Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio updates from Michael Tsirkin:
 "virtio: virtio 1.0 support, misc patches

  This adds a lot of infrastructure for virtio 1.0 support.  Notable
  missing pieces: virtio pci, virtio balloon (needs spec extension),
  vhost scsi.

  Plus, there are some minor fixes in a couple of places.

  Note: some net drivers are affected by these patches.  David said he's
  fine with merging these patches through my tree.

  Rusty's on vacation, he acked using my tree for these, too"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (70 commits)
  virtio_ccw: finalize_features error handling
  virtio_ccw: future-proof finalize_features
  virtio_pci: rename virtio_pci -> virtio_pci_common
  virtio_pci: update file descriptions and copyright
  virtio_pci: split out legacy device support
  virtio_pci: setup config vector indirectly
  virtio_pci: setup vqs indirectly
  virtio_pci: delete vqs indirectly
  virtio_pci: use priv for vq notification
  virtio_pci: free up vq->priv
  virtio_pci: fix coding style for structs
  virtio_pci: add isr field
  virtio: drop legacy_only driver flag
  virtio_balloon: drop legacy_only driver flag
  virtio_ccw: rev 1 devices set VIRTIO_F_VERSION_1
  virtio: allow finalize_features to fail
  virtio_ccw: legacy: don't negotiate rev 1/features
  virtio: add API to detect legacy devices
  virtio_console: fix sparse warnings
  vhost: remove unnecessary forward declarations in vhost.h
  ...

40 files changed, 2048 insertions, 1428 deletions

diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index c6a27d54ad62..1fb9e09fbbc5 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -80,7 +80,7 @@ static int __virtblk_add_req(struct virtqueue *vq,
 {
 	struct scatterlist hdr, status, cmd, sense, inhdr, *sgs[6];
 	unsigned int num_out = 0, num_in = 0;
-	int type = vbr->out_hdr.type & ~VIRTIO_BLK_T_OUT;
+	__virtio32 type = vbr->out_hdr.type & ~cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_OUT);
 
 	sg_init_one(&hdr, &vbr->out_hdr, sizeof(vbr->out_hdr));
 	sgs[num_out++] = &hdr;
@@ -91,19 +91,19 @@ static int __virtblk_add_req(struct virtqueue *vq,
 	 * block, and before the normal inhdr we put the sense data and the
 	 * inhdr with additional status information.
 	 */
-	if (type == VIRTIO_BLK_T_SCSI_CMD) {
+	if (type == cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_SCSI_CMD)) {
 		sg_init_one(&cmd, vbr->req->cmd, vbr->req->cmd_len);
 		sgs[num_out++] = &cmd;
 	}
 
 	if (have_data) {
-		if (vbr->out_hdr.type & VIRTIO_BLK_T_OUT)
+		if (vbr->out_hdr.type & cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_OUT))
 			sgs[num_out++] = data_sg;
 		else
 			sgs[num_out + num_in++] = data_sg;
 	}
 
-	if (type == VIRTIO_BLK_T_SCSI_CMD) {
+	if (type == cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_SCSI_CMD)) {
 		sg_init_one(&sense, vbr->req->sense, SCSI_SENSE_BUFFERSIZE);
 		sgs[num_out + num_in++] = &sense;
 		sg_init_one(&inhdr, &vbr->in_hdr, sizeof(vbr->in_hdr));
@@ -119,12 +119,13 @@ static int __virtblk_add_req(struct virtqueue *vq,
 static inline void virtblk_request_done(struct request *req)
 {
 	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
+	struct virtio_blk *vblk = req->q->queuedata;
 	int error = virtblk_result(vbr);
 
 	if (req->cmd_type == REQ_TYPE_BLOCK_PC) {
-		req->resid_len = vbr->in_hdr.residual;
-		req->sense_len = vbr->in_hdr.sense_len;
-		req->errors = vbr->in_hdr.errors;
+		req->resid_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.residual);
+		req->sense_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.sense_len);
+		req->errors = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.errors);
 	} else if (req->cmd_type == REQ_TYPE_SPECIAL) {
 		req->errors = (error != 0);
 	}
@@ -173,25 +174,25 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req,
 
 	vbr->req = req;
 	if (req->cmd_flags & REQ_FLUSH) {
-		vbr->out_hdr.type = VIRTIO_BLK_T_FLUSH;
+		vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_FLUSH);
 		vbr->out_hdr.sector = 0;
-		vbr->out_hdr.ioprio = req_get_ioprio(vbr->req);
+		vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
 	} else {
 		switch (req->cmd_type) {
 		case REQ_TYPE_FS:
 			vbr->out_hdr.type = 0;
-			vbr->out_hdr.sector = blk_rq_pos(vbr->req);
-			vbr->out_hdr.ioprio = req_get_ioprio(vbr->req);
+			vbr->out_hdr.sector = cpu_to_virtio64(vblk->vdev, blk_rq_pos(vbr->req));
+			vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
 			break;
 		case REQ_TYPE_BLOCK_PC:
-			vbr->out_hdr.type = VIRTIO_BLK_T_SCSI_CMD;
+			vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_SCSI_CMD);
 			vbr->out_hdr.sector = 0;
-			vbr->out_hdr.ioprio = req_get_ioprio(vbr->req);
+			vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
 			break;
 		case REQ_TYPE_SPECIAL:
-			vbr->out_hdr.type = VIRTIO_BLK_T_GET_ID;
+			vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_GET_ID);
 			vbr->out_hdr.sector = 0;
-			vbr->out_hdr.ioprio = req_get_ioprio(vbr->req);
+			vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
 			break;
 		default:
 			/* We don't put anything else in the queue. */
@@ -204,9 +205,9 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req,
 	num = blk_rq_map_sg(hctx->queue, vbr->req, vbr->sg);
 	if (num) {
 		if (rq_data_dir(vbr->req) == WRITE)
-			vbr->out_hdr.type |= VIRTIO_BLK_T_OUT;
+			vbr->out_hdr.type |= cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_OUT);
 		else
-			vbr->out_hdr.type |= VIRTIO_BLK_T_IN;
+			vbr->out_hdr.type |= cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_IN);
 	}
 
 	spin_lock_irqsave(&vblk->vqs[qid].lock, flags);
@@ -331,7 +332,8 @@ static ssize_t virtblk_serial_show(struct device *dev,
 
 	return err;
 }
-DEVICE_ATTR(serial, S_IRUGO, virtblk_serial_show, NULL);
+
+static DEVICE_ATTR(serial, S_IRUGO, virtblk_serial_show, NULL);
 
 static void virtblk_config_changed_work(struct work_struct *work)
 {
@@ -476,7 +478,8 @@ static int virtblk_get_cache_mode(struct virtio_device *vdev)
 				   struct virtio_blk_config, wce,
 				   &writeback);
 	if (err)
-		writeback = virtio_has_feature(vdev, VIRTIO_BLK_F_WCE);
+		writeback = virtio_has_feature(vdev, VIRTIO_BLK_F_WCE) ||
+		            virtio_has_feature(vdev, VIRTIO_F_VERSION_1);
 
 	return writeback;
 }
@@ -821,25 +824,34 @@ static const struct virtio_device_id id_table[] = {
 	{ 0 },
 };
 
-static unsigned int features[] = {
+static unsigned int features_legacy[] = {
 	VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY,
 	VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE, VIRTIO_BLK_F_SCSI,
 	VIRTIO_BLK_F_WCE, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE,
 	VIRTIO_BLK_F_MQ,
+}
+;
+static unsigned int features[] = {
+	VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY,
+	VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE,
+	VIRTIO_BLK_F_TOPOLOGY,
+	VIRTIO_BLK_F_MQ,
 };
 
 static struct virtio_driver virtio_blk = {
-	.feature_table		= features,
-	.feature_table_size	= ARRAY_SIZE(features),
-	.driver.name		= KBUILD_MODNAME,
-	.driver.owner		= THIS_MODULE,
-	.id_table		= id_table,
-	.probe			= virtblk_probe,
-	.remove			= virtblk_remove,
-	.config_changed		= virtblk_config_changed,
+	.feature_table			= features,
+	.feature_table_size		= ARRAY_SIZE(features),
+	.feature_table_legacy		= features_legacy,
+	.feature_table_size_legacy	= ARRAY_SIZE(features_legacy),
+	.driver.name			= KBUILD_MODNAME,
+	.driver.owner			= THIS_MODULE,
+	.id_table			= id_table,
+	.probe				= virtblk_probe,
+	.remove				= virtblk_remove,
+	.config_changed			= virtblk_config_changed,
 #ifdef CONFIG_PM_SLEEP
-	.freeze			= virtblk_freeze,
-	.restore		= virtblk_restore,
+	.freeze				= virtblk_freeze,
+	.restore			= virtblk_restore,
 #endif
 };
 
@@ -871,8 +883,8 @@ out_destroy_workqueue:
 
 static void __exit fini(void)
 {
-	unregister_blkdev(major, "virtblk");
 	unregister_virtio_driver(&virtio_blk);
+	unregister_blkdev(major, "virtblk");
 	destroy_workqueue(virtblk_wq);
 }
 module_init(init);
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index cf7a561fad7c..de03df9dd7c9 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -355,7 +355,7 @@ static inline bool use_multiport(struct ports_device *portdev)
 	 */
 	if (!portdev->vdev)
 		return 0;
-	return portdev->vdev->features[0] & (1 << VIRTIO_CONSOLE_F_MULTIPORT);
+	return __virtio_test_bit(portdev->vdev, VIRTIO_CONSOLE_F_MULTIPORT);
 }
 
 static DEFINE_SPINLOCK(dma_bufs_lock);
@@ -566,9 +566,9 @@ static ssize_t __send_control_msg(struct ports_device *portdev, u32 port_id,
 	if (!use_multiport(portdev))
 		return 0;
 
-	cpkt.id = port_id;
-	cpkt.event = event;
-	cpkt.value = value;
+	cpkt.id = cpu_to_virtio32(portdev->vdev, port_id);
+	cpkt.event = cpu_to_virtio16(portdev->vdev, event);
+	cpkt.value = cpu_to_virtio16(portdev->vdev, value);
 
 	vq = portdev->c_ovq;
 
@@ -669,8 +669,8 @@ done:
  * Give out the data that's requested from the buffer that we have
  * queued up.
  */
-static ssize_t fill_readbuf(struct port *port, char *out_buf, size_t out_count,
-			    bool to_user)
+static ssize_t fill_readbuf(struct port *port, char __user *out_buf,
+			    size_t out_count, bool to_user)
 {
 	struct port_buffer *buf;
 	unsigned long flags;
@@ -688,7 +688,8 @@ static ssize_t fill_readbuf(struct port *port, char *out_buf, size_t out_count,
 		if (ret)
 			return -EFAULT;
 	} else {
-		memcpy(out_buf, buf->buf + buf->offset, out_count);
+		memcpy((__force char *)out_buf, buf->buf + buf->offset,
+		       out_count);
 	}
 
 	buf->offset += out_count;
@@ -1162,7 +1163,7 @@ static int get_chars(u32 vtermno, char *buf, int count)
 	/* If we don't have an input queue yet, we can't get input. */
 	BUG_ON(!port->in_vq);
 
-	return fill_readbuf(port, buf, count, false);
+	return fill_readbuf(port, (__force char __user *)buf, count, false);
 }
 
 static void resize_console(struct port *port)
@@ -1602,7 +1603,8 @@ static void unplug_port(struct port *port)
 }
 
 /* Any private messages that the Host and Guest want to share */
-static void handle_control_message(struct ports_device *portdev,
+static void handle_control_message(struct virtio_device *vdev,
+				   struct ports_device *portdev,
 				   struct port_buffer *buf)
 {
 	struct virtio_console_control *cpkt;
@@ -1612,15 +1614,16 @@ static void handle_control_message(struct ports_device *portdev,
 
 	cpkt = (struct virtio_console_control *)(buf->buf + buf->offset);
 
-	port = find_port_by_id(portdev, cpkt->id);
-	if (!port && cpkt->event != VIRTIO_CONSOLE_PORT_ADD) {
+	port = find_port_by_id(portdev, virtio32_to_cpu(vdev, cpkt->id));
+	if (!port &&
+	    cpkt->event != cpu_to_virtio16(vdev, VIRTIO_CONSOLE_PORT_ADD)) {
 		/* No valid header at start of buffer.  Drop it. */
 		dev_dbg(&portdev->vdev->dev,
 			"Invalid index %u in control packet\n", cpkt->id);
 		return;
 	}
 
-	switch (cpkt->event) {
+	switch (virtio16_to_cpu(vdev, cpkt->event)) {
 	case VIRTIO_CONSOLE_PORT_ADD:
 		if (port) {
 			dev_dbg(&portdev->vdev->dev,
@@ -1628,13 +1631,15 @@ static void handle_control_message(struct ports_device *portdev,
 			send_control_msg(port, VIRTIO_CONSOLE_PORT_READY, 1);
 			break;
 		}
-		if (cpkt->id >= portdev->config.max_nr_ports) {
+		if (virtio32_to_cpu(vdev, cpkt->id) >=
+		    portdev->config.max_nr_ports) {
 			dev_warn(&portdev->vdev->dev,
-				"Request for adding port with out-of-bound id %u, max. supported id: %u\n",
+				"Request for adding port with "
+				"out-of-bound id %u, max. supported id: %u\n",
 				cpkt->id, portdev->config.max_nr_ports - 1);
 			break;
 		}
-		add_port(portdev, cpkt->id);
+		add_port(portdev, virtio32_to_cpu(vdev, cpkt->id));
 		break;
 	case VIRTIO_CONSOLE_PORT_REMOVE:
 		unplug_port(port);
@@ -1670,7 +1675,7 @@ static void handle_control_message(struct ports_device *portdev,
 		break;
 	}
 	case VIRTIO_CONSOLE_PORT_OPEN:
-		port->host_connected = cpkt->value;
+		port->host_connected = virtio16_to_cpu(vdev, cpkt->value);
 		wake_up_interruptible(&port->waitqueue);
 		/*
 		 * If the host port got closed and the host had any
@@ -1752,7 +1757,7 @@ static void control_work_handler(struct work_struct *work)
 		buf->len = len;
 		buf->offset = 0;
 
-		handle_control_message(portdev, buf);
+		handle_control_message(vq->vdev, portdev, buf);
 
 		spin_lock(&portdev->c_ivq_lock);
 		if (add_inbuf(portdev->c_ivq, buf) < 0) {
diff --git a/drivers/lguest/lguest_device.c b/drivers/lguest/lguest_device.c
index d0a1d8a45c81..89088d6538fd 100644
--- a/drivers/lguest/lguest_device.c
+++ b/drivers/lguest/lguest_device.c
@@ -94,7 +94,7 @@ static unsigned desc_size(const struct lguest_device_desc *desc)
 }
 
 /* This gets the device's feature bits. */
-static u32 lg_get_features(struct virtio_device *vdev)
+static u64 lg_get_features(struct virtio_device *vdev)
 {
 	unsigned int i;
 	u32 features = 0;
@@ -126,7 +126,7 @@ static void status_notify(struct virtio_device *vdev)
  * sorted out, this routine is called so we can tell the Host which features we
  * understand and accept.
  */
-static void lg_finalize_features(struct virtio_device *vdev)
+static int lg_finalize_features(struct virtio_device *vdev)
 {
 	unsigned int i, bits;
 	struct lguest_device_desc *desc = to_lgdev(vdev)->desc;
@@ -136,20 +136,25 @@ static void lg_finalize_features(struct virtio_device *vdev)
 	/* Give virtio_ring a chance to accept features. */
 	vring_transport_features(vdev);
 
+	/* Make sure we don't have any features > 32 bits! */
+	BUG_ON((u32)vdev->features != vdev->features);
+
 	/*
-	 * The vdev->feature array is a Linux bitmask: this isn't the same as a
-	 * the simple array of bits used by lguest devices for features.  So we
-	 * do this slow, manual conversion which is completely general.
+	 * Since lguest is currently x86-only, we're little-endian.  That
+	 * means we could just memcpy.  But it's not time critical, and in
+	 * case someone copies this code, we do it the slow, obvious way.
 	 */
 	memset(out_features, 0, desc->feature_len);
 	bits = min_t(unsigned, desc->feature_len, sizeof(vdev->features)) * 8;
 	for (i = 0; i < bits; i++) {
-		if (test_bit(i, vdev->features))
+		if (__virtio_test_bit(vdev, i))
 			out_features[i / 8] |= (1 << (i % 8));
 	}
 
 	/* Tell Host we've finished with this device's feature negotiation */
 	status_notify(vdev);
+
+	return 0;
 }
 
 /* Once they've found a field, getting a copy of it is easy. */
diff --git a/drivers/misc/mic/card/mic_virtio.c b/drivers/misc/mic/card/mic_virtio.c
index e64794730e21..e486a0c26267 100644
--- a/drivers/misc/mic/card/mic_virtio.c
+++ b/drivers/misc/mic/card/mic_virtio.c
@@ -68,7 +68,7 @@ static inline struct device *mic_dev(struct mic_vdev *mvdev)
 }
 
 /* This gets the device's feature bits. */
-static u32 mic_get_features(struct virtio_device *vdev)
+static u64 mic_get_features(struct virtio_device *vdev)
 {
 	unsigned int i, bits;
 	u32 features = 0;
@@ -76,8 +76,7 @@ static u32 mic_get_features(struct virtio_device *vdev)
 	u8 __iomem *in_features = mic_vq_features(desc);
 	int feature_len = ioread8(&desc->feature_len);
 
-	bits = min_t(unsigned, feature_len,
-		sizeof(vdev->features)) * 8;
+	bits = min_t(unsigned, feature_len, sizeof(features)) * 8;
 	for (i = 0; i < bits; i++)
 		if (ioread8(&in_features[i / 8]) & (BIT(i % 8)))
 			features |= BIT(i);
@@ -85,7 +84,7 @@ static u32 mic_get_features(struct virtio_device *vdev)
 	return features;
 }
 
-static void mic_finalize_features(struct virtio_device *vdev)
+static int mic_finalize_features(struct virtio_device *vdev)
 {
 	unsigned int i, bits;
 	struct mic_device_desc __iomem *desc = to_micvdev(vdev)->desc;
@@ -97,14 +96,19 @@ static void mic_finalize_features(struct virtio_device *vdev)
 	/* Give virtio_ring a chance to accept features. */
 	vring_transport_features(vdev);
 
+	/* Make sure we don't have any features > 32 bits! */
+	BUG_ON((u32)vdev->features != vdev->features);
+
 	memset_io(out_features, 0, feature_len);
 	bits = min_t(unsigned, feature_len,
 		sizeof(vdev->features)) * 8;
 	for (i = 0; i < bits; i++) {
-		if (test_bit(i, vdev->features))
+		if (__virtio_test_bit(vdev, i))
 			iowrite8(ioread8(&out_features[i / 8]) | (1 << (i % 8)),
 				 &out_features[i / 8]);
 	}
+
+	return 0;
 }
 
 /*
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 880cc090dc44..af90ab5e5768 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -45,6 +45,18 @@ struct macvtap_queue {
 	struct list_head next;
 };
 
+#define MACVTAP_FEATURES (IFF_VNET_HDR | IFF_VNET_LE | IFF_MULTI_QUEUE)
+
+static inline u16 macvtap16_to_cpu(struct macvtap_queue *q, __virtio16 val)
+{
+	return __virtio16_to_cpu(q->flags & IFF_VNET_LE, val);
+}
+
+static inline __virtio16 cpu_to_macvtap16(struct macvtap_queue *q, u16 val)
+{
+	return __cpu_to_virtio16(q->flags & IFF_VNET_LE, val);
+}
+
 static struct proto macvtap_proto = {
 	.name = "macvtap",
 	.owner = THIS_MODULE,
@@ -557,7 +569,8 @@ static inline struct sk_buff *macvtap_alloc_skb(struct sock *sk, size_t prepad,
  * macvtap_skb_from_vnet_hdr and macvtap_skb_to_vnet_hdr should
  * be shared with the tun/tap driver.
  */
-static int macvtap_skb_from_vnet_hdr(struct sk_buff *skb,
+static int macvtap_skb_from_vnet_hdr(struct macvtap_queue *q,
+				     struct sk_buff *skb,
 				     struct virtio_net_hdr *vnet_hdr)
 {
 	unsigned short gso_type = 0;
@@ -588,13 +601,13 @@ static int macvtap_skb_from_vnet_hdr(struct sk_buff *skb,
 	}
 
 	if (vnet_hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
-		if (!skb_partial_csum_set(skb, vnet_hdr->csum_start,
-					  vnet_hdr->csum_offset))
+		if (!skb_partial_csum_set(skb, macvtap16_to_cpu(q, vnet_hdr->csum_start),
+					  macvtap16_to_cpu(q, vnet_hdr->csum_offset)))
 			return -EINVAL;
 	}
 
 	if (vnet_hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
-		skb_shinfo(skb)->gso_size = vnet_hdr->gso_size;
+		skb_shinfo(skb)->gso_size = macvtap16_to_cpu(q, vnet_hdr->gso_size);
 		skb_shinfo(skb)->gso_type = gso_type;
 
 		/* Header must be checked, and gso_segs computed. */
@@ -604,8 +617,9 @@ static int macvtap_skb_from_vnet_hdr(struct sk_buff *skb,
 	return 0;
 }
 
-static void macvtap_skb_to_vnet_hdr(const struct sk_buff *skb,
-				   struct virtio_net_hdr *vnet_hdr)
+static void macvtap_skb_to_vnet_hdr(struct macvtap_queue *q,
+				    const struct sk_buff *skb,
+				    struct virtio_net_hdr *vnet_hdr)
 {
 	memset(vnet_hdr, 0, sizeof(*vnet_hdr));
 
@@ -613,8 +627,8 @@ static void macvtap_skb_to_vnet_hdr(const struct sk_buff *skb,
 		struct skb_shared_info *sinfo = skb_shinfo(skb);
 
 		/* This is a hint as to how much should be linear. */
-		vnet_hdr->hdr_len = skb_headlen(skb);
-		vnet_hdr->gso_size = sinfo->gso_size;
+		vnet_hdr->hdr_len = cpu_to_macvtap16(q, skb_headlen(skb));
+		vnet_hdr->gso_size = cpu_to_macvtap16(q, sinfo->gso_size);
 		if (sinfo->gso_type & SKB_GSO_TCPV4)
 			vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
 		else if (sinfo->gso_type & SKB_GSO_TCPV6)
@@ -628,10 +642,13 @@ static void macvtap_skb_to_vnet_hdr(const struct sk_buff *skb,
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		vnet_hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
-		vnet_hdr->csum_start = skb_checksum_start_offset(skb);
 		if (vlan_tx_tag_present(skb))
-			vnet_hdr->csum_start += VLAN_HLEN;
-		vnet_hdr->csum_offset = skb->csum_offset;
+			vnet_hdr->csum_start = cpu_to_macvtap16(q,
+				skb_checksum_start_offset(skb) + VLAN_HLEN);
+		else
+			vnet_hdr->csum_start = cpu_to_macvtap16(q,
+				skb_checksum_start_offset(skb));
+		vnet_hdr->csum_offset = cpu_to_macvtap16(q, skb->csum_offset);
 	} else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
 		vnet_hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID;
 	} /* else everything is zero */
@@ -666,12 +683,14 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 		if (err < 0)
 			goto err;
 		if ((vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) &&
-		     vnet_hdr.csum_start + vnet_hdr.csum_offset + 2 >
-							vnet_hdr.hdr_len)
-			vnet_hdr.hdr_len = vnet_hdr.csum_start +
-						vnet_hdr.csum_offset + 2;
+		     macvtap16_to_cpu(q, vnet_hdr.csum_start) +
+		     macvtap16_to_cpu(q, vnet_hdr.csum_offset) + 2 >
+			     macvtap16_to_cpu(q, vnet_hdr.hdr_len))
+			vnet_hdr.hdr_len = cpu_to_macvtap16(q,
+				 macvtap16_to_cpu(q, vnet_hdr.csum_start) +
+				 macvtap16_to_cpu(q, vnet_hdr.csum_offset) + 2);
 		err = -EINVAL;
-		if (vnet_hdr.hdr_len > len)
+		if (macvtap16_to_cpu(q, vnet_hdr.hdr_len) > len)
 			goto err;
 	}
 
@@ -684,7 +703,8 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 		goto err;
 
 	if (m && m->msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY)) {
-		copylen = vnet_hdr.hdr_len ? vnet_hdr.hdr_len : GOODCOPY_LEN;
+		copylen = vnet_hdr.hdr_len ?
+			macvtap16_to_cpu(q, vnet_hdr.hdr_len) : GOODCOPY_LEN;
 		if (copylen > good_linear)
 			copylen = good_linear;
 		linear = copylen;
@@ -695,10 +715,10 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 
 	if (!zerocopy) {
 		copylen = len;
-		if (vnet_hdr.hdr_len > good_linear)
+		if (macvtap16_to_cpu(q, vnet_hdr.hdr_len) > good_linear)
 			linear = good_linear;
 		else
-			linear = vnet_hdr.hdr_len;
+			linear = macvtap16_to_cpu(q, vnet_hdr.hdr_len);
 	}
 
 	skb = macvtap_alloc_skb(&q->sk, NET_IP_ALIGN, copylen,
@@ -725,7 +745,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 	skb->protocol = eth_hdr(skb)->h_proto;
 
 	if (vnet_hdr_len) {
-		err = macvtap_skb_from_vnet_hdr(skb, &vnet_hdr);
+		err = macvtap_skb_from_vnet_hdr(q, skb, &vnet_hdr);
 		if (err)
 			goto err_kfree;
 	}
@@ -791,7 +811,7 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
 		if ((len -= vnet_hdr_len) < 0)
 			return -EINVAL;
 
-		macvtap_skb_to_vnet_hdr(skb, &vnet_hdr);
+		macvtap_skb_to_vnet_hdr(q, skb, &vnet_hdr);
 
 		if (memcpy_toiovecend(iv, (void *)&vnet_hdr, 0, sizeof(vnet_hdr)))
 			return -EFAULT;
@@ -1003,8 +1023,7 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd,
 			return -EFAULT;
 
 		ret = 0;
-		if ((u & ~(IFF_VNET_HDR | IFF_MULTI_QUEUE)) !=
-		    (IFF_NO_PI | IFF_TAP))
+		if ((u & ~MACVTAP_FEATURES) != (IFF_NO_PI | IFF_TAP))
 			ret = -EINVAL;
 		else
 			q->flags = u;
@@ -1036,8 +1055,7 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd,
 		return ret;
 
 	case TUNGETFEATURES:
-		if (put_user(IFF_TAP | IFF_NO_PI | IFF_VNET_HDR |
-			     IFF_MULTI_QUEUE, up))
+		if (put_user(IFF_TAP | IFF_NO_PI | MACVTAP_FEATURES, up))
 			return -EFAULT;
 		return 0;
 
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 4d332dc93b70..798ce70e3d61 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -103,6 +103,15 @@ do {								\
 } while (0)
 #endif
 
+/* TUN device flags */
+
+/* IFF_ATTACH_QUEUE is never stored in device flags,
+ * overload it to mean fasync when stored there.
+ */
+#define TUN_FASYNC	IFF_ATTACH_QUEUE
+
+#define TUN_FEATURES (IFF_NO_PI | IFF_ONE_QUEUE | IFF_VNET_HDR | \
+		      IFF_VNET_LE | IFF_MULTI_QUEUE)
 #define GOODCOPY_LEN 128
 
 #define FLT_EXACT_COUNT 8
@@ -196,6 +205,16 @@ struct tun_struct {
 	u32 flow_count;
 };
 
+static inline u16 tun16_to_cpu(struct tun_struct *tun, __virtio16 val)
+{
+	return __virtio16_to_cpu(tun->flags & IFF_VNET_LE, val);
+}
+
+static inline __virtio16 cpu_to_tun16(struct tun_struct *tun, u16 val)
+{
+	return __cpu_to_virtio16(tun->flags & IFF_VNET_LE, val);
+}
+
 static inline u32 tun_hashfn(u32 rxhash)
 {
 	return rxhash & 0x3ff;
@@ -472,7 +491,7 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
 		if (tun && tun->numqueues == 0 && tun->numdisabled == 0) {
 			netif_carrier_off(tun->dev);
 
-			if (!(tun->flags & TUN_PERSIST) &&
+			if (!(tun->flags & IFF_PERSIST) &&
 			    tun->dev->reg_state == NETREG_REGISTERED)
 				unregister_netdevice(tun->dev);
 		}
@@ -523,7 +542,7 @@ static void tun_detach_all(struct net_device *dev)
 	}
 	BUG_ON(tun->numdisabled != 0);
 
-	if (tun->flags & TUN_PERSIST)
+	if (tun->flags & IFF_PERSIST)
 		module_put(THIS_MODULE);
 }
 
@@ -541,7 +560,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filte
 		goto out;
 
 	err = -EBUSY;
-	if (!(tun->flags & TUN_TAP_MQ) && tun->numqueues == 1)
+	if (!(tun->flags & IFF_MULTI_QUEUE) && tun->numqueues == 1)
 		goto out;
 
 	err = -E2BIG;
@@ -920,7 +939,7 @@ static void tun_net_init(struct net_device *dev)
 	struct tun_struct *tun = netdev_priv(dev);
 
 	switch (tun->flags & TUN_TYPE_MASK) {
-	case TUN_TUN_DEV:
+	case IFF_TUN:
 		dev->netdev_ops = &tun_netdev_ops;
 
 		/* Point-to-Point TUN Device */
@@ -934,7 +953,7 @@ static void tun_net_init(struct net_device *dev)
 		dev->tx_queue_len = TUN_READQ_SIZE;  /* We prefer our own queue length */
 		break;
 
-	case TUN_TAP_DEV:
+	case IFF_TAP:
 		dev->netdev_ops = &tap_netdev_ops;
 		/* Ethernet TAP Device */
 		ether_setup(dev);
@@ -1025,7 +1044,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	int err;
 	u32 rxhash;
 
-	if (!(tun->flags & TUN_NO_PI)) {
+	if (!(tun->flags & IFF_NO_PI)) {
 		if (len < sizeof(pi))
 			return -EINVAL;
 		len -= sizeof(pi);
@@ -1035,7 +1054,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		offset += sizeof(pi);
 	}
 
-	if (tun->flags & TUN_VNET_HDR) {
+	if (tun->flags & IFF_VNET_HDR) {
 		if (len < tun->vnet_hdr_sz)
 			return -EINVAL;
 		len -= tun->vnet_hdr_sz;
@@ -1044,18 +1063,18 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 			return -EFAULT;
 
 		if ((gso.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) &&
-		    gso.csum_start + gso.csum_offset + 2 > gso.hdr_len)
-			gso.hdr_len = gso.csum_start + gso.csum_offset + 2;
+		    tun16_to_cpu(tun, gso.csum_start) + tun16_to_cpu(tun, gso.csum_offset) + 2 > tun16_to_cpu(tun, gso.hdr_len))
+			gso.hdr_len = cpu_to_tun16(tun, tun16_to_cpu(tun, gso.csum_start) + tun16_to_cpu(tun, gso.csum_offset) + 2);
 
-		if (gso.hdr_len > len)
+		if (tun16_to_cpu(tun, gso.hdr_len) > len)
 			return -EINVAL;
 		offset += tun->vnet_hdr_sz;
 	}
 
-	if ((tun->flags & TUN_TY