tun: enable gso over UDP tunnel support.

Add new tun features to represent the newly introduced virtio
GSO over UDP tunnel offload. Allows detection and selection of
such features via the existing TUNSETOFFLOAD ioctl and compute
the expected virtio header size and tunnel header offset using
the current netdev features, so that we can plug almost seamless
the newly introduced virtio helpers to serialize the extended
virtio header.

Acked-by: Jason Wang <[e-mail]>
Signed-off-by: Paolo Abeni <[e-mail]>
---
v6 -> v7:
- rebased

v4 -> v5:
- encapsulate the guest feature guessing in a tun helper
- dropped irrelevant check on xdp buff headroom
- do not remove unrelated black line
- avoid line len > 80 char

v3 -> v4:
- virtio tnl-related fields are at fixed offset, cleanup
the code accordingly.
- use netdev features instead of flags bit to check for
the configured offload
- drop packet in case of enabled features/configured hdr
size mismatch

v2 -> v3:
- cleaned-up uAPI comments
- use explicit struct layout instead of raw buf.

drivers/net/tun.c

···
 	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;
···
 	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 |
···
 	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;
···
 	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))
···
 	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;
 
···
 		 * (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;
···
 		}
 	}
 
-	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;
···
 	}
 
 	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;
 	}
···
 {
 	unsigned int datasize = xdp->data_end - xdp->data;
 	struct tun_xdp_hdr *hdr = xdp->data_hard_start;
+	struct virtio_net_hdr_v1_hash_tunnel *tnl_hdr;
 	struct virtio_net_hdr *gso = &hdr->gso;
 	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 = hdr->buflen;
 	int metasize = 0;
···
 	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;
···
 
 }
 
+#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)
···
 		if (arg & TUN_F_USO4 && arg & TUN_F_USO6) {
 			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);
 		}
 	}
 

drivers/net/tun_vnet.h

···
 #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) &&
···
 	}
 }
 
-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);
···
 	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_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, parsed_size, iter) != parsed_size))
+		return -EFAULT;
+
+	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)
 {
-	if (unlikely(iov_iter_count(iter) < sz))
-		return -EINVAL;
-
-	if (unlikely(copy_to_iter(hdr, sizeof(*hdr), iter) != sizeof(*hdr)))
-		return -EFAULT;
-
-	if (iov_iter_zero(sz - sizeof(*hdr), iter) != sz - sizeof(*hdr))
-		return -EFAULT;
-
-	return 0;
+	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,
···
 				       DUMP_PREFIX_NONE,
 				       16, 1, skb->head,
 				       min(tun_vnet16_to_cpu(flags, hdr->hdr_len), 64), true);
+		}
+		WARN_ON_ONCE(1);
+		return -EINVAL;
+	}
+
+	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;

include/uapi/linux/if_tun.h

···
 #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 {