On Tue, 11 Oct 2016 01:58:37 +0530
Kirti Wankhede <kwankhede@xxxxxxxxxx> wrote:
> Add common functions for SET_IRQS and to add capability buffer for
> GET_REGION_INFO ioctls
Clearly should be two (or more) separate patches since SET_IRQS and
REGION_INFO are unrelated changes. Each of the two capabilities handled
could possibly be separate patches as well.
> Signed-off-by: Kirti Wankhede <kwankhede@xxxxxxxxxx>
> Signed-off-by: Neo Jia <cjia@xxxxxxxxxx>
> Change-Id: Id9e976a2c08b9b2b37da77dac4365ae8f6024b4a
> ---
> drivers/vfio/pci/vfio_pci.c | 103 +++++++++++++++------------------------
> drivers/vfio/vfio.c | 116 ++++++++++++++++++++++++++++++++++++++++++++
> include/linux/vfio.h | 7 +++
> 3 files changed, 162 insertions(+), 64 deletions(-)
>
> diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
> index 188b1ff03f5f..f312cbb0eebc 100644
> --- a/drivers/vfio/pci/vfio_pci.c
> +++ b/drivers/vfio/pci/vfio_pci.c
> @@ -478,12 +478,12 @@ static int vfio_pci_for_each_slot_or_bus(struct pci_dev *pdev,
> }
>
> static int msix_sparse_mmap_cap(struct vfio_pci_device *vdev,
> + struct vfio_region_info *info,
> struct vfio_info_cap *caps)
> {
> - struct vfio_info_cap_header *header;
> struct vfio_region_info_cap_sparse_mmap *sparse;
> size_t end, size;
> - int nr_areas = 2, i = 0;
> + int nr_areas = 2, i = 0, ret;
>
> end = pci_resource_len(vdev->pdev, vdev->msix_bar);
>
> @@ -494,13 +494,10 @@ static int msix_sparse_mmap_cap(struct vfio_pci_device *vdev,
>
> size = sizeof(*sparse) + (nr_areas * sizeof(*sparse->areas));
>
> - header = vfio_info_cap_add(caps, size,
> - VFIO_REGION_INFO_CAP_SPARSE_MMAP, 1);
> - if (IS_ERR(header))
> - return PTR_ERR(header);
> + sparse = kzalloc(size, GFP_KERNEL);
> + if (!sparse)
> + return -ENOMEM;
>
> - sparse = container_of(header,
> - struct vfio_region_info_cap_sparse_mmap, header);
> sparse->nr_areas = nr_areas;
>
> if (vdev->msix_offset & PAGE_MASK) {
> @@ -516,24 +513,14 @@ static int msix_sparse_mmap_cap(struct vfio_pci_device *vdev,
> i++;
> }
>
> - return 0;
> -}
> -
> -static int region_type_cap(struct vfio_pci_device *vdev,
> - struct vfio_info_cap *caps,
> - unsigned int type, unsigned int subtype)
> -{
> - struct vfio_info_cap_header *header;
> - struct vfio_region_info_cap_type *cap;
> + info->flags |= VFIO_REGION_INFO_FLAG_CAPS;
>
> - header = vfio_info_cap_add(caps, sizeof(*cap),
> - VFIO_REGION_INFO_CAP_TYPE, 1);
> - if (IS_ERR(header))
> - return PTR_ERR(header);
> + ret = vfio_info_add_capability(info, caps,
> + VFIO_REGION_INFO_CAP_SPARSE_MMAP, sparse);
> + kfree(sparse);
>
> - cap = container_of(header, struct vfio_region_info_cap_type, header);
> - cap->type = type;
> - cap->subtype = subtype;
> + if (ret)
> + return ret;
>
> return 0;
Just: return ret;
> }
> @@ -628,7 +615,8 @@ static long vfio_pci_ioctl(void *device_data,
> IORESOURCE_MEM && info.size >= PAGE_SIZE) {
> info.flags |= VFIO_REGION_INFO_FLAG_MMAP;
> if (info.index == vdev->msix_bar) {
> - ret = msix_sparse_mmap_cap(vdev, &caps);
> + ret = msix_sparse_mmap_cap(vdev, &info,
> + &caps);
> if (ret)
> return ret;
> }
> @@ -676,6 +664,9 @@ static long vfio_pci_ioctl(void *device_data,
>
> break;
> default:
> + {
> + struct vfio_region_info_cap_type cap_type;
> +
> if (info.index >=
> VFIO_PCI_NUM_REGIONS + vdev->num_regions)
> return -EINVAL;
> @@ -684,29 +675,26 @@ static long vfio_pci_ioctl(void *device_data,
>
> info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
> info.size = vdev->region[i].size;
> - info.flags = vdev->region[i].flags;
> + info.flags = vdev->region[i].flags |
> + VFIO_REGION_INFO_FLAG_CAPS;
>
> - ret = region_type_cap(vdev, &caps,
> - vdev->region[i].type,
> - vdev->region[i].subtype);
> + cap_type.type = vdev->region[i].type;
> + cap_type.subtype = vdev->region[i].subtype;
> +
> + ret = vfio_info_add_capability(&info, &caps,
> + VFIO_REGION_INFO_CAP_TYPE,
> + &cap_type);
> if (ret)
> return ret;
> +
> + }
> }
>
> - if (caps.size) {
> - info.flags |= VFIO_REGION_INFO_FLAG_CAPS;
> - if (info.argsz < sizeof(info) + caps.size) {
> - info.argsz = sizeof(info) + caps.size;
> - info.cap_offset = 0;
> - } else {
> - vfio_info_cap_shift(&caps, sizeof(info));
> - if (copy_to_user((void __user *)arg +
> - sizeof(info), caps.buf,
> - caps.size)) {
> - kfree(caps.buf);
> - return -EFAULT;
> - }
> - info.cap_offset = sizeof(info);
> + if (info.cap_offset) {
> + if (copy_to_user((void __user *)arg + info.cap_offset,
> + caps.buf, caps.size)) {
> + kfree(caps.buf);
> + return -EFAULT;
> }
>
> kfree(caps.buf);
> @@ -754,35 +742,22 @@ static long vfio_pci_ioctl(void *device_data,
> } else if (cmd == VFIO_DEVICE_SET_IRQS) {
> struct vfio_irq_set hdr;
> u8 *data = NULL;
> - int ret = 0;
> + int max, ret = 0, data_size = 0;
>
> minsz = offsetofend(struct vfio_irq_set, count);
>
> if (copy_from_user(&hdr, (void __user *)arg, minsz))
> return -EFAULT;
>
> - if (hdr.argsz < minsz || hdr.index >= VFIO_PCI_NUM_IRQS ||
> - hdr.flags & ~(VFIO_IRQ_SET_DATA_TYPE_MASK |
> - VFIO_IRQ_SET_ACTION_TYPE_MASK))
> - return -EINVAL;
> -
> - if (!(hdr.flags & VFIO_IRQ_SET_DATA_NONE)) {
> - size_t size;
> - int max = vfio_pci_get_irq_count(vdev, hdr.index);
> + max = vfio_pci_get_irq_count(vdev, hdr.index);
>
> - if (hdr.flags & VFIO_IRQ_SET_DATA_BOOL)
> - size = sizeof(uint8_t);
> - else if (hdr.flags & VFIO_IRQ_SET_DATA_EVENTFD)
> - size = sizeof(int32_t);
> - else
> - return -EINVAL;
> -
> - if (hdr.argsz - minsz < hdr.count * size ||
> - hdr.start >= max || hdr.start + hdr.count > max)
> - return -EINVAL;
vfio_platform has very similar code that would also need to be updated.
> + ret = vfio_set_irqs_validate_and_prepare(&hdr, max, &data_size);
> + if (ret)
> + return ret;
>
> + if (data_size) {
> data = memdup_user((void __user *)(arg + minsz),
> - hdr.count * size);
> + data_size);
> if (IS_ERR(data))
> return PTR_ERR(data);
> }
> @@ -790,7 +765,7 @@ static long vfio_pci_ioctl(void *device_data,
> mutex_lock(&vdev->igate);
>
> ret = vfio_pci_set_irqs_ioctl(vdev, hdr.flags, hdr.index,
> - hdr.start, hdr.count, data);
> + hdr.start, hdr.count, data);
White space bogosity.
>
> mutex_unlock(&vdev->igate);
> kfree(data);
> diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
> index e3e342861e04..0185d5fb2c85 100644
> --- a/drivers/vfio/vfio.c
> +++ b/drivers/vfio/vfio.c
> @@ -1782,6 +1782,122 @@ void vfio_info_cap_shift(struct vfio_info_cap *caps, size_t offset)
> }
> EXPORT_SYMBOL_GPL(vfio_info_cap_shift);
>
> +static int sparse_mmap_cap(struct vfio_info_cap *caps, void *cap_type)
> +{
> + struct vfio_info_cap_header *header;
> + struct vfio_region_info_cap_sparse_mmap *sparse_cap, *sparse = cap_type;
> + size_t size;
> +
> + size = sizeof(*sparse) + sparse->nr_areas * sizeof(*sparse->areas);
> + header = vfio_info_cap_add(caps, size,
> + VFIO_REGION_INFO_CAP_SPARSE_MMAP, 1);
> + if (IS_ERR(header))
> + return PTR_ERR(header);
> +
> + sparse_cap = container_of(header,
> + struct vfio_region_info_cap_sparse_mmap, header);
> + sparse_cap->nr_areas = sparse->nr_areas;
> + memcpy(sparse_cap->areas, sparse->areas,
> + sparse->nr_areas * sizeof(*sparse->areas));
> + return 0;
> +}
> +
> +static int region_type_cap(struct vfio_info_cap *caps, void *cap_type)
> +{
> + struct vfio_info_cap_header *header;
> + struct vfio_region_info_cap_type *type_cap, *cap = cap_type;
> +
> + header = vfio_info_cap_add(caps, sizeof(*cap),
> + VFIO_REGION_INFO_CAP_TYPE, 1);
> + if (IS_ERR(header))
> + return PTR_ERR(header);
> +
> + type_cap = container_of(header, struct vfio_region_info_cap_type,
> + header);
> + type_cap->type = cap->type;
> + type_cap->subtype = cap->subtype;
> + return 0;
> +}
Why can't we just do a memcpy of all the data past the header? Do we
need separate functions for these?
vfio_info_cap_add() should now be static and unexported, right?
> +
> +int vfio_info_add_capability(struct vfio_region_info *info,
> + struct vfio_info_cap *caps,
> + int cap_type_id,
> + void *cap_type)
> +{
> + int ret;
> +
> + if (!(info->flags & VFIO_REGION_INFO_FLAG_CAPS) || !cap_type)
Why make the caller set flags, seems rather arbitrary since this
function controls the cap_offset and whether we actually end up copying
the data.
> + return 0;
> +
> + switch (cap_type_id) {
> + case VFIO_REGION_INFO_CAP_SPARSE_MMAP:
> + ret = sparse_mmap_cap(caps, cap_type);
> + if (ret)
> + return ret;
> + break;
> +
> + case VFIO_REGION_INFO_CAP_TYPE:
> + ret = region_type_cap(caps, cap_type);
> + if (ret)
> + return ret;
> + break;
> + default:
> + return -EINVAL;
> + }
> +
> + if (caps->size) {
> + if (info->argsz < sizeof(*info) + caps->size) {
> + info->argsz = sizeof(*info) + caps->size;
> + info->cap_offset = 0;
> + } else {
> + vfio_info_cap_shift(caps, sizeof(*info));
> + info->cap_offset = sizeof(*info);
> + }
> + }
> + return 0;
> +}
> +EXPORT_SYMBOL(vfio_info_add_capability);
> +
> +int vfio_set_irqs_validate_and_prepare(struct vfio_irq_set *hdr, int num_irqs,
> + int *data_size)
> +{
> + unsigned long minsz;
> +
> + minsz = offsetofend(struct vfio_irq_set, count);
> +
> + if ((hdr->argsz < minsz) || (hdr->index >= VFIO_PCI_NUM_IRQS) ||
> + (hdr->flags & ~(VFIO_IRQ_SET_DATA_TYPE_MASK |
> + VFIO_IRQ_SET_ACTION_TYPE_MASK)))
> + return -EINVAL;
> +
> + if (data_size)
> + *data_size = 0;
> +
> + if (!(hdr->flags & VFIO_IRQ_SET_DATA_NONE)) {
> + size_t size;
> +
> + if (hdr->flags & VFIO_IRQ_SET_DATA_BOOL)
> + size = sizeof(uint8_t);
> + else if (hdr->flags & VFIO_IRQ_SET_DATA_EVENTFD)
> + size = sizeof(int32_t);
> + else
> + return -EINVAL;
> +
> + if ((hdr->argsz - minsz < hdr->count * size) ||
> + (hdr->start >= num_irqs) ||
> + (hdr->start + hdr->count > num_irqs))
> + return -EINVAL;
> +
> + if (!data_size)
> + return -EINVAL;
> +
> + *data_size = hdr->count * size;
> + }
> +
> + return 0;
> +}
> +EXPORT_SYMBOL(vfio_set_irqs_validate_and_prepare);
> +
> static struct vfio_group *vfio_group_from_dev(struct device *dev)
> {
> struct vfio_device *device;
> diff --git a/include/linux/vfio.h b/include/linux/vfio.h
> index 0bd25ba6223d..5641dab72ded 100644
> --- a/include/linux/vfio.h
> +++ b/include/linux/vfio.h
> @@ -108,6 +108,13 @@ extern struct vfio_info_cap_header *vfio_info_cap_add(
> struct vfio_info_cap *caps, size_t size, u16 id, u16 version);
> extern void vfio_info_cap_shift(struct vfio_info_cap *caps, size_t offset);
>
> +extern int vfio_info_add_capability(struct vfio_region_info *info,
> + struct vfio_info_cap *caps,
> + int cap_type_id, void *cap_type);
> +
> +extern int vfio_set_irqs_validate_and_prepare(struct vfio_irq_set *hdr,
> + int num_irqs, int *data_size);
> +
> struct pci_dev;
> #ifdef CONFIG_EEH
> extern void vfio_spapr_pci_eeh_open(struct pci_dev *pdev);
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
