Re: [PATCH v2] habanalabs: Stop using iommu_present()

[Oded Gabbay]

On Mon, Apr 11, 2022 at 3:36 PM Robin Murphy <robin.murphy@xxxxxxx> wrote:
>
> Even if an IOMMU might be present for some PCI segment in the system,
> that doesn't necessarily mean it provides translation for the device
> we care about. Replace iommu_present() with a more appropriate check.
>
> Signed-off-by: Robin Murphy <robin.murphy@xxxxxxx>
> ---
>
> v2: Rebase on habanalabs-next
>
>  drivers/misc/habanalabs/common/debugfs.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/misc/habanalabs/common/debugfs.c b/drivers/misc/habanalabs/common/debugfs.c
> index 7c4a4d504e4c..a94f01713efd 100644
> --- a/drivers/misc/habanalabs/common/debugfs.c
> +++ b/drivers/misc/habanalabs/common/debugfs.c
> @@ -722,7 +722,7 @@ static int hl_access_mem(struct hl_device *hdev, u64 addr, u64 *val,
>         if (found)
>                 return 0;
>
> -       if (!user_address || iommu_present(&pci_bus_type)) {
> +       if (!user_address || device_iommu_mapped(&hdev->pdev->dev)) {
>                 rc = -EINVAL;
>                 goto err;
>         }
> --
> 2.28.0.dirty
>
Reviewed-by: Oded Gabbay <ogabbay@xxxxxxxxxx>
Applied to -next.
Thanks,
Oded