On Mon, 16 Nov 2020 12:00:18 +0100
Eric Auger <eric.au...@redhat.com> wrote:
> From: "Liu, Yi L" <yi.l....@linux.intel.com>
>
> This patch adds an VFIO_IOMMU_SET_PASID_TABLE ioctl
> which aims to pass the virtual iommu guest configuration
> to the host. This latter takes the form of the so-called
> PASID table.
>
> Signed-off-by: Jacob Pan <jacob.jun....@linux.intel.com>
> Signed-off-by: Liu, Yi L <yi.l....@linux.intel.com>
> Signed-off-by: Eric Auger <eric.au...@redhat.com>
>
> ---
> v11 -> v12:
> - use iommu_uapi_set_pasid_table
> - check SET and UNSET are not set simultaneously (Zenghui)
>
> v8 -> v9:
> - Merge VFIO_IOMMU_ATTACH/DETACH_PASID_TABLE into a single
> VFIO_IOMMU_SET_PASID_TABLE ioctl.
>
> v6 -> v7:
> - add a comment related to VFIO_IOMMU_DETACH_PASID_TABLE
>
> v3 -> v4:
> - restore ATTACH/DETACH
> - add unwind on failure
>
> v2 -> v3:
> - s/BIND_PASID_TABLE/SET_PASID_TABLE
>
> v1 -> v2:
> - s/BIND_GUEST_STAGE/BIND_PASID_TABLE
> - remove the struct device arg
> ---
> drivers/vfio/vfio_iommu_type1.c | 65 +++++++++++++++++++++++++++++++++
> include/uapi/linux/vfio.h | 19 ++++++++++
> 2 files changed, 84 insertions(+)
>
> diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
> index 67e827638995..87ddd9e882dc 100644
> --- a/drivers/vfio/vfio_iommu_type1.c
> +++ b/drivers/vfio/vfio_iommu_type1.c
> @@ -2587,6 +2587,41 @@ static int vfio_iommu_iova_build_caps(struct
> vfio_iommu *iommu,
> return ret;
> }
>
> +static void
> +vfio_detach_pasid_table(struct vfio_iommu *iommu)
> +{
> + struct vfio_domain *d;
> +
> + mutex_lock(&iommu->lock);
> + list_for_each_entry(d, &iommu->domain_list, next)
> + iommu_detach_pasid_table(d->domain);
> +
> + mutex_unlock(&iommu->lock);
> +}
> +
> +static int
> +vfio_attach_pasid_table(struct vfio_iommu *iommu, unsigned long arg)
> +{
> + struct vfio_domain *d;
> + int ret = 0;
> +
> + mutex_lock(&iommu->lock);
> +
> + list_for_each_entry(d, &iommu->domain_list, next) {
> + ret = iommu_uapi_attach_pasid_table(d->domain, (void __user
> *)arg);
> + if (ret)
> + goto unwind;
> + }
> + goto unlock;
> +unwind:
> + list_for_each_entry_continue_reverse(d, &iommu->domain_list, next) {
> + iommu_detach_pasid_table(d->domain);
> + }
> +unlock:
This goto leap frog could be avoided with just:
list_for_each_entry(d, &iommu->domain_list, next) {
ret = iommu_uapi_attach_pasid_table(d->domain, (void __user *)arg);
if (ret) {
list_for_each_entry_continue_reverse(d, &iommu->domain_list,
next) {
iommu_detach_pasid_table(d->domain);
}
break;
}
}
> + mutex_unlock(&iommu->lock);
> + return ret;
> +}
> +
> static int vfio_iommu_migration_build_caps(struct vfio_iommu *iommu,
> struct vfio_info_cap *caps)
> {
> @@ -2747,6 +2782,34 @@ static int vfio_iommu_type1_unmap_dma(struct
> vfio_iommu *iommu,
> -EFAULT : 0;
> }
>
> +static int vfio_iommu_type1_set_pasid_table(struct vfio_iommu *iommu,
> + unsigned long arg)
> +{
> + struct vfio_iommu_type1_set_pasid_table spt;
> + unsigned long minsz;
> + int ret = -EINVAL;
> +
> + minsz = offsetofend(struct vfio_iommu_type1_set_pasid_table, flags);
> +
> + if (copy_from_user(&spt, (void __user *)arg, minsz))
> + return -EFAULT;
> +
> + if (spt.argsz < minsz)
> + return -EINVAL;
> +
> + if (spt.flags & VFIO_PASID_TABLE_FLAG_SET &&
> + spt.flags & VFIO_PASID_TABLE_FLAG_UNSET)
> + return -EINVAL;
> +
> + if (spt.flags & VFIO_PASID_TABLE_FLAG_SET)
> + ret = vfio_attach_pasid_table(iommu, arg + minsz);
> + else if (spt.flags & VFIO_PASID_TABLE_FLAG_UNSET) {
> + vfio_detach_pasid_table(iommu);
> + ret = 0;
> + }
This doesn't really validate that the other flag bits are zero, ex.
user could pass flags = (1 << 8) | VFIO_PASID_TABLE_FLAG_SET and we'd
just ignore the extra bit. So this probably needs to be:
if (spt.flags == VFIO_PASID_TABLE_FLAG_SET)
ret = vfio_attach_pasid_table(iommu, arg + minsz);
else if (spt.flags == VFIO_PASID_TABLE_FLAG_UNSET)
vfio_detach_pasid_table(iommu);
Or otherwise validate that none of the other bits are set. It also
seems cleaner to me to set the initial value of ret = 0 and end this
with:
else
ret = -EINVAL;
> + return ret;
> +}
> +
> static int vfio_iommu_type1_dirty_pages(struct vfio_iommu *iommu,
> unsigned long arg)
> {
> @@ -2867,6 +2930,8 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
> return vfio_iommu_type1_unmap_dma(iommu, arg);
> case VFIO_IOMMU_DIRTY_PAGES:
> return vfio_iommu_type1_dirty_pages(iommu, arg);
> + case VFIO_IOMMU_SET_PASID_TABLE:
> + return vfio_iommu_type1_set_pasid_table(iommu, arg);
> default:
> return -ENOTTY;
> }
> diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
> index 2f313a238a8f..78ce3ce6c331 100644
> --- a/include/uapi/linux/vfio.h
> +++ b/include/uapi/linux/vfio.h
> @@ -14,6 +14,7 @@
>
> #include <linux/types.h>
> #include <linux/ioctl.h>
> +#include <linux/iommu.h>
>
> #define VFIO_API_VERSION 0
>
> @@ -1180,6 +1181,24 @@ struct vfio_iommu_type1_dirty_bitmap_get {
>
> #define VFIO_IOMMU_DIRTY_PAGES _IO(VFIO_TYPE, VFIO_BASE + 17)
>
> +/*
> + * VFIO_IOMMU_SET_PASID_TABLE - _IOWR(VFIO_TYPE, VFIO_BASE + 22,
We already reuse ioctl indexes between type1 and spapr (ex. +17 is
either VFIO_IOMMU_DIRTY_PAGES or VFIO_IOMMU_SPAPR_REGISTER_MEMORY
depending on the iommu type). I wonder if we should reuse +18 here
instead.
> + * struct vfio_iommu_type1_set_pasid_table)
> + *
> + * The SET operation passes a PASID table to the host while the
> + * UNSET operation detaches the one currently programmed. Setting
> + * a table while another is already programmed replaces the old table.
> + */
> +struct vfio_iommu_type1_set_pasid_table {
> + __u32 argsz;
> + __u32 flags;
> +#define VFIO_PASID_TABLE_FLAG_SET (1 << 0)
> +#define VFIO_PASID_TABLE_FLAG_UNSET (1 << 1)
> + struct iommu_pasid_table_config config; /* used on SET */
> +};
> +
> +#define VFIO_IOMMU_SET_PASID_TABLE _IO(VFIO_TYPE, VFIO_BASE + 22)
> +
> /* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */
>
> /*
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
