Re: [PATCH v2 3/5] mm/notifier: add migration invalidation type

[Ralph Campbell <rcampbell@nvidia.com>]

On 7/20/20 11:40 AM, Jason Gunthorpe wrote:
> On Mon, Jul 13, 2020 at 10:21:47AM -0700, Ralph Campbell wrote:
>> Currently migrate_vma_setup() calls mmu_notifier_invalidate_range_start()
>> which flushes all device private page mappings whether or not a page
>> is being migrated to/from device private memory. In order to not disrupt
>> device mappings that are not being migrated, shift the responsibility
>> for clearing device private mappings to the device driver and leave
>> CPU page table unmapping handled by migrate_vma_setup(). To support
>> this, the caller of migrate_vma_setup() should always set struct
>> migrate_vma::src_owner to a non NULL value that matches the device
>> private page->pgmap->owner. This value is then passed to the struct
>> mmu_notifier_range with a new event type which the driver's invalidation
>> function can use to avoid device MMU invalidations.
>>
>> Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
>>   include/linux/mmu_notifier.h | 7 +++++++
>>   mm/migrate.c                 | 8 +++++++-
>>   2 files changed, 14 insertions(+), 1 deletion(-)
>>
>> diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
>> index fc68f3570e19..1921fcf6be5b 100644
>> +++ b/include/linux/mmu_notifier.h
>> @@ -38,6 +38,10 @@ struct mmu_interval_notifier;
>>    *
>>    * @MMU_NOTIFY_RELEASE: used during mmu_interval_notifier invalidate to signal
>>    * that the mm refcount is zero and the range is no longer accessible.
>> + *
>> + * @MMU_NOTIFY_MIGRATE: used during migrate_vma_collect() invalidate to signal
>> + * a device driver to possibly ignore the invalidation if the
>> + * migrate_pgmap_owner field matches the driver's device private pgmap owner.
>>    */
>>   enum mmu_notifier_event {
>>   	MMU_NOTIFY_UNMAP = 0,
>> @@ -46,6 +50,7 @@ enum mmu_notifier_event {
>>   	MMU_NOTIFY_PROTECTION_PAGE,
>>   	MMU_NOTIFY_SOFT_DIRTY,
>>   	MMU_NOTIFY_RELEASE,
>> +	MMU_NOTIFY_MIGRATE,
>>   };
>>   
>>   #define MMU_NOTIFIER_RANGE_BLOCKABLE (1 << 0)
>> @@ -264,6 +269,7 @@ struct mmu_notifier_range {
>>   	unsigned long end;
>>   	unsigned flags;
>>   	enum mmu_notifier_event event;
>> +	void *migrate_pgmap_owner;
>>   };
>>   
>>   static inline int mm_has_notifiers(struct mm_struct *mm)
>> @@ -513,6 +519,7 @@ static inline void mmu_notifier_range_init(struct mmu_notifier_range *range,
>>   	range->start = start;
>>   	range->end = end;
>>   	range->flags = flags;
>> +	range->migrate_pgmap_owner = NULL;
>>   }
>>   
>>   #define ptep_clear_flush_young_notify(__vma, __address, __ptep)		\
>> diff --git a/mm/migrate.c b/mm/migrate.c
>> index 2bbc5c4c672e..9b3dcb81be5f 100644
>> +++ b/mm/migrate.c
>> @@ -2391,8 +2391,14 @@ static void migrate_vma_collect(struct migrate_vma *migrate)
>>   {
>>   	struct mmu_notifier_range range;
>>   
>> -	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL,
>> +	/*
>> +	 * Note that the src_owner is passed to the mmu notifier callback so
>> +	 * that the registered device driver can skip invalidating device
>> +	 * private page mappings that won't be migrated.
>> +	 */
>> +	mmu_notifier_range_init(&range, MMU_NOTIFY_MIGRATE, 0, migrate->vma,
>>   			migrate->vma->vm_mm, migrate->start, migrate->end);
> 
> So the idea is that src_owner is always set to the pgmap owner when
> working with DEVICE_PRIVATE?
> 
> But then the comment in the prior patch should be fixed:
> 
> @@ -199,11 +204,12 @@  struct migrate_vma {
>   
>   	/*
>   	 * Set to the owner value also stored in page->pgmap->owner for
> +	 * migrating device private memory. The direction also needs to
> +	 * be set to MIGRATE_VMA_FROM_DEVICE_PRIVATE.
> 
> To say the caller must always provide src_owner.
> 
> And that field should probably be renamed at this point, as there is
> nothing "src" about it. It is just the pgmap_owner of the
> DEVICE_PRIVATE pages the TO/FROM DEVICE migration is working on.
> 
> Jason

Good point. I'll send a v3 with your suggested changes.