Merge tag 'for-linus-hmm' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Pull hmm updates from Jason Gunthorpe:
 "Ralph has been working on nouveau's use of hmm_range_fault() and
  migrate_vma() which resulted in this small series. It adds reporting
  of the page table order from hmm_range_fault() and some optimization
  of migrate_vma():

   - Report the size of the page table mapping out of hmm_range_fault().

     This makes it easier to establish a large/huge/etc mapping in the
     device's page table.

   - Allow devices to ignore the invalidations during migration in cases
     where the migration is not going to change pages.

     For instance migrating pages to a device does not require the
     device to invalidate pages already in the device.

   - Update nouveau and hmm_tests to use the above"

* tag 'for-linus-hmm' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
  mm/hmm/test: use the new migration invalidation
  nouveau/svm: use the new migration invalidation
  mm/notifier: add migration invalidation type
  mm/migrate: add a flags parameter to migrate_vma
  nouveau: fix storing invalid ptes
  nouveau/hmm: support mapping large sysmem pages
  nouveau: fix mapping 2MB sysmem pages
  nouveau/hmm: fault one page at a time
  mm/hmm: add tests for hmm_pfn_to_map_order()
  mm/hmm: provide the page mapping order in hmm_range_fault()

1 files changed, 24 insertions, 23 deletions

diff --git a/lib/test_hmm.c b/lib/test_hmm.c
index a2a82262b97b..e7dc3de355b7 100644
--- a/lib/test_hmm.c
+++ b/lib/test_hmm.c
@@ -214,6 +214,14 @@ static bool dmirror_interval_invalidate(struct mmu_interval_notifier *mni,
 {
 	struct dmirror *dmirror = container_of(mni, struct dmirror, notifier);
 
+	/*
+	 * Ignore invalidation callbacks for device private pages since
+	 * the invalidation is handled as part of the migration process.
+	 */
+	if (range->event == MMU_NOTIFY_MIGRATE &&
+	    range->migrate_pgmap_owner == dmirror->mdevice)
+		return true;
+
 	if (mmu_notifier_range_blockable(range))
 		mutex_lock(&dmirror->mutex);
 	else if (!mutex_trylock(&dmirror->mutex))
@@ -585,15 +593,6 @@ static void dmirror_migrate_alloc_and_copy(struct migrate_vma *args,
 		 */
 		spage = migrate_pfn_to_page(*src);
 
-		/*
-		 * Don't migrate device private pages from our own driver or
-		 * others. For our own we would do a device private memory copy
-		 * not a migration and for others, we would need to fault the
-		 * other device's page into system memory first.
-		 */
-		if (spage && is_zone_device_page(spage))
-			continue;
-
 		dpage = dmirror_devmem_alloc_page(mdevice);
 		if (!dpage)
 			continue;
@@ -702,7 +701,8 @@ static int dmirror_migrate(struct dmirror *dmirror,
 		args.dst = dst_pfns;
 		args.start = addr;
 		args.end = next;
-		args.src_owner = NULL;
+		args.pgmap_owner = dmirror->mdevice;
+		args.flags = MIGRATE_VMA_SELECT_SYSTEM;
 		ret = migrate_vma_setup(&args);
 		if (ret)
 			goto out;
@@ -766,6 +766,10 @@ static void dmirror_mkentry(struct dmirror *dmirror, struct hmm_range *range,
 		*perm |= HMM_DMIRROR_PROT_WRITE;
 	else
 		*perm |= HMM_DMIRROR_PROT_READ;
+	if (hmm_pfn_to_map_order(entry) + PAGE_SHIFT == PMD_SHIFT)
+		*perm |= HMM_DMIRROR_PROT_PMD;
+	else if (hmm_pfn_to_map_order(entry) + PAGE_SHIFT == PUD_SHIFT)
+		*perm |= HMM_DMIRROR_PROT_PUD;
 }
 
 static bool dmirror_snapshot_invalidate(struct mmu_interval_notifier *mni,
@@ -987,7 +991,7 @@ static void dmirror_devmem_free(struct page *page)
 }
 
 static vm_fault_t dmirror_devmem_fault_alloc_and_copy(struct migrate_vma *args,
-						struct dmirror_device *mdevice)
+						      struct dmirror *dmirror)
 {
 	const unsigned long *src = args->src;
 	unsigned long *dst = args->dst;
@@ -1009,6 +1013,7 @@ static vm_fault_t dmirror_devmem_fault_alloc_and_copy(struct migrate_vma *args,
 			continue;
 
 		lock_page(dpage);
+		xa_erase(&dmirror->pt, addr >> PAGE_SHIFT);
 		copy_highpage(dpage, spage);
 		*dst = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED;
 		if (*src & MIGRATE_PFN_WRITE)
@@ -1017,15 +1022,6 @@ static vm_fault_t dmirror_devmem_fault_alloc_and_copy(struct migrate_vma *args,
 	return 0;
 }
 
-static void dmirror_devmem_fault_finalize_and_map(struct migrate_vma *args,
-						  struct dmirror *dmirror)
-{
-	/* Invalidate the device's page table mapping. */
-	mutex_lock(&dmirror->mutex);
-	dmirror_do_update(dmirror, args->start, args->end);
-	mutex_unlock(&dmirror->mutex);
-}
-
 static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf)
 {
 	struct migrate_vma args;
@@ -1049,16 +1045,21 @@ static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf)
 	args.end = args.start + PAGE_SIZE;
 	args.src = &src_pfns;
 	args.dst = &dst_pfns;
-	args.src_owner = dmirror->mdevice;
+	args.pgmap_owner = dmirror->mdevice;
+	args.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE;
 
 	if (migrate_vma_setup(&args))
 		return VM_FAULT_SIGBUS;
 
-	ret = dmirror_devmem_fault_alloc_and_copy(&args, dmirror->mdevice);
+	ret = dmirror_devmem_fault_alloc_and_copy(&args, dmirror);
 	if (ret)
 		return ret;
 	migrate_vma_pages(&args);
-	dmirror_devmem_fault_finalize_and_map(&args, dmirror);
+	/*
+	 * No device finalize step is needed since
+	 * dmirror_devmem_fault_alloc_and_copy() will have already
+	 * invalidated the device page table.
+	 */
 	migrate_vma_finalize(&args);
 	return 0;
 }