[v5 10/15] mm/migrate_device: add THP splitting during migration

[Balbir Singh <balbirs@nvidia.com>]

Implement migrate_vma_split_pages() to handle THP splitting during
the migration process when destination cannot allocate compound pages.

This addresses the common scenario where migrate_vma_setup() succeeds
with MIGRATE_PFN_COMPOUND pages, but the destination device cannot
allocate large pages during the migration phase.

Key changes:
- migrate_vma_split_pages(): Split already-isolated pages during migration
- Enhanced folio_split() and __split_unmapped_folio() with isolated
  parameter to avoid redundant unmap/remap operations

This provides a fallback mechansim to ensure migration succeeds
even when large page allocation fails at the destination.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Gregory Price <gourry@gourry.net>
Cc: Ying Huang <ying.huang@linux.alibaba.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com>
Cc: Nico Pache <npache@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Lyude Paul <lyude@redhat.com>
Cc: Danilo Krummrich <dakr@kernel.org>
Cc: David Airlie <airlied@gmail.com>
Cc: Simona Vetter <simona@ffwll.ch>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Mika Penttilä <mpenttil@redhat.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Francois Dugast <francois.dugast@intel.com>

Signed-off-by: Balbir Singh <balbirs@nvidia.com>
---
 include/linux/huge_mm.h | 11 +++++--
 lib/test_hmm.c          |  9 ++++++
 mm/huge_memory.c        | 45 ++++++++++++++-------------
 mm/migrate_device.c     | 69 ++++++++++++++++++++++++++++++++++-------
 4 files changed, 100 insertions(+), 34 deletions(-)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 2c6a0c3c862c..3242a262b79e 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -365,8 +365,8 @@ unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long add
 		vm_flags_t vm_flags);
 
 bool can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins);
-int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
-		unsigned int new_order);
+int __split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
+		unsigned int new_order, bool unmapped);
 int min_order_for_split(struct folio *folio);
 int split_folio_to_list(struct folio *folio, struct list_head *list);
 bool uniform_split_supported(struct folio *folio, unsigned int new_order,
@@ -375,6 +375,13 @@ bool non_uniform_split_supported(struct folio *folio, unsigned int new_order,
 		bool warns);
 int folio_split(struct folio *folio, unsigned int new_order, struct page *page,
 		struct list_head *list);
+
+static inline int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
+		unsigned int new_order)
+{
+	return __split_huge_page_to_list_to_order(page, list, new_order, false);
+}
+
 /*
  * try_folio_split - try to split a @folio at @page using non uniform split.
  * @folio: folio to be split
diff --git a/lib/test_hmm.c b/lib/test_hmm.c
index 41092c065c2d..6455707df902 100644
--- a/lib/test_hmm.c
+++ b/lib/test_hmm.c
@@ -1611,6 +1611,15 @@ static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf)
 	order = folio_order(page_folio(vmf->page));
 	nr = 1 << order;
 
+	/*
+	 * When folios are partially mapped, we can't rely on the folio
+	 * order of vmf->page as the folio might not be fully split yet
+	 */
+	if (vmf->pte) {
+		order = 0;
+		nr = 1;
+	}
+
 	/*
 	 * Consider a per-cpu cache of src and dst pfns, but with
 	 * large number of cpus that might not scale well.
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index e38482e6e5c0..c69adc69c424 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3459,15 +3459,6 @@ static void __split_folio_to_order(struct folio *folio, int old_order,
 		new_folio->mapping = folio->mapping;
 		new_folio->index = folio->index + i;
 
-		/*
-		 * page->private should not be set in tail pages. Fix up and warn once
-		 * if private is unexpectedly set.
-		 */
-		if (unlikely(new_folio->private)) {
-			VM_WARN_ON_ONCE_PAGE(true, new_head);
-			new_folio->private = NULL;
-		}
-
 		if (folio_test_swapcache(folio))
 			new_folio->swap.val = folio->swap.val + i;
 
@@ -3696,6 +3687,7 @@ bool uniform_split_supported(struct folio *folio, unsigned int new_order,
  * @lock_at: a page within @folio to be left locked to caller
  * @list: after-split folios will be put on it if non NULL
  * @uniform_split: perform uniform split or not (non-uniform split)
+ * @unmapped: The pages are already unmapped, they are migration entries.
  *
  * It calls __split_unmapped_folio() to perform uniform and non-uniform split.
  * It is in charge of checking whether the split is supported or not and
@@ -3711,7 +3703,7 @@ bool uniform_split_supported(struct folio *folio, unsigned int new_order,
  */
 static int __folio_split(struct folio *folio, unsigned int new_order,
 		struct page *split_at, struct page *lock_at,
-		struct list_head *list, bool uniform_split)
+		struct list_head *list, bool uniform_split, bool unmapped)
 {
 	struct deferred_split *ds_queue = get_deferred_split_queue(folio);
 	XA_STATE(xas, &folio->mapping->i_pages, folio->index);
@@ -3761,13 +3753,15 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 		 * is taken to serialise against parallel split or collapse
 		 * operations.
 		 */
-		anon_vma = folio_get_anon_vma(folio);
-		if (!anon_vma) {
-			ret = -EBUSY;
-			goto out;
+		if (!unmapped) {
+			anon_vma = folio_get_anon_vma(folio);
+			if (!anon_vma) {
+				ret = -EBUSY;
+				goto out;
+			}
+			anon_vma_lock_write(anon_vma);
 		}
 		mapping = NULL;
-		anon_vma_lock_write(anon_vma);
 	} else {
 		unsigned int min_order;
 		gfp_t gfp;
@@ -3834,7 +3828,8 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 		goto out_unlock;
 	}
 
-	unmap_folio(folio);
+	if (!unmapped)
+		unmap_folio(folio);
 
 	/* block interrupt reentry in xa_lock and spinlock */
 	local_irq_disable();
@@ -3921,10 +3916,13 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 
 			next = folio_next(new_folio);
 
+			zone_device_private_split_cb(folio, new_folio);
+
 			expected_refs = folio_expected_ref_count(new_folio) + 1;
 			folio_ref_unfreeze(new_folio, expected_refs);
 
-			lru_add_split_folio(folio, new_folio, lruvec, list);
+			if (!unmapped)
+				lru_add_split_folio(folio, new_folio, lruvec, list);
 
 			/*
 			 * Anonymous folio with swap cache.
@@ -3958,6 +3956,7 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 			folio_put_refs(new_folio, nr_pages);
 		}
 
+		zone_device_private_split_cb(folio, NULL);
 		/*
 		 * Unfreeze @folio only after all page cache entries, which
 		 * used to point to it, have been updated with new folios.
@@ -3981,6 +3980,9 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 
 	local_irq_enable();
 
+	if (unmapped)
+		return ret;
+
 	if (nr_shmem_dropped)
 		shmem_uncharge(mapping->host, nr_shmem_dropped);
 
@@ -4071,12 +4073,13 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
  * Returns -EINVAL when trying to split to an order that is incompatible
  * with the folio. Splitting to order 0 is compatible with all folios.
  */
-int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
-				     unsigned int new_order)
+int __split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
+				     unsigned int new_order, bool unmapped)
 {
 	struct folio *folio = page_folio(page);
 
-	return __folio_split(folio, new_order, &folio->page, page, list, true);
+	return __folio_split(folio, new_order, &folio->page, page, list, true,
+				unmapped);
 }
 
 /*
@@ -4105,7 +4108,7 @@ int folio_split(struct folio *folio, unsigned int new_order,
 		struct page *split_at, struct list_head *list)
 {
 	return __folio_split(folio, new_order, split_at, &folio->page, list,
-			false);
+			false, false);
 }
 
 int min_order_for_split(struct folio *folio)
diff --git a/mm/migrate_device.c b/mm/migrate_device.c
index 1dfcf4799ea5..32cb7355f525 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -910,6 +910,29 @@ static int migrate_vma_insert_huge_pmd_page(struct migrate_vma *migrate,
 		src[i] &= ~MIGRATE_PFN_MIGRATE;
 	return 0;
 }
+
+static int migrate_vma_split_pages(struct migrate_vma *migrate,
+					unsigned long idx, unsigned long addr,
+					struct folio *folio)
+{
+	unsigned long i;
+	unsigned long pfn;
+	unsigned long flags;
+	int ret = 0;
+
+	folio_get(folio);
+	split_huge_pmd_address(migrate->vma, addr, true);
+	ret = __split_huge_page_to_list_to_order(folio_page(folio, 0), NULL,
+							0, true);
+	if (ret)
+		return ret;
+	migrate->src[idx] &= ~MIGRATE_PFN_COMPOUND;
+	flags = migrate->src[idx] & ((1UL << MIGRATE_PFN_SHIFT) - 1);
+	pfn = migrate->src[idx] >> MIGRATE_PFN_SHIFT;
+	for (i = 1; i < HPAGE_PMD_NR; i++)
+		migrate->src[i+idx] = migrate_pfn(pfn + i) | flags;
+	return ret;
+}
 #else /* !CONFIG_ARCH_ENABLE_THP_MIGRATION */
 static int migrate_vma_insert_huge_pmd_page(struct migrate_vma *migrate,
 					 unsigned long addr,
@@ -919,6 +942,13 @@ static int migrate_vma_insert_huge_pmd_page(struct migrate_vma *migrate,
 {
 	return 0;
 }
+
+static int migrate_vma_split_pages(struct migrate_vma *migrate,
+					unsigned long idx, unsigned long addr,
+					struct folio *folio)
+{
+	return 0;
+}
 #endif
 
 /*
@@ -1068,8 +1098,9 @@ static void __migrate_device_pages(unsigned long *src_pfns,
 				struct migrate_vma *migrate)
 {
 	struct mmu_notifier_range range;
-	unsigned long i;
+	unsigned long i, j;
 	bool notified = false;
+	unsigned long addr;
 
 	for (i = 0; i < npages; ) {
 		struct page *newpage = migrate_pfn_to_page(dst_pfns[i]);
@@ -1111,12 +1142,16 @@ static void __migrate_device_pages(unsigned long *src_pfns,
 				(!(dst_pfns[i] & MIGRATE_PFN_COMPOUND))) {
 				nr = HPAGE_PMD_NR;
 				src_pfns[i] &= ~MIGRATE_PFN_COMPOUND;
-				src_pfns[i] &= ~MIGRATE_PFN_MIGRATE;
-				goto next;
+			} else {
+				nr = 1;
 			}
 
-			migrate_vma_insert_page(migrate, addr, &dst_pfns[i],
-						&src_pfns[i]);
+			for (j = 0; j < nr && i + j < npages; j++) {
+				src_pfns[i+j] |= MIGRATE_PFN_MIGRATE;
+				migrate_vma_insert_page(migrate,
+					addr + j * PAGE_SIZE,
+					&dst_pfns[i+j], &src_pfns[i+j]);
+			}
 			goto next;
 		}
 
@@ -1138,7 +1173,14 @@ static void __migrate_device_pages(unsigned long *src_pfns,
 							 MIGRATE_PFN_COMPOUND);
 					goto next;
 				}
-				src_pfns[i] &= ~MIGRATE_PFN_MIGRATE;
+				nr = 1 << folio_order(folio);
+				addr = migrate->start + i * PAGE_SIZE;
+				if (migrate_vma_split_pages(migrate, i, addr,
+								folio)) {
+					src_pfns[i] &= ~(MIGRATE_PFN_MIGRATE |
+							 MIGRATE_PFN_COMPOUND);
+					goto next;
+				}
 			} else if ((src_pfns[i] & MIGRATE_PFN_MIGRATE) &&
 				(dst_pfns[i] & MIGRATE_PFN_COMPOUND) &&
 				!(src_pfns[i] & MIGRATE_PFN_COMPOUND)) {
@@ -1174,11 +1216,16 @@ static void __migrate_device_pages(unsigned long *src_pfns,
 
 		if (migrate && migrate->fault_page == page)
 			extra_cnt = 1;
-		r = folio_migrate_mapping(mapping, newfolio, folio, extra_cnt);
-		if (r)
-			src_pfns[i] &= ~MIGRATE_PFN_MIGRATE;
-		else
-			folio_migrate_flags(newfolio, folio);
+		for (j = 0; j < nr && i + j < npages; j++) {
+			folio = page_folio(migrate_pfn_to_page(src_pfns[i+j]));
+			newfolio = page_folio(migrate_pfn_to_page(dst_pfns[i+j]));
+
+			r = folio_migrate_mapping(mapping, newfolio, folio, extra_cnt);
+			if (r)
+				src_pfns[i+j] &= ~MIGRATE_PFN_MIGRATE;
+			else
+				folio_migrate_flags(newfolio, folio);
+		}
 next:
 		i += nr;
 	}
-- 
2.50.1