On Mon, Nov 7, 2022 at 6:19 PM David Hildenbrand wrote:
>
> FOLL_FORCE is really only for debugger access. As we unpin the pinned pages
> using unpin_user_pages_dirty_lock(true), the assumption is that all these
> pages are writable.
>
> FOLL_FORCE in this case seems to be due to copy-and-past from other
> drivers. Let's just remove it.
>
> Cc: Oded Gabbay
> Cc: Arnd Bergmann
> Cc: Greg Kroah-Hartman
> Signed-off-by: David Hildenbrand
> ---
> drivers/misc/habanalabs/common/memory.c | 3 +--
> 1 file changed, 1 insertion(+), 2 deletions(-)
>
> diff --git a/drivers/misc/habanalabs/common/memory.c
> b/drivers/misc/habanalabs/common/memory.c
> index ef28f3b37b93..e35cca96bbef 100644
> --- a/drivers/misc/habanalabs/common/memory.c
> +++ b/drivers/misc/habanalabs/common/memory.c
> @@ -2312,8 +2312,7 @@ static int get_user_memory(struct hl_device *hdev, u64
> addr, u64 size,
> if (!userptr->pages)
> return -ENOMEM;
>
> - rc = pin_user_pages_fast(start, npages,
> -FOLL_FORCE | FOLL_WRITE | FOLL_LONGTERM,
> + rc = pin_user_pages_fast(start, npages, FOLL_WRITE | FOLL_LONGTERM,
> userptr->pages);
>
> if (rc != npages) {
> --
> 2.38.1
>
>
Acked-by: Oded Gabbay
Thanks,
Oded
