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@xxxxxxxxxx>
> 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
