[v1 resend 08/12] 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>

Signed-off-by: Balbir Singh <balbirs@nvidia.com>
---
 include/linux/huge_mm.h | 11 ++++++--
 mm/huge_memory.c        | 54 ++++++++++++++++++++-----------------
 mm/migrate_device.c     | 59 ++++++++++++++++++++++++++++++++---------
 3 files changed, 85 insertions(+), 39 deletions(-)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 65a1bdf29bb9..5f55a754e57c 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -343,8 +343,8 @@ 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 isolated);
 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,
@@ -353,6 +353,13 @@ 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 d55e36ae0c39..e00ddfed22fa 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3424,15 +3424,6 @@ 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;
 
@@ -3519,7 +3510,7 @@ static int __split_unmapped_folio(struct folio *folio, int new_order,
 		struct page *split_at, struct page *lock_at,
 		struct list_head *list, pgoff_t end,
 		struct xa_state *xas, struct address_space *mapping,
-		bool uniform_split)
+		bool uniform_split, bool isolated)
 {
 	struct lruvec *lruvec;
 	struct address_space *swap_cache = NULL;
@@ -3643,8 +3634,9 @@ static int __split_unmapped_folio(struct folio *folio, int new_order,
 				percpu_ref_get_many(&release->pgmap->ref,
 							(1 << new_order) - 1);
 
-			lru_add_split_folio(origin_folio, release, lruvec,
-					list);
+			if (!isolated)
+				lru_add_split_folio(origin_folio, release,
+							lruvec, list);
 
 			/* Some pages can be beyond EOF: drop them from cache */
 			if (release->index >= end) {
@@ -3697,6 +3689,12 @@ static int __split_unmapped_folio(struct folio *folio, int new_order,
 	if (nr_dropped)
 		shmem_uncharge(mapping->host, nr_dropped);
 
+	/*
+	 * Don't remap and unlock isolated folios
+	 */
+	if (isolated)
+		return ret;
+
 	remap_page(origin_folio, 1 << order,
 			folio_test_anon(origin_folio) ?
 				RMP_USE_SHARED_ZEROPAGE : 0);
@@ -3790,6 +3788,7 @@ 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)
+ * @isolated: The pages are already unmapped
  *
  * 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
@@ -3800,7 +3799,7 @@ 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 isolated)
 {
 	struct deferred_split *ds_queue = get_deferred_split_queue(folio);
 	XA_STATE(xas, &folio->mapping->i_pages, folio->index);
@@ -3846,14 +3845,16 @@ 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 (!isolated) {
+			anon_vma = folio_get_anon_vma(folio);
+			if (!anon_vma) {
+				ret = -EBUSY;
+				goto out;
+			}
+			anon_vma_lock_write(anon_vma);
 		}
 		end = -1;
 		mapping = NULL;
-		anon_vma_lock_write(anon_vma);
 	} else {
 		unsigned int min_order;
 		gfp_t gfp;
@@ -3920,7 +3921,8 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 		goto out_unlock;
 	}
 
-	unmap_folio(folio);
+	if (!isolated)
+		unmap_folio(folio);
 
 	/* block interrupt reentry in xa_lock and spinlock */
 	local_irq_disable();
@@ -3973,14 +3975,15 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 
 		ret = __split_unmapped_folio(folio, new_order,
 				split_at, lock_at, list, end, &xas, mapping,
-				uniform_split);
+				uniform_split, isolated);
 	} else {
 		spin_unlock(&ds_queue->split_queue_lock);
 fail:
 		if (mapping)
 			xas_unlock(&xas);
 		local_irq_enable();
-		remap_page(folio, folio_nr_pages(folio), 0);
+		if (!isolated)
+			remap_page(folio, folio_nr_pages(folio), 0);
 		ret = -EAGAIN;
 	}
 
@@ -4046,12 +4049,13 @@ 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 isolated)
 {
 	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,
+				isolated);
 }
 
 /*
@@ -4080,7 +4084,7 @@ 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 41d0bd787969..acd2f03b178d 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -813,6 +813,24 @@ static int migrate_vma_insert_huge_pmd_page(struct migrate_vma *migrate,
 		src[i] &= ~MIGRATE_PFN_MIGRATE;
 	return 0;
 }
+
+static void 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;
+
+	folio_get(folio);
+	split_huge_pmd_address(migrate->vma, addr, true);
+	__split_huge_page_to_list_to_order(folio_page(folio, 0), NULL, 0, true);
+	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;
+}
 #else /* !CONFIG_ARCH_ENABLE_THP_MIGRATION */
 static int migrate_vma_insert_huge_pmd_page(struct migrate_vma *migrate,
 					 unsigned long addr,
@@ -822,6 +840,11 @@ 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
 
 /*
@@ -971,8 +994,9 @@ 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]);
@@ -1014,12 +1038,16 @@ 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;
 		}
 
@@ -1041,7 +1069,9 @@ 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;
+				migrate_vma_split_pages(migrate, i, addr, folio);
 			} else if ((src_pfns[i] & MIGRATE_PFN_MIGRATE) &&
 				(dst_pfns[i] & MIGRATE_PFN_COMPOUND) &&
 				!(src_pfns[i] & MIGRATE_PFN_COMPOUND)) {
@@ -1076,12 +1106,17 @@ 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;
 	}
-- 
2.49.0