On Fri, 9 Apr 2021 11:44:18 +0800
Shenming Lu <lushenming@xxxxxxxxxx> wrote:
> If IOPF enabled for the VFIO container, there is no need to statically
> pin and map the entire DMA range, we can do it on demand. And unmap
> according to the IOPF mapped bitmap when removing vfio_dma.
>
> Note that we still mark all pages dirty even if IOPF enabled, we may
> add IOPF-based fine grained dirty tracking support in the future.
>
> Signed-off-by: Shenming Lu <lushenming@xxxxxxxxxx>
> ---
> drivers/vfio/vfio_iommu_type1.c | 38 +++++++++++++++++++++++++++------
> 1 file changed, 32 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
> index 7df5711e743a..dcc93c3b258c 100644
> --- a/drivers/vfio/vfio_iommu_type1.c
> +++ b/drivers/vfio/vfio_iommu_type1.c
> @@ -175,6 +175,7 @@ struct vfio_iopf_group {
> #define IOPF_MAPPED_BITMAP_GET(dma, i) \
> ((dma->iopf_mapped_bitmap[(i) / BITS_PER_LONG] \
> >> ((i) % BITS_PER_LONG)) & 0x1)
> +#define IOPF_MAPPED_BITMAP_BYTES(n) DIRTY_BITMAP_BYTES(n)
>
> #define WAITED 1
>
> @@ -959,7 +960,8 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data,
> * already pinned and accounted. Accouting should be done if there is no
> * iommu capable domain in the container.
> */
> - do_accounting = !IS_IOMMU_CAP_DOMAIN_IN_CONTAINER(iommu);
> + do_accounting = !IS_IOMMU_CAP_DOMAIN_IN_CONTAINER(iommu) ||
> + iommu->iopf_enabled;
>
> for (i = 0; i < npage; i++) {
> struct vfio_pfn *vpfn;
> @@ -1048,7 +1050,8 @@ static int vfio_iommu_type1_unpin_pages(void *iommu_data,
>
> mutex_lock(&iommu->lock);
>
> - do_accounting = !IS_IOMMU_CAP_DOMAIN_IN_CONTAINER(iommu);
> + do_accounting = !IS_IOMMU_CAP_DOMAIN_IN_CONTAINER(iommu) ||
> + iommu->iopf_enabled;
pin/unpin are actually still pinning pages, why does iopf exempt them
from accounting?
> for (i = 0; i < npage; i++) {
> struct vfio_dma *dma;
> dma_addr_t iova;
> @@ -1169,7 +1172,7 @@ static long vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma,
> if (!dma->size)
> return 0;
>
> - if (!IS_IOMMU_CAP_DOMAIN_IN_CONTAINER(iommu))
> + if (!IS_IOMMU_CAP_DOMAIN_IN_CONTAINER(iommu) || iommu->iopf_enabled)
> return 0;
>
> /*
> @@ -1306,11 +1309,20 @@ static void vfio_unmap_partial_iopf(struct vfio_iommu *iommu,
> }
> }
>
> +static void vfio_dma_clean_iopf(struct vfio_iommu *iommu, struct vfio_dma *dma)
> +{
> + vfio_unmap_partial_iopf(iommu, dma, dma->iova, dma->iova + dma->size);
> +
> + kfree(dma->iopf_mapped_bitmap);
> +}
> +
> static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *dma)
> {
> WARN_ON(!RB_EMPTY_ROOT(&dma->pfn_list));
> vfio_unmap_unpin(iommu, dma, true);
> vfio_unlink_dma(iommu, dma);
> + if (iommu->iopf_enabled)
> + vfio_dma_clean_iopf(iommu, dma);
> put_task_struct(dma->task);
> vfio_dma_bitmap_free(dma);
> if (dma->vaddr_invalid) {
> @@ -1359,7 +1371,8 @@ static int update_user_bitmap(u64 __user *bitmap, struct vfio_iommu *iommu,
> * mark all pages dirty if any IOMMU capable device is not able
> * to report dirty pages and all pages are pinned and mapped.
> */
> - if (iommu->num_non_pinned_groups && dma->iommu_mapped)
> + if (iommu->num_non_pinned_groups &&
> + (dma->iommu_mapped || iommu->iopf_enabled))
> bitmap_set(dma->bitmap, 0, nbits);
This seems like really poor integration of iopf into dirty page
tracking. I'd expect dirty logging to flush the mapped pages and
write faults to mark pages dirty. Shouldn't the fault handler also
provide only the access faulted, so for example a read fault wouldn't
mark the page dirty?
>
> if (shift) {
> @@ -1772,6 +1785,16 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,
> goto out_unlock;
> }
>
> + if (iommu->iopf_enabled) {
> + dma->iopf_mapped_bitmap = kvzalloc(IOPF_MAPPED_BITMAP_BYTES(
> + size >> PAGE_SHIFT), GFP_KERNEL);
> + if (!dma->iopf_mapped_bitmap) {
> + ret = -ENOMEM;
> + kfree(dma);
> + goto out_unlock;
> + }
So we're assuming nothing can fault and therefore nothing can reference
the iopf_mapped_bitmap until this point in the series?
> + }
> +
> iommu->dma_avail--;
> dma->iova = iova;
> dma->vaddr = vaddr;
> @@ -1811,8 +1834,11 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,
> /* Insert zero-sized and grow as we map chunks of it */
> vfio_link_dma(iommu, dma);
>
> - /* Don't pin and map if container doesn't contain IOMMU capable domain*/
> - if (!IS_IOMMU_CAP_DOMAIN_IN_CONTAINER(iommu))
> + /*
> + * Don't pin and map if container doesn't contain IOMMU capable domain,
> + * or IOPF enabled for the container.
> + */
> + if (!IS_IOMMU_CAP_DOMAIN_IN_CONTAINER(iommu) || iommu->iopf_enabled)
> dma->size = size;
> else
> ret = vfio_pin_map_dma(iommu, dma, size);
