During a pagecache folio split, an xarray node allocation can happen and
needs to charge at folio's memcg instead of folio split invoker's memcg,
because for example folio split can happen during reclaim and reclaim's
active memcg might not be folio's memcg. Switch to folio's memcg at the
beginning and switch back afterwards.

Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
Fixes: 6b24ca4a1a8d4 ("mm: Use multi-index entries in the page cache")
Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 mm/huge_memory.c | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 04e8a6b553435..b9c2d8908e564 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -4063,34 +4063,42 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 	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 nr_shmem_dropped = 0;
 	enum ttu_flags ttu_flags = 0;
-	int ret;
 	pgoff_t end = 0;
+	int ret;
 
 	VM_WARN_ON_ONCE_FOLIO(!folio_test_locked(folio), folio);
 	VM_WARN_ON_ONCE_FOLIO(!folio_test_large(folio), folio);
 
 	if (folio != page_folio(split_at) || folio != page_folio(lock_at)) {
 		ret = -EINVAL;
-		goto out;
+		goto out_no_memcg;
 	}
 
 	if (new_order >= old_order) {
 		ret = -EINVAL;
-		goto out;
+		goto out_no_memcg;
 	}
 
 	ret = folio_check_splittable(folio, new_order, split_type);
 	if (ret) {
 		VM_WARN_ONCE(ret == -EINVAL, "Tried to split an unsplittable folio");
-		goto out;
+		goto out_no_memcg;
 	}
 
+	/*
+	 * switch to folio's memcg as xarray node allocation can happen and
+	 * needs to charge to it.
+	 */
+	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
@@ -4231,6 +4239,10 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 	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);

-- 
2.53.0

XArray operations that allocate xa_nodes, such as xas_nomem() and
xas_alloc(), add __GFP_ACCOUNT when the array has XA_FLAGS_ACCOUNT set.
This charges the allocated memory and avoids the workingset convergence
issue described by commit 7b785645e8f13 ("mm: fix page cache convergence
regression").

xas_split_alloc() does not have that flag. Add it when necessary.

Fixes: 6b24ca4a1a8d4 ("mm: Use multi-index entries in the page cache")
Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 lib/xarray.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/lib/xarray.c b/lib/xarray.c
index 9a8b4916540cf..bfe7bef80f34e 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -1053,6 +1053,9 @@ void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order,
 	if (xas->xa_shift + XA_CHUNK_SHIFT > order)
 		return;
 
+	if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT)
+		gfp |= __GFP_ACCOUNT;
+
 	do {
 		struct xa_node *node;
 

-- 
2.53.0