virtio_pci: split out legacy device support
Move everything dealing with legacy devices out to virtio_pci_legacy.c. Expose common code APIs in virtio_pci.h Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
This commit is contained in:
parent
6f8f23d63d
commit
38eb4a29a7
|
@ -14,179 +14,10 @@
|
|||
*
|
||||
*/
|
||||
|
||||
#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");
|
||||
|
||||
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;
|
||||
};
|
||||
|
||||
/* 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;
|
||||
|
||||
/* the IO mapping for ISR operation */
|
||||
void __iomem *isr;
|
||||
|
||||
/* a list of queues so we can dispatch IRQs */
|
||||
spinlock_t lock;
|
||||
struct list_head virtqueues;
|
||||
|
||||
/* array of all queues for house-keeping */
|
||||
struct virtio_pci_vq_info **vqs;
|
||||
|
||||
/* 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;
|
||||
|
||||
struct virtqueue *(*setup_vq)(struct virtio_pci_device *vp_dev,
|
||||
struct virtio_pci_vq_info *info,
|
||||
unsigned idx,
|
||||
void (*callback)(struct virtqueue *vq),
|
||||
const char *name,
|
||||
u16 msix_vec);
|
||||
void (*del_vq)(struct virtio_pci_vq_info *info);
|
||||
u16 (*config_vector)(struct virtio_pci_device *vp_dev, u16 vector);
|
||||
};
|
||||
|
||||
/* 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,
|
||||
};
|
||||
|
||||
/* 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 u64 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 int 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);
|
||||
|
||||
/* Make sure we don't have any features > 32 bits! */
|
||||
BUG_ON((u32)vdev->features != vdev->features);
|
||||
|
||||
/* We only support 32 feature bits. */
|
||||
iowrite32(vdev->features, vp_dev->ioaddr + VIRTIO_PCI_GUEST_FEATURES);
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
/* 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);
|
||||
}
|
||||
#include "virtio_pci_legacy.c"
|
||||
|
||||
/* wait for pending irq handlers */
|
||||
static void vp_synchronize_vectors(struct virtio_device *vdev)
|
||||
void vp_synchronize_vectors(struct virtio_device *vdev)
|
||||
{
|
||||
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
|
||||
int i;
|
||||
|
@ -198,20 +29,8 @@ static void vp_synchronize_vectors(struct virtio_device *vdev)
|
|||
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)
|
||||
bool vp_notify(struct virtqueue *vq)
|
||||
{
|
||||
/* we write the queue's selector into the notification register to
|
||||
* signal the other end */
|
||||
|
@ -272,15 +91,6 @@ static irqreturn_t vp_interrupt(int irq, void *opaque)
|
|||
return vp_vring_interrupt(irq, opaque);
|
||||
}
|
||||
|
||||
static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
|
||||
{
|
||||
/* Setup the vector used for configuration events */
|
||||
iowrite16(vector, vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
|
||||
/* Verify we had enough resources to assign the vector */
|
||||
/* Will also flush the write out to device */
|
||||
return ioread16(vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
|
||||
}
|
||||
|
||||
static void vp_free_vectors(struct virtio_device *vdev)
|
||||
{
|
||||
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
|
||||
|
@ -401,68 +211,6 @@ static int vp_request_intx(struct virtio_device *vdev)
|
|||
return err;
|
||||
}
|
||||
|
||||
static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
|
||||
struct virtio_pci_vq_info *info,
|
||||
unsigned index,
|
||||
void (*callback)(struct virtqueue *vq),
|
||||
const char *name,
|
||||
u16 msix_vec)
|
||||
{
|
||||
struct virtqueue *vq;
|
||||
unsigned long 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);
|
||||
|
||||
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)
|
||||
return ERR_PTR(-ENOMEM);
|
||||
|
||||
/* 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, &vp_dev->vdev,
|
||||
true, info->queue, vp_notify, callback, name);
|
||||
if (!vq) {
|
||||
err = -ENOMEM;
|
||||
goto out_activate_queue;
|
||||
}
|
||||
|
||||
vq->priv = (void __force *)vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY;
|
||||
|
||||
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;
|
||||
}
|
||||
}
|
||||
|
||||
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);
|
||||
return ERR_PTR(err);
|
||||
}
|
||||
|
||||
static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned index,
|
||||
void (*callback)(struct virtqueue *vq),
|
||||
const char *name,
|
||||
|
@ -498,30 +246,6 @@ out_info:
|
|||
return vq;
|
||||
}
|
||||
|
||||
static void del_vq(struct virtio_pci_vq_info *info)
|
||||
{
|
||||
struct virtqueue *vq = info->vq;
|
||||
struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
|
||||
unsigned long size;
|
||||
|
||||
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);
|
||||
}
|
||||
|
||||
static void vp_del_vq(struct virtqueue *vq)
|
||||
{
|
||||
struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
|
||||
|
@ -537,7 +261,7 @@ static void vp_del_vq(struct virtqueue *vq)
|
|||
}
|
||||
|
||||
/* the config->del_vqs() implementation */
|
||||
static void vp_del_vqs(struct virtio_device *vdev)
|
||||
void vp_del_vqs(struct virtio_device *vdev)
|
||||
{
|
||||
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
|
||||
struct virtqueue *vq, *n;
|
||||
|
@ -637,10 +361,10 @@ error_find:
|
|||
}
|
||||
|
||||
/* 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 vp_find_vqs(struct virtio_device *vdev, unsigned nvqs,
|
||||
struct virtqueue *vqs[],
|
||||
vq_callback_t *callbacks[],
|
||||
const char *names[])
|
||||
{
|
||||
int err;
|
||||
|
||||
|
@ -658,7 +382,7 @@ static int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs,
|
|||
false, false);
|
||||
}
|
||||
|
||||
static const char *vp_bus_name(struct virtio_device *vdev)
|
||||
const char *vp_bus_name(struct virtio_device *vdev)
|
||||
{
|
||||
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
|
||||
|
||||
|
@ -670,7 +394,7 @@ static const char *vp_bus_name(struct virtio_device *vdev)
|
|||
* - 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)
|
||||
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);
|
||||
|
@ -694,21 +418,7 @@ static int vp_set_vq_affinity(struct virtqueue *vq, int cpu)
|
|||
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)
|
||||
void virtio_pci_release_dev(struct device *_d)
|
||||
{
|
||||
/*
|
||||
* No need for a release method as we allocate/free
|
||||
|
@ -717,100 +427,6 @@ static void virtio_pci_release_dev(struct device *_d)
|
|||
*/
|
||||
}
|
||||
|
||||
/* 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;
|
||||
}
|
||||
|
||||
vp_dev->isr = vp_dev->ioaddr + VIRTIO_PCI_ISR;
|
||||
|
||||
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;
|
||||
|
||||
vp_dev->config_vector = vp_config_vector;
|
||||
vp_dev->setup_vq = setup_vq;
|
||||
vp_dev->del_vq = del_vq;
|
||||
|
||||
/* 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)
|
||||
{
|
||||
|
@ -839,19 +455,7 @@ static int virtio_pci_restore(struct device *dev)
|
|||
return virtio_device_restore(&vp_dev->vdev);
|
||||
}
|
||||
|
||||
static const struct dev_pm_ops virtio_pci_pm_ops = {
|
||||
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);
|
||||
|
|
|
@ -0,0 +1,133 @@
|
|||
#ifndef _DRIVERS_VIRTIO_VIRTIO_PCI_H
|
||||
#define _DRIVERS_VIRTIO_VIRTIO_PCI_H
|
||||
/*
|
||||
* 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>
|
||||
#define VIRTIO_PCI_NO_LEGACY
|
||||
#include <linux/virtio_pci.h>
|
||||
#include <linux/highmem.h>
|
||||
#include <linux/spinlock.h>
|
||||
|
||||
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;
|
||||
};
|
||||
|
||||
/* 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;
|
||||
|
||||
/* the IO mapping for ISR operation */
|
||||
void __iomem *isr;
|
||||
|
||||
/* a list of queues so we can dispatch IRQs */
|
||||
spinlock_t lock;
|
||||
struct list_head virtqueues;
|
||||
|
||||
/* array of all queues for house-keeping */
|
||||
struct virtio_pci_vq_info **vqs;
|
||||
|
||||
/* 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;
|
||||
|
||||
struct virtqueue *(*setup_vq)(struct virtio_pci_device *vp_dev,
|
||||
struct virtio_pci_vq_info *info,
|
||||
unsigned idx,
|
||||
void (*callback)(struct virtqueue *vq),
|
||||
const char *name,
|
||||
u16 msix_vec);
|
||||
void (*del_vq)(struct virtio_pci_vq_info *info);
|
||||
|
||||
u16 (*config_vector)(struct virtio_pci_device *vp_dev, u16 vector);
|
||||
};
|
||||
|
||||
/* 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,
|
||||
};
|
||||
|
||||
/* 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);
|
||||
}
|
||||
|
||||
/* wait for pending irq handlers */
|
||||
void vp_synchronize_vectors(struct virtio_device *vdev);
|
||||
/* the notify function used when creating a virt queue */
|
||||
bool vp_notify(struct virtqueue *vq);
|
||||
/* the config->del_vqs() implementation */
|
||||
void vp_del_vqs(struct virtio_device *vdev);
|
||||
/* the config->find_vqs() implementation */
|
||||
int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs,
|
||||
struct virtqueue *vqs[],
|
||||
vq_callback_t *callbacks[],
|
||||
const char *names[]);
|
||||
const char *vp_bus_name(struct virtio_device *vdev);
|
||||
|
||||
/* 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
|
||||
*/
|
||||
int vp_set_vq_affinity(struct virtqueue *vq, int cpu);
|
||||
void virtio_pci_release_dev(struct device *);
|
||||
|
||||
#ifdef CONFIG_PM_SLEEP
|
||||
extern const struct dev_pm_ops virtio_pci_pm_ops;
|
||||
#endif
|
||||
|
||||
#endif
|
|
@ -0,0 +1,323 @@
|
|||
/*
|
||||
* 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 "virtio_pci.h"
|
||||
|
||||
/* 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);
|
||||
|
||||
/* virtio config->get_features() implementation */
|
||||
static u64 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 int 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);
|
||||
|
||||
/* Make sure we don't have any features > 32 bits! */
|
||||
BUG_ON((u32)vdev->features != vdev->features);
|
||||
|
||||
/* We only support 32 feature bits. */
|
||||
iowrite32(vdev->features, vp_dev->ioaddr + VIRTIO_PCI_GUEST_FEATURES);
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
/* 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);
|
||||
}
|
||||
|
||||
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);
|
||||
}
|
||||
|
||||
static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
|
||||
{
|
||||
/* Setup the vector used for configuration events */
|
||||
iowrite16(vector, vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
|
||||
/* Verify we had enough resources to assign the vector */
|
||||
/* Will also flush the write out to device */
|
||||
return ioread16(vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
|
||||
}
|
||||
|
||||
static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
|
||||
struct virtio_pci_vq_info *info,
|
||||
unsigned index,
|
||||
void (*callback)(struct virtqueue *vq),
|
||||
const char *name,
|
||||
u16 msix_vec)
|
||||
{
|
||||
struct virtqueue *vq;
|
||||
unsigned long 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);
|
||||
|
||||
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)
|
||||
return ERR_PTR(-ENOMEM);
|
||||
|
||||
/* 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, &vp_dev->vdev,
|
||||
true, info->queue, vp_notify, callback, name);
|
||||
if (!vq) {
|
||||
err = -ENOMEM;
|
||||
goto out_activate_queue;
|
||||
}
|
||||
|
||||
vq->priv = (void __force *)vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY;
|
||||
|
||||
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;
|
||||
}
|
||||
}
|
||||
|
||||
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);
|
||||
return ERR_PTR(err);
|
||||
}
|
||||
|
||||
static void del_vq(struct virtio_pci_vq_info *info)
|
||||
{
|
||||
struct virtqueue *vq = info->vq;
|
||||
struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
|
||||
unsigned long size;
|
||||
|
||||
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);
|
||||
}
|
||||
|
||||
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,
|
||||
};
|
||||
|
||||
/* 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;
|
||||
}
|
||||
|
||||
vp_dev->isr = vp_dev->ioaddr + VIRTIO_PCI_ISR;
|
||||
|
||||
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;
|
||||
|
||||
vp_dev->config_vector = vp_config_vector;
|
||||
vp_dev->setup_vq = setup_vq;
|
||||
vp_dev->del_vq = del_vq;
|
||||
|
||||
/* 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);
|
||||
}
|
||||
|
||||
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);
|
Loading…
Reference in New Issue