Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/sparc-2.6

* 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/sparc-2.6: (26 commits)
  [SPARC64]: Fix UP build.
  [SPARC64]: dr-cpu unconfigure support.
  [SERIAL]: Fix console write locking in sparc drivers.
  [SPARC64]: Give more accurate errors in dr_cpu_configure().
  [SPARC64]: Clear cpu_{core,sibling}_map[] in smp_fill_in_sib_core_maps()
  [SPARC64]: Fix leak when DR added cpu does not bootup.
  [SPARC64]: Add ->set_affinity IRQ handlers.
  [SPARC64]: Process dr-cpu events in a kthread instead of workqueue.
  [SPARC64]: More sensible udelay implementation.
  [SPARC64]: SMP build fixes.
  [SPARC64]: mdesc.c needs linux/mm.h
  [SPARC64]: Fix build regressions added by dr-cpu changes.
  [SPARC64]: Unconditionally register vio_bus_type.
  [SPARC64]: Initial LDOM cpu hotplug support.
  [SPARC64]: Fix setting of variables in LDOM guest.
  [SPARC64]: Fix MD property lifetime bugs.
  [SPARC64]: Abstract out mdesc accesses for better MD update handling.
  [SPARC64]: Use more mearningful names for IRQ registry.
  [SPARC64]: Initial domain-services driver.
  [SPARC64]: Export powerd facilities for external entities.
  ...

11 files changed, 2289 insertions, 12 deletions

diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index fd7a53bdcb6..e49162b1557 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -423,6 +423,13 @@ config ATA_OVER_ETH
 	This driver provides Support for ATA over Ethernet block
 	devices like the Coraid EtherDrive (R) Storage Blade.
 
+config SUNVDC
+	tristate "Sun Virtual Disk Client support"
+	depends on SUN_LDOMS
+	help
+	  Support for virtual disk devices as a client under Sun
+	  Logical Domains.
+
 source "drivers/s390/block/Kconfig"
 
 endif # BLK_DEV
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index e5f98acc5d5..43371c59623 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -19,6 +19,7 @@ obj-$(CONFIG_BLK_CPQ_DA)	+= cpqarray.o
 obj-$(CONFIG_BLK_CPQ_CISS_DA)  += cciss.o
 obj-$(CONFIG_BLK_DEV_DAC960)	+= DAC960.o
 obj-$(CONFIG_CDROM_PKTCDVD)	+= pktcdvd.o
+obj-$(CONFIG_SUNVDC)		+= sunvdc.o
 
 obj-$(CONFIG_BLK_DEV_UMEM)	+= umem.o
 obj-$(CONFIG_BLK_DEV_NBD)	+= nbd.o
diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c
new file mode 100644
index 00000000000..0f5e3caf85d
--- /dev/null
+++ b/drivers/block/sunvdc.c
@@ -0,0 +1,972 @@
+/* sunvdc.c: Sun LDOM Virtual Disk Client.
+ *
+ * Copyright (C) 2007 David S. Miller <davem@davemloft.net>
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/blkdev.h>
+#include <linux/hdreg.h>
+#include <linux/genhd.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/list.h>
+
+#include <asm/vio.h>
+#include <asm/ldc.h>
+
+#define DRV_MODULE_NAME		"sunvdc"
+#define PFX DRV_MODULE_NAME	": "
+#define DRV_MODULE_VERSION	"1.0"
+#define DRV_MODULE_RELDATE	"June 25, 2007"
+
+static char version[] __devinitdata =
+	DRV_MODULE_NAME ".c:v" DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")\n";
+MODULE_AUTHOR("David S. Miller (davem@davemloft.net)");
+MODULE_DESCRIPTION("Sun LDOM virtual disk client driver");
+MODULE_LICENSE("GPL");
+MODULE_VERSION(DRV_MODULE_VERSION);
+
+#define VDC_TX_RING_SIZE	256
+
+#define WAITING_FOR_LINK_UP	0x01
+#define WAITING_FOR_TX_SPACE	0x02
+#define WAITING_FOR_GEN_CMD	0x04
+#define WAITING_FOR_ANY		-1
+
+struct vdc_req_entry {
+	struct request		*req;
+};
+
+struct vdc_port {
+	struct vio_driver_state	vio;
+
+	struct vdc		*vp;
+
+	struct gendisk		*disk;
+
+	struct vdc_completion	*cmp;
+
+	u64			req_id;
+	u64			seq;
+	struct vdc_req_entry	rq_arr[VDC_TX_RING_SIZE];
+
+	unsigned long		ring_cookies;
+
+	u64			max_xfer_size;
+	u32			vdisk_block_size;
+
+	/* The server fills these in for us in the disk attribute
+	 * ACK packet.
+	 */
+	u64			operations;
+	u32			vdisk_size;
+	u8			vdisk_type;
+	u8			dev_no;
+
+	char			disk_name[32];
+
+	struct vio_disk_geom	geom;
+	struct vio_disk_vtoc	label;
+
+	struct list_head	list;
+};
+
+static inline struct vdc_port *to_vdc_port(struct vio_driver_state *vio)
+{
+	return container_of(vio, struct vdc_port, vio);
+}
+
+struct vdc {
+	/* Protects prot_list.  */
+	spinlock_t		lock;
+
+	struct vio_dev		*dev;
+
+	struct list_head	port_list;
+};
+
+/* Ordered from largest major to lowest */
+static struct vio_version vdc_versions[] = {
+	{ .major = 1, .minor = 0 },
+};
+
+#define VDCBLK_NAME	"vdisk"
+static int vdc_major;
+#define PARTITION_SHIFT	3
+
+static inline u32 vdc_tx_dring_avail(struct vio_dring_state *dr)
+{
+	return vio_dring_avail(dr, VDC_TX_RING_SIZE);
+}
+
+static int vdc_getgeo(struct block_device *bdev, struct hd_geometry *geo)
+{
+	struct gendisk *disk = bdev->bd_disk;
+	struct vdc_port *port = disk->private_data;
+
+	geo->heads = (u8) port->geom.num_hd;
+	geo->sectors = (u8) port->geom.num_sec;
+	geo->cylinders = port->geom.num_cyl;
+
+	return 0;
+}
+
+static struct block_device_operations vdc_fops = {
+	.owner		= THIS_MODULE,
+	.getgeo		= vdc_getgeo,
+};
+
+static void vdc_finish(struct vio_driver_state *vio, int err, int waiting_for)
+{
+	if (vio->cmp &&
+	    (waiting_for == -1 ||
+	     vio->cmp->waiting_for == waiting_for)) {
+		vio->cmp->err = err;
+		complete(&vio->cmp->com);
+		vio->cmp = NULL;
+	}
+}
+
+static void vdc_handshake_complete(struct vio_driver_state *vio)
+{
+	vdc_finish(vio, 0, WAITING_FOR_LINK_UP);
+}
+
+static int vdc_handle_unknown(struct vdc_port *port, void *arg)
+{
+	struct vio_msg_tag *pkt = arg;
+
+	printk(KERN_ERR PFX "Received unknown msg [%02x:%02x:%04x:%08x]\n",
+	       pkt->type, pkt->stype, pkt->stype_env, pkt->sid);
+	printk(KERN_ERR PFX "Resetting connection.\n");
+
+	ldc_disconnect(port->vio.lp);
+
+	return -ECONNRESET;
+}
+
+static int vdc_send_attr(struct vio_driver_state *vio)
+{
+	struct vdc_port *port = to_vdc_port(vio);
+	struct vio_disk_attr_info pkt;
+
+	memset(&pkt, 0, sizeof(pkt));
+
+	pkt.tag.type = VIO_TYPE_CTRL;
+	pkt.tag.stype = VIO_SUBTYPE_INFO;
+	pkt.tag.stype_env = VIO_ATTR_INFO;
+	pkt.tag.sid = vio_send_sid(vio);
+
+	pkt.xfer_mode = VIO_DRING_MODE;
+	pkt.vdisk_block_size = port->vdisk_block_size;
+	pkt.max_xfer_size = port->max_xfer_size;
+
+	viodbg(HS, "SEND ATTR xfer_mode[0x%x] blksz[%u] max_xfer[%lu]\n",
+	       pkt.xfer_mode, pkt.vdisk_block_size, pkt.max_xfer_size);
+
+	return vio_ldc_send(&port->vio, &pkt, sizeof(pkt));
+}
+
+static int vdc_handle_attr(struct vio_driver_state *vio, void *arg)
+{
+	struct vdc_port *port = to_vdc_port(vio);
+	struct vio_disk_attr_info *pkt = arg;
+
+	viodbg(HS, "GOT ATTR stype[0x%x] ops[%lx] disk_size[%lu] disk_type[%x] "
+	       "xfer_mode[0x%x] blksz[%u] max_xfer[%lu]\n",
+	       pkt->tag.stype, pkt->operations,
+	       pkt->vdisk_size, pkt->vdisk_type,
+	       pkt->xfer_mode, pkt->vdisk_block_size,
+	       pkt->max_xfer_size);
+
+	if (pkt->tag.stype == VIO_SUBTYPE_ACK) {
+		switch (pkt->vdisk_type) {
+		case VD_DISK_TYPE_DISK:
+		case VD_DISK_TYPE_SLICE:
+			break;
+
+		default:
+			printk(KERN_ERR PFX "%s: Bogus vdisk_type 0x%x\n",
+			       vio->name, pkt->vdisk_type);
+			return -ECONNRESET;
+		}
+
+		if (pkt->vdisk_block_size > port->vdisk_block_size) {
+			printk(KERN_ERR PFX "%s: BLOCK size increased "
+			       "%u --> %u\n",
+			       vio->name,
+			       port->vdisk_block_size, pkt->vdisk_block_size);
+			return -ECONNRESET;
+		}
+
+		port->operations = pkt->operations;
+		port->vdisk_size = pkt->vdisk_size;
+		port->vdisk_type = pkt->vdisk_type;
+		if (pkt->max_xfer_size < port->max_xfer_size)
+			port->max_xfer_size = pkt->max_xfer_size;
+		port->vdisk_block_size = pkt->vdisk_block_size;
+		return 0;
+	} else {
+		printk(KERN_ERR PFX "%s: Attribute NACK\n", vio->name);
+
+		return -ECONNRESET;
+	}
+}
+
+static void vdc_end_special(struct vdc_port *port, struct vio_disk_desc *desc)
+{
+	int err = desc->status;
+
+	vdc_finish(&port->vio, -err, WAITING_FOR_GEN_CMD);
+}
+
+static void vdc_end_request(struct request *req, int uptodate, int num_sectors)
+{
+	if (end_that_request_first(req, uptodate, num_sectors))
+		return;
+	add_disk_randomness(req->rq_disk);
+	end_that_request_last(req, uptodate);
+}
+
+static void vdc_end_one(struct vdc_port *port, struct vio_dring_state *dr,
+			unsigned int index)
+{
+	struct vio_disk_desc *desc = vio_dring_entry(dr, index);
+	struct vdc_req_entry *rqe = &port->rq_arr[index];
+	struct request *req;
+
+	if (unlikely(desc->hdr.state != VIO_DESC_DONE))
+		return;
+
+	ldc_unmap(port->vio.lp, desc->cookies, desc->ncookies);
+	desc->hdr.state = VIO_DESC_FREE;
+	dr->cons = (index + 1) & (VDC_TX_RING_SIZE - 1);
+
+	req = rqe->req;
+	if (req == NULL) {
+		vdc_end_special(port, desc);
+		return;
+	}
+
+	rqe->req = NULL;
+
+	vdc_end_request(req, !desc->status, desc->size >> 9);
+
+	if (blk_queue_stopped(port->disk->queue))
+		blk_start_queue(port->disk->queue);
+}
+
+static int vdc_ack(struct vdc_port *port, void *msgbuf)
+{
+	struct vio_dring_state *dr = &port->vio.drings[VIO_DRIVER_TX_RING];
+	struct vio_dring_data *pkt = msgbuf;
+
+	if (unlikely(pkt->dring_ident != dr->ident ||
+		     pkt->start_idx != pkt->end_idx ||
+		     pkt->start_idx >= VDC_TX_RING_SIZE))
+		return 0;
+
+	vdc_end_one(port, dr, pkt->start_idx);
+
+	return 0;
+}
+
+static int vdc_nack(struct vdc_port *port, void *msgbuf)
+{
+	/* XXX Implement me XXX */
+	return 0;
+}
+
+static void vdc_event(void *arg, int event)
+{
+	struct vdc_port *port = arg;
+	struct vio_driver_state *vio = &port->vio;
+	unsigned long flags;
+	int err;
+
+	spin_lock_irqsave(&vio->lock, flags);
+
+	if (unlikely(event == LDC_EVENT_RESET ||
+		     event == LDC_EVENT_UP)) {
+		vio_link_state_change(vio, event);
+		spin_unlock_irqrestore(&vio->lock, flags);
+		return;
+	}
+
+	if (unlikely(event != LDC_EVENT_DATA_READY)) {
+		printk(KERN_WARNING PFX "Unexpected LDC event %d\n", event);
+		spin_unlock_irqrestore(&vio->lock, flags);
+		return;
+	}
+
+	err = 0;
+	while (1) {
+		union {
+			struct vio_msg_tag tag;
+			u64 raw[8];
+		} msgbuf;
+
+		err = ldc_read(vio->lp, &msgbuf, sizeof(msgbuf));
+		if (unlikely(err < 0)) {
+			if (err == -ECONNRESET)
+				vio_conn_reset(vio);
+			break;
+		}
+		if (err == 0)
+			break;
+		viodbg(DATA, "TAG [%02x:%02x:%04x:%08x]\n",
+		       msgbuf.tag.type,
+		       msgbuf.tag.stype,
+		       msgbuf.tag.stype_env,
+		       msgbuf.tag.sid);
+		err = vio_validate_sid(vio, &msgbuf.tag);
+		if (err < 0)
+			break;
+
+		if (likely(msgbuf.tag.type == VIO_TYPE_DATA)) {
+			if (msgbuf.tag.stype == VIO_SUBTYPE_ACK)
+				err = vdc_ack(port, &msgbuf);
+			else if (msgbuf.tag.stype == VIO_SUBTYPE_NACK)
+				err = vdc_nack(port, &msgbuf);
+			else
+				err = vdc_handle_unknown(port, &msgbuf);
+		} else if (msgbuf.tag.type == VIO_TYPE_CTRL) {
+			err = vio_control_pkt_engine(vio, &msgbuf);
+		} else {
+			err = vdc_handle_unknown(port, &msgbuf);
+		}
+		if (err < 0)
+			break;
+	}
+	if (err < 0)
+		vdc_finish(&port->vio, err, WAITING_FOR_ANY);
+	spin_unlock_irqrestore(&vio->lock, flags);
+}
+
+static int __vdc_tx_trigger(struct vdc_port *port)
+{
+	struct vio_dring_state *dr = &port->vio.drings[VIO_DRIVER_TX_RING];
+	struct vio_dring_data hdr = {
+		.tag = {
+			.type		= VIO_TYPE_DATA,
+			.stype		= VIO_SUBTYPE_INFO,
+			.stype_env	= VIO_DRING_DATA,
+			.sid		= vio_send_sid(&port->vio),
+		},
+		.dring_ident		= dr->ident,
+		.start_idx		= dr->prod,
+		.end_idx		= dr->prod,
+	};
+	int err, delay;
+
+	hdr.seq = dr->snd_nxt;
+	delay = 1;
+	do {
+		err = vio_ldc_send(&port->vio, &hdr, sizeof(hdr));
+		if (err > 0) {
+			dr->snd_nxt++;
+			break;
+		}
+		udelay(delay);
+		if ((delay <<= 1) > 128)
+			delay = 128;
+	} while (err == -EAGAIN);
+
+	return err;
+}
+
+static int __send_request(struct request *req)
+{
+	struct vdc_port *port = req->rq_disk->private_data;
+	struct vio_dring_state *dr = &port->vio.drings[VIO_DRIVER_TX_RING];
+	struct scatterlist sg[port->ring_cookies];
+	struct vdc_req_entry *rqe;
+	struct vio_disk_desc *desc;
+	unsigned int map_perm;
+	int nsg, err, i;
+	u64 len;
+	u8 op;
+
+	map_perm = LDC_MAP_SHADOW | LDC_MAP_DIRECT | LDC_MAP_IO;
+
+	if (rq_data_dir(req) == READ) {
+		map_perm |= LDC_MAP_W;
+		op = VD_OP_BREAD;
+	} else {
+		map_perm |= LDC_MAP_R;
+		op = VD_OP_BWRITE;
+	}
+
+	nsg = blk_rq_map_sg(req->q, req, sg);
+
+	len = 0;
+	for (i = 0; i < nsg; i++)
+		len += sg[i].length;
+
+	if (unlikely(vdc_tx_dring_avail(dr) < 1)) {
+		blk_stop_queue(port->disk->queue);
+		err = -ENOMEM;
+		goto out;
+	}
+
+	desc = vio_dring_cur(dr);
+
+	err = ldc_map_sg(port->vio.lp, sg, nsg,
+			 desc->cookies, port->ring_cookies,
+			 map_perm);
+	if (err < 0) {
+		printk(KERN_ERR PFX "ldc_map_sg() failure, err=%d.\n", err);
+		return err;
+	}
+
+	rqe = &port->rq_arr[dr->prod];
+	rqe->req = req;
+
+	desc->hdr.ack = VIO_ACK_ENABLE;
+	desc->req_id = port->req_id;
+	desc->operation = op;
+	if (port->vdisk_type == VD_DISK_TYPE_DISK) {
+		desc->slice = 2;
+	} else {
+		desc->slice = 0;
+	}
+	desc->status = ~0;
+	desc->offset = (req->sector << 9) / port->vdisk_block_size;
+	desc->size = len;
+	desc->ncookies = err;
+
+	/* This has to be a non-SMP write barrier because we are writing
+	 * to memory which is shared with the peer LDOM.
+	 */
+	wmb();
+	desc->hdr.state = VIO_DESC_READY;
+
+	err = __vdc_tx_trigger(port);
+	if (err < 0) {
+		printk(KERN_ERR PFX "vdc_tx_trigger() failure, err=%d\n", err);
+	} else {
+		port->req_id++;
+		dr->prod = (dr->prod + 1) & (VDC_TX_RING_SIZE - 1);
+	}
+out:
+
+	return err;
+}
+
+static void do_vdc_request(request_queue_t *q)
+{
+	while (1) {
+		struct request *req = elv_next_request(q);
+
+		if (!req)
+			break;
+
+		blkdev_dequeue_request(req);
+		if (__send_request(req) < 0)
+			vdc_end_request(req, 0, req->hard_nr_sectors);
+	}
+}
+
+static int generic_request(struct vdc_port *port, u8 op, void *buf, int len)
+{
+	struct vio_dring_state *dr;
+	struct vio_completion comp;
+	struct vio_disk_desc *desc;
+	unsigned int map_perm;
+	unsigned long flags;
+	int op_len, err;
+	void *req_buf;
+
+	if (!(((u64)1 << ((u64)op - 1)) & port->operations))
+		return -EOPNOTSUPP;
+
+	switch (op) {
+	case VD_OP_BREAD:
+	case VD_OP_BWRITE:
+	default:
+		return -EINVAL;
+
+	case VD_OP_FLUSH:
+		op_len = 0;
+		map_perm = 0;
+		break;
+
+	case VD_OP_GET_WCE:
+		op_len = sizeof(u32);
+		map_perm = LDC_MAP_W;
+		break;
+
+	case VD_OP_SET_WCE:
+		op_len = sizeof(u32);
+		map_perm = LDC_MAP_R;
+		break;
+
+	case VD_OP_GET_VTOC:
+		op_len = sizeof(struct vio_disk_vtoc);
+		map_perm = LDC_MAP_W;
+		break;
+
+	case VD_OP_SET_VTOC:
+		op_len = sizeof(struct vio_disk_vtoc);
+		map_perm = LDC_MAP_R;
+		break;
+
+	case VD_OP_GET_DISKGEOM:
+		op_len = sizeof(struct vio_disk_geom);
+		map_perm = LDC_MAP_W;
+		break;
+
+	case VD_OP_SET_DISKGEOM:
+		op_len = sizeof(struct vio_disk_geom);
+		map_perm = LDC_MAP_R;
+		break;
+
+	case VD_OP_SCSICMD:
+		op_len = 16;
+		map_perm = LDC_MAP_RW;
+		break;
+
+	case VD_OP_GET_DEVID:
+		op_len = sizeof(struct vio_disk_devid);
+		map_perm = LDC_MAP_W;
+		break;
+
+	case VD_OP_GET_EFI:
+	case VD_OP_SET_EFI:
+		return -EOPNOTSUPP;
+		break;
+	};
+
+	map_perm |= LDC_MAP_SHADOW | LDC_MAP_DIRECT | LDC_MAP_IO;
+
+	op_len = (op_len + 7) & ~7;
+	req_buf = kzalloc(op_len, GFP_KERNEL);
+	if (!req_buf)
+		return -ENOMEM;
+
+	if (len > op_len)
+		len = op_len;
+
+	if (map_perm & LDC_MAP_R)
+		memcpy(req_buf, buf, len);
+
+	spin_lock_irqsave(&port->vio.lock, flags);
+
+	dr = &port->vio.drings[VIO_DRIVER_TX_RING];
+
+	/* XXX If we want to use this code generically we have to
+	 * XXX handle TX ring exhaustion etc.
+	 */
+	desc = vio_dring_cur(dr);
+
+	err = ldc_map_single(port->vio.lp, req_buf, op_len,
+			     desc->cookies, port->ring_cookies,
+			     map_perm);
+	if (err < 0) {
+		spin_unlock_irqrestore(&port->vio.lock, flags);
+		kfree(req_buf);
+		return err;
+	}
+
+	init_completion(&comp.com);
+	comp.waiting_for = WAITING_FOR_GEN_CMD;
+	port->vio.cmp = &comp;
+
+	desc->hdr.ack = VIO_ACK_ENABLE;
+	desc->req_id = port->req_id;
+	desc->operation = op;
+	desc->slice = 0;
+	desc->status = ~0;
+	desc->offset = 0;
+	desc->size = op_len;
+	desc->ncookies = err;
+
+	/* This has to be a non-SMP write barrier because we are writing
+	 * to memory which is shared with the peer LDOM.
+	 */
+	wmb();
+	desc->hdr.state = VIO_DESC_READY;
+
+	err = __vdc_tx_trigger(port);
+	if (err >= 0) {
+		port->req_id++;
+		dr->prod = (dr->prod + 1) & (VDC_TX_RING_SIZE - 1);
+		spin_unlock_irqrestore(&port->vio.lock, flags);
+
+		wait_for_completion(&comp.com);
+		err = comp.err;
+	} else {
+		port->vio.cmp = NULL;
+		spin_unlock_irqrestore(&port->vio.lock, flags);
+	}
+
+	if (map_perm & LDC_MAP_W)
+		memcpy(buf, req_buf, len);
+
+	kfree(req_buf);
+
+	return err;
+}
+
+static int __devinit vdc_alloc_tx_ring(struct vdc_port *port)
+{
+	struct vio_dring_state *dr = &port->vio.drings[VIO_DRIVER_TX_RING];
+	unsigned long len, entry_size;
+	int ncookies;
+	void *dring;
+
+	entry_size = sizeof(struct vio_disk_desc) +
+		(sizeof(struct ldc_trans_cookie) * port->ring_cookies);
+	len = (VDC_TX_RING_SIZE * entry_size);
+
+	ncookies = VIO_MAX_RING_COOKIES;
+	dring = ldc_alloc_exp_dring(port->vio.lp, len,
+				    dr->cookies, &ncookies,
+				    (LDC_MAP_SHADOW |
+				     LDC_MAP_DIRECT |
+				     LDC_MAP_RW));
+	if (IS_ERR(dring))
+		return PTR_ERR(dring);
+
+	dr->base = dring;
+	dr->entry_size = entry_size;
+	dr->num_entries = VDC_TX_RING_SIZE;
+	dr->prod = dr->cons = 0;
+	dr->pending = VDC_TX_RING_SIZE;
+	dr->ncookies = ncookies;
+
+	return 0;
+}
+
+static void vdc_free_tx_ring(struct vdc_port *port)
+{
+	struct vio_dring_state *dr = &port->vio.drings[VIO_DRIVER_TX_RING];
+
+	if (dr->base) {
+		ldc_free_exp_dring(port->vio.lp, dr->base,
+				   (dr->entry_size * dr->num_entries),
+				   dr->cookies, dr->ncookies);
+		dr->base = NULL;
+		dr->entry_size = 0;
+		dr->num_entries = 0;
+		dr->pending = 0;
+		dr->ncookies = 0;
+	}
+}
+
+static int probe_disk(struct vdc_port *port)
+{
+	struct vio_completion comp;
+	struct request_queue *q;
+	struct gendisk *g;
+	int err;
+
+	init_completion(&comp.com);
+	comp.err = 0;
+	comp.waiting_for = WAITING_FOR_LINK_UP;
+	port->vio.cmp = &comp;
+
+	vio_port_up(&port->vio);
+
+	wait_for_completion(&comp.com);
+	if (comp.err)
+		return comp.err;
+
+	err = generic_request(port, VD_OP_GET_VTOC,
+			      &port->label, sizeof(port->label));
+	if (err < 0) {
+		printk(KERN_ERR PFX "VD_OP_GET_VTOC returns error %d\n", err);
+		return err;
+	}
+
+	err = generic_request(port, VD_OP_GET_DISKGEOM,
+			      &port->geom, sizeof(port->geom));
+	if (err < 0) {
+		printk(KERN_ERR PFX "VD_OP_GET_DISKGEOM returns "
+		       "error %d\n", err);
+		return err;
+	}
+
+	port->vdisk_size = ((u64)port->geom.num_cyl *
+			    (u64)port->geom.num_hd *
+			    (u64)port->geom.num_sec);
+
+	q = blk_init_queue(do_vdc_request, &port->vio.lock);
+	if (!q) {
+		printk(KERN_ERR PFX "%s: Could not allocate queue.\n",
+		       port->vio.name);
+		return -ENOMEM;
+	}
+	g = alloc_disk(1 << PARTITION_SHIFT);
+	if (!g) {
+		printk(KERN_ERR PFX "%s: Could not allocate gendisk.\n",
+		       port->vio.name);
+		blk_cleanup_queue(q);
+		return -ENOMEM;
+	}
+
+	port->disk = g;
+
+	blk_queue_max_hw_segments(q, port->ring_cookies);
+	blk_queue_max_phys_segments(q, port->ring_cookies);
+	blk_queue_max_sectors(q, port->max_xfer_size);
+	g->major = vdc_major;
+	g->first_minor = port->dev_no << PARTITION_SHIFT;
+	strcpy(g->disk_name, port->disk_name);
+
+	g->fops = &vdc_fops;
+	g->queue = q;
+	g->private_data = port;
+	g->driverfs_dev = &port->vio.vdev->dev;
+
+	set_capacity(g, port->vdisk_size);
+
+	printk(KERN_INFO PFX "%s: %u sectors (%u MB)\n",
+	       g->disk_name,
+	       port->vdisk_size, (port->vdisk_size >> (20 - 9)));
+
+	add_disk(g);
+
+	return 0;
+}
+
+static struct ldc_channel_config vdc_ldc_cfg = {
+	.event		= vdc_event,
+	.mtu		= 64,
+	.mode		= LDC_MODE_UNRELIABLE,
+};
+
+static struct vio_driver_ops vdc_vio_ops = {
+	.send_attr		= vdc_send_attr,
+	.handle_attr		= vdc_handle_attr,
+	.handshake_complete	= vdc_handshake_complete,
+};
+
+static int __devinit vdc_port_probe(struct vio_dev *vdev,
+				    const struct vio_device_id *id)
+{
+	struct mdesc_handle *hp;
+	struct vdc_port *port;
+	unsigned long flags;
+	struct vdc *vp;
+	const u64 *port_id;
+	int err;
+
+	vp = dev_get_drvdata(vdev->dev.parent);
+	if (!vp) {
+		printk(KERN_ERR PFX "Cannot find port parent vdc.\n");
+		return -ENODEV;
+	}
+
+	hp = mdesc_grab();
+
+	port_id = mdesc_get_property(hp, vdev->mp, "id", NULL);
+	err = -ENODEV;
+	if (!port_id) {
+		printk(KERN_ERR PFX "Port lacks id property.\n");
+		goto err_out_release_mdesc;
+	}
+	if ((*port_id << PARTITION_SHIFT) & ~(u64)MINORMASK) {
+		printk(KERN_ERR PFX "Port id [%lu] too large.\n", *port_id);
+		goto err_out_release_mdesc;
+	}
+
+	port = kzalloc(sizeof(*port), GFP_KERNEL);
+	err = -ENOMEM;
+	if (!port) {
+		printk(KERN_ERR PFX "Cannot allocate vdc_port.\n");
+		goto err_out_release_mdesc;
+	}
+
+	port->vp = vp;
+	port->dev_no = *port_id;
+
+	if (port->dev_no >= 26)
+		snprintf(port->disk_name, sizeof(port->disk_name),
+			 VDCBLK_NAME "%c%c",
+			 'a' + (port->dev_no / 26) - 1,
+			 'a' + (port->dev_no % 26));
+	else
+		snprintf(port->disk_name, sizeof(port->disk_name),
+			 VDCBLK_NAME "%c", 'a' + (port->dev_no % 26));
+
+	err = vio_driver_init(&port->vio, vdev, VDEV_DISK,
+			      vdc_versions, ARRAY_SIZE(vdc_versions),
+			      &vdc_vio_ops, port->disk_name);
+	if (err)
+		goto err_out_free_port;
+
+	port->vdisk_block_size = 512;
+	port->max_xfer_size = ((128 * 1024) / port->vdisk_block_size);
+	port->ring_cookies = ((port->max_xfer_size *
+			       port->vdisk_block_size) / PAGE_SIZE) + 2;
+
+	err = vio_ldc_alloc(&port->vio, &vdc_ldc_cfg, port);
+	if (err)
+		goto err_out_free_port;
+
+	err = vdc_alloc_tx_ring(port);
+	if (err)
+		goto err_out_free_ldc;
+
+	err = probe_disk(port);
+	if (err)
+		goto err_out_free_tx_ring;
+
+	INIT_LIST_HEAD(&port->list);
+
+	spin_lock_irqsave(&vp->lock, flags);
+	list_add(&port->list, &vp->port_list);
+	spin_unlock_irqrestore(&vp->lock, flags);
+
+	dev_set_drvdata(&vdev->dev, port);
+
+	mdesc_release(hp);
+
+	return 0;
+
+err_out_free_tx_ring:
+	vdc_free_tx_ring(port);
+
+err_out_free_ldc:
+	vio_ldc_free(&port->vio);
+
+err_out_free_port:
+	kfree(port);
+
+err_out_release_mdesc:
+	mdesc_release(hp);
+	return err;
+}
+
+static int vdc_port_remove(struct vio_dev *vdev)
+{
+	struct vdc_port *port = dev_get_drvdata(&vdev->dev);
+
+	if (port) {
+		del_timer_sync(&port->vio.timer);
+
+		vdc_free_tx_ring(port);
+		vio_ldc_free(&port->vio);
+
+		dev_set_drvdata(&vdev->dev, NULL);
+
+		kfree(port);
+	}
+	return 0;
+}
+
+static struct vio_device_id vdc_port_match[] = {
+	{
+		.type = "vdc-port",
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(vio, vdc_match);
+
+static struct vio_driver vdc_port_driver = {
+	.id_table	= vdc_port_match,
+	.probe		= vdc_port_probe,
+	.remove		= vdc_port_remove,
+	.driver		= {
+		.name	= "vdc_port",
+		.owner	= THIS_MODULE,
+	}
+};
+
+static int __devinit vdc_probe(struct vio_dev *vdev,
+			       const struct vio_device_id *id)
+{
+	static int vdc_version_printed;
+	struct vdc *vp;
+
+	if (vdc_version_printed++ == 0)
+		printk(KERN_INFO "%s", version);
+
+	vp = kzalloc(sizeof(struct vdc), GFP_KERNEL);
+	if (!vp)
+		return -ENOMEM;
+
+	spin_lock_init(&vp->lock);
+	vp->dev = vdev;
+	INIT_LIST_HEAD(&vp->port_list);
+
+	dev_set_drvdata(&vdev->dev, vp);
+
+	return 0;
+}
+
+static int vdc_remove(struct vio_dev *vdev)
+{
+
+	struct vdc *vp = dev_get_drvdata(&vdev->dev);
+
+	if (vp) {
+		kfree(vp);
+		dev_set_drvdata(&vdev->dev, NULL);
+	}
+	return 0;
+}
+
+static struct vio_device_id vdc_match[] = {
+	{
+		.type = "block",
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(vio, vdc_match);
+
+static struct vio_driver vdc_driver = {
+	.id_table	= vdc_match,
+	.probe		= vdc_probe,
+	.remove		= vdc_remove,
+	.driver		= {
+		.name	= "vdc",
+		.owner	= THIS_MODULE,
+	}
+};
+
+static int __init vdc_init(void)
+{
+	int err;
+
+	err = register_blkdev(0, VDCBLK_NAME);
+	if (err < 0)
+		goto out_err;
+
+	vdc_major = err;
+	err = vio_register_driver(&vdc_driver);
+	if (err)
+		goto out_unregister_blkdev;
+
+	err = vio_register_driver(&vdc_port_driver);
+	if (err)
+		goto out_unregister_vdc;
+
+	return 0;
+
+out_unregister_vdc:
+	vio_unregister_driver(&vdc_driver);
+
+out_unregister_blkdev:
+	unregister_blkdev(vdc_major, VDCBLK_NAME);
+	vdc_major = 0;
+
+out_err:
+	return err;
+}
+
+static void __exit vdc_exit(void)
+{
+	vio_unregister_driver(&vdc_port_driver);
+	vio_unregister_driver(&vdc_driver);
+	unregister_blkdev(vdc_major, VDCBLK_NAME);
+}
+
+module_init(vdc_init);
+module_exit(vdc_exit);
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index d17d64eb706..7903f9c7839 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -604,6 +604,12 @@ config CASSINI
 	  Support for the Sun Cassini chip, aka Sun GigaSwift Ethernet. See also
 	  <http://www.sun.com/products-n-solutions/hardware/docs/pdf/817-4341-10.pdf>
 
+config SUNVNET
+	tristate "Sun Virtual Network support"
+	depends on SUN_LDOMS
+	help
+	  Support for virtual network devices under Sun Logical Domains.
+
 config NET_VENDOR_3COM
 	bool "3COM cards"
 	depends on ISA || EISA || MCA || PCI
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index c26b8674213..b95b1b237a2 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -34,6 +34,7 @@ obj-$(CONFIG_SUNBMAC) += sunbmac.o
 obj-$(CONFIG_MYRI_SBUS) += myri_sbus.o
 obj-$(CONFIG_SUNGEM) += sungem.o sungem_phy.o
 obj-$(CONFIG_CASSINI) += cassini.o
+obj-$(CONFIG_SUNVNET) += sunvnet.o
 
 obj-$(CONFIG_MACE) += mace.o
 obj-$(CONFIG_BMAC) += bmac.o
diff --git a/drivers/net/sunvnet.c b/drivers/net/sunvnet.c
new file mode 100644
index 00000000000..8a667c13fae
--- /dev/null
+++ b/drivers/net/sunvnet.c
@@ -0,0 +1,1164 @@
+/* sunvnet.c: Sun LDOM Virtual Network Driver.
+ *
+ * Copyright (C) 2007 David S. Miller <davem@davemloft.net>
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/netdevice.h>
+#include <linux/ethtool.h>
+#include <linux/etherdevice.h>
+
+#include <asm/vio.h>
+#include <asm/ldc.h>
+
+#include "sunvnet.h"
+
+#define DRV_MODULE_NAME		"sunvnet"
+#define PFX DRV_MODULE_NAME	": "
+#define DRV_MODULE_VERSION	"1.0"
+#define DRV_MODULE_RELDATE	"June 25, 2007"
+
+static char version[] __devinitdata =
+	DRV_MODULE_NAME ".c:v" DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")\n";
+MODULE_AUTHOR("David S. Miller (davem@davemloft.net)");
+MODULE_DESCRIPTION("Sun LDOM virtual network driver");
+MODULE_LICENSE("GPL");
+MODULE_VERSION(DRV_MODULE_VERSION);
+
+/* Ordered from largest major to lowest */
+static struct vio_version vnet_versions[] = {
+	{ .major = 1, .minor = 0 },
+};
+
+static inline u32 vnet_tx_dring_avail(struct vio_dring_state *dr)
+{
+	return vio_dring_avail(dr, VNET_TX_RING_SIZE);
+}
+
+static int vnet_handle_unknown(struct vnet_port *port, void *arg)
+{
+	struct vio_msg_tag *pkt = arg;
+
+	printk(KERN_ERR PFX "Received unknown msg [%02x:%02x:%04x:%08x]\n",
+	       pkt->type, pkt->stype, pkt->stype_env, pkt->sid);
+	printk(KERN_ERR PFX "Resetting connection.\n");
+
+	ldc_disconnect(port->vio.lp);
+
+	return -ECONNRESET;
+}
+
+static int vnet_send_attr(struct vio_driver_state *vio)
+{
+	struct vnet_port *port = to_vnet_port(vio);
+	struct net_device *dev = port->vp->dev;
+	struct vio_net_attr_info pkt;
+	int i;
+
+	memset(&pkt, 0, sizeof(pkt));
+	pkt.tag.type = VIO_TYPE_CTRL;
+	pkt.tag.stype = VIO_SUBTYPE_INFO;
+	pkt.tag.stype_env = VIO_ATTR_INFO;
+	pkt.tag.sid = vio_send_sid(vio);
+	pkt.xfer_mode = VIO_DRING_MODE;
+	pkt.addr_type = VNET_ADDR_ETHERMAC;
+	pkt.ack_freq = 0;
+	for (i = 0; i < 6; i++)
+		pkt.addr |= (u64)dev->dev_addr[i] << ((5 - i) * 8);
+	pkt.mtu = ETH_FRAME_LEN;
+
+	viodbg(HS, "SEND NET ATTR xmode[0x%x] atype[0x%x] addr[%llx] "
+	       "ackfreq[%u] mtu[%llu]\n",
+	       pkt.xfer_mode, pkt.addr_type,
+	       (unsigned long long) pkt.addr,
+	       pkt.ack_freq,
+	       (unsigned long long) pkt.mtu);
+
+	return vio_ldc_send(vio, &pkt, sizeof(pkt));
+}
+
+static int handle_attr_info(struct vio_driver_state *vio,
+			    struct vio_net_attr_info *pkt)
+{
+	viodbg(HS, "GOT NET ATTR INFO xmode[0x%x] atype[0x%x] addr[%llx] "
+	       "ackfreq[%u] mtu[%llu]\n",
+	       pkt->xfer_mode, pkt->addr_type,
+	       (unsigned long long) pkt->addr,
+	       pkt->ack_freq,
+	       (unsigned long long) pkt->mtu);
+
+	pkt->tag.sid = vio_send_sid(vio);
+
+	if (pkt->xfer_mode != VIO_DRING_MODE ||
+	    pkt->addr_type != VNET_ADDR_ETHERMAC ||
+	    pkt->mtu != ETH_FRAME_LEN) {
+		viodbg(HS, "SEND NET ATTR NACK\n");
+
+		pkt->tag.stype = VIO_SUBTYPE_NACK;
+
+		(void) vio_ldc_send(vio, pkt, sizeof(*pkt));
+
+		return -ECONNRESET;
+	} else {
+		viodbg(HS, "SEND NET ATTR ACK\n");
+
+		pkt->tag.stype = VIO_SUBTYPE_ACK;
+
+		return vio_ldc_send(vio, pkt, sizeof(*pkt));
+	}
+
+}
+
+static int handle_attr_ack(struct vio_driver_state *vio,
+			   struct vio_net_attr_info *pkt)
+{
+	viodbg(HS, "GOT NET ATTR ACK\n");
+
+	return 0;
+}
+
+static int handle_attr_nack(struct vio_driver_state *vio,
+			    struct vio_net_attr_info *pkt)
+{
+	viodbg(HS, "GOT NET ATTR NACK\n");
+
+	return -ECONNRESET;
+}
+
+static int vnet_handle_attr(struct vio_driver_state *vio, void *arg)
+{
+	struct vio_net_attr_info *pkt = arg;
+
+	switch (pkt->tag.stype) {
+	case VIO_SUBTYPE_INFO:
+		return handle_attr_info(vio, pkt);
+
+	case VIO_SUBTYPE_ACK:
+		return handle_attr_ack(vio, pkt);
+
+	case VIO_SUBTYPE_NACK:
+		return handle_attr_nack(vio, pkt);
+
+	default:
+		return -ECONNRESET;
+	}
+}
+
+static void vnet_handshake_complete(struct vio_driver_state *vio)
+{
+	struct vio_dring_state *dr;
+
+	dr = &vio->drings[VIO_DRIVER_RX_RING];
+	dr->snd_nxt = dr->rcv_nxt = 1;
+
+	dr = &vio->drings[VIO_DRIVER_TX_RING];
+	dr->snd_nxt = dr->rcv_nxt = 1;
+}
+
+/* The hypervisor interface that implements copying to/from imported
+ * memory from another domain requires that copies are done to 8-byte
+ * aligned buffers, and that the lengths of such copies are also 8-byte
+ * multiples.
+ *
+ * So we align skb->data to an 8-byte multiple and pad-out the data
+ * area so we can round the copy length up to the next multiple of
+ * 8 for the copy.
+ *
+ * The transmitter puts the actual start of the packet 6 bytes into
+ * the buffer it sends over, so that the IP headers after the ethernet
+ * header are aligned properly.  These 6 bytes are not in the descriptor
+ * length, they are simply implied.  This offset is represented using
+ * the VNET_PACKET_SKIP macro.
+ */
+static struct sk_buff *alloc_and_align_skb(struct net_device *dev,
+					   unsigned int len)
+{
+	struct sk_buff *skb = netdev_alloc_skb(dev, len+VNET_PACKET_SKIP+8+8);
+	unsigned long addr, off;
+
+	if (unlikely(!skb))
+		return NULL;
+
+	addr = (unsigned long) skb->data;
+	off = ((addr + 7UL) & ~7UL) - addr;
+	if (off)
+		skb_reserve(skb, off);
+
+	return skb;
+}
+
+static int vnet_rx_one(struct vnet_port *port, unsigned int len,
+		       struct ldc_trans_cookie *cookies, int ncookies)
+{
+	struct net_device *dev = port->vp->dev;
+	unsigned int copy_len;
+	struct sk_buff *skb;
+	int err;
+
+	err = -EMSGSIZE;
+	if (unlikely(len < ETH_ZLEN || len > ETH_FRAME_LEN)) {
+		dev->stats.rx_length_errors++;
+		goto out_dropped;
+	}
+
+	skb = alloc_and_align_skb(dev, len);
+	err = -ENOMEM;
+	if (unlikely(!skb)) {
+		dev->stats.rx_missed_errors++;
+		goto out_dropped;
+	}
+
+	copy_len = (len + VNET_PACKET_SKIP + 7U) & ~7U;
+	skb_put(skb, copy_len);
+	err = ldc_copy(port->vio.lp, LDC_COPY_IN,
+		       skb->data, copy_len, 0,
+		       cookies, ncookies);
+	if (unlikely(err < 0)) {
+		dev->stats.rx_frame_errors++;
+		goto out_free_skb;
+	}
+
+	skb_pull(skb, VNET_PACKET_SKIP);
+	skb_trim(skb, len);
+	skb->protocol = eth_type_trans(skb, dev);
+
+	dev->stats.rx_packets++;
+	dev->stats.rx_bytes += len;
+
+	netif_rx(skb);
+
+	return 0;
+
+out_free_skb:
+	kfree_skb(skb);
+
+out_dropped:
+	dev->stats.rx_dropped++;
+	return err;
+}
+
+static int vnet_send_ack(struct vnet_port *port, struct vio_dring_state *dr,
+			 u32 start, u32 end, u8 vio_dring_state)
+{
+	struct vio_dring_data hdr = {
+		.tag = {
+			.type		= VIO_TYPE_DATA,
+			.stype		= VIO_SUBTYPE_ACK,
+			.stype_env	= VIO_DRING_DATA,
+			.sid		= vio_send_sid(&port->vio),
+		},
+		.dring_ident		= dr->ident,
+		.start_idx		= start,
+		.end_idx		= end,
+		.state			= vio_dring_state,
+	};
+	int err, delay;
+
+	hdr.seq = dr->snd_nxt;
+	delay = 1;
+	do {
+		err = vio_ldc_send(&port->vio, &hdr, sizeof(hdr));
+		if (err > 0) {
+			dr->snd_nxt++;
+			break;
+		}
+		udelay(delay);
+		if ((delay <<= 1) > 128)
+			delay = 128;
+	} while (err == -EAGAIN);
+
+	return err;
+}
+
+static u32 next_idx(u32 idx, struct vio_dring_state *dr)
+{
+	if (++idx == dr->num_entries)
+		idx = 0;
+	return idx;
+}
+
+static u32 prev_idx(u32 idx, struct vio_dring_state *dr)
+{
+	if (idx == 0)
+		idx = dr->num_entries - 1;
+	else
+		idx--;
+
+	return idx;
+}
+
+static struct vio_net_desc *get_rx_desc(struct vnet_port *port,
+					struct vio_dring_state *dr,
+					u32 index)
+{
+	struct vio_net_desc *desc = port->vio.desc_buf;
+	int err;
+
+	err = ldc_get_dring_entry(port->vio.lp, desc, dr->entry_size,
+				  (index * dr->entry_size),
+				  dr->cookies, dr->ncookies);
+	if (err < 0)
+		return ERR_PTR(err);
+
+	return desc;
+}
+
+static int put_rx_desc(struct vnet_port *port,
+		       struct vio_dring_state *dr,
+		       struct vio_net_desc *desc,
+		       u32 index)
+{
+	int err;
+
+	err = ldc_put_dring_entry(port->vio.lp, desc, dr->entry_size,
+				  (index * dr->entry_size),
+				  dr->cookies, dr->ncookies);
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+static int vnet_walk_rx_one(struct vnet_port *port,
+			    struct vio_dring_state *dr,
+			    u32 index, int *needs_ack)
+{
+	struct vio_net_desc *desc = get_rx_desc(port, dr, index);
+	struct vio_driver_state *vio = &port->vio;
+	int err;
+
+	if (IS_ERR(desc))
+		return PTR_ERR(desc);
+
+	viodbg(DATA, "vio_walk_rx_one desc[%02x:%02x:%08x:%08x:%lx:%lx]\n",
+	       desc->hdr.state, desc->hdr.ack,
+	       desc->size, desc->ncookies,
+	       desc->cookies[0].cookie_addr,
+	       desc->cookies[0].cookie_size);
+
+	if (desc->hdr.state != VIO_DESC_READY)
+		return 1;
+	err = vnet_rx_one(port, desc->size, desc->cookies, desc->ncookies);
+	if (err == -ECONNRESET)
+		return err;
+	desc->hdr.state = VIO_DESC_DONE;
+	err = put_rx_desc(port, dr, desc, index);
+	if (err < 0)
+		return err;
+	*needs_ack = desc->hdr.ack;
+	return 0;
+}
+
+static int vnet_walk_rx(struct vnet_port *port, struct vio_dring_state *dr,
+			u32 start, u32 end)
+{
+	struct vio_driver_state *vio = &port->vio;
+	int ack_start = -1, ack_end = -1;
+
+	end = (end == (u32) -1) ? prev_idx(start, dr) : next_idx(end, dr);
+
+	viodbg(DATA, "vnet_walk_rx start[%08x] end[%08x]\n", start, end);
+
+	while (start != end) {
+		int ack = 0, err = vnet_walk_rx_one(port, dr, start, &ack);
+		if (err == -ECONNRESET)
+			return err;
+		if (err != 0)
+			break;
+		if (ack_start == -1)
+			ack_start = start;
+		ack_end = start;
+		start = next_idx(start, dr);
+		if (ack && start != end) {
+			err = vnet_send_ack(port, dr, ack_start, ack_end,
+					    VIO_DRING_ACTIVE);
+			if (err == -ECONNRESET)
+				return err;
+			ack_start = -1;
+		}
+	}
+	if (unlikely(ack_start == -1))
+		ack_start = ack_end = prev_idx(start, dr);
+	return vnet_send_ack(port, dr, ack_start, ack_end, VIO_DRING_STOPPED);
+}
+
+static int vnet_rx(struct vnet_port *port, void *msgbuf)
+{
+	struct vio_dring_data *pkt = msgbuf;
+	struct vio_dring_state *dr = &port->vio.drings[VIO_DRIVER_RX_RING];
+	struct vio_driver_state *vio = &port->vio;
+
+	viodbg(DATA, "vnet_rx stype_env[%04x] seq[%016lx] rcv_nxt[%016lx]\n",
+	       pkt->tag.stype_env, pkt->seq, dr->rcv_nxt);
+
+	if (unlikely(pkt->tag.stype_env != VIO_DRING_DATA))
+		return 0;
+	if (unlikely(pkt->seq != dr->rcv_nxt)) {
+		printk(KERN_ERR PFX "RX out of sequence seq[0x%lx] "
+		       "rcv_nxt[0x%lx]\n", pkt->seq, dr->rcv_nxt);
+		return 0;
+	}
+
+	dr->rcv_nxt++;
+
+	/* XXX Validate pkt->start_idx and pkt->end_idx XXX */
+
+	return vnet_walk_rx(port, dr, pkt->start_idx, pkt->end_idx);
+}
+
+static int idx_is_pending(struct vio_dring_state *dr, u32 end)
+{
+	u32 idx = dr->cons;
+	int found = 0;
+
+	while (idx != dr->prod) {
+		if (idx == end) {
+			found = 1;
+			break;
+		}
+		idx = next_idx(idx, dr);
+	}
+	return found;
+}
+
+static int vnet_ack(struct vnet_port *port, void *msgbuf)
+{
+	struct vio_dring_state *dr = &port->vio.drings[VIO_DRIVER_TX_RING];
+	struct vio_dring_data *pkt = msgbuf;
+	struct net_device *dev;
+	struct vnet *vp;
+	u32 end;
+
+	if (unlikely(pkt->tag.stype_env != VIO_DRING_DATA))
+		return 0;
+
+	end = pkt->end_idx;
+	if (unlikely(!idx_is_pending(dr, end)))
+		return 0;
+
+	dr->cons = next_idx(end, dr);
+
+	vp = port->vp;
+	dev = vp->dev;
+	if (unlikely(netif_queue_stopped(dev) &&
+		     vnet_tx_dring_avail(dr) >= VNET_TX_WAKEUP_THRESH(dr)))
+		return 1;
+
+	return 0;
+}
+
+static int vnet_nack(struct vnet_port *port, void *msgbuf)
+{
+	/* XXX just reset or similar XXX */
+	return 0;
+}
+
+static void maybe_tx_wakeup(struct vnet *vp)
+{
+	struct net_device *dev = vp->dev;
+
+	netif_tx_lock(dev);
+	if (likely(netif_queue_stopped(dev))) {
+		struct vnet_port *port;
+		int wake = 1;
+
+		list_for_each_entry(port, &vp->port_list, list) {
+			struct vio_dring_state *dr;
+
+			dr = &port->vio.drings[VIO_DRIVER_TX_RING];
+			if (vnet_tx_dring_avail(dr) <
+			    VNET_TX_WAKEUP_THRESH(dr)) {
+				wake = 0;
+				break;
+			}
+		}
+		if (wake)
+			netif_wake_queue(dev);
+	}
+	netif_tx_unlock(dev);
+}
+
+static void vnet_event(void *arg, int event)
+{
+	struct vnet_port *port = arg;
+	struct vio_driver_state *vio = &port->vio;
+	unsigned long flags;
+	int tx_wakeup, err;
+
+	spin_lock_irqsave(&vio->lock, flags);
+
+	if (unlikely(event == LDC_EVENT_RESET ||
+		     event == LDC_EVENT_UP)) {
+		vio_link_state_change(vio, event);
+		spin_unlock_irqrestore(&vio->lock, flags);
+
+		return;
+	}
+
+	if (unlikely(event != LDC_EVENT_DATA_READY)) {
+		printk(KERN_WARNING PFX "Unexpected LDC event %d\n", event);
+		spin_unlock_irqrestore(&vio->lock, flags);
+		return;
+	}
+
+	tx_wakeup = err = 0;
+	while (1) {
+		union {
+			struct vio_msg_tag tag;
+			u64 raw[8];
+		} msgbuf;
+
+		err = ldc_read(vio->lp, &msgbuf, sizeof(msgbuf));
+		if (unlikely(err < 0)) {
+			if (err == -ECONNRESET)
+				vio_conn_reset(vio);
+			break;
+		}
+		if (err == 0)
+			break;
+		viodbg(DATA, "TAG [%02x:%02x:%04x:%08x]\n",
+		       msgbuf.tag.type,
+		       msgbuf.tag.stype,
+		       msgbuf.tag.stype_env,
+		       msgbuf.tag.sid);
+		err = vio_validate_sid(vio, &msgbuf.tag);
+		if (err < 0)
+			break;
+
+		if (likely(msgbuf.tag.type == VIO_TYPE_DATA)) {
+			if (msgbuf.tag.stype == VIO_SUBTYPE_INFO) {
+				err = vnet_rx(port, &msgbuf);
+			} else if (msgbuf.tag.stype == VIO_SUBTYPE_ACK) {
+				err = vnet_ack(port, &msgbuf);
+				if (err > 0)
+					tx_wakeup |= err;
+			} else if (msgbuf.tag.stype == VIO_SUBTYPE_NACK) {
+				err = vnet_nack(port, &msgbuf);
+			}
+		} else if (msgbuf.tag.type == VIO_TYPE_CTRL) {
+			err = vio_control_pkt_engine(vio, &msgbuf);
+			if (err)
+				break;
+		} else {
+			err = vnet_handle_unknown(port, &msgbuf);
+		}
+		if (err == -ECONNRESET)
+			break;
+	}
+	spin_unlock(&vio->lock);
+	if (unlikely(tx_wakeup && err != -ECONNRESET))
+		maybe_tx_wakeup(port->vp);
+	local_irq_restore(flags);
+}
+
+static int __vnet_tx_trigger(struct vnet_port *port)
+{
+	struct vio_dring_state *dr = &port->vio.drings[VIO_DRIVER_TX_RING];
+	struct vio_dring_data hdr = {
+		.tag = {
+			.type		= VIO_TYPE_DATA,
+			.stype		= VIO_SUBTYPE_INFO,
+			.stype_env	= VIO_DRING_DATA,
+			.sid		= vio_send_sid(&port->vio),
+		},
+		.dring_ident		= dr->ident,
+		.start_idx		= dr->prod,
+		.end_idx		= (u32) -1,
+	};
+	int err, delay;
+
+	hdr.seq = dr->snd_nxt;
+	delay = 1;
+	do {
+		err = vio_ldc_send(&port->vio, &hdr, sizeof(hdr));
+		if (err > 0) {
+			dr->snd_nxt++;
+			break;
+		}
+		udelay(delay);
+		if ((delay <<= 1) > 128)
+			delay = 128;
+	} while (err == -EAGAIN);
+
+	return err;
+}
+
+struct vnet_port *__tx_port_find(struct vnet *vp, struct sk_buff *skb)
+{
+	unsigned int hash = vnet_hashfn(skb->data);
+	struct hlist_head *hp = &vp->port_hash[hash];
+	struct hlist_node *n;
+	struct vnet_port *port;
+
+	hlist_for_each_entry(port, n, hp, hash) {
+		if (!compare_ether_addr(port->raddr, skb->data))
+			return port;
+	}
+	port = NULL;
+	if (!list_empty(&vp->port_list))
+		port = list_entry(vp->port_list.next, struct vnet_port, list);
+
+	return port;
+}
+
+struct vnet_port *tx_port_find(struct vnet *vp, struct sk_buff *skb)
+{
+	struct vnet_port *ret;
+	unsigned long flags;
+
+	spin_lock_irqsave(&vp->lock, flags);
+	ret = __tx_port_find(vp, skb);
+	spin_unlock_irqrestore(&vp->lock, flags);
+
+	return ret;
+}
+
+static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct vnet *vp = netdev_priv(dev);
+	struct vnet_port *port = tx_port_find(vp, skb);
+	struct vio_dring_state *dr;
+	struct vio_net_desc *d;
+	unsigned long flags;
+	unsigned int len;
+	void *tx_buf;
+	int i, err;
+
+	if (unlikely(!port))
+		goto out_dropped;
+
+	spin_lock_irqsave(&port->vio.lock, flags);
+
+	dr = &port->vio.drings[VIO_DRIVER_TX_RING];
+	if (unlikely(vnet_tx_dring_avail(dr) < 2)) {
+		if (!netif_queue_stopped(dev)) {
+			netif_stop_queue(dev);
+
+			/* This is a hard error, log it. */
+			printk(KERN_ERR PFX "%s: BUG! Tx Ring full when "
+			       "queue awake!\n", dev->name);
+			dev->stats.tx_errors++;
+		}
+		spin_unlock_irqrestore(&port->vio.lock, flags);
+		return NETDEV_TX_BUSY;
+	}
+
+	d = vio_dring_cur(dr);
+
+	tx_buf = port->tx_bufs[dr->prod].buf;
+	skb_copy_from_linear_data(skb, tx_buf + VNET_PACKET_SKIP, skb->len);
+
+	len = skb->len;
+	if (len < ETH_ZLEN) {
+		len = ETH_ZLEN;
+		memset(tx_buf+VNET_PACKET_SKIP+skb->len, 0, len - skb->len);
+	}
+
+	d->hdr.ack = VIO_ACK_ENABLE;
+	d->size = len;
+	d->ncookies = port->tx_bufs[dr->prod].ncookies;
+	for (i = 0; i < d->ncookies; i++)
+		d->cookies[i] = port->tx_bufs[dr->prod].cookies[i];
+
+	/* This has to be a non-SMP write barrier because we are writing
+	 * to memory which is shared with the peer LDOM.
+	 */
+	wmb();
+
+	d->hdr.state = VIO_DESC_READY;
+
+	err = __vnet_tx_trigger(port);
+	if (unlikely(err < 0)) {
+		printk(KERN_INFO PFX "%s: TX trigger error %d\n",
+		       dev->name, err);
+		d->hdr.state = VIO_DESC_FREE;
+		dev->stats.tx_carrier_errors++;
+		goto out_dropped_unlock;
+	}
+
+	dev->stats.tx_packets++;
+	dev->stats.tx_bytes += skb->len;
+
+	dr->prod = (dr->prod + 1) & (VNET_TX_RING_SIZE - 1);
+	if (unlikely(vnet_tx_dring_avail(dr) < 2)) {
+		netif_stop_queue(dev);
+		if (vnet_tx_dring_avail(dr) > VNET_TX_WAKEUP_THRESH(dr))
+			netif_wake_queue(dev);
+	}
+
+	spin_unlock_irqrestore(&port->vio.lock, flags);
+
+	dev_kfree_skb(skb);
+
+	dev->trans_start = jiffies;
+	return NETDEV_TX_OK;
+
+out_dropped_unlock:
+	spin_unlock_irqrestore(&port->vio.lock, flags);
+
+out_dropped:
+	dev_kfree_skb(skb);
+	dev->stats.tx_dropped++;
+	return NETDEV_TX_OK;
+}
+
+static void vnet_tx_timeout(struct net_device *dev)
+{
+	/* XXX Implement me XXX */
+}
+
+static int vnet_open(struct net_device *dev)
+{
+	netif_carrier_on(dev);
+	netif_start_queue(dev);
+
+	return 0;
+}
+
+static int vnet_close(struct net_device *dev)
+{
+	netif_stop_queue(dev);
+	netif_carrier_off(dev);
+
+	return 0;
+}
+
+static void vnet_set_rx_mode(struct net_device *dev)
+{
+	/* XXX Implement multicast support XXX */
+}
+
+static int vnet_change_mtu(struct net_device *dev, int new_mtu)
+{
+	if (new_mtu != ETH_DATA_LEN)
+		return -EINVAL;
+
+	dev->mtu = new_mtu;
+	return 0;
+}
+
+static int vnet_set_mac_addr(struct net_device *dev, void *p)
+{
+	return -EINVAL;
+}
+
+static void vnet_get_drvinfo(struct net_device *dev,
+			     struct ethtool_drvinfo *info)
+{
+	strcpy(info->driver, DRV_MODULE_NAME);
+	strcpy(info->version, DRV_MODULE_VERSION);
+}
+
+static u32 vnet_get_msglevel(struct net_device *dev)
+{
+	struct vnet *vp = netdev_priv(dev);
+	return vp->msg_enable;
+}
+
+static void vnet_set_msglevel(struct net_device *dev, u32 value)
+{
+	struct vnet *vp = netdev_priv(dev);
+	vp->msg_enable = value;
+}
+
+static const struct ethtool_ops vnet_ethtool_ops = {
+	.get_drvinfo		= vnet_get_drvinfo,
+	.get_msglevel		= vnet_get_msglevel,
+	.set_msglevel		= vnet_set_msglevel,
+	.get_link		= ethtool_op_get_link,
+	.get_perm_addr		= ethtool_op_get_perm_addr,
+};
+
+static void vnet_port_free_tx_bufs(struct vnet_port *port)
+{
+	struct vio_dring_state *dr;
+	int i;
+
+	dr = &port->vio.drings[VIO_DRIVER_TX_RING];
+	if (dr->base) {
+		ldc_free_exp_dring(port->vio.lp, dr->base,
+				   (dr->entry_size * dr->num_entries),
+				   dr->cookies, dr->ncookies);
+		dr->base = NULL;
+		dr->entry_size = 0;
+		dr->num_entries = 0;
+		dr->pending = 0;
+		dr->ncookies = 0;
+	}
+
+	for (i = 0; i < VNET_TX_RING_SIZE; i++) {
+		void *buf = port->tx_bufs[i].buf;
+
+		if (!buf)
+			continue;
+
+		ldc_unmap(port->vio.lp,
+			  port->tx_bufs[i].cookies,
+			  port->tx_bufs[i].ncookies);
+
+		kfree(buf);
+		port->tx_bufs[i].buf = NULL;
+	}
+}
+
+static int __devinit vnet_port_alloc_tx_bufs(struct vnet_port *port)
+{
+	struct vio_dring_state *dr;
+	unsigned long len;
+	int i, err, ncookies;
+	void *dring;
+
+	for (i = 0; i < VNET_TX_RING_SIZE; i++) {
+		void *buf = kzalloc(ETH_FRAME_LEN + 8, GFP_KERNEL);
+		int map_len = (ETH_FRAME_LEN + 7) & ~7;
+
+		err = -ENOMEM;
+		if (!buf) {
+			printk(KERN_ERR "TX buffer allocation failure\n");
+			goto err_out;
+		}
+		err = -EFAULT;
+		if ((unsigned long)buf & (8UL - 1)) {
+			printk(KERN_ERR "TX buffer misaligned\n");
+			kfree(buf);
+			goto err_out;
+		}
+
+		err = ldc_map_single(port->vio.lp, buf, map_len,
+				     port->tx_bufs[i].cookies, 2,
+				     (LDC_MAP_SHADOW |
+				      LDC_MAP_DIRECT |
+				      LDC_MAP_RW));
+		if (err < 0) {
+			kfree(buf);
+			goto err_out;
+		}
+		port->tx_bufs[i].buf = buf;
+		port->tx_bufs[i].ncookies = err;
+	}
+
+	dr = &port->vio.drings[VIO_DRIVER_TX_RING];
+
+	len = (VNET_TX_RING_SIZE *
+	       (sizeof(struct vio_net_desc) +
+		(sizeof(struct ldc_trans_cookie) * 2)));
+
+	ncookies = VIO_MAX_RING_COOKIES;
+	dring = ldc_alloc_exp_dring(port->vio.lp, len,
+				    dr->cookies, &ncookies,
+				    (LDC_MAP_SHADOW |
+				     LDC_MAP_DIRECT |
+				     LDC_MAP_RW));
+	if (IS_ERR(dring)) {
+		err = PTR_ERR(dring);
+		goto err_out;
+	}
+
+	dr->base = dring;
+	dr->entry_size = (sizeof(struct vio_net_desc) +
+			  (sizeof(struct ldc_trans_cookie) * 2));
+	dr->num_entries = VNET_TX_RING_SIZE;
+	dr->prod = dr->cons = 0;
+	dr->pending = VNET_TX_RING_SIZE;
+	dr->ncookies = ncookies;
+
+	return 0;
+
+err_out:
+	vnet_port_free_tx_bufs(port);
+
+	return err;
+}
+
+static struct ldc_channel_config vnet_ldc_cfg = {
+	.event		= vnet_event,
+	.mtu		= 64,
+	.mode		= LDC_MODE_UNRELIABLE,
+};
+
+static struct vio_driver_ops vnet_vio_ops = {
+	.send_attr		= vnet_send_attr,
+	.handle_attr		= vnet_handle_attr,
+	.handshake_complete	= vnet_handshake_complete,
+};
+
+const char *remote_macaddr_prop = "remote-mac-address";
+
+static int __devinit vnet_port_probe(struct vio_dev *vdev,
+				     const struct vio_device_id *id)
+{
+	struct mdesc_handle *hp;
+	struct vnet_port *port;
+	unsigned long flags;
+	struct vnet *vp;
+	const u64 *rmac;
+	int len, i, err, switch_port;
+
+	vp = dev_get_drvdata(vdev->dev.parent);
+	if (!vp) {
+		printk(KERN_ERR PFX "Cannot find port parent vnet.\n");
+		return -ENODEV;
+	}
+
+	hp = mdesc_grab();
+
+	rmac = mdesc_get_property(hp, vdev->mp, remote_macaddr_prop, &len);
+	err = -ENODEV;
+	if (!rmac) {
+		printk(KERN_ERR PFX "Port lacks %s property.\n",
+		       remote_macaddr_prop);
+		goto err_out_put_mdesc;
+	}
+
+	port = kzalloc(sizeof(*port), GFP_KERNEL);
+	err = -ENOMEM;
+	if (!port) {
+		printk(KERN_ERR PFX "Cannot allocate vnet_port.\n");
+		goto err_out_put_mdesc;
+	}
+
+	for (i = 0; i < ETH_ALEN; i++)
+		port->raddr[i] = (*rmac >> (5 - i) * 8) & 0xff;
+
+	port->vp = vp;
+
+	err = vio_driver_init(&port->vio, vdev, VDEV_NETWORK,
+			      vnet_versions, ARRAY_SIZE(vnet_versions),
+			      &vnet_vio_ops, vp->dev->name);
+	if (err)
+		goto err_out_free_port;
+
+	err = vio_ldc_alloc(&port->vio, &vnet_ldc_cfg, port);
+	if (err)
+		goto err_out_free_port;
+
+	err = vnet_port_alloc_tx_bufs(port);
+	if (err)
+		goto err_out_free_ldc;
+
+	INIT_HLIST_NODE(&port->hash);
+	INIT_LIST_HEAD(&port->list);
+
+	switch_port = 0;
+	if (mdesc_get_property(hp, vdev->mp, "switch-port", NULL) != NULL)
+		switch_port = 1;
+
+	spin_lock_irqsave(&vp->lock, flags);
+	if (switch_port)
+		list_add(&port->list, &vp->port_list);
+	else
+		list_add_tail(&port->list, &vp->port_list);
+	hlist_add_head(&port->hash, &vp->port_hash[vnet_hashfn(port->raddr)]);
+	spin_unlock_irqrestore(&vp->lock, flags);
+
+	dev_set_drvdata(&vdev->dev, port);
+
+	printk(KERN_INFO "%s: PORT ( remote-mac ", vp->dev->name);
+	for (i = 0; i < 6; i++)
+		printk("%2.2x%c", port->raddr[i], i == 5 ? ' ' : ':');
+	if (switch_port)
+		printk("switch-port ");
+	printk(")\n");
+
+	vio_port_up(&port->vio);
+
+	mdesc_release(hp);
+
+	return 0;
+
+err_out_free_ldc:
+	vio_ldc_free(&port->vio);
+
+err_out_free_port:
+	kfree(port);
+
+err_out_put_mdesc:
+	mdesc_release(hp);
+	return err;
+}
+
+static int vnet_port_remove(struct vio_dev *vdev)
+{
+	struct vnet_port *port = dev_get_drvdata(&vdev->dev);
+
+	if (port) {
+		struct vnet *vp = port->vp;
+		unsigned long flags;
+
+		del_timer_sync(&port->vio.timer);
+
+		spin_lock_irqsave(&vp->lock, flags);
+		list_del(&port->list);
+		hlist_del(&port->hash);
+		spin_unlock_irqrestore(&vp->lock, flags);
+
+		vnet_port_free_tx_bufs(port);
+		vio_ldc_free(&port->vio);
+
+		dev_set_drvdata(&vdev->dev, NULL);
+
+		kfree(port);
+	}
+	return 0;
+}
+
+static struct vio_device_id vnet_port_match[] = {
+	{
+		.type = "vnet-port",
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(vio, vnet_match);
+
+static struct vio_driver vnet_port_driver = {
+	.id_table	= vnet_port_match,
+	.probe		= vnet_port_probe,
+	.remove		= vnet_port_remove,
+	.driver		= {
+		.name	= "vnet_port",
+		.owner	= THIS_MODULE,
+	}
+};
+
+const char *local_mac_prop = "local-mac-address";
+
+static int __devinit vnet_probe(struct vio_dev *vdev,
+				const struct vio_device_id *id)
+{
+	static int vnet_version_printed;
+	struct mdesc_handle *hp;
+	struct net_device *dev;
+	struct vnet *vp;
+	const u64 *mac;
+	int err, i, len;
+
+	if (vnet_version_printed++ == 0)
+		printk(KERN_INFO "%s", version);
+
+	hp = mdesc_grab();
+
+	mac = mdesc_get_property(hp, vdev->mp, local_mac_prop, &len);
+	if (!mac) {
+		printk(KERN_ERR PFX "vnet lacks %s property.\n",
+		       local_mac_prop);
+		err = -ENODEV;
+		goto err_out;
+	}
+
+	dev = alloc_etherdev(sizeof(*vp));
+	if (!dev) {
+		printk(KERN_ERR PFX "Etherdev alloc failed, aborting.\n");
+		err = -ENOMEM;
+		goto err_out;
+	}
+
+	for (i = 0; i < ETH_ALEN; i++)
+		dev->dev_addr[i] = (*mac >> (5 - i) * 8) & 0xff;
+
+	memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len);
+
+	SET_NETDEV_DEV(dev, &vdev->dev);
+
+	vp = netdev_priv(dev);
+
+	spin_lock_init(&vp->lock);
+	vp->dev = dev;
+	vp->vdev = vdev;
+
+	INIT_LIST_HEAD(&vp->port_list);
+	for (i = 0; i < VNET_PORT_HASH_SIZE; i++)
+		INIT_HLIST_HEAD(&vp->port_hash[i]);
+
+	dev->open = vnet_open;
+	dev->stop = vnet_close;
+	dev->set_multicast_list = vnet_set_rx_mode;
+	dev->set_mac_address = vnet_set_mac_addr;
+	dev->tx_timeout = vnet_tx_timeout;
+	dev->ethtool_ops = &vnet_ethtool_ops;
+	dev->watchdog_timeo = VNET_TX_TIMEOUT;
+	dev->change_mtu = vnet_change_mtu;
+	dev->hard_start_xmit = vnet_start_xmit;
+
+	err = register_netdev(dev);
+	if (err) {
+		printk(KERN_ERR PFX "Cannot register net device, "
+		       "aborting.\n");
+		goto err_out_free_dev;
+	}
+
+	printk(KERN_INFO "%s: Sun LDOM vnet ", dev->name);
+
+	for (i = 0; i < 6; i++)
+		printk("%2.2x%c", dev->dev_addr[i], i == 5 ? '\n' : ':');
+
+	dev_set_drvdata(&vdev->dev, vp);
+
+	mdesc_release(hp);
+
+	return 0;
+
+err_out_free_dev:
+	free_netdev(dev);
+
+err_out:
+	mdesc_release(hp);
+	return err;
+}
+
+static int vnet_remove(struct vio_dev *vdev)
+{
+
+	struct vnet *vp = dev_get_drvdata(&vdev->dev);
+
+	if (vp) {
+		/* XXX unregister port, or at least check XXX */
+		unregister_netdevice(vp->dev);
+		dev_set_drvdata(&vdev->dev, NULL);
+	}
+	return 0;
+}
+
+static struct vio_device_id vnet_match[] = {
+	{
+		.type = "network",
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(vio, vnet_match);
+
+static struct vio_driver vnet_driver = {
+	.id_table	= vnet_match,
+	.probe		= vnet_probe,
+	.remove		= vnet_remove,
+	.driver		= {
+		.name	= "vnet",
+		.owner	= THIS_MODULE,
+	}
+};
+
+static int __init vnet_init(void)
+{
+	int err = vio_register_driver(&vnet_driver);
+
+	if (!err) {
+		err = vio_register_driver(&vnet_port_driver);
+		if (err)
+			vio_unregister_driver(&vnet_driver);
+	}
+
+	return err;
+}
+
+static void __exit vnet_exit(void)
+{
+	vio_unregister_driver(&vnet_port_driver);
+	vio_unregister_driver(&vnet_driver);
+}
+
+module_init(vnet_init);
+module_exit(vnet_exit);
diff --git a/drivers/net/sunvnet.h b/drivers/net/sunvnet.h
new file mode 100644
index 00000000000..1c887302d46
--- /dev/null
+++ b/drivers/net/sunvnet.h
@@ -0,0 +1,70 @@
+#ifndef _SUNVNET_H
+#define _SUNVNET_H
+
+#define DESC_NCOOKIES(entry_size)	\
+	((entry_size) - sizeof(struct vio_net_desc))
+
+/* length of time before we decide the hardware is borked,
+ * and dev->tx_timeout() should be called to fix the problem
+ */
+#define VNET_TX_TIMEOUT			(5 * HZ)
+
+#define VNET_TX_RING_SIZE		512
+#define VNET_TX_WAKEUP_THRESH(dr)	((dr)->pending / 4)
+
+/* VNET packets are sent in buffers with the first 6 bytes skipped
+ * so that after the ethernet header the IPv4/IPv6 headers are aligned
+ * properly.
+ */
+#define VNET_PACKET_SKIP		6
+
+struct vnet_tx_entry {
+	void			*buf;
+	unsigned int		ncookies;
+	struct ldc_trans_cookie	cookies[2];
+};
+
+struct vnet;
+struct vnet_port {
+	struct vio_driver_state	vio;
+
+	struct hlist_node	hash;
+	u8			raddr[ETH_ALEN];
+
+	struct vnet		*vp;
+
+	struct vnet_tx_entry	tx_bufs[VNET_TX_RING_SIZE];
+
+	struct list_head	list;
+};
+
+static inline struct vnet_port *to_vnet_port(struct vio_driver_state *vio)
+{
+	return container_of(vio, struct vnet_port, vio);
+}
+
+#define VNET_PORT_HASH_SIZE	16
+#define VNET_PORT_HASH_MASK	(VNET_PORT_HASH_SIZE - 1)
+
+static inline unsigned int vnet_hashfn(u8 *mac)
+{
+	unsigned int val = mac[4] ^ mac[5];
+
+	return val & (VNET_PORT_HASH_MASK);
+}
+
+struct vnet {
+	/* Protects port_list and port_hash.  */
+	spinlock_t		lock;
+
+	struct net_device	*dev;
+
+	u32			msg_enable;
+	struct vio_dev		*vdev;
+
+	struct list_head	port_list;
+
+	struct hlist_head	port_hash[VNET_PORT_HASH_SIZE];
+};
+
+#endif /* _SUNVNET_H */
diff --git a/drivers/serial/sunhv.c b/drivers/serial/sunhv.c
index 96557e6dba6..17bcca53d6a 100644
--- a/drivers/serial/sunhv.c
+++ b/drivers/serial/sunhv.c
@@ -440,8 +440,16 @@ static void sunhv_console_write_paged(struct console *con, const char *s, unsign
 {
 	struct uart_port *port = sunhv_port;
 	unsigned long flags;
+	int locked = 1;
+
+	local_irq_save(flags);
+	if (port->sysrq) {
+		locked = 0;
+	} else if (oops_in_progress) {
+		locked = spin_trylock(&port->lock);
+	} else
+		spin_lock(&port->lock);
 
-	spin_lock_irqsave(&port->lock, flags);
 	while (n > 0) {
 		unsigned long ra = __pa(con_write_page);
 		unsigned long page_bytes;
@@ -469,7 +477,10 @@ static void sunhv_console_write_paged(struct console *con, const char *s, unsign
 			ra += written;
 		}
 	}
-	spin_unlock_irqrestore(&port->lock, flags);
+
+	if (locked)
+		spin_unlock(&port->lock);
+	local_irq_restore(flags);
 }
 
 static inline void sunhv_console_putchar(struct uart_port *port, char c)
@@ -488,7 +499,15 @@ static void sunhv_console_write_bychar(struct console *con, const char *s, unsig
 {
 	struct uart_port *port = sunhv_port;
 	unsigned long flags;
-	int i;
+	int i, locked = 1;
+
+	local_irq_save(flags);
+	if (port->sysrq) {
+		locked = 0;
+	} else if (oops_in_progress) {
+		locked = spin_trylock(&port->lock);
+	} else
+		spin_lock(&port->lock);
 
 	spin_lock_irqsave(&port->lock, flags);
 	for (i = 0; i < n; i++) {
@@ -496,7 +515,10 @@ static void sunhv_console_write_bychar(struct console *con, const char *s, unsig
 			sunhv_console_putchar(port, '\r');
 		sunhv_console_putchar(port, *s++);
 	}
-	spin_unlock_irqrestore(&port->lock, flags);
+
+	if (locked)
+		spin_unlock(&port->lock);
+	local_irq_restore(flags);
 }
 
 static struct console sunhv_console = {
diff --git a/drivers/serial/sunsab.c b/drivers/serial/sunsab.c
index deb9ab4b5a0..8a0f9e4408d 100644
--- a/drivers/serial/sunsab.c
+++ b/drivers/serial/sunsab.c
@@ -860,22 +860,31 @@ static int num_channels;
 static void sunsab_console_putchar(struct uart_port *port, int c)
 {
 	struct uart_sunsab_port *up = (struct uart_sunsab_port *)port;
-	unsigned long flags;
-
-	spin_lock_irqsave(&up->port.lock, flags);
 
 	sunsab_tec_wait(up);
 	writeb(c, &up->regs->w.tic);
-
-	spin_unlock_irqrestore(&up->port.lock, flags);
 }
 
 static void sunsab_console_write(struct console *con, const char *s, unsigned n)
 {
 	struct uart_sunsab_port *up = &sunsab_ports[con->index];
+	unsigned long flags;
+	int locked = 1;
+
+	local_irq_save(flags);
+	if (up->port.sysrq) {
+		locked = 0;
+	} else if (oops_in_progress) {
+		locked = spin_trylock(&up->port.lock);
+	} else
+		spin_lock(&up->port.lock);
 
 	uart_console_write(&up->port, s, n, sunsab_console_putchar);
 	sunsab_tec_wait(up);
+
+	if (locked)
+		spin_unlock(&up->port.lock);
+	local_irq_restore(flags);
 }
 
 static int sunsab_console_setup(struct console *con, char *options)
diff --git a/drivers/serial/sunsu.c b/drivers/serial/sunsu.c
index 2a63cdba320..26d720baf88 100644
--- a/drivers/serial/sunsu.c
+++ b/drivers/serial/sunsu.c
@@ -1288,7 +1288,17 @@ static void sunsu_console_write(struct console *co, const char *s,
 				unsigned int count)
 {
 	struct uart_sunsu_port *up = &sunsu_ports[co->index];
+	unsigned long flags;
 	unsigned int ier;
+	int locked = 1;
+
+	local_irq_save(flags);
+	if (up->port.sysrq) {
+		locked = 0;
+	} else if (oops_in_progress) {
+		locked = spin_trylock(&up->port.lock);
+	} else
+		spin_lock(&up->port.lock);
 
 	/*
 	 *	First save the UER then disable the interrupts
@@ -1304,6 +1314,10 @@ static void sunsu_console_write(struct console *co, const char *s,
 	 */
 	wait_for_xmitr(up);
 	serial_out(up, UART_IER, ier);
+
+	if (locked)
+		spin_unlock(&up->port.lock);
+	local_irq_restore(flags);
 }
 
 /*
diff --git a/drivers/serial/sunzilog.c b/drivers/serial/sunzilog.c
index 15b6e1cb040..0a3e10a4a35 100644
--- a/drivers/serial/sunzilog.c
+++ b/drivers/serial/sunzilog.c
@@ -9,7 +9,7 @@
  * C. Dost, Pete Zaitcev, Ted Ts'o and Alex Buell for their
  * work there.
  *
- *  Copyright (C) 2002, 2006 David S. Miller (davem@davemloft.net)
+ * Copyright (C) 2002, 2006, 2007 David S. Miller (davem@davemloft.net)
  */
 
 #include <linux/module.h>
@@ -1151,11 +1151,22 @@ sunzilog_console_write(struct console *con, const char *s, unsigned int count)
 {
 	struct uart_sunzilog_port *up = &sunzilog_port_table[con->index];
 	unsigned long flags;
+	int locked = 1;
+
+	local_irq_save(flags);
+	if (up->port.sysrq) {
+		locked = 0;
+	} else if (oops_in_progress) {
+		locked = spin_trylock(&up->port.lock);
+	} else
+		spin_lock(&up->port.lock);
 
-	spin_lock_irqsave(&up->port.lock, flags);
 	uart_console_write(&up->port, s, count, sunzilog_putchar);
 	udelay(2);
-	spin_unlock_irqrestore(&up->port.lock, flags);
+
+	if (locked)
+		spin_unlock(&up->port.lock);
+	local_irq_restore(flags);
 }
 
 static int __init sunzilog_console_setup(struct console *con, char *options)