Re: [PATCH] mm/hmm: fault non-owner device private entries

[Alistair Popple <apopple@nvidia.com>]

Ralph Campbell <rcampbell@nvidia.com> writes:

> If hmm_range_fault() is called with the HMM_PFN_REQ_FAULT flag and a
> device private PTE is found, the hmm_range::dev_private_owner page is
> used to determine if the device private page should not be faulted in.
> However, if the device private page is not owned by the caller,
> hmm_range_fault() returns an error instead of calling migrate_to_ram()
> to fault in the page.

		/*
		 * Never fault in device private pages, but just report
		 * the PFN even if not present.
		 */

This comment needs updating because it will be possible to fault in
device private pages now.

It also looks a bit strange to be checking for device private entries
twice - I think it would be clearer if hmm_is_device_private_entry() is
removed and the ownership check done directly in hmm_vma_handle_pte().

 - Alistair

> Cc: stable@vger.kernel.org
> Fixes: 76612d6ce4cc ("mm/hmm: reorganize how !pte_present is handled in hmm_vma_handle_pte()")
> Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
> Reported-by: Felix Kuehling <felix.kuehling@amd.com>
> ---
>  mm/hmm.c | 3 +++
>  1 file changed, 3 insertions(+)
>
> diff --git a/mm/hmm.c b/mm/hmm.c
> index 3fd3242c5e50..7db2b29bdc85 100644
> --- a/mm/hmm.c
> +++ b/mm/hmm.c
> @@ -273,6 +273,9 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
>  		if (!non_swap_entry(entry))
>  			goto fault;
>
> +		if (is_device_private_entry(entry))
> +			goto fault;
> +
>  		if (is_device_exclusive_entry(entry))
>  			goto fault;