mm: thp: split huge page to any lower order pages

To split a THP to any lower order pages, we need to reform THPs on
subpages at given order and add page refcount based on the new page order.
Also we need to reinitialize page_deferred_list after removing the page
from the split_queue, otherwise a subsequent split will see list
corruption when checking the page_deferred_list again.

Note: Anonymous order-1 folio is not supported because _deferred_list,
which is used by partially mapped folios, is stored in subpage 2 and an
order-1 folio only has subpage 0 and 1.  File-backed order-1 folios are
fine, since they do not use _deferred_list.

[ziy@nvidia.com: fixup per discussion with Ryan]
  Link: https://lkml.kernel.org/r/494F48CD-1F0F-4CAD-884E-6D48F40AF990@nvidia.com
Link: https://lkml.kernel.org/r/20240226205534.1603748-8-zi.yan@sent.com
Signed-off-by: Zi Yan <ziy@nvidia.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michal Koutny <mkoutny@suse.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Zach O'Keefe <zokeefe@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 83 insertions, 24 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index b2df788c11fa..006b192ea6ab 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2770,7 +2770,6 @@ static void lru_add_page_tail(struct page *head, struct page *tail,
 		struct lruvec *lruvec, struct list_head *list)
 {
 	VM_BUG_ON_PAGE(!PageHead(head), head);
-	VM_BUG_ON_PAGE(PageCompound(tail), head);
 	VM_BUG_ON_PAGE(PageLRU(tail), head);
 	lockdep_assert_held(&lruvec->lru_lock);
 
@@ -2791,7 +2790,8 @@ static void lru_add_page_tail(struct page *head, struct page *tail,
 }
 
 static void __split_huge_page_tail(struct folio *folio, int tail,
-		struct lruvec *lruvec, struct list_head *list)
+		struct lruvec *lruvec, struct list_head *list,
+		unsigned int new_order)
 {
 	struct page *head = &folio->page;
 	struct page *page_tail = head + tail;
@@ -2861,10 +2861,15 @@ static void __split_huge_page_tail(struct folio *folio, int tail,
 	 * which needs correct compound_head().
 	 */
 	clear_compound_head(page_tail);
+	if (new_order) {
+		prep_compound_page(page_tail, new_order);
+		folio_prep_large_rmappable(new_folio);
+	}
 
 	/* Finally unfreeze refcount. Additional reference from page cache. */
-	page_ref_unfreeze(page_tail, 1 + (!folio_test_anon(folio) ||
-					  folio_test_swapcache(folio)));
+	page_ref_unfreeze(page_tail,
+		1 + ((!folio_test_anon(folio) || folio_test_swapcache(folio)) ?
+			     folio_nr_pages(new_folio) : 0));
 
 	if (folio_test_young(folio))
 		folio_set_young(new_folio);
@@ -2882,7 +2887,7 @@ static void __split_huge_page_tail(struct folio *folio, int tail,
 }
 
 static void __split_huge_page(struct page *page, struct list_head *list,
-		pgoff_t end)
+		pgoff_t end, unsigned int new_order)
 {
 	struct folio *folio = page_folio(page);
 	struct page *head = &folio->page;
@@ -2890,11 +2895,12 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 	struct address_space *swap_cache = NULL;
 	unsigned long offset = 0;
 	int i, nr_dropped = 0;
+	unsigned int new_nr = 1 << new_order;
 	int order = folio_order(folio);
 	unsigned int nr = 1 << order;
 
 	/* complete memcg works before add pages to LRU */
-	split_page_memcg(head, order, 0);
+	split_page_memcg(head, order, new_order);
 
 	if (folio_test_anon(folio) && folio_test_swapcache(folio)) {
 		offset = swp_offset(folio->swap);
@@ -2907,8 +2913,8 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 
 	ClearPageHasHWPoisoned(head);
 
-	for (i = nr - 1; i >= 1; i--) {
-		__split_huge_page_tail(folio, i, lruvec, list);
+	for (i = nr - new_nr; i >= new_nr; i -= new_nr) {
+		__split_huge_page_tail(folio, i, lruvec, list, new_order);
 		/* Some pages can be beyond EOF: drop them from page cache */
 		if (head[i].index >= end) {
 			struct folio *tail = page_folio(head + i);
@@ -2929,24 +2935,30 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 		}
 	}
 
-	ClearPageCompound(head);
+	if (!new_order)
+		ClearPageCompound(head);
+	else {
+		struct folio *new_folio = (struct folio *)head;
+
+		folio_set_order(new_folio, new_order);
+	}
 	unlock_page_lruvec(lruvec);
 	/* Caller disabled irqs, so they are still disabled here */
 
-	split_page_owner(head, order, 0);
+	split_page_owner(head, order, new_order);
 
 	/* See comment in __split_huge_page_tail() */
 	if (PageAnon(head)) {
 		/* Additional pin to swap cache */
 		if (PageSwapCache(head)) {
-			page_ref_add(head, 2);
+			page_ref_add(head, 1 + new_nr);
 			xa_unlock(&swap_cache->i_pages);
 		} else {
 			page_ref_inc(head);
 		}
 	} else {
 		/* Additional pin to page cache */
-		page_ref_add(head, 2);
+		page_ref_add(head, 1 + new_nr);
 		xa_unlock(&head->mapping->i_pages);
 	}
 	local_irq_enable();
@@ -2958,7 +2970,15 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 	if (folio_test_swapcache(folio))
 		split_swap_cluster(folio->swap);
 
-	for (i = 0; i < nr; i++) {
+	/*
+	 * set page to its compound_head when split to non order-0 pages, so
+	 * we can skip unlocking it below, since PG_locked is transferred to
+	 * the compound_head of the page and the caller will unlock it.
+	 */
+	if (new_order)
+		page = compound_head(page);
+
+	for (i = 0; i < nr; i += new_nr) {
 		struct page *subpage = head + i;
 		if (subpage == page)
 			continue;
@@ -2992,29 +3012,36 @@ bool can_split_folio(struct folio *folio, int *pextra_pins)
 }
 
 /*
- * This function splits huge page into normal pages. @page can point to any
- * subpage of huge page to split. Split doesn't change the position of @page.
+ * This function splits huge page into pages in @new_order. @page can point to
+ * any subpage of huge page to split. Split doesn't change the position of
+ * @page.
+ *
+ * NOTE: order-1 anonymous folio is not supported because _deferred_list,
+ * which is used by partially mapped folios, is stored in subpage 2 and an
+ * order-1 folio only has subpage 0 and 1. File-backed order-1 folios are OK,
+ * since they do not use _deferred_list.
  *
  * Only caller must hold pin on the @page, otherwise split fails with -EBUSY.
  * The huge page must be locked.
  *
  * If @list is null, tail pages will be added to LRU list, otherwise, to @list.
  *
- * Both head page and tail pages will inherit mapping, flags, and so on from
- * the hugepage.
+ * Pages in new_order will inherit mapping, flags, and so on from the hugepage.
  *
- * GUP pin and PG_locked transferred to @page. Rest subpages can be freed if
- * they are not mapped.
+ * GUP pin and PG_locked transferred to @page or the compound page @page belongs
+ * to. Rest subpages can be freed if they are not mapped.
  *
  * Returns 0 if the hugepage is split successfully.
  * Returns -EBUSY if the page is pinned or if anon_vma disappeared from under
  * us.
  */
-int split_huge_page_to_list(struct page *page, struct list_head *list)
+int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
+				     unsigned int new_order)
 {
 	struct folio *folio = page_folio(page);
 	struct deferred_split *ds_queue = get_deferred_split_queue(folio);
-	XA_STATE(xas, &folio->mapping->i_pages, folio->index);
+	/* reset xarray order to new order after split */
+	XA_STATE_ORDER(xas, &folio->mapping->i_pages, folio->index, new_order);
 	struct anon_vma *anon_vma = NULL;
 	struct address_space *mapping = NULL;
 	int extra_pins, ret;
@@ -3024,6 +3051,31 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
 	VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);
 
+	/* Cannot split anonymous THP to order-1 */
+	if (new_order == 1 && folio_test_anon(folio)) {
+		VM_WARN_ONCE(1, "Cannot split to order-1 folio");
+		return -EINVAL;
+	}
+
+	if (new_order) {
+		/* Only swapping a whole PMD-mapped folio is supported */
+		if (folio_test_swapcache(folio))
+			return -EINVAL;
+		/* Split shmem folio to non-zero order not supported */
+		if (shmem_mapping(folio->mapping)) {
+			VM_WARN_ONCE(1,
+				"Cannot split shmem folio to non-0 order");
+			return -EINVAL;
+		}
+		/* No split if the file system does not support large folio */
+		if (!mapping_large_folio_support(folio->mapping)) {
+			VM_WARN_ONCE(1,
+				"Cannot split file folio to non-0 order");
+			return -EINVAL;
+		}
+	}
+
+
 	is_hzp = is_huge_zero_page(&folio->page);
 	if (is_hzp) {
 		pr_warn_ratelimited("Called split_huge_page for huge zero page\n");
@@ -3120,14 +3172,21 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		if (folio_order(folio) > 1 &&
 		    !list_empty(&folio->_deferred_list)) {
 			ds_queue->split_queue_len--;
-			list_del(&folio->_deferred_list);
+			/*
+			 * Reinitialize page_deferred_list after removing the
+			 * page from the split_queue, otherwise a subsequent
+			 * split will see list corruption when checking the
+			 * page_deferred_list.
+			 */
+			list_del_init(&folio->_deferred_list);
 		}
 		spin_unlock(&ds_queue->split_queue_lock);
 		if (mapping) {
 			int nr = folio_nr_pages(folio);
 
 			xas_split(&xas, folio, folio_order(folio));
-			if (folio_test_pmd_mappable(folio)) {
+			if (folio_test_pmd_mappable(folio) &&
+			    new_order < HPAGE_PMD_ORDER) {
 				if (folio_test_swapbacked(folio)) {
 					__lruvec_stat_mod_folio(folio,
 							NR_SHMEM_THPS, -nr);
@@ -3139,7 +3198,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 			}
 		}
 
-		__split_huge_page(page, list, end);
+		__split_huge_page(page, list, end, new_order);
 		ret = 0;
 	} else {
 		spin_unlock(&ds_queue->split_queue_lock);