Merge git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-for-linus

* git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-for-linus: (25 commits)
  virtio: balloon driver
  virtio: Use PCI revision field to indicate virtio PCI ABI version
  virtio: PCI device
  virtio_blk: implement naming for vda-vdz,vdaa-vdzz,vdaaa-vdzzz
  virtio_blk: Dont waste major numbers
  virtio_blk: provide getgeo
  virtio_net: parametrize the napi_weight for virtio receive queue.
  virtio: free transmit skbs when notified, not on next xmit.
  virtio: flush buffers on open
  virtnet: remove double ether_setup
  virtio: Allow virtio to be modular and used by modules
  virtio: Use the sg_phys convenience function.
  virtio: Put the virtio under the virtualization menu
  virtio: handle interrupts after callbacks turned off
  virtio: reset function
  virtio: populate network rings in the probe routine, not open
  virtio: Tweak virtio_net defines
  virtio: Net header needs hdr_len
  virtio: remove unused id field from struct virtio_blk_outhdr
  virtio: clarify NO_NOTIFY flag usage
  ...

13 files changed, 1055 insertions, 243 deletions

diff --git a/drivers/Kconfig b/drivers/Kconfig
index 08d4ae20159..3f8a231fe75 100644
--- a/drivers/Kconfig
+++ b/drivers/Kconfig
@@ -91,6 +91,4 @@ source "drivers/dca/Kconfig"
 source "drivers/auxdisplay/Kconfig"
 
 source "drivers/uio/Kconfig"
-
-source "drivers/virtio/Kconfig"
 endmenu
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index f2122855d4e..64e5148d82b 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -440,6 +440,7 @@ config VIRTIO_BLK
 	tristate "Virtio block driver (EXPERIMENTAL)"
 	depends on EXPERIMENTAL && VIRTIO
 	---help---
-	  This is the virtual block driver for lguest.  Say Y or M.
+	  This is the virtual block driver for virtio.  It can be used with
+          lguest or QEMU based VMMs (like KVM or Xen).  Say Y or M.
 
 endif # BLK_DEV
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 924ddd8bccd..3b1a68d6edd 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -7,8 +7,10 @@
 #include <linux/scatterlist.h>
 
 #define VIRTIO_MAX_SG	(3+MAX_PHYS_SEGMENTS)
+#define PART_BITS 4
+
+static int major, index;
 
-static unsigned char virtblk_index = 'a';
 struct virtio_blk
 {
 	spinlock_t lock;
@@ -36,7 +38,7 @@ struct virtblk_req
 	struct virtio_blk_inhdr in_hdr;
 };
 
-static bool blk_done(struct virtqueue *vq)
+static void blk_done(struct virtqueue *vq)
 {
 	struct virtio_blk *vblk = vq->vdev->priv;
 	struct virtblk_req *vbr;
@@ -65,7 +67,6 @@ static bool blk_done(struct virtqueue *vq)
 	/* In case queue is stopped waiting for more buffers. */
 	blk_start_queue(vblk->disk->queue);
 	spin_unlock_irqrestore(&vblk->lock, flags);
-	return true;
 }
 
 static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
@@ -153,20 +154,37 @@ static int virtblk_ioctl(struct inode *inode, struct file *filp,
 			      (void __user *)data);
 }
 
+/* We provide getgeo only to please some old bootloader/partitioning tools */
+static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo)
+{
+	/* some standard values, similar to sd */
+	geo->heads = 1 << 6;
+	geo->sectors = 1 << 5;
+	geo->cylinders = get_capacity(bd->bd_disk) >> 11;
+	return 0;
+}
+
 static struct block_device_operations virtblk_fops = {
-	.ioctl = virtblk_ioctl,
-	.owner = THIS_MODULE,
+	.ioctl  = virtblk_ioctl,
+	.owner  = THIS_MODULE,
+	.getgeo = virtblk_getgeo,
 };
 
+static int index_to_minor(int index)
+{
+	return index << PART_BITS;
+}
+
 static int virtblk_probe(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk;
-	int err, major;
-	void *token;
-	unsigned int len;
+	int err;
 	u64 cap;
 	u32 v;
 
+	if (index_to_minor(index) >= 1 << MINORBITS)
+		return -ENOSPC;
+
 	vdev->priv = vblk = kmalloc(sizeof(*vblk), GFP_KERNEL);
 	if (!vblk) {
 		err = -ENOMEM;
@@ -178,7 +196,7 @@ static int virtblk_probe(struct virtio_device *vdev)
 	vblk->vdev = vdev;
 
 	/* We expect one virtqueue, for output. */
-	vblk->vq = vdev->config->find_vq(vdev, blk_done);
+	vblk->vq = vdev->config->find_vq(vdev, 0, blk_done);
 	if (IS_ERR(vblk->vq)) {
 		err = PTR_ERR(vblk->vq);
 		goto out_free_vblk;
@@ -190,17 +208,11 @@ static int virtblk_probe(struct virtio_device *vdev)
 		goto out_free_vq;
 	}
 
-	major = register_blkdev(0, "virtblk");
-	if (major < 0) {
-		err = major;
-		goto out_mempool;
-	}
-
 	/* FIXME: How many partitions?  How long is a piece of string? */
-	vblk->disk = alloc_disk(1 << 4);
+	vblk->disk = alloc_disk(1 << PART_BITS);
 	if (!vblk->disk) {
 		err = -ENOMEM;
-		goto out_unregister_blkdev;
+		goto out_mempool;
 	}
 
 	vblk->disk->queue = blk_init_queue(do_virtblk_request, &vblk->lock);
@@ -209,22 +221,32 @@ static int virtblk_probe(struct virtio_device *vdev)
 		goto out_put_disk;
 	}
 
-	sprintf(vblk->disk->disk_name, "vd%c", virtblk_index++);
+	if (index < 26) {
+		sprintf(vblk->disk->disk_name, "vd%c", 'a' + index % 26);
+	} else if (index < (26 + 1) * 26) {
+		sprintf(vblk->disk->disk_name, "vd%c%c",
+			'a' + index / 26 - 1, 'a' + index % 26);
+	} else {
+		const unsigned int m1 = (index / 26 - 1) / 26 - 1;
+		const unsigned int m2 = (index / 26 - 1) % 26;
+		const unsigned int m3 =  index % 26;
+		sprintf(vblk->disk->disk_name, "vd%c%c%c",
+			'a' + m1, 'a' + m2, 'a' + m3);
+	}
+
 	vblk->disk->major = major;
-	vblk->disk->first_minor = 0;
+	vblk->disk->first_minor = index_to_minor(index);
 	vblk->disk->private_data = vblk;
 	vblk->disk->fops = &virtblk_fops;
+	index++;
 
 	/* If barriers are supported, tell block layer that queue is ordered */
-	token = vdev->config->find(vdev, VIRTIO_CONFIG_BLK_F, &len);
-	if (virtio_use_bit(vdev, token, len, VIRTIO_BLK_F_BARRIER))
+	if (vdev->config->feature(vdev, VIRTIO_BLK_F_BARRIER))
 		blk_queue_ordered(vblk->disk->queue, QUEUE_ORDERED_TAG, NULL);
 
-	err = virtio_config_val(vdev, VIRTIO_CONFIG_BLK_F_CAPACITY, &cap);
-	if (err) {
-		dev_err(&vdev->dev, "Bad/missing capacity in config\n");
-		goto out_cleanup_queue;
-	}
+	/* Host must always specify the capacity. */
+	__virtio_config_val(vdev, offsetof(struct virtio_blk_config, capacity),
+			    &cap);
 
 	/* If capacity is too big, truncate with warning. */
 	if ((sector_t)cap != cap) {
@@ -234,31 +256,25 @@ static int virtblk_probe(struct virtio_device *vdev)
 	}
 	set_capacity(vblk->disk, cap);
 
-	err = virtio_config_val(vdev, VIRTIO_CONFIG_BLK_F_SIZE_MAX, &v);
+	/* Host can optionally specify maximum segment size and number of
+	 * segments. */
+	err = virtio_config_val(vdev, VIRTIO_BLK_F_SIZE_MAX,
+				offsetof(struct virtio_blk_config, size_max),
+				&v);
 	if (!err)
 		blk_queue_max_segment_size(vblk->disk->queue, v);
-	else if (err != -ENOENT) {
-		dev_err(&vdev->dev, "Bad SIZE_MAX in config\n");
-		goto out_cleanup_queue;
-	}
 
-	err = virtio_config_val(vdev, VIRTIO_CONFIG_BLK_F_SEG_MAX, &v);
+	err = virtio_config_val(vdev, VIRTIO_BLK_F_SEG_MAX,
+				offsetof(struct virtio_blk_config, seg_max),
+				&v);
 	if (!err)
 		blk_queue_max_hw_segments(vblk->disk->queue, v);
-	else if (err != -ENOENT) {
-		dev_err(&vdev->dev, "Bad SEG_MAX in config\n");
-		goto out_cleanup_queue;
-	}
 
 	add_disk(vblk->disk);
 	return 0;
 
-out_cleanup_queue:
-	blk_cleanup_queue(vblk->disk->queue);
 out_put_disk:
 	put_disk(vblk->disk);
-out_unregister_blkdev:
-	unregister_blkdev(major, "virtblk");
 out_mempool:
 	mempool_destroy(vblk->pool);
 out_free_vq:
@@ -274,12 +290,16 @@ static void virtblk_remove(struct virtio_device *vdev)
 	struct virtio_blk *vblk = vdev->priv;
 	int major = vblk->disk->major;
 
+	/* Nothing should be pending. */
 	BUG_ON(!list_empty(&vblk->reqs));
+
+	/* Stop all the virtqueues. */
+	vdev->config->reset(vdev);
+
 	blk_cleanup_queue(vblk->disk->queue);
 	put_disk(vblk->disk);
 	unregister_blkdev(major, "virtblk");
 	mempool_destroy(vblk->pool);
-	/* There should be nothing in the queue now, so no need to shutdown */
 	vdev->config->del_vq(vblk->vq);
 	kfree(vblk);
 }
@@ -299,11 +319,15 @@ static struct virtio_driver virtio_blk = {
 
 static int __init init(void)
 {
+	major = register_blkdev(0, "virtblk");
+	if (major < 0)
+		return major;
 	return register_virtio_driver(&virtio_blk);
 }
 
 static void __exit fini(void)
 {
+	unregister_blkdev(major, "virtblk");
 	unregister_virtio_driver(&virtio_blk);
 }
 module_init(init);
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index e34da5c9719..dc17fe3a88b 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -158,13 +158,13 @@ static int __devinit virtcons_probe(struct virtio_device *dev)
 	/* Find the input queue. */
 	/* FIXME: This is why we want to wean off hvc: we do nothing
 	 * when input comes in. */
-	in_vq = vdev->config->find_vq(vdev, NULL);
+	in_vq = vdev->config->find_vq(vdev, 0, NULL);
 	if (IS_ERR(in_vq)) {
 		err = PTR_ERR(in_vq);
 		goto free;
 	}
 
-	out_vq = vdev->config->find_vq(vdev, NULL);
+	out_vq = vdev->config->find_vq(vdev, 1, NULL);
 	if (IS_ERR(out_vq)) {
 		err = PTR_ERR(out_vq);
 		goto free_in_vq;
diff --git a/drivers/lguest/lguest_device.c b/drivers/lguest/lguest_device.c
index e2eec38c83c..84f85e23cca 100644
--- a/drivers/lguest/lguest_device.c
+++ b/drivers/lguest/lguest_device.c
@@ -52,57 +52,82 @@ struct lguest_device {
 /*D:130
  * Device configurations
  *
- * The configuration information for a device consists of a series of fields.
- * We don't really care what they are: the Launcher set them up, and the driver
- * will look at them during setup.
+ * The configuration information for a device consists of one or more
+ * virtqueues, a feature bitmaks, and some configuration bytes.  The
+ * configuration bytes don't really matter to us: the Launcher sets them up, and
+ * the driver will look at them during setup.
  *
- * For us these fields come immediately after that device's descriptor in the
- * lguest_devices page.
- *
- * Each field starts with a "type" byte, a "length" byte, then that number of
- * bytes of configuration information.  The device descriptor tells us the
- * total configuration length so we know when we've reached the last field. */
+ * A convenient routine to return the device's virtqueue config array:
+ * immediately after the descriptor. */
+static struct lguest_vqconfig *lg_vq(const struct lguest_device_desc *desc)
+{
+	return (void *)(desc + 1);
+}
 
-/* type + length bytes */
-#define FHDR_LEN 2
+/* The features come immediately after the virtqueues. */
+static u8 *lg_features(const struct lguest_device_desc *desc)
+{
+	return (void *)(lg_vq(desc) + desc->num_vq);
+}
 
-/* This finds the first field of a given type for a device's configuration. */
-static void *lg_find(struct virtio_device *vdev, u8 type, unsigned int *len)
+/* The config space comes after the two feature bitmasks. */
+static u8 *lg_config(const struct lguest_device_desc *desc)
 {
-	struct lguest_device_desc *desc = to_lgdev(vdev)->desc;
-	int i;
-
-	for (i = 0; i < desc->config_len; i += FHDR_LEN + desc->config[i+1]) {
-		if (desc->config[i] == type) {
-			/* Mark it used, so Host can know we looked at it, and
-			 * also so we won't find the same one twice. */
-			desc->config[i] |= 0x80;
-			/* Remember, the second byte is the length. */
-			*len = desc->config[i+1];
-			/* We return a pointer to the field header. */
-			return desc->config + i;
-		}
-	}
+	return lg_features(desc) + desc->feature_len * 2;
+}
 
-	/* Not found: return NULL for failure. */
-	return NULL;
+/* The total size of the config page used by this device (incl. desc) */
+static unsigned desc_size(const struct lguest_device_desc *desc)
+{
+	return sizeof(*desc)
+		+ desc->num_vq * sizeof(struct lguest_vqconfig)
+		+ desc->feature_len * 2
+		+ desc->config_len;
+}
+
+/* This tests (and acknowleges) a feature bit. */
+static bool lg_feature(struct virtio_device *vdev, unsigned fbit)
+{
+	struct lguest_device_desc *desc = to_lgdev(vdev)->desc;
+	u8 *features;
+
+	/* Obviously if they ask for a feature off the end of our feature
+	 * bitmap, it's not set. */
+	if (fbit / 8 > desc->feature_len)
+		return false;
+
+	/* The feature bitmap comes after the virtqueues. */
+	features = lg_features(desc);
+	if (!(features[fbit / 8] & (1 << (fbit % 8))))
+		return false;
+
+	/* We set the matching bit in the other half of the bitmap to tell the
+	 * Host we want to use this feature.  We don't use this yet, but we
+	 * could in future. */
+	features[desc->feature_len + fbit / 8] |= (1 << (fbit % 8));
+	return true;
 }
 
 /* Once they've found a field, getting a copy of it is easy. */
-static void lg_get(struct virtio_device *vdev, void *token,
+static void lg_get(struct virtio_device *vdev, unsigned int offset,
 		   void *buf, unsigned len)
 {
-	/* Check they didn't ask for more than the length of the field! */
-	BUG_ON(len > ((u8 *)token)[1]);
-	memcpy(buf, token + FHDR_LEN, len);
+	struct lguest_device_desc *desc = to_lgdev(vdev)->desc;
+
+	/* Check they didn't ask for more than the length of the config! */
+	BUG_ON(offset + len > desc->config_len);
+	memcpy(buf, lg_config(desc) + offset, len);
 }
 
 /* Setting the contents is also trivial. */
-static void lg_set(struct virtio_device *vdev, void *token,
+static void lg_set(struct virtio_device *vdev, unsigned int offset,
 		   const void *buf, unsigned len)
 {
-	BUG_ON(len > ((u8 *)token)[1]);
-	memcpy(token + FHDR_LEN, buf, len);
+	struct lguest_device_desc *desc = to_lgdev(vdev)->desc;
+
+	/* Check they didn't ask for more than the length of the config! */
+	BUG_ON(offset + len > desc->config_len);
+	memcpy(lg_config(desc) + offset, buf, len);
 }
 
 /* The operations to get and set the status word just access the status field
@@ -114,9 +139,20 @@ static u8 lg_get_status(struct virtio_device *vdev)
 
 static void lg_set_status(struct virtio_device *vdev, u8 status)
 {
+	BUG_ON(!status);
 	to_lgdev(vdev)->desc->status = status;
 }
 
+/* To reset the device, we (ab)use the NOTIFY hypercall, with the descriptor
+ * address of the device.  The Host will zero the status and all the
+ * features. */
+static void lg_reset(struct virtio_device *vdev)
+{
+	unsigned long offset = (void *)to_lgdev(vdev)->desc - lguest_devices;
+
+	hcall(LHCALL_NOTIFY, (max_pfn<<PAGE_SHIFT) + offset, 0, 0);
+}
+
 /*
  * Virtqueues
  *
@@ -165,39 +201,29 @@ static void lg_notify(struct virtqueue *vq)
  *
  * So we provide devices with a "find virtqueue and set it up" function. */
 static struct virtqueue *lg_find_vq(struct virtio_device *vdev,
-				    bool (*callback)(struct virtqueue *vq))
+				    unsigned index,
+				    void (*callback)(struct virtqueue *vq))
 {
+	struct lguest_device *ldev = to_lgdev(vdev);
 	struct lguest_vq_info *lvq;
 	struct virtqueue *vq;
-	unsigned int len;
-	void *token;
 	int err;
 
-	/* Look for a field of the correct type to mark a virtqueue.  Note that
-	 * if this succeeds, then the type will be changed so it won't be found
-	 * again, and future lg_find_vq() calls will find the next
-	 * virtqueue (if any). */
-	token = vdev->config->find(vdev, VIRTIO_CONFIG_F_VIRTQUEUE, &len);
-	if (!token)
+	/* We must have this many virtqueues. */
+	if (index >= ldev->desc->num_vq)
 		return ERR_PTR(-ENOENT);
 
 	lvq = kmalloc(sizeof(*lvq), GFP_KERNEL);
 	if (!lvq)
 		return ERR_PTR(-ENOMEM);
 
-	/* Note: we could use a configuration space inside here, just like we
-	 * do for the device.  This would allow expansion in future, because
-	 * our configuration system is designed to be expansible.  But this is
-	 * way easier. */
-	if (len != sizeof(lvq->config)) {
-		dev_err(&vdev->dev, "Unexpected virtio config len %u\n", len);
-		err = -EIO;
-		goto free_lvq;
-	}
-	/* Make a copy of the "struct lguest_vqconfig" field.  We need a copy
-	 * because the config space might not be aligned correctly. */
-	vdev->config->get(vdev, token, &lvq->config, sizeof(lvq->config));
+	/* Make a copy of the "struct lguest_vqconfig" entry, which sits after
+	 * the descriptor.  We need a copy because the config space might not
+	 * be aligned correctly. */
+	memcpy(&lvq->config, lg_vq(ldev->desc)+index, sizeof(lvq->config));
 
+	printk("Mapping virtqueue %i addr %lx\n", index,
+	       (unsigned long)lvq->config.pfn << PAGE_SHIFT);
 	/* Figure out how many pages the ring will take, and map that memory */
 	lvq->pages = lguest_map((unsigned long)lvq->config.pfn << PAGE_SHIFT,
 				DIV_ROUND_UP(vring_size(lvq->config.num,
@@ -259,11 +285,12 @@ static void lg_del_vq(struct virtqueue *vq)
 
 /* The ops structure which hooks everything together. */
 static struct virtio_config_ops lguest_config_ops = {
-	.find = lg_find,
+	.feature = lg_feature,
 	.get = lg_get,
 	.set = lg_set,
 	.get_status = lg_get_status,
 	.set_status = lg_set_status,
+	.reset = lg_reset,
 	.find_vq = lg_find_vq,
 	.del_vq = lg_del_vq,
 };
@@ -329,13 +356,14 @@ static void scan_devices(void)
 	struct lguest_device_desc *d;
 
 	/* We start at the page beginning, and skip over each entry. */
-	for (i = 0; i < PAGE_SIZE; i += sizeof(*d) + d->config_len) {
+	for (i = 0; i < PAGE_SIZE; i += desc_size(d)) {
 		d = lguest_devices + i;
 
 		/* Once we hit a zero, stop. */
 		if (d->type == 0)
 			break;
 
+		printk("Device at %i has size %u\n", i, desc_size(d));
 		add_lguest_device(d);
 	}
 }
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 55d224c8a0b..f234ba3f040 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -3114,6 +3114,7 @@ config VIRTIO_NET
 	tristate "Virtio network driver (EXPERIMENTAL)"
 	depends on EXPERIMENTAL && VIRTIO
 	---help---
-	  This is the virtual network driver for lguest.  Say Y or M.
+	  This is the virtual network driver for virtio.  It can be used with
+          lguest or QEMU based VMMs (like KVM or Xen).  Say Y or M.
 
 endif # NETDEVICES
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 5413dbf3d4a..e66de0c12fc 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -24,6 +24,13 @@
 #include <linux/virtio_net.h>
 #include <linux/scatterlist.h>
 
+static int napi_weight = 128;
+module_param(napi_weight, int, 0444);
+
+static int csum = 1, gso = 1;
+module_param(csum, bool, 0444);
+module_param(gso, bool, 0444);
+
 /* FIXME: MTU in config. */
 #define MAX_PACKET_LEN (ETH_HLEN+ETH_DATA_LEN)
 
@@ -52,13 +59,14 @@ static inline void vnet_hdr_to_sg(struct scatterlist *sg, struct sk_buff *skb)
 	sg_init_one(sg, skb_vnet_hdr(skb), sizeof(struct virtio_net_hdr));
 }
 
-static bool skb_xmit_done(struct virtqueue *rvq)
+static void skb_xmit_done(struct virtqueue *svq)
 {
-	struct virtnet_info *vi = rvq->vdev->priv;
+	struct virtnet_info *vi = svq->vdev->priv;
 
-	/* In case we were waiting for output buffers. */
+	/* Suppress further interrupts. */
+	svq->vq_ops->disable_cb(svq);
+	/* We were waiting for more output buffers. */
 	netif_wake_queue(vi->dev);
-	return true;
 }
 
 static void receive_skb(struct net_device *dev, struct sk_buff *skb,
@@ -83,28 +91,16 @@ static void receive_skb(struct net_device *dev, struct sk_buff *skb,
 
 	if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
 		pr_debug("Needs csum!\n");
-		skb->ip_summed = CHECKSUM_PARTIAL;
-		skb->csum_start = hdr->csum_start;
-		skb->csum_offset = hdr->csum_offset;
-		if (skb->csum_start > skb->len - 2
-		    || skb->csum_offset > skb->len - 2) {
-			if (net_ratelimit())
-				printk(KERN_WARNING "%s: csum=%u/%u len=%u\n",
-				       dev->name, skb->csum_start,
-				       skb->csum_offset, skb->len);
+		if (!skb_partial_csum_set(skb,hdr->csum_start,hdr->csum_offset))
 			goto frame_err;
-		}
 	}
 
 	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
 		pr_debug("GSO!\n");
-		switch (hdr->gso_type) {
+		switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
 		case VIRTIO_NET_HDR_GSO_TCPV4:
 			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
 			break;
-		case VIRTIO_NET_HDR_GSO_TCPV4_ECN:
-			skb_shinfo(skb)->gso_type = SKB_GSO_TCP_ECN;
-			break;
 		case VIRTIO_NET_HDR_GSO_UDP:
 			skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
 			break;
@@ -118,6 +114,9 @@ static void receive_skb(struct net_device *dev, struct sk_buff *skb,
 			goto frame_err;
 		}
 
+		if (hdr->gso_type & VIRTIO_NET_HDR_GSO_ECN)
+			skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
+
 		skb_shinfo(skb)->gso_size = hdr->gso_size;
 		if (skb_shinfo(skb)->gso_size == 0) {
 			if (net_ratelimit())
@@ -170,12 +169,14 @@ static void try_fill_recv(struct virtnet_info *vi)
 	vi->rvq->vq_ops->kick(vi->rvq);
 }
 
-static bool skb_recv_done(struct virtqueue *rvq)
+static void skb_recv_done(struct virtqueue *rvq)
 {
 	struct virtnet_info *vi = rvq->vdev->priv;
-	netif_rx_schedule(vi->dev, &vi->napi);
-	/* Suppress further interrupts. */
-	return false;
+	/* Schedule NAPI, Suppress further interrupts if successful. */
+	if (netif_rx_schedule_prep(vi->dev, &vi->napi)) {
+		rvq->vq_ops->disable_cb(rvq);
+		__netif_rx_schedule(vi->dev, &vi->napi);
+	}
 }
 
 static int virtnet_poll(struct napi_struct *napi, int budget)
@@ -201,7 +202,7 @@ again:
 	/* Out of packets? */
 	if (received < budget) {
 		netif_rx_complete(vi->dev, napi);
-		if (unlikely(!vi->rvq->vq_ops->restart(vi->rvq))
+		if (unlikely(!vi->rvq->vq_ops->enable_cb(vi->rvq))
 		    && netif_rx_reschedule(vi->dev, napi))
 			goto again;
 	}
@@ -236,8 +237,6 @@ static int start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	pr_debug("%s: xmit %p %s\n", dev->name, skb, print_mac(mac, dest));
 
-	free_old_xmit_skbs(vi);
-
 	/* Encode metadata header at front. */
 	hdr = skb_vnet_hdr(skb);
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
@@ -250,10 +249,9 @@ static int start_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	if (skb_is_gso(skb)) {
+		hdr->hdr_len = skb_transport_header(skb) - skb->data;
 		hdr->gso_size = skb_shinfo(skb)->gso_size;
-		if (skb_shinfo(skb)->gso_type & SKB_GSO_TCP_ECN)
-			hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4_ECN;
-		else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
+		if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
 			hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
 		else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
 			hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
@@ -261,19 +259,34 @@ static int start_xmit(struct sk_buff *skb, struct net_device *dev)
 			hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP;
 		else
 			BUG();
+		if (skb_shinfo(skb)->gso_type & SKB_GSO_TCP_ECN)
+			hdr->gso_type |= VIRTIO_NET_HDR_GSO_ECN;
 	} else {
 		hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE;
-		hdr->gso_size = 0;
+		hdr->gso_size = hdr->hdr_len = 0;
 	}
 
 	vnet_hdr_to_sg(sg, skb);
 	num = skb_to_sgvec(skb, sg+1, 0, skb->len) + 1;
 	__skb_queue_head(&vi->send, skb);
+
+again:
+	/* Free up any pending old buffers before queueing new ones. */
+	free_old_xmit_skbs(vi);
 	err = vi->svq->vq_ops->add_buf(vi->svq, sg, num, 0, skb);
 	if (err) {
 		pr_debug("%s: virtio not prepared to send\n", dev->name);
-		skb_unlink(skb, &vi->send);
 		netif_stop_queue(dev);
+
+		/* Activate callback for using skbs: if this fails it
+		 * means some were used in the meantime. */
+		if (unlikely(!vi->svq->vq_ops->enable_cb(vi->svq))) {
+			printk("Unlikely: restart svq failed\n");
+			netif_start_queue(dev);
+			goto again;
+		}
+		__skb_unlink(skb, &vi->send);
+
 		return NETDEV_TX_BUSY;
 	}
 	vi->svq->vq_ops->kick(vi->svq);
@@ -285,45 +298,31 @@ static int virtnet_open(struct net_device *dev)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
 
-	try_fill_recv(vi);
+	napi_enable(&vi->napi);
 
-	/* If we didn't even get one input buffer, we're useless. */
-	if (vi->num == 0)
-		return -ENOMEM;
+	/* If all buffers were filled by other side before we napi_enabled, we
+	 * won't get another interrupt, so process any outstanding packets
+	 * now.  virtnet_poll wants re-enable the queue, so we disable here. */
+	vi->rvq->vq_ops->disable_cb(vi->rvq);
+	netif_rx_schedule(vi->dev, &vi->napi);
 
-	napi_enable(&vi->napi);
 	return 0;
 }
 
 static int virtnet_close(struct net_device *dev)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
-	struct sk_buff *skb;
 
 	napi_disable(&vi->napi);
 
-	/* networking core has neutered skb_xmit_done/skb_recv_done, so don't
-	 * worry about races vs. get(). */
-	vi->rvq->vq_ops->shutdown(vi->rvq);
-	while ((skb = __skb_dequeue(&vi->recv)) != NULL) {
-		kfree_skb(skb);
-		vi->num--;
-	}
-	vi->svq->vq_ops->shutdown(vi->svq);
-	while ((skb = __skb_dequeue(&vi->send)) != NULL)
-		kfree_skb(skb);
-
-	BUG_ON(vi->num != 0);
 	return 0;
 }
 
 static int virtnet_probe(struct virtio_device *vdev)
 {
 	int err;
-	unsigned int len;
 	struct net_device *dev;
 	struct virtnet_info *vi;
-	void *token;
 
 	/* Allocate ourselves a network device with room for our info */
 	dev = alloc_etherdev(sizeof(struct virtnet_info));
@@ -331,7 +330,6 @@ static int virtnet_probe(struct virtio_device *vdev)
 		return -ENOMEM;
 
 	/* Set up network device as normal. */
-	ether_setup(dev);
 	dev->open = virtnet_open;
 	dev->stop = virtnet_close;
 	dev->hard_start_xmit = start_xmit;
@@ -339,42 +337,37 @@ static int virtnet_probe(struct virtio_device *vdev)
 	SET_NETDEV_DEV(dev, &vdev->dev);
 
 	/* Do we support "hardware" checksums? */
-	token = vdev->config->find(vdev, VIRTIO_CONFIG_NET_F, &len);
-	if (virtio_use_bit(vdev, token, len, VIRTIO_NET_F_NO_CSUM)) {
+	if (csum && vdev->config->feature(vdev, VIRTIO_NET_F_CSUM)) {
 		/* This opens up the world of extra features. */
 		dev->features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST;
-		if (virtio_use_bit(vdev, token, len, VIRTIO_NET_F_TSO4))
-			dev->features |= NETIF_F_TSO;
-		if (virtio_use_bit(vdev, token, len, VIRTIO_NET_F_UFO))
-			dev->features |= NETIF_F_UFO;
-		if (virtio_use_bit(vdev, token, len, VIRTIO_NET_F_TSO4_ECN))
-			dev->features |= NETIF_F_TSO_ECN;
-		if (virtio_use_bit(vdev, token, len, VIRTIO_NET_F_TSO6))
-			dev->features |= NETIF_F_TSO6;
+		if (gso && vdev->config->feature(vdev, VIRTIO_NET_F_GSO)) {
+			dev->features |= NETIF_F_TSO | NETIF_F_UFO
+				| NETIF_F_TSO_ECN | NETIF_F_TSO6;
+		}
 	}
 
 	/* Configuration may specify what MAC to use.  Otherwise random. */
-	token = vdev->config->find(vdev, VIRTIO_CONFIG_NET_MAC_F, &len);
-	if (token) {
-		dev->addr_len = len;
-		vdev->config->get(vdev, token, dev->dev_addr, len);
+	if (vdev->config->feature(vdev, VIRTIO_NET_F_MAC)) {
+		vdev->config->get(vdev,
+				  offsetof(struct virtio_net_config, mac),
+				  dev->dev_addr, dev->addr_len);
 	} else
 		random_ether_addr(dev->dev_addr);
 
 	/* Set up our device-specific information */
 	vi = netdev_priv(dev);
-	netif_napi_add(dev, &vi->napi, virtnet_poll, 16);
+	netif_napi_add(dev, &vi->napi, virtnet_poll, napi_weight);
 	vi->dev = dev;
 	vi->vdev = vdev;
 
 	/* We expect two virtqueues, receive then send. */
-	vi->rvq = vdev->config->find_vq(vdev, skb_recv_done);
+	vi->rvq = vdev->config->find_vq(vdev, 0, skb_recv_done);
 	if (IS_ERR(vi->rvq)) {
 		err = PTR_ERR(vi->rvq);
 		goto free;
 	}
 
-	vi->svq = vdev->config->find_vq(vdev, skb_xmit_done);
+	vi->svq = vdev->config->find_vq(vdev, 1, skb_xmit_done);
 	if (IS_ERR(vi->svq)) {
 		err = PTR_ERR(vi->svq);
 		goto free_recv;
@@ -389,10 +382,22 @@ static int virtnet_probe(struct virtio_device *vdev)
 		pr_debug("virtio_net: registering device failed\n");
 		goto free_send;
 	}
+
+	/* Last of all, set up some receive buffers. */
+	try_fill_recv(vi);
+
+	/* If we didn't even get one input buffer, we're useless. */
+	if (vi->num == 0) {
+		err = -ENOMEM;
+		goto unregister;
+	}
+
 	pr_debug("virtnet: registered device %s\n", dev->name);
 	vdev->priv = vi;
 	return 0;
 
+unregister:
+	unregister_netdev(dev);
 free_send:
 	vdev->config->del_vq(vi->svq);
 free_recv:
@@ -405,6 +410,20 @@ free:
 static void virtnet_remove(struct virtio_device *vdev)
 {
 	struct virtnet_info *vi = vdev->priv;
+	struct sk_buff *skb;
+
+	/* Stop all the virtqueues. */
+	vdev->config->reset(vdev);
+
+	/* Free our skbs in send and recv queues, if any. */
+	while ((skb = __skb_dequeue(&vi->recv)) != NULL) {
+		kfree_skb(skb);
+		vi->num--;
+	}
+	while ((skb = __skb_dequeue(&vi->send)) != NULL)
+		kfree_skb(skb);
+
+	BUG_ON(vi->num != 0);
 
 	vdev->config->del_vq(vi->svq);
 	vdev->config->del_vq(vi->rvq);
diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
index 9e33fc4da87..3dd6294d10b 100644
--- a/drivers/virtio/Kconfig
+++ b/drivers/virtio/Kconfig
@@ -1,8 +1,35 @@
 # Virtio always gets selected by whoever wants it.
 config VIRTIO
-	bool
+	tristate
 
 # Similarly the virtio ring implementation.
 config VIRTIO_RING
-	bool
+	tristate
 	depends on VIRTIO
+
+config VIRTIO_PCI
+	tristate "PCI driver for virtio devices (EXPERIMENTAL)"
+	depends on PCI && EXPERIMENTAL
+	select VIRTIO
+	select VIRTIO_RING
+	---help---
+	  This drivers provides support for virtio based paravirtual device
+	  drivers over PCI.  This requires that your VMM has appropriate PCI
+	  virtio backends.  Most QEMU based VMMs should support these devices
+	  (like KVM or Xen).
+
+	  Currently, the ABI is not considered stable so there is no guarantee
+	  that this version of the driver will work with your VMM.
+
+	  If unsure, say M.
+
+config VIRTIO_BALLOON
+	tristate "Virtio balloon driver (EXPERIMENTAL)"
+	select VIRTIO
+	select VIRTIO_RING
+	---help---
+	 This driver supports increasing and decreasing the amount
+	 of memory within a KVM guest.
+
+	 If unsure, say M.
+
diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile
index f70e40971dd..6738c446c19 100644
--- a/drivers/virtio/Makefile
+++ b/drivers/virtio/Makefile
@@ -1,2 +1,4 @@
 obj-$(CONFIG_VIRTIO) += virtio.o
 obj-$(CONFIG_VIRTIO_RING) += virtio_ring.o
+obj-$(CONFIG_VIRTIO_PCI) += virtio_pci.o
+obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 69d7ea02cd4..b535483bc55 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -102,9 +102,13 @@ static int virtio_dev_remove(struct device *_d)
 	struct virtio_driver *drv = container_of(dev->dev.driver,
 						 struct virtio_driver, driver);
 
-	dev->config->set_status(dev, dev->config->get_status(dev)
-				& ~VIRTIO_CONFIG_S_DRIVER);
 	drv->remove(dev);
+
+	/* Driver should have reset device. */
+	BUG_ON(dev->config->get_status(dev));
+
+	/* Acknowledge the device's existence again. */
+	add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE);
 	return 0;
 }
 
@@ -130,6 +134,10 @@ int register_virtio_device(struct virtio_device *dev)
 	dev->dev.bus = &virtio_bus;
 	sprintf(dev->dev.bus_id, "%u", dev->index);
 
+	/* We always start by resetting the device, in case a previous
+	 * driver messed it up.  This also tests that code path a little. */
+	dev->config->reset(dev);
+
 	/* Acknowledge that we've seen the device. */
 	add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE);
 
@@ -148,55 +156,18 @@ void unregister_virtio_device(struct virtio_device *dev)
 }
 EXPORT_SYMBOL_GPL(unregister_virtio_device);
 <