Fixed MTP to work with TWRP

drivers/virtio/Kconfig

@@ -0,0 +1,56 @@
+config VIRTIO
+	tristate
+	---help---
+	  This option is selected by any driver which implements the virtio
+	  bus, such as CONFIG_VIRTIO_PCI, CONFIG_VIRTIO_MMIO, CONFIG_LGUEST,
+	  CONFIG_RPMSG or CONFIG_S390_GUEST.
+
+menu "Virtio drivers"
+
+config VIRTIO_PCI
+	tristate "PCI driver for virtio devices"
+	depends on PCI
+	select VIRTIO
+	---help---
+	  This drivers provides support for virtio based paravirtual device
+	  drivers over PCI.  This requires that your VMM has appropriate PCI
+	  virtio backends.  Most QEMU based VMMs should support these devices
+	  (like KVM or Xen).
+
+	  Currently, the ABI is not considered stable so there is no guarantee
+	  that this version of the driver will work with your VMM.
+
+	  If unsure, say M.
+
+config VIRTIO_BALLOON
+	tristate "Virtio balloon driver"
+	depends on VIRTIO
+	select MEMORY_BALLOON
+	---help---
+	 This driver supports increasing and decreasing the amount
+	 of memory within a KVM guest.
+
+	 If unsure, say M.
+
+ config VIRTIO_MMIO
+	tristate "Platform bus driver for memory mapped virtio devices"
+	depends on HAS_IOMEM
+ 	select VIRTIO
+ 	---help---
+ 	 This drivers provides support for memory mapped virtio
+	 platform device driver.
+
+ 	 If unsure, say N.
+
+config VIRTIO_MMIO_CMDLINE_DEVICES
+	bool "Memory mapped virtio devices parameter parsing"
+	depends on VIRTIO_MMIO
+	---help---
+	 Allow virtio-mmio devices instantiation via the kernel command line
+	 or module parameters. Be aware that using incorrect parameters (base
+	 address in particular) can crash your system - you have been warned.
+	 See Documentation/kernel-parameters.txt for details.
+
+	 If unsure, say 'N'.
+
+endmenu

drivers/virtio/Makefile

@@ -0,0 +1,4 @@
+obj-$(CONFIG_VIRTIO) += virtio.o virtio_ring.o
+obj-$(CONFIG_VIRTIO_MMIO) += virtio_mmio.o
+obj-$(CONFIG_VIRTIO_PCI) += virtio_pci.o
+obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o

drivers/virtio/config.c

@@ -0,0 +1,12 @@
+/* Configuration space parsing helpers for virtio.
+ *
+ * The configuration is [type][len][... len bytes ...] fields.
+ *
+ * Copyright 2007 Rusty Russell, IBM Corporation.
+ * GPL v2 or later.
+ */
+#include <linux/err.h>
+#include <linux/virtio.h>
+#include <linux/virtio_config.h>
+#include <linux/bug.h>
+

drivers/virtio/virtio.c

@@ -0,0 +1,359 @@
+#include <linux/virtio.h>
+#include <linux/spinlock.h>
+#include <linux/virtio_config.h>
+#include <linux/module.h>
+#include <linux/idr.h>
+
+/* Unique numbering for virtio devices. */
+static DEFINE_IDA(virtio_index_ida);
+
+static ssize_t device_show(struct device *_d,
+			   struct device_attribute *attr, char *buf)
+{
+	struct virtio_device *dev = dev_to_virtio(_d);
+	return sprintf(buf, "0x%04x\n", dev->id.device);
+}
+static DEVICE_ATTR_RO(device);
+
+static ssize_t vendor_show(struct device *_d,
+			   struct device_attribute *attr, char *buf)
+{
+	struct virtio_device *dev = dev_to_virtio(_d);
+	return sprintf(buf, "0x%04x\n", dev->id.vendor);
+}
+static DEVICE_ATTR_RO(vendor);
+
+static ssize_t status_show(struct device *_d,
+			   struct device_attribute *attr, char *buf)
+{
+	struct virtio_device *dev = dev_to_virtio(_d);
+	return sprintf(buf, "0x%08x\n", dev->config->get_status(dev));
+}
+static DEVICE_ATTR_RO(status);
+
+static ssize_t modalias_show(struct device *_d,
+			     struct device_attribute *attr, char *buf)
+{
+	struct virtio_device *dev = dev_to_virtio(_d);
+	return sprintf(buf, "virtio:d%08Xv%08X\n",
+		       dev->id.device, dev->id.vendor);
+}
+static DEVICE_ATTR_RO(modalias);
+
+static ssize_t features_show(struct device *_d,
+			     struct device_attribute *attr, char *buf)
+{
+	struct virtio_device *dev = dev_to_virtio(_d);
+	unsigned int i;
+	ssize_t len = 0;
+
+	/* We actually represent this as a bitstring, as it could be
+	 * arbitrary length in future. */
+	for (i = 0; i < ARRAY_SIZE(dev->features)*BITS_PER_LONG; i++)
+		len += sprintf(buf+len, "%c",
+			       test_bit(i, dev->features) ? '1' : '0');
+	len += sprintf(buf+len, "\n");
+	return len;
+}
+static DEVICE_ATTR_RO(features);
+
+static struct attribute *virtio_dev_attrs[] = {
+	&dev_attr_device.attr,
+	&dev_attr_vendor.attr,
+	&dev_attr_status.attr,
+	&dev_attr_modalias.attr,
+	&dev_attr_features.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(virtio_dev);
+
+static inline int virtio_id_match(const struct virtio_device *dev,
+				  const struct virtio_device_id *id)
+{
+	if (id->device != dev->id.device && id->device != VIRTIO_DEV_ANY_ID)
+		return 0;
+
+	return id->vendor == VIRTIO_DEV_ANY_ID || id->vendor == dev->id.vendor;
+}
+
+/* This looks through all the IDs a driver claims to support.  If any of them
+ * match, we return 1 and the kernel will call virtio_dev_probe(). */
+static int virtio_dev_match(struct device *_dv, struct device_driver *_dr)
+{
+	unsigned int i;
+	struct virtio_device *dev = dev_to_virtio(_dv);
+	const struct virtio_device_id *ids;
+
+	ids = drv_to_virtio(_dr)->id_table;
+	for (i = 0; ids[i].device; i++)
+		if (virtio_id_match(dev, &ids[i]))
+			return 1;
+	return 0;
+}
+
+static int virtio_uevent(struct device *_dv, struct kobj_uevent_env *env)
+{
+	struct virtio_device *dev = dev_to_virtio(_dv);
+
+	return add_uevent_var(env, "MODALIAS=virtio:d%08Xv%08X",
+			      dev->id.device, dev->id.vendor);
+}
+
+static void add_status(struct virtio_device *dev, unsigned status)
+{
+	dev->config->set_status(dev, dev->config->get_status(dev) | status);
+}
+
+void virtio_check_driver_offered_feature(const struct virtio_device *vdev,
+					 unsigned int fbit)
+{
+	unsigned int i;
+	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)
+			return;
+	BUG();
+}
+EXPORT_SYMBOL_GPL(virtio_check_driver_offered_feature);
+
+static void __virtio_config_changed(struct virtio_device *dev)
+{
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+
+	if (!dev->config_enabled)
+		dev->config_change_pending = true;
+	else if (drv && drv->config_changed)
+		drv->config_changed(dev);
+}
+
+void virtio_config_changed(struct virtio_device *dev)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->config_lock, flags);
+	__virtio_config_changed(dev);
+	spin_unlock_irqrestore(&dev->config_lock, flags);
+}
+EXPORT_SYMBOL_GPL(virtio_config_changed);
+
+static void virtio_config_disable(struct virtio_device *dev)
+{
+	spin_lock_irq(&dev->config_lock);
+	dev->config_enabled = false;
+	spin_unlock_irq(&dev->config_lock);
+}
+
+static void virtio_config_enable(struct virtio_device *dev)
+{
+	spin_lock_irq(&dev->config_lock);
+	dev->config_enabled = true;
+	if (dev->config_change_pending)
+		__virtio_config_changed(dev);
+	dev->config_change_pending = false;
+	spin_unlock_irq(&dev->config_lock);
+}
+
+static int virtio_dev_probe(struct device *_d)
+{
+	int err, i;
+	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! */
+	add_status(dev, VIRTIO_CONFIG_S_DRIVER);
+
+	/* Figure out what features the device supports. */
+	device_features = dev->config->get_features(dev);
+
+	/* Features supported by both device and driver into dev->features. */
+	memset(dev->features, 0, sizeof(dev->features));
+	for (i = 0; i < drv->feature_table_size; i++) {
+		unsigned int f = drv->feature_table[i];
+		BUG_ON(f >= 32);
+		if (device_features & (1 << f))
+			set_bit(f, dev->features);
+	}
+
+	/* Transport features always preserved to pass to finalize_features. */
+	for (i = VIRTIO_TRANSPORT_F_START; i < VIRTIO_TRANSPORT_F_END; i++)
+		if (device_features & (1 << i))
+			set_bit(i, dev->features);
+
+	dev->config->finalize_features(dev);
+
+	err = drv->probe(dev);
+	if (err)
+		add_status(dev, VIRTIO_CONFIG_S_FAILED);
+	else {
+		add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK);
+		if (drv->scan)
+			drv->scan(dev);
+
+		virtio_config_enable(dev);
+	}
+
+	return err;
+}
+
+static int virtio_dev_remove(struct device *_d)
+{
+	struct virtio_device *dev = dev_to_virtio(_d);
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+
+	virtio_config_disable(dev);
+
+	drv->remove(dev);
+
+	/* Driver should have reset device. */
+	WARN_ON_ONCE(dev->config->get_status(dev));
+
+	/* Acknowledge the device's existence again. */
+	add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE);
+	return 0;
+}
+
+static struct bus_type virtio_bus = {
+	.name  = "virtio",
+	.match = virtio_dev_match,
+	.dev_groups = virtio_dev_groups,
+	.uevent = virtio_uevent,
+	.probe = virtio_dev_probe,
+	.remove = virtio_dev_remove,
+};
+
+int register_virtio_driver(struct virtio_driver *driver)
+{
+	/* Catch this early. */
+	BUG_ON(driver->feature_table_size && !driver->feature_table);
+	driver->driver.bus = &virtio_bus;
+	return driver_register(&driver->driver);
+}
+EXPORT_SYMBOL_GPL(register_virtio_driver);
+
+void unregister_virtio_driver(struct virtio_driver *driver)
+{
+	driver_unregister(&driver->driver);
+}
+EXPORT_SYMBOL_GPL(unregister_virtio_driver);
+
+int register_virtio_device(struct virtio_device *dev)
+{
+	int err;
+
+	dev->dev.bus = &virtio_bus;
+
+	/* Assign a unique device index and hence name. */
+	err = ida_simple_get(&virtio_index_ida, 0, 0, GFP_KERNEL);
+	if (err < 0)
+		goto out;
+
+	dev->index = err;
+	dev_set_name(&dev->dev, "virtio%u", dev->index);
+
+	spin_lock_init(&dev->config_lock);
+	dev->config_enabled = false;
+	dev->config_change_pending = false;
+
+	/* We always start by resetting the device, in case a previous
+	 * driver messed it up.  This also tests that code path a little. */
+	dev->config->reset(dev);
+
+	/* Acknowledge that we've seen the device. */
+	add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE);
+
+	INIT_LIST_HEAD(&dev->vqs);
+
+	/* device_register() causes the bus infrastructure to look for a
+	 * matching driver. */
+	err = device_register(&dev->dev);
+out:
+	if (err)
+		add_status(dev, VIRTIO_CONFIG_S_FAILED);
+	return err;
+}
+EXPORT_SYMBOL_GPL(register_virtio_device);
+
+void unregister_virtio_device(struct virtio_device *dev)
+{
+	int index = dev->index; /* save for after device release */
+
+	device_unregister(&dev->dev);
+	ida_simple_remove(&virtio_index_ida, index);
+}
+EXPORT_SYMBOL_GPL(unregister_virtio_device);
+
+#ifdef CONFIG_PM_SLEEP
+int virtio_device_freeze(struct virtio_device *dev)
+{
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+
+	virtio_config_disable(dev);
+
+	dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED;
+
+	if (drv && drv->freeze)
+		return drv->freeze(dev);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_device_freeze);
+
+int virtio_device_restore(struct virtio_device *dev)
+{
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+
+	/* We always start by resetting the device, in case a previous
+	 * driver messed it up. */
+	dev->config->reset(dev);
+
+	/* Acknowledge that we've seen the device. */
+	add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE);
+
+	/* Maybe driver failed before freeze.
+	 * Restore the failed status, for debugging. */
+	if (dev->failed)
+		add_status(dev, VIRTIO_CONFIG_S_FAILED);
+
+	if (!drv)
+		return 0;
+
+	/* We have a driver! */
+	add_status(dev, VIRTIO_CONFIG_S_DRIVER);
+
+	dev->config->finalize_features(dev);
+
+	if (drv->restore) {
+		int ret = drv->restore(dev);
+		if (ret) {
+			add_status(dev, VIRTIO_CONFIG_S_FAILED);
+			return ret;
+		}
+	}
+
+	/* Finally, tell the device we're all set */
+	add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK);
+
+	virtio_config_enable(dev);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_device_restore);
+#endif
+
+static int virtio_init(void)
+{
+	if (bus_register(&virtio_bus) != 0)
+		panic("virtio bus registration failed");
+	return 0;
+}
+
+static void __exit virtio_exit(void)
+{
+	bus_unregister(&virtio_bus);
+}
+core_initcall(virtio_init);
+module_exit(virtio_exit);
+
+MODULE_LICENSE("GPL");

drivers/virtio/virtio_balloon.c

@@ -0,0 +1,549 @@
+/*
+ * Virtio balloon implementation, inspired by Dor Laor and Marcelo
+ * Tosatti's implementations.
+ *
+ *  Copyright 2008 Rusty Russell IBM Corporation
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+
+#include <linux/virtio.h>
+#include <linux/virtio_balloon.h>
+#include <linux/swap.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/balloon_compaction.h>
+#include <linux/wait.h>
+
+/*
+ * Balloon device works in 4K page units.  So each page is pointed to by
+ * multiple balloon pages.  All memory counters in this driver are in balloon
+ * page units.
+ */
+#define VIRTIO_BALLOON_PAGES_PER_PAGE (unsigned)(PAGE_SIZE >> VIRTIO_BALLOON_PFN_SHIFT)
+#define VIRTIO_BALLOON_ARRAY_PFNS_MAX 256
+
+struct virtio_balloon
+{
+	struct virtio_device *vdev;
+	struct virtqueue *inflate_vq, *deflate_vq, *stats_vq;
+
+	/* Where the ballooning thread waits for config to change. */
+	wait_queue_head_t config_change;
+
+	/* The thread servicing the balloon. */
+	struct task_struct *thread;
+
+	/* Waiting for host to ack the pages we released. */
+	wait_queue_head_t acked;
+
+	/* Number of balloon pages we've told the Host we're not using. */
+	unsigned int num_pages;
+	/*
+	 * The pages we've told the Host we're not using are enqueued
+	 * at vb_dev_info->pages list.
+	 * Each page on this list adds VIRTIO_BALLOON_PAGES_PER_PAGE
+	 * to num_pages above.
+	 */
+	struct balloon_dev_info vb_dev_info;
+
+	/* Synchronize access/update to this struct virtio_balloon elements */
+	struct mutex balloon_lock;
+
+	/* The array of pfns we tell the Host about. */
+	unsigned int num_pfns;
+	u32 pfns[VIRTIO_BALLOON_ARRAY_PFNS_MAX];
+
+	/* Memory statistics */
+	int need_stats_update;
+	struct virtio_balloon_stat stats[VIRTIO_BALLOON_S_NR];
+};
+
+static struct virtio_device_id id_table[] = {
+	{ VIRTIO_ID_BALLOON, VIRTIO_DEV_ANY_ID },
+	{ 0 },
+};
+
+static u32 page_to_balloon_pfn(struct page *page)
+{
+	unsigned long pfn = page_to_pfn(page);
+
+	BUILD_BUG_ON(PAGE_SHIFT < VIRTIO_BALLOON_PFN_SHIFT);
+	/* Convert pfn from Linux page size to balloon page size. */
+	return pfn * VIRTIO_BALLOON_PAGES_PER_PAGE;
+}
+
+static struct page *balloon_pfn_to_page(u32 pfn)
+{
+	BUG_ON(pfn % VIRTIO_BALLOON_PAGES_PER_PAGE);
+	return pfn_to_page(pfn / VIRTIO_BALLOON_PAGES_PER_PAGE);
+}
+
+static void balloon_ack(struct virtqueue *vq)
+{
+	struct virtio_balloon *vb = vq->vdev->priv;
+
+	wake_up(&vb->acked);
+}
+
+static void tell_host(struct virtio_balloon *vb, struct virtqueue *vq)
+{
+	struct scatterlist sg;
+	unsigned int len;
+
+	sg_init_one(&sg, vb->pfns, sizeof(vb->pfns[0]) * vb->num_pfns);
+
+	/* We should always be able to add one buffer to an empty queue. */
+	virtqueue_add_outbuf(vq, &sg, 1, vb, GFP_KERNEL);
+	virtqueue_kick(vq);
+
+	/* When host has read buffer, this completes via balloon_ack */
+	wait_event(vb->acked, virtqueue_get_buf(vq, &len));
+}
+
+static void set_page_pfns(u32 pfns[], struct page *page)
+{
+	unsigned int i;
+
+	/* Set balloon pfns pointing at this page.
+	 * Note that the first pfn points at start of the page. */
+	for (i = 0; i < VIRTIO_BALLOON_PAGES_PER_PAGE; i++)
+		pfns[i] = page_to_balloon_pfn(page) + i;
+}
+
+static void fill_balloon(struct virtio_balloon *vb, size_t num)
+{
+	struct balloon_dev_info *vb_dev_info = &vb->vb_dev_info;
+
+	/* We can only do one array worth at a time. */
+	num = min(num, ARRAY_SIZE(vb->pfns));
+
+	mutex_lock(&vb->balloon_lock);
+	for (vb->num_pfns = 0; vb->num_pfns < num;
+	     vb->num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE) {
+		struct page *page = balloon_page_enqueue(vb_dev_info);
+
+		if (!page) {
+			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. */
+			msleep(200);
+			break;
+		}
+		set_page_pfns(vb->pfns + vb->num_pfns, page);
+		vb->num_pages += VIRTIO_BALLOON_PAGES_PER_PAGE;
+		adjust_managed_page_count(page, -1);
+	}
+
+	/* Did we get any? */
+	if (vb->num_pfns != 0)
+		tell_host(vb, vb->inflate_vq);
+	mutex_unlock(&vb->balloon_lock);
+}
+
+static void release_pages_by_pfn(const u32 pfns[], unsigned int num)
+{
+	unsigned int i;
+
+	/* Find pfns pointing at start of each page, get pages and free them. */
+	for (i = 0; i < num; i += VIRTIO_BALLOON_PAGES_PER_PAGE) {
+		struct page *page = balloon_pfn_to_page(pfns[i]);
+		adjust_managed_page_count(page, 1);
+		put_page(page); /* balloon reference */
+	}
+}
+
+static void leak_balloon(struct virtio_balloon *vb, size_t num)
+{
+	struct page *page;
+	struct balloon_dev_info *vb_dev_info = &vb->vb_dev_info;
+
+	/* We can only do one array worth at a time. */
+	num = min(num, ARRAY_SIZE(vb->pfns));
+
+	mutex_lock(&vb->balloon_lock);
+	for (vb->num_pfns = 0; vb->num_pfns < num;
+	     vb->num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE) {
+		page = balloon_page_dequeue(vb_dev_info);
+		if (!page)
+			break;
+		set_page_pfns(vb->pfns + vb->num_pfns, page);
+		vb->num_pages -= VIRTIO_BALLOON_PAGES_PER_PAGE;
+	}
+
+	/*
+	 * Note that if
+	 * virtio_has_feature(vdev, VIRTIO_BALLOON_F_MUST_TELL_HOST);
+	 * is true, we *have* to do it in this order
+	 */
+	if (vb->num_pfns != 0)
+		tell_host(vb, vb->deflate_vq);
+	mutex_unlock(&vb->balloon_lock);
+	release_pages_by_pfn(vb->pfns, vb->num_pfns);
+}
+
+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 = vq->vdev->priv;
+
+	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;
+	unsigned int len;
+
+	vb->need_stats_update = 0;
+	update_balloon_stats(vb);
+
+	vq = vb->stats_vq;
+	if (!virtqueue_get_buf(vq, &len))
+		return;
+	sg_init_one(&sg, vb->stats, sizeof(vb->stats));
+	virtqueue_add_outbuf(vq, &sg, 1, vb, GFP_KERNEL);
+	virtqueue_kick(vq);
+}
+
+static void virtballoon_changed(struct virtio_device *vdev)
+{
+	struct virtio_balloon *vb = vdev->priv;
+
+	wake_up(&vb->config_change);
+}
+
+static inline s64 towards_target(struct virtio_balloon *vb)
+{
+	__le32 v;
+	s64 target;
+
+	virtio_cread(vb->vdev, struct virtio_balloon_config, num_pages, &v);
+
+	target = le32_to_cpu(v);
+	return target - vb->num_pages;
+}
+
+static void update_balloon_size(struct virtio_balloon *vb)
+{
+	__le32 actual = cpu_to_le32(vb->num_pages);
+
+	virtio_cwrite(vb->vdev, struct virtio_balloon_config, actual,
+		      &actual);
+}
+
+static int balloon(void *_vballoon)
+{
+	struct virtio_balloon *vb = _vballoon;
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
+
+	set_freezable();
+	while (!kthread_should_stop()) {
+		s64 diff;
+
+		try_to_freeze();
+
+		add_wait_queue(&vb->config_change, &wait);
+		for (;;) {
+			if ((diff = towards_target(vb)) != 0 ||
+			    vb->need_stats_update ||
+			    kthread_should_stop() ||
+			    freezing(current))
+				break;
+			wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
+		}
+		remove_wait_queue(&vb->config_change, &wait);
+
+		if (vb->need_stats_update)
+			stats_handle_request(vb);
+		if (diff > 0)
+			fill_balloon(vb, diff);
+		else if (diff < 0)
+			leak_balloon(vb, -diff);
+		update_balloon_size(vb);
+
+		/*
+		 * For large balloon changes, we could spend a lot of time
+		 * and always have work to do.  Be nice if preempt disabled.
+		 */
+		cond_resched();
+	}
+	return 0;
+}
+
+static int init_vqs(struct virtio_balloon *vb)
+{
+	struct virtqueue *vqs[3];
+	vq_callback_t *callbacks[] = { balloon_ack, balloon_ack, stats_request };
+	const char *names[] = { "inflate", "deflate", "stats" };
+	int err, nvqs;
+
+	/*
+	 * We expect two virtqueues: inflate and deflate, and
+	 * optionally stat.
+	 */
+	nvqs = virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2;
+	err = vb->vdev->config->find_vqs(vb->vdev, nvqs, vqs, callbacks, names);
+	if (err)
+		return err;
+
+	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 (it can't be broken yet!).
+		 */
+		sg_init_one(&sg, vb->stats, sizeof vb->stats);
+		if (virtqueue_add_outbuf(vb->stats_vq, &sg, 1, vb, GFP_KERNEL)
+		    < 0)
+			BUG();
+		virtqueue_kick(vb->stats_vq);
+	}
+	return 0;
+}
+
+#ifdef CONFIG_BALLOON_COMPACTION
+/*
+ * virtballoon_migratepage - perform the balloon page migration on behalf of
+ *			     a compation thread.     (called under page lock)
+ * @vb_dev_info: the balloon device
+ * @newpage: page that will replace the isolated page after migration finishes.
+ * @page   : the isolated (old) page that is about to be migrated to newpage.
+ * @mode   : compaction mode -- not used for balloon page migration.
+ *
+ * After a ballooned page gets isolated by compaction procedures, this is the
+ * function that performs the page migration on behalf of a compaction thread
+ * The page migration for virtio balloon is done in a simple swap fashion which
+ * follows these two macro steps:
+ *  1) insert newpage into vb->pages list and update the host about it;
+ *  2) update the host about the old page removed from vb->pages list;
+ *
+ * This function preforms the balloon page migration task.
+ * Called through balloon_mapping->a_ops->migratepage
+ */
+static int virtballoon_migratepage(struct balloon_dev_info *vb_dev_info,
+		struct page *newpage, struct page *page, enum migrate_mode mode)
+{
+	struct virtio_balloon *vb = container_of(vb_dev_info,
+			struct virtio_balloon, vb_dev_info);
+	unsigned long flags;
+
+	/*
+	 * In order to avoid lock contention while migrating pages concurrently
+	 * to leak_balloon() or fill_balloon() we just give up the balloon_lock
+	 * this turn, as it is easier to retry the page migration later.
+	 * This also prevents fill_balloon() getting stuck into a mutex
+	 * recursion in the case it ends up triggering memory compaction
+	 * while it is attempting to inflate the ballon.
+	 */
+	if (!mutex_trylock(&vb->balloon_lock))
+		return -EAGAIN;
+
+	get_page(newpage); /* balloon reference */
+
+	/* balloon's page migration 1st step  -- inflate "newpage" */
+	spin_lock_irqsave(&vb_dev_info->pages_lock, flags);
+	balloon_page_insert(vb_dev_info, newpage);
+	vb_dev_info->isolated_pages--;
+	__count_vm_event(BALLOON_MIGRATE);
+	spin_unlock_irqrestore(&vb_dev_info->pages_lock, flags);
+	vb->num_pfns = VIRTIO_BALLOON_PAGES_PER_PAGE;
+	set_page_pfns(vb->pfns, newpage);
+	tell_host(vb, vb->inflate_vq);
+
+	/* balloon's page migration 2nd step -- deflate "page" */
+	balloon_page_delete(page);
+	vb->num_pfns = VIRTIO_BALLOON_PAGES_PER_PAGE;
+	set_page_pfns(vb->pfns, page);
+	tell_host(vb, vb->deflate_vq);
+
+	mutex_unlock(&vb->balloon_lock);
+
+	put_page(page); /* balloon reference */
+
+	return MIGRATEPAGE_SUCCESS;
+}
+#endif /* CONFIG_BALLOON_COMPACTION */
+
+static int virtballoon_probe(struct virtio_device *vdev)
+{
+	struct virtio_balloon *vb;
+	int err;
+
+	vdev->priv = vb = kmalloc(sizeof(*vb), GFP_KERNEL);
+	if (!vb) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	vb->num_pages = 0;
+	mutex_init(&vb->balloon_lock);
+	init_waitqueue_head(&vb->config_change);
+	init_waitqueue_head(&vb->acked);
+	vb->vdev = vdev;
+	vb->need_stats_update = 0;
+
+	balloon_devinfo_init(&vb->vb_dev_info);
+#ifdef CONFIG_BALLOON_COMPACTION
+	vb->vb_dev_info.migratepage = virtballoon_migratepage;
+#endif
+
+	err = init_vqs(vb);
+	if (err)
+		goto out_free_vb;
+
+	virtio_device_ready(vdev);
+
+	vb->thread = kthread_run(balloon, vb, "vballoon");
+	if (IS_ERR(vb->thread)) {
+		err = PTR_ERR(vb->thread);
+		goto out_del_vqs;
+	}
+
+	return 0;
+
+out_del_vqs:
+	vdev->config->del_vqs(vdev);
+out_free_vb:
+	kfree(vb);
+out:
+	return err;
+}
+
+static void remove_common(struct virtio_balloon *vb)
+{
+	/* There might be pages left in the balloon: free them. */
+	while (vb->num_pages)
+		leak_balloon(vb, vb->num_pages);
+	update_balloon_size(vb);
+
+	/* Now we reset the device so we can clean up the queues. */
+	vb->vdev->config->reset(vb->vdev);
+
+	vb->vdev->config->del_vqs(vb->vdev);
+}
+
+static void virtballoon_remove(struct virtio_device *vdev)
+{
+	struct virtio_balloon *vb = vdev->priv;
+
+	kthread_stop(vb->thread);
+	remove_common(vb);
+	kfree(vb);
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int virtballoon_freeze(struct virtio_device *vdev)
+{
+	struct virtio_balloon *vb = vdev->priv;
+
+	/*
+	 * The kthread is already frozen by the PM core before this
+	 * function is called.
+	 */
+
+	remove_common(vb);
+	return 0;
+}
+
+static int virtballoon_restore(struct virtio_device *vdev)
+{
+	struct virtio_balloon *vb = vdev->priv;
+	int ret;
+
+	ret = init_vqs(vdev->priv);
+	if (ret)
+		return ret;
+
+	virtio_device_ready(vdev);
+
+	fill_balloon(vb, towards_target(vb));
+	update_balloon_size(vb);
+	return 0;
+}
+#endif
+
+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,
+	.feature_table_size = ARRAY_SIZE(features),
+	.driver.name =	KBUILD_MODNAME,
+	.driver.owner =	THIS_MODULE,
+	.id_table =	id_table,
+	.probe =	virtballoon_probe,
+	.remove =	virtballoon_remove,
+	.config_changed = virtballoon_changed,
+#ifdef CONFIG_PM_SLEEP
+	.freeze	=	virtballoon_freeze,
+	.restore =	virtballoon_restore,
+#endif
+};
+
+module_virtio_driver(virtio_balloon_driver);
+MODULE_DEVICE_TABLE(virtio, id_table);
+MODULE_DESCRIPTION("Virtio balloon driver");
+MODULE_LICENSE("GPL");

drivers/virtio/virtio_mmio.c

@@ -0,0 +1,663 @@
+/*
+ * Virtio memory mapped device driver
+ *
+ * Copyright 2011, ARM Ltd.
+ *
+ * This module allows virtio devices to be used over a virtual, memory mapped
+ * platform device.
+ *
+ * The guest device(s) may be instantiated in one of three equivalent ways:
+ *
+ * 1. Static platform device in board's code, eg.:
+ *
+ *	static struct platform_device v2m_virtio_device = {
+ *		.name = "virtio-mmio",
+ *		.id = -1,
+ *		.num_resources = 2,
+ *		.resource = (struct resource []) {
+ *			{
+ *				.start = 0x1001e000,
+ *				.end = 0x1001e0ff,
+ *				.flags = IORESOURCE_MEM,
+ *			}, {
+ *				.start = 42 + 32,
+ *				.end = 42 + 32,
+ *				.flags = IORESOURCE_IRQ,
+ *			},
+ *		}
+ *	};
+ *
+ * 2. Device Tree node, eg.:
+ *
+ *		virtio_block@1e000 {
+ *			compatible = "virtio,mmio";
+ *			reg = <0x1e000 0x100>;
+ *			interrupts = <42>;
+ *		}
+ *
+ * 3. Kernel module (or command line) parameter. Can be used more than once -
+ *    one device will be created for each one. Syntax:
+ *
+ *		[virtio_mmio.]device=<size>@<baseaddr>:<irq>[:<id>]
+ *    where:
+ *		<size>     := size (can use standard suffixes like K, M or G)
+ *		<baseaddr> := physical base address
+ *		<irq>      := interrupt number (as passed to request_irq())
+ *		<id>       := (optional) platform device id
+ *    eg.:
+ *		virtio_mmio.device=0x100@0x100b0000:48 \
+ *				virtio_mmio.device=1K@0x1001e000:74
+ *
+ *
+ *
+ * Registers layout (all 32-bit wide):
+ *
+ * offset d. name             description
+ * ------ -- ---------------- -----------------
+ *
+ * 0x000  R  MagicValue       Magic value "virt"
+ * 0x004  R  Version          Device version (current max. 1)
+ * 0x008  R  DeviceID         Virtio device ID
+ * 0x00c  R  VendorID         Virtio vendor ID
+ *
+ * 0x010  R  HostFeatures     Features supported by the host
+ * 0x014  W  HostFeaturesSel  Set of host features to access via HostFeatures
+ *
+ * 0x020  W  GuestFeatures    Features activated by the guest
+ * 0x024  W  GuestFeaturesSel Set of activated features to set via GuestFeatures
+ * 0x028  W  GuestPageSize    Size of guest's memory page in bytes
+ *
+ * 0x030  W  QueueSel         Queue selector
+ * 0x034  R  QueueNumMax      Maximum size of the currently selected queue
+ * 0x038  W  QueueNum         Queue size for the currently selected queue
+ * 0x03c  W  QueueAlign       Used Ring alignment for the current queue
+ * 0x040  RW QueuePFN         PFN for the currently selected queue
+ *
+ * 0x050  W  QueueNotify      Queue notifier
+ * 0x060  R  InterruptStatus  Interrupt status register
+ * 0x064  W  InterruptACK     Interrupt acknowledge register
+ * 0x070  RW Status           Device status register
+ *
+ * 0x100+ RW                  Device-specific configuration space
+ *
+ * Based on Virtio PCI driver by Anthony Liguori, copyright IBM Corp. 2007
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#define pr_fmt(fmt) "virtio-mmio: " fmt
+
+#include <linux/highmem.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/virtio.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_mmio.h>
+#include <linux/virtio_ring.h>
+
+
+
+/* The alignment to use between consumer and producer parts of vring.
+ * Currently hardcoded to the page size. */
+#define VIRTIO_MMIO_VRING_ALIGN		PAGE_SIZE
+
+
+
+#define to_virtio_mmio_device(_plat_dev) \
+	container_of(_plat_dev, struct virtio_mmio_device, vdev)
+
+struct virtio_mmio_device {
+	struct virtio_device vdev;
+	struct platform_device *pdev;
+
+	void __iomem *base;
+	unsigned long version;
+
+	/* a list of queues so we can dispatch IRQs */
+	spinlock_t lock;
+	struct list_head virtqueues;
+};
+
+struct virtio_mmio_vq_info {
+	/* the actual virtqueue */
+	struct virtqueue *vq;
+
+	/* the number of entries in the queue */
+	unsigned int num;
+
+	/* the virtual address of the ring queue */
+	void *queue;
+
+	/* the list node for the virtqueues list */
+	struct list_head node;
+};
+
+
+
+/* Configuration interface */
+
+static u32 vm_get_features(struct virtio_device *vdev)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+
+	/* TODO: Features > 32 bits */
+	writel(0, vm_dev->base + VIRTIO_MMIO_HOST_FEATURES_SEL);
+
+	return readl(vm_dev->base + VIRTIO_MMIO_HOST_FEATURES);
+}
+
+static void vm_finalize_features(struct virtio_device *vdev)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+	int i;
+
+	/* Give virtio_ring a chance to accept features. */
+	vring_transport_features(vdev);
+
+	for (i = 0; i < ARRAY_SIZE(vdev->features); i++) {
+		writel(i, vm_dev->base + VIRTIO_MMIO_GUEST_FEATURES_SEL);
+		writel(vdev->features[i],
+				vm_dev->base + VIRTIO_MMIO_GUEST_FEATURES);
+	}
+}
+
+static void vm_get(struct virtio_device *vdev, unsigned offset,
+		   void *buf, unsigned len)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+	u8 *ptr = buf;
+	int i;
+
+	for (i = 0; i < len; i++)
+		ptr[i] = readb(vm_dev->base + VIRTIO_MMIO_CONFIG + offset + i);
+}
+
+static void vm_set(struct virtio_device *vdev, unsigned offset,
+		   const void *buf, unsigned len)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+	const u8 *ptr = buf;
+	int i;
+
+	for (i = 0; i < len; i++)
+		writeb(ptr[i], vm_dev->base + VIRTIO_MMIO_CONFIG + offset + i);
+}
+
+static u8 vm_get_status(struct virtio_device *vdev)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+
+	return readl(vm_dev->base + VIRTIO_MMIO_STATUS) & 0xff;
+}
+
+static void vm_set_status(struct virtio_device *vdev, u8 status)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+
+	/* We should never be setting status to 0. */
+	BUG_ON(status == 0);
+
+	writel(status, vm_dev->base + VIRTIO_MMIO_STATUS);
+}
+
+static void vm_reset(struct virtio_device *vdev)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+
+	/* 0 status means a reset. */
+	writel(0, vm_dev->base + VIRTIO_MMIO_STATUS);
+}
+
+
+
+/* Transport interface */
+
+/* the notify function used when creating a virt queue */
+static bool vm_notify(struct virtqueue *vq)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vq->vdev);
+
+	/* We write the queue's selector into the notification register to
+	 * signal the other end */
+	writel(vq->index, vm_dev->base + VIRTIO_MMIO_QUEUE_NOTIFY);
+	return true;
+}
+
+/* Notify all virtqueues on an interrupt. */
+static irqreturn_t vm_interrupt(int irq, void *opaque)
+{
+	struct virtio_mmio_device *vm_dev = opaque;
+	struct virtio_mmio_vq_info *info;
+	unsigned long status;
+	unsigned long flags;
+	irqreturn_t ret = IRQ_NONE;
+
+	/* Read and acknowledge interrupts */
+	status = readl(vm_dev->base + VIRTIO_MMIO_INTERRUPT_STATUS);
+	writel(status, vm_dev->base + VIRTIO_MMIO_INTERRUPT_ACK);
+
+	if (unlikely(status & VIRTIO_MMIO_INT_CONFIG)) {
+		virtio_config_changed(&vm_dev->vdev);
+		ret = IRQ_HANDLED;
+	}
+
+	if (likely(status & VIRTIO_MMIO_INT_VRING)) {
+		spin_lock_irqsave(&vm_dev->lock, flags);
+		list_for_each_entry(info, &vm_dev->virtqueues, node)
+			ret |= vring_interrupt(irq, info->vq);
+		spin_unlock_irqrestore(&vm_dev->lock, flags);
+	}
+
+	return ret;
+}
+
+
+
+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 = vq->index;
+
+	spin_lock_irqsave(&vm_dev->lock, flags);
+	list_del(&info->node);
+	spin_unlock_irqrestore(&vm_dev->lock, flags);
+
+	vring_del_virtqueue(vq);
+
+	/* Select and deactivate the queue */
+	writel(index, vm_dev->base + VIRTIO_MMIO_QUEUE_SEL);
+	writel(0, vm_dev->base + VIRTIO_MMIO_QUEUE_PFN);
+
+	size = PAGE_ALIGN(vring_size(info->num, VIRTIO_MMIO_VRING_ALIGN));
+	free_pages_exact(info->queue, size);
+	kfree(info);
+}
+
+static void vm_del_vqs(struct virtio_device *vdev)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+	struct virtqueue *vq, *n;
+
+	list_for_each_entry_safe(vq, n, &vdev->vqs, list)
+		vm_del_vq(vq);
+
+	free_irq(platform_get_irq(vm_dev->pdev, 0), vm_dev);
+}
+
+
+
+static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned index,
+				  void (*callback)(struct virtqueue *vq),
+				  const char *name)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+	struct virtio_mmio_vq_info *info;
+	struct virtqueue *vq;
+	unsigned long flags, size;
+	int err;
+
+	if (!name)
+		return NULL;
+
+	/* Select the queue we're interested in */
+	writel(index, vm_dev->base + VIRTIO_MMIO_QUEUE_SEL);
+
+	/* Queue shouldn't already be set up. */
+	if (readl(vm_dev->base + VIRTIO_MMIO_QUEUE_PFN)) {
+		err = -ENOENT;
+		goto error_available;
+	}
+
+	/* Allocate and fill out our active queue description */
+	info = kmalloc(sizeof(*info), GFP_KERNEL);
+	if (!info) {
+		err = -ENOMEM;
+		goto error_kmalloc;
+	}
+
+	/* Allocate pages for the queue - start with a queue as big as
+	 * possible (limited by maximum size allowed by device), drop down
+	 * to a minimal size, just big enough to fit descriptor table
+	 * and two rings (which makes it "alignment_size * 2")
+	 */
+	info->num = readl(vm_dev->base + VIRTIO_MMIO_QUEUE_NUM_MAX);
+
+	/* If the device reports a 0 entry queue, we won't be able to
+	 * use it to perform I/O, and vring_new_virtqueue() can't create
+	 * empty queues anyway, so don't bother to set up the device.
+	 */
+	if (info->num == 0) {
+		err = -ENOENT;
+		goto error_alloc_pages;
+	}
+
+	while (1) {
+		size = PAGE_ALIGN(vring_size(info->num,
+				VIRTIO_MMIO_VRING_ALIGN));
+		/* Did the last iter shrink the queue below minimum size? */
+		if (size < VIRTIO_MMIO_VRING_ALIGN * 2) {
+			err = -ENOMEM;
+			goto error_alloc_pages;
+		}
+
+		info->queue = alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO);
+		if (info->queue)
+			break;
+
+		info->num /= 2;
+	}
+
+	/* Activate the queue */
+	writel(info->num, vm_dev->base + VIRTIO_MMIO_QUEUE_NUM);
+	writel(VIRTIO_MMIO_VRING_ALIGN,
+			vm_dev->base + VIRTIO_MMIO_QUEUE_ALIGN);
+	writel(virt_to_phys(info->queue) >> PAGE_SHIFT,
+			vm_dev->base + VIRTIO_MMIO_QUEUE_PFN);
+
+	/* Create the vring */
+	vq = vring_new_virtqueue(index, info->num, VIRTIO_MMIO_VRING_ALIGN, vdev,
+				 true, info->queue, vm_notify, callback, name);
+	if (!vq) {
+		err = -ENOMEM;
+		goto error_new_virtqueue;
+	}
+
+	vq->priv = info;
+	info->vq = vq;
+
+	spin_lock_irqsave(&vm_dev->lock, flags);
+	list_add(&info->node, &vm_dev->virtqueues);
+	spin_unlock_irqrestore(&vm_dev->lock, flags);
+
+	return vq;
+
+error_new_virtqueue:
+	writel(0, vm_dev->base + VIRTIO_MMIO_QUEUE_PFN);
+	free_pages_exact(info->queue, size);
+error_alloc_pages:
+	kfree(info);
+error_kmalloc:
+error_available:
+	return ERR_PTR(err);
+}
+
+static int vm_find_vqs(struct virtio_device *vdev, unsigned nvqs,
+		       struct virtqueue *vqs[],
+		       vq_callback_t *callbacks[],
+		       const char *names[])
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+	unsigned int irq = platform_get_irq(vm_dev->pdev, 0);
+	int i, err;
+
+	err = request_irq(irq, vm_interrupt, IRQF_SHARED,
+			dev_name(&vdev->dev), vm_dev);
+	if (err)
+		return err;
+
+	for (i = 0; i < nvqs; ++i) {
+		vqs[i] = vm_setup_vq(vdev, i, callbacks[i], names[i]);
+		if (IS_ERR(vqs[i])) {
+			vm_del_vqs(vdev);
+			return PTR_ERR(vqs[i]);
+		}
+	}
+
+	return 0;
+}
+
+static const char *vm_bus_name(struct virtio_device *vdev)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+
+	return vm_dev->pdev->name;
+}
+
+static const struct virtio_config_ops virtio_mmio_config_ops = {
+	.get		= vm_get,
+	.set		= vm_set,
+	.get_status	= vm_get_status,
+	.set_status	= vm_set_status,
+	.reset		= vm_reset,
+	.find_vqs	= vm_find_vqs,
+	.del_vqs	= vm_del_vqs,
+	.get_features	= vm_get_features,
+	.finalize_features = vm_finalize_features,
+	.bus_name	= vm_bus_name,
+};
+
+
+
+/* Platform device */
+
+static int virtio_mmio_probe(struct platform_device *pdev)
+{
+	struct virtio_mmio_device *vm_dev;
+	struct resource *mem;
+	unsigned long magic;
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!mem)
+		return -EINVAL;
+
+	if (!devm_request_mem_region(&pdev->dev, mem->start,
+			resource_size(mem), pdev->name))
+		return -EBUSY;
+
+	vm_dev = devm_kzalloc(&pdev->dev, sizeof(*vm_dev), GFP_KERNEL);
+	if (!vm_dev)
+		return  -ENOMEM;
+
+	vm_dev->vdev.dev.parent = &pdev->dev;
+	vm_dev->vdev.config = &virtio_mmio_config_ops;
+	vm_dev->pdev = pdev;
+	INIT_LIST_HEAD(&vm_dev->virtqueues);
+	spin_lock_init(&vm_dev->lock);
+
+	vm_dev->base = devm_ioremap(&pdev->dev, mem->start, resource_size(mem));
+	if (vm_dev->base == NULL)
+		return -EFAULT;
+
+	/* Check magic value */
+	magic = readl(vm_dev->base + VIRTIO_MMIO_MAGIC_VALUE);
+	if (magic != ('v' | 'i' << 8 | 'r' << 16 | 't' << 24)) {
+		dev_warn(&pdev->dev, "Wrong magic value 0x%08lx!\n", magic);
+		return -ENODEV;
+	}
+
+	/* Check device version */
+	vm_dev->version = readl(vm_dev->base + VIRTIO_MMIO_VERSION);
+	if (vm_dev->version != 1) {
+		dev_err(&pdev->dev, "Version %ld not supported!\n",
+				vm_dev->version);
+		return -ENXIO;
+	}
+
+	vm_dev->vdev.id.device = readl(vm_dev->base + VIRTIO_MMIO_DEVICE_ID);
+	vm_dev->vdev.id.vendor = readl(vm_dev->base + VIRTIO_MMIO_VENDOR_ID);
+
+	writel(PAGE_SIZE, vm_dev->base + VIRTIO_MMIO_GUEST_PAGE_SIZE);
+
+	platform_set_drvdata(pdev, vm_dev);
+
+	return register_virtio_device(&vm_dev->vdev);
+}
+
+static int virtio_mmio_remove(struct platform_device *pdev)
+{
+	struct virtio_mmio_device *vm_dev = platform_get_drvdata(pdev);
+
+	unregister_virtio_device(&vm_dev->vdev);
+
+	return 0;
+}
+
+
+
+/* Devices list parameter */
+
+#if defined(CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES)
+
+static struct device vm_cmdline_parent = {
+	.init_name = "virtio-mmio-cmdline",
+};
+
+static int vm_cmdline_parent_registered;
+static int vm_cmdline_id;
+
+static int vm_cmdline_set(const char *device,
+		const struct kernel_param *kp)
+{
+	int err;
+	struct resource resources[2] = {};
+	char *str;
+	long long int base, size;
+	unsigned int irq;
+	int processed, consumed = 0;
+	struct platform_device *pdev;
+
+	/* 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, &irq, &consumed,
+			&vm_cmdline_id, &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 + 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);
+		if (err) {
+			pr_err("Failed to register parent device!\n");
+			return err;
+		}
+		vm_cmdline_parent_registered = 1;
+	}
+
+	pr_info("Registering device virtio-mmio.%d at 0x%llx-0x%llx, IRQ %d.\n",
+		       vm_cmdline_id,
+		       (unsigned long long)resources[0].start,
+		       (unsigned long long)resources[0].end,
+		       (int)resources[1].start);
+
+	pdev = platform_device_register_resndata(&vm_cmdline_parent,
+			"virtio-mmio", vm_cmdline_id++,
+			resources, ARRAY_SIZE(resources), NULL, 0);
+	if (IS_ERR(pdev))
+		return PTR_ERR(pdev);
+
+	return 0;
+}
+
+static int vm_cmdline_get_device(struct device *dev, void *data)
+{
+	char *buffer = data;
+	unsigned int len = strlen(buffer);
+	struct platform_device *pdev = to_platform_device(dev);
+
+	snprintf(buffer + len, PAGE_SIZE - len, "0x%llx@0x%llx:%llu:%d\n",
+			pdev->resource[0].end - pdev->resource[0].start + 1ULL,
+			(unsigned long long)pdev->resource[0].start,
+			(unsigned long long)pdev->resource[1].start,
+			pdev->id);
+	return 0;
+}
+
+static int vm_cmdline_get(char *buffer, const struct kernel_param *kp)
+{
+	buffer[0] = '\0';
+	device_for_each_child(&vm_cmdline_parent, buffer,
+			vm_cmdline_get_device);
+	return strlen(buffer) + 1;
+}
+
+static struct kernel_param_ops vm_cmdline_param_ops = {
+	.set = vm_cmdline_set,
+	.get = vm_cmdline_get,
+};
+
+device_param_cb(device, &vm_cmdline_param_ops, NULL, S_IRUSR);
+
+static int vm_unregister_cmdline_device(struct device *dev,
+		void *data)
+{
+	platform_device_unregister(to_platform_device(dev));
+
+	return 0;
+}
+
+static void vm_unregister_cmdline_devices(void)
+{
+	if (vm_cmdline_parent_registered) {
+		device_for_each_child(&vm_cmdline_parent, NULL,
+				vm_unregister_cmdline_device);
+		device_unregister(&vm_cmdline_parent);
+		vm_cmdline_parent_registered = 0;
+	}
+}
+
+#else
+
+static void vm_unregister_cmdline_devices(void)
+{
+}
+
+#endif
+
+/* Platform driver */
+
+static struct of_device_id virtio_mmio_match[] = {
+	{ .compatible = "virtio,mmio", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, virtio_mmio_match);
+
+static struct platform_driver virtio_mmio_driver = {
+	.probe		= virtio_mmio_probe,
+	.remove		= virtio_mmio_remove,
+	.driver		= {
+		.name	= "virtio-mmio",
+		.owner	= THIS_MODULE,
+		.of_match_table	= virtio_mmio_match,
+	},
+};
+
+static int __init virtio_mmio_init(void)
+{
+	return platform_driver_register(&virtio_mmio_driver);
+}
+
+static void __exit virtio_mmio_exit(void)
+{
+	platform_driver_unregister(&virtio_mmio_driver);
+	vm_unregister_cmdline_devices();
+}
+
+module_init(virtio_mmio_init);
+module_exit(virtio_mmio_exit);
+
+MODULE_AUTHOR("Pawel Moll <pawel.moll@arm.com>");
+MODULE_DESCRIPTION("Platform bus driver for memory mapped virtio devices");
+MODULE_LICENSE("GPL");

drivers/virtio/virtio_pci.c

@@ -0,0 +1,802 @@
+/*
+ * Virtio PCI driver
+ *
+ * This module allows virtio devices to be used over a virtual PCI device.
+ * This can be used with QEMU based VMMs like KVM or Xen.
+ *
+ * Copyright IBM Corp. 2007
+ *
+ * Authors:
+ *  Anthony Liguori  <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/virtio.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_ring.h>
+#include <linux/virtio_pci.h>
+#include <linux/highmem.h>
+#include <linux/spinlock.h>
+
+MODULE_AUTHOR("Anthony Liguori <aliguori@us.ibm.com>");
+MODULE_DESCRIPTION("virtio-pci");
+MODULE_LICENSE("GPL");
+MODULE_VERSION("1");
+
+/* Our device structure */
+struct virtio_pci_device
+{
+	struct virtio_device vdev;
+	struct pci_dev *pci_dev;
+
+	/* the IO mapping for the PCI config space */
+	void __iomem *ioaddr;
+
+	/* a list of queues so we can dispatch IRQs */
+	spinlock_t lock;
+	struct list_head virtqueues;
+
+	/* MSI-X support */
+	int msix_enabled;
+	int intx_enabled;
+	struct msix_entry *msix_entries;
+	cpumask_var_t *msix_affinity_masks;
+	/* Name strings for interrupts. This size should be enough,
+	 * and I'm too lazy to allocate each name separately. */
+	char (*msix_names)[256];
+	/* Number of available vectors */
+	unsigned msix_vectors;
+	/* Vectors allocated, excluding per-vq vectors if any */
+	unsigned msix_used_vectors;
+
+	/* Whether we have vector per vq */
+	bool per_vq_vectors;
+};
+
+/* Constants for MSI-X */
+/* Use first vector for configuration changes, second and the rest for
+ * virtqueues Thus, we need at least 2 vectors for MSI. */
+enum {
+	VP_MSIX_CONFIG_VECTOR = 0,
+	VP_MSIX_VQ_VECTOR = 1,
+};
+
+struct virtio_pci_vq_info
+{
+	/* the actual virtqueue */
+	struct virtqueue *vq;
+
+	/* the number of entries in the queue */
+	int num;
+
+	/* the virtual address of the ring queue */
+	void *queue;
+
+	/* the list node for the virtqueues list */
+	struct list_head node;
+
+	/* MSI-X vector (or none) */
+	unsigned msix_vector;
+};
+
+/* Qumranet donated their vendor ID for devices 0x1000 thru 0x10FF. */
+static const struct pci_device_id virtio_pci_id_table[] = {
+	{ PCI_DEVICE(0x1af4, PCI_ANY_ID) },
+	{ 0 }
+};
+
+MODULE_DEVICE_TABLE(pci, virtio_pci_id_table);
+
+/* Convert a generic virtio device to our structure */
+static struct virtio_pci_device *to_vp_device(struct virtio_device *vdev)
+{
+	return container_of(vdev, struct virtio_pci_device, vdev);
+}
+
+/* virtio config->get_features() implementation */
+static u32 vp_get_features(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	/* When someone needs more than 32 feature bits, we'll need to
+	 * steal a bit to indicate that the rest are somewhere else. */
+	return ioread32(vp_dev->ioaddr + VIRTIO_PCI_HOST_FEATURES);
+}
+
+/* virtio config->finalize_features() implementation */
+static void vp_finalize_features(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	/* Give virtio_ring a chance to accept features. */
+	vring_transport_features(vdev);
+
+	/* We only support 32 feature bits. */
+	BUILD_BUG_ON(ARRAY_SIZE(vdev->features) != 1);
+	iowrite32(vdev->features[0], vp_dev->ioaddr+VIRTIO_PCI_GUEST_FEATURES);
+}
+
+/* virtio config->get() implementation */
+static void vp_get(struct virtio_device *vdev, unsigned offset,
+		   void *buf, unsigned len)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	void __iomem *ioaddr = vp_dev->ioaddr +
+				VIRTIO_PCI_CONFIG(vp_dev) + offset;
+	u8 *ptr = buf;
+	int i;
+
+	for (i = 0; i < len; i++)
+		ptr[i] = ioread8(ioaddr + i);
+}
+
+/* the config->set() implementation.  it's symmetric to the config->get()
+ * implementation */
+static void vp_set(struct virtio_device *vdev, unsigned offset,
+		   const void *buf, unsigned len)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	void __iomem *ioaddr = vp_dev->ioaddr +
+				VIRTIO_PCI_CONFIG(vp_dev) + offset;
+	const u8 *ptr = buf;
+	int i;
+
+	for (i = 0; i < len; i++)
+		iowrite8(ptr[i], ioaddr + i);
+}
+
+/* config->{get,set}_status() implementations */
+static u8 vp_get_status(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	return ioread8(vp_dev->ioaddr + VIRTIO_PCI_STATUS);
+}
+
+static void vp_set_status(struct virtio_device *vdev, u8 status)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	/* We should never be setting status to 0. */
+	BUG_ON(status == 0);
+	iowrite8(status, vp_dev->ioaddr + VIRTIO_PCI_STATUS);
+}
+
+/* wait for pending irq handlers */
+static void vp_synchronize_vectors(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	int i;
+
+	if (vp_dev->intx_enabled)
+		synchronize_irq(vp_dev->pci_dev->irq);
+
+	for (i = 0; i < vp_dev->msix_vectors; ++i)
+		synchronize_irq(vp_dev->msix_entries[i].vector);
+}
+
+static void vp_reset(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	/* 0 status means a reset. */
+	iowrite8(0, vp_dev->ioaddr + VIRTIO_PCI_STATUS);
+	/* Flush out the status write, and flush in device writes,
+	 * including MSi-X interrupts, if any. */
+	ioread8(vp_dev->ioaddr + VIRTIO_PCI_STATUS);
+	/* Flush pending VQ/configuration callbacks. */
+	vp_synchronize_vectors(vdev);
+}
+
+/* the notify function used when creating a virt queue */
+static bool vp_notify(struct virtqueue *vq)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
+
+	/* we write the queue's selector into the notification register to
+	 * signal the other end */
+	iowrite16(vq->index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY);
+	return true;
+}
+
+/* Handle a configuration change: Tell driver if it wants to know. */
+static irqreturn_t vp_config_changed(int irq, void *opaque)
+{
+	struct virtio_pci_device *vp_dev = opaque;
+
+	virtio_config_changed(&vp_dev->vdev);
+	return IRQ_HANDLED;
+}
+
+/* Notify all virtqueues on an interrupt. */
+static irqreturn_t vp_vring_interrupt(int irq, void *opaque)
+{
+	struct virtio_pci_device *vp_dev = opaque;
+	struct virtio_pci_vq_info *info;
+	irqreturn_t ret = IRQ_NONE;
+	unsigned long flags;
+
+	spin_lock_irqsave(&vp_dev->lock, flags);
+	list_for_each_entry(info, &vp_dev->virtqueues, node) {
+		if (vring_interrupt(irq, info->vq) == IRQ_HANDLED)
+			ret = IRQ_HANDLED;
+	}
+	spin_unlock_irqrestore(&vp_dev->lock, flags);
+
+	return ret;
+}
+
+/* A small wrapper to also acknowledge the interrupt when it's handled.
+ * I really need an EIO hook for the vring so I can ack the interrupt once we
+ * know that we'll be handling the IRQ but before we invoke the callback since
+ * the callback may notify the host which results in the host attempting to
+ * raise an interrupt that we would then mask once we acknowledged the
+ * interrupt. */
+static irqreturn_t vp_interrupt(int irq, void *opaque)
+{
+	struct virtio_pci_device *vp_dev = opaque;
+	u8 isr;
+
+	/* reading the ISR has the effect of also clearing it so it's very
+	 * important to save off the value. */
+	isr = ioread8(vp_dev->ioaddr + VIRTIO_PCI_ISR);
+
+	/* It's definitely not us if the ISR was not high */
+	if (!isr)
+		return IRQ_NONE;
+
+	/* Configuration change?  Tell driver if it wants to know. */
+	if (isr & VIRTIO_PCI_ISR_CONFIG)
+		vp_config_changed(irq, opaque);
+
+	return vp_vring_interrupt(irq, opaque);
+}
+
+static void vp_free_vectors(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	int i;
+
+	if (vp_dev->intx_enabled) {
+		free_irq(vp_dev->pci_dev->irq, vp_dev);
+		vp_dev->intx_enabled = 0;
+	}
+
+	for (i = 0; i < vp_dev->msix_used_vectors; ++i)
+		free_irq(vp_dev->msix_entries[i].vector, vp_dev);
+
+	for (i = 0; i < vp_dev->msix_vectors; i++)
+		if (vp_dev->msix_affinity_masks[i])
+			free_cpumask_var(vp_dev->msix_affinity_masks[i]);
+
+	if (vp_dev->msix_enabled) {
+		/* Disable the vector used for configuration */
+		iowrite16(VIRTIO_MSI_NO_VECTOR,
+			  vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
+		/* Flush the write out to device */
+		ioread16(vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
+
+		pci_disable_msix(vp_dev->pci_dev);
+		vp_dev->msix_enabled = 0;
+	}
+
+	vp_dev->msix_vectors = 0;
+	vp_dev->msix_used_vectors = 0;
+	kfree(vp_dev->msix_names);
+	vp_dev->msix_names = NULL;
+	kfree(vp_dev->msix_entries);
+	vp_dev->msix_entries = NULL;
+	kfree(vp_dev->msix_affinity_masks);
+	vp_dev->msix_affinity_masks = NULL;
+}
+
+static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors,
+				   bool per_vq_vectors)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	const char *name = dev_name(&vp_dev->vdev.dev);
+	unsigned i, v;
+	int err = -ENOMEM;
+
+	vp_dev->msix_vectors = nvectors;
+
+	vp_dev->msix_entries = kmalloc(nvectors * sizeof *vp_dev->msix_entries,
+				       GFP_KERNEL);
+	if (!vp_dev->msix_entries)
+		goto error;
+	vp_dev->msix_names = kmalloc(nvectors * sizeof *vp_dev->msix_names,
+				     GFP_KERNEL);
+	if (!vp_dev->msix_names)
+		goto error;
+	vp_dev->msix_affinity_masks
+		= kzalloc(nvectors * sizeof *vp_dev->msix_affinity_masks,
+			  GFP_KERNEL);
+	if (!vp_dev->msix_affinity_masks)
+		goto error;
+	for (i = 0; i < nvectors; ++i)
+		if (!alloc_cpumask_var(&vp_dev->msix_affinity_masks[i],
+					GFP_KERNEL))
+			goto error;
+
+	for (i = 0; i < nvectors; ++i)
+		vp_dev->msix_entries[i].entry = i;
+
+	err = pci_enable_msix_exact(vp_dev->pci_dev,
+				    vp_dev->msix_entries, nvectors);
+	if (err)
+		goto error;
+	vp_dev->msix_enabled = 1;
+
+	/* Set the vector used for configuration */
+	v = vp_dev->msix_used_vectors;
+	snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names,
+		 "%s-config", name);
+	err = request_irq(vp_dev->msix_entries[v].vector,
+			  vp_config_changed, 0, vp_dev->msix_names[v],
+			  vp_dev);
+	if (err)
+		goto error;
+	++vp_dev->msix_used_vectors;
+
+	iowrite16(v, vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
+	/* Verify we had enough resources to assign the vector */
+	v = ioread16(vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
+	if (v == VIRTIO_MSI_NO_VECTOR) {
+		err = -EBUSY;
+		goto error;
+	}
+
+	if (!per_vq_vectors) {
+		/* Shared vector for all VQs */
+		v = vp_dev->msix_used_vectors;
+		snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names,
+			 "%s-virtqueues", name);
+		err = request_irq(vp_dev->msix_entries[v].vector,
+				  vp_vring_interrupt, 0, vp_dev->msix_names[v],
+				  vp_dev);
+		if (err)
+			goto error;
+		++vp_dev->msix_used_vectors;
+	}
+	return 0;
+error:
+	vp_free_vectors(vdev);
+	return err;
+}
+
+static int vp_request_intx(struct virtio_device *vdev)
+{
+	int err;
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	err = request_irq(vp_dev->pci_dev->irq, vp_interrupt,
+			  IRQF_SHARED, dev_name(&vdev->dev), vp_dev);
+	if (!err)
+		vp_dev->intx_enabled = 1;
+	return err;
+}
+
+static struct virtqueue *setup_vq(struct virtio_device *vdev, unsigned index,
+				  void (*callback)(struct virtqueue *vq),
+				  const char *name,
+				  u16 msix_vec)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_vq_info *info;
+	struct virtqueue *vq;
+	unsigned long flags, size;
+	u16 num;
+	int err;
+
+	/* Select the queue we're interested in */
+	iowrite16(index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
+
+	/* Check if queue is either not available or already active. */
+	num = ioread16(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NUM);
+	if (!num || ioread32(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN))
+		return ERR_PTR(-ENOENT);
+
+	/* allocate and fill out our structure the represents an active
+	 * queue */
+	info = kmalloc(sizeof(struct virtio_pci_vq_info), GFP_KERNEL);
+	if (!info)
+		return ERR_PTR(-ENOMEM);
+
+	info->num = num;
+	info->msix_vector = msix_vec;
+
+	size = PAGE_ALIGN(vring_size(num, VIRTIO_PCI_VRING_ALIGN));
+	info->queue = alloc_pages_exact(size, GFP_KERNEL|__GFP_ZERO);
+	if (info->queue == NULL) {
+		err = -ENOMEM;
+		goto out_info;
+	}
+
+	/* activate the queue */
+	iowrite32(virt_to_phys(info->queue) >> VIRTIO_PCI_QUEUE_ADDR_SHIFT,
+		  vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
+
+	/* create the vring */
+	vq = vring_new_virtqueue(index, info->num, VIRTIO_PCI_VRING_ALIGN, vdev,
+				 true, info->queue, vp_notify, callback, name);
+	if (!vq) {
+		err = -ENOMEM;
+		goto out_activate_queue;
+	}
+
+	vq->priv = info;
+	info->vq = vq;
+
+	if (msix_vec != VIRTIO_MSI_NO_VECTOR) {
+		iowrite16(msix_vec, vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
+		msix_vec = ioread16(vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
+		if (msix_vec == VIRTIO_MSI_NO_VECTOR) {
+			err = -EBUSY;
+			goto out_assign;
+		}
+	}
+
+	if (callback) {
+		spin_lock_irqsave(&vp_dev->lock, flags);
+		list_add(&info->node, &vp_dev->virtqueues);
+		spin_unlock_irqrestore(&vp_dev->lock, flags);
+	} else {
+		INIT_LIST_HEAD(&info->node);
+	}
+
+	return vq;
+
+out_assign:
+	vring_del_virtqueue(vq);
+out_activate_queue:
+	iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
+	free_pages_exact(info->queue, size);
+out_info:
+	kfree(info);
+	return ERR_PTR(err);
+}
+
+static void vp_del_vq(struct virtqueue *vq)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
+	struct virtio_pci_vq_info *info = vq->priv;
+	unsigned long flags, size;
+
+	spin_lock_irqsave(&vp_dev->lock, flags);
+	list_del(&info->node);
+	spin_unlock_irqrestore(&vp_dev->lock, flags);
+
+	iowrite16(vq->index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
+
+	if (vp_dev->msix_enabled) {
+		iowrite16(VIRTIO_MSI_NO_VECTOR,
+			  vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
+		/* Flush the write out to device */
+		ioread8(vp_dev->ioaddr + VIRTIO_PCI_ISR);
+	}
+
+	vring_del_virtqueue(vq);
+
+	/* Select and deactivate the queue */
+	iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
+
+	size = PAGE_ALIGN(vring_size(info->num, VIRTIO_PCI_VRING_ALIGN));
+	free_pages_exact(info->queue, size);
+	kfree(info);
+}
+
+/* the config->del_vqs() implementation */
+static void vp_del_vqs(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtqueue *vq, *n;
+	struct virtio_pci_vq_info *info;
+
+	list_for_each_entry_safe(vq, n, &vdev->vqs, list) {
+		info = vq->priv;
+		if (vp_dev->per_vq_vectors &&
+			info->msix_vector != VIRTIO_MSI_NO_VECTOR)
+			free_irq(vp_dev->msix_entries[info->msix_vector].vector,
+				 vq);
+		vp_del_vq(vq);
+	}
+	vp_dev->per_vq_vectors = false;
+
+	vp_free_vectors(vdev);
+}
+
+static int vp_try_to_find_vqs(struct virtio_device *vdev, unsigned nvqs,
+			      struct virtqueue *vqs[],
+			      vq_callback_t *callbacks[],
+			      const char *names[],
+			      bool use_msix,
+			      bool per_vq_vectors)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	u16 msix_vec;
+	int i, err, nvectors, allocated_vectors;
+
+	if (!use_msix) {
+		/* Old style: one normal interrupt for change and all vqs. */
+		err = vp_request_intx(vdev);
+		if (err)
+			goto error_request;
+	} else {
+		if (per_vq_vectors) {
+			/* Best option: one for change interrupt, one per vq. */
+			nvectors = 1;
+			for (i = 0; i < nvqs; ++i)
+				if (callbacks[i])
+					++nvectors;
+		} else {
+			/* Second best: one for change, shared for all vqs. */
+			nvectors = 2;
+		}
+
+		err = vp_request_msix_vectors(vdev, nvectors, per_vq_vectors);
+		if (err)
+			goto error_request;
+	}
+
+	vp_dev->per_vq_vectors = per_vq_vectors;
+	allocated_vectors = vp_dev->msix_used_vectors;
+	for (i = 0; i < nvqs; ++i) {
+		if (!names[i]) {
+			vqs[i] = NULL;
+			continue;
+		} else if (!callbacks[i] || !vp_dev->msix_enabled)
+			msix_vec = VIRTIO_MSI_NO_VECTOR;
+		else if (vp_dev->per_vq_vectors)
+			msix_vec = allocated_vectors++;
+		else
+			msix_vec = VP_MSIX_VQ_VECTOR;
+		vqs[i] = setup_vq(vdev, i, callbacks[i], names[i], msix_vec);
+		if (IS_ERR(vqs[i])) {
+			err = PTR_ERR(vqs[i]);
+			goto error_find;
+		}
+
+		if (!vp_dev->per_vq_vectors || msix_vec == VIRTIO_MSI_NO_VECTOR)
+			continue;
+
+		/* allocate per-vq irq if available and necessary */
+		snprintf(vp_dev->msix_names[msix_vec],
+			 sizeof *vp_dev->msix_names,
+			 "%s-%s",
+			 dev_name(&vp_dev->vdev.dev), names[i]);
+		err = request_irq(vp_dev->msix_entries[msix_vec].vector,
+				  vring_interrupt, 0,
+				  vp_dev->msix_names[msix_vec],
+				  vqs[i]);
+		if (err) {
+			vp_del_vq(vqs[i]);
+			goto error_find;
+		}
+	}
+	return 0;
+
+error_find:
+	vp_del_vqs(vdev);
+
+error_request:
+	return err;
+}
+
+/* the config->find_vqs() implementation */
+static int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs,
+		       struct virtqueue *vqs[],
+		       vq_callback_t *callbacks[],
+		       const char *names[])
+{
+	int err;
+
+	/* Try MSI-X with one vector per queue. */
+	err = vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names, true, true);
+	if (!err)
+		return 0;
+	/* Fallback: MSI-X with one vector for config, one shared for queues. */
+	err = vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names,
+				 true, false);
+	if (!err)
+		return 0;
+	/* Finally fall back to regular interrupts. */
+	return vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names,
+				  false, false);
+}
+
+static const char *vp_bus_name(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	return pci_name(vp_dev->pci_dev);
+}
+
+/* Setup the affinity for a virtqueue:
+ * - force the affinity for per vq vector
+ * - OR over all affinities for shared MSI
+ * - ignore the affinity request if we're using INTX
+ */
+static int vp_set_vq_affinity(struct virtqueue *vq, int cpu)
+{
+	struct virtio_device *vdev = vq->vdev;
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_vq_info *info = vq->priv;
+	struct cpumask *mask;
+	unsigned int irq;
+
+	if (!vq->callback)
+		return -EINVAL;
+
+	if (vp_dev->msix_enabled) {
+		mask = vp_dev->msix_affinity_masks[info->msix_vector];
+		irq = vp_dev->msix_entries[info->msix_vector].vector;
+		if (cpu == -1)
+			irq_set_affinity_hint(irq, NULL);
+		else {
+			cpumask_set_cpu(cpu, mask);
+			irq_set_affinity_hint(irq, mask);
+		}
+	}
+	return 0;
+}
+
+static const struct virtio_config_ops virtio_pci_config_ops = {
+	.get		= vp_get,
+	.set		= vp_set,
+	.get_status	= vp_get_status,
+	.set_status	= vp_set_status,
+	.reset		= vp_reset,
+	.find_vqs	= vp_find_vqs,
+	.del_vqs	= vp_del_vqs,
+	.get_features	= vp_get_features,
+	.finalize_features = vp_finalize_features,
+	.bus_name	= vp_bus_name,
+	.set_vq_affinity = vp_set_vq_affinity,
+};
+
+static void virtio_pci_release_dev(struct device *_d)
+{
+	/*
+	 * No need for a release method as we allocate/free
+	 * all devices together with the pci devices.
+	 * Provide an empty one to avoid getting a warning from core.
+	 */
+}
+
+/* the PCI probing function */
+static int virtio_pci_probe(struct pci_dev *pci_dev,
+			    const struct pci_device_id *id)
+{
+	struct virtio_pci_device *vp_dev;
+	int err;
+
+	/* We only own devices >= 0x1000 and <= 0x103f: leave the rest. */
+	if (pci_dev->device < 0x1000 || pci_dev->device > 0x103f)
+		return -ENODEV;
+
+	if (pci_dev->revision != VIRTIO_PCI_ABI_VERSION) {
+		printk(KERN_ERR "virtio_pci: expected ABI version %d, got %d\n",
+		       VIRTIO_PCI_ABI_VERSION, pci_dev->revision);
+		return -ENODEV;
+	}
+
+	/* allocate our structure and fill it out */
+	vp_dev = kzalloc(sizeof(struct virtio_pci_device), GFP_KERNEL);
+	if (vp_dev == NULL)
+		return -ENOMEM;
+
+	vp_dev->vdev.dev.parent = &pci_dev->dev;
+	vp_dev->vdev.dev.release = virtio_pci_release_dev;
+	vp_dev->vdev.config = &virtio_pci_config_ops;
+	vp_dev->pci_dev = pci_dev;
+	INIT_LIST_HEAD(&vp_dev->virtqueues);
+	spin_lock_init(&vp_dev->lock);
+
+	/* Disable MSI/MSIX to bring device to a known good state. */
+	pci_msi_off(pci_dev);
+
+	/* enable the device */
+	err = pci_enable_device(pci_dev);
+	if (err)
+		goto out;
+
+	err = pci_request_regions(pci_dev, "virtio-pci");
+	if (err)
+		goto out_enable_device;
+
+	vp_dev->ioaddr = pci_iomap(pci_dev, 0, 0);
+	if (vp_dev->ioaddr == NULL) {
+		err = -ENOMEM;
+		goto out_req_regions;
+	}
+
+	pci_set_drvdata(pci_dev, vp_dev);
+	pci_set_master(pci_dev);
+
+	/* we use the subsystem vendor/device id as the virtio vendor/device
+	 * id.  this allows us to use the same PCI vendor/device id for all
+	 * virtio devices and to identify the particular virtio driver by
+	 * the subsystem ids */
+	vp_dev->vdev.id.vendor = pci_dev->subsystem_vendor;
+	vp_dev->vdev.id.device = pci_dev->subsystem_device;
+
+	/* finally register the virtio device */
+	err = register_virtio_device(&vp_dev->vdev);
+	if (err)
+		goto out_set_drvdata;
+
+	return 0;
+
+out_set_drvdata:
+	pci_iounmap(pci_dev, vp_dev->ioaddr);
+out_req_regions:
+	pci_release_regions(pci_dev);
+out_enable_device:
+	pci_disable_device(pci_dev);
+out:
+	kfree(vp_dev);
+	return err;
+}
+
+static void virtio_pci_remove(struct pci_dev *pci_dev)
+{
+	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+
+	unregister_virtio_device(&vp_dev->vdev);
+
+	vp_del_vqs(&vp_dev->vdev);
+	pci_iounmap(pci_dev, vp_dev->ioaddr);
+	pci_release_regions(pci_dev);
+	pci_disable_device(pci_dev);
+	kfree(vp_dev);
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int virtio_pci_freeze(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+	int ret;
+
+	ret = virtio_device_freeze(&vp_dev->vdev);
+
+	if (!ret)
+		pci_disable_device(pci_dev);
+	return ret;
+}
+
+static int virtio_pci_restore(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+	int ret;
+
+	ret = pci_enable_device(pci_dev);
+	if (ret)
+		return ret;
+
+	pci_set_master(pci_dev);
+	return virtio_device_restore(&vp_dev->vdev);
+}
+
+static const struct dev_pm_ops virtio_pci_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(virtio_pci_freeze, virtio_pci_restore)
+};
+#endif
+
+static struct pci_driver virtio_pci_driver = {
+	.name		= "virtio-pci",
+	.id_table	= virtio_pci_id_table,
+	.probe		= virtio_pci_probe,
+	.remove		= virtio_pci_remove,
+#ifdef CONFIG_PM_SLEEP
+	.driver.pm	= &virtio_pci_pm_ops,
+#endif
+};
+
+module_pci_driver(virtio_pci_driver);

drivers/virtio/virtio_ring.c

@@ -0,0 +1,829 @@
+/* Virtio ring implementation.
+ *
+ *  Copyright 2007 Rusty Russell IBM Corporation
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+#include <linux/virtio.h>
+#include <linux/virtio_ring.h>
+#include <linux/virtio_config.h>
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/hrtimer.h>
+#include <linux/kmemleak.h>
+
+#ifdef DEBUG
+/* For development, we want to crash whenever the ring is screwed. */
+#define BAD_RING(_vq, fmt, args...)				\
+	do {							\
+		dev_err(&(_vq)->vq.vdev->dev,			\
+			"%s:"fmt, (_vq)->vq.name, ##args);	\
+		BUG();						\
+	} while (0)
+/* Caller is supposed to guarantee no reentry. */
+#define START_USE(_vq)						\
+	do {							\
+		if ((_vq)->in_use)				\
+			panic("%s:in_use = %i\n",		\
+			      (_vq)->vq.name, (_vq)->in_use);	\
+		(_vq)->in_use = __LINE__;			\
+	} while (0)
+#define END_USE(_vq) \
+	do { BUG_ON(!(_vq)->in_use); (_vq)->in_use = 0; } while(0)
+#else
+#define BAD_RING(_vq, fmt, args...)				\
+	do {							\
+		dev_err(&_vq->vq.vdev->dev,			\
+			"%s:"fmt, (_vq)->vq.name, ##args);	\
+		(_vq)->broken = true;				\
+	} while (0)
+#define START_USE(vq)
+#define END_USE(vq)
+#endif
+
+struct vring_virtqueue
+{
+	struct virtqueue vq;
+
+	/* Actual memory layout for this queue */
+	struct vring vring;
+
+	/* Can we use weak barriers? */
+	bool weak_barriers;
+
+	/* Other side has made a mess, don't try any more. */
+	bool broken;
+
+	/* Host supports indirect buffers */
+	bool indirect;
+
+	/* Host publishes avail event idx */
+	bool event;
+
+	/* Head of free buffer list. */
+	unsigned int free_head;
+	/* Number we've added since last sync. */
+	unsigned int num_added;
+
+	/* Last used index we've seen. */
+	u16 last_used_idx;
+
+	/* How to notify other side. FIXME: commonalize hcalls! */
+	bool (*notify)(struct virtqueue *vq);
+
+#ifdef DEBUG
+	/* They're supposed to lock for us. */
+	unsigned int in_use;
+
+	/* Figure out if their kicks are too delayed. */
+	bool last_add_time_valid;
+	ktime_t last_add_time;
+#endif
+
+	/* Tokens for callbacks. */
+	void *data[];
+};
+
+#define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq)
+
+static struct vring_desc *alloc_indirect(unsigned int total_sg, gfp_t gfp)
+{
+	struct vring_desc *desc;
+	unsigned 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(total_sg * sizeof(struct vring_desc), gfp);
+	if (!desc)
+		return NULL;
+
+	for (i = 0; i < total_sg; i++)
+		desc[i].next = i+1;
+	return desc;
+}
+
+static inline int virtqueue_add(struct virtqueue *_vq,
+				struct scatterlist *sgs[],
+				unsigned int total_sg,
+				unsigned int out_sgs,
+				unsigned int in_sgs,
+				void *data,
+				gfp_t gfp)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	struct scatterlist *sg;
+	struct vring_desc *desc;
+	unsigned int i, n, avail, descs_used, uninitialized_var(prev);
+	int head;
+	bool indirect;
+
+	START_USE(vq);
+
+	BUG_ON(data == NULL);
+
+	if (unlikely(vq->broken)) {
+		END_USE(vq);
+		return -EIO;
+	}
+
+#ifdef DEBUG
+	{
+		ktime_t now = ktime_get();
+
+		/* No kick or get, with .1 second between?  Warn. */
+		if (vq->last_add_time_valid)
+			WARN_ON(ktime_to_ms(ktime_sub(now, vq->last_add_time))
+					    > 100);
+		vq->last_add_time = now;
+		vq->last_add_time_valid = true;
+	}
+#endif
+
+	BUG_ON(total_sg > vq->vring.num);
+	BUG_ON(total_sg == 0);
+
+	head = vq->free_head;
+
+	/* If the host supports indirect descriptor tables, and we have multiple
+	 * buffers, then go indirect. FIXME: tune this threshold */
+	if (vq->indirect && total_sg > 1 && vq->vq.num_free)
+		desc = alloc_indirect(total_sg, gfp);
+	else
+		desc = NULL;
+
+	if (desc) {
+		/* Use a single buffer which doesn't continue */
+		vq->vring.desc[head].flags = VRING_DESC_F_INDIRECT;
+		vq->vring.desc[head].addr = virt_to_phys(desc);
+		/* avoid kmemleak false positive (hidden by virt_to_phys) */
+		kmemleak_ignore(desc);
+		vq->vring.desc[head].len = total_sg * sizeof(struct vring_desc);
+
+		/* Set up rest to use this indirect table. */
+		i = 0;
+		descs_used = 1;
+		indirect = true;
+	} else {
+		desc = vq->vring.desc;
+		i = head;
+		descs_used = total_sg;
+		indirect = false;
+	}
+
+	if (vq->vq.num_free < descs_used) {
+		pr_debug("Can't add buf len %i - avail = %i\n",
+			 descs_used, 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. */
+		if (out_sgs)
+			vq->notify(&vq->vq);
+		END_USE(vq);
+		return -ENOSPC;
+	}
+
+	/* We're about to use some buffers from the free list. */
+	vq->vq.num_free -= descs_used;
+
+	for (n = 0; n < out_sgs; n++) {
+		for (sg = sgs[n]; sg; sg = sg_next(sg)) {
+			desc[i].flags = VRING_DESC_F_NEXT;
+			desc[i].addr = sg_phys(sg);
+			desc[i].len = sg->length;
+			prev = i;
+			i = desc[i].next;
+		}
+	}
+	for (; n < (out_sgs + in_sgs); n++) {
+		for (sg = sgs[n]; sg; sg = sg_next(sg)) {
+			desc[i].flags = VRING_DESC_F_NEXT|VRING_DESC_F_WRITE;
+			desc[i].addr = sg_phys(sg);
+			desc[i].len = sg->length;
+			prev = i;
+			i = desc[i].next;
+		}
+	}
+	/* Last one doesn't continue. */
+	desc[prev].flags &= ~VRING_DESC_F_NEXT;
+
+	/* Update free pointer */
+	if (indirect)
+		vq->free_head = vq->vring.desc[head].next;
+	else
+		vq->free_head = i;
+
+	/* Set token. */
+	vq->data[head] = data;
+
+	/* Put entry in available array (but don't update avail->idx until they
+	 * do sync). */
+	avail = (vq->vring.avail->idx & (vq->vring.num-1));
+	vq->vring.avail->ring[avail] = head;
+
+	/* Descriptors and available array need to be set before we expose the
+	 * new available array entries. */
+	virtio_wmb(vq->weak_barriers);
+	vq->vring.avail->idx++;
+	vq->num_added++;
+
+	/* This is very unlikely, but theoretically possible.  Kick
+	 * just in case. */
+	if (unlikely(vq->num_added == (1 << 16) - 1))
+		virtqueue_kick(_vq);
+
+	pr_debug("Added buffer head %i to %p\n", head, vq);
+	END_USE(vq);
+
+	return 0;
+}
+
+/**
+ * virtqueue_add_sgs - expose buffers to other end
+ * @vq: the struct virtqueue we're talking about.
+ * @sgs: array of terminated scatterlists.
+ * @out_num: the number of scatterlists readable by other side
+ * @in_num: the number of scatterlists which are writable (after readable ones)
+ * @data: the token identifying the buffer.
+ * @gfp: how to do memory allocations (if necessary).
+ *
+ * Caller must ensure we don't call this with other virtqueue operations
+ * at the same time (except where noted).
+ *
+ * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO).
+ */
+int virtqueue_add_sgs(struct virtqueue *_vq,
+		      struct scatterlist *sgs[],
+		      unsigned int out_sgs,
+		      unsigned int in_sgs,
+		      void *data,
+		      gfp_t gfp)
+{
+	unsigned int i, total_sg = 0;
+
+	/* Count them first. */
+	for (i = 0; i < out_sgs + in_sgs; i++) {
+		struct scatterlist *sg;
+		for (sg = sgs[i]; sg; sg = sg_next(sg))
+			total_sg++;
+	}
+	return virtqueue_add(_vq, sgs, total_sg, out_sgs, in_sgs, data, gfp);
+}
+EXPORT_SYMBOL_GPL(virtqueue_add_sgs);
+
+/**
+ * virtqueue_add_outbuf - expose output buffers to other end
+ * @vq: the struct virtqueue we're talking about.
+ * @sg: scatterlist (must be well-formed and terminated!)
+ * @num: the number of entries in @sg readable by other side
+ * @data: the token identifying the buffer.
+ * @gfp: how to do memory allocations (if necessary).
+ *
+ * Caller must ensure we don't call this with other virtqueue operations
+ * at the same time (except where noted).
+ *
+ * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO).
+ */
+int virtqueue_add_outbuf(struct virtqueue *vq,
+			 struct scatterlist *sg, unsigned int num,
+			 void *data,
+			 gfp_t gfp)
+{
+	return virtqueue_add(vq, &sg, num, 1, 0, data, gfp);
+}
+EXPORT_SYMBOL_GPL(virtqueue_add_outbuf);
+
+/**
+ * virtqueue_add_inbuf - expose input buffers to other end
+ * @vq: the struct virtqueue we're talking about.
+ * @sg: scatterlist (must be well-formed and terminated!)
+ * @num: the number of entries in @sg writable by other side
+ * @data: the token identifying the buffer.
+ * @gfp: how to do memory allocations (if necessary).
+ *
+ * Caller must ensure we don't call this with other virtqueue operations
+ * at the same time (except where noted).
+ *
+ * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO).
+ */
+int virtqueue_add_inbuf(struct virtqueue *vq,
+			struct scatterlist *sg, unsigned int num,
+			void *data,
+			gfp_t gfp)
+{
+	return virtqueue_add(vq, &sg, num, 0, 1, data, gfp);
+}
+EXPORT_SYMBOL_GPL(virtqueue_add_inbuf);
+
+/**
+ * virtqueue_kick_prepare - first half of split virtqueue_kick call.
+ * @vq: the struct virtqueue
+ *
+ * Instead of virtqueue_kick(), you can do:
+ *	if (virtqueue_kick_prepare(vq))
+ *		virtqueue_notify(vq);
+ *
+ * This is sometimes useful because the virtqueue_kick_prepare() needs
+ * to be serialized, but the actual virtqueue_notify() call does not.
+ */
+bool virtqueue_kick_prepare(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	u16 new, old;
+	bool needs_kick;
+
+	START_USE(vq);
+	/* We need to expose available array entries before checking avail
+	 * event. */
+	virtio_mb(vq->weak_barriers);
+
+	old = vq->vring.avail->idx - vq->num_added;
+	new = vq->vring.avail->idx;
+	vq->num_added = 0;
+
+#ifdef DEBUG
+	if (vq->last_add_time_valid) {
+		WARN_ON(ktime_to_ms(ktime_sub(ktime_get(),
+					      vq->last_add_time)) > 100);
+	}
+	vq->last_add_time_valid = false;
+#endif
+
+	if (vq->event) {
+		needs_kick = vring_need_event(vring_avail_event(&vq->vring),
+					      new, old);
+	} else {
+		needs_kick = !(vq->vring.used->flags & VRING_USED_F_NO_NOTIFY);
+	}
+	END_USE(vq);
+	return needs_kick;
+}
+EXPORT_SYMBOL_GPL(virtqueue_kick_prepare);
+
+/**
+ * virtqueue_notify - second half of split virtqueue_kick call.
+ * @vq: the struct virtqueue
+ *
+ * This does not need to be serialized.
+ *
+ * Returns false if host notify failed or queue is broken, otherwise true.
+ */
+bool virtqueue_notify(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	if (unlikely(vq->broken))
+		return false;
+
+	/* Prod other side to tell it about changes. */
+	if (!vq->notify(_vq)) {
+		vq->broken = true;
+		return false;
+	}
+	return true;
+}
+EXPORT_SYMBOL_GPL(virtqueue_notify);
+
+/**
+ * virtqueue_kick - update after add_buf
+ * @vq: the struct virtqueue
+ *
+ * After one or more virtqueue_add_* calls, invoke this to kick
+ * the other side.
+ *
+ * Caller must ensure we don't call this with other virtqueue
+ * operations at the same time (except where noted).
+ *
+ * Returns false if kick failed, otherwise true.
+ */
+bool virtqueue_kick(struct virtqueue *vq)
+{
+	if (virtqueue_kick_prepare(vq))
+		return virtqueue_notify(vq);
+	return true;
+}
+EXPORT_SYMBOL_GPL(virtqueue_kick);
+
+static void detach_buf(struct vring_virtqueue *vq, unsigned int head)
+{
+	unsigned int i;
+
+	/* Clear data ptr. */
+	vq->data[head] = NULL;
+
+	/* Put back on free list: find end */
+	i = head;
+
+	/* Free the indirect table */
+	if (vq->vring.desc[i].flags & VRING_DESC_F_INDIRECT)
+		kfree(phys_to_virt(vq->vring.desc[i].addr));
+
+	while (vq->vring.desc[i].flags & VRING_DESC_F_NEXT) {
+		i = vq->vring.desc[i].next;
+		vq->vq.num_free++;
+	}
+
+	vq->vring.desc[i].next = vq->free_head;
+	vq->free_head = head;
+	/* Plus final descriptor */
+	vq->vq.num_free++;
+}
+
+static inline bool more_used(const struct vring_virtqueue *vq)
+{
+	return vq->last_used_idx != vq->vring.used->idx;
+}
+
+/**
+ * virtqueue_get_buf - get the next used buffer
+ * @vq: the struct virtqueue we're talking about.
+ * @len: the length written into the buffer
+ *
+ * If the driver wrote data into the buffer, @len will be set to the
+ * amount written.  This means you don't need to clear the buffer
+ * beforehand to ensure there's no data leakage in the case of short
+ * writes.
+ *
+ * Caller must ensure we don't call this with other virtqueue
+ * operations at the same time (except where noted).
+ *
+ * Returns NULL if there are no used buffers, or the "data" token
+ * handed to virtqueue_add_*().
+ */
+void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	void *ret;
+	unsigned int i;
+	u16 last_used;
+
+	START_USE(vq);
+
+	if (unlikely(vq->broken)) {
+		END_USE(vq);
+		return NULL;
+	}
+
+	if (!more_used(vq)) {
+		pr_debug("No more buffers in queue\n");
+		END_USE(vq);
+		return NULL;
+	}
+
+	/* Only get used array entries after they have been exposed by host. */
+	virtio_rmb(vq->weak_barriers);
+
+	last_used = (vq->last_used_idx & (vq->vring.num - 1));
+	i = vq->vring.used->ring[last_used].id;
+	*len = vq->vring.used->ring[last_used].len;
+
+	if (unlikely(i >= vq->vring.num)) {
+		BAD_RING(vq, "id %u out of range\n", i);
+		return NULL;
+	}
+	if (unlikely(!vq->data[i])) {
+		BAD_RING(vq, "id %u is not a head!\n", i);
+		return NULL;
+	}
+
+	/* detach_buf clears data, so grab it now. */
+	ret = vq->data[i];
+	detach_buf(vq, i);
+	vq->last_used_idx++;
+	/* If we expect an interrupt for the next entry, tell host
+	 * by writing event index and flush out the write before
+	 * the read in the next get_buf call. */
+	if (!(vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT)) {
+		vring_used_event(&vq->vring) = vq->last_used_idx;
+		virtio_mb(vq->weak_barriers);
+	}
+
+#ifdef DEBUG
+	vq->last_add_time_valid = false;
+#endif
+
+	END_USE(vq);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(virtqueue_get_buf);
+
+/**
+ * virtqueue_disable_cb - disable callbacks
+ * @vq: the struct virtqueue we're talking about.
+ *
+ * Note that this is not necessarily synchronous, hence unreliable and only
+ * useful as an optimization.
+ *
+ * Unlike other operations, this need not be serialized.
+ */
+void virtqueue_disable_cb(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	vq->vring.avail->flags |= VRING_AVAIL_F_NO_INTERRUPT;
+}
+EXPORT_SYMBOL_GPL(virtqueue_disable_cb);
+
+/**
+ * virtqueue_enable_cb_prepare - restart callbacks after disable_cb
+ * @vq: the struct virtqueue we're talking about.
+ *
+ * This re-enables callbacks; it returns current queue state
+ * in an opaque unsigned value. This value should be later tested by
+ * virtqueue_poll, to detect a possible race between the driver checking for
+ * more work, and enabling callbacks.
+ *
+ * Caller must ensure we don't call this with other virtqueue
+ * operations at the same time (except where noted).
+ */
+unsigned virtqueue_enable_cb_prepare(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	u16 last_used_idx;
+
+	START_USE(vq);
+
+	/* We optimistically turn back on interrupts, then check if there was
+	 * more to do. */
+	/* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to
+	 * either clear the flags bit or point the event index at the next
+	 * entry. Always do both to keep code simple. */
+	vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT;
+	vring_used_event(&vq->vring) = last_used_idx = vq->last_used_idx;
+	END_USE(vq);
+	return last_used_idx;
+}
+EXPORT_SYMBOL_GPL(virtqueue_enable_cb_prepare);
+
+/**
+ * virtqueue_poll - query pending used buffers
+ * @vq: the struct virtqueue we're talking about.
+ * @last_used_idx: virtqueue state (from call to virtqueue_enable_cb_prepare).
+ *
+ * Returns "true" if there are pending used buffers in the queue.
+ *
+ * This does not need to be serialized.
+ */
+bool virtqueue_poll(struct virtqueue *_vq, unsigned last_used_idx)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	virtio_mb(vq->weak_barriers);
+	return (u16)last_used_idx != vq->vring.used->idx;
+}
+EXPORT_SYMBOL_GPL(virtqueue_poll);
+
+/**
+ * virtqueue_enable_cb - restart callbacks after disable_cb.
+ * @vq: the struct virtqueue we're talking about.
+ *
+ * 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.
+ *
+ * Caller must ensure we don't call this with other virtqueue
+ * operations at the same time (except where noted).
+ */
+bool virtqueue_enable_cb(struct virtqueue *_vq)
+{
+	unsigned last_used_idx = virtqueue_enable_cb_prepare(_vq);
+	return !virtqueue_poll(_vq, last_used_idx);
+}
+EXPORT_SYMBOL_GPL(virtqueue_enable_cb);
+
+/**
+ * virtqueue_enable_cb_delayed - restart callbacks after disable_cb.
+ * @vq: the struct virtqueue we're talking about.
+ *
+ * This re-enables callbacks but hints to the other side to delay
+ * interrupts until most of the available buffers have been processed;
+ * it returns "false" if there are many pending buffers in the queue,
+ * to detect a possible race between the driver checking for more work,
+ * and enabling callbacks.
+ *
+ * Caller must ensure we don't call this with other virtqueue
+ * operations at the same time (except where noted).
+ */
+bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	u16 bufs;
+
+	START_USE(vq);
+
+	/* We optimistically turn back on interrupts, then check if there was
+	 * more to do. */
+	/* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to
+	 * either clear the flags bit or point the event index at the next
+	 * entry. Always do both to keep code simple. */
+	vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT;
+	/* TODO: tune this threshold */
+	bufs = (u16)(vq->vring.avail->idx - vq->last_used_idx) * 3 / 4;
+	vring_used_event(&vq->vring) = vq->last_used_idx + bufs;
+	virtio_mb(vq->weak_barriers);
+	if (unlikely((u16)(vq->vring.used->idx - vq->last_used_idx) > bufs)) {
+		END_USE(vq);
+		return false;
+	}
+
+	END_USE(vq);
+	return true;
+}
+EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed);
+
+/**
+ * virtqueue_detach_unused_buf - detach first unused buffer
+ * @vq: the struct virtqueue we're talking about.
+ *
+ * Returns NULL or the "data" token handed to virtqueue_add_*().
+ * This is not valid on an active queue; it is useful only for device
+ * shutdown.
+ */
+void *virtqueue_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);
+		vq->vring.avail->idx--;
+		END_USE(vq);
+		return buf;
+	}
+	/* That should have freed everything. */
+	BUG_ON(vq->vq.num_free != vq->vring.num);
+
+	END_USE(vq);
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(virtqueue_detach_unused_buf);
+
+irqreturn_t vring_interrupt(int irq, void *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	if (!more_used(vq)) {
+		pr_debug("virtqueue interrupt with no work for %p\n", vq);
+		return IRQ_NONE;
+	}
+
+	if (unlikely(vq->broken))
+		return IRQ_HANDLED;
+
+	pr_debug("virtqueue callback for %p (%p)\n", vq, vq->vq.callback);
+	if (vq->vq.callback)
+		vq->vq.callback(&vq->vq);
+
+	return IRQ_HANDLED;
+}
+EXPORT_SYMBOL_GPL(vring_interrupt);
+
+struct virtqueue *vring_new_virtqueue(unsigned int index,
+				      unsigned int num,
+				      unsigned int vring_align,
+				      struct virtio_device *vdev,
+				      bool weak_barriers,
+				      void *pages,
+				      bool (*notify)(struct virtqueue *),
+				      void (*callback)(struct virtqueue *),
+				      const char *name)
+{
+	struct vring_virtqueue *vq;
+	unsigned int i;
+
+	/* We assume num is a power of 2. */
+	if (num & (num - 1)) {
+		dev_warn(&vdev->dev, "Bad virtqueue length %u\n", num);
+		return NULL;
+	}
+
+	vq = kmalloc(sizeof(*vq) + sizeof(void *)*num, GFP_KERNEL);
+	if (!vq)
+		return NULL;
+
+	vring_init(&vq->vring, num, pages, vring_align);
+	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;
+	list_add_tail(&vq->vq.list, &vdev->vqs);
+#ifdef DEBUG
+	vq->in_use = false;
+	vq->last_add_time_valid = false;
+#endif
+
+	vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC);
+	vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
+
+	/* No callback?  Tell other side not to bother us. */
+	if (!callback)
+		vq->vring.avail->flags |= VRING_AVAIL_F_NO_INTERRUPT;
+
+	/* Put everything in free lists. */
+	vq->free_head = 0;
+	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;
+}
+EXPORT_SYMBOL_GPL(vring_new_virtqueue);
+
+void vring_del_virtqueue(struct virtqueue *vq)
+{
+	list_del(&vq->list);
+	kfree(to_vvq(vq));
+}
+EXPORT_SYMBOL_GPL(vring_del_virtqueue);
+
+/* Manipulates transport-specific feature bits. */
+void vring_transport_features(struct virtio_device *vdev)
+{
+	unsigned int i;
+
+	for (i = VIRTIO_TRANSPORT_F_START; i < VIRTIO_TRANSPORT_F_END; i++) {
+		switch (i) {
+		case VIRTIO_RING_F_INDIRECT_DESC:
+			break;
+		case VIRTIO_RING_F_EVENT_IDX:
+			break;
+		default:
+			/* We don't understand this bit. */
+			clear_bit(i, vdev->features);
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(vring_transport_features);
+
+/**
+ * virtqueue_get_vring_size - return the size of the virtqueue's vring
+ * @vq: the struct virtqueue containing the vring of interest.
+ *
+ * Returns the size of the vring.  This is mainly used for boasting to
+ * userspace.  Unlike other operations, this need not be serialized.
+ */
+unsigned int virtqueue_get_vring_size(struct virtqueue *_vq)
+{
+
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	return vq->vring.num;
+}
+EXPORT_SYMBOL_GPL(virtqueue_get_vring_size);
+
+bool virtqueue_is_broken(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	return vq->broken;
+}
+EXPORT_SYMBOL_GPL(virtqueue_is_broken);
+
+/*
+ * This should prevent the device from being used, allowing drivers to
+ * recover.  You may need to grab appropriate locks to flush.
+ */
+void virtio_break_device(struct virtio_device *dev)
+{
+	struct virtqueue *_vq;
+
+	list_for_each_entry(_vq, &dev->vqs, list) {
+		struct vring_virtqueue *vq = to_vvq(_vq);
+		vq->broken = true;
+	}
+}
+EXPORT_SYMBOL_GPL(virtio_break_device);
+
+MODULE_LICENSE("GPL");