b769f57908
Anthony Liguori points out that three different transports use the virtio code, but each one keeps its own counter to set the virtio_device's index field. In theory (though not in current practice) this means that names could be duplicated, and that risk grows as more transports are created. So we move the selection of the unique virtio_device.index into the common code in virtio.c, which has the side-benefit of removing duplicate code. The only complexity is that lguest and S/390 use the index to uniquely identify the device in case of catastrophic failure before register_virtio_device() is called: now we use the offset within the descriptor page as a unique identifier for the printks. Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Carsten Otte <cotte@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Chris Lalancette <clalance@redhat.com> Cc: Anthony Liguori <anthony@codemonkey.ws>
340 lines
7.9 KiB
C
340 lines
7.9 KiB
C
/*
|
|
* kvm_virtio.c - virtio for kvm on s390
|
|
*
|
|
* Copyright IBM Corp. 2008
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License (version 2 only)
|
|
* as published by the Free Software Foundation.
|
|
*
|
|
* Author(s): Christian Borntraeger <borntraeger@de.ibm.com>
|
|
*/
|
|
|
|
#include <linux/init.h>
|
|
#include <linux/bootmem.h>
|
|
#include <linux/err.h>
|
|
#include <linux/virtio.h>
|
|
#include <linux/virtio_config.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/virtio_ring.h>
|
|
#include <linux/pfn.h>
|
|
#include <asm/io.h>
|
|
#include <asm/kvm_para.h>
|
|
#include <asm/kvm_virtio.h>
|
|
#include <asm/setup.h>
|
|
#include <asm/s390_ext.h>
|
|
|
|
#define VIRTIO_SUBCODE_64 0x0D00
|
|
|
|
/*
|
|
* The pointer to our (page) of device descriptions.
|
|
*/
|
|
static void *kvm_devices;
|
|
|
|
struct kvm_device {
|
|
struct virtio_device vdev;
|
|
struct kvm_device_desc *desc;
|
|
};
|
|
|
|
#define to_kvmdev(vd) container_of(vd, struct kvm_device, vdev)
|
|
|
|
/*
|
|
* memory layout:
|
|
* - kvm_device_descriptor
|
|
* struct kvm_device_desc
|
|
* - configuration
|
|
* struct kvm_vqconfig
|
|
* - feature bits
|
|
* - config space
|
|
*/
|
|
static struct kvm_vqconfig *kvm_vq_config(const struct kvm_device_desc *desc)
|
|
{
|
|
return (struct kvm_vqconfig *)(desc + 1);
|
|
}
|
|
|
|
static u8 *kvm_vq_features(const struct kvm_device_desc *desc)
|
|
{
|
|
return (u8 *)(kvm_vq_config(desc) + desc->num_vq);
|
|
}
|
|
|
|
static u8 *kvm_vq_configspace(const struct kvm_device_desc *desc)
|
|
{
|
|
return kvm_vq_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 kvm_device_desc *desc)
|
|
{
|
|
return sizeof(*desc)
|
|
+ desc->num_vq * sizeof(struct kvm_vqconfig)
|
|
+ desc->feature_len * 2
|
|
+ desc->config_len;
|
|
}
|
|
|
|
/* This gets the device's feature bits. */
|
|
static u32 kvm_get_features(struct virtio_device *vdev)
|
|
{
|
|
unsigned int i;
|
|
u32 features = 0;
|
|
struct kvm_device_desc *desc = to_kvmdev(vdev)->desc;
|
|
u8 *in_features = kvm_vq_features(desc);
|
|
|
|
for (i = 0; i < min(desc->feature_len * 8, 32); i++)
|
|
if (in_features[i / 8] & (1 << (i % 8)))
|
|
features |= (1 << i);
|
|
return features;
|
|
}
|
|
|
|
static void kvm_set_features(struct virtio_device *vdev, u32 features)
|
|
{
|
|
unsigned int i;
|
|
struct kvm_device_desc *desc = to_kvmdev(vdev)->desc;
|
|
/* Second half of bitmap is features we accept. */
|
|
u8 *out_features = kvm_vq_features(desc) + desc->feature_len;
|
|
|
|
memset(out_features, 0, desc->feature_len);
|
|
for (i = 0; i < min(desc->feature_len * 8, 32); i++) {
|
|
if (features & (1 << i))
|
|
out_features[i / 8] |= (1 << (i % 8));
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Reading and writing elements in config space
|
|
*/
|
|
static void kvm_get(struct virtio_device *vdev, unsigned int offset,
|
|
void *buf, unsigned len)
|
|
{
|
|
struct kvm_device_desc *desc = to_kvmdev(vdev)->desc;
|
|
|
|
BUG_ON(offset + len > desc->config_len);
|
|
memcpy(buf, kvm_vq_configspace(desc) + offset, len);
|
|
}
|
|
|
|
static void kvm_set(struct virtio_device *vdev, unsigned int offset,
|
|
const void *buf, unsigned len)
|
|
{
|
|
struct kvm_device_desc *desc = to_kvmdev(vdev)->desc;
|
|
|
|
BUG_ON(offset + len > desc->config_len);
|
|
memcpy(kvm_vq_configspace(desc) + offset, buf, len);
|
|
}
|
|
|
|
/*
|
|
* The operations to get and set the status word just access
|
|
* the status field of the device descriptor. set_status will also
|
|
* make a hypercall to the host, to tell about status changes
|
|
*/
|
|
static u8 kvm_get_status(struct virtio_device *vdev)
|
|
{
|
|
return to_kvmdev(vdev)->desc->status;
|
|
}
|
|
|
|
static void kvm_set_status(struct virtio_device *vdev, u8 status)
|
|
{
|
|
BUG_ON(!status);
|
|
to_kvmdev(vdev)->desc->status = status;
|
|
kvm_hypercall1(KVM_S390_VIRTIO_SET_STATUS,
|
|
(unsigned long) to_kvmdev(vdev)->desc);
|
|
}
|
|
|
|
/*
|
|
* To reset the device, we use the KVM_VIRTIO_RESET hypercall, using the
|
|
* descriptor address. The Host will zero the status and all the
|
|
* features.
|
|
*/
|
|
static void kvm_reset(struct virtio_device *vdev)
|
|
{
|
|
kvm_hypercall1(KVM_S390_VIRTIO_RESET,
|
|
(unsigned long) to_kvmdev(vdev)->desc);
|
|
}
|
|
|
|
/*
|
|
* When the virtio_ring code wants to notify the Host, it calls us here and we
|
|
* make a hypercall. We hand the address of the virtqueue so the Host
|
|
* knows which virtqueue we're talking about.
|
|
*/
|
|
static void kvm_notify(struct virtqueue *vq)
|
|
{
|
|
struct kvm_vqconfig *config = vq->priv;
|
|
|
|
kvm_hypercall1(KVM_S390_VIRTIO_NOTIFY, config->address);
|
|
}
|
|
|
|
/*
|
|
* This routine finds the first virtqueue described in the configuration of
|
|
* this device and sets it up.
|
|
*/
|
|
static struct virtqueue *kvm_find_vq(struct virtio_device *vdev,
|
|
unsigned index,
|
|
void (*callback)(struct virtqueue *vq))
|
|
{
|
|
struct kvm_device *kdev = to_kvmdev(vdev);
|
|
struct kvm_vqconfig *config;
|
|
struct virtqueue *vq;
|
|
int err;
|
|
|
|
if (index >= kdev->desc->num_vq)
|
|
return ERR_PTR(-ENOENT);
|
|
|
|
config = kvm_vq_config(kdev->desc)+index;
|
|
|
|
err = vmem_add_mapping(config->address,
|
|
vring_size(config->num, PAGE_SIZE));
|
|
if (err)
|
|
goto out;
|
|
|
|
vq = vring_new_virtqueue(config->num, vdev, (void *) config->address,
|
|
kvm_notify, callback);
|
|
if (!vq) {
|
|
err = -ENOMEM;
|
|
goto unmap;
|
|
}
|
|
|
|
/*
|
|
* register a callback token
|
|
* The host will sent this via the external interrupt parameter
|
|
*/
|
|
config->token = (u64) vq;
|
|
|
|
vq->priv = config;
|
|
return vq;
|
|
unmap:
|
|
vmem_remove_mapping(config->address,
|
|
vring_size(config->num, PAGE_SIZE));
|
|
out:
|
|
return ERR_PTR(err);
|
|
}
|
|
|
|
static void kvm_del_vq(struct virtqueue *vq)
|
|
{
|
|
struct kvm_vqconfig *config = vq->priv;
|
|
|
|
vring_del_virtqueue(vq);
|
|
vmem_remove_mapping(config->address,
|
|
vring_size(config->num, PAGE_SIZE));
|
|
}
|
|
|
|
/*
|
|
* The config ops structure as defined by virtio config
|
|
*/
|
|
static struct virtio_config_ops kvm_vq_configspace_ops = {
|
|
.get_features = kvm_get_features,
|
|
.set_features = kvm_set_features,
|
|
.get = kvm_get,
|
|
.set = kvm_set,
|
|
.get_status = kvm_get_status,
|
|
.set_status = kvm_set_status,
|
|
.reset = kvm_reset,
|
|
.find_vq = kvm_find_vq,
|
|
.del_vq = kvm_del_vq,
|
|
};
|
|
|
|
/*
|
|
* The root device for the kvm virtio devices.
|
|
* This makes them appear as /sys/devices/kvm_s390/0,1,2 not /sys/devices/0,1,2.
|
|
*/
|
|
static struct device kvm_root = {
|
|
.parent = NULL,
|
|
.bus_id = "kvm_s390",
|
|
};
|
|
|
|
/*
|
|
* adds a new device and register it with virtio
|
|
* appropriate drivers are loaded by the device model
|
|
*/
|
|
static void add_kvm_device(struct kvm_device_desc *d, unsigned int offset)
|
|
{
|
|
struct kvm_device *kdev;
|
|
|
|
kdev = kzalloc(sizeof(*kdev), GFP_KERNEL);
|
|
if (!kdev) {
|
|
printk(KERN_EMERG "Cannot allocate kvm dev %u type %u\n",
|
|
offset, d->type);
|
|
return;
|
|
}
|
|
|
|
kdev->vdev.dev.parent = &kvm_root;
|
|
kdev->vdev.id.device = d->type;
|
|
kdev->vdev.config = &kvm_vq_configspace_ops;
|
|
kdev->desc = d;
|
|
|
|
if (register_virtio_device(&kdev->vdev) != 0) {
|
|
printk(KERN_ERR "Failed to register kvm device %u type %u\n",
|
|
offset, d->type);
|
|
kfree(kdev);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* scan_devices() simply iterates through the device page.
|
|
* The type 0 is reserved to mean "end of devices".
|
|
*/
|
|
static void scan_devices(void)
|
|
{
|
|
unsigned int i;
|
|
struct kvm_device_desc *d;
|
|
|
|
for (i = 0; i < PAGE_SIZE; i += desc_size(d)) {
|
|
d = kvm_devices + i;
|
|
|
|
if (d->type == 0)
|
|
break;
|
|
|
|
add_kvm_device(d, i);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* we emulate the request_irq behaviour on top of s390 extints
|
|
*/
|
|
static void kvm_extint_handler(u16 code)
|
|
{
|
|
void *data = (void *) *(long *) __LC_PFAULT_INTPARM;
|
|
u16 subcode = S390_lowcore.cpu_addr;
|
|
|
|
if ((subcode & 0xff00) != VIRTIO_SUBCODE_64)
|
|
return;
|
|
|
|
vring_interrupt(0, data);
|
|
}
|
|
|
|
/*
|
|
* Init function for virtio
|
|
* devices are in a single page above top of "normal" mem
|
|
*/
|
|
static int __init kvm_devices_init(void)
|
|
{
|
|
int rc;
|
|
|
|
if (!MACHINE_IS_KVM)
|
|
return -ENODEV;
|
|
|
|
rc = device_register(&kvm_root);
|
|
if (rc) {
|
|
printk(KERN_ERR "Could not register kvm_s390 root device");
|
|
return rc;
|
|
}
|
|
|
|
rc = vmem_add_mapping(PFN_PHYS(max_pfn), PAGE_SIZE);
|
|
if (rc) {
|
|
device_unregister(&kvm_root);
|
|
return rc;
|
|
}
|
|
|
|
kvm_devices = (void *) PFN_PHYS(max_pfn);
|
|
|
|
ctl_set_bit(0, 9);
|
|
register_external_interrupt(0x2603, kvm_extint_handler);
|
|
|
|
scan_devices();
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* We do this after core stuff, but before the drivers.
|
|
*/
|
|
postcore_initcall(kvm_devices_init);
|