/*P:050
* Lguest guests use a very simple method to describe devices. It's a
* series of device descriptors contained just above the top of normal Guest
* memory.
*
* We use the standard "virtio" device infrastructure, which provides us with a
* console, a network and a block driver. Each one expects some configuration
* information and a "virtqueue" or two to send and receive data.
:*/
#include <linux/init.h>
#include <linux/bootmem.h>
#include <linux/lguest_launcher.h>
#include <linux/virtio.h>
#include <linux/virtio_config.h>
#include <linux/interrupt.h>
#include <linux/virtio_ring.h>
#include <linux/err.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <asm/io.h>
#include <asm/paravirt.h>
#include <asm/lguest_hcall.h>
/* The pointer to our (page) of device descriptions. */
static void *lguest_devices;
/*
* For Guests, device memory can be used as normal memory, so we cast away the
* __iomem to quieten sparse.
*/
static inline void *lguest_map(unsigned long phys_addr, unsigned long pages)
{
return (__force void *)ioremap_cache(phys_addr, PAGE_SIZE*pages);
}
static inline void lguest_unmap(void *addr)
{
iounmap((__force void __iomem *)addr);
}
/*D:100
* Each lguest device is just a virtio device plus a pointer to its entry
* in the lguest_devices page.
*/
struct lguest_device {
struct virtio_device vdev;
/* The entry in the lguest_devices page for this device. */
struct lguest_device_desc *desc;
};
/*
* Since the virtio infrastructure hands us a pointer to the virtio_device all
* the time, it helps to have a curt macro to get a pointer to the struct
* lguest_device it's enclosed in.
*/
#define to_lgdev(vd) container_of(vd, struct lguest_device, vdev)
/*D:130
* Device configurations
*
* The configuration information for a device consists of one or more
* virtqueues, a feature bitmap, and some configuration bytes. The
* configuration bytes don't really matter to us: the Launcher sets them up, and
* the driver will look at them during setup.
*
* A convenient routine to return the device's virtqueue config array:
* immediately after the descriptor.
*/
static struct lguest_vqconfig *lg_vq(const struct lguest_device_desc *desc)
{
return (void *)(desc + 1);
}
/* The features come immediately after the virtqueues. */
static u8 *lg_features(const struct lguest_device_desc *desc)
{
return (void *)(lg_vq(desc) + desc->num_vq);
}
/* The config space comes after the two feature bitmasks. */
static u8 *lg_config(const struct lguest_device_desc *desc)
{
return lg_features(desc) + desc->feature_len * 2;
}
/* The total size of the config page used by this device (incl. desc) */
static unsigned desc_size(const struct lguest_device_desc *desc)
{
return sizeof(*desc)
+ desc->num_vq * sizeof(struct lguest_vqconfig)
+ desc->feature_len * 2
+ desc->config_len;
}
/* This gets the device's feature bits. */
static u64 lg_get_features(struct virtio_device *vdev)
{
unsigned int i;
u32 features = 0;
struct lguest_device_desc *desc = to_lgdev(vdev)->desc;
u8 *in_features = lg_features(desc);
/* We do this the slow but generic way. */
for (i = 0; i < min(desc->feature_len * 8, 32); i++)
if (in_features[i / 8] & (1 << (i % 8)))
features |= (1 << i);
return features;
}
/*
* To notify on reset or feature finalization, we (ab)use the NOTIFY
* hypercall, with the descriptor address of the device.
*/
static void status_notify(struct virtio_device *vdev)
{
unsigned long offset = (void *)to_lgdev(vdev)->desc - lguest_devices;
hcall(LHCALL_NOTIFY, (max_pfn << PAGE_SHIFT) + offset, 0, 0, 0);
}
/*
* The virtio core takes the features the Host offers, and copies the ones
* supported by the driver into the vdev->features array. Once that's all
* sorted out, this routine is called so we can tell the Host which features we
* understand and accept.
*/
static int lg_finalize_features(struct virtio_device *vdev)
{
unsigned int i, bits;
struct lguest_device_desc *desc = to_lgdev(vdev)->desc;
/* Second half of bitmap is features we accept. */
u8 *out_features = lg_features(desc) + desc->feature_len;
/* Give virtio_ring a chance to accept features. */
vring_transport_features(vdev);
/* Make sure we don't have any features > 32 bits! */
BUG_ON((u32)vdev->features != vdev->features);
/*
* Since lguest is currently x86-only, we're little-endian. That
* means we could just memcpy. But it's not time critical, and in
* case someone copies this code, we do it the slow, obvious way.
*/
memset(out_features, 0, desc->feature_len);
bits = min_t(unsigned, desc->feature_len, sizeof(vdev->features)) * 8;
for (i = 0; i < bits; i++) {
if (__virtio_test_bit(vdev, i))
out_features[i / 8] |= (1 << (i % 8));
}
/* Tell Host we've finished with this device's feature negotiation */
status_notify(vdev);
return 0;
}
/* Once they've found a field, getting a copy of it is easy. */
static void lg_get(struct virtio_device *vdev, unsigned int offset,
void *buf, unsigned len)
{
struct lguest_device_desc *desc = to_lgdev(vdev)->desc;
/* Check they didn't ask for more than the length of the config! */
BUG_ON(offset + len > desc->config_len);
memcpy(buf, lg_config(desc) + offset, len);
}
/* Setting the contents is also trivial. */
static void lg_set(struct virtio_device *vdev, unsigned int offset,
const void *buf, unsigned len)
{
struct lguest_device_desc *desc = to_lgdev(vdev)->desc;
/* Check they didn't ask for more than the length of the config! */
BUG_ON(offset + len > desc->config_len);
memcpy(lg_config(desc) + offset, buf, len);
}
/*
* The operations to get and set the status word just access the status field
* of the device descriptor.
*/
static u8 lg_get_status(struct virtio_device *vdev)
{
return to_lgdev(vdev)->desc->status;
}
static void lg_set_status(struct virtio_device *vdev, u8 status)
{
BUG_ON(!status);
to_lgdev(vdev)->desc->status = status;
/* Tell Host immediately if we failed. */
if (status & VIRTIO_CONFIG_S_FAILED)
status_notify(vdev);
}
static void lg_reset(struct virtio_device *vdev)
{
/* 0 status means "reset" */
to_lgdev(vdev)->desc->status = 0;
status_notify(vdev);
}
/*
* Virtqueues
*
* The other piece of infrastructure virtio needs is a "virtqueue": a way of
* the Guest device registering buffers for the other side to read from or
* write into (ie. send and receive buffers). Each device can have multiple
* virtqueues: for example the console driver uses one queue for sending and
* another for receiving.
*
* Fortunately for us, a very fast shared-memory-plus-descriptors virtqueue
* already exists in virtio_ring.c. We just need to connect it up.
*
* We start with the information we need to keep about each virtqueue.
*/
/*D:140 This is the information we remember about each virtqueue. */
struct lguest_vq_info {
/* A copy of the information contained in the device config. */
struct lguest_vqconfig config;
/* The address where we mapped the virtio ring, so we can unmap it. */
void *pages;
};
/*
* When the virtio_ring code wants to prod the Host, it calls us here and we
* make a hypercall. We hand the physical address of the virtqueue so the Host
* knows which virtqueue we're talking about.
*/
static bool lg_notify(struct virtqueue *vq)
{
/*
* We store our virtqueue information in the "priv" pointer of the
* virtqueue structure.
*/
struct lguest_vq_info *lvq = vq->priv;
hcall(LHCALL_NOTIFY, lvq->config.pfn << PAGE_SHIFT, 0, 0, 0);
return true;
}
/* An extern declaration inside a C file is bad form. Don't do it. */
extern int lguest_setup_irq(unsigned int irq);
/*
* This routine finds the Nth virtqueue described in the configuration of
* this device and sets it up.
*
* This is kind of an ugly duckling. It'd be nicer to have a standard
* representation of a virtqueue in the configuration space, but it seems that
* everyone wants to do it differently. The KVM coders want the Guest to
* allocate it