/kdoc/kdoc_parser.py
+++ b/scripts/lib/kdoc/kdoc_parser.py
@@ -666,6 +666,7 @@ class KernelDoc:
             (KernRe(r'(?:__)?DECLARE_FLEX_ARRAY\s*\(' + args_pattern + r',\s*' + args_pattern + r'\)', re.S), r'\1 \2[]'),
             (KernRe(r'DEFINE_DMA_UNMAP_ADDR\s*\(' + args_pattern + r'\)', re.S), r'dma_addr_t \1'),
             (KernRe(r'DEFINE_DMA_UNMAP_LEN\s*\(' + args_pattern + r'\)', re.S), r'__u32 \1'),
+            (KernRe(r'VIRTIO_DECLARE_FEATURES\s*\(' + args_pattern + r'\)', re.S), r'u64 \1; u64 \1_array[VIRTIO_FEATURES_DWORDS]'),
         ]
 
         # Regexes here are guaranteed to have the end limiter matching