virtio: fixups

Latest header update will break QEMU (if it's rebuilt with the new
 header) - and it seems that the code there is so fragile that any change
 in this header will break it.  Add a better interface so users do not
 need to change their code every time that header changes.
 
 Fix virtio console for spec compliance.
 
 Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iQEcBAABAgAGBQJa4L3jAAoJECgfDbjSjVRpJiAIAMLVjPeMTsES6BX4duG/jhhc
 QmAflHg73Qmgvanbpqit/B1TRRsOsVnUGQ/4SubfQdEFZld8u/1ZNur9LKDika7h
 qhCM1HN9KN3O7E4IIF45i8jmsXoqBWOIb3BqBdAyeqNDWH4q48524IvYizPMgkDd
 ZnEZ/2pRi2HRstlwBD/JTcsfWRp/nUjarxnj8ZhUEUDFbJfjr7sPTeDwPSDShuIQ
 PrC9U8gliNRuxuq1v5Afn9F6mQptgvMxMLmtUqvYydlYgwu7cJUQ+Qxp8i7rNfM8
 kCKkn/24UdUYHft4596bEEgDWR6nriMFCQAYKWlsCtwIvbZnURURl5TKT5ceI7Y=
 =N0il
 -----END PGP SIGNATURE-----

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

Pull virtio fixups from Michael Tsirkin:

 - Latest header update will break QEMU (if it's rebuilt with the new
   header) - and it seems that the code there is so fragile that any
   change in this header will break it. Add a better interface so users
   do not need to change their code every time that header changes.

 - Fix virtio console for spec compliance.

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
  virtio_console: reset on out of memory
  virtio_console: move removal code
  virtio_console: drop custom control queue cleanup
  virtio_console: free buffers after reset
  virtio: add ability to iterate over vqs
  virtio_console: don't tie bufs to a vq
  virtio_balloon: add array of stat names

drivers/char/virtio_console.c

@@ -422,7 +422,7 @@ static void reclaim_dma_bufs(void)
 	}
 }
 
-static struct port_buffer *alloc_buf(struct virtqueue *vq, size_t buf_size,
+static struct port_buffer *alloc_buf(struct virtio_device *vdev, size_t buf_size,
 				     int pages)
 {
 	struct port_buffer *buf;
@@ -445,16 +445,16 @@ static struct port_buffer *alloc_buf(struct virtqueue *vq, size_t buf_size,
 		return buf;
 	}
 
-	if (is_rproc_serial(vq->vdev)) {
+	if (is_rproc_serial(vdev)) {
 		/*
 		 * Allocate DMA memory from ancestor. When a virtio
 		 * device is created by remoteproc, the DMA memory is
 		 * associated with the grandparent device:
 		 * vdev => rproc => platform-dev.
 		 */
-		if (!vq->vdev->dev.parent || !vq->vdev->dev.parent->parent)
+		if (!vdev->dev.parent || !vdev->dev.parent->parent)
 			goto free_buf;
-		buf->dev = vq->vdev->dev.parent->parent;
+		buf->dev = vdev->dev.parent->parent;
 
 		/* Increase device refcnt to avoid freeing it */
 		get_device(buf->dev);
@@ -838,7 +838,7 @@ static ssize_t port_fops_write(struct file *filp, const char __user *ubuf,
 
 	count = min((size_t)(32 * 1024), count);
 
-	buf = alloc_buf(port->out_vq, count, 0);
+	buf = alloc_buf(port->portdev->vdev, count, 0);
 	if (!buf)
 		return -ENOMEM;
 
@@ -957,7 +957,7 @@ static ssize_t port_fops_splice_write(struct pipe_inode_info *pipe,
 	if (ret < 0)
 		goto error_out;
 
-	buf = alloc_buf(port->out_vq, 0, pipe->nrbufs);
+	buf = alloc_buf(port->portdev->vdev, 0, pipe->nrbufs);
 	if (!buf) {
 		ret = -ENOMEM;
 		goto error_out;
@@ -1374,7 +1374,7 @@ static unsigned int fill_queue(struct virtqueue *vq, spinlock_t *lock)
 
 	nr_added_bufs = 0;
 	do {
-		buf = alloc_buf(vq, PAGE_SIZE, 0);
+		buf = alloc_buf(vq->vdev, PAGE_SIZE, 0);
 		if (!buf)
 			break;
 
@@ -1402,7 +1402,6 @@ static int add_port(struct ports_device *portdev, u32 id)
 {
 	char debugfs_name[16];
 	struct port *port;
-	struct port_buffer *buf;
 	dev_t devt;
 	unsigned int nr_added_bufs;
 	int err;
@@ -1513,8 +1512,6 @@ static int add_port(struct ports_device *portdev, u32 id)
 	return 0;
 
 free_inbufs:
-	while ((buf = virtqueue_detach_unused_buf(port->in_vq)))
-		free_buf(buf, true);
 free_device:
 	device_destroy(pdrvdata.class, port->dev->devt);
 free_cdev:
@@ -1539,34 +1536,14 @@ static void remove_port(struct kref *kref)
 
 static void remove_port_data(struct port *port)
 {
-	struct port_buffer *buf;
-
 	spin_lock_irq(&port->inbuf_lock);
 	/* Remove unused data this port might have received. */
 	discard_port_data(port);
 	spin_unlock_irq(&port->inbuf_lock);
 
-	/* Remove buffers we queued up for the Host to send us data in. */
-	do {
-		spin_lock_irq(&port->inbuf_lock);
-		buf = virtqueue_detach_unused_buf(port->in_vq);
-		spin_unlock_irq(&port->inbuf_lock);
-		if (buf)
-			free_buf(buf, true);
-	} while (buf);
-
 	spin_lock_irq(&port->outvq_lock);
 	reclaim_consumed_buffers(port);
 	spin_unlock_irq(&port->outvq_lock);
-
-	/* Free pending buffers from the out-queue. */
-	do {
-		spin_lock_irq(&port->outvq_lock);
-		buf = virtqueue_detach_unused_buf(port->out_vq);
-		spin_unlock_irq(&port->outvq_lock);
-		if (buf)
-			free_buf(buf, true);
-	} while (buf);
 }
 
 /*
@@ -1791,13 +1768,24 @@ static void control_work_handler(struct work_struct *work)
 	spin_unlock(&portdev->c_ivq_lock);
 }
 
+static void flush_bufs(struct virtqueue *vq, bool can_sleep)
+{
+	struct port_buffer *buf;
+	unsigned int len;
+
+	while ((buf = virtqueue_get_buf(vq, &len)))
+		free_buf(buf, can_sleep);
+}
+
 static void out_intr(struct virtqueue *vq)
 {
 	struct port *port;
 
 	port = find_port_by_vq(vq->vdev->priv, vq);
-	if (!port)
+	if (!port) {
+		flush_bufs(vq, false);
 		return;
+	}
 
 	wake_up_interruptible(&port->waitqueue);
 }
@@ -1808,8 +1796,10 @@ static void in_intr(struct virtqueue *vq)
 	unsigned long flags;
 
 	port = find_port_by_vq(vq->vdev->priv, vq);
-	if (!port)
+	if (!port) {
+		flush_bufs(vq, false);
 		return;
+	}
 
 	spin_lock_irqsave(&port->inbuf_lock, flags);
 	port->inbuf = get_inbuf(port);
@@ -1984,24 +1974,54 @@ static const struct file_operations portdev_fops = {
 
 static void remove_vqs(struct ports_device *portdev)
 {
+	struct virtqueue *vq;
+
+	virtio_device_for_each_vq(portdev->vdev, vq) {
+		struct port_buffer *buf;
+
+		flush_bufs(vq, true);
+		while ((buf = virtqueue_detach_unused_buf(vq)))
+			free_buf(buf, true);
+	}
 	portdev->vdev->config->del_vqs(portdev->vdev);
 	kfree(portdev->in_vqs);
 	kfree(portdev->out_vqs);
 }
 
-static void remove_controlq_data(struct ports_device *portdev)
+static void virtcons_remove(struct virtio_device *vdev)
 {
-	struct port_buffer *buf;
-	unsigned int len;
+	struct ports_device *portdev;
+	struct port *port, *port2;
 
-	if (!use_multiport(portdev))
-		return;
+	portdev = vdev->priv;
 
-	while ((buf = virtqueue_get_buf(portdev->c_ivq, &len)))
-		free_buf(buf, true);
+	spin_lock_irq(&pdrvdata_lock);
+	list_del(&portdev->list);
+	spin_unlock_irq(&pdrvdata_lock);
 
-	while ((buf = virtqueue_detach_unused_buf(portdev->c_ivq)))
-		free_buf(buf, true);
+	/* Disable interrupts for vqs */
+	vdev->config->reset(vdev);
+	/* Finish up work that's lined up */
+	if (use_multiport(portdev))
+		cancel_work_sync(&portdev->control_work);
+	else
+		cancel_work_sync(&portdev->config_work);
+
+	list_for_each_entry_safe(port, port2, &portdev->ports, list)
+		unplug_port(port);
+
+	unregister_chrdev(portdev->chr_major, "virtio-portsdev");
+
+	/*
+	 * When yanking out a device, we immediately lose the
+	 * (device-side) queues.  So there's no point in keeping the
+	 * guest side around till we drop our final reference.  This
+	 * also means that any ports which are in an open state will
+	 * have to just stop using the port, as the vqs are going
+	 * away.
+	 */
+	remove_vqs(portdev);
+	kfree(portdev);
 }
 
 /*
@@ -2070,6 +2090,7 @@ static int virtcons_probe(struct virtio_device *vdev)
 
 	spin_lock_init(&portdev->ports_lock);
 	INIT_LIST_HEAD(&portdev->ports);
+	INIT_LIST_HEAD(&portdev->list);
 
 	virtio_device_ready(portdev->vdev);
 
@@ -2087,8 +2108,15 @@ static int virtcons_probe(struct virtio_device *vdev)
 		if (!nr_added_bufs) {
 			dev_err(&vdev->dev,
 				"Error allocating buffers for control queue\n");
-			err = -ENOMEM;
-			goto free_vqs;
+			/*
+			 * The host might want to notify mgmt sw about device
+			 * add failure.
+			 */
+			__send_control_msg(portdev, VIRTIO_CONSOLE_BAD_ID,
+					   VIRTIO_CONSOLE_DEVICE_READY, 0);
+			/* Device was functional: we need full cleanup. */
+			virtcons_remove(vdev);
+			return -ENOMEM;
 		}
 	} else {
 		/*
@@ -2119,11 +2147,6 @@ static int virtcons_probe(struct virtio_device *vdev)
 
 	return 0;
 
-free_vqs:
-	/* The host might want to notify mgmt sw about device add failure */
-	__send_control_msg(portdev, VIRTIO_CONSOLE_BAD_ID,
-			   VIRTIO_CONSOLE_DEVICE_READY, 0);
-	remove_vqs(portdev);
 free_chrdev:
 	unregister_chrdev(portdev->chr_major, "virtio-portsdev");
 free:
@@ -2132,43 +2155,6 @@ fail:
 	return err;
 }
 
-static void virtcons_remove(struct virtio_device *vdev)
-{
-	struct ports_device *portdev;
-	struct port *port, *port2;
-
-	portdev = vdev->priv;
-
-	spin_lock_irq(&pdrvdata_lock);
-	list_del(&portdev->list);
-	spin_unlock_irq(&pdrvdata_lock);
-
-	/* Disable interrupts for vqs */
-	vdev->config->reset(vdev);
-	/* Finish up work that's lined up */
-	if (use_multiport(portdev))
-		cancel_work_sync(&portdev->control_work);
-	else
-		cancel_work_sync(&portdev->config_work);
-
-	list_for_each_entry_safe(port, port2, &portdev->ports, list)
-		unplug_port(port);
-
-	unregister_chrdev(portdev->chr_major, "virtio-portsdev");
-
-	/*
-	 * When yanking out a device, we immediately lose the
-	 * (device-side) queues.  So there's no point in keeping the
-	 * guest side around till we drop our final reference.  This
-	 * also means that any ports which are in an open state will
-	 * have to just stop using the port, as the vqs are going
-	 * away.
-	 */
-	remove_controlq_data(portdev);
-	remove_vqs(portdev);
-	kfree(portdev);
-}
-
 static struct virtio_device_id id_table[] = {
 	{ VIRTIO_ID_CONSOLE, VIRTIO_DEV_ANY_ID },
 	{ 0 },
@@ -2209,7 +2195,6 @@ static int virtcons_freeze(struct virtio_device *vdev)
 	 */
 	if (use_multiport(portdev))
 		virtqueue_disable_cb(portdev->c_ivq);
-	remove_controlq_data(portdev);
 
 	list_for_each_entry(port, &portdev->ports, list) {
 		virtqueue_disable_cb(port->in_vq);

include/linux/virtio.h

@@ -157,6 +157,9 @@ int virtio_device_freeze(struct virtio_device *dev);
 int virtio_device_restore(struct virtio_device *dev);
 #endif
 
+#define virtio_device_for_each_vq(vdev, vq) \
+	list_for_each_entry(vq, &vdev->vqs, list)
+
 /**
  * virtio_driver - operations for a virtio I/O driver
  * @driver: underlying device driver (populate name and owner).

include/uapi/linux/virtio_balloon.h

@@ -57,6 +57,21 @@ struct virtio_balloon_config {
 #define VIRTIO_BALLOON_S_HTLB_PGFAIL   9  /* Hugetlb page allocation failures */
 #define VIRTIO_BALLOON_S_NR       10
 
+#define VIRTIO_BALLOON_S_NAMES_WITH_PREFIX(VIRTIO_BALLOON_S_NAMES_prefix) { \
+	VIRTIO_BALLOON_S_NAMES_prefix "swap-in", \
+	VIRTIO_BALLOON_S_NAMES_prefix "swap-out", \
+	VIRTIO_BALLOON_S_NAMES_prefix "major-faults", \
+	VIRTIO_BALLOON_S_NAMES_prefix "minor-faults", \
+	VIRTIO_BALLOON_S_NAMES_prefix "free-memory", \
+	VIRTIO_BALLOON_S_NAMES_prefix "total-memory", \
+	VIRTIO_BALLOON_S_NAMES_prefix "available-memory", \
+	VIRTIO_BALLOON_S_NAMES_prefix "disk-caches", \
+	VIRTIO_BALLOON_S_NAMES_prefix "hugetlb-allocations", \
+	VIRTIO_BALLOON_S_NAMES_prefix "hugetlb-failures" \
+}
+
+#define VIRTIO_BALLOON_S_NAMES VIRTIO_BALLOON_S_NAMES_WITH_PREFIX("")
+
 /*
  * Memory statistics structure.
  * Driver fills an array of these structures and passes to device.