mm/codetag: move tag retrieval back upfront in __free_pages()

Commit 51ff4d7 ("mm: avoid extra mem_alloc_profiling_enabled()
 checks") introduces a possible use-after-free scenario, when page
is non-compound, page[0] could be released by other thread right
after put_page_testzero failed in current thread, pgalloc_tag_sub_pages
afterwards would manipulate an invalid page for accounting remaining
pages:

[timeline]   [thread1]                     [thread2]
  |          alloc_page non-compound
  V
  |                                        get_page, rf counter inc
  V
  |          in ___free_pages
  |          put_page_testzero fails
  V
  |                                        put_page, page released
  V
  |          in ___free_pages,
  |          pgalloc_tag_sub_pages
  |          manipulate an invalid page
  V

Restore __free_pages() to its state before, retrieve alloc tag
beforehand.

Link: https://lkml.kernel.org/r/20250505193034.91682-1-00107082@163.com
Fixes: 51ff4d7 ("mm: avoid extra mem_alloc_profiling_enabled() checks")
Signed-off-by: David Wang <00107082@163.com>
Acked-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Author: zq-david-wang

include/linux/pgalloc_tag.h

@@ -188,6 +188,13 @@ static inline struct alloc_tag *__pgalloc_tag_get(struct page *page)
 	return tag;
 }
 
+static inline struct alloc_tag *pgalloc_tag_get(struct page *page)
+{
+	if (mem_alloc_profiling_enabled())
+		return __pgalloc_tag_get(page);
+	return NULL;
+}
+
 void pgalloc_tag_split(struct folio *folio, int old_order, int new_order);
 void pgalloc_tag_swap(struct folio *new, struct folio *old);
 
@@ -199,6 +206,7 @@ static inline void clear_page_tag_ref(struct page *page) {}
 static inline void alloc_tag_sec_init(void) {}
 static inline void pgalloc_tag_split(struct folio *folio, int old_order, int new_order) {}
 static inline void pgalloc_tag_swap(struct folio *new, struct folio *old) {}
+static inline struct alloc_tag *pgalloc_tag_get(struct page *page) { return NULL; }
 
 #endif /* CONFIG_MEM_ALLOC_PROFILING */
 

mm/page_alloc.c

@@ -1151,14 +1151,9 @@ static inline void pgalloc_tag_sub(struct page *page, unsigned int nr)
 		__pgalloc_tag_sub(page, nr);
 }
 
-static inline void pgalloc_tag_sub_pages(struct page *page, unsigned int nr)
+/* When tag is not NULL, assuming mem_alloc_profiling_enabled */
+static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr)
 {
-	struct alloc_tag *tag;
-
-	if (!mem_alloc_profiling_enabled())
-		return;
-
-	tag = __pgalloc_tag_get(page);
 	if (tag)
 		this_cpu_sub(tag->counters->bytes, PAGE_SIZE * nr);
 }
@@ -1168,7 +1163,7 @@ static inline void pgalloc_tag_sub_pages(struct page *page, unsigned int nr)
 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_sub_pages(struct page *page, unsigned int nr) {}
+static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) {}
 
 #endif /* CONFIG_MEM_ALLOC_PROFILING */
 
@@ -5065,11 +5060,13 @@ static void ___free_pages(struct page *page, unsigned int order,
 {
 	/* get PageHead before we drop reference */
 	int head = PageHead(page);
+	/* get alloc tag in case the page is released by others */
+	struct alloc_tag *tag = pgalloc_tag_get(page);
 
 	if (put_page_testzero(page))
 		__free_frozen_pages(page, order, fpi_flags);
 	else if (!head) {
-		pgalloc_tag_sub_pages(page, (1 << order) - 1);
+		pgalloc_tag_sub_pages(tag, (1 << order) - 1);
 		while (order-- > 0)
 			__free_frozen_pages(page + (1 << order), order,
 					    fpi_flags);