mm: fix non-compound multi-order memory accounting in __free_pages

When a non-compound multi-order page is freed, it is possible that a
speculative reference keeps the page pinned.  In this case we free all
pages except for the first page, which will be freed later by the last
put_page().  However the page passed to put_page() is indistinguishable
from an order-0 page, so it cannot do the accounting, just as it cannot
free the subsequent pages.  Do the accounting here, where we free the
pages.

Link: https://lkml.kernel.org/r/[email protected]
Reported-by: Vlastimil Babka <[email protected]>
Signed-off-by: Suren Baghdasaryan <[email protected]>
Tested-by: Kees Cook <[email protected]>
Cc: Alexander Viro <[email protected]>
Cc: Alex Gaynor <[email protected]>
Cc: Alice Ryhl <[email protected]>
Cc: Andreas Hindborg <[email protected]>
Cc: Benno Lossin <[email protected]>
Cc: "Björn Roy Baron" <[email protected]>
Cc: Boqun Feng <[email protected]>
Cc: Christoph Lameter <[email protected]>
Cc: Dennis Zhou <[email protected]>
Cc: Gary Guo <[email protected]>
Cc: Kent Overstreet <[email protected]>
Cc: Miguel Ojeda <[email protected]>
Cc: Pasha Tatashin <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Tejun Heo <[email protected]>
Cc: Wedson Almeida Filho <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>

2 files changed, 28 insertions, 1 deletions

diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h
index 093edf98c3d7..50d212330bbb 100644
--- a/include/linux/pgalloc_tag.h
+++ b/include/linux/pgalloc_tag.h
@@ -96,12 +96,36 @@ out:
 	page_ext_put(page_ext);
 }
 
+static inline struct alloc_tag *pgalloc_tag_get(struct page *page)
+{
+	struct alloc_tag *tag = NULL;
+
+	if (mem_alloc_profiling_enabled()) {
+		union codetag_ref *ref = get_page_tag_ref(page);
+
+		alloc_tag_sub_check(ref);
+		if (ref && ref->ct)
+			tag = ct_to_alloc_tag(ref->ct);
+		put_page_tag_ref(ref);
+	}
+
+	return tag;
+}
+
+static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr)
+{
+	if (mem_alloc_profiling_enabled() && tag)
+		this_cpu_sub(tag->counters->bytes, PAGE_SIZE * nr);
+}
+
 #else /* CONFIG_MEM_ALLOC_PROFILING */
 
 static inline void pgalloc_tag_add(struct page *page, struct task_struct *task,
 				   unsigned int nr) {}
 static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) {}
 static inline void pgalloc_tag_split(struct page *page, unsigned int nr) {}
+static inline struct alloc_tag *pgalloc_tag_get(struct page *page) { return NULL; }
+static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) {}
 
 #endif /* CONFIG_MEM_ALLOC_PROFILING */
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e453ee22d489..e1241ecef271 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4664,12 +4664,15 @@ void __free_pages(struct page *page, unsigned int order)
 {
 	/* get PageHead before we drop reference */
 	int head = PageHead(page);
+	struct alloc_tag *tag = pgalloc_tag_get(page);
 
 	if (put_page_testzero(page))
 		free_the_page(page, order);
-	else if (!head)
+	else if (!head) {
+		pgalloc_tag_sub_pages(tag, (1 << order) - 1);
 		while (order-- > 0)
 			free_the_page(page + (1 << order), order);
+	}
 }
 EXPORT_SYMBOL(__free_pages);