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>

1 files changed, 87 insertions, 23 deletions

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[] = {