[PATCH v2 1/2] mm/hmm: fault non-owner device private entries

[PATCH v2 1/2] mm/hmm: fault non-owner device private entries

[Ralph Campbell]

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.

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 | 19 ++++++++-----------
 1 file changed, 8 insertions(+), 11 deletions(-)

diff --git a/mm/hmm.c b/mm/hmm.c
index 3fd3242c5e50..f2aa63b94d9b 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -212,14 +212,6 @@ int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr,
 		unsigned long end, unsigned long hmm_pfns[], pmd_t pmd);
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
-static inline bool hmm_is_device_private_entry(struct hmm_range *range,
-		swp_entry_t entry)
-{
-	return is_device_private_entry(entry) &&
-		pfn_swap_entry_to_page(entry)->pgmap->owner ==
-		range->dev_private_owner;
-}
-
 static inline unsigned long pte_to_hmm_pfn_flags(struct hmm_range *range,
 						 pte_t pte)
 {
@@ -252,10 +244,12 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 		swp_entry_t entry = pte_to_swp_entry(pte);
 
 		/*
-		 * Never fault in device private pages, but just report
-		 * the PFN even if not present.
+		 * Don't fault in device private pages owned by the caller,
+		 * just report the PFN.
 		 */
-		if (hmm_is_device_private_entry(range, entry)) {
+		if (is_device_private_entry(entry) &&
+		    pfn_swap_entry_to_page(entry)->pgmap->owner ==
+		    range->dev_private_owner) {
 			cpu_flags = HMM_PFN_VALID;
 			if (is_writable_device_private_entry(entry))
 				cpu_flags |= HMM_PFN_WRITE;
@@ -273,6 +267,9 @@ 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;
 
-- 
2.35.3

Re: [PATCH v2 1/2] mm/hmm: fault non-owner device private entries

[Alistair Popple]

Thanks Ralph, please add:

Reviewed-by: Alistair Popple <apopple@nvidia.com>

However I think the fixes tag is wrong, see below.

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.
>
> Cc: stable@vger.kernel.org
> Fixes: 76612d6ce4cc ("mm/hmm: reorganize how !pte_present is handled in hmm_vma_handle_pte()")

This should be 08ddddda667b ("mm/hmm: check the device private page owner in hmm_range_fault()")

> Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
> Reported-by: Felix Kuehling <felix.kuehling@amd.com>
> ---
>  mm/hmm.c | 19 ++++++++-----------
>  1 file changed, 8 insertions(+), 11 deletions(-)
>
> diff --git a/mm/hmm.c b/mm/hmm.c
> index 3fd3242c5e50..f2aa63b94d9b 100644
> --- a/mm/hmm.c
> +++ b/mm/hmm.c
> @@ -212,14 +212,6 @@ int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr,
>  		unsigned long end, unsigned long hmm_pfns[], pmd_t pmd);
>  #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
>
> -static inline bool hmm_is_device_private_entry(struct hmm_range *range,
> -		swp_entry_t entry)
> -{
> -	return is_device_private_entry(entry) &&
> -		pfn_swap_entry_to_page(entry)->pgmap->owner ==
> -		range->dev_private_owner;
> -}
> -
>  static inline unsigned long pte_to_hmm_pfn_flags(struct hmm_range *range,
>  						 pte_t pte)
>  {
> @@ -252,10 +244,12 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
>  		swp_entry_t entry = pte_to_swp_entry(pte);
>
>  		/*
> -		 * Never fault in device private pages, but just report
> -		 * the PFN even if not present.
> +		 * Don't fault in device private pages owned by the caller,
> +		 * just report the PFN.
>  		 */
> -		if (hmm_is_device_private_entry(range, entry)) {
> +		if (is_device_private_entry(entry) &&
> +		    pfn_swap_entry_to_page(entry)->pgmap->owner ==
> +		    range->dev_private_owner) {
>  			cpu_flags = HMM_PFN_VALID;
>  			if (is_writable_device_private_entry(entry))
>  				cpu_flags |= HMM_PFN_WRITE;
> @@ -273,6 +267,9 @@ 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;

Re: [PATCH v2 1/2] mm/hmm: fault non-owner device private entries

[Ralph Campbell]

On 7/25/22 18:26, Alistair Popple wrote:
> Thanks Ralph, please add:
>
> Reviewed-by: Alistair Popple <apopple@nvidia.com>
>
> However I think the fixes tag is wrong, see below.
>
> 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.
>>
>> Cc: stable@vger.kernel.org
>> Fixes: 76612d6ce4cc ("mm/hmm: reorganize how !pte_present is handled in hmm_vma_handle_pte()")
> This should be 08ddddda667b ("mm/hmm: check the device private page owner in hmm_range_fault()")

Looks better to me too.
I assume Andrew will update the tags.

Re: [PATCH v2 1/2] mm/hmm: fault non-owner device private entries

[Andrew Morton]

On Tue, 26 Jul 2022 09:51:24 -0700 Ralph Campbell <rcampbell@nvidia.com> wrote:

> >> Cc: stable@vger.kernel.org
> >> Fixes: 76612d6ce4cc ("mm/hmm: reorganize how !pte_present is handled in hmm_vma_handle_pte()")
> > This should be 08ddddda667b ("mm/hmm: check the device private page owner in hmm_range_fault()")
> 
> Looks better to me too.
> I assume Andrew will update the tags.

Yes, I updated the patch.

Re: [PATCH v2 1/2] mm/hmm: fault non-owner device private entries

[John Hubbard]

On 7/25/22 11:36, Ralph Campbell wrote:
> 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.

Hi Ralph,

Just for our future sanity when trying to read through the log,
it's best to describe the problem, and then describe the fix. The
text above does not makes it quite difficult to tell if it refers to
the pre-patch or post-patch code.

Also, a higher-level description of what this enables is good to have.

thanks,
-- 
John Hubbard
NVIDIA
> 
> 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 | 19 ++++++++-----------
>   1 file changed, 8 insertions(+), 11 deletions(-)
> 
> diff --git a/mm/hmm.c b/mm/hmm.c
> index 3fd3242c5e50..f2aa63b94d9b 100644
> --- a/mm/hmm.c
> +++ b/mm/hmm.c
> @@ -212,14 +212,6 @@ int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr,
>   		unsigned long end, unsigned long hmm_pfns[], pmd_t pmd);
>   #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
>   
> -static inline bool hmm_is_device_private_entry(struct hmm_range *range,
> -		swp_entry_t entry)
> -{
> -	return is_device_private_entry(entry) &&
> -		pfn_swap_entry_to_page(entry)->pgmap->owner ==
> -		range->dev_private_owner;
> -}
> -
>   static inline unsigned long pte_to_hmm_pfn_flags(struct hmm_range *range,
>   						 pte_t pte)
>   {
> @@ -252,10 +244,12 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
>   		swp_entry_t entry = pte_to_swp_entry(pte);
>   
>   		/*
> -		 * Never fault in device private pages, but just report
> -		 * the PFN even if not present.
> +		 * Don't fault in device private pages owned by the caller,
> +		 * just report the PFN.
>   		 */
> -		if (hmm_is_device_private_entry(range, entry)) {
> +		if (is_device_private_entry(entry) &&
> +		    pfn_swap_entry_to_page(entry)->pgmap->owner ==
> +		    range->dev_private_owner) {
>   			cpu_flags = HMM_PFN_VALID;
>   			if (is_writable_device_private_entry(entry))
>   				cpu_flags |= HMM_PFN_WRITE;
> @@ -273,6 +267,9 @@ 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;
>