1 files changed, 393 insertions, 118 deletions

diff --git a/mm/page_owner.c b/mm/page_owner.c
index 2d27f532df4c..a70245684206 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -32,6 +32,26 @@ struct page_owner {
 	char comm[TASK_COMM_LEN];
 	pid_t pid;
 	pid_t tgid;
+	pid_t free_pid;
+	pid_t free_tgid;
+};
+
+struct stack {
+	struct stack_record *stack_record;
+	struct stack *next;
+};
+static struct stack dummy_stack;
+static struct stack failure_stack;
+static struct stack *stack_list;
+static DEFINE_SPINLOCK(stack_list_lock);
+
+#define STACK_PRINT_FLAG_STACK		0x1
+#define STACK_PRINT_FLAG_PAGES		0x2
+#define STACK_PRINT_FLAG_HANDLE		0x4
+
+struct stack_print_ctx {
+	struct stack *stack;
+	u8 flags;
 };
 
 static bool page_owner_enabled __initdata;
@@ -43,12 +63,28 @@ static depot_stack_handle_t early_handle;
 
 static void init_early_allocated_pages(void);
 
+static inline void set_current_in_page_owner(void)
+{
+	/*
+	 * Avoid recursion.
+	 *
+	 * We might need to allocate more memory from page_owner code, so make
+	 * sure to signal it in order to avoid recursion.
+	 */
+	current->in_page_owner = 1;
+}
+
+static inline void unset_current_in_page_owner(void)
+{
+	current->in_page_owner = 0;
+}
+
 static int __init early_page_owner_param(char *buf)
 {
 	int ret = kstrtobool(buf, &page_owner_enabled);
 
 	if (page_owner_enabled)
-		stack_depot_want_early_init();
+		stack_depot_request_early_init();
 
 	return ret;
 }
@@ -91,19 +127,29 @@ static __init void init_page_owner(void)
 	register_dummy_stack();
 	register_failure_stack();
 	register_early_stack();
-	static_branch_enable(&page_owner_inited);
 	init_early_allocated_pages();
+	/* Initialize dummy and failure stacks and link them to stack_list */
+	dummy_stack.stack_record = __stack_depot_get_stack_record(dummy_handle);
+	failure_stack.stack_record = __stack_depot_get_stack_record(failure_handle);
+	if (dummy_stack.stack_record)
+		refcount_set(&dummy_stack.stack_record->count, 1);
+	if (failure_stack.stack_record)
+		refcount_set(&failure_stack.stack_record->count, 1);
+	dummy_stack.next = &failure_stack;
+	stack_list = &dummy_stack;
+	static_branch_enable(&page_owner_inited);
 }
 
 struct page_ext_operations page_owner_ops = {
 	.size = sizeof(struct page_owner),
 	.need = need_page_owner,
 	.init = init_page_owner,
+	.need_shared_flags = true,
 };
 
 static inline struct page_owner *get_page_owner(struct page_ext *page_ext)
 {
-	return (void *)page_ext + page_owner_ops.offset;
+	return page_ext_data(page_ext, &page_owner_ops);
 }
 
 static noinline depot_stack_handle_t save_stack(gfp_t flags)
@@ -112,93 +158,196 @@ static noinline depot_stack_handle_t save_stack(gfp_t flags)
 	depot_stack_handle_t handle;
 	unsigned int nr_entries;
 
-	/*
-	 * Avoid recursion.
-	 *
-	 * Sometimes page metadata allocation tracking requires more
-	 * memory to be allocated:
-	 * - when new stack trace is saved to stack depot
-	 * - when backtrace itself is calculated (ia64)
-	 */
 	if (current->in_page_owner)
 		return dummy_handle;
-	current->in_page_owner = 1;
 
+	set_current_in_page_owner();
 	nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 2);
 	handle = stack_depot_save(entries, nr_entries, flags);
 	if (!handle)
 		handle = failure_handle;
+	unset_current_in_page_owner();
 
-	current->in_page_owner = 0;
 	return handle;
 }
 
-void __reset_page_owner(struct page *page, unsigned short order)
+static void add_stack_record_to_list(struct stack_record *stack_record,
+				     gfp_t gfp_mask)
 {
-	int i;
-	struct page_ext *page_ext;
-	depot_stack_handle_t handle;
-	struct page_owner *page_owner;
-	u64 free_ts_nsec = local_clock();
+	unsigned long flags;
+	struct stack *stack;
 
-	page_ext = page_ext_get(page);
-	if (unlikely(!page_ext))
+	if (!gfpflags_allow_spinning(gfp_mask))
 		return;
 
-	handle = save_stack(GFP_NOWAIT | __GFP_NOWARN);
-	for (i = 0; i < (1 << order); i++) {
-		__clear_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags);
-		page_owner = get_page_owner(page_ext);
-		page_owner->free_handle = handle;
-		page_owner->free_ts_nsec = free_ts_nsec;
-		page_ext = page_ext_next(page_ext);
+	set_current_in_page_owner();
+	stack = kmalloc(sizeof(*stack), gfp_nested_mask(gfp_mask));
+	if (!stack) {
+		unset_current_in_page_owner();
+		return;
 	}
-	page_ext_put(page_ext);
+	unset_current_in_page_owner();
+
+	stack->stack_record = stack_record;
+	stack->next = NULL;
+
+	spin_lock_irqsave(&stack_list_lock, flags);
+	stack->next = stack_list;
+	/*
+	 * This pairs with smp_load_acquire() from function
+	 * stack_start(). This guarantees that stack_start()
+	 * will see an updated stack_list before starting to
+	 * traverse the list.
+	 */
+	smp_store_release(&stack_list, stack);
+	spin_unlock_irqrestore(&stack_list_lock, flags);
 }
 
-static inline void __set_page_owner_handle(struct page_ext *page_ext,
-					depot_stack_handle_t handle,
-					unsigned short order, gfp_t gfp_mask)
+static void inc_stack_record_count(depot_stack_handle_t handle, gfp_t gfp_mask,
+				   int nr_base_pages)
 {
+	struct stack_record *stack_record = __stack_depot_get_stack_record(handle);
+
+	if (!stack_record)
+		return;
+
+	/*
+	 * New stack_record's that do not use STACK_DEPOT_FLAG_GET start
+	 * with REFCOUNT_SATURATED to catch spurious increments of their
+	 * refcount.
+	 * Since we do not use STACK_DEPOT_FLAG_GET API, let us
+	 * set a refcount of 1 ourselves.
+	 */
+	if (refcount_read(&stack_record->count) == REFCOUNT_SATURATED) {
+		int old = REFCOUNT_SATURATED;
+
+		if (atomic_try_cmpxchg_relaxed(&stack_record->count.refs, &old, 1))
+			/* Add the new stack_record to our list */
+			add_stack_record_to_list(stack_record, gfp_mask);
+	}
+	refcount_add(nr_base_pages, &stack_record->count);
+}
+
+static void dec_stack_record_count(depot_stack_handle_t handle,
+				   int nr_base_pages)
+{
+	struct stack_record *stack_record = __stack_depot_get_stack_record(handle);
+
+	if (!stack_record)
+		return;
+
+	if (refcount_sub_and_test(nr_base_pages, &stack_record->count))
+		pr_warn("%s: refcount went to 0 for %u handle\n", __func__,
+			handle);
+}
+
+static inline void __update_page_owner_handle(struct page *page,
+					      depot_stack_handle_t handle,
+					      unsigned short order,
+					      gfp_t gfp_mask,
+					      short last_migrate_reason, u64 ts_nsec,
+					      pid_t pid, pid_t tgid, char *comm)
+{
+	struct page_ext_iter iter;
+	struct page_ext *page_ext;
 	struct page_owner *page_owner;
-	int i;
 
-	for (i = 0; i < (1 << order); i++) {
+	rcu_read_lock();
+	for_each_page_ext(page, 1 << order, page_ext, iter) {
 		page_owner = get_page_owner(page_ext);
 		page_owner->handle = handle;
 		page_owner->order = order;
 		page_owner->gfp_mask = gfp_mask;
-		page_owner->last_migrate_reason = -1;
-		page_owner->pid = current->pid;
-		page_owner->tgid = current->tgid;
-		page_owner->ts_nsec = local_clock();
-		strscpy(page_owner->comm, current->comm,
+		page_owner->last_migrate_reason = last_migrate_reason;
+		page_owner->pid = pid;
+		page_owner->tgid = tgid;
+		page_owner->ts_nsec = ts_nsec;
+		strscpy(page_owner->comm, comm,
 			sizeof(page_owner->comm));
 		__set_bit(PAGE_EXT_OWNER, &page_ext->flags);
 		__set_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags);
+	}
+	rcu_read_unlock();
+}
+
+static inline void __update_page_owner_free_handle(struct page *page,
+						   depot_stack_handle_t handle,
+						   unsigned short order,
+						   pid_t pid, pid_t tgid,
+						   u64 free_ts_nsec)
+{
+	struct page_ext_iter iter;
+	struct page_ext *page_ext;
+	struct page_owner *page_owner;
 
-		page_ext = page_ext_next(page_ext);
+	rcu_read_lock();
+	for_each_page_ext(page, 1 << order, page_ext, iter) {
+		page_owner = get_page_owner(page_ext);
+		/* Only __reset_page_owner() wants to clear the bit */
+		if (handle) {
+			__clear_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags);
+			page_owner->free_handle = handle;
+		}
+		page_owner->free_ts_nsec = free_ts_nsec;
+		page_owner->free_pid = current->pid;
+		page_owner->free_tgid = current->tgid;
 	}
+	rcu_read_unlock();
 }
 
-noinline void __set_page_owner(struct page *page, unsigned short order,
-					gfp_t gfp_mask)
+void __reset_page_owner(struct page *page, unsigned short order)
 {
 	struct page_ext *page_ext;
 	depot_stack_handle_t handle;
-
-	handle = save_stack(gfp_mask);
+	depot_stack_handle_t alloc_handle;
+	struct page_owner *page_owner;
+	u64 free_ts_nsec = local_clock();
 
 	page_ext = page_ext_get(page);
 	if (unlikely(!page_ext))
 		return;
-	__set_page_owner_handle(page_ext, handle, order, gfp_mask);
+
+	page_owner = get_page_owner(page_ext);
+	alloc_handle = page_owner->handle;
 	page_ext_put(page_ext);
+
+	/*
+	 * Do not specify GFP_NOWAIT to make gfpflags_allow_spinning() == false
+	 * to prevent issues in stack_depot_save().
+	 * This is similar to alloc_pages_nolock() gfp flags, but only used
+	 * to signal stack_depot to avoid spin_locks.
+	 */
+	handle = save_stack(__GFP_NOWARN);
+	__update_page_owner_free_handle(page, handle, order, current->pid,
+					current->tgid, free_ts_nsec);
+
+	if (alloc_handle != early_handle)
+		/*
+		 * early_handle is being set as a handle for all those
+		 * early allocated pages. See init_pages_in_zone().
+		 * Since their refcount is not being incremented because
+		 * the machinery is not ready yet, we cannot decrement
+		 * their refcount either.
+		 */
+		dec_stack_record_count(alloc_handle, 1 << order);
 }
 
-void __set_page_owner_migrate_reason(struct page *page, int reason)
+noinline void __set_page_owner(struct page *page, unsigned short order,
+					gfp_t gfp_mask)
 {
-	struct page_ext *page_ext = page_ext_get(page);
+	u64 ts_nsec = local_clock();
+	depot_stack_handle_t handle;
+
+	handle = save_stack(gfp_mask);
+	__update_page_owner_handle(page, handle, order, gfp_mask, -1,
+				   ts_nsec, current->pid, current->tgid,
+				   current->comm);
+	inc_stack_record_count(handle, gfp_mask, 1 << order);
+}
+
+void __folio_set_owner_migrate_reason(struct folio *folio, int reason)
+{
+	struct page_ext *page_ext = page_ext_get(&folio->page);
 	struct page_owner *page_owner;
 
 	if (unlikely(!page_ext))
@@ -209,65 +358,68 @@ void __set_page_owner_migrate_reason(struct page *page, int reason)
 	page_ext_put(page_ext);
 }
 
-void __split_page_owner(struct page *page, unsigned int nr)
+void __split_page_owner(struct page *page, int old_order, int new_order)
 {
-	int i;
-	struct page_ext *page_ext = page_ext_get(page);
+	struct page_ext_iter iter;
+	struct page_ext *page_ext;
 	struct page_owner *page_owner;
 
-	if (unlikely(!page_ext))
-		return;
-
-	for (i = 0; i < nr; i++) {
+	rcu_read_lock();
+	for_each_page_ext(page, 1 << old_order, page_ext, iter) {
 		page_owner = get_page_owner(page_ext);
-		page_owner->order = 0;
-		page_ext = page_ext_next(page_ext);
+		page_owner->order = new_order;
 	}
-	page_ext_put(page_ext);
+	rcu_read_unlock();
 }
 
 void __folio_copy_owner(struct folio *newfolio, struct folio *old)
 {
-	struct page_ext *old_ext;
-	struct page_ext *new_ext;
-	struct page_owner *old_page_owner, *new_page_owner;
+	struct page_ext *page_ext;
+	struct page_ext_iter iter;
+	struct page_owner *old_page_owner;
+	struct page_owner *new_page_owner;
+	depot_stack_handle_t migrate_handle;
 
-	old_ext = page_ext_get(&old->page);
-	if (unlikely(!old_ext))
+	page_ext = page_ext_get(&old->page);
+	if (unlikely(!page_ext))
 		return;
 
-	new_ext = page_ext_get(&newfolio->page);
-	if (unlikely(!new_ext)) {
-		page_ext_put(old_ext);
+	old_page_owner = get_page_owner(page_ext);
+	page_ext_put(page_ext);
+
+	page_ext = page_ext_get(&newfolio->page);
+	if (unlikely(!page_ext))
 		return;
-	}
 
-	old_page_owner = get_page_owner(old_ext);
-	new_page_owner = get_page_owner(new_ext);
-	new_page_owner->order = old_page_owner->order;
-	new_page_owner->gfp_mask = old_page_owner->gfp_mask;
-	new_page_owner->last_migrate_reason =
-		old_page_owner->last_migrate_reason;
-	new_page_owner->handle = old_page_owner->handle;
-	new_page_owner->pid = old_page_owner->pid;
-	new_page_owner->tgid = old_page_owner->tgid;
-	new_page_owner->ts_nsec = old_page_owner->ts_nsec;
-	new_page_owner->free_ts_nsec = old_page_owner->ts_nsec;
-	strcpy(new_page_owner->comm, old_page_owner->comm);
+	new_page_owner = get_page_owner(page_ext);
+	page_ext_put(page_ext);
 
+	migrate_handle = new_page_owner->handle;
+	__update_page_owner_handle(&newfolio->page, old_page_owner->handle,
+				   old_page_owner->order, old_page_owner->gfp_mask,
+				   old_page_owner->last_migrate_reason,
+				   old_page_owner->ts_nsec, old_page_owner->pid,
+				   old_page_owner->tgid, old_page_owner->comm);
+	/*
+	 * Do not proactively clear PAGE_EXT_OWNER{_ALLOCATED} bits as the folio
+	 * will be freed after migration. Keep them until then as they may be
+	 * useful.
+	 */
+	__update_page_owner_free_handle(&newfolio->page, 0, old_page_owner->order,
+					old_page_owner->free_pid,
+					old_page_owner->free_tgid,
+					old_page_owner->free_ts_nsec);
 	/*
-	 * We don't clear the bit on the old folio as it's going to be freed
-	 * after migration. Until then, the info can be useful in case of
-	 * a bug, and the overall stats will be off a bit only temporarily.
-	 * Also, migrate_misplaced_transhuge_page() can still fail the
-	 * migration and then we want the old folio to retain the info. But
-	 * in that case we also don't need to explicitly clear the info from
-	 * the new page, which will be freed.
+	 * We linked the original stack to the new folio, we need to do the same
+	 * for the new one and the old folio otherwise there will be an imbalance
+	 * when subtracting those pages from the stack.
 	 */
-	__set_bit(PAGE_EXT_OWNER, &new_ext->flags);
-	__set_bit(PAGE_EXT_OWNER_ALLOCATED, &new_ext->flags);
-	page_ext_put(new_ext);
-	page_ext_put(old_ext);
+	rcu_read_lock();
+	for_each_page_ext(&old->page, 1 << new_page_owner->order, page_ext, iter) {
+		old_page_owner = get_page_owner(page_ext);
+		old_page_owner->handle = migrate_handle;
+	}
+	rcu_read_unlock();
 }
 
 void pagetypeinfo_showmixedcount_print(struct seq_file *m,
@@ -313,7 +465,7 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m,
 				unsigned long freepage_order;
 
 				freepage_order = buddy_order_unsafe(page);
-				if (freepage_order < MAX_ORDER)
+				if (freepage_order <= MAX_PAGE_ORDER)
 					pfn += (1UL << freepage_order) - 1;
 				continue;
 			}
@@ -367,10 +519,10 @@ static inline int print_page_owner_memcg(char *kbuf, size_t count, int ret,
 
 	rcu_read_lock();
 	memcg_data = READ_ONCE(page->memcg_data);
-	if (!memcg_data)
+	if (!memcg_data || PageTail(page))
 		goto out_unlock;
 
-	if (memcg_data & MEMCG_DATA_OBJCGS)
+	if (memcg_data & MEMCG_DATA_OBJEXTS)
 		ret += scnprintf(kbuf + ret, count - ret,
 				"Slab cache page\n");
 
@@ -406,17 +558,17 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn,
 		return -ENOMEM;
 
 	ret = scnprintf(kbuf, count,
-			"Page allocated via order %u, mask %#x(%pGg), pid %d, tgid %d (%s), ts %llu ns, free_ts %llu ns\n",
+			"Page allocated via order %u, mask %#x(%pGg), pid %d, tgid %d (%s), ts %llu ns\n",
 			page_owner->order, page_owner->gfp_mask,
 			&page_owner->gfp_mask, page_owner->pid,
 			page_owner->tgid, page_owner->comm,
-			page_owner->ts_nsec, page_owner->free_ts_nsec);
+			page_owner->ts_nsec);
 
 	/* Print information relevant to grouping pages by mobility */
 	pageblock_mt = get_pageblock_migratetype(page);
 	page_mt  = gfp_migratetype(page_owner->gfp_mask);
 	ret += scnprintf(kbuf + ret, count - ret,
-			"PFN %lu type %s Block %lu type %s Flags %pGp\n",
+			"PFN 0x%lx type %s Block %lu type %s Flags %pGp\n",
 			pfn,
 			migratetype_names[page_mt],
 			pfn >> pageblock_order,
@@ -493,7 +645,8 @@ void __dump_page_owner(const struct page *page)
 	if (!handle) {
 		pr_alert("page_owner free stack trace missing\n");
 	} else {
-		pr_alert("page last free stack trace:\n");
+		pr_alert("page last free pid %d tgid %d stack trace:\n",
+			  page_owner->free_pid, page_owner->free_tgid);
 		stack_depot_print(handle);
 	}
 
@@ -547,7 +700,7 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 		if (PageBuddy(page)) {
 			unsigned long freepage_order = buddy_order_unsafe(page);
 
-			if (freepage_order < MAX_ORDER)
+			if (freepage_order <= MAX_PAGE_ORDER)
 				pfn += (1UL << freepage_order) - 1;
 			continue;
 		}
@@ -616,7 +769,7 @@ static loff_t lseek_page_owner(struct file *file, loff_t offset, int orig)
 	return file->f_pos;
 }
 
-static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone)
+static void init_pages_in_zone(struct zone *zone)
 {
 	unsigned long pfn = zone->zone_start_pfn;
 	unsigned long end_pfn = zone_end_pfn(zone);
@@ -655,7 +808,7 @@ static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone)
 			if (PageBuddy(page)) {
 				unsigned long order = buddy_order_unsafe(page);
 
-				if (order > 0 && order < MAX_ORDER)
+				if (order > 0 && order <= MAX_PAGE_ORDER)
 					pfn += (1UL << order) - 1;
 				continue;
 			}
@@ -672,8 +825,9 @@ static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone)
 				goto ext_put_continue;
 
 			/* Found early allocated page */
-			__set_page_owner_handle(page_ext, early_handle,
-						0, 0);
+			__update_page_owner_handle(page, early_handle, 0, 0,
+						   -1, local_clock(), current->pid,
+						   current->tgid, current->comm);
 			count++;
 ext_put_continue:
 			page_ext_put(page_ext);
@@ -682,45 +836,166 @@ ext_put_continue:
 	}
 
 	pr_info("Node %d, zone %8s: page owner found early allocated %lu pages\n",
-		pgdat->node_id, zone->name, count);
+		zone->zone_pgdat->node_id, zone->name, count);
 }
 
-static void init_zones_in_node(pg_data_t *pgdat)
+static void init_early_allocated_pages(void)
 {
 	struct zone *zone;
-	struct zone *node_zones = pgdat->node_zones;
 
-	for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) {
-		if (!populated_zone(zone))
-			continue;
+	for_each_populated_zone(zone)
+		init_pages_in_zone(zone);
+}
+
+static const struct file_operations page_owner_fops = {
+	.read		= read_page_owner,
+	.llseek		= lseek_page_owner,
+};
+
+static void *stack_start(struct seq_file *m, loff_t *ppos)
+{
+	struct stack *stack;
+	struct stack_print_ctx *ctx = m->private;
+
+	if (*ppos == -1UL)
+		return NULL;
+
+	if (!*ppos) {
+		/*
+		 * This pairs with smp_store_release() from function
+		 * add_stack_record_to_list(), so we get a consistent
+		 * value of stack_list.
+		 */
+		stack = smp_load_acquire(&stack_list);
+		ctx->stack = stack;
+	} else {
+		stack = ctx->stack;
+	}
+
+	return stack;
+}
+
+static void *stack_next(struct seq_file *m, void *v, loff_t *ppos)
+{
+	struct stack *stack = v;
+	struct stack_print_ctx *ctx = m->private;
+
+	stack = stack->next;
+	*ppos = stack ? *ppos + 1 : -1UL;
+	ctx->stack = stack;
 
-		init_pages_in_zone(pgdat, zone);
+	return stack;
+}
+
+static unsigned long page_owner_pages_threshold;
+
+static int stack_print(struct seq_file *m, void *v)
+{
+	int i, nr_base_pages;
+	struct stack *stack = v;
+	unsigned long *entries;
+	unsigned long nr_entries;
+	struct stack_record *stack_record = stack->stack_record;
+	struct stack_print_ctx *ctx = m->private;
+
+	if (!stack->stack_record)
+		return 0;
+
+	nr_base_pages = refcount_read(&stack_record->count) - 1;
+
+	if (ctx->flags & STACK_PRINT_FLAG_PAGES &&
+	    (nr_base_pages < 1 || nr_base_pages < page_owner_pages_threshold))
+		return 0;
+
+	if (ctx->flags & STACK_PRINT_FLAG_STACK) {
+		nr_entries = stack_record->size;
+		entries = stack_record->entries;
+		for (i = 0; i < nr_entries; i++)
+			seq_printf(m, " %pS\n", (void *)entries[i]);
 	}
+	if (ctx->flags & STACK_PRINT_FLAG_HANDLE)
+		seq_printf(m, "handle: %d\n", stack_record->handle.handle);
+	if (ctx->flags & STACK_PRINT_FLAG_PAGES)
+		seq_printf(m, "nr_base_pages: %d\n", nr_base_pages);
+	seq_putc(m, '\n');
+
+	return 0;
 }
 
-static void init_early_allocated_pages(void)
+static void stack_stop(struct seq_file *m, void *v)
+{
+}
+
+static const struct seq_operations page_owner_stack_op = {
+	.start	= stack_start,
+	.next	= stack_next,
+	.stop	= stack_stop,
+	.show	= stack_print
+};
+
+static int page_owner_stack_open(struct inode *inode, struct file *file)
 {
-	pg_data_t *pgdat;
+	int ret = seq_open_private(file, &page_owner_stack_op,
+				   sizeof(struct stack_print_ctx));
+
+	if (!ret) {
+		struct seq_file *m = file->private_data;
+		struct stack_print_ctx *ctx = m->private;
+
+		ctx->flags = (uintptr_t) inode->i_private;
+	}
 
-	for_each_online_pgdat(pgdat)
-		init_zones_in_node(pgdat);
+	return ret;
 }
 
-static const struct file_operations proc_page_owner_operations = {
-	.read		= read_page_owner,
-	.llseek		= lseek_page_owner,
+static const struct file_operations page_owner_stack_fops = {
+	.open		= page_owner_stack_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
 };
 
+static int page_owner_threshold_get(void *data, u64 *val)
+{
+	*val = READ_ONCE(page_owner_pages_threshold);
+	return 0;
+}
+
+static int page_owner_threshold_set(void *data, u64 val)
+{
+	WRITE_ONCE(page_owner_pages_threshold, val);
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(page_owner_threshold_fops, &page_owner_threshold_get,
+			&page_owner_threshold_set, "%llu");
+
+
 static int __init pageowner_init(void)
 {
+	struct dentry *dir;
+
 	if (!static_branch_unlikely(&page_owner_inited)) {
 		pr_info("page_owner is disabled\n");
 		return 0;
 	}
 
-	debugfs_create_file("page_owner", 0400, NULL, NULL,
-			    &proc_page_owner_operations);
-
+	debugfs_create_file("page_owner", 0400, NULL, NULL, &page_owner_fops);
+	dir = debugfs_create_dir("page_owner_stacks", NULL);
+	debugfs_create_file("show_stacks", 0400, dir,
+			    (void *)(STACK_PRINT_FLAG_STACK |
+				     STACK_PRINT_FLAG_PAGES),
+			     &page_owner_stack_fops);
+	debugfs_create_file("show_handles", 0400, dir,
+			    (void *)(STACK_PRINT_FLAG_HANDLE |
+				     STACK_PRINT_FLAG_PAGES),
+			    &page_owner_stack_fops);
+	debugfs_create_file("show_stacks_handles", 0400, dir,
+			    (void *)(STACK_PRINT_FLAG_STACK |
+				     STACK_PRINT_FLAG_HANDLE),
+			    &page_owner_stack_fops);
+	debugfs_create_file("count_threshold", 0600, dir, NULL,
+			    &page_owner_threshold_fops);
 	return 0;
 }
 late_initcall(pageowner_init)