1 files changed, 28 insertions, 42 deletions

diff --git a/mm/page_owner.c b/mm/page_owner.c
index d15c7c4994f5..adfabb560eb9 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -27,6 +27,7 @@ struct page_owner {
 	depot_stack_handle_t handle;
 	depot_stack_handle_t free_handle;
 	u64 ts_nsec;
+	u64 free_ts_nsec;
 	pid_t pid;
 };
 
@@ -41,13 +42,7 @@ static void init_early_allocated_pages(void);
 
 static int __init early_page_owner_param(char *buf)
 {
-	if (!buf)
-		return -EINVAL;
-
-	if (strcmp(buf, "on") == 0)
-		page_owner_enabled = true;
-
-	return 0;
+	return kstrtobool(buf, &page_owner_enabled);
 }
 early_param("page_owner", early_page_owner_param);
 
@@ -103,42 +98,30 @@ static inline struct page_owner *get_page_owner(struct page_ext *page_ext)
 	return (void *)page_ext + page_owner_ops.offset;
 }
 
-static inline bool check_recursive_alloc(unsigned long *entries,
-					 unsigned int nr_entries,
-					 unsigned long ip)
-{
-	unsigned int i;
-
-	for (i = 0; i < nr_entries; i++) {
-		if (entries[i] == ip)
-			return true;
-	}
-	return false;
-}
-
 static noinline depot_stack_handle_t save_stack(gfp_t flags)
 {
 	unsigned long entries[PAGE_OWNER_STACK_DEPTH];
 	depot_stack_handle_t handle;
 	unsigned int nr_entries;
 
-	nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 2);
-
 	/*
-	 * We need to check recursion here because our request to
-	 * stackdepot could trigger memory allocation to save new
-	 * entry. New memory allocation would reach here and call
-	 * stack_depot_save_entries() again if we don't catch it. There is
-	 * still not enough memory in stackdepot so it would try to
-	 * allocate memory again and loop forever.
+	 * 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 (check_recursive_alloc(entries, nr_entries, _RET_IP_))
+	if (current->in_page_owner)
 		return dummy_handle;
+	current->in_page_owner = 1;
 
+	nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 2);
 	handle = stack_depot_save(entries, nr_entries, flags);
 	if (!handle)
 		handle = failure_handle;
 
+	current->in_page_owner = 0;
 	return handle;
 }
 
@@ -146,25 +129,27 @@ void __reset_page_owner(struct page *page, unsigned int order)
 {
 	int i;
 	struct page_ext *page_ext;
-	depot_stack_handle_t handle = 0;
+	depot_stack_handle_t handle;
 	struct page_owner *page_owner;
-
-	handle = save_stack(GFP_NOWAIT | __GFP_NOWARN);
+	u64 free_ts_nsec = local_clock();
 
 	page_ext = lookup_page_ext(page);
 	if (unlikely(!page_ext))
 		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);
 	}
 }
 
-static inline void __set_page_owner_handle(struct page *page,
-	struct page_ext *page_ext, depot_stack_handle_t handle,
-	unsigned int order, gfp_t gfp_mask)
+static inline void __set_page_owner_handle(struct page_ext *page_ext,
+					depot_stack_handle_t handle,
+					unsigned int order, gfp_t gfp_mask)
 {
 	struct page_owner *page_owner;
 	int i;
@@ -194,7 +179,7 @@ noinline void __set_page_owner(struct page *page, unsigned int order,
 		return;
 
 	handle = save_stack(gfp_mask);
-	__set_page_owner_handle(page, page_ext, handle, order, gfp_mask);
+	__set_page_owner_handle(page_ext, handle, order, gfp_mask);
 }
 
 void __set_page_owner_migrate_reason(struct page *page, int reason)
@@ -243,11 +228,12 @@ void __copy_page_owner(struct page *oldpage, struct page *newpage)
 	new_page_owner->handle = old_page_owner->handle;
 	new_page_owner->pid = old_page_owner->pid;
 	new_page_owner->ts_nsec = old_page_owner->ts_nsec;
+	new_page_owner->free_ts_nsec = old_page_owner->ts_nsec;
 
 	/*
 	 * We don't clear the bit on the oldpage as it's going to be freed
 	 * after migration. Until then, the info can be useful in case of
-	 * a bug, and the overal stats will be off a bit only temporarily.
+	 * 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 oldpage to retain the info. But
 	 * in that case we also don't need to explicitly clear the info from
@@ -356,10 +342,10 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn,
 		return -ENOMEM;
 
 	ret = snprintf(kbuf, count,
-			"Page allocated via order %u, mask %#x(%pGg), pid %d, ts %llu ns\n",
+			"Page allocated via order %u, mask %#x(%pGg), pid %d, ts %llu ns, free_ts %llu ns\n",
 			page_owner->order, page_owner->gfp_mask,
 			&page_owner->gfp_mask, page_owner->pid,
-			page_owner->ts_nsec);
+			page_owner->ts_nsec, page_owner->free_ts_nsec);
 
 	if (ret >= count)
 		goto err;
@@ -435,9 +421,9 @@ void __dump_page_owner(struct page *page)
 	else
 		pr_alert("page_owner tracks the page as freed\n");
 
-	pr_alert("page last allocated via order %u, migratetype %s, gfp_mask %#x(%pGg), pid %d, ts %llu\n",
+	pr_alert("page last allocated via order %u, migratetype %s, gfp_mask %#x(%pGg), pid %d, ts %llu, free_ts %llu\n",
 		 page_owner->order, migratetype_names[mt], gfp_mask, &gfp_mask,
-		 page_owner->pid, page_owner->ts_nsec);
+		 page_owner->pid, page_owner->ts_nsec, page_owner->free_ts_nsec);
 
 	handle = READ_ONCE(page_owner->handle);
 	if (!handle) {
@@ -612,7 +598,7 @@ static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone)
 				continue;
 
 			/* Found early allocated page */
-			__set_page_owner_handle(page, page_ext, early_handle,
+			__set_page_owner_handle(page_ext, early_handle,
 						0, 0);
 			count++;
 		}