Merge git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-for-linus

#include <zlib.h>

#include <assert.h>

#include <sched.h>

#include <limits.h>

#include <stddef.h>

#include "linux/lguest_launcher.h"

#include "linux/virtio_config.h"

#include "linux/virtio_net.h"

	/* The descriptor page for the devices. */

	u8 *descpage;

	/* The tail of the last descriptor. */

	unsigned int desc_used;

	/* A single linked list of devices. */

	struct device *dev;

	/* ... And an end pointer so we can easily append new devices */

	struct device **lastdev;

	/* And a pointer to the last device for easy append and also for

	 * configuration appending. */

	struct device *lastdev;

};

/* The list of Guest devices, based on command line arguments. */

#define cpu_to_le64(v64) (v64)

#define le16_to_cpu(v16) (v16)

#define le32_to_cpu(v32) (v32)

#define le64_to_cpu(v32) (v64)

#define le64_to_cpu(v64) (v64)

/* The device virtqueue descriptors are followed by feature bitmasks. */

static u8 *get_feature_bits(struct device *dev)

{

	return (u8 *)(dev->desc + 1)

		+ dev->desc->num_vq * sizeof(struct lguest_vqconfig);

}

/*L:100 The Launcher code itself takes us out into userspace, that scary place

 * where pointers run wild and free!  Unfortunately, like most userspace

	write(waker_fd, &vq->dev->fd, sizeof(vq->dev->fd));

}

/* Resetting a device is fairly easy. */

static void reset_device(struct device *dev)

{

	struct virtqueue *vq;

	verbose("Resetting device %s\n", dev->name);

	/* Clear the status. */

	dev->desc->status = 0;

	/* Clear any features they've acked. */

	memset(get_feature_bits(dev) + dev->desc->feature_len, 0,

	       dev->desc->feature_len);

	/* Zero out the virtqueues. */

	for (vq = dev->vq; vq; vq = vq->next) {

		memset(vq->vring.desc, 0,

		       vring_size(vq->config.num, getpagesize()));

		vq->last_avail_idx = 0;

	}

}

/* This is the generic routine we call when the Guest uses LHCALL_NOTIFY. */

static void handle_output(int fd, unsigned long addr)

{

	struct device *i;

	struct virtqueue *vq;

	/* Check each virtqueue. */

	/* Check each device and virtqueue. */

	for (i = devices.dev; i; i = i->next) {

		/* Notifications to device descriptors reset the device. */

		if (from_guest_phys(addr) == i->desc) {

			reset_device(i);

			return;

		}

		/* Notifications to virtqueues mean output has occurred. */

		for (vq = i->vq; vq; vq = vq->next) {

			if (vq->config.pfn == addr/getpagesize()

			    && vq->handle_output) {

			if (vq->config.pfn != addr/getpagesize())

				continue;

			/* Guest should acknowledge (and set features!)  before

			 * using the device. */

			if (i->desc->status == 0) {

				warnx("%s gave early output", i->name);

				return;

			}

			if (strcmp(vq->dev->name, "console") != 0)

				verbose("Output to %s\n", vq->dev->name);

			if (vq->handle_output)

				vq->handle_output(fd, vq);

			return;

		}

	}

	}

	/* Early console write is done using notify on a nul-terminated string

	 * in Guest memory. */

 *

 * All devices need a descriptor so the Guest knows it exists, and a "struct

 * device" so the Launcher can keep track of it.  We have common helper

 * routines to allocate them.

 *

 * This routine allocates a new "struct lguest_device_desc" from descriptor

 * table just above the Guest's normal memory.  It returns a pointer to that

 * descriptor. */

static struct lguest_device_desc *new_dev_desc(u16 type)

{

	struct lguest_device_desc *d;

	/* We only have one page for all the descriptors. */

	if (devices.desc_used + sizeof(*d) > getpagesize())

		errx(1, "Too many devices");

 * routines to allocate and manage them. */

	/* We don't need to set config_len or status: page is 0 already. */

	d = (void *)devices.descpage + devices.desc_used;

	d->type = type;

	devices.desc_used += sizeof(*d);

	return d;

/* The layout of the device page is a "struct lguest_device_desc" followed by a

 * number of virtqueue descriptors, then two sets of feature bits, then an

 * array of configuration bytes.  This routine returns the configuration

 * pointer. */

static u8 *device_config(const struct device *dev)

{

	return (void *)(dev->desc + 1)

		+ dev->desc->num_vq * sizeof(struct lguest_vqconfig)

		+ dev->desc->feature_len * 2;

}

/* Each device descriptor is followed by some configuration information.

 * Each configuration field looks like: u8 type, u8 len, [... len bytes...].

 *

 * This routine adds a new field to an existing device's descriptor.  It only

 * works for the last device, but that's OK because that's how we use it. */

static void add_desc_field(struct device *dev, u8 type, u8 len, const void *c)

/* This routine allocates a new "struct lguest_device_desc" from descriptor

 * table page just above the Guest's normal memory.  It returns a pointer to

 * that descriptor. */

static struct lguest_device_desc *new_dev_desc(u16 type)

{

	/* This is the last descriptor, right? */

	assert(devices.descpage + devices.desc_used

	       == (u8 *)(dev->desc + 1) + dev->desc->config_len);

	struct lguest_device_desc d = { .type = type };

	void *p;

	/* We only have one page of device descriptions. */

	if (devices.desc_used + 2 + len > getpagesize())

		errx(1, "Too many devices");

	/* Figure out where the next device config is, based on the last one. */

	if (devices.lastdev)

		p = device_config(devices.lastdev)

			+ devices.lastdev->desc->config_len;

	else

		p = devices.descpage;

	/* Copy in the new config header: type then length. */

	devices.descpage[devices.desc_used++] = type;

	devices.descpage[devices.desc_used++] = len;

	memcpy(devices.descpage + devices.desc_used, c, len);

	devices.desc_used += len;

	/* We only have one page for all the descriptors. */

	if (p + sizeof(d) > (void *)devices.descpage + getpagesize())

		errx(1, "Too many devices");

	/* Update the device descriptor length: two byte head then data. */

	dev->desc->config_len += 2 + len;

	/* p might not be aligned, so we memcpy in. */

	return memcpy(p, &d, sizeof(d));

}

/* This routine adds a virtqueue to a device.  We specify how many descriptors

 * the virtqueue is to have. */

/* Each device descriptor is followed by the description of its virtqueues.  We

 * specify how many descriptors the virtqueue is to have. */

static void add_virtqueue(struct device *dev, unsigned int num_descs,

			  void (*handle_output)(int fd, struct virtqueue *me))

{

	/* Initialize the vring. */

	vring_init(&vq->vring, num_descs, p, getpagesize());

	/* Add the configuration information to this device's descriptor. */

	add_desc_field(dev, VIRTIO_CONFIG_F_VIRTQUEUE,

		       sizeof(vq->config), &vq->config);

	/* Append virtqueue to this device's descriptor.  We use

	 * device_config() to get the end of the device's current virtqueues;

	 * we check that we haven't added any config or feature information

	 * yet, otherwise we'd be overwriting them. */

	assert(dev->desc->config_len == 0 && dev->desc->feature_len == 0);

	memcpy(device_config(dev), &vq->config, sizeof(vq->config));

	dev->desc->num_vq++;

	verbose("Virtqueue page %#lx\n", to_guest_phys(p));

	/* Add to tail of list, so dev->vq is first vq, dev->vq->next is

	 * second.  */

	 * virtqueue. */

	vq->handle_output = handle_output;

	/* Set the "Don't Notify Me" flag if we don't have a handler */

	/* As an optimization, set the advisory "Don't Notify Me" flag if we

	 * don't have a handler */

	if (!handle_output)

		vq->vring.used->flags = VRING_USED_F_NO_NOTIFY;

}

/* The first half of the feature bitmask is for us to advertise features.  The

 * second half if for the Guest to accept features. */

static void add_feature(struct device *dev, unsigned bit)

{

	u8 *features = get_feature_bits(dev);

	/* We can't extend the feature bits once we've added config bytes */

	if (dev->desc->feature_len <= bit / CHAR_BIT) {

		assert(dev->desc->config_len == 0);

		dev->desc->feature_len = (bit / CHAR_BIT) + 1;

	}

	features[bit / CHAR_BIT] |= (1 << (bit % CHAR_BIT));

}

/* This routine sets the configuration fields for an existing device's

 * descriptor.  It only works for the last device, but that's OK because that's

 * how we use it. */

static void set_config(struct device *dev, unsigned len, const void *conf)

{

	/* Check we haven't overflowed our single page. */

	if (device_config(dev) + len > devices.descpage + getpagesize())

		errx(1, "Too many devices");

	/* Copy in the config information, and store the length. */

	memcpy(device_config(dev), conf, len);

	dev->desc->config_len = len;

}

/* This routine does all the creation and setup of a new device, including

 * calling new_dev_desc() to allocate the descriptor and device memory. */

static struct device *new_device(const char *name, u16 type, int fd,

{

	struct device *dev = malloc(sizeof(*dev));

	/* Append to device list.  Prepending to a single-linked list is

	 * easier, but the user expects the devices to be arranged on the bus

	 * in command-line order.  The first network device on the command line

	 * is eth0, the first block device /dev/vda, etc. */

	*devices.lastdev = dev;

	dev->next = NULL;

	devices.lastdev = &dev->next;

	/* Now we populate the fields one at a time. */

	dev->fd = fd;

	/* If we have an input handler for this file descriptor, then we add it

	dev->handle_input = handle_input;

	dev->name = name;

	dev->vq = NULL;

	/* Append to device list.  Prepending to a single-linked list is

	 * easier, but the user expects the devices to be arranged on the bus

	 * in command-line order.  The first network device on the command line

	 * is eth0, the first block device /dev/vda, etc. */

	if (devices.lastdev)

		devices.lastdev->next = dev;

	else

		devices.dev = dev;

	devices.lastdev = dev;

	return dev;

}

	int netfd, ipfd;

	u32 ip;

	const char *br_name = NULL;

	u8 hwaddr[6];

	struct virtio_net_config conf;

	/* We open the /dev/net/tun device and tell it we want a tap device.  A

	 * tap device is like a tun device, only somehow different.  To tell

		ip = str2ip(arg);

	/* Set up the tun device, and get the mac address for the interface. */

	configure_device(ipfd, ifr.ifr_name, ip, hwaddr);

	configure_device(ipfd, ifr.ifr_name, ip, conf.mac);

	/* Tell Guest what MAC address to use. */

	add_desc_field(dev, VIRTIO_CONFIG_NET_MAC_F, sizeof(hwaddr), hwaddr);

	add_feature(dev, VIRTIO_NET_F_MAC);

	set_config(dev, sizeof(conf), &conf);

	/* We don't seed the socket any more; setup is done. */

	/* We don't need the socket any more; setup is done. */

	close(ipfd);

	verbose("device %u: tun net %u.%u.%u.%u\n",

	struct device *dev;

	struct vblk_info *vblk;

	void *stack;

	u64 cap;

	unsigned int val;

	struct virtio_blk_config conf;

	/* This is the pipe the I/O thread will use to tell us I/O is done. */

	pipe(p);

	vblk->fd = open_or_die(filename, O_RDWR|O_LARGEFILE);

	vblk->len = lseek64(vblk->fd, 0, SEEK_END);

	/* We support barriers. */

	add_feature(dev, VIRTIO_BLK_F_BARRIER);

	/* Tell Guest how many sectors this device has. */

	cap = cpu_to_le64(vblk->len / 512);

	add_desc_field(dev, VIRTIO_CONFIG_BLK_F_CAPACITY, sizeof(cap), &cap);

	conf.capacity = cpu_to_le64(vblk->len / 512);

	/* Tell Guest not to put in too many descriptors at once: two are used

	 * for the in and out elements. */

	val = cpu_to_le32(VIRTQUEUE_NUM - 2);

	add_desc_field(dev, VIRTIO_CONFIG_BLK_F_SEG_MAX, sizeof(val), &val);

	add_feature(dev, VIRTIO_BLK_F_SEG_MAX);

	conf.seg_max = cpu_to_le32(VIRTQUEUE_NUM - 2);

	set_config(dev, sizeof(conf), &conf);

	/* The I/O thread writes to this end of the pipe when done. */

	vblk->done_fd = p[1];

	close(vblk->workpipe[0]);

	verbose("device %u: virtblock %llu sectors\n",

		devices.device_num, cap);

		devices.device_num, le64_to_cpu(conf.capacity));

}

/* That's the end of device setup. :*/

	/* First we initialize the device list.  Since console and network

	 * device receive input from a file descriptor, we keep an fdset

	 * (infds) and the maximum fd number (max_infd) with the head of the

	 * list.  We also keep a pointer to the last device, for easy appending

	 * to the list.  Finally, we keep the next interrupt number to hand out

	 * (1: remember that 0 is used by the timer). */

	 * list.  We also keep a pointer to the last device.  Finally, we keep

	 * the next interrupt number to hand out (1: remember that 0 is used by

	 * the timer). */

	FD_ZERO(&devices.infds);

	devices.max_infd = -1;

	devices.lastdev = &devices.dev;

	devices.lastdev = NULL;

	devices.next_irq = 1;

	cpu_id = 0;

# OK, it's a little counter-intuitive to do this, but it puts it neatly under

# the virtualization menu.

source drivers/lguest/Kconfig

source drivers/virtio/Kconfig

endif # VIRTUALIZATION

source "drivers/auxdisplay/Kconfig"

source "drivers/uio/Kconfig"

source "drivers/virtio/Kconfig"

endmenu

	tristate "Virtio block driver (EXPERIMENTAL)"

	depends on EXPERIMENTAL && VIRTIO

	---help---

	  This is the virtual block driver for lguest.  Say Y or M.

	  This is the virtual block driver for virtio.  It can be used with

          lguest or QEMU based VMMs (like KVM or Xen).  Say Y or M.

endif # BLK_DEV

#include <linux/scatterlist.h>

#define VIRTIO_MAX_SG	(3+MAX_PHYS_SEGMENTS)

#define PART_BITS 4

static int major, index;

static unsigned char virtblk_index = 'a';

struct virtio_blk

{

	spinlock_t lock;

	struct virtio_blk_inhdr in_hdr;

};

static bool blk_done(struct virtqueue *vq)

static void blk_done(struct virtqueue *vq)

{

	struct virtio_blk *vblk = vq->vdev->priv;

	struct virtblk_req *vbr;

	/* In case queue is stopped waiting for more buffers. */

	blk_start_queue(vblk->disk->queue);

	spin_unlock_irqrestore(&vblk->lock, flags);

	return true;

}

static bool do_req(struct request_queue *q, struct virtio_blk *vblk,

			      (void __user *)data);

}

/* We provide getgeo only to please some old bootloader/partitioning tools */

static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo)

{

	/* some standard values, similar to sd */

	geo->heads = 1 << 6;

	geo->sectors = 1 << 5;

	geo->cylinders = get_capacity(bd->bd_disk) >> 11;

	return 0;

}

static struct block_device_operations virtblk_fops = {

	.ioctl  = virtblk_ioctl,

	.owner  = THIS_MODULE,

	.getgeo = virtblk_getgeo,

};

static int index_to_minor(int index)

{

	return index << PART_BITS;

}

static int virtblk_probe(struct virtio_device *vdev)

{

	struct virtio_blk *vblk;

	int err, major;

	void *token;

	unsigned int len;

	int err;

	u64 cap;

	u32 v;

	if (index_to_minor(index) >= 1 << MINORBITS)

		return -ENOSPC;

	vdev->priv = vblk = kmalloc(sizeof(*vblk), GFP_KERNEL);

	if (!vblk) {

		err = -ENOMEM;

	vblk->vdev = vdev;

	/* We expect one virtqueue, for output. */

	vblk->vq = vdev->config->find_vq(vdev, blk_done);

	vblk->vq = vdev->config->find_vq(vdev, 0, blk_done);

	if (IS_ERR(vblk->vq)) {

		err = PTR_ERR(vblk->vq);

		goto out_free_vblk;

		goto out_free_vq;

	}

	major = register_blkdev(0, "virtblk");

	if (major < 0) {

		err = major;

		goto out_mempool;

	}

	/* FIXME: How many partitions?  How long is a piece of string? */

	vblk->disk = alloc_disk(1 << 4);

	vblk->disk = alloc_disk(1 << PART_BITS);

	if (!vblk->disk) {

		err = -ENOMEM;

		goto out_unregister_blkdev;

		goto out_mempool;

	}

	vblk->disk->queue = blk_init_queue(do_virtblk_request, &vblk->lock);

		goto out_put_disk;

	}

	sprintf(vblk->disk->disk_name, "vd%c", virtblk_index++);

	if (index < 26) {

		sprintf(vblk->disk->disk_name, "vd%c", 'a' + index % 26);

	} else if (index < (26 + 1) * 26) {

		sprintf(vblk->disk->disk_name, "vd%c%c",

			'a' + index / 26 - 1, 'a' + index % 26);

	} else {

		const unsigned int m1 = (index / 26 - 1) / 26 - 1;

		const unsigned int m2 = (index / 26 - 1) % 26;

		const unsigned int m3 =  index % 26;

		sprintf(vblk->disk->disk_name, "vd%c%c%c",

			'a' + m1, 'a' + m2, 'a' + m3);

	}

	vblk->disk->major = major;

	vblk->disk->first_minor = 0;

	vblk->disk->first_minor = index_to_minor(index);

	vblk->disk->private_data = vblk;

	vblk->disk->fops = &virtblk_fops;

	index++;

	/* If barriers are supported, tell block layer that queue is ordered */

	token = vdev->config->find(vdev, VIRTIO_CONFIG_BLK_F, &len);

	if (virtio_use_bit(vdev, token, len, VIRTIO_BLK_F_BARRIER))

	if (vdev->config->feature(vdev, VIRTIO_BLK_F_BARRIER))

		blk_queue_ordered(vblk->disk->queue, QUEUE_ORDERED_TAG, NULL);

	err = virtio_config_val(vdev, VIRTIO_CONFIG_BLK_F_CAPACITY, &cap);

	if (err) {

		dev_err(&vdev->dev, "Bad/missing capacity in config\n");

		goto out_cleanup_queue;

	}

	/* Host must always specify the capacity. */

	__virtio_config_val(vdev, offsetof(struct virtio_blk_config, capacity),

			    &cap);

	/* If capacity is too big, truncate with warning. */

	if ((sector_t)cap != cap) {

	}

	set_capacity(vblk->disk, cap);

	err = virtio_config_val(vdev, VIRTIO_CONFIG_BLK_F_SIZE_MAX, &v);

	/* Host can optionally specify maximum segment size and number of

	 * segments. */

	err = virtio_config_val(vdev, VIRTIO_BLK_F_SIZE_MAX,

				offsetof(struct virtio_blk_config, size_max),

				&v);

	if (!err)

		blk_queue_max_segment_size(vblk->disk->queue, v);

	else if (err != -ENOENT) {

		dev_err(&vdev->dev, "Bad SIZE_MAX in config\n");

		goto out_cleanup_queue;

	}

	err = virtio_config_val(vdev, VIRTIO_CONFIG_BLK_F_SEG_MAX, &v);

	err = virtio_config_val(vdev, VIRTIO_BLK_F_SEG_MAX,

				offsetof(struct virtio_blk_config, seg_max),

				&v);

	if (!err)

		blk_queue_max_hw_segments(vblk->disk->queue, v);

	else if (err != -ENOENT) {

		dev_err(&vdev->dev, "Bad SEG_MAX in config\n");

		goto out_cleanup_queue;

	}

	add_disk(vblk->disk);

	return 0;

out_cleanup_queue:

	blk_cleanup_queue(vblk->disk->queue);

out_put_disk:

	put_disk(vblk->disk);

out_unregister_blkdev:

	unregister_blkdev(major, "virtblk");

out_mempool:

	mempool_destroy(vblk->pool);

out_free_vq:

	struct virtio_blk *vblk = vdev->priv;

	int major = vblk->disk->major;

	/* Nothing should be pending. */

	BUG_ON(!list_empty(&vblk->reqs));

	/* Stop all the virtqueues. */

	vdev->config->reset(vdev);

	blk_cleanup_queue(vblk->disk->queue);

	put_disk(vblk->disk);

	unregister_blkdev(major, "virtblk");

	mempool_destroy(vblk->pool);

	/* There should be nothing in the queue now, so no need to shutdown */

	vdev->config->del_vq(vblk->vq);

	kfree(vblk);

}

static int __init init(void)

{

	major = register_blkdev(0, "virtblk");

	if (major < 0)

		return major;

	return register_virtio_driver(&virtio_blk);

}

static void __exit fini(void)

{

	unregister_blkdev(major, "virtblk");

	unregister_virtio_driver(&virtio_blk);

}

module_init(init);