Ralph Campbell <rcampbell@xxxxxxxxxx> 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@xxxxxxxxxxxxxxx
> Fixes: 76612d6ce4cc ("mm/hmm: reorganize how !pte_present is handled in hmm_vma_handle_pte()")
> Signed-off-by: Ralph Campbell <rcampbell@xxxxxxxxxx>
> Reported-by: Felix Kuehling <felix.kuehling@xxxxxxx>
> ---
> 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;
