Merge tag 'virtio-next-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux

Pull virtio update from Rusty Russell:
 "Some nice cleanups, and even a patch my wife did as a "live" demo for
  Latinoware 2012.

  There's a slightly non-trivial merge in virtio-net, as we cleaned up
  the virtio add_buf interface while DaveM accepted the mq virtio-net
  patches."

* tag 'virtio-next-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux: (27 commits)
  virtio_console: Add support for remoteproc serial
  virtio_console: Merge struct buffer_token into struct port_buffer
  virtio: add drv_to_virtio to make code clearly
  virtio: use dev_to_virtio wrapper in virtio
  virtio-mmio: Fix irq parsing in command line parameter
  virtio_console: Free buffers from out-queue upon close
  virtio: Convert dev_printk(KERN_<LEVEL> to dev_<level>(
  virtio_console: Use kmalloc instead of kzalloc
  virtio_console: Free buffer if splice fails
  virtio: tools: make it clear that virtqueue_add_buf() no longer returns > 0
  virtio: scsi: make it clear that virtqueue_add_buf() no longer returns > 0
  virtio: rpmsg: make it clear that virtqueue_add_buf() no longer returns > 0
  virtio: net: make it clear that virtqueue_add_buf() no longer returns > 0
  virtio: console: make it clear that virtqueue_add_buf() no longer returns > 0
  virtio: make virtqueue_add_buf() returning 0 on success, not capacity.
  virtio: console: don't rely on virtqueue_add_buf() returning capacity.
  virtio_net: don't rely on virtqueue_add_buf() returning capacity.
  virtio-net: remove unused skb_vnet_hdr->num_sg field
  virtio-net: correct capacity math on ring full
  virtio: move queue_index and num_free fields into core struct virtqueue.
  ...

drivers/char/virtio_console.c

@@ -37,8 +37,12 @@
 #include <linux/wait.h>
 #include <linux/workqueue.h>
 #include <linux/module.h>
+#include <linux/dma-mapping.h>
+#include <linux/kconfig.h>
 #include "../tty/hvc/hvc_console.h"
 
+#define is_rproc_enabled IS_ENABLED(CONFIG_REMOTEPROC)
+
 /*
  * This is a global struct for storing common data for all the devices
  * this driver handles.
@@ -111,6 +115,21 @@ struct port_buffer {
 	size_t len;
 	/* offset in the buf from which to consume data */
 	size_t offset;
+
+	/* DMA address of buffer */
+	dma_addr_t dma;
+
+	/* Device we got DMA memory from */
+	struct device *dev;
+
+	/* List of pending dma buffers to free */
+	struct list_head list;
+
+	/* If sgpages == 0 then buf is used */
+	unsigned int sgpages;
+
+	/* sg is used if spages > 0. sg must be the last in is struct */
+	struct scatterlist sg[0];
 };
 
 /*
@@ -325,6 +344,11 @@ static bool is_console_port(struct port *port)
 	return false;
 }
 
+static bool is_rproc_serial(const struct virtio_device *vdev)
+{
+	return is_rproc_enabled && vdev->id.device == VIRTIO_ID_RPROC_SERIAL;
+}
+
 static inline bool use_multiport(struct ports_device *portdev)
 {
 	/*
@@ -336,20 +360,110 @@ static inline bool use_multiport(struct ports_device *portdev)
 	return portdev->vdev->features[0] & (1 << VIRTIO_CONSOLE_F_MULTIPORT);
 }
 
-static void free_buf(struct port_buffer *buf)
+static DEFINE_SPINLOCK(dma_bufs_lock);
+static LIST_HEAD(pending_free_dma_bufs);
+
+static void free_buf(struct port_buffer *buf, bool can_sleep)
 {
+	unsigned int i;
+
+	for (i = 0; i < buf->sgpages; i++) {
+		struct page *page = sg_page(&buf->sg[i]);
+		if (!page)
+			break;
+		put_page(page);
+	}
+
+	if (!buf->dev) {
 		kfree(buf->buf);
+	} else if (is_rproc_enabled) {
+		unsigned long flags;
+
+		/* dma_free_coherent requires interrupts to be enabled. */
+		if (!can_sleep) {
+			/* queue up dma-buffers to be freed later */
+			spin_lock_irqsave(&dma_bufs_lock, flags);
+			list_add_tail(&buf->list, &pending_free_dma_bufs);
+			spin_unlock_irqrestore(&dma_bufs_lock, flags);
+			return;
+		}
+		dma_free_coherent(buf->dev, buf->size, buf->buf, buf->dma);
+
+		/* Release device refcnt and allow it to be freed */
+		put_device(buf->dev);
+	}
+
 	kfree(buf);
 }
 
-static struct port_buffer *alloc_buf(size_t buf_size)
+static void reclaim_dma_bufs(void)
+{
+	unsigned long flags;
+	struct port_buffer *buf, *tmp;
+	LIST_HEAD(tmp_list);
+
+	if (list_empty(&pending_free_dma_bufs))
+		return;
+
+	/* Create a copy of the pending_free_dma_bufs while holding the lock */
+	spin_lock_irqsave(&dma_bufs_lock, flags);
+	list_cut_position(&tmp_list, &pending_free_dma_bufs,
+			  pending_free_dma_bufs.prev);
+	spin_unlock_irqrestore(&dma_bufs_lock, flags);
+
+	/* Release the dma buffers, without irqs enabled */
+	list_for_each_entry_safe(buf, tmp, &tmp_list, list) {
+		list_del(&buf->list);
+		free_buf(buf, true);
+	}
+}
+
+static struct port_buffer *alloc_buf(struct virtqueue *vq, size_t buf_size,
+				     int pages)
 {
 	struct port_buffer *buf;
 
-	buf = kmalloc(sizeof(*buf), GFP_KERNEL);
+	reclaim_dma_bufs();
+
+	/*
+	 * Allocate buffer and the sg list. The sg list array is allocated
+	 * directly after the port_buffer struct.
+	 */
+	buf = kmalloc(sizeof(*buf) + sizeof(struct scatterlist) * pages,
+		      GFP_KERNEL);
 	if (!buf)
 		goto fail;
-	buf->buf = kzalloc(buf_size, GFP_KERNEL);
+
+	buf->sgpages = pages;
+	if (pages > 0) {
+		buf->dev = NULL;
+		buf->buf = NULL;
+		return buf;
+	}
+
+	if (is_rproc_serial(vq->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.
+		 * The code here would have been less quirky if
+		 * DMA_MEMORY_INCLUDES_CHILDREN had been supported
+		 * in dma-coherent.c
+		 */
+		if (!vq->vdev->dev.parent || !vq->vdev->dev.parent->parent)
+			goto free_buf;
+		buf->dev = vq->vdev->dev.parent->parent;
+
+		/* Increase device refcnt to avoid freeing it */
+		get_device(buf->dev);
+		buf->buf = dma_alloc_coherent(buf->dev, buf_size, &buf->dma,
+					      GFP_KERNEL);
+	} else {
+		buf->dev = NULL;
+		buf->buf = kmalloc(buf_size, GFP_KERNEL);
+	}
+
 	if (!buf->buf)
 		goto free_buf;
 	buf->len = 0;
@@ -396,6 +510,8 @@ static int add_inbuf(struct virtqueue *vq, struct port_buffer *buf)
 
 	ret = virtqueue_add_buf(vq, sg, 0, 1, buf, GFP_ATOMIC);
 	virtqueue_kick(vq);
+	if (!ret)
+		ret = vq->num_free;
 	return ret;
 }
 
@@ -416,7 +532,7 @@ static void discard_port_data(struct port *port)
 		port->stats.bytes_discarded += buf->len - buf->offset;
 		if (add_inbuf(port->in_vq, buf) < 0) {
 			err++;
-			free_buf(buf);
+			free_buf(buf, false);
 		}
 		port->inbuf = NULL;
 		buf = get_inbuf(port);
@@ -459,7 +575,7 @@ static ssize_t __send_control_msg(struct ports_device *portdev, u32 port_id,
 	vq = portdev->c_ovq;
 
 	sg_init_one(sg, &cpkt, sizeof(cpkt));
-	if (virtqueue_add_buf(vq, sg, 1, 0, &cpkt, GFP_ATOMIC) >= 0) {
+	if (virtqueue_add_buf(vq, sg, 1, 0, &cpkt, GFP_ATOMIC) == 0) {
 		virtqueue_kick(vq);
 		while (!virtqueue_get_buf(vq, &len))
 			cpu_relax();
@@ -476,55 +592,29 @@ static ssize_t send_control_msg(struct port *port, unsigned int event,
 	return 0;
 }
 
-struct buffer_token {
-	union {
-		void *buf;
-		struct scatterlist *sg;
-	} u;
-	/* If sgpages == 0 then buf is used, else sg is used */
-	unsigned int sgpages;
-};
-
-static void reclaim_sg_pages(struct scatterlist *sg, unsigned int nrpages)
-{
-	int i;
-	struct page *page;
-
-	for (i = 0; i < nrpages; i++) {
-		page = sg_page(&sg[i]);
-		if (!page)
-			break;
-		put_page(page);
-	}
-	kfree(sg);
-}
 
 /* Callers must take the port->outvq_lock */
 static void reclaim_consumed_buffers(struct port *port)
 {
-	struct buffer_token *tok;
+	struct port_buffer *buf;
 	unsigned int len;
 
 	if (!port->portdev) {
 		/* Device has been unplugged.  vqs are already gone. */
 		return;
 	}
-	while ((tok = virtqueue_get_buf(port->out_vq, &len))) {
-		if (tok->sgpages)
-			reclaim_sg_pages(tok->u.sg, tok->sgpages);
-		else
-			kfree(tok->u.buf);
-		kfree(tok);
+	while ((buf = virtqueue_get_buf(port->out_vq, &len))) {
+		free_buf(buf, false);
 		port->outvq_full = false;
 	}
 }
 
 static ssize_t __send_to_port(struct port *port, struct scatterlist *sg,
 			      int nents, size_t in_count,
-			      struct buffer_token *tok, bool nonblock)
+			      void *data, bool nonblock)
 {
 	struct virtqueue *out_vq;
-	ssize_t ret;
+	int err;
 	unsigned long flags;
 	unsigned int len;
 
@@ -534,17 +624,17 @@ static ssize_t __send_to_port(struct port *port, struct scatterlist *sg,
 
 	reclaim_consumed_buffers(port);
 
-	ret = virtqueue_add_buf(out_vq, sg, nents, 0, tok, GFP_ATOMIC);
+	err = virtqueue_add_buf(out_vq, sg, nents, 0, data, GFP_ATOMIC);
 
 	/* Tell Host to go! */
 	virtqueue_kick(out_vq);
 
-	if (ret < 0) {
+	if (err) {
 		in_count = 0;
 		goto done;
 	}
 
-	if (ret == 0)
+	if (out_vq->num_free == 0)
 		port->outvq_full = true;
 
 	if (nonblock)
@@ -572,37 +662,6 @@ static ssize_t __send_to_port(struct port *port, struct scatterlist *sg,
 	return in_count;
 }
 
-static ssize_t send_buf(struct port *port, void *in_buf, size_t in_count,
-			bool nonblock)
-{
-	struct scatterlist sg[1];
-	struct buffer_token *tok;
-
-	tok = kmalloc(sizeof(*tok), GFP_ATOMIC);
-	if (!tok)
-		return -ENOMEM;
-	tok->sgpages = 0;
-	tok->u.buf = in_buf;
-
-	sg_init_one(sg, in_buf, in_count);
-
-	return __send_to_port(port, sg, 1, in_count, tok, nonblock);
-}
-
-static ssize_t send_pages(struct port *port, struct scatterlist *sg, int nents,
-			  size_t in_count, bool nonblock)
-{
-	struct buffer_token *tok;
-
-	tok = kmalloc(sizeof(*tok), GFP_ATOMIC);
-	if (!tok)
-		return -ENOMEM;
-	tok->sgpages = nents;
-	tok->u.sg = sg;
-
-	return __send_to_port(port, sg, nents, in_count, tok, nonblock);
-}
-
 /*
  * Give out the data that's requested from the buffer that we have
  * queued up.
@@ -748,9 +807,10 @@ static ssize_t port_fops_write(struct file *filp, const char __user *ubuf,
 			       size_t count, loff_t *offp)
 {
 	struct port *port;
-	char *buf;
+	struct port_buffer *buf;
 	ssize_t ret;
 	bool nonblock;
+	struct scatterlist sg[1];
 
 	/* Userspace could be out to fool us */
 	if (!count)
@@ -766,11 +826,11 @@ static ssize_t port_fops_write(struct file *filp, const char __user *ubuf,
 
 	count = min((size_t)(32 * 1024), count);
 
-	buf = kmalloc(count, GFP_KERNEL);
+	buf = alloc_buf(port->out_vq, count, 0);
 	if (!buf)
 		return -ENOMEM;
 
-	ret = copy_from_user(buf, ubuf, count);
+	ret = copy_from_user(buf->buf, ubuf, count);
 	if (ret) {
 		ret = -EFAULT;
 		goto free_buf;
@@ -784,13 +844,14 @@ static ssize_t port_fops_write(struct file *filp, const char __user *ubuf,
 	 * through to the host.
 	 */
 	nonblock = true;
-	ret = send_buf(port, buf, count, nonblock);
+	sg_init_one(sg, buf->buf, count);
+	ret = __send_to_port(port, sg, 1, count, buf, nonblock);
 
 	if (nonblock && ret > 0)
 		goto out;
 
 free_buf:
-	kfree(buf);
+	free_buf(buf, true);
 out:
 	return ret;
 }
@@ -856,6 +917,7 @@ static ssize_t port_fops_splice_write(struct pipe_inode_info *pipe,
 	struct port *port = filp->private_data;
 	struct sg_list sgl;
 	ssize_t ret;
+	struct port_buffer *buf;
 	struct splice_desc sd = {
 		.total_len = len,
 		.flags = flags,
@@ -863,22 +925,34 @@ static ssize_t port_fops_splice_write(struct pipe_inode_info *pipe,
 		.u.data = &sgl,
 	};
 
+	/*
+	 * Rproc_serial does not yet support splice. To support splice
+	 * pipe_to_sg() must allocate dma-buffers and copy content from
+	 * regular pages to dma pages. And alloc_buf and free_buf must
+	 * support allocating and freeing such a list of dma-buffers.
+	 */
+	if (is_rproc_serial(port->out_vq->vdev))
+		return -EINVAL;
+
 	ret = wait_port_writable(port, filp->f_flags & O_NONBLOCK);
 	if (ret < 0)
 		return ret;
 
+	buf = alloc_buf(port->out_vq, 0, pipe->nrbufs);
+	if (!buf)
+		return -ENOMEM;
+
 	sgl.n = 0;
 	sgl.len = 0;
 	sgl.size = pipe->nrbufs;
-	sgl.sg = kmalloc(sizeof(struct scatterlist) * sgl.size, GFP_KERNEL);
-	if (unlikely(!sgl.sg))
-		return -ENOMEM;
-
+	sgl.sg = buf->sg;
 	sg_init_table(sgl.sg, sgl.size);
 	ret = __splice_from_pipe(pipe, &sd, pipe_to_sg);
 	if (likely(ret > 0))
-		ret = send_pages(port, sgl.sg, sgl.n, sgl.len, true);
+		ret = __send_to_port(port, buf->sg, sgl.n, sgl.len, buf, true);
 
+	if (unlikely(ret <= 0))
+		free_buf(buf, true);
 	return ret;
 }
 
@@ -927,6 +1001,7 @@ static int port_fops_release(struct inode *inode, struct file *filp)
 	reclaim_consumed_buffers(port);
 	spin_unlock_irq(&port->outvq_lock);
 
+	reclaim_dma_bufs();
 	/*
 	 * Locks aren't necessary here as a port can't be opened after
 	 * unplug, and if a port isn't unplugged, a kref would already
@@ -1031,6 +1106,7 @@ static const struct file_operations port_fops = {
 static int put_chars(u32 vtermno, const char *buf, int count)
 {
 	struct port *port;
+	struct scatterlist sg[1];
 
 	if (unlikely(early_put_chars))
 		return early_put_chars(vtermno, buf, count);
@@ -1039,7 +1115,8 @@ static int put_chars(u32 vtermno, const char *buf, int count)
 	if (!port)
 		return -EPIPE;
 
-	return send_buf(port, (void *)buf, count, false);
+	sg_init_one(sg, buf, count);
+	return __send_to_port(port, sg, 1, count, (void *)buf, false);
 }
 
 /*
@@ -1076,7 +1153,10 @@ static void resize_console(struct port *port)
 		return;
 
 	vdev = port->portdev->vdev;
-	if (virtio_has_feature(vdev, VIRTIO_CONSOLE_F_SIZE))
+
+	/* Don't test F_SIZE at all if we're rproc: not a valid feature! */
+	if (!is_rproc_serial(vdev) &&
+	    virtio_has_feature(vdev, VIRTIO_CONSOLE_F_SIZE))
 		hvc_resize(port->cons.hvc, port->cons.ws);
 }
 
@@ -1260,7 +1340,7 @@ static unsigned int fill_queue(struct virtqueue *vq, spinlock_t *lock)
 
 	nr_added_bufs = 0;
 	do {
-		buf = alloc_buf(PAGE_SIZE);
+		buf = alloc_buf(vq, PAGE_SIZE, 0);
 		if (!buf)
 			break;
 
@@ -1268,7 +1348,7 @@ static unsigned int fill_queue(struct virtqueue *vq, spinlock_t *lock)
 		ret = add_inbuf(vq, buf);
 		if (ret < 0) {
 			spin_unlock_irq(lock);
-			free_buf(buf);
+			free_buf(buf, true);
 			break;
 		}
 		nr_added_bufs++;
@@ -1356,10 +1436,18 @@ static int add_port(struct ports_device *portdev, u32 id)
 		goto free_device;
 	}
 
+	if (is_rproc_serial(port->portdev->vdev))
 		/*
-	 * If we're not using multiport support, this has to be a console port
+		 * For rproc_serial assume remote processor is connected.
+		 * rproc_serial does not want the console port, only
+		 * the generic port implementation.
+		 */
+		port->host_connected = true;
+	else if (!use_multiport(port->portdev)) {
+		/*
+		 * If we're not using multiport support,
+		 * this has to be a console port.
 		 */
-	if (!use_multiport(port->portdev)) {
 		err = init_port_console(port);
 		if (err)
 			goto free_inbufs;
@@ -1392,7 +1480,7 @@ static int add_port(struct ports_device *portdev, u32 id)
 
 free_inbufs:
 	while ((buf = virtqueue_detach_unused_buf(port->in_vq)))
-		free_buf(buf);
+		free_buf(buf, true);
 free_device:
 	device_destroy(pdrvdata.class, port->dev->devt);
 free_cdev:
@@ -1434,7 +1522,11 @@ static void remove_port_data(struct port *port)
 
 	/* Remove buffers we queued up for the Host to send us data in. */
 	while ((buf = virtqueue_detach_unused_buf(port->in_vq)))
-		free_buf(buf);
+		free_buf(buf, true);
+
+	/* Free pending buffers from the out-queue. */
+	while ((buf = virtqueue_detach_unused_buf(port->out_vq)))
+		free_buf(buf, true);
 }
 
 /*
@@ -1636,7 +1728,7 @@ static void control_work_handler(struct work_struct *work)
 		if (add_inbuf(portdev->c_ivq, buf) < 0) {
 			dev_warn(&portdev->vdev->dev,
 				 "Error adding buffer to queue\n");
-			free_buf(buf);
+			free_buf(buf, false);
 		}
 	}
 	spin_unlock(&portdev->cvq_lock);
@@ -1832,10 +1924,10 @@ static void remove_controlq_data(struct ports_device *portdev)
 		return;
 
 	while ((buf = virtqueue_get_buf(portdev->c_ivq, &len)))
-		free_buf(buf);
+		free_buf(buf, true);
 
 	while ((buf = virtqueue_detach_unused_buf(portdev->c_ivq)))
-		free_buf(buf);
+		free_buf(buf, true);
 }
 
 /*
@@ -1882,11 +1974,15 @@ static int virtcons_probe(struct virtio_device *vdev)
 
 	multiport = false;
 	portdev->config.max_nr_ports = 1;
-	if (virtio_config_val(vdev, VIRTIO_CONSOLE_F_MULTIPORT,
+
+	/* Don't test MULTIPORT at all if we're rproc: not a valid feature! */
+	if (!is_rproc_serial(vdev) &&
+	    virtio_config_val(vdev, VIRTIO_CONSOLE_F_MULTIPORT,
 				  offsetof(struct virtio_console_config,
 					   max_nr_ports),
-			      &portdev->config.max_nr_ports) == 0)
+				  &portdev->config.max_nr_ports) == 0) {
 		multiport = true;
+	}
 
 	err = init_vqs(portdev);
 	if (err < 0) {
@@ -1996,6 +2092,16 @@ static unsigned int features[] = {
 	VIRTIO_CONSOLE_F_MULTIPORT,
 };
 
+static struct virtio_device_id rproc_serial_id_table[] = {
+#if IS_ENABLED(CONFIG_REMOTEPROC)
+	{ VIRTIO_ID_RPROC_SERIAL, VIRTIO_DEV_ANY_ID },
+#endif
+	{ 0 },
+};
+
+static unsigned int rproc_serial_features[] = {
+};
+
 #ifdef CONFIG_PM
 static int virtcons_freeze(struct virtio_device *vdev)
 {
@@ -2080,6 +2186,20 @@ static struct virtio_driver virtio_console = {
 #endif
 };
 
+/*
+ * virtio_rproc_serial refers to __devinit function which causes
+ * section mismatch warnings. So use __refdata to silence warnings.
+ */
+static struct virtio_driver __refdata virtio_rproc_serial = {
+	.feature_table = rproc_serial_features,
+	.feature_table_size = ARRAY_SIZE(rproc_serial_features),
+	.driver.name =	"virtio_rproc_serial",
+	.driver.owner =	THIS_MODULE,
+	.id_table =	rproc_serial_id_table,
+	.probe =	virtcons_probe,
+	.remove =	virtcons_remove,
+};
+
 static int __init init(void)
 {
 	int err;
@@ -2104,7 +2224,15 @@ static int __init init(void)
 		pr_err("Error %d registering virtio driver\n", err);
 		goto free;
 	}
+	err = register_virtio_driver(&virtio_rproc_serial);
+	if (err < 0) {
+		pr_err("Error %d registering virtio rproc serial driver\n",
+		       err);
+		goto unregister;
+	}
 	return 0;
+unregister:
+	unregister_virtio_driver(&virtio_console);
 free:
 	if (pdrvdata.debugfs_dir)
 		debugfs_remove_recursive(pdrvdata.debugfs_dir);
@@ -2114,7 +2242,10 @@ static int __init init(void)
 
 static void __exit fini(void)
 {
+	reclaim_dma_bufs();
+
 	unregister_virtio_driver(&virtio_console);
+	unregister_virtio_driver(&virtio_rproc_serial);
 
 	class_destroy(pdrvdata.class);
 	if (pdrvdata.debugfs_dir)

drivers/lguest/core.c

@@ -225,7 +225,7 @@ int run_guest(struct lg_cpu *cpu, unsigned long __user *user)
 			 * eventfd (ie. the appropriate virtqueue thread)?
 			 */
 			if (!send_notify_to_eventfd(cpu)) {
-				/* OK, we tell the main Laucher. */
+				/* OK, we tell the main Launcher. */
 				if (put_user(cpu->pending_notify, user))
 					return -EFAULT;
 				return sizeof(cpu->pending_notify);

drivers/net/virtio_net.c

@@ -130,7 +130,6 @@ struct skb_vnet_hdr {
 		struct virtio_net_hdr hdr;
 		struct virtio_net_hdr_mrg_rxbuf mhdr;
 	};
-	unsigned int num_sg;
 };
 
 struct padded_vnet_hdr {
@@ -530,10 +529,10 @@ static bool try_fill_recv(struct receive_queue *rq, gfp_t gfp)
 			err = add_recvbuf_small(rq, gfp);
 
 		oom = err == -ENOMEM;
-		if (err < 0)
+		if (err)
 			break;
 		++rq->num;
-	} while (err > 0);
+	} while (rq->vq->num_free);
 	if (unlikely(rq->num > rq->max))
 		rq->max = rq->num;
 	virtqueue_kick(rq->vq);
@@ -640,10 +639,10 @@ static int virtnet_open(struct net_device *dev)
 	return 0;
 }
 
-static unsigned int free_old_xmit_skbs(struct send_queue *sq)
+static void free_old_xmit_skbs(struct send_queue *sq)
 {
 	struct sk_buff *skb;
-	unsigned int len, tot_sgs = 0;
+	unsigned int len;
 	struct virtnet_info *vi = sq->vq->vdev->priv;
 	struct virtnet_stats *stats = this_cpu_ptr(vi->stats);
 
@@ -655,10 +654,8 @@ static unsigned int free_old_xmit_skbs(struct send_queue *sq)
 		stats->tx_packets++;
 		u64_stats_update_end(&stats->tx_syncp);
 
-		tot_sgs += skb_vnet_hdr(skb)->num_sg;
 		dev_kfree_skb_any(skb);
 	}
-	return tot_sgs;
 }
 
 static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
@@ -666,6 +663,7 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
 	struct skb_vnet_hdr *hdr = skb_vnet_hdr(skb);
 	const unsigned char *dest = ((struct ethhdr *)skb->data)->h_dest;
 	struct virtnet_info *vi = sq->vq->vdev->priv;
+	unsigned num_sg;
 
 	pr_debug("%s: xmit %p %pM\n", vi->dev->name, skb, dest);
 
@@ -704,8 +702,8 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
 	else
 		sg_set_buf(sq->sg, &hdr->hdr, sizeof hdr->hdr);
 
-	hdr->num_sg = skb_to_sgvec(skb, sq->sg + 1, 0, skb->len) + 1;
-	return virtqueue_add_buf(sq->vq, sq->sg, hdr->num_sg,
+	num_sg = skb_to_sgvec(skb, sq->sg + 1, 0, skb->len) + 1;
+	return virtqueue_add_buf(sq->vq, sq->sg, num_sg,
 				 0, skb, GFP_ATOMIC);
 }
 
@@ -714,28 +712,20 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct virtnet_info *vi = netdev_priv(dev);
 	int qnum = skb_get_queue_mapping(skb);
 	struct send_queue *sq = &vi->sq[qnum];
-	int capacity;
+	int err;
 
 	/* Free up any pending old buffers before queueing new ones. */
 	free_old_xmit_skbs(sq);
 
 	/* Try to transmit */
-	capacity = xmit_skb(sq, skb);
+	err = xmit_skb(sq, skb);
 
-	/* This can happen with OOM and indirect buffers. */
-	if (unlikely(capacity < 0)) {
-		if (likely(capacity == -ENOMEM)) {
-			if (net_ratelimit())
-				dev_warn(&dev->dev,
-					 "TXQ (%d) failure: out of memory\n",
-					 qnum);
-		} else {
+	/* This should not happen! */
+	if (unlikely(err)) {
 		dev->stats.tx_fifo_errors++;
 		if (net_ratelimit())
 			dev_warn(&dev->dev,
-					 "Unexpected TXQ (%d) failure: %d\n",
-					 qnum, capacity);
-		}
+				 "Unexpected TXQ (%d) queue failure: %d\n", qnum, err);
 		dev->stats.tx_dropped++;
 		kfree_skb(skb);
 		return NETDEV_TX_OK;
@@ -748,12 +738,12 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	/* Apparently nice girls don't return TX_BUSY; stop the queue
 	 * before it gets out of hand.  Naturally, this wastes entries. */
-	if (capacity < 2+MAX_SKB_FRAGS) {
+	if (sq->vq->num_free < 2+MAX_SKB_FRAGS) {
 		netif_stop_subqueue(dev, qnum);
 		if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) {
 			/* More just got used, free them then recheck. */
-			capacity += free_old_xmit_skbs(sq);
-			if (capacity >= 2+MAX_SKB_FRAGS) {
+			free_old_xmit_skbs(sq);
+			if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) {
 				netif_start_subqueue(dev, qnum);
 				virtqueue_disable_cb(sq->vq);
 			}

drivers/rpmsg/virtio_rpmsg_bus.c

@@ -764,7 +764,7 @@ int rpmsg_send_offchannel_raw(struct rpmsg_channel *rpdev, u32 src, u32 dst,
 
 	/* add message to the remote processor's virtqueue */
 	err = virtqueue_add_buf(vrp->svq, &sg, 1, 0, msg, GFP_KERNEL);
-	if (err < 0) {
+	if (err) {
 		/*
 		 * need to reclaim the buffer here, otherwise it's lost
 		 * (memory won't leak, but rpmsg won't use it again for TX).
@@ -776,8 +776,6 @@ int rpmsg_send_offchannel_raw(struct rpmsg_channel *rpdev, u32 src, u32 dst,
 
 	/* tell the remote processor it has a pending message to read */
 	virtqueue_kick(vrp->svq);
-
-	err = 0;
 out:
 	mutex_unlock(&vrp->tx_lock);
 	return err;
@@ -980,7 +978,7 @@ static int rpmsg_probe(struct virtio_device *vdev)
 
 		err = virtqueue_add_buf(vrp->rvq, &sg, 0, 1, cpu_addr,
 								GFP_KERNEL);
-		WARN_ON(err < 0); /* sanity check; this can't really happen */
+		WARN_ON(err); /* sanity check; this can't really happen */
 	}
 
 	/* suppress "tx-complete" interrupts */

drivers/scsi/virtio_scsi.c

@@ -215,7 +215,7 @@ static void virtscsi_ctrl_done(struct virtqueue *vq)
 static int virtscsi_kick_event(struct virtio_scsi *vscsi,
 			       struct virtio_scsi_event_node *event_node)
 {
-	int ret;
+	int err;
 	struct scatterlist sg;
 	unsigned long flags;
 
@@ -223,13 +223,14 @@ static int virtscsi_kick_event(struct virtio_scsi *vscsi,
 
 	spin_lock_irqsave(&vscsi->event_vq.vq_lock, flags);
 
-	ret = virtqueue_add_buf(vscsi->event_vq.vq, &sg, 0, 1, event_node, GFP_ATOMIC);
-	if (ret >= 0)
+	err = virtqueue_add_buf(vscsi->event_vq.vq, &sg, 0, 1, event_node,
+				GFP_ATOMIC);
+	if (!err)
 		virtqueue_kick(vscsi->event_vq.vq);
 
 	spin_unlock_irqrestore(&vscsi->event_vq.vq_lock, flags);
 
-	return ret;
+	return err;
 }
 
 static int virtscsi_kick_event_all(struct virtio_scsi *vscsi)
@@ -410,22 +411,23 @@ static int virtscsi_kick_cmd(struct virtio_scsi_target_state *tgt,
 {
 	unsigned int out_num, in_num;
 	unsigned long flags;
-	int ret;
+	int err;
+	bool needs_kick = false;
 
 	spin_lock_irqsave(&tgt->tgt_lock, flags);
 	virtscsi_map_cmd(tgt, cmd, &out_num, &in_num, req_size, resp_size);
 
 	spin_lock(&vq->vq_lock);
-	ret = virtqueue_add_buf(vq->vq, tgt->sg, out_num, in_num, cmd, gfp);
+	err = virtqueue_add_buf(vq->vq, tgt->sg, out_num, in_num, cmd, gfp);
 	spin_unlock(&tgt->tgt_lock);
-	if (ret >= 0)
-		ret = virtqueue_kick_prepare(vq->vq);
+	if (!err)
+		needs_kick = virtqueue_kick_prepare(vq->vq);
 
 	spin_unlock_irqrestore(&vq->vq_lock, flags);
 
-	if (ret > 0)
+	if (needs_kick)
 		virtqueue_notify(vq->vq);
-	return ret;
+	return err;
 }
 
 static int virtscsi_queuecommand(struct Scsi_Host *sh, struct scsi_cmnd *sc)
@@ -467,7 +469,7 @@ static int virtscsi_queuecommand(struct Scsi_Host *sh, struct scsi_cmnd *sc)
 
 	if (virtscsi_kick_cmd(tgt, &vscsi->req_vq, cmd,
 			      sizeof cmd->req.cmd, sizeof cmd->resp.cmd,
-			      GFP_ATOMIC) >= 0)
+			      GFP_ATOMIC) == 0)
 		ret = 0;
 	else
 		mempool_free(cmd, virtscsi_cmd_pool);

drivers/virtio/virtio.c

@@ -10,33 +10,32 @@ static DEFINE_IDA(virtio_index_ida);
 static ssize_t device_show(struct device *_d,
 			   struct device_attribute *attr, char *buf)
 {
-	struct virtio_device *dev = container_of(_d,struct virtio_device,dev);
+	struct virtio_device *dev = dev_to_virtio(_d);
 	return sprintf(buf, "0x%04x\n", dev->id.device);
 }
 static ssize_t vendor_show(struct device *_d,
 			   struct device_attribute *attr, char *buf)
 {
-	struct virtio_device *dev = container_of(_d,struct virtio_device,dev);
+	struct virtio_device *dev = dev_to_virtio(_d);
 	return sprintf(buf, "0x%04x\n", dev->id.vendor);
 }
 static ssize_t status_show(struct device *_d,
 			   struct device_attribute *attr, char *buf)
 {
-	struct virtio_device *dev = container_of(_d,struct virtio_device,dev);
+	struct virtio_device *dev = dev_to_virtio(_d);
 	return sprintf(buf, "0x%08x\n", dev->config->get_status(dev));
 }
 static ssize_t modalias_show(struct device *_d,
 			     struct device_attribute *attr, char *buf)
 {
-	struct virtio_device *dev = container_of(_d,struct virtio_device,dev);
-
+	struct virtio_device *dev = dev_to_virtio(_d);
 	return sprintf(buf, "virtio:d%08Xv%08X\n",
 		       dev->id.device, dev->id.vendor);
 }
 static ssize_t features_show(struct device *_d,
 			     struct device_attribute *attr, char *buf)
 {
-	struct virtio_device *dev = container_of(_d, struct virtio_device, dev);
+	struct virtio_device *dev = dev_to_virtio(_d);
 	unsigned int i;
 	ssize_t len = 0;
 
@@ -71,10 +70,10 @@ static inline int virtio_id_match(const struct virtio_device *dev,
 static int virtio_dev_match(struct device *_dv, struct device_driver *_dr)
 {
 	unsigned int i;
-	struct virtio_device *dev = container_of(_dv,struct virtio_device,dev);
+	struct virtio_device *dev = dev_to_virtio(_dv);
 	const struct virtio_device_id *ids;
 
-	ids = container_of(_dr, struct virtio_driver, driver)->id_table;
+	ids = drv_to_virtio(_dr)->id_table;
 	for (i = 0; ids[i].device; i++)
 		if (virtio_id_match(dev, &ids[i]))
 			return 1;
@@ -83,7 +82,7 @@ static int virtio_dev_match(struct device *_dv, struct device_driver *_dr)
 
 static int virtio_uevent(struct device *_dv, struct kobj_uevent_env *env)
 {
-	struct virtio_device *dev = container_of(_dv,struct virtio_device,dev);
+	struct virtio_device *dev = dev_to_virtio(_dv);
 
 	return add_uevent_var(env, "MODALIAS=virtio:d%08Xv%08X",
 			      dev->id.device, dev->id.vendor);
@@ -98,8 +97,7 @@ void virtio_check_driver_offered_feature(const struct virtio_device *vdev,
 					 unsigned int fbit)
 {
 	unsigned int i;
-	struct virtio_driver *drv = container_of(vdev->dev.driver,
-						 struct virtio_driver, driver);
+	struct virtio_driver *drv = drv_to_virtio(vdev->dev.driver);
 
 	for (i = 0; i < drv->feature_table_size; i++)
 		if (drv->feature_table[i] == fbit)
@@ -111,9 +109,8 @@ EXPORT_SYMBOL_GPL(virtio_check_driver_offered_feature);
 static int virtio_dev_probe(struct device *_d)
 {
 	int err, i;
-	struct virtio_device *dev = container_of(_d,struct virtio_device,dev);
-	struct virtio_driver *drv = container_of(dev->dev.driver,
-						 struct virtio_driver, driver);
+	struct virtio_device *dev = dev_to_virtio(_d);
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
 	u32 device_features;
 
 	/* We have a driver! */
@@ -152,9 +149,8 @@ static int virtio_dev_probe(struct device *_d)
 
 static int virtio_dev_remove(struct device *_d)
 {
-	struct virtio_device *dev = container_of(_d,struct virtio_device,dev);
-	struct virtio_driver *drv = container_of(dev->dev.driver,
-						 struct virtio_driver, driver);
+	struct virtio_device *dev = dev_to_virtio(_d);
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
 
 	drv->remove(dev);
 

drivers/virtio/virtio_balloon.c

@@ -139,8 +139,7 @@ static void fill_balloon(struct virtio_balloon *vb, size_t num)
 		struct page *page = balloon_page_enqueue(vb_dev_info);
 
 		if (!page) {
-			if (printk_ratelimit())
-				dev_printk(KERN_INFO, &vb->vdev->dev,
+			dev_info_ratelimited(&vb->vdev->dev,
 					     "Out of puff! Can't get %u pages\n",
 					     VIRTIO_BALLOON_PAGES_PER_PAGE);
 			/* Sleep for at least 1/5 of a second before retry. */

drivers/virtio/virtio_mmio.c

@@ -225,7 +225,7 @@ static void vm_notify(struct virtqueue *vq)
 
 	/* We write the queue's selector into the notification register to
 	 * signal the other end */
-	writel(virtqueue_get_queue_index(vq), vm_dev->base + VIRTIO_MMIO_QUEUE_NOTIFY);
+	writel(vq->index, vm_dev->base + VIRTIO_MMIO_QUEUE_NOTIFY);
 }
 
 /* Notify all virtqueues on an interrupt. */
@@ -266,7 +266,7 @@ static void vm_del_vq(struct virtqueue *vq)
 	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vq->vdev);
 	struct virtio_mmio_vq_info *info = vq->priv;
 	unsigned long flags, size;
-	unsigned int index = virtqueue_get_queue_index(vq);
+	unsigned int index = vq->index;
 
 	spin_lock_irqsave(&vm_dev->lock, flags);
 	list_del(&info->node);
@@ -521,25 +521,33 @@ static int vm_cmdline_set(const char *device,
 	int err;
 	struct resource resources[2] = {};
 	char *str;
-	long long int base;
+	long long int base, size;
+	unsigned int irq;
 	int processed, consumed = 0;
 	struct platform_device *pdev;
 
-	resources[0].flags = IORESOURCE_MEM;
-	resources[1].flags = IORESOURCE_IRQ;
-
-	resources[0].end = memparse(device, &str) - 1;
+	/* Consume "size" part of the command line parameter */
+	size = memparse(device, &str);
 
+	/* Get "@<base>:<irq>[:<id>]" chunks */
 	processed = sscanf(str, "@%lli:%u%n:%d%n",
-			&base, &resources[1].start, &consumed,
+			&base, &irq, &consumed,
 			&vm_cmdline_id, &consumed);
 
-	if (processed < 2 || processed > 3 || str[consumed])
+	/*
+	 * sscanf() must processes at least 2 chunks; also there
+	 * must be no extra characters after the last chunk, so
+	 * str[consumed] must be '\0'
+	 */
+	if (processed < 2 || str[consumed])
 		return -EINVAL;
 
+	resources[0].flags = IORESOURCE_MEM;
 	resources[0].start = base;
-	resources[0].end += base;
-	resources[1].end = resources[1].start;
+	resources[0].end = base + size - 1;
+
+	resources[1].flags = IORESOURCE_IRQ;
+	resources[1].start = resources[1].end = irq;
 
 	if (!vm_cmdline_parent_registered) {
 		err = device_register(&vm_cmdline_parent);

drivers/virtio/virtio_pci.c

@@ -203,8 +203,7 @@ static void vp_notify(struct virtqueue *vq)
 
 	/* we write the queue's selector into the notification register to
 	 * signal the other end */
-	iowrite16(virtqueue_get_queue_index(vq),
-		  vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY);
+	iowrite16(vq->index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY);
 }
 
 /* Handle a configuration change: Tell driver if it wants to know. */
@@ -479,8 +478,7 @@ static void vp_del_vq(struct virtqueue *vq)
 	list_del(&info->node);
 	spin_unlock_irqrestore(&vp_dev->lock, flags);
 
-	iowrite16(virtqueue_get_queue_index(vq),
-		vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
+	iowrite16(vq->index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
 
 	if (vp_dev->msix_enabled) {
 		iowrite16(VIRTIO_MSI_NO_VECTOR,
@@ -830,16 +828,4 @@ static struct pci_driver virtio_pci_driver = {
 #endif
 };
 
-static int __init virtio_pci_init(void)
-{
-	return pci_register_driver(&virtio_pci_driver);
-}
-
-module_init(virtio_pci_init);
-
-static void __exit virtio_pci_exit(void)
-{
-	pci_unregister_driver(&virtio_pci_driver);
-}
-
-module_exit(virtio_pci_exit);
+module_pci_driver(virtio_pci_driver);

drivers/virtio/virtio_ring.c

@@ -93,8 +93,6 @@ struct vring_virtqueue
 	/* Host publishes avail event idx */
 	bool event;
 
-	/* Number of free buffers */
-	unsigned int num_free;
 	/* Head of free buffer list. */
 	unsigned int free_head;
 	/* Number we've added since last sync. */
@@ -106,9 +104,6 @@ struct vring_virtqueue
 	/* How to notify other side. FIXME: commonalize hcalls! */
 	void (*notify)(struct virtqueue *vq);
 
-	/* Index of the queue */
-	int queue_index;
-
 #ifdef DEBUG
 	/* They're supposed to lock for us. */
 	unsigned int in_use;
@@ -135,6 +130,13 @@ static int vring_add_indirect(struct vring_virtqueue *vq,
 	unsigned head;
 	int i;
 
+	/*
+	 * We require lowmem mappings for the descriptors because
+	 * otherwise virt_to_phys will give us bogus addresses in the
+	 * virtqueue.
+	 */
+	gfp &= ~(__GFP_HIGHMEM | __GFP_HIGH);
+
 	desc = kmalloc((out + in) * sizeof(struct vring_desc), gfp);
 	if (!desc)
 		return -ENOMEM;
@@ -160,7 +162,7 @@ static int vring_add_indirect(struct vring_virtqueue *vq,
 	desc[i-1].next = 0;
 
 	/* We're about to use a buffer */
-	vq->num_free--;
+	vq->vq.num_free--;
 
 	/* Use a single buffer which doesn't continue */
 	head = vq->free_head;
@@ -174,13 +176,6 @@ static int vring_add_indirect(struct vring_virtqueue *vq,
 	return head;
 }
 
-int virtqueue_get_queue_index(struct virtqueue *_vq)
-{
-	struct vring_virtqueue *vq = to_vvq(_vq);
-	return vq->queue_index;
-}
-EXPORT_SYMBOL_GPL(virtqueue_get_queue_index);
-
 /**
  * virtqueue_add_buf - expose buffer to other end
  * @vq: the struct virtqueue we're talking about.
@@ -193,10 +188,7 @@ EXPORT_SYMBOL_GPL(virtqueue_get_queue_index);
  * Caller must ensure we don't call this with other virtqueue operations
  * at the same time (except where noted).
  *
- * Returns remaining capacity of queue or a negative error
- * (ie. ENOSPC).  Note that it only really makes sense to treat all
- * positive return values as "available": indirect buffers mean that
- * we can put an entire sg[] array inside a single queue entry.
+ * Returns zero or a negative error (ie. ENOSPC, ENOMEM).
  */
 int virtqueue_add_buf(struct virtqueue *_vq,
 		      struct scatterlist sg[],
@@ -228,7 +220,7 @@ int virtqueue_add_buf(struct virtqueue *_vq,
 
 	/* If the host supports indirect descriptor tables, and we have multiple
 	 * buffers, then go indirect. FIXME: tune this threshold */
-	if (vq->indirect && (out + in) > 1 && vq->num_free) {
+	if (vq->indirect && (out + in) > 1 && vq->vq.num_free) {
 		head = vring_add_indirect(vq, sg, out, in, gfp);
 		if (likely(head >= 0))
 			goto add_head;
@@ -237,9 +229,9 @@ int virtqueue_add_buf(struct virtqueue *_vq,
 	BUG_ON(out + in > vq->vring.num);
 	BUG_ON(out + in == 0);
 
-	if (vq->num_free < out + in) {
+	if (vq->vq.num_free < out + in) {
 		pr_debug("Can't add buf len %i - avail = %i\n",
-			 out + in, vq->num_free);
+			 out + in, vq->vq.num_free);
 		/* FIXME: for historical reasons, we force a notify here if
 		 * there are outgoing parts to the buffer.  Presumably the
 		 * host should service the ring ASAP. */
@@ -250,7 +242,7 @@ int virtqueue_add_buf(struct virtqueue *_vq,
 	}
 
 	/* We're about to use some buffers from the free list. */
-	vq->num_free -= out + in;
+	vq->vq.num_free -= out + in;
 
 	head = vq->free_head;
 	for (i = vq->free_head; out; i = vq->vring.desc[i].next, out--) {
@@ -296,7 +288,7 @@ int virtqueue_add_buf(struct virtqueue *_vq,
 	pr_debug("Added buffer head %i to %p\n", head, vq);
 	END_USE(vq);
 
-	return vq->num_free;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(virtqueue_add_buf);
 
@@ -393,13 +385,13 @@ static void detach_buf(struct vring_virtqueue *vq, unsigned int head)
 
 	while (vq->vring.desc[i].flags & VRING_DESC_F_NEXT) {
 		i = vq->vring.desc[i].next;
-		vq->num_free++;
+		vq->vq.num_free++;
 	}
 
 	vq->vring.desc[i].next = vq->free_head;
 	vq->free_head = head;
 	/* Plus final descriptor */
-	vq->num_free++;
+	vq->vq.num_free++;
 }
 
 static inline bool more_used(const struct vring_virtqueue *vq)
@@ -599,7 +591,7 @@ void *virtqueue_detach_unused_buf(struct virtqueue *_vq)
 		return buf;
 	}
 	/* That should have freed everything. */
-	BUG_ON(vq->num_free != vq->vring.num);
+	BUG_ON(vq->vq.num_free != vq->vring.num);
 
 	END_USE(vq);
 	return NULL;
@@ -653,12 +645,13 @@ struct virtqueue *vring_new_virtqueue(unsigned int index,
 	vq->vq.callback = callback;
 	vq->vq.vdev = vdev;
 	vq->vq.name = name;
+	vq->vq.num_free = num;
+	vq->vq.index = index;
 	vq->notify = notify;
 	vq->weak_barriers = weak_barriers;
 	vq->broken = false;
 	vq->last_used_idx = 0;
 	vq->num_added = 0;
-	vq->queue_index = index;
 	list_add_tail(&vq->vq.list, &vdev->vqs);
 #ifdef DEBUG
 	vq->in_use = false;
@@ -673,7 +666,6 @@ struct virtqueue *vring_new_virtqueue(unsigned int index,
 		vq->vring.avail->flags |= VRING_AVAIL_F_NO_INTERRUPT;
 
 	/* Put everything in free lists. */
-	vq->num_free = num;
 	vq->free_head = 0;
 	for (i = 0; i < num-1; i++) {
 		vq->vring.desc[i].next = i+1;

include/linux/virtio.h

@@ -16,12 +16,20 @@
  * @name: the name of this virtqueue (mainly for debugging)
  * @vdev: the virtio device this queue was created for.
  * @priv: a pointer for the virtqueue implementation to use.
+ * @index: the zero-based ordinal number for this queue.
+ * @num_free: number of elements we expect to be able to fit.
+ *
+ * A note on @num_free: with indirect buffers, each buffer needs one
+ * element in the queue, otherwise a buffer will need one element per
+ * sg element.
  */
 struct virtqueue {
 	struct list_head list;
 	void (*callback)(struct virtqueue *vq);
 	const char *name;
 	struct virtio_device *vdev;
+	unsigned int index;
+	unsigned int num_free;
 	void *priv;
 };
 
@@ -50,7 +58,11 @@ void *virtqueue_detach_unused_buf(struct virtqueue *vq);
 
 unsigned int virtqueue_get_vring_size(struct virtqueue *vq);
 
-int virtqueue_get_queue_index(struct virtqueue *vq);
+/* FIXME: Obsolete accessor, but required for virtio_net merge. */
+static inline unsigned int virtqueue_get_queue_index(struct virtqueue *vq)
+{
+	return vq->index;
+}
 
 /**
  * virtio_device - representation of a device using virtio
@@ -73,7 +85,11 @@ struct virtio_device {
 	void *priv;
 };
 
-#define dev_to_virtio(dev) container_of(dev, struct virtio_device, dev)
+static inline struct virtio_device *dev_to_virtio(struct device *_dev)
+{
+	return container_of(_dev, struct virtio_device, dev);
+}
+
 int register_virtio_device(struct virtio_device *dev);
 void unregister_virtio_device(struct virtio_device *dev);
 
@@ -103,6 +119,11 @@ struct virtio_driver {
 #endif
 };
 
+static inline struct virtio_driver *drv_to_virtio(struct device_driver *drv)
+{
+	return container_of(drv, struct virtio_driver, driver);
+}
+
 int register_virtio_driver(struct virtio_driver *drv);
 void unregister_virtio_driver(struct virtio_driver *drv);
 #endif /* _LINUX_VIRTIO_H */

include/linux/virtio_scsi.h

+/*
+ * This header is BSD licensed so anyone can use the definitions to implement
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY AUTHOR AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL AUTHOR OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ */
+
 #ifndef _LINUX_VIRTIO_SCSI_H
 #define _LINUX_VIRTIO_SCSI_H
-/* This header is BSD licensed so anyone can use the definitions to implement
- * compatible drivers/servers. */
 
 #define VIRTIO_SCSI_CDB_SIZE   32
 #define VIRTIO_SCSI_SENSE_SIZE 96

include/uapi/linux/virtio_ids.h

@@ -37,5 +37,6 @@
 #define VIRTIO_ID_RPMSG		7 /* virtio remote processor messaging */
 #define VIRTIO_ID_SCSI		8 /* virtio scsi */
 #define VIRTIO_ID_9P		9 /* 9p virtio console */
+#define VIRTIO_ID_RPROC_SERIAL 11 /* virtio remoteproc serial link */
 
 #endif /* _LINUX_VIRTIO_IDS_H */

mm/highmem.c

@@ -105,6 +105,7 @@ struct page *kmap_to_page(void *vaddr)
 
 	return virt_to_page(addr);
 }
+EXPORT_SYMBOL(kmap_to_page);
 
 static void flush_all_zero_pkmaps(void)
 {

net/9p/trans_virtio.c

@@ -39,6 +39,7 @@
 #include <linux/inet.h>
 #include <linux/idr.h>
 #include <linux/file.h>
+#include <linux/highmem.h>
 #include <linux/slab.h>
 #include <net/9p/9p.h>
 #include <linux/parser.h>
@@ -325,7 +326,7 @@ static int p9_get_mapped_pages(struct virtio_chan *chan,
 		int count = nr_pages;
 		while (nr_pages) {
 			s = rest_of_page(data);
-			pages[index++] = virt_to_page(data);
+			pages[index++] = kmap_to_page(data);
 			data += s;
 			nr_pages--;
 		}

tools/lguest/lguest.c

@@ -179,29 +179,6 @@ static struct termios orig_term;
 #define wmb() __asm__ __volatile__("" : : : "memory")
 #define mb() __asm__ __volatile__("" : : : "memory")
 
-/*
- * Convert an iovec element to the given type.
- *
- * This is a fairly ugly trick: we need to know the size of the type and
- * alignment requirement to check the pointer is kosher.  It's also nice to
- * have the name of the type in case we report failure.
- *
- * Typing those three things all the time is cumbersome and error prone, so we
- * have a macro which sets them all up and passes to the real function.
- */
-#define convert(iov, type) \
-	((type *)_convert((iov), sizeof(type), __alignof__(type), #type))
-
-static void *_convert(struct iovec *iov, size_t size, size_t align,
-		      const char *name)
-{
-	if (iov->iov_len != size)
-		errx(1, "Bad iovec size %zu for %s", iov->iov_len, name);
-	if ((unsigned long)iov->iov_base % align != 0)
-		errx(1, "Bad alignment %p for %s", iov->iov_base, name);
-	return iov->iov_base;
-}
-
 /* Wrapper for the last available index.  Makes it easier to change. */
 #define lg_last_avail(vq)	((vq)->last_avail_idx)
 
@@ -228,7 +205,8 @@ static bool iov_empty(const struct iovec iov[], unsigned int num_iov)
 }
 
 /* Take len bytes from the front of this iovec. */
-static void iov_consume(struct iovec iov[], unsigned num_iov, unsigned len)
+static void iov_consume(struct iovec iov[], unsigned num_iov,
+			void *dest, unsigned len)
 {
 	unsigned int i;
 
@@ -236,11 +214,16 @@ static void iov_consume(struct iovec iov[], unsigned num_iov, unsigned len)
 		unsigned int used;
 
 		used = iov[i].iov_len < len ? iov[i].iov_len : len;
+		if (dest) {
+			memcpy(dest, iov[i].iov_base, used);
+			dest += used;
+		}
 		iov[i].iov_base += used;
 		iov[i].iov_len -= used;
 		len -= used;
 	}
-	assert(len == 0);
+	if (len != 0)
+		errx(1, "iovec too short!");
 }
 
 /* The device virtqueue descriptors are followed by feature bitmasks. */
@@ -864,7 +847,7 @@ static void console_output(struct virtqueue *vq)
 			warn("Write to stdout gave %i (%d)", len, errno);
 			break;
 		}
-		iov_consume(iov, out, len);
+		iov_consume(iov, out, NULL, len);
 	}
 
 	/*
@@ -1591,9 +1574,9 @@ static void blk_request(struct virtqueue *vq)
 {
 	struct vblk_info *vblk = vq->dev->priv;
 	unsigned int head, out_num, in_num, wlen;
-	int ret;
+	int ret, i;
 	u8 *in;
-	struct virtio_blk_outhdr *out;
+	struct virtio_blk_outhdr out;
 	struct iovec iov[vq->vring.num];
 	off64_t off;
 
@@ -1603,32 +1586,36 @@ static void blk_request(struct virtqueue *vq)
 	 */
 	head = wait_for_vq_desc(vq, iov, &out_num, &in_num);
 
-	/*
-	 * Every block request should contain at least one output buffer
-	 * (detailing the location on disk and the type of request) and one
-	 * input buffer (to hold the result).
-	 */
-	if (out_num == 0 || in_num == 0)
-		errx(1, "Bad virtblk cmd %u out=%u in=%u",
-		     head, out_num, in_num);
+	/* Copy the output header from the front of the iov (adjusts iov) */
+	iov_consume(iov, out_num, &out, sizeof(out));
+
+	/* Find and trim end of iov input array, for our status byte. */
+	in = NULL;
+	for (i = out_num + in_num - 1; i >= out_num; i--) {
+		if (iov[i].iov_len > 0) {
+			in = iov[i].iov_base + iov[i].iov_len - 1;
+			iov[i].iov_len--;
+			break;
+		}
+	}
+	if (!in)
+		errx(1, "Bad virtblk cmd with no room for status");
 
-	out = convert(&iov[0], struct virtio_blk_outhdr);
-	in = convert(&iov[out_num+in_num-1], u8);
 	/*
 	 * For historical reasons, block operations are expressed in 512 byte
 	 * "sectors".
 	 */
-	off = out->sector * 512;
+	off = out.sector * 512;
 
 	/*
 	 * In general the virtio block driver is allowed to try SCSI commands.
 	 * It'd be nice if we supported eject, for example, but we don't.
 	 */
-	if (out->type & VIRTIO_BLK_T_SCSI_CMD) {
+	if (out.type & VIRTIO_BLK_T_SCSI_CMD) {
 		fprintf(stderr, "Scsi commands unsupported\n");
 		*in = VIRTIO_BLK_S_UNSUPP;
 		wlen = sizeof(*in);
-	} else if (out->type & VIRTIO_BLK_T_OUT) {
+	} else if (out.type & VIRTIO_BLK_T_OUT) {
 		/*
 		 * Write
 		 *
@@ -1636,10 +1623,10 @@ static void blk_request(struct virtqueue *vq)
 		 * if they try to write past end.
 		 */
 		if (lseek64(vblk->fd, off, SEEK_SET) != off)
-			err(1, "Bad seek to sector %llu", out->sector);
+			err(1, "Bad seek to sector %llu", out.sector);
 
-		ret = writev(vblk->fd, iov+1, out_num-1);
-		verbose("WRITE to sector %llu: %i\n", out->sector, ret);
+		ret = writev(vblk->fd, iov, out_num);
+		verbose("WRITE to sector %llu: %i\n", out.sector, ret);
 
 		/*
 		 * Grr... Now we know how long the descriptor they sent was, we
@@ -1655,7 +1642,7 @@ static void blk_request(struct virtqueue *vq)
 
 		wlen = sizeof(*in);
 		*in = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR);
-	} else if (out->type & VIRTIO_BLK_T_FLUSH) {
+	} else if (out.type & VIRTIO_BLK_T_FLUSH) {
 		/* Flush */
 		ret = fdatasync(vblk->fd);
 		verbose("FLUSH fdatasync: %i\n", ret);
@@ -1669,10 +1656,9 @@ static void blk_request(struct virtqueue *vq)
 		 * if they try to read past end.
 		 */
 		if (lseek64(vblk->fd, off, SEEK_SET) != off)
-			err(1, "Bad seek to sector %llu", out->sector);
+			err(1, "Bad seek to sector %llu", out.sector);
 
-		ret = readv(vblk->fd, iov+1, in_num-1);
-		verbose("READ from sector %llu: %i\n", out->sector, ret);
+		ret = readv(vblk->fd, iov + out_num, in_num);
 		if (ret >= 0) {
 			wlen = sizeof(*in) + ret;
 			*in = VIRTIO_BLK_S_OK;
@@ -1758,7 +1744,7 @@ static void rng_input(struct virtqueue *vq)
 		len = readv(rng_info->rfd, iov, in_num);
 		if (len <= 0)
 			err(1, "Read from /dev/random gave %i", len);
-		iov_consume(iov, in_num, len);
+		iov_consume(iov, in_num, NULL, len);
 		totlen += len;
 	}
 

tools/virtio/virtio_test.c

@@ -164,7 +164,7 @@ static void run_test(struct vdev_info *dev, struct vq_info *vq,
 				r = virtqueue_add_buf(vq->vq, &sl, 1, 0,
 						      dev->buf + started,
 						      GFP_ATOMIC);
-				if (likely(r >= 0)) {
+				if (likely(r == 0)) {
 					++started;
 					virtqueue_kick(vq->vq);
 				}
@@ -177,7 +177,7 @@ static void run_test(struct vdev_info *dev, struct vq_info *vq,
 				r = 0;
 			}
 
-		} while (r >= 0);
+		} while (r == 0);
 		if (completed == completed_before)
 			++spurious;
 		assert(completed <= bufs);