On Thu, 24 Oct 2019 08:26:22 -0400
Liu Yi L <yi.l.liu@xxxxxxxxx> wrote:
> This patch adds VFIO_IOMMU_PASID_REQUEST ioctl which aims
> to passdown PASID allocation/free request from the virtual
> iommu. This is required to get PASID managed in system-wide.
>
> Cc: Kevin Tian <kevin.tian@xxxxxxxxx>
> Signed-off-by: Liu Yi L <yi.l.liu@xxxxxxxxx>
> Signed-off-by: Yi Sun <yi.y.sun@xxxxxxxxxxxxxxx>
> Signed-off-by: Jacob Pan <jacob.jun.pan@xxxxxxxxxxxxxxx>
> ---
> drivers/vfio/vfio_iommu_type1.c | 114 ++++++++++++++++++++++++++++++++++++++++
> include/uapi/linux/vfio.h | 25 +++++++++
> 2 files changed, 139 insertions(+)
>
> diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
> index cd8d3a5..3d73a7d 100644
> --- a/drivers/vfio/vfio_iommu_type1.c
> +++ b/drivers/vfio/vfio_iommu_type1.c
> @@ -2248,6 +2248,83 @@ static int vfio_cache_inv_fn(struct device *dev, void *data)
> return iommu_cache_invalidate(dc->domain, dev, &ustruct->info);
> }
>
> +static int vfio_iommu_type1_pasid_alloc(struct vfio_iommu *iommu,
> + int min_pasid,
> + int max_pasid)
> +{
> + int ret;
> + ioasid_t pasid;
> + struct mm_struct *mm = NULL;
> +
> + mutex_lock(&iommu->lock);
> + if (!IS_IOMMU_CAP_DOMAIN_IN_CONTAINER(iommu)) {
> + ret = -EINVAL;
> + goto out_unlock;
> + }
> + mm = get_task_mm(current);
> + /* Track ioasid allocation owner by mm */
> + pasid = ioasid_alloc((struct ioasid_set *)mm, min_pasid,
> + max_pasid, NULL);
Are we sure we want to tie this to the task mm vs perhaps the
vfio_iommu pointer?
> + if (pasid == INVALID_IOASID) {
> + ret = -ENOSPC;
> + goto out_unlock;
> + }
> + ret = pasid;
> +out_unlock:
> + mutex_unlock(&iommu->lock);
> + if (mm)
> + mmput(mm);
> + return ret;
> +}
> +
> +static int vfio_iommu_type1_pasid_free(struct vfio_iommu *iommu,
> + unsigned int pasid)
> +{
> + struct mm_struct *mm = NULL;
> + void *pdata;
> + int ret = 0;
> +
> + mutex_lock(&iommu->lock);
> + if (!IS_IOMMU_CAP_DOMAIN_IN_CONTAINER(iommu)) {
> + ret = -EINVAL;
> + goto out_unlock;
> + }
> +
> + /**
> + * REVISIT:
> + * There are two cases free could fail:
> + * 1. free pasid by non-owner, we use ioasid_set to track mm, if
> + * the set does not match, caller is not permitted to free.
> + * 2. free before unbind all devices, we can check if ioasid private
> + * data, if data != NULL, then fail to free.
> + */
> + mm = get_task_mm(current);
> + pdata = ioasid_find((struct ioasid_set *)mm, pasid, NULL);
> + if (IS_ERR(pdata)) {
> + if (pdata == ERR_PTR(-ENOENT))
> + pr_err("PASID %u is not allocated\n", pasid);
> + else if (pdata == ERR_PTR(-EACCES))
> + pr_err("Free PASID %u by non-owner, denied", pasid);
> + else
> + pr_err("Error searching PASID %u\n", pasid);
This should be removed, errno is sufficient for the user, this just
provides the user with a trivial DoS vector filling logs.
> + ret = -EPERM;
But why not return PTR_ERR(pdata)?
> + goto out_unlock;
> + }
> + if (pdata) {
> + pr_debug("Cannot free pasid %d with private data\n", pasid);
> + /* Expect PASID has no private data if not bond */
> + ret = -EBUSY;
> + goto out_unlock;
> + }
> + ioasid_free(pasid);
We only ever get here with pasid == NULL?! Something is wrong. Should
that be 'if (!pdata)'? (which also makes that pr_debug another DoS
vector)
> +
> +out_unlock:
> + if (mm)
> + mmput(mm);
> + mutex_unlock(&iommu->lock);
> + return ret;
> +}
> +
> static long vfio_iommu_type1_ioctl(void *iommu_data,
> unsigned int cmd, unsigned long arg)
> {
> @@ -2370,6 +2447,43 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
> &ustruct);
> mutex_unlock(&iommu->lock);
> return ret;
> +
> + } else if (cmd == VFIO_IOMMU_PASID_REQUEST) {
> + struct vfio_iommu_type1_pasid_request req;
> + int min_pasid, max_pasid, pasid;
> +
> + minsz = offsetofend(struct vfio_iommu_type1_pasid_request,
> + flag);
> +
> + if (copy_from_user(&req, (void __user *)arg, minsz))
> + return -EFAULT;
> +
> + if (req.argsz < minsz)
> + return -EINVAL;
> +
> + switch (req.flag) {
This works, but it's strange. Let's make the code a little easier for
the next flag bit that gets used so they don't need to rework this case
statement. I'd suggest creating a VFIO_IOMMU_PASID_OPS_MASK that is
the OR of the ALLOC/FREE options, test that no bits are set outside of
that mask, then AND that mask as the switch arg with the code below.
> + /**
> + * TODO: min_pasid and max_pasid align with
> + * typedef unsigned int ioasid_t
> + */
> + case VFIO_IOMMU_PASID_ALLOC:
> + if (copy_from_user(&min_pasid,
> + (void __user *)arg + minsz, sizeof(min_pasid)))
> + return -EFAULT;
> + if (copy_from_user(&max_pasid,
> + (void __user *)arg + minsz + sizeof(min_pasid),
> + sizeof(max_pasid)))
> + return -EFAULT;
> + return vfio_iommu_type1_pasid_alloc(iommu,
> + min_pasid, max_pasid);
> + case VFIO_IOMMU_PASID_FREE:
> + if (copy_from_user(&pasid,
> + (void __user *)arg + minsz, sizeof(pasid)))
> + return -EFAULT;
> + return vfio_iommu_type1_pasid_free(iommu, pasid);
> + default:
> + return -EINVAL;
> + }
> }
>
> return -ENOTTY;
> diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
> index ccf60a2..04de290 100644
> --- a/include/uapi/linux/vfio.h
> +++ b/include/uapi/linux/vfio.h
> @@ -807,6 +807,31 @@ struct vfio_iommu_type1_cache_invalidate {
> };
> #define VFIO_IOMMU_CACHE_INVALIDATE _IO(VFIO_TYPE, VFIO_BASE + 24)
>
> +/*
> + * @flag=VFIO_IOMMU_PASID_ALLOC, refer to the @min_pasid and @max_pasid fields
> + * @flag=VFIO_IOMMU_PASID_FREE, refer to @pasid field
> + */
> +struct vfio_iommu_type1_pasid_request {
> + __u32 argsz;
> +#define VFIO_IOMMU_PASID_ALLOC (1 << 0)
> +#define VFIO_IOMMU_PASID_FREE (1 << 1)
> + __u32 flag;
> + union {
> + struct {
> + int min_pasid;
> + int max_pasid;
> + };
> + int pasid;
Perhaps:
struct {
u32 min;
u32 max;
} alloc_pasid;
u32 free_pasid;
(note also the s/int/u32/)
> + };
> +};
> +
> +/**
> + * VFIO_IOMMU_PASID_REQUEST - _IOWR(VFIO_TYPE, VFIO_BASE + 27,
> + * struct vfio_iommu_type1_pasid_request)
> + *
> + */
> +#define VFIO_IOMMU_PASID_REQUEST _IO(VFIO_TYPE, VFIO_BASE + 27)
> +
> /* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */
>
> /*
