[v2 07/11] mm/thp: add split during migration support

[Balbir Singh <balbirs@nvidia.com>]

Support splitting pages during THP zone device migration as needed.
The common case that arises is that after setup, during migrate
the destination might not be able to allocate MIGRATE_PFN_COMPOUND
pages.

Add a new routine migrate_vma_split_pages() to support the splitting
of already isolated pages. The pages being migrated are already unmapped
and marked for migration during setup (via unmap). folio_split() and
__split_unmapped_folio() take additional isolated arguments, to avoid
unmapping and remaping these pages and unlocking/putting the folio.

Cc: Karol Herbst <kherbst@redhat.com>
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: "Jérôme Glisse" <jglisse@redhat.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Jane Chu <jane.chu@oracle.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Donet Tom <donettom@linux.ibm.com>
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 +++++--
 mm/huge_memory.c        | 46 ++++++++++++++-------------
 mm/migrate_device.c     | 69 ++++++++++++++++++++++++++++++++++-------
 3 files changed, 91 insertions(+), 35 deletions(-)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 56fdcaf7604b..19e7e3b7c2b7 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -343,9 +343,9 @@ 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_device_private_folio(struct folio *folio);
+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,
@@ -354,6 +354,13 @@ 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/mm/huge_memory.c b/mm/huge_memory.c
index 75b368e7e33f..1fc1efa219c8 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3538,15 +3538,6 @@ 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;
 
@@ -3775,6 +3766,7 @@ 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
@@ -3790,7 +3782,7 @@ 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);
@@ -3840,13 +3832,15 @@ 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;
@@ -3913,7 +3907,8 @@ 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();
@@ -4000,10 +3995,13 @@ 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.
@@ -4037,6 +4035,7 @@ 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.
@@ -4060,11 +4059,15 @@ 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);
 
 	if (!ret && is_anon)
 		remap_flags = RMP_USE_SHARED_ZEROPAGE;
+
 	remap_page(folio, 1 << order, remap_flags);
 
 	/*
@@ -4149,12 +4152,13 @@ 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);
 }
 
 /*
@@ -4183,7 +4187,7 @@ 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 4c3334cc3228..49962ea19109 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -816,6 +816,29 @@ 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,
@@ -825,6 +848,11 @@ static int migrate_vma_insert_huge_pmd_page(struct migrate_vma *migrate,
 {
 	return 0;
 }
+
+static void migrate_vma_split_pages(struct migrate_vma *migrate,
+					unsigned long idx, unsigned long addr,
+					struct folio *folio)
+{}
 #endif
 
 /*
@@ -974,8 +1002,9 @@ 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]);
@@ -1017,12 +1046,16 @@ 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;
 		}
 
@@ -1044,7 +1077,14 @@ 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)) {
@@ -1079,12 +1119,17 @@ static void __migrate_device_pages(unsigned long *src_pfns,
 		BUG_ON(folio_test_writeback(folio));
 
 		if (migrate && migrate->fault_page == page)
-			extra_cnt = 1;
-		r = folio_migrate_mapping(mapping, newfolio, folio, extra_cnt);
-		if (r != MIGRATEPAGE_SUCCESS)
-			src_pfns[i] &= ~MIGRATE_PFN_MIGRATE;
-		else
-			folio_migrate_flags(newfolio, folio);
+			extra_cnt++;
+		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 != MIGRATEPAGE_SUCCESS)
+				src_pfns[i+j] &= ~MIGRATE_PFN_MIGRATE;
+			else
+				folio_migrate_flags(newfolio, folio);
+		}
 next:
 		i += nr;
 	}
-- 
2.50.1