virtio: introduce GSO over UDP tunnel

index 95d5d7993e5b..5c48788cdbec 100644
@@ -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();

index 95c8fc7705bb..d58713ddf2e5 100644
@@ -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);
 

index 64cb4b04be7a..04b90c88d164 100644
@@ -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
 };
 

79 lines not on this page · raw message

88 lines not on this page · raw message

index 7182f43ed055..dd0e65f71d41 100644
@@ -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,

103 lines not on this page · raw message

55 lines not on this page · raw message

index 7cbfc7d718b3..b7dd50aa1ba3 100644
@@ -69,12 +69,12 @@ 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),
 };
 
 enum {

@@ -1614,16 +1614,17 @@ static long vhost_net_reset_owner(struct vhost_net *n)
 	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, VHOST_NET_F_VIRTIO_NET_HDR)) {
 		/* vhost provides vnet_hdr */
 		vhost_hlen = hdr_len;
 		sock_hlen = 0;

@@ -1633,18 +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);

@@ -1681,12 +1683,13 @@ static long vhost_net_set_owner(struct vhost_net *n)
 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:

@@ -1694,16 +1697,59 @@ 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 (get_user(count, featurep))
+			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, (count - copied) * sizeof(u64)))
+			return -EFAULT;
+		return 0;
+	case VHOST_SET_FEATURES_ARRAY:
+		if (get_user(count, featurep))
+			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 (get_user(features, featurep + 1 + i))
+				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)))

index 3a5ebb973dba..1094256a943c 100644
@@ -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;

index bb75a292d50c..d1aed35c4b07 100644
@@ -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)

index d4b3e2ae1314..d6ad01fbb8d2 100644
@@ -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

index d7656908f730..1c39cc5f5a31 100644
@@ -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 */

index 07e41dce4203..ad73863324e8 100644
@@ -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

@@ -7026,9 +7043,13 @@ 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();

index 02a9f4dc594d..20e0584db1dd 100644
@@ -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 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 		}
 	}
 
-	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 @@ static inline int virtio_net_hdr_to_skb(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)
+{
+	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 */

index 963540deae66..8bf27ab8bcb4 100644
@@ -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

index ad73863324e8..68bf35dae31a 100644
@@ -79,15 +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];

@@ -440,6 +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;
 

@@ -499,6 +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;
 	};
 };
 

@@ -2532,14 +2544,21 @@ 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;
 	}
 

@@ -3251,9 +3270,9 @@ 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;

@@ -3266,17 +3285,17 @@ 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) {

@@ -6765,10 +6784,20 @@ 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() */
 	}
 

@@ -6861,7 +6890,10 @@ 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))

@@ -6869,6 +6901,13 @@ 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;

@@ -7179,6 +7218,10 @@ 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[] = {

index f8c5e2fd04df..abc91f28dac4 100644
@@ -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;
 	}

@@ -2357,10 +2379,12 @@ static int tun_xdp_one(struct tun_struct *tun,
 {
 	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;

@@ -2426,7 +2450,9 @@ static int tun_xdp_one(struct tun_struct *tun,
 	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;

@@ -2812,6 +2838,8 @@ 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)

@@ -2841,6 +2869,18 @@ 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

150 lines not on this page · raw message

index 287cdc81c939..79d53c7a1ebd 100644
@@ -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 {

index b7dd50aa1ba3..3d99da3381ce 100644
@@ -75,6 +75,8 @@ static const u64 vhost_net_features[VIRTIO_FEATURES_DWORDS] = {
 	(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 {

@@ -1624,6 +1626,12 @@ static int vhost_net_set_features(struct vhost_net *n, const u64 *features)
 		  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;