/*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
+ * 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" mechanism to send and receive data. :*/
+ * information and a "virtqueue" or two to send and receive data. :*/
#include <linux/init.h>
#include <linux/bootmem.h>
#include <linux/lguest_launcher.h>
/* The pointer to our (page) of device descriptions. */
static void *lguest_devices;
-/* Unique numbering for lguest devices. */
-static unsigned int dev_index;
-
/* 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(phys_addr, PAGE_SIZE*pages);
+ return (__force void *)ioremap_cache(phys_addr, PAGE_SIZE*pages);
}
static inline void lguest_unmap(void *addr)
/* 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(vdev) container_of(vdev, struct lguest_device, vdev)
+#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 bitmaks, and some configuration bytes. The
- * configuration bytes don't really matter to us: the Launcher set them up, and
+ * 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:
+ desc->config_len;
}
-/* This tests (and acknowleges) a feature bit. */
-static bool lg_feature(struct virtio_device *vdev, unsigned fbit)
+/* This gets the device's feature bits. */
+static u32 lg_get_features(struct virtio_device *vdev)
{
+ unsigned int i;
+ u32 features = 0;
struct lguest_device_desc *desc = to_lgdev(vdev)->desc;
- u8 *features;
-
- /* Obviously if they ask for a feature off the end of our feature
- * bitmap, it's not set. */
- if (fbit / 8 > desc->feature_len)
- return false;
-
- /* The feature bitmap comes after the virtqueues. */
- features = lg_features(desc);
- if (!(features[fbit / 8] & (1 << (fbit % 8))))
- return false;
-
- /* We set the matching bit in the other half of the bitmap to tell the
- * Host we want to use this feature. We don't use this yet, but we
- * could in future. */
- features[desc->feature_len + fbit / 8] |= (1 << (fbit % 8));
- return true;
+ 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;
+}
+
+/* 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 void 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);
+
+ /* The vdev->feature array is a Linux bitmask: this isn't the
+ * same as a the simple array of bits used by lguest devices
+ * for features. So we do this slow, manual conversion which is
+ * completely general. */
+ 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 (test_bit(i, vdev->features))
+ out_features[i / 8] |= (1 << (i % 8));
+ }
}
/* Once they've found a field, getting a copy of it is easy. */
return to_lgdev(vdev)->desc->status;
}
-static void lg_set_status(struct virtio_device *vdev, u8 status)
+/* To notify on status updates, we (ab)use the NOTIFY hypercall, with the
+ * descriptor address of the device. A zero status means "reset". */
+static void set_status(struct virtio_device *vdev, u8 status)
{
+ unsigned long offset = (void *)to_lgdev(vdev)->desc - lguest_devices;
+
+ /* We set the status. */
to_lgdev(vdev)->desc->status = status;
+ kvm_hypercall1(LHCALL_NOTIFY, (max_pfn << PAGE_SHIFT) + offset);
+}
+
+static void lg_set_status(struct virtio_device *vdev, u8 status)
+{
+ BUG_ON(!status);
+ set_status(vdev, status);
+}
+
+static void lg_reset(struct virtio_device *vdev)
+{
+ set_status(vdev, 0);
}
/*
};
/* When the virtio_ring code wants to prod the Host, it calls us here and we
- * make a hypercall. We hand the page number of the virtqueue so the Host
+ * make a hypercall. We hand the physical address of the virtqueue so the Host
* knows which virtqueue we're talking about. */
static void lg_notify(struct virtqueue *vq)
{
* virtqueue structure. */
struct lguest_vq_info *lvq = vq->priv;
- hcall(LHCALL_NOTIFY, lvq->config.pfn << PAGE_SHIFT, 0, 0);
+ kvm_hypercall1(LHCALL_NOTIFY, lvq->config.pfn << PAGE_SHIFT);
}
+/* An extern declaration inside a C file is bad form. Don't do it. */
+extern void lguest_setup_irq(unsigned int irq);
+
/* This routine finds the first virtqueue described in the configuration of
* this device and sets it up.
*
* allocate its own pages and tell the Host where they are, but for lguest it's
* simpler for the Host to simply tell us where the pages are.
*
- * So we provide devices with a "find virtqueue and set it up" function. */
+ * So we provide drivers with a "find the Nth virtqueue and set it up"
+ * function. */
static struct virtqueue *lg_find_vq(struct virtio_device *vdev,
unsigned index,
- bool (*callback)(struct virtqueue *vq))
+ void (*callback)(struct virtqueue *vq))
{
struct lguest_device *ldev = to_lgdev(vdev);
struct lguest_vq_info *lvq;
/* Figure out how many pages the ring will take, and map that memory */
lvq->pages = lguest_map((unsigned long)lvq->config.pfn << PAGE_SHIFT,
DIV_ROUND_UP(vring_size(lvq->config.num,
- PAGE_SIZE),
+ LGUEST_VRING_ALIGN),
PAGE_SIZE));
if (!lvq->pages) {
err = -ENOMEM;
/* OK, tell virtio_ring.c to set up a virtqueue now we know its size
* and we've got a pointer to its pages. */
- vq = vring_new_virtqueue(lvq->config.num, vdev, lvq->pages,
- lg_notify, callback);
+ vq = vring_new_virtqueue(lvq->config.num, LGUEST_VRING_ALIGN,
+ vdev, lvq->pages, lg_notify, callback);
if (!vq) {
err = -ENOMEM;
goto unmap;
}
+ /* Make sure the interrupt is allocated. */
+ lguest_setup_irq(lvq->config.irq);
+
/* Tell the interrupt for this virtqueue to go to the virtio_ring
* interrupt handler. */
/* FIXME: We used to have a flag for the Host to tell us we could use
* the interrupt as a source of randomness: it'd be nice to have that
* back.. */
err = request_irq(lvq->config.irq, vring_interrupt, IRQF_SHARED,
- vdev->dev.bus_id, vq);
+ dev_name(&vdev->dev), vq);
if (err)
goto destroy_vring;
/* The ops structure which hooks everything together. */
static struct virtio_config_ops lguest_config_ops = {
- .feature = lg_feature,
+ .get_features = lg_get_features,
+ .finalize_features = lg_finalize_features,
.get = lg_get,
.set = lg_set,
.get_status = lg_get_status,
.set_status = lg_set_status,
+ .reset = lg_reset,
.find_vq = lg_find_vq,
.del_vq = lg_del_vq,
};
/* The root device for the lguest virtio devices. This makes them appear as
* /sys/devices/lguest/0,1,2 not /sys/devices/0,1,2. */
-static struct device lguest_root = {
- .parent = NULL,
- .bus_id = "lguest",
-};
+static struct device *lguest_root;
/*D:120 This is the core of the lguest bus: actually adding a new device.
* It's a separate function because it's neater that way, and because an
* As Andrew Tridgell says, "Untested code is buggy code".
*
* It's worth reading this carefully: we start with a pointer to the new device
- * descriptor in the "lguest_devices" page. */
-static void add_lguest_device(struct lguest_device_desc *d)
+ * descriptor in the "lguest_devices" page, and the offset into the device
+ * descriptor page so we can uniquely identify it if things go badly wrong. */
+static void add_lguest_device(struct lguest_device_desc *d,
+ unsigned int offset)
{
struct lguest_device *ldev;
* it. */
ldev = kzalloc(sizeof(*ldev), GFP_KERNEL);
if (!ldev) {
- printk(KERN_EMERG "Cannot allocate lguest dev %u\n",
- dev_index++);
+ printk(KERN_EMERG "Cannot allocate lguest dev %u type %u\n",
+ offset, d->type);
return;
}
/* This devices' parent is the lguest/ dir. */
- ldev->vdev.dev.parent = &lguest_root;
+ ldev->vdev.dev.parent = lguest_root;
/* We have a unique device index thanks to the dev_index counter. */
- ldev->vdev.index = dev_index++;
- /* The device type comes straight from the descriptor. There's also a
- * device vendor field in the virtio_device struct, which we leave as
- * 0. */
ldev->vdev.id.device = d->type;
/* We have a simple set of routines for querying the device's
* configuration information and setting its status. */
* virtio_device and calls device_register(). This makes the bus
* infrastructure look for a matching driver. */
if (register_virtio_device(&ldev->vdev) != 0) {
- printk(KERN_ERR "Failed to register lguest device %u\n",
- ldev->vdev.index);
+ printk(KERN_ERR "Failed to register lguest dev %u type %u\n",
+ offset, d->type);
kfree(ldev);
}
}
break;
printk("Device at %i has size %u\n", i, desc_size(d));
- add_lguest_device(d);
+ add_lguest_device(d, i);
}
}
if (strcmp(pv_info.name, "lguest") != 0)
return 0;
- if (device_register(&lguest_root) != 0)
+ lguest_root = root_device_register("lguest");
+ if (IS_ERR(lguest_root))
panic("Could not register lguest root");
/* Devices are in a single page above top of "normal" mem */