1 files changed, 311 insertions, 66 deletions

diff --git a/mm/page_owner.c b/mm/page_owner.c
index 5634e5d890..8eed0f3dc0 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -36,6 +36,15 @@ struct page_owner {
 	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);
+
 static bool page_owner_enabled __initdata;
 DEFINE_STATIC_KEY_FALSE(page_owner_inited);
 
@@ -45,6 +54,22 @@ 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);
@@ -93,8 +118,17 @@ 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 = {
@@ -115,81 +149,177 @@ 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
-	 */
 	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;
+
+	/* Filter gfp_mask the same way stackdepot does, for consistency */
+	gfp_mask &= ~GFP_ZONEMASK;
+	gfp_mask &= (GFP_ATOMIC | GFP_KERNEL | __GFP_NOLOCKDEP);
+	gfp_mask |= __GFP_NOWARN;
+
+	set_current_in_page_owner();
+	stack = kmalloc(sizeof(*stack), gfp_mask);
+	if (!stack) {
+		unset_current_in_page_owner();
+		return;
+	}
+	unset_current_in_page_owner();
 
-	page_ext = page_ext_get(page);
-	if (unlikely(!page_ext))
+	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 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;
 
-	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_owner->free_pid = current->pid;
-		page_owner->free_tgid = current->tgid;
-		page_ext = page_ext_next(page_ext);
+	/*
+	 * 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);
 	}
-	page_ext_put(page_ext);
+	refcount_add(nr_base_pages, &stack_record->count);
 }
 
-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 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_ext *page_ext,
+					      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_owner *page_owner;
 	int i;
-	u64 ts_nsec = local_clock();
+	struct page_owner *page_owner;
 
 	for (i = 0; i < (1 << order); i++) {
 		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->last_migrate_reason = last_migrate_reason;
+		page_owner->pid = pid;
+		page_owner->tgid = tgid;
 		page_owner->ts_nsec = ts_nsec;
-		strscpy(page_owner->comm, current->comm,
+		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);
+		page_ext = page_ext_next(page_ext);
+	}
+}
+
+static inline void __update_page_owner_free_handle(struct page_ext *page_ext,
+						   depot_stack_handle_t handle,
+						   unsigned short order,
+						   pid_t pid, pid_t tgid,
+						   u64 free_ts_nsec)
+{
+	int i;
+	struct page_owner *page_owner;
 
+	for (i = 0; i < (1 << order); i++) {
+		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;
 		page_ext = page_ext_next(page_ext);
 	}
 }
 
+void __reset_page_owner(struct page *page, unsigned short order)
+{
+	struct page_ext *page_ext;
+	depot_stack_handle_t handle;
+	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;
+
+	page_owner = get_page_owner(page_ext);
+	alloc_handle = page_owner->handle;
+
+	handle = save_stack(GFP_NOWAIT | __GFP_NOWARN);
+	__update_page_owner_free_handle(page_ext, handle, order, current->pid,
+					current->tgid, free_ts_nsec);
+	page_ext_put(page_ext);
+
+	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);
+}
+
 noinline void __set_page_owner(struct page *page, unsigned short order,
 					gfp_t gfp_mask)
 {
 	struct page_ext *page_ext;
+	u64 ts_nsec = local_clock();
 	depot_stack_handle_t handle;
 
 	handle = save_stack(gfp_mask);
@@ -197,8 +327,11 @@ noinline void __set_page_owner(struct page *page, unsigned short order,
 	page_ext = page_ext_get(page);
 	if (unlikely(!page_ext))
 		return;
-	__set_page_owner_handle(page_ext, handle, order, gfp_mask);
+	__update_page_owner_handle(page_ext, handle, order, gfp_mask, -1,
+				   ts_nsec, current->pid, current->tgid,
+				   current->comm);
 	page_ext_put(page_ext);
+	inc_stack_record_count(handle, gfp_mask, 1 << order);
 }
 
 void __set_page_owner_migrate_reason(struct page *page, int reason)
@@ -214,7 +347,7 @@ 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);
@@ -223,9 +356,9 @@ void __split_page_owner(struct page *page, unsigned int nr)
 	if (unlikely(!page_ext))
 		return;
 
-	for (i = 0; i < nr; i++) {
+	for (i = 0; i < (1 << old_order); i++) {
 		page_owner = get_page_owner(page_ext);
-		page_owner->order = 0;
+		page_owner->order = new_order;
 		page_ext = page_ext_next(page_ext);
 	}
 	page_ext_put(page_ext);
@@ -233,9 +366,12 @@ void __split_page_owner(struct page *page, unsigned int nr)
 
 void __folio_copy_owner(struct folio *newfolio, struct folio *old)
 {
+	int i;
 	struct page_ext *old_ext;
 	struct page_ext *new_ext;
-	struct page_owner *old_page_owner, *new_page_owner;
+	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))
@@ -249,30 +385,32 @@ void __folio_copy_owner(struct folio *newfolio, struct folio *old)
 
 	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->free_pid = old_page_owner->free_pid;
-	new_page_owner->free_tgid = old_page_owner->free_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);
-
+	migrate_handle = new_page_owner->handle;
+	__update_page_owner_handle(new_ext, 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);
 	/*
-	 * 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.
+	 * 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.
 	 */
-	__set_bit(PAGE_EXT_OWNER, &new_ext->flags);
-	__set_bit(PAGE_EXT_OWNER_ALLOCATED, &new_ext->flags);
+	__update_page_owner_free_handle(new_ext, 0, old_page_owner->order,
+					old_page_owner->free_pid,
+					old_page_owner->free_tgid,
+					old_page_owner->free_ts_nsec);
+	/*
+	 * 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.
+	 */
+	for (i = 0; i < (1 << new_page_owner->order); i++) {
+		old_page_owner->handle = migrate_handle;
+		old_ext = page_ext_next(old_ext);
+		old_page_owner = get_page_owner(old_ext);
+	}
+
 	page_ext_put(new_ext);
 	page_ext_put(old_ext);
 }
@@ -680,8 +818,9 @@ 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_ext, early_handle, 0, 0,
+						   -1, local_clock(), current->pid,
+						   current->tgid, current->comm);
 			count++;
 ext_put_continue:
 			page_ext_put(page_ext);
@@ -719,8 +858,109 @@ static const struct file_operations proc_page_owner_operations = {
 	.llseek		= lseek_page_owner,
 };
 
+static void *stack_start(struct seq_file *m, loff_t *ppos)
+{
+	struct stack *stack;
+
+	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);
+		m->private = stack;
+	} else {
+		stack = m->private;
+	}
+
+	return stack;
+}
+
+static void *stack_next(struct seq_file *m, void *v, loff_t *ppos)
+{
+	struct stack *stack = v;
+
+	stack = stack->next;
+	*ppos = stack ? *ppos + 1 : -1UL;
+	m->private = stack;
+
+	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;
+
+	if (!stack->stack_record)
+		return 0;
+
+	nr_entries = stack_record->size;
+	entries = stack_record->entries;
+	nr_base_pages = refcount_read(&stack_record->count) - 1;
+
+	if (nr_base_pages < 1 || nr_base_pages < page_owner_pages_threshold)
+		return 0;
+
+	for (i = 0; i < nr_entries; i++)
+		seq_printf(m, " %pS\n", (void *)entries[i]);
+	seq_printf(m, "nr_base_pages: %d\n\n", nr_base_pages);
+
+	return 0;
+}
+
+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)
+{
+	return seq_open_private(file, &page_owner_stack_op, 0);
+}
+
+static const struct file_operations page_owner_stack_operations = {
+	.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(proc_page_owner_threshold, &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;
@@ -728,6 +968,11 @@ static int __init pageowner_init(void)
 
 	debugfs_create_file("page_owner", 0400, NULL, NULL,
 			    &proc_page_owner_operations);
+	dir = debugfs_create_dir("page_owner_stacks", NULL);
+	debugfs_create_file("show_stacks", 0400, dir, NULL,
+			    &page_owner_stack_operations);
+	debugfs_create_file("count_threshold", 0600, dir, NULL,
+			    &proc_page_owner_threshold);
 
 	return 0;
 }