mm,page_owner: fix refcount imbalance

Current code does not contemplate scenarios were an allocation and free
operation on the same pages do not handle it in the same amount at once. 
To give an example, page_alloc_exact(), where we will allocate a page of
enough order to stafisfy the size request, but we will free the remainings
right away.

In the above example, we will increment the stack_record refcount only
once, but we will decrease it the same number of times as number of unused
pages we have to free.  This will lead to a warning because of refcount
imbalance.

Fix this by recording the number of base pages in the refcount field.

Link: https://lkml.kernel.org/r/20240404070702.2744-3-osalvador@suse.de
Reported-by: syzbot+41bbfdb8d41003d12c0f@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/linux-mm/00000000000090e8ff0613eda0e5@google.com
Fixes: 217b2119b9e2 ("mm,page_owner: implement the tracking of the stacks count")
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Tested-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Marco Elver <elver@google.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 20 insertions, 14 deletions

diff --git a/mm/page_owner.c b/mm/page_owner.c
index 52d1ced0b57f..5df0d6892bdc 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -196,7 +196,8 @@ static void add_stack_record_to_list(struct stack_record *stack_record,
 	spin_unlock_irqrestore(&stack_list_lock, flags);
 }
 
-static void inc_stack_record_count(depot_stack_handle_t handle, 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);
 
@@ -217,15 +218,20 @@ static void inc_stack_record_count(depot_stack_handle_t handle, gfp_t gfp_mask)
 			/* Add the new stack_record to our list */
 			add_stack_record_to_list(stack_record, gfp_mask);
 	}
-	refcount_inc(&stack_record->count);
+	refcount_add(nr_base_pages, &stack_record->count);
 }
 
-static void dec_stack_record_count(depot_stack_handle_t handle)
+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)
-		refcount_dec(&stack_record->count);
+	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,
@@ -306,7 +312,7 @@ void __reset_page_owner(struct page *page, unsigned short order)
 		 * the machinery is not ready yet, we cannot decrement
 		 * their refcount either.
 		 */
-		dec_stack_record_count(alloc_handle);
+		dec_stack_record_count(alloc_handle, 1 << order);
 }
 
 noinline void __set_page_owner(struct page *page, unsigned short order,
@@ -325,7 +331,7 @@ noinline void __set_page_owner(struct page *page, unsigned short order,
 				   current->pid, current->tgid, ts_nsec,
 				   current->comm);
 	page_ext_put(page_ext);
-	inc_stack_record_count(handle, gfp_mask);
+	inc_stack_record_count(handle, gfp_mask, 1 << order);
 }
 
 void __set_page_owner_migrate_reason(struct page *page, int reason)
@@ -872,11 +878,11 @@ static void *stack_next(struct seq_file *m, void *v, loff_t *ppos)
 	return stack;
 }
 
-static unsigned long page_owner_stack_threshold;
+static unsigned long page_owner_pages_threshold;
 
 static int stack_print(struct seq_file *m, void *v)
 {
-	int i, stack_count;
+	int i, nr_base_pages;
 	struct stack *stack = v;
 	unsigned long *entries;
 	unsigned long nr_entries;
@@ -887,14 +893,14 @@ static int stack_print(struct seq_file *m, void *v)
 
 	nr_entries = stack_record->size;
 	entries = stack_record->entries;
-	stack_count = refcount_read(&stack_record->count) - 1;
+	nr_base_pages = refcount_read(&stack_record->count) - 1;
 
-	if (stack_count < 1 || stack_count < page_owner_stack_threshold)
+	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, "stack_count: %d\n\n", stack_count);
+	seq_printf(m, "nr_base_pages: %d\n\n", nr_base_pages);
 
 	return 0;
 }
@@ -924,13 +930,13 @@ static const struct file_operations page_owner_stack_operations = {
 
 static int page_owner_threshold_get(void *data, u64 *val)
 {
-	*val = READ_ONCE(page_owner_stack_threshold);
+	*val = READ_ONCE(page_owner_pages_threshold);
 	return 0;
 }
 
 static int page_owner_threshold_set(void *data, u64 val)
 {
-	WRITE_ONCE(page_owner_stack_threshold, val);
+	WRITE_ONCE(page_owner_pages_threshold, val);
 	return 0;
 }