mm/memcontrol.c

@@ -1921,9 +1921,18 @@ void drain_all_stock(struct mem_cgroup *root_memcg)
 static int memcg_hotplug_cpu_dead(unsigned int cpu)
 {
 	struct memcg_stock_pcp *stock;
+	struct obj_cgroup *old;
+	unsigned long flags;
 
 	stock = &per_cpu(memcg_stock, cpu);
+
+	/* drain_obj_stock requires stock_lock */
+	local_lock_irqsave(&memcg_stock.stock_lock, flags);
+	old = drain_obj_stock(stock);
+	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+
 	drain_stock(stock);
+	obj_cgroup_put(old);
 
 	return 0;
 }
@@ -4993,7 +5002,7 @@ void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry)
 		mem_cgroup_id_get_many(swap_memcg, nr_entries - 1);
 	mod_memcg_state(swap_memcg, MEMCG_SWAP, nr_entries);
 
-	swap_cgroup_record(folio, entry);
+	swap_cgroup_record(folio, mem_cgroup_id(swap_memcg), entry);
 
 	folio_unqueue_deferred_split(folio);
 	folio->memcg_data = 0;
@@ -5055,7 +5064,7 @@ int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry)
 		mem_cgroup_id_get_many(memcg, nr_pages - 1);
 	mod_memcg_state(memcg, MEMCG_SWAP, nr_pages);
 
-	swap_cgroup_record(folio, entry);
+	swap_cgroup_record(folio, mem_cgroup_id(memcg), entry);
 
 	return 0;
 }

mm/migrate.c

@@ -518,15 +518,13 @@ static int __folio_migrate_mapping(struct address_space *mapping,
 	if (folio_test_anon(folio) && folio_test_large(folio))
 		mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON, 1);
 	folio_ref_add(newfolio, nr); /* add cache reference */
-	if (folio_test_swapbacked(folio)) {
+	if (folio_test_swapbacked(folio))
 		__folio_set_swapbacked(newfolio);
-		if (folio_test_swapcache(folio)) {
-			folio_set_swapcache(newfolio);
-			newfolio->private = folio_get_private(folio);
-		}
+	if (folio_test_swapcache(folio)) {
+		folio_set_swapcache(newfolio);
+		newfolio->private = folio_get_private(folio);
 		entries = nr;
 	} else {
-		VM_BUG_ON_FOLIO(folio_test_swapcache(folio), folio);
 		entries = 1;
 	}
 

mm/page_alloc.c

@@ -7004,7 +7004,7 @@ static inline bool has_unaccepted_memory(void)
 
 static bool cond_accept_memory(struct zone *zone, unsigned int order)
 {
-	long to_accept;
+	long to_accept, wmark;
 	bool ret = false;
 
 	if (!has_unaccepted_memory())
@@ -7013,8 +7013,18 @@ static bool cond_accept_memory(struct zone *zone, unsigned int order)
 	if (list_empty(&zone->unaccepted_pages))
 		return false;
 
+	wmark = promo_wmark_pages(zone);
+
+	/*
+	 * Watermarks have not been initialized yet.
+	 *
+	 * Accepting one MAX_ORDER page to ensure progress.
+	 */
+	if (!wmark)
+		return try_to_accept_memory_one(zone);
+
 	/* How much to accept to get to promo watermark? */
-	to_accept = promo_wmark_pages(zone) -
+	to_accept = wmark -
 		    (zone_page_state(zone, NR_FREE_PAGES) -
 		    __zone_watermark_unusable_free(zone, order, 0) -
 		    zone_page_state(zone, NR_UNACCEPTED));

mm/swap_cgroup.c

@@ -58,9 +58,11 @@ static unsigned short __swap_cgroup_id_xchg(struct swap_cgroup *map,
  * entries must not have been charged
  *
  * @folio: the folio that the swap entry belongs to
+ * @id: mem_cgroup ID to be recorded
  * @ent: the first swap entry to be recorded
  */
-void swap_cgroup_record(struct folio *folio, swp_entry_t ent)
+void swap_cgroup_record(struct folio *folio, unsigned short id,
+			swp_entry_t ent)
 {
 	unsigned int nr_ents = folio_nr_pages(folio);
 	struct swap_cgroup *map;
@@ -72,8 +74,7 @@ void swap_cgroup_record(struct folio *folio, swp_entry_t ent)
 	map = swap_cgroup_ctrl[swp_type(ent)].map;
 
 	do {
-		old = __swap_cgroup_id_xchg(map, offset,
-					    mem_cgroup_id(folio_memcg(folio)));
+		old = __swap_cgroup_id_xchg(map, offset, id);
 		VM_BUG_ON(old);
 	} while (++offset != end);
 }

mm/vma.c

@@ -2381,7 +2381,8 @@ static int __mmap_new_vma(struct mmap_state *map, struct vm_area_struct **vmap)
 	 * vma_merge_new_range() calls khugepaged_enter_vma() too, the below
 	 * call covers the non-merge case.
 	 */
-	khugepaged_enter_vma(vma, map->flags);
+	if (!vma_is_anonymous(vma))
+		khugepaged_enter_vma(vma, map->flags);
 	ksm_add_vma(vma);
 	*vmap = vma;
 	return 0;

tools/testing/selftests/mm/run_vmtests.sh

@@ -304,7 +304,9 @@ uffd_stress_bin=./uffd-stress
 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} anon 20 16
 # Hugetlb tests require source and destination huge pages. Pass in half
 # the size of the free pages we have, which is used for *each*.
-half_ufd_size_MB=$((freepgs / 2))
+# uffd-stress expects a region expressed in MiB, so we adjust
+# half_ufd_size_MB accordingly.
+half_ufd_size_MB=$(((freepgs * hpgsize_KB) / 1024 / 2))
 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb "$half_ufd_size_MB" 32
 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb-private "$half_ufd_size_MB" 32
 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} shmem 20 16