[PATCH v2 09/17] mm/huge_memory: move anon_vma and filemap management into split helpers

[Kairui Song via B4 Relay]

From: Kairui Song <kasong@xxxxxxxxxxx>

Only anon split needs vma info, and only file split needs the filemap
handling. Move the related code into separate helpers so they are
genuinely more self-contained.

Reviewed-by: Zi Yan <ziy@xxxxxxxxxx>
Signed-off-by: Kairui Song <kasong@xxxxxxxxxxx>
---
 mm/huge_memory.c | 177 +++++++++++++++++++++++++------------------------------
 1 file changed, 79 insertions(+), 98 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index aa10a13bc255..1a3ca2606c60 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3950,12 +3950,33 @@ static int __folio_split_unmap_and_freeze_anon(struct folio *folio, unsigned int
 	struct swap_cluster_info *ci = NULL;
 	struct folio *new_folio, *next;
 	int old_order = folio_order(folio);
+	struct anon_vma *anon_vma = NULL;
 	enum ttu_flags ttu_flags = 0;
 	struct list_lru_one *lru;
 	struct lruvec *lruvec;
 	bool dequeue_deferred;
 	int ret = 0;
 
+	/*
+	 * Unmap/remap needs the anon_vma. The caller does not necessarily
+	 * hold an mmap_lock that would prevent the anon_vma from
+	 * disappearing, so we first take a reference and lock it. This is
+	 * similar to folio_lock_anon_vma_read() except the write lock is
+	 * taken to serialize against parallel split or collapse.
+	 */
+	if (unmap) {
+		anon_vma = folio_get_anon_vma(folio);
+		if (!anon_vma)
+			return -EBUSY;
+		anon_vma_lock_write(anon_vma);
+	}
+
+	/* Racy check if we can split the page, before the optional unmap. */
+	if (folio_expected_ref_count(folio) != folio_ref_count(folio) - 1) {
+		ret = -EAGAIN;
+		goto out_unlock;
+	}
+
 	if (unmap)
 		unmap_folio(folio);
 
@@ -4039,21 +4060,58 @@ static int __folio_split_unmap_and_freeze_anon(struct folio *folio, unsigned int
 			ttu_flags = TTU_USE_SHARED_ZEROPAGE;
 		remap_page(folio, 1 << old_order, ttu_flags);
 	}
+out_unlock:
+	if (anon_vma) {
+		anon_vma_unlock_write(anon_vma);
+		put_anon_vma(anon_vma);
+	}
 
 	return ret;
 }
 
 static int __folio_split_unmap_and_freeze_file(struct folio *folio, unsigned int new_order,
-					       struct page *split_at, struct xa_state *xas,
-					       struct address_space *mapping, bool do_lru,
+					       struct page *split_at, bool do_lru,
 					       struct list_head *list, enum split_type split_type)
 {
+	struct address_space *mapping = folio->mapping;
+	XA_STATE(xas, &mapping->i_pages, folio->index);
 	struct folio *end_folio = folio_next(folio);
 	struct folio *new_folio, *next;
 	int nr_shmem_dropped = 0;
+	unsigned int min_order;
 	struct lruvec *lruvec;
 	pgoff_t end = 0;
-	int ret;
+	gfp_t gfp;
+	int ret = 0;
+
+	min_order = mapping_min_folio_order(mapping);
+	if (new_order < min_order)
+		return -EINVAL;
+
+	gfp = current_gfp_context(mapping_gfp_mask(mapping) & GFP_RECLAIM_MASK);
+	if (!filemap_release_folio(folio, gfp))
+		return -EBUSY;
+
+	mapping_set_update(&xas, mapping);
+
+	if (split_type == SPLIT_TYPE_UNIFORM) {
+		int old_order = folio_order(folio);
+
+		xas_set_order(&xas, folio->index, new_order);
+		xas_split_alloc(&xas, folio, old_order, gfp);
+		if (xas_error(&xas)) {
+			ret = xas_error(&xas);
+			goto fail_free;
+		}
+	}
+
+	i_mmap_lock_read(mapping);
+
+	/* Racy check if we can split the page, before unmap_folio() */
+	if (folio_expected_ref_count(folio) != folio_ref_count(folio) - 1) {
+		ret = -EAGAIN;
+		goto fail_mmap_unlock;
+	}
 
 	/*
 	 * __split_frozen_folio() may need to trim off pages beyond
@@ -4068,13 +4126,13 @@ static int __folio_split_unmap_and_freeze_file(struct folio *folio, unsigned int
 
 	unmap_folio(folio);
 
-	xas_lock_irq(xas);
+	xas_lock_irq(&xas);
 
 	/*
 	 * Check if the folio is present in page cache.
 	 * We assume all tail are present too, if folio is there.
 	 */
-	if (xas_load(xas) != folio) {
+	if (xas_load(&xas) != folio) {
 		ret = -EAGAIN;
 		goto fail;
 	}
@@ -4101,7 +4159,7 @@ static int __folio_split_unmap_and_freeze_file(struct folio *folio, unsigned int
 	if (do_lru)
 		lruvec = folio_lruvec_lock(folio);
 
-	ret = __split_frozen_folio(folio, new_order, split_at, xas,
+	ret = __split_frozen_folio(folio, new_order, split_at, &xas,
 				   mapping, split_type);
 
 	/*
@@ -4153,9 +4211,19 @@ static int __folio_split_unmap_and_freeze_file(struct folio *folio, unsigned int
 	 * If we want to use try_to_migrate() on file in unmap_folio,
 	 * remember to add remap_page() and adapt it.
 	 */
-	xas_unlock_irq(xas);
+	xas_unlock_irq(&xas);
+fail_mmap_unlock:
 	if (nr_shmem_dropped)
 		shmem_uncharge(mapping->host, nr_shmem_dropped);
+	/*
+	 * Drop the mapping while the inode is still pinned. @folio stays
+	 * locked and present in the page cache, so eviction cannot free
+	 * the inode yet, nothing past this point may touch the inode or
+	 * the mapping.
+	 */
+	i_mmap_unlock_read(mapping);
+fail_free:
+	xas_destroy(&xas);
 	return ret;
 }
 
@@ -4184,12 +4252,9 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 		struct page *split_at, struct page *lock_at,
 		struct list_head *list, enum split_type split_type)
 {
-	XA_STATE(xas, &folio->mapping->i_pages, folio->index);
 	struct folio *end_folio = folio_next(folio);
 	bool is_anon = folio_test_anon(folio);
 	struct mem_cgroup *memcg, *old_memcg;
-	struct address_space *mapping = NULL;
-	struct anon_vma *anon_vma = NULL;
 	int old_order = folio_order(folio);
 	struct folio *new_folio, *next;
 	int ret;
@@ -4220,84 +4285,12 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 	memcg = get_mem_cgroup_from_folio(folio);
 	old_memcg = set_active_memcg(memcg);
 
-	if (is_anon) {
-		/*
-		 * The caller does not necessarily hold an mmap_lock that would
-		 * prevent the anon_vma disappearing so we first we take a
-		 * reference to it and then lock the anon_vma for write. This
-		 * is similar to folio_lock_anon_vma_read except the write lock
-		 * is taken to serialise against parallel split or collapse
-		 * operations.
-		 */
-		anon_vma = folio_get_anon_vma(folio);
-		if (!anon_vma) {
-			ret = -EBUSY;
-			goto out;
-		}
-		anon_vma_lock_write(anon_vma);
-		mapping = NULL;
-	} else {
-		unsigned int min_order;
-		gfp_t gfp;
-
-		mapping = folio->mapping;
-		min_order = mapping_min_folio_order(mapping);
-		if (new_order < min_order) {
-			ret = -EINVAL;
-			goto out;
-		}
-
-		gfp = current_gfp_context(mapping_gfp_mask(mapping) &
-							GFP_RECLAIM_MASK);
-
-		if (!filemap_release_folio(folio, gfp)) {
-			ret = -EBUSY;
-			goto out;
-		}
-
-		mapping_set_update(&xas, mapping);
-
-		if (split_type == SPLIT_TYPE_UNIFORM) {
-			xas_set_order(&xas, folio->index, new_order);
-			xas_split_alloc(&xas, folio, old_order, gfp);
-			if (xas_error(&xas)) {
-				ret = xas_error(&xas);
-				goto out;
-			}
-		}
-
-		anon_vma = NULL;
-		i_mmap_lock_read(mapping);
-	}
-
-	/*
-	 * Racy check if we can split the page, before unmap_folio() will
-	 * split PMDs
-	 */
-	if (folio_expected_ref_count(folio) != folio_ref_count(folio) - 1) {
-		ret = -EAGAIN;
-		goto out_unlock;
-	}
-
-	if (!is_anon) {
-		ret = __folio_split_unmap_and_freeze_file(folio, new_order, split_at, &xas, mapping,
-							  true, list, split_type);
-	} else {
+	if (is_anon)
 		ret = __folio_split_unmap_and_freeze_anon(folio, new_order, split_at, true,
 							  true, list, split_type);
-	}
-
-	/*
-	 * Drop the mapping while the inode is still pinned. @folio stays
-	 * locked and present in the page cache until the loop below, so
-	 * eviction cannot free the inode yet; @lock_at is not enough, it may
-	 * be a tail beyond EOF that the split already dropped from the page
-	 * cache. Nothing past this point may touch the inode or the mapping.
-	 */
-	if (mapping) {
-		i_mmap_unlock_read(mapping);
-		mapping = NULL;
-	}
+	else
+		ret = __folio_split_unmap_and_freeze_file(folio, new_order, split_at,
+							  true, list, split_type);
 
 	/*
 	 * Unlock all after-split folios except the one containing
@@ -4318,19 +4311,10 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 		free_folio_and_swap_cache(new_folio);
 	}
 
-out_unlock:
-	if (anon_vma) {
-		anon_vma_unlock_write(anon_vma);
-		put_anon_vma(anon_vma);
-	}
-	if (mapping)
-		i_mmap_unlock_read(mapping);
-out:
 	/* restore to caller's old_memcg */
 	set_active_memcg(old_memcg);
 	mem_cgroup_put(memcg);
 out_no_memcg:
-	xas_destroy(&xas);
 	if (is_pmd_order(old_order))
 		count_vm_event(!ret ? THP_SPLIT_PAGE : THP_SPLIT_PAGE_FAILED);
 	count_mthp_stat(old_order, !ret ? MTHP_STAT_SPLIT : MTHP_STAT_SPLIT_FAILED);
@@ -4366,9 +4350,6 @@ int folio_split_unmapped(struct folio *folio, unsigned int new_order)
 	VM_WARN_ON_ONCE_FOLIO(!folio_test_large(folio), folio);
 	VM_WARN_ON_ONCE_FOLIO(!folio_test_anon(folio), folio);
 
-	if (folio_expected_ref_count(folio) != folio_ref_count(folio) - 1)
-		return -EAGAIN;
-
 	return __folio_split_unmap_and_freeze_anon(folio, new_order, &folio->page, false,
 						   false, NULL, SPLIT_TYPE_UNIFORM);
 }

-- 
2.55.0