mirror of
https://github.com/torvalds/linux.git
synced 2024-12-26 12:52:30 +00:00
6e52fc446d
This patch introduces helper for getting queue num of modern device. Signed-off-by: Jason Wang <jasowang@redhat.com> Link: https://lore.kernel.org/r/20210104065503.199631-14-jasowang@redhat.com Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
1064 lines
29 KiB
C
1064 lines
29 KiB
C
// SPDX-License-Identifier: GPL-2.0-or-later
|
|
/*
|
|
* Virtio PCI driver - modern (virtio 1.0) device support
|
|
*
|
|
* 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
|
|
* Copyright Red Hat, Inc. 2014
|
|
*
|
|
* Authors:
|
|
* Anthony Liguori <aliguori@us.ibm.com>
|
|
* Rusty Russell <rusty@rustcorp.com.au>
|
|
* Michael S. Tsirkin <mst@redhat.com>
|
|
*/
|
|
|
|
#include <linux/delay.h>
|
|
#define VIRTIO_PCI_NO_LEGACY
|
|
#define VIRTIO_RING_NO_LEGACY
|
|
#include "virtio_pci_common.h"
|
|
|
|
/*
|
|
* Type-safe wrappers for io accesses.
|
|
* Use these to enforce at compile time the following spec requirement:
|
|
*
|
|
* The driver MUST access each field using the “natural” access
|
|
* method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses
|
|
* for 16-bit fields and 8-bit accesses for 8-bit fields.
|
|
*/
|
|
static inline u8 vp_ioread8(const u8 __iomem *addr)
|
|
{
|
|
return ioread8(addr);
|
|
}
|
|
static inline u16 vp_ioread16 (const __le16 __iomem *addr)
|
|
{
|
|
return ioread16(addr);
|
|
}
|
|
|
|
static inline u32 vp_ioread32(const __le32 __iomem *addr)
|
|
{
|
|
return ioread32(addr);
|
|
}
|
|
|
|
static inline void vp_iowrite8(u8 value, u8 __iomem *addr)
|
|
{
|
|
iowrite8(value, addr);
|
|
}
|
|
|
|
static inline void vp_iowrite16(u16 value, __le16 __iomem *addr)
|
|
{
|
|
iowrite16(value, addr);
|
|
}
|
|
|
|
static inline void vp_iowrite32(u32 value, __le32 __iomem *addr)
|
|
{
|
|
iowrite32(value, addr);
|
|
}
|
|
|
|
static void vp_iowrite64_twopart(u64 val,
|
|
__le32 __iomem *lo, __le32 __iomem *hi)
|
|
{
|
|
vp_iowrite32((u32)val, lo);
|
|
vp_iowrite32(val >> 32, hi);
|
|
}
|
|
|
|
static void __iomem *map_capability(struct pci_dev *dev, int off,
|
|
size_t minlen,
|
|
u32 align,
|
|
u32 start, u32 size,
|
|
size_t *len)
|
|
{
|
|
u8 bar;
|
|
u32 offset, length;
|
|
void __iomem *p;
|
|
|
|
pci_read_config_byte(dev, off + offsetof(struct virtio_pci_cap,
|
|
bar),
|
|
&bar);
|
|
pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, offset),
|
|
&offset);
|
|
pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, length),
|
|
&length);
|
|
|
|
if (length <= start) {
|
|
dev_err(&dev->dev,
|
|
"virtio_pci: bad capability len %u (>%u expected)\n",
|
|
length, start);
|
|
return NULL;
|
|
}
|
|
|
|
if (length - start < minlen) {
|
|
dev_err(&dev->dev,
|
|
"virtio_pci: bad capability len %u (>=%zu expected)\n",
|
|
length, minlen);
|
|
return NULL;
|
|
}
|
|
|
|
length -= start;
|
|
|
|
if (start + offset < offset) {
|
|
dev_err(&dev->dev,
|
|
"virtio_pci: map wrap-around %u+%u\n",
|
|
start, offset);
|
|
return NULL;
|
|
}
|
|
|
|
offset += start;
|
|
|
|
if (offset & (align - 1)) {
|
|
dev_err(&dev->dev,
|
|
"virtio_pci: offset %u not aligned to %u\n",
|
|
offset, align);
|
|
return NULL;
|
|
}
|
|
|
|
if (length > size)
|
|
length = size;
|
|
|
|
if (len)
|
|
*len = length;
|
|
|
|
if (minlen + offset < minlen ||
|
|
minlen + offset > pci_resource_len(dev, bar)) {
|
|
dev_err(&dev->dev,
|
|
"virtio_pci: map virtio %zu@%u "
|
|
"out of range on bar %i length %lu\n",
|
|
minlen, offset,
|
|
bar, (unsigned long)pci_resource_len(dev, bar));
|
|
return NULL;
|
|
}
|
|
|
|
p = pci_iomap_range(dev, bar, offset, length);
|
|
if (!p)
|
|
dev_err(&dev->dev,
|
|
"virtio_pci: unable to map virtio %u@%u on bar %i\n",
|
|
length, offset, bar);
|
|
return p;
|
|
}
|
|
|
|
/*
|
|
* vp_modern_get_features - get features from device
|
|
* @mdev: the modern virtio-pci device
|
|
*
|
|
* Returns the features read from the device
|
|
*/
|
|
static u64 vp_modern_get_features(struct virtio_pci_modern_device *mdev)
|
|
{
|
|
struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
|
|
|
|
u64 features;
|
|
|
|
vp_iowrite32(0, &cfg->device_feature_select);
|
|
features = vp_ioread32(&cfg->device_feature);
|
|
vp_iowrite32(1, &cfg->device_feature_select);
|
|
features |= ((u64)vp_ioread32(&cfg->device_feature) << 32);
|
|
|
|
return features;
|
|
}
|
|
|
|
/* virtio config->get_features() implementation */
|
|
static u64 vp_get_features(struct virtio_device *vdev)
|
|
{
|
|
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
|
|
|
|
return vp_modern_get_features(&vp_dev->mdev);
|
|
}
|
|
|
|
static void vp_transport_features(struct virtio_device *vdev, u64 features)
|
|
{
|
|
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
|
|
struct pci_dev *pci_dev = vp_dev->pci_dev;
|
|
|
|
if ((features & BIT_ULL(VIRTIO_F_SR_IOV)) &&
|
|
pci_find_ext_capability(pci_dev, PCI_EXT_CAP_ID_SRIOV))
|
|
__virtio_set_bit(vdev, VIRTIO_F_SR_IOV);
|
|
}
|
|
|
|
/*
|
|
* vp_modern_set_features - set features to device
|
|
* @mdev: the modern virtio-pci device
|
|
* @features: the features set to device
|
|
*/
|
|
static void vp_modern_set_features(struct virtio_pci_modern_device *mdev,
|
|
u64 features)
|
|
{
|
|
struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
|
|
|
|
vp_iowrite32(0, &cfg->guest_feature_select);
|
|
vp_iowrite32((u32)features, &cfg->guest_feature);
|
|
vp_iowrite32(1, &cfg->guest_feature_select);
|
|
vp_iowrite32(features >> 32, &cfg->guest_feature);
|
|
}
|
|
|
|
/*
|
|
* vp_modern_queue_vector - set the MSIX vector for a specific virtqueue
|
|
* @mdev: the modern virtio-pci device
|
|
* @index: queue index
|
|
* @vector: the config vector
|
|
*
|
|
* Returns the config vector read from the device
|
|
*/
|
|
static u16 vp_modern_queue_vector(struct virtio_pci_modern_device *mdev,
|
|
u16 index, u16 vector)
|
|
{
|
|
struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
|
|
|
|
vp_iowrite16(index, &cfg->queue_select);
|
|
vp_iowrite16(vector, &cfg->queue_msix_vector);
|
|
/* Flush the write out to device */
|
|
return vp_ioread16(&cfg->queue_msix_vector);
|
|
}
|
|
|
|
/*
|
|
* vp_modern_queue_address - set the virtqueue address
|
|
* @mdev: the modern virtio-pci device
|
|
* @index: the queue index
|
|
* @desc_addr: address of the descriptor area
|
|
* @driver_addr: address of the driver area
|
|
* @device_addr: address of the device area
|
|
*/
|
|
static void vp_modern_queue_address(struct virtio_pci_modern_device *mdev,
|
|
u16 index, u64 desc_addr, u64 driver_addr,
|
|
u64 device_addr)
|
|
{
|
|
struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
|
|
|
|
vp_iowrite16(index, &cfg->queue_select);
|
|
|
|
vp_iowrite64_twopart(desc_addr, &cfg->queue_desc_lo,
|
|
&cfg->queue_desc_hi);
|
|
vp_iowrite64_twopart(driver_addr, &cfg->queue_avail_lo,
|
|
&cfg->queue_avail_hi);
|
|
vp_iowrite64_twopart(device_addr, &cfg->queue_used_lo,
|
|
&cfg->queue_used_hi);
|
|
}
|
|
|
|
/*
|
|
* vp_modern_set_queue_enable - enable a virtqueue
|
|
* @mdev: the modern virtio-pci device
|
|
* @index: the queue index
|
|
* @enable: whether the virtqueue is enable or not
|
|
*/
|
|
static void vp_modern_set_queue_enable(struct virtio_pci_modern_device *mdev,
|
|
u16 index, bool enable)
|
|
{
|
|
vp_iowrite16(index, &mdev->common->queue_select);
|
|
vp_iowrite16(enable, &mdev->common->queue_enable);
|
|
}
|
|
|
|
/*
|
|
* vp_modern_get_queue_enable - enable a virtqueue
|
|
* @mdev: the modern virtio-pci device
|
|
* @index: the queue index
|
|
*
|
|
* Returns whether a virtqueue is enabled or not
|
|
*/
|
|
static bool vp_modern_get_queue_enable(struct virtio_pci_modern_device *mdev,
|
|
u16 index)
|
|
{
|
|
vp_iowrite16(index, &mdev->common->queue_select);
|
|
|
|
return vp_ioread16(&mdev->common->queue_enable);
|
|
}
|
|
|
|
/*
|
|
* vp_modern_set_queue_size - set size for a virtqueue
|
|
* @mdev: the modern virtio-pci device
|
|
* @index: the queue index
|
|
* @size: the size of the virtqueue
|
|
*/
|
|
static void vp_modern_set_queue_size(struct virtio_pci_modern_device *mdev,
|
|
u16 index, u16 size)
|
|
{
|
|
vp_iowrite16(index, &mdev->common->queue_select);
|
|
vp_iowrite16(size, &mdev->common->queue_size);
|
|
|
|
}
|
|
|
|
/*
|
|
* vp_modern_get_queue_size - get size for a virtqueue
|
|
* @mdev: the modern virtio-pci device
|
|
* @index: the queue index
|
|
*
|
|
* Returns the size of the virtqueue
|
|
*/
|
|
static u16 vp_modern_get_queue_size(struct virtio_pci_modern_device *mdev,
|
|
u16 index)
|
|
{
|
|
vp_iowrite16(index, &mdev->common->queue_select);
|
|
|
|
return vp_ioread16(&mdev->common->queue_size);
|
|
|
|
}
|
|
|
|
/*
|
|
* vp_modern_get_num_queues - get the number of virtqueues
|
|
* @mdev: the modern virtio-pci device
|
|
*
|
|
* Returns the number of virtqueues
|
|
*/
|
|
static u16 vp_modern_get_num_queues(struct virtio_pci_modern_device *mdev)
|
|
{
|
|
return vp_ioread16(&mdev->common->num_queues);
|
|
}
|
|
|
|
/* virtio config->finalize_features() implementation */
|
|
static int vp_finalize_features(struct virtio_device *vdev)
|
|
{
|
|
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
|
|
u64 features = vdev->features;
|
|
|
|
/* Give virtio_ring a chance to accept features. */
|
|
vring_transport_features(vdev);
|
|
|
|
/* Give virtio_pci a chance to accept features. */
|
|
vp_transport_features(vdev, features);
|
|
|
|
if (!__virtio_test_bit(vdev, VIRTIO_F_VERSION_1)) {
|
|
dev_err(&vdev->dev, "virtio: device uses modern interface "
|
|
"but does not have VIRTIO_F_VERSION_1\n");
|
|
return -EINVAL;
|
|
}
|
|
|
|
vp_modern_set_features(&vp_dev->mdev, vdev->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);
|
|
struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
|
|
void __iomem *device = mdev->device;
|
|
u8 b;
|
|
__le16 w;
|
|
__le32 l;
|
|
|
|
BUG_ON(offset + len > mdev->device_len);
|
|
|
|
switch (len) {
|
|
case 1:
|
|
b = ioread8(device + offset);
|
|
memcpy(buf, &b, sizeof b);
|
|
break;
|
|
case 2:
|
|
w = cpu_to_le16(ioread16(device + offset));
|
|
memcpy(buf, &w, sizeof w);
|
|
break;
|
|
case 4:
|
|
l = cpu_to_le32(ioread32(device + offset));
|
|
memcpy(buf, &l, sizeof l);
|
|
break;
|
|
case 8:
|
|
l = cpu_to_le32(ioread32(device + offset));
|
|
memcpy(buf, &l, sizeof l);
|
|
l = cpu_to_le32(ioread32(device + offset + sizeof l));
|
|
memcpy(buf + sizeof l, &l, sizeof l);
|
|
break;
|
|
default:
|
|
BUG();
|
|
}
|
|
}
|
|
|
|
/* 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);
|
|
struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
|
|
void __iomem *device = mdev->device;
|
|
u8 b;
|
|
__le16 w;
|
|
__le32 l;
|
|
|
|
BUG_ON(offset + len > mdev->device_len);
|
|
|
|
switch (len) {
|
|
case 1:
|
|
memcpy(&b, buf, sizeof b);
|
|
iowrite8(b, device + offset);
|
|
break;
|
|
case 2:
|
|
memcpy(&w, buf, sizeof w);
|
|
iowrite16(le16_to_cpu(w), device + offset);
|
|
break;
|
|
case 4:
|
|
memcpy(&l, buf, sizeof l);
|
|
iowrite32(le32_to_cpu(l), device + offset);
|
|
break;
|
|
case 8:
|
|
memcpy(&l, buf, sizeof l);
|
|
iowrite32(le32_to_cpu(l), device + offset);
|
|
memcpy(&l, buf + sizeof l, sizeof l);
|
|
iowrite32(le32_to_cpu(l), device + offset + sizeof l);
|
|
break;
|
|
default:
|
|
BUG();
|
|
}
|
|
}
|
|
|
|
/*
|
|
* vp_modern_generation - get the device genreation
|
|
* @mdev: the modern virtio-pci device
|
|
*
|
|
* Returns the genreation read from device
|
|
*/
|
|
static u32 vp_modern_generation(struct virtio_pci_modern_device *mdev)
|
|
{
|
|
struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
|
|
|
|
return vp_ioread8(&cfg->config_generation);
|
|
}
|
|
|
|
static u32 vp_generation(struct virtio_device *vdev)
|
|
{
|
|
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
|
|
|
|
return vp_modern_generation(&vp_dev->mdev);
|
|
}
|
|
|
|
/*
|
|
* vp_modern_get_status - get the device status
|
|
* @mdev: the modern virtio-pci device
|
|
*
|
|
* Returns the status read from device
|
|
*/
|
|
static u8 vp_modern_get_status(struct virtio_pci_modern_device *mdev)
|
|
{
|
|
struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
|
|
|
|
return vp_ioread8(&cfg->device_status);
|
|
}
|
|
|
|
/* 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 vp_modern_get_status(&vp_dev->mdev);
|
|
}
|
|
|
|
/*
|
|
* vp_modern_set_status - set status to device
|
|
* @mdev: the modern virtio-pci device
|
|
* @status: the status set to device
|
|
*/
|
|
static void vp_modern_set_status(struct virtio_pci_modern_device *mdev,
|
|
u8 status)
|
|
{
|
|
struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
|
|
|
|
vp_iowrite8(status, &cfg->device_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);
|
|
vp_modern_set_status(&vp_dev->mdev, status);
|
|
}
|
|
|
|
static void vp_reset(struct virtio_device *vdev)
|
|
{
|
|
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
|
|
struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
|
|
|
|
/* 0 status means a reset. */
|
|
vp_modern_set_status(mdev, 0);
|
|
/* After writing 0 to device_status, the driver MUST wait for a read of
|
|
* device_status to return 0 before reinitializing the device.
|
|
* This will flush out the status write, and flush in device writes,
|
|
* including MSI-X interrupts, if any.
|
|
*/
|
|
while (vp_modern_get_status(mdev))
|
|
msleep(1);
|
|
/* Flush pending VQ/configuration callbacks. */
|
|
vp_synchronize_vectors(vdev);
|
|
}
|
|
|
|
/*
|
|
* vp_modern_config_vector - set the vector for config interrupt
|
|
* @mdev: the modern virtio-pci device
|
|
* @vector: the config vector
|
|
*
|
|
* Returns the config vector read from the device
|
|
*/
|
|
static u16 vp_modern_config_vector(struct virtio_pci_modern_device *mdev,
|
|
u16 vector)
|
|
{
|
|
struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
|
|
|
|
/* Setup the vector used for configuration events */
|
|
vp_iowrite16(vector, &cfg->msix_config);
|
|
/* Verify we had enough resources to assign the vector */
|
|
/* Will also flush the write out to device */
|
|
return vp_ioread16(&cfg->msix_config);
|
|
}
|
|
|
|
static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
|
|
{
|
|
return vp_modern_config_vector(&vp_dev->mdev, 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,
|
|
bool ctx,
|
|
u16 msix_vec)
|
|
{
|
|
|
|
struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
|
|
struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
|
|
struct virtqueue *vq;
|
|
u16 num, off;
|
|
int err;
|
|
|
|
if (index >= vp_modern_get_num_queues(mdev))
|
|
return ERR_PTR(-ENOENT);
|
|
|
|
/* Select the queue we're interested in */
|
|
vp_iowrite16(index, &cfg->queue_select);
|
|
|
|
/* Check if queue is either not available or already active. */
|
|
num = vp_modern_get_queue_size(mdev, index);
|
|
if (!num || vp_modern_get_queue_enable(mdev, index))
|
|
return ERR_PTR(-ENOENT);
|
|
|
|
if (num & (num - 1)) {
|
|
dev_warn(&vp_dev->pci_dev->dev, "bad queue size %u", num);
|
|
return ERR_PTR(-EINVAL);
|
|
}
|
|
|
|
/* get offset of notification word for this vq */
|
|
off = vp_ioread16(&cfg->queue_notify_off);
|
|
|
|
info->msix_vector = msix_vec;
|
|
|
|
/* create the vring */
|
|
vq = vring_create_virtqueue(index, num,
|
|
SMP_CACHE_BYTES, &vp_dev->vdev,
|
|
true, true, ctx,
|
|
vp_notify, callback, name);
|
|
if (!vq)
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
/* activate the queue */
|
|
vp_modern_set_queue_size(mdev, index, virtqueue_get_vring_size(vq));
|
|
vp_modern_queue_address(mdev, index, virtqueue_get_desc_addr(vq),
|
|
virtqueue_get_avail_addr(vq),
|
|
virtqueue_get_used_addr(vq));
|
|
|
|
if (mdev->notify_base) {
|
|
/* offset should not wrap */
|
|
if ((u64)off * mdev->notify_offset_multiplier + 2
|
|
> mdev->notify_len) {
|
|
dev_warn(&mdev->pci_dev->dev,
|
|
"bad notification offset %u (x %u) "
|
|
"for queue %u > %zd",
|
|
off, mdev->notify_offset_multiplier,
|
|
index, mdev->notify_len);
|
|
err = -EINVAL;
|
|
goto err_map_notify;
|
|
}
|
|
vq->priv = (void __force *)mdev->notify_base +
|
|
off * mdev->notify_offset_multiplier;
|
|
} else {
|
|
vq->priv = (void __force *)map_capability(mdev->pci_dev,
|
|
mdev->notify_map_cap, 2, 2,
|
|
off * mdev->notify_offset_multiplier, 2,
|
|
NULL);
|
|
}
|
|
|
|
if (!vq->priv) {
|
|
err = -ENOMEM;
|
|
goto err_map_notify;
|
|
}
|
|
|
|
if (msix_vec != VIRTIO_MSI_NO_VECTOR) {
|
|
msix_vec = vp_modern_queue_vector(mdev, index, msix_vec);
|
|
if (msix_vec == VIRTIO_MSI_NO_VECTOR) {
|
|
err = -EBUSY;
|
|
goto err_assign_vector;
|
|
}
|
|
}
|
|
|
|
return vq;
|
|
|
|
err_assign_vector:
|
|
if (!mdev->notify_base)
|
|
pci_iounmap(mdev->pci_dev, (void __iomem __force *)vq->priv);
|
|
err_map_notify:
|
|
vring_del_virtqueue(vq);
|
|
return ERR_PTR(err);
|
|
}
|
|
|
|
static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned nvqs,
|
|
struct virtqueue *vqs[],
|
|
vq_callback_t *callbacks[],
|
|
const char * const names[], const bool *ctx,
|
|
struct irq_affinity *desc)
|
|
{
|
|
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
|
|
struct virtqueue *vq;
|
|
int rc = vp_find_vqs(vdev, nvqs, vqs, callbacks, names, ctx, desc);
|
|
|
|
if (rc)
|
|
return rc;
|
|
|
|
/* Select and activate all queues. Has to be done last: once we do
|
|
* this, there's no way to go back except reset.
|
|
*/
|
|
list_for_each_entry(vq, &vdev->vqs, list)
|
|
vp_modern_set_queue_enable(&vp_dev->mdev, vq->index, true);
|
|
|
|
return 0;
|
|
}
|
|
|
|
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);
|
|
struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
|
|
|
|
if (vp_dev->msix_enabled)
|
|
vp_modern_queue_vector(mdev, vq->index,
|
|
VIRTIO_MSI_NO_VECTOR);
|
|
|
|
if (!mdev->notify_base)
|
|
pci_iounmap(mdev->pci_dev, (void __force __iomem *)vq->priv);
|
|
|
|
vring_del_virtqueue(vq);
|
|
}
|
|
|
|
static int virtio_pci_find_shm_cap(struct pci_dev *dev, u8 required_id,
|
|
u8 *bar, u64 *offset, u64 *len)
|
|
{
|
|
int pos;
|
|
|
|
for (pos = pci_find_capability(dev, PCI_CAP_ID_VNDR); pos > 0;
|
|
pos = pci_find_next_capability(dev, pos, PCI_CAP_ID_VNDR)) {
|
|
u8 type, cap_len, id;
|
|
u32 tmp32;
|
|
u64 res_offset, res_length;
|
|
|
|
pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
|
|
cfg_type), &type);
|
|
if (type != VIRTIO_PCI_CAP_SHARED_MEMORY_CFG)
|
|
continue;
|
|
|
|
pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
|
|
cap_len), &cap_len);
|
|
if (cap_len != sizeof(struct virtio_pci_cap64)) {
|
|
dev_err(&dev->dev, "%s: shm cap with bad size offset:"
|
|
" %d size: %d\n", __func__, pos, cap_len);
|
|
continue;
|
|
}
|
|
|
|
pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
|
|
id), &id);
|
|
if (id != required_id)
|
|
continue;
|
|
|
|
/* Type, and ID match, looks good */
|
|
pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
|
|
bar), bar);
|
|
|
|
/* Read the lower 32bit of length and offset */
|
|
pci_read_config_dword(dev, pos + offsetof(struct virtio_pci_cap,
|
|
offset), &tmp32);
|
|
res_offset = tmp32;
|
|
pci_read_config_dword(dev, pos + offsetof(struct virtio_pci_cap,
|
|
length), &tmp32);
|
|
res_length = tmp32;
|
|
|
|
/* and now the top half */
|
|
pci_read_config_dword(dev,
|
|
pos + offsetof(struct virtio_pci_cap64,
|
|
offset_hi), &tmp32);
|
|
res_offset |= ((u64)tmp32) << 32;
|
|
pci_read_config_dword(dev,
|
|
pos + offsetof(struct virtio_pci_cap64,
|
|
length_hi), &tmp32);
|
|
res_length |= ((u64)tmp32) << 32;
|
|
|
|
*offset = res_offset;
|
|
*len = res_length;
|
|
|
|
return pos;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static bool vp_get_shm_region(struct virtio_device *vdev,
|
|
struct virtio_shm_region *region, u8 id)
|
|
{
|
|
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
|
|
struct pci_dev *pci_dev = vp_dev->pci_dev;
|
|
u8 bar;
|
|
u64 offset, len;
|
|
phys_addr_t phys_addr;
|
|
size_t bar_len;
|
|
|
|
if (!virtio_pci_find_shm_cap(pci_dev, id, &bar, &offset, &len))
|
|
return false;
|
|
|
|
phys_addr = pci_resource_start(pci_dev, bar);
|
|
bar_len = pci_resource_len(pci_dev, bar);
|
|
|
|
if ((offset + len) < offset) {
|
|
dev_err(&pci_dev->dev, "%s: cap offset+len overflow detected\n",
|
|
__func__);
|
|
return false;
|
|
}
|
|
|
|
if (offset + len > bar_len) {
|
|
dev_err(&pci_dev->dev, "%s: bar shorter than cap offset+len\n",
|
|
__func__);
|
|
return false;
|
|
}
|
|
|
|
region->len = len;
|
|
region->addr = (u64) phys_addr + offset;
|
|
|
|
return true;
|
|
}
|
|
|
|
static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
|
|
.get = NULL,
|
|
.set = NULL,
|
|
.generation = vp_generation,
|
|
.get_status = vp_get_status,
|
|
.set_status = vp_set_status,
|
|
.reset = vp_reset,
|
|
.find_vqs = vp_modern_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,
|
|
.get_vq_affinity = vp_get_vq_affinity,
|
|
.get_shm_region = vp_get_shm_region,
|
|
};
|
|
|
|
static const struct virtio_config_ops virtio_pci_config_ops = {
|
|
.get = vp_get,
|
|
.set = vp_set,
|
|
.generation = vp_generation,
|
|
.get_status = vp_get_status,
|
|
.set_status = vp_set_status,
|
|
.reset = vp_reset,
|
|
.find_vqs = vp_modern_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,
|
|
.get_vq_affinity = vp_get_vq_affinity,
|
|
.get_shm_region = vp_get_shm_region,
|
|
};
|
|
|
|
/**
|
|
* virtio_pci_find_capability - walk capabilities to find device info.
|
|
* @dev: the pci device
|
|
* @cfg_type: the VIRTIO_PCI_CAP_* value we seek
|
|
* @ioresource_types: IORESOURCE_MEM and/or IORESOURCE_IO.
|
|
* @bars: the bitmask of BARs
|
|
*
|
|
* Returns offset of the capability, or 0.
|
|
*/
|
|
static inline int virtio_pci_find_capability(struct pci_dev *dev, u8 cfg_type,
|
|
u32 ioresource_types, int *bars)
|
|
{
|
|
int pos;
|
|
|
|
for (pos = pci_find_capability(dev, PCI_CAP_ID_VNDR);
|
|
pos > 0;
|
|
pos = pci_find_next_capability(dev, pos, PCI_CAP_ID_VNDR)) {
|
|
u8 type, bar;
|
|
pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
|
|
cfg_type),
|
|
&type);
|
|
pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
|
|
bar),
|
|
&bar);
|
|
|
|
/* Ignore structures with reserved BAR values */
|
|
if (bar > 0x5)
|
|
continue;
|
|
|
|
if (type == cfg_type) {
|
|
if (pci_resource_len(dev, bar) &&
|
|
pci_resource_flags(dev, bar) & ioresource_types) {
|
|
*bars |= (1 << bar);
|
|
return pos;
|
|
}
|
|
}
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
/* This is part of the ABI. Don't screw with it. */
|
|
static inline void check_offsets(void)
|
|
{
|
|
/* Note: disk space was harmed in compilation of this function. */
|
|
BUILD_BUG_ON(VIRTIO_PCI_CAP_VNDR !=
|
|
offsetof(struct virtio_pci_cap, cap_vndr));
|
|
BUILD_BUG_ON(VIRTIO_PCI_CAP_NEXT !=
|
|
offsetof(struct virtio_pci_cap, cap_next));
|
|
BUILD_BUG_ON(VIRTIO_PCI_CAP_LEN !=
|
|
offsetof(struct virtio_pci_cap, cap_len));
|
|
BUILD_BUG_ON(VIRTIO_PCI_CAP_CFG_TYPE !=
|
|
offsetof(struct virtio_pci_cap, cfg_type));
|
|
BUILD_BUG_ON(VIRTIO_PCI_CAP_BAR !=
|
|
offsetof(struct virtio_pci_cap, bar));
|
|
BUILD_BUG_ON(VIRTIO_PCI_CAP_OFFSET !=
|
|
offsetof(struct virtio_pci_cap, offset));
|
|
BUILD_BUG_ON(VIRTIO_PCI_CAP_LENGTH !=
|
|
offsetof(struct virtio_pci_cap, length));
|
|
BUILD_BUG_ON(VIRTIO_PCI_NOTIFY_CAP_MULT !=
|
|
offsetof(struct virtio_pci_notify_cap,
|
|
notify_off_multiplier));
|
|
BUILD_BUG_ON(VIRTIO_PCI_COMMON_DFSELECT !=
|
|
offsetof(struct virtio_pci_common_cfg,
|
|
device_feature_select));
|
|
BUILD_BUG_ON(VIRTIO_PCI_COMMON_DF !=
|
|
offsetof(struct virtio_pci_common_cfg, device_feature));
|
|
BUILD_BUG_ON(VIRTIO_PCI_COMMON_GFSELECT !=
|
|
offsetof(struct virtio_pci_common_cfg,
|
|
guest_feature_select));
|
|
BUILD_BUG_ON(VIRTIO_PCI_COMMON_GF !=
|
|
offsetof(struct virtio_pci_common_cfg, guest_feature));
|
|
BUILD_BUG_ON(VIRTIO_PCI_COMMON_MSIX !=
|
|
offsetof(struct virtio_pci_common_cfg, msix_config));
|
|
BUILD_BUG_ON(VIRTIO_PCI_COMMON_NUMQ !=
|
|
offsetof(struct virtio_pci_common_cfg, num_queues));
|
|
BUILD_BUG_ON(VIRTIO_PCI_COMMON_STATUS !=
|
|
offsetof(struct virtio_pci_common_cfg, device_status));
|
|
BUILD_BUG_ON(VIRTIO_PCI_COMMON_CFGGENERATION !=
|
|
offsetof(struct virtio_pci_common_cfg, config_generation));
|
|
BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SELECT !=
|
|
offsetof(struct virtio_pci_common_cfg, queue_select));
|
|
BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SIZE !=
|
|
offsetof(struct virtio_pci_common_cfg, queue_size));
|
|
BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_MSIX !=
|
|
offsetof(struct virtio_pci_common_cfg, queue_msix_vector));
|
|
BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_ENABLE !=
|
|
offsetof(struct virtio_pci_common_cfg, queue_enable));
|
|
BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_NOFF !=
|
|
offsetof(struct virtio_pci_common_cfg, queue_notify_off));
|
|
BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCLO !=
|
|
offsetof(struct virtio_pci_common_cfg, queue_desc_lo));
|
|
BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCHI !=
|
|
offsetof(struct virtio_pci_common_cfg, queue_desc_hi));
|
|
BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILLO !=
|
|
offsetof(struct virtio_pci_common_cfg, queue_avail_lo));
|
|
BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILHI !=
|
|
offsetof(struct virtio_pci_common_cfg, queue_avail_hi));
|
|
BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDLO !=
|
|
offsetof(struct virtio_pci_common_cfg, queue_used_lo));
|
|
BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDHI !=
|
|
offsetof(struct virtio_pci_common_cfg, queue_used_hi));
|
|
}
|
|
|
|
/*
|
|
* vp_modern_probe: probe the modern virtio pci device, note that the
|
|
* caller is required to enable PCI device before calling this function.
|
|
* @mdev: the modern virtio-pci device
|
|
*
|
|
* Return 0 on succeed otherwise fail
|
|
*/
|
|
static int vp_modern_probe(struct virtio_pci_modern_device *mdev)
|
|
{
|
|
struct pci_dev *pci_dev = mdev->pci_dev;
|
|
int err, common, isr, notify, device;
|
|
u32 notify_length;
|
|
u32 notify_offset;
|
|
|
|
check_offsets();
|
|
|
|
mdev->pci_dev = pci_dev;
|
|
|
|
/* We only own devices >= 0x1000 and <= 0x107f: leave the rest. */
|
|
if (pci_dev->device < 0x1000 || pci_dev->device > 0x107f)
|
|
return -ENODEV;
|
|
|
|
if (pci_dev->device < 0x1040) {
|
|
/* Transitional devices: use the PCI subsystem device id as
|
|
* virtio device id, same as legacy driver always did.
|
|
*/
|
|
mdev->id.device = pci_dev->subsystem_device;
|
|
} else {
|
|
/* Modern devices: simply use PCI device id, but start from 0x1040. */
|
|
mdev->id.device = pci_dev->device - 0x1040;
|
|
}
|
|
mdev->id.vendor = pci_dev->subsystem_vendor;
|
|
|
|
/* check for a common config: if not, use legacy mode (bar 0). */
|
|
common = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_COMMON_CFG,
|
|
IORESOURCE_IO | IORESOURCE_MEM,
|
|
&mdev->modern_bars);
|
|
if (!common) {
|
|
dev_info(&pci_dev->dev,
|
|
"virtio_pci: leaving for legacy driver\n");
|
|
return -ENODEV;
|
|
}
|
|
|
|
/* If common is there, these should be too... */
|
|
isr = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_ISR_CFG,
|
|
IORESOURCE_IO | IORESOURCE_MEM,
|
|
&mdev->modern_bars);
|
|
notify = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_NOTIFY_CFG,
|
|
IORESOURCE_IO | IORESOURCE_MEM,
|
|
&mdev->modern_bars);
|
|
if (!isr || !notify) {
|
|
dev_err(&pci_dev->dev,
|
|
"virtio_pci: missing capabilities %i/%i/%i\n",
|
|
common, isr, notify);
|
|
return -EINVAL;
|
|
}
|
|
|
|
err = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(64));
|
|
if (err)
|
|
err = dma_set_mask_and_coherent(&pci_dev->dev,
|
|
DMA_BIT_MASK(32));
|
|
if (err)
|
|
dev_warn(&pci_dev->dev, "Failed to enable 64-bit or 32-bit DMA. Trying to continue, but this might not work.\n");
|
|
|
|
/* Device capability is only mandatory for devices that have
|
|
* device-specific configuration.
|
|
*/
|
|
device = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_DEVICE_CFG,
|
|
IORESOURCE_IO | IORESOURCE_MEM,
|
|
&mdev->modern_bars);
|
|
|
|
err = pci_request_selected_regions(pci_dev, mdev->modern_bars,
|
|
"virtio-pci-modern");
|
|
if (err)
|
|
return err;
|
|
|
|
err = -EINVAL;
|
|
mdev->common = map_capability(pci_dev, common,
|
|
sizeof(struct virtio_pci_common_cfg), 4,
|
|
0, sizeof(struct virtio_pci_common_cfg),
|
|
NULL);
|
|
if (!mdev->common)
|
|
goto err_map_common;
|
|
mdev->isr = map_capability(pci_dev, isr, sizeof(u8), 1,
|
|
0, 1,
|
|
NULL);
|
|
if (!mdev->isr)
|
|
goto err_map_isr;
|
|
|
|
/* Read notify_off_multiplier from config space. */
|
|
pci_read_config_dword(pci_dev,
|
|
notify + offsetof(struct virtio_pci_notify_cap,
|
|
notify_off_multiplier),
|
|
&mdev->notify_offset_multiplier);
|
|
/* Read notify length and offset from config space. */
|
|
pci_read_config_dword(pci_dev,
|
|
notify + offsetof(struct virtio_pci_notify_cap,
|
|
cap.length),
|
|
¬ify_length);
|
|
|
|
pci_read_config_dword(pci_dev,
|
|
notify + offsetof(struct virtio_pci_notify_cap,
|
|
cap.offset),
|
|
¬ify_offset);
|
|
|
|
/* We don't know how many VQs we'll map, ahead of the time.
|
|
* If notify length is small, map it all now.
|
|
* Otherwise, map each VQ individually later.
|
|
*/
|
|
if ((u64)notify_length + (notify_offset % PAGE_SIZE) <= PAGE_SIZE) {
|
|
mdev->notify_base = map_capability(pci_dev, notify, 2, 2,
|
|
0, notify_length,
|
|
&mdev->notify_len);
|
|
if (!mdev->notify_base)
|
|
goto err_map_notify;
|
|
} else {
|
|
mdev->notify_map_cap = notify;
|
|
}
|
|
|
|
/* Again, we don't know how much we should map, but PAGE_SIZE
|
|
* is more than enough for all existing devices.
|
|
*/
|
|
if (device) {
|
|
mdev->device = map_capability(pci_dev, device, 0, 4,
|
|
0, PAGE_SIZE,
|
|
&mdev->device_len);
|
|
if (!mdev->device)
|
|
goto err_map_device;
|
|
}
|
|
|
|
return 0;
|
|
|
|
err_map_device:
|
|
if (mdev->notify_base)
|
|
pci_iounmap(pci_dev, mdev->notify_base);
|
|
err_map_notify:
|
|
pci_iounmap(pci_dev, mdev->isr);
|
|
err_map_isr:
|
|
pci_iounmap(pci_dev, mdev->common);
|
|
err_map_common:
|
|
return err;
|
|
}
|
|
|
|
/* the PCI probing function */
|
|
int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
|
|
{
|
|
struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
|
|
struct pci_dev *pci_dev = vp_dev->pci_dev;
|
|
int err;
|
|
|
|
mdev->pci_dev = pci_dev;
|
|
|
|
err = vp_modern_probe(mdev);
|
|
if (err)
|
|
return err;
|
|
|
|
if (mdev->device)
|
|
vp_dev->vdev.config = &virtio_pci_config_ops;
|
|
else
|
|
vp_dev->vdev.config = &virtio_pci_config_nodev_ops;
|
|
|
|
vp_dev->config_vector = vp_config_vector;
|
|
vp_dev->setup_vq = setup_vq;
|
|
vp_dev->del_vq = del_vq;
|
|
vp_dev->isr = mdev->isr;
|
|
vp_dev->vdev.id = mdev->id;
|
|
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* vp_modern_probe: remove and cleanup the modern virtio pci device
|
|
* @mdev: the modern virtio-pci device
|
|
*/
|
|
static void vp_modern_remove(struct virtio_pci_modern_device *mdev)
|
|
{
|
|
struct pci_dev *pci_dev = mdev->pci_dev;
|
|
|
|
if (mdev->device)
|
|
pci_iounmap(pci_dev, mdev->device);
|
|
if (mdev->notify_base)
|
|
pci_iounmap(pci_dev, mdev->notify_base);
|
|
pci_iounmap(pci_dev, mdev->isr);
|
|
pci_iounmap(pci_dev, mdev->common);
|
|
pci_release_selected_regions(pci_dev, mdev->modern_bars);
|
|
}
|
|
|
|
void virtio_pci_modern_remove(struct virtio_pci_device *vp_dev)
|
|
{
|
|
struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
|
|
|
|
vp_modern_remove(mdev);
|
|
}
|