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: (44 commits)
  Add MAINTAINERS entry for virtio_console
  virtio: console: Fill ports' entire in_vq with buffers
  virtio: console: Error out if we can't allocate buffers for control queue
  virtio: console: Add ability to remove module
  virtio: console: Ensure no memleaks in case of unused buffers
  virtio: console: show error message if hvc_alloc fails for console ports
  virtio: console: Add debugfs files for each port to expose debug info
  virtio: console: Add ability to hot-unplug ports
  virtio: console: Handle port hot-plug
  virtio: console: Remove cached data on port close
  virtio: console: Register with sysfs and create a 'name' attribute for ports
  virtio: console: Ensure only one process can have a port open at a time
  virtio: console: Add file operations to ports for open/read/write/poll
  virtio: console: Associate each port with a char device
  virtio: console: Prepare for writing to userspace buffers
  virtio: console: Add a new MULTIPORT feature, support for generic ports
  virtio: console: Introduce a send_buf function for a common path for sending data to host
  virtio: console: Introduce function to hand off data from host to readers
  virtio: console: Separate out find_vqs operation into a different function
  virtio: console: Separate out console init into a new function
  ...

Documentation/lguest/lguest.c

@@ -34,7 +34,6 @@
 #include <sys/uio.h>
 #include <termios.h>
 #include <getopt.h>
-#include <zlib.h>
 #include <assert.h>
 #include <sched.h>
 #include <limits.h>

MAINTAINERS

@@ -2393,6 +2393,12 @@ L:	linuxppc-dev@ozlabs.org
 S:	Odd Fixes
 F:	drivers/char/hvc_*
 
+VIRTIO CONSOLE DRIVER
+M:	Amit Shah <amit.shah@redhat.com>
+L:	virtualization@lists.linux-foundation.org
+S:	Maintained
+F:	drivers/char/virtio_console.c
+
 GSPCA FINEPIX SUBDRIVER
 M:	Frank Zago <frank@zago.net>
 L:	linux-media@vger.kernel.org

drivers/block/virtio_blk.c

@@ -243,10 +243,12 @@ static int index_to_minor(int index)
 static int __devinit virtblk_probe(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk;
+	struct request_queue *q;
 	int err;
 	u64 cap;
-	u32 v;
-	u32 blk_size, sg_elems;
+	u32 v, blk_size, sg_elems, opt_io_size;
+	u16 min_io_size;
+	u8 physical_block_exp, alignment_offset;
 
 	if (index_to_minor(index) >= 1 << MINORBITS)
 		return -ENOSPC;
@@ -293,13 +295,13 @@ static int __devinit virtblk_probe(struct virtio_device *vdev)
 		goto out_mempool;
 	}
 
-	vblk->disk->queue = blk_init_queue(do_virtblk_request, &vblk->lock);
-	if (!vblk->disk->queue) {
+	q = vblk->disk->queue = blk_init_queue(do_virtblk_request, &vblk->lock);
+	if (!q) {
 		err = -ENOMEM;
 		goto out_put_disk;
 	}
 
-	vblk->disk->queue->queuedata = vblk;
+	q->queuedata = vblk;
 
 	if (index < 26) {
 		sprintf(vblk->disk->disk_name, "vd%c", 'a' + index % 26);
@@ -323,10 +325,10 @@ static int __devinit virtblk_probe(struct virtio_device *vdev)
 
 	/* If barriers are supported, tell block layer that queue is ordered */
 	if (virtio_has_feature(vdev, VIRTIO_BLK_F_FLUSH))
-		blk_queue_ordered(vblk->disk->queue, QUEUE_ORDERED_DRAIN_FLUSH,
+		blk_queue_ordered(q, QUEUE_ORDERED_DRAIN_FLUSH,
 				  virtblk_prepare_flush);
 	else if (virtio_has_feature(vdev, VIRTIO_BLK_F_BARRIER))
-		blk_queue_ordered(vblk->disk->queue, QUEUE_ORDERED_TAG, NULL);
+		blk_queue_ordered(q, QUEUE_ORDERED_TAG, NULL);
 
 	/* If disk is read-only in the host, the guest should obey */
 	if (virtio_has_feature(vdev, VIRTIO_BLK_F_RO))
@@ -345,14 +347,14 @@ static int __devinit virtblk_probe(struct virtio_device *vdev)
 	set_capacity(vblk->disk, cap);
 
 	/* We can handle whatever the host told us to handle. */
-	blk_queue_max_phys_segments(vblk->disk->queue, vblk->sg_elems-2);
-	blk_queue_max_hw_segments(vblk->disk->queue, vblk->sg_elems-2);
+	blk_queue_max_phys_segments(q, vblk->sg_elems-2);
+	blk_queue_max_hw_segments(q, vblk->sg_elems-2);
 
 	/* No need to bounce any requests */
-	blk_queue_bounce_limit(vblk->disk->queue, BLK_BOUNCE_ANY);
+	blk_queue_bounce_limit(q, BLK_BOUNCE_ANY);
 
 	/* No real sector limit. */
-	blk_queue_max_sectors(vblk->disk->queue, -1U);
+	blk_queue_max_sectors(q, -1U);
 
 	/* Host can optionally specify maximum segment size and number of
 	 * segments. */
@@ -360,16 +362,45 @@ static int __devinit virtblk_probe(struct virtio_device *vdev)
 				offsetof(struct virtio_blk_config, size_max),
 				&v);
 	if (!err)
-		blk_queue_max_segment_size(vblk->disk->queue, v);
+		blk_queue_max_segment_size(q, v);
 	else
-		blk_queue_max_segment_size(vblk->disk->queue, -1U);
+		blk_queue_max_segment_size(q, -1U);
 
 	/* Host can optionally specify the block size of the device */
 	err = virtio_config_val(vdev, VIRTIO_BLK_F_BLK_SIZE,
 				offsetof(struct virtio_blk_config, blk_size),
 				&blk_size);
 	if (!err)
-		blk_queue_logical_block_size(vblk->disk->queue, blk_size);
+		blk_queue_logical_block_size(q, blk_size);
+	else
+		blk_size = queue_logical_block_size(q);
+
+	/* Use topology information if available */
+	err = virtio_config_val(vdev, VIRTIO_BLK_F_TOPOLOGY,
+			offsetof(struct virtio_blk_config, physical_block_exp),
+			&physical_block_exp);
+	if (!err && physical_block_exp)
+		blk_queue_physical_block_size(q,
+				blk_size * (1 << physical_block_exp));
+
+	err = virtio_config_val(vdev, VIRTIO_BLK_F_TOPOLOGY,
+			offsetof(struct virtio_blk_config, alignment_offset),
+			&alignment_offset);
+	if (!err && alignment_offset)
+		blk_queue_alignment_offset(q, blk_size * alignment_offset);
+
+	err = virtio_config_val(vdev, VIRTIO_BLK_F_TOPOLOGY,
+			offsetof(struct virtio_blk_config, min_io_size),
+			&min_io_size);
+	if (!err && min_io_size)
+		blk_queue_io_min(q, blk_size * min_io_size);
+
+	err = virtio_config_val(vdev, VIRTIO_BLK_F_TOPOLOGY,
+			offsetof(struct virtio_blk_config, opt_io_size),
+			&opt_io_size);
+	if (!err && opt_io_size)
+		blk_queue_io_opt(q, blk_size * opt_io_size);
+
 
 	add_disk(vblk->disk);
 	return 0;
@@ -412,7 +443,7 @@ static struct virtio_device_id id_table[] = {
 static unsigned int features[] = {
 	VIRTIO_BLK_F_BARRIER, 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_FLUSH
+	VIRTIO_BLK_F_SCSI, VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_TOPOLOGY
 };
 
 /*

drivers/char/Kconfig

@@ -666,6 +666,14 @@ config VIRTIO_CONSOLE
 	help
 	  Virtio console for use with lguest and other hypervisors.
 
+	  Also serves as a general-purpose serial device for data
+	  transfer between the guest and host.  Character devices at
+	  /dev/vportNpn will be created when corresponding ports are
+	  found, where N is the device number and n is the port number
+	  within that device.  If specified by the host, a sysfs
+	  attribute called 'name' will be populated with a name for
+	  the port which can be used by udev scripts to create a
+	  symlink to the device.
 
 config HVCS
 	tristate "IBM Hypervisor Virtual Console Server support"

drivers/char/hvc_beat.c

@@ -84,7 +84,7 @@ static int hvc_beat_put_chars(uint32_t vtermno, const char *buf, int cnt)
 	return cnt;
 }
 
-static struct hv_ops hvc_beat_get_put_ops = {
+static const struct hv_ops hvc_beat_get_put_ops = {
 	.get_chars = hvc_beat_get_chars,
 	.put_chars = hvc_beat_put_chars,
 };

drivers/char/hvc_console.c

@@ -125,7 +125,7 @@ static struct hvc_struct *hvc_get_by_index(int index)
  * console interfaces but can still be used as a tty device.  This has to be
  * static because kmalloc will not work during early console init.
  */
-static struct hv_ops *cons_ops[MAX_NR_HVC_CONSOLES];
+static const struct hv_ops *cons_ops[MAX_NR_HVC_CONSOLES];
 static uint32_t vtermnos[MAX_NR_HVC_CONSOLES] =
 	{[0 ... MAX_NR_HVC_CONSOLES - 1] = -1};
 
@@ -247,7 +247,7 @@ static void destroy_hvc_struct(struct kref *kref)
  * vty adapters do NOT get an hvc_instantiate() callback since they
  * appear after early console init.
  */
-int hvc_instantiate(uint32_t vtermno, int index, struct hv_ops *ops)
+int hvc_instantiate(uint32_t vtermno, int index, const struct hv_ops *ops)
 {
 	struct hvc_struct *hp;
 
@@ -749,7 +749,8 @@ static const struct tty_operations hvc_ops = {
 };
 
 struct hvc_struct __devinit *hvc_alloc(uint32_t vtermno, int data,
-					struct hv_ops *ops, int outbuf_size)
+				       const struct hv_ops *ops,
+				       int outbuf_size)
 {
 	struct hvc_struct *hp;
 	int i;

drivers/char/hvc_console.h

@@ -55,7 +55,7 @@ struct hvc_struct {
 	int outbuf_size;
 	int n_outbuf;
 	uint32_t vtermno;
-	struct hv_ops *ops;
+	const struct hv_ops *ops;
 	int irq_requested;
 	int data;
 	struct winsize ws;
@@ -76,11 +76,12 @@ struct hv_ops {
 };
 
 /* Register a vterm and a slot index for use as a console (console_init) */
-extern int hvc_instantiate(uint32_t vtermno, int index, struct hv_ops *ops);
+extern int hvc_instantiate(uint32_t vtermno, int index,
+			   const struct hv_ops *ops);
 
 /* register a vterm for hvc tty operation (module_init or hotplug add) */
 extern struct hvc_struct * __devinit hvc_alloc(uint32_t vtermno, int data,
-				struct hv_ops *ops, int outbuf_size);
+				const struct hv_ops *ops, int outbuf_size);
 /* remove a vterm from hvc tty operation (module_exit or hotplug remove) */
 extern int hvc_remove(struct hvc_struct *hp);
 

drivers/char/hvc_iseries.c

@@ -197,7 +197,7 @@ done:
 	return sent;
 }
 
-static struct hv_ops hvc_get_put_ops = {
+static const struct hv_ops hvc_get_put_ops = {
 	.get_chars = get_chars,
 	.put_chars = put_chars,
 	.notifier_add = notifier_add_irq,

drivers/char/hvc_iucv.c

@@ -922,7 +922,7 @@ static int hvc_iucv_pm_restore_thaw(struct device *dev)
 
 
 /* HVC operations */
-static struct hv_ops hvc_iucv_ops = {
+static const struct hv_ops hvc_iucv_ops = {
 	.get_chars = hvc_iucv_get_chars,
 	.put_chars = hvc_iucv_put_chars,
 	.notifier_add = hvc_iucv_notifier_add,

drivers/char/hvc_rtas.c

@@ -71,7 +71,7 @@ static int hvc_rtas_read_console(uint32_t vtermno, char *buf, int count)
 	return i;
 }
 
-static struct hv_ops hvc_rtas_get_put_ops = {
+static const struct hv_ops hvc_rtas_get_put_ops = {
 	.get_chars = hvc_rtas_read_console,
 	.put_chars = hvc_rtas_write_console,
 };

drivers/char/hvc_udbg.c

@@ -58,7 +58,7 @@ static int hvc_udbg_get(uint32_t vtermno, char *buf, int count)
 	return i;
 }
 
-static struct hv_ops hvc_udbg_ops = {
+static const struct hv_ops hvc_udbg_ops = {
 	.get_chars = hvc_udbg_get,
 	.put_chars = hvc_udbg_put,
 };

drivers/char/hvc_vio.c

@@ -77,7 +77,7 @@ static int filtered_get_chars(uint32_t vtermno, char *buf, int count)
 	return got;
 }
 
-static struct hv_ops hvc_get_put_ops = {
+static const struct hv_ops hvc_get_put_ops = {
 	.get_chars = filtered_get_chars,
 	.put_chars = hvc_put_chars,
 	.notifier_add = notifier_add_irq,

drivers/char/hvc_xen.c

@@ -122,7 +122,7 @@ static int read_console(uint32_t vtermno, char *buf, int len)
 	return recv;
 }
 
-static struct hv_ops hvc_ops = {
+static const struct hv_ops hvc_ops = {
 	.get_chars = read_console,
 	.put_chars = write_console,
 	.notifier_add = notifier_add_irq,

drivers/virtio/virtio_balloon.c

@@ -28,7 +28,7 @@
 struct virtio_balloon
 {
 	struct virtio_device *vdev;
-	struct virtqueue *inflate_vq, *deflate_vq;
+	struct virtqueue *inflate_vq, *deflate_vq, *stats_vq;
 
 	/* Where the ballooning thread waits for config to change. */
 	wait_queue_head_t config_change;
@@ -49,6 +49,10 @@ struct virtio_balloon
 	/* The array of pfns we tell the Host about. */
 	unsigned int num_pfns;
 	u32 pfns[256];
+
+	/* Memory statistics */
+	int need_stats_update;
+	struct virtio_balloon_stat stats[VIRTIO_BALLOON_S_NR];
 };
 
 static struct virtio_device_id id_table[] = {
@@ -154,6 +158,72 @@ static void leak_balloon(struct virtio_balloon *vb, size_t num)
 	}
 }
 
+static inline void update_stat(struct virtio_balloon *vb, int idx,
+			       u16 tag, u64 val)
+{
+	BUG_ON(idx >= VIRTIO_BALLOON_S_NR);
+	vb->stats[idx].tag = tag;
+	vb->stats[idx].val = val;
+}
+
+#define pages_to_bytes(x) ((u64)(x) << PAGE_SHIFT)
+
+static void update_balloon_stats(struct virtio_balloon *vb)
+{
+	unsigned long events[NR_VM_EVENT_ITEMS];
+	struct sysinfo i;
+	int idx = 0;
+
+	all_vm_events(events);
+	si_meminfo(&i);
+
+	update_stat(vb, idx++, VIRTIO_BALLOON_S_SWAP_IN,
+				pages_to_bytes(events[PSWPIN]));
+	update_stat(vb, idx++, VIRTIO_BALLOON_S_SWAP_OUT,
+				pages_to_bytes(events[PSWPOUT]));
+	update_stat(vb, idx++, VIRTIO_BALLOON_S_MAJFLT, events[PGMAJFAULT]);
+	update_stat(vb, idx++, VIRTIO_BALLOON_S_MINFLT, events[PGFAULT]);
+	update_stat(vb, idx++, VIRTIO_BALLOON_S_MEMFREE,
+				pages_to_bytes(i.freeram));
+	update_stat(vb, idx++, VIRTIO_BALLOON_S_MEMTOT,
+				pages_to_bytes(i.totalram));
+}
+
+/*
+ * While most virtqueues communicate guest-initiated requests to the hypervisor,
+ * the stats queue operates in reverse.  The driver initializes the virtqueue
+ * with a single buffer.  From that point forward, all conversations consist of
+ * a hypervisor request (a call to this function) which directs us to refill
+ * the virtqueue with a fresh stats buffer.  Since stats collection can sleep,
+ * we notify our kthread which does the actual work via stats_handle_request().
+ */
+static void stats_request(struct virtqueue *vq)
+{
+	struct virtio_balloon *vb;
+	unsigned int len;
+
+	vb = vq->vq_ops->get_buf(vq, &len);
+	if (!vb)
+		return;
+	vb->need_stats_update = 1;
+	wake_up(&vb->config_change);
+}
+
+static void stats_handle_request(struct virtio_balloon *vb)
+{
+	struct virtqueue *vq;
+	struct scatterlist sg;
+
+	vb->need_stats_update = 0;
+	update_balloon_stats(vb);
+
+	vq = vb->stats_vq;
+	sg_init_one(&sg, vb->stats, sizeof(vb->stats));
+	if (vq->vq_ops->add_buf(vq, &sg, 1, 0, vb) < 0)
+		BUG();
+	vq->vq_ops->kick(vq);
+}
+
 static void virtballoon_changed(struct virtio_device *vdev)
 {
 	struct virtio_balloon *vb = vdev->priv;
@@ -190,8 +260,11 @@ static int balloon(void *_vballoon)
 		try_to_freeze();
 		wait_event_interruptible(vb->config_change,
 					 (diff = towards_target(vb)) != 0
+					 || vb->need_stats_update
 					 || kthread_should_stop()
 					 || freezing(current));
+		if (vb->need_stats_update)
+			stats_handle_request(vb);
 		if (diff > 0)
 			fill_balloon(vb, diff);
 		else if (diff < 0)
@@ -204,10 +277,10 @@ static int balloon(void *_vballoon)
 static int virtballoon_probe(struct virtio_device *vdev)
 {
 	struct virtio_balloon *vb;
-	struct virtqueue *vqs[2];
-	vq_callback_t *callbacks[] = { balloon_ack, balloon_ack };
-	const char *names[] = { "inflate", "deflate" };
-	int err;
+	struct virtqueue *vqs[3];
+	vq_callback_t *callbacks[] = { balloon_ack, balloon_ack, stats_request };
+	const char *names[] = { "inflate", "deflate", "stats" };
+	int err, nvqs;
 
 	vdev->priv = vb = kmalloc(sizeof(*vb), GFP_KERNEL);
 	if (!vb) {
@@ -219,14 +292,31 @@ static int virtballoon_probe(struct virtio_device *vdev)
 	vb->num_pages = 0;
 	init_waitqueue_head(&vb->config_change);
 	vb->vdev = vdev;
+	vb->need_stats_update = 0;
 
-	/* We expect two virtqueues. */
-	err = vdev->config->find_vqs(vdev, 2, vqs, callbacks, names);
+	/* We expect two virtqueues: inflate and deflate,
+	 * and optionally stat. */
+	nvqs = virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2;
+	err = vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names);
 	if (err)
 		goto out_free_vb;
 
 	vb->inflate_vq = vqs[0];
 	vb->deflate_vq = vqs[1];
+	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) {
+		struct scatterlist sg;
+		vb->stats_vq = vqs[2];
+
+		/*
+		 * Prime this virtqueue with one buffer so the hypervisor can
+		 * use it to signal us later.
+		 */
+		sg_init_one(&sg, vb->stats, sizeof vb->stats);
+		if (vb->stats_vq->vq_ops->add_buf(vb->stats_vq,
+						  &sg, 1, 0, vb) < 0)
+			BUG();
+		vb->stats_vq->vq_ops->kick(vb->stats_vq);
+	}
 
 	vb->thread = kthread_run(balloon, vb, "vballoon");
 	if (IS_ERR(vb->thread)) {
@@ -264,7 +354,10 @@ static void __devexit virtballoon_remove(struct virtio_device *vdev)
 	kfree(vb);
 }
 
-static unsigned int features[] = { VIRTIO_BALLOON_F_MUST_TELL_HOST };
+static unsigned int features[] = {
+	VIRTIO_BALLOON_F_MUST_TELL_HOST,
+	VIRTIO_BALLOON_F_STATS_VQ,
+};
 
 static struct virtio_driver virtio_balloon_driver = {
 	.feature_table = features,

drivers/virtio/virtio_pci.c

@@ -702,7 +702,7 @@ static struct pci_driver virtio_pci_driver = {
 	.name		= "virtio-pci",
 	.id_table	= virtio_pci_id_table,
 	.probe		= virtio_pci_probe,
-	.remove		= virtio_pci_remove,
+	.remove		= __devexit_p(virtio_pci_remove),
 #ifdef CONFIG_PM
 	.suspend	= virtio_pci_suspend,
 	.resume		= virtio_pci_resume,

drivers/virtio/virtio_ring.c

@@ -21,6 +21,24 @@
 #include <linux/virtio_config.h>
 #include <linux/device.h>
 
+/* virtio guest is communicating with a virtual "device" that actually runs on
+ * a host processor.  Memory barriers are used to control SMP effects. */
+#ifdef CONFIG_SMP
+/* Where possible, use SMP barriers which are more lightweight than mandatory
+ * barriers, because mandatory barriers control MMIO effects on accesses
+ * through relaxed memory I/O windows (which virtio does not use). */
+#define virtio_mb() smp_mb()
+#define virtio_rmb() smp_rmb()
+#define virtio_wmb() smp_wmb()
+#else
+/* We must force memory ordering even if guest is UP since host could be
+ * running on another CPU, but SMP barriers are defined to barrier() in that
+ * configuration. So fall back to mandatory barriers instead. */
+#define virtio_mb() mb()
+#define virtio_rmb() rmb()
+#define virtio_wmb() wmb()
+#endif
+
 #ifdef DEBUG
 /* For development, we want to crash whenever the ring is screwed. */
 #define BAD_RING(_vq, fmt, args...)				\
@@ -36,10 +54,9 @@
 			panic("%s:in_use = %i\n",		\
 			      (_vq)->vq.name, (_vq)->in_use);	\
 		(_vq)->in_use = __LINE__;			\
-		mb();						\
 	} while (0)
 #define END_USE(_vq) \
-	do { BUG_ON(!(_vq)->in_use); (_vq)->in_use = 0; mb(); } while(0)
+	do { BUG_ON(!(_vq)->in_use); (_vq)->in_use = 0; } while(0)
 #else
 #define BAD_RING(_vq, fmt, args...)				\
 	do {							\
@@ -221,13 +238,13 @@ static void vring_kick(struct virtqueue *_vq)
 	START_USE(vq);
 	/* Descriptors and available array need to be set before we expose the
 	 * new available array entries. */
-	wmb();
+	virtio_wmb();
 
 	vq->vring.avail->idx += vq->num_added;
 	vq->num_added = 0;
 
 	/* Need to update avail index before checking if we should notify */
-	mb();
+	virtio_mb();
 
 	if (!(vq->vring.used->flags & VRING_USED_F_NO_NOTIFY))
 		/* Prod other side to tell it about changes. */
@@ -286,7 +303,7 @@ static void *vring_get_buf(struct virtqueue *_vq, unsigned int *len)
 	}
 
 	/* Only get used array entries after they have been exposed by host. */
-	rmb();
+	virtio_rmb();
 
 	i = vq->vring.used->ring[vq->last_used_idx%vq->vring.num].id;
 	*len = vq->vring.used->ring[vq->last_used_idx%vq->vring.num].len;
@@ -324,7 +341,7 @@ static bool vring_enable_cb(struct virtqueue *_vq)
 	/* We optimistically turn back on interrupts, then check if there was
 	 * more to do. */
 	vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT;
-	mb();
+	virtio_mb();
 	if (unlikely(more_used(vq))) {
 		END_USE(vq);
 		return false;
@@ -334,6 +351,30 @@ static bool vring_enable_cb(struct virtqueue *_vq)
 	return true;
 }
 
+static void *vring_detach_unused_buf(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	unsigned int i;
+	void *buf;
+
+	START_USE(vq);
+
+	for (i = 0; i < vq->vring.num; i++) {
+		if (!vq->data[i])
+			continue;
+		/* detach_buf clears data, so grab it now. */
+		buf = vq->data[i];
+		detach_buf(vq, i);
+		END_USE(vq);
+		return buf;
+	}
+	/* That should have freed everything. */
+	BUG_ON(vq->num_free != vq->vring.num);
+
+	END_USE(vq);
+	return NULL;
+}
+
 irqreturn_t vring_interrupt(int irq, void *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
@@ -360,6 +401,7 @@ static struct virtqueue_ops vring_vq_ops = {
 	.kick = vring_kick,
 	.disable_cb = vring_disable_cb,
 	.enable_cb = vring_enable_cb,
+	.detach_unused_buf = vring_detach_unused_buf,
 };
 
 struct virtqueue *vring_new_virtqueue(unsigned int num,
@@ -406,8 +448,11 @@ struct virtqueue *vring_new_virtqueue(unsigned int num,
 	/* Put everything in free lists. */
 	vq->num_free = num;
 	vq->free_head = 0;
-	for (i = 0; i < num-1; i++)
+	for (i = 0; i < num-1; i++) {
 		vq->vring.desc[i].next = i+1;
+		vq->data[i] = NULL;
+	}
+	vq->data[i] = NULL;
 
 	return &vq->vq;
 }

include/linux/virtio.h

@@ -51,6 +51,9 @@ struct virtqueue {
  *	This re-enables callbacks; it returns "false" if there are pending
  *	buffers in the queue, to detect a possible race between the driver
  *	checking for more work, and enabling callbacks.
+ * @detach_unused_buf: detach first unused buffer
+ * 	vq: the struct virtqueue we're talking about.
+ * 	Returns NULL or the "data" token handed to add_buf
  *
  * Locking rules are straightforward: the driver is responsible for
  * locking.  No two operations may be invoked simultaneously, with the exception
@@ -71,6 +74,7 @@ struct virtqueue_ops {
 
 	void (*disable_cb)(struct virtqueue *vq);
 	bool (*enable_cb)(struct virtqueue *vq);
+	void *(*detach_unused_buf)(struct virtqueue *vq);
 };
 
 /**

include/linux/virtio_balloon.h

@@ -7,6 +7,7 @@
 
 /* The feature bitmap for virtio balloon */
 #define VIRTIO_BALLOON_F_MUST_TELL_HOST	0 /* Tell before reclaiming pages */
+#define VIRTIO_BALLOON_F_STATS_VQ	1 /* Memory Stats virtqueue */
 
 /* Size of a PFN in the balloon interface. */
 #define VIRTIO_BALLOON_PFN_SHIFT 12
@@ -18,4 +19,18 @@ struct virtio_balloon_config
 	/* Number of pages we've actually got in balloon. */
 	__le32 actual;
 };
+
+#define VIRTIO_BALLOON_S_SWAP_IN  0   /* Amount of memory swapped in */
+#define VIRTIO_BALLOON_S_SWAP_OUT 1   /* Amount of memory swapped out */
+#define VIRTIO_BALLOON_S_MAJFLT   2   /* Number of major faults */
+#define VIRTIO_BALLOON_S_MINFLT   3   /* Number of minor faults */
+#define VIRTIO_BALLOON_S_MEMFREE  4   /* Total amount of free memory */
+#define VIRTIO_BALLOON_S_MEMTOT   5   /* Total amount of memory */
+#define VIRTIO_BALLOON_S_NR       6
+
+struct virtio_balloon_stat {
+	u16 tag;
+	u64 val;
+} __attribute__((packed));
+
 #endif /* _LINUX_VIRTIO_BALLOON_H */

include/linux/virtio_blk.h

@@ -15,6 +15,7 @@
 #define VIRTIO_BLK_F_BLK_SIZE	6	/* Block size of disk is available*/
 #define VIRTIO_BLK_F_SCSI	7	/* Supports scsi command passthru */
 #define VIRTIO_BLK_F_FLUSH	9	/* Cache flush command support */
+#define VIRTIO_BLK_F_TOPOLOGY	10	/* Topology information is available */
 
 struct virtio_blk_config {
 	/* The capacity (in 512-byte sectors). */
@@ -29,8 +30,20 @@ struct virtio_blk_config {
 		__u8 heads;
 		__u8 sectors;
 	} geometry;
+
 	/* block size of device (if VIRTIO_BLK_F_BLK_SIZE) */
 	__u32 blk_size;
+
+	/* the next 4 entries are guarded by VIRTIO_BLK_F_TOPOLOGY  */
+	/* exponent for physical block per logical block. */
+	__u8 physical_block_exp;
+	/* alignment offset in logical blocks. */
+	__u8 alignment_offset;
+	/* minimum I/O size without performance penalty in logical blocks. */
+	__u16 min_io_size;
+	/* optimal sustained I/O size in logical blocks. */
+	__u32 opt_io_size;
+
 } __attribute__((packed));
 
 /*

include/linux/virtio_console.h

@@ -3,19 +3,45 @@
 #include <linux/types.h>
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>
-/* This header, excluding the #ifdef __KERNEL__ part, is BSD licensed so
- * anyone can use the definitions to implement compatible drivers/servers. */
+/*
+ * This header, excluding the #ifdef __KERNEL__ part, is BSD licensed so
+ * anyone can use the definitions to implement compatible drivers/servers.
+ *
+ * Copyright (C) Red Hat, Inc., 2009, 2010
+ */
 
 /* Feature bits */
 #define VIRTIO_CONSOLE_F_SIZE	0	/* Does host provide console size? */
+#define VIRTIO_CONSOLE_F_MULTIPORT 1	/* Does host provide multiple ports? */
 
 struct virtio_console_config {
 	/* colums of the screens */
 	__u16 cols;
 	/* rows of the screens */
 	__u16 rows;
+	/* max. number of ports this device can hold */
+	__u32 max_nr_ports;
+	/* number of ports added so far */
+	__u32 nr_ports;
 } __attribute__((packed));
 
+/*
+ * A message that's passed between the Host and the Guest for a
+ * particular port.
+ */
+struct virtio_console_control {
+	__u32 id;		/* Port number */
+	__u16 event;		/* The kind of control event (see below) */
+	__u16 value;		/* Extra information for the key */
+};
+
+/* Some events for control messages */
+#define VIRTIO_CONSOLE_PORT_READY	0
+#define VIRTIO_CONSOLE_CONSOLE_PORT	1
+#define VIRTIO_CONSOLE_RESIZE		2
+#define VIRTIO_CONSOLE_PORT_OPEN	3
+#define VIRTIO_CONSOLE_PORT_NAME	4
+#define VIRTIO_CONSOLE_PORT_REMOVE	5
 
 #ifdef __KERNEL__
 int __init virtio_cons_early_init(int (*put_chars)(u32, const char *, int));