On Sun, 17 Mar 2019 18:22:18 +0100
Eric Auger <eric.auger@xxxxxxxxxx> wrote:
> From: "Liu, Yi L" <yi.l.liu@xxxxxxxxxxxxxxx>
>
> When the guest "owns" the stage 1 translation structures, the host
> IOMMU driver has no knowledge of caching structure updates unless
> the guest invalidation requests are trapped and passed down to the
> host.
>
> This patch adds the VFIO_IOMMU_CACHE_INVALIDATE ioctl with aims
> at propagating guest stage1 IOMMU cache invalidations to the host.
>
> Signed-off-by: Liu, Yi L <yi.l.liu@xxxxxxxxxxxxxxx>
> Signed-off-by: Eric Auger <eric.auger@xxxxxxxxxx>
>
> ---
>
> v2 -> v3:
> - introduce vfio_iommu_for_each_dev back in this patch
>
> v1 -> v2:
> - s/TLB/CACHE
> - remove vfio_iommu_task usage
> - commit message rewording
> ---
> drivers/vfio/vfio_iommu_type1.c | 47 +++++++++++++++++++++++++++++++++
> include/uapi/linux/vfio.h | 13 +++++++++
> 2 files changed, 60 insertions(+)
>
> diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
> index 222e9199edbf..12a40b9db6aa 100644
> --- a/drivers/vfio/vfio_iommu_type1.c
> +++ b/drivers/vfio/vfio_iommu_type1.c
> @@ -113,6 +113,26 @@ struct vfio_regions {
> #define IS_IOMMU_CAP_DOMAIN_IN_CONTAINER(iommu) \
> (!list_empty(&iommu->domain_list))
>
static struct foo {
struct iommu_domain *domain;
void *data;
};
> +/* iommu->lock must be held */
> +static int
> +vfio_iommu_for_each_dev(struct vfio_iommu *iommu, void *data,
> + int (*fn)(struct device *, void *))
> +{
> + struct vfio_domain *d;
> + struct vfio_group *g;
> + int ret = 0;
struct foo bar = { .data = data };
> +
> + list_for_each_entry(d, &iommu->domain_list, next) {
bar.domain = d->domain;
> + list_for_each_entry(g, &d->group_list, next) {
> + ret = iommu_group_for_each_dev(g->iommu_group,
> + data, fn);
s/data/&bar/
> + if (ret)
> + break;
> + }
> + }
> + return ret;
> +}
> +
> static int put_pfn(unsigned long pfn, int prot);
>
> /*
> @@ -1681,6 +1701,15 @@ vfio_attach_pasid_table(struct vfio_iommu *iommu,
> return ret;
> }
>
> +static int vfio_cache_inv_fn(struct device *dev, void *data)
> +{
struct foo *bar = data;
> + struct vfio_iommu_type1_cache_invalidate *ustruct =
> + (struct vfio_iommu_type1_cache_invalidate *)data;
... = bar->data;
> + struct iommu_domain *d = iommu_get_domain_for_dev(dev);
... = bar->domain;
¯\_(ツ)_/¯ seems more efficient that doing a lookup.
> +
> + return iommu_cache_invalidate(d, dev, &ustruct->info);
> +}
> +
> static long vfio_iommu_type1_ioctl(void *iommu_data,
> unsigned int cmd, unsigned long arg)
> {
> @@ -1767,6 +1796,24 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
> } else if (cmd == VFIO_IOMMU_DETACH_PASID_TABLE) {
> vfio_detach_pasid_table(iommu);
> return 0;
> + } else if (cmd == VFIO_IOMMU_CACHE_INVALIDATE) {
> + struct vfio_iommu_type1_cache_invalidate ustruct;
> + int ret;
> +
> + minsz = offsetofend(struct vfio_iommu_type1_cache_invalidate,
> + info);
> +
> + if (copy_from_user(&ustruct, (void __user *)arg, minsz))
> + return -EFAULT;
> +
> + if (ustruct.argsz < minsz || ustruct.flags)
> + return -EINVAL;
> +
> + mutex_lock(&iommu->lock);
> + ret = vfio_iommu_for_each_dev(iommu, &ustruct,
> + vfio_cache_inv_fn);
Guess what has a version field that never gets checked ;)
Thanks,
Alex
> + mutex_unlock(&iommu->lock);
> + return ret;
> }
>
> return -ENOTTY;
> diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
> index 329d378565d9..29f0ef2d805d 100644
> --- a/include/uapi/linux/vfio.h
> +++ b/include/uapi/linux/vfio.h
> @@ -776,6 +776,19 @@ struct vfio_iommu_type1_attach_pasid_table {
> #define VFIO_IOMMU_ATTACH_PASID_TABLE _IO(VFIO_TYPE, VFIO_BASE + 22)
> #define VFIO_IOMMU_DETACH_PASID_TABLE _IO(VFIO_TYPE, VFIO_BASE + 23)
>
> +/**
> + * VFIO_IOMMU_CACHE_INVALIDATE - _IOWR(VFIO_TYPE, VFIO_BASE + 24,
> + * struct vfio_iommu_type1_cache_invalidate)
> + *
> + * Propagate guest IOMMU cache invalidation to the host.
> + */
> +struct vfio_iommu_type1_cache_invalidate {
> + __u32 argsz;
> + __u32 flags;
> + struct iommu_cache_invalidate_info info;
> +};
> +#define VFIO_IOMMU_CACHE_INVALIDATE _IO(VFIO_TYPE, VFIO_BASE + 24)
> +
> /* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */
>
> /*
