mm: fix use-after free of page_ext after race with memory-offline

The below is one path where race between page_ext and offline of the respective memory blocks will cause use-after-free on the access of page_ext structure. process1 process2 --------- --------- a)doing /proc/page_owner doing memory offline through offline_pages. b) PageBuddy check is failed thus proceed to get the page_owner information through page_ext access. page_ext = lookup_page_ext(page); migrate_pages(); ................. Since all pages are successfully migrated as part of the offline operation,send MEM_OFFLINE notification where for page_ext it calls: offline_page_ext()--> __free_page_ext()--> free_page_ext()--> vfree(ms->page_ext) mem_section->page_ext = NULL c) Check for the PAGE_EXT flags in the page_ext->flags access results into the use-after-free (leading to the translation faults). As mentioned above, there is really no synchronization between page_ext access and its freeing in the memory_offline. The memory offline steps(roughly) on a memory block is as below: 1) Isolate all the pages 2) while(1) try free the pages to buddy.(->free_list[MIGRATE_ISOLATE]) 3) delete the pages from this buddy list. 4) Then free page_ext.(Note: The struct page is still alive as it is freed only during hot remove of the memory which frees the memmap, which steps the user might not perform). This design leads to the state where struct page is alive but the struct page_ext is freed, where the later is ideally part of the former which just representing the page_flags (check [3] for why this design is chosen). The abovementioned race is just one example __but the problem persists in the other paths too involving page_ext->flags access(eg: page_is_idle())__. Fix all the paths where offline races with page_ext access by maintaining synchronization with rcu lock and is achieved in 3 steps: 1) Invalidate all the page_ext's of the sections of a memory block by storing a flag in the LSB of mem_section->page_ext. 2) Wait until all the existing readers to finish working with the ->page_ext's with synchronize_rcu(). Any parallel process that starts after this call will not get page_ext, through lookup_page_ext(), for the block parallel offline operation is being performed. 3) Now safely free all sections ->page_ext's of the block on which offline operation is being performed. Note: If synchronize_rcu() takes time then optimizations can be done in this path through call_rcu()[2]. Thanks to David Hildenbrand for his views/suggestions on the initial discussion[1] and Pavan kondeti for various inputs on this patch. [1] https://lore.kernel.org/linux-mm/[email protected]/ [2] https://lore.kernel.org/all/[email protected]/T/#u [3] https://lore.kernel.org/all/[email protected]/ [[email protected]: rename label `loop' to `ext_put_continue' per David] Link: https://lkml.kernel.org/r/[email protected] Link: https://lkml.kernel.org/r/[email protected] Signed-off-by: Charan Teja Kalla <[email protected]> Suggested-by: David Hildenbrand <[email protected]> Suggested-by: Michal Hocko <[email protected]> Acked-by: Michal Hocko <[email protected]> Acked-by: David Hildenbrand <[email protected]> Cc: Fernand Sieber <[email protected]> Cc: Minchan Kim <[email protected]> Cc: Pasha Tatashin <[email protected]> Cc: Pavan Kondeti <[email protected]> Cc: SeongJae Park <[email protected]> Cc: Shakeel Butt <[email protected]> Cc: Vlastimil Babka <[email protected]> Cc: William Kucharski <[email protected]> Signed-off-by: Andrew Morton <[email protected]>
mpe · Sep 12, 2022 · b1d5488 · b1d5488
1 parent 08262ac
commit b1d5488
Show file tree

Hide file tree

Showing 5 changed files with 192 additions and 45 deletions.
diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h
@@ -55,7 +55,8 @@ static inline void page_ext_init(void)
 }
 #endif
 
-struct page_ext *lookup_page_ext(const struct page *page);
+extern struct page_ext *page_ext_get(struct page *page);
+extern void page_ext_put(struct page_ext *page_ext);
 
 static inline struct page_ext *page_ext_next(struct page_ext *curr)
 {
@@ -71,11 +72,6 @@ static inline void pgdat_page_ext_init(struct pglist_data *pgdat)
 {
 }
 
-static inline struct page_ext *lookup_page_ext(const struct page *page)
-{
-	return NULL;
-}
-
 static inline void page_ext_init(void)
 {
 }
@@ -87,5 +83,14 @@ static inline void page_ext_init_flatmem_late(void)
 static inline void page_ext_init_flatmem(void)
 {
 }
+
+static inline struct page_ext *page_ext_get(struct page *page)
+{
+	return NULL;
+}
+
+static inline void page_ext_put(struct page_ext *page_ext)
+{
+}
 #endif /* CONFIG_PAGE_EXTENSION */
 #endif /* __LINUX_PAGE_EXT_H */
diff --git a/include/linux/page_idle.h b/include/linux/page_idle.h
@@ -13,65 +13,79 @@
  * If there is not enough space to store Idle and Young bits in page flags, use
  * page ext flags instead.
  */
-
 static inline bool folio_test_young(struct folio *folio)
 {
-	struct page_ext *page_ext = lookup_page_ext(&folio->page);
+	struct page_ext *page_ext = page_ext_get(&folio->page);
+	bool page_young;
 
 	if (unlikely(!page_ext))
 		return false;
 
-	return test_bit(PAGE_EXT_YOUNG, &page_ext->flags);
+	page_young = test_bit(PAGE_EXT_YOUNG, &page_ext->flags);
+	page_ext_put(page_ext);
+
+	return page_young;
 }
 
 static inline void folio_set_young(struct folio *folio)
 {
-	struct page_ext *page_ext = lookup_page_ext(&folio->page);
+	struct page_ext *page_ext = page_ext_get(&folio->page);
 
 	if (unlikely(!page_ext))
 		return;
 
 	set_bit(PAGE_EXT_YOUNG, &page_ext->flags);
+	page_ext_put(page_ext);
 }
 
 static inline bool folio_test_clear_young(struct folio *folio)
 {
-	struct page_ext *page_ext = lookup_page_ext(&folio->page);
+	struct page_ext *page_ext = page_ext_get(&folio->page);
+	bool page_young;
 
 	if (unlikely(!page_ext))
 		return false;
 
-	return test_and_clear_bit(PAGE_EXT_YOUNG, &page_ext->flags);
+	page_young = test_and_clear_bit(PAGE_EXT_YOUNG, &page_ext->flags);
+	page_ext_put(page_ext);
+
+	return page_young;
 }
 
 static inline bool folio_test_idle(struct folio *folio)
 {
-	struct page_ext *page_ext = lookup_page_ext(&folio->page);
+	struct page_ext *page_ext = page_ext_get(&folio->page);
+	bool page_idle;
 
 	if (unlikely(!page_ext))
 		return false;
 
-	return test_bit(PAGE_EXT_IDLE, &page_ext->flags);
+	page_idle =  test_bit(PAGE_EXT_IDLE, &page_ext->flags);
+	page_ext_put(page_ext);
+
+	return page_idle;
 }
 
 static inline void folio_set_idle(struct folio *folio)
 {
-	struct page_ext *page_ext = lookup_page_ext(&folio->page);
+	struct page_ext *page_ext = page_ext_get(&folio->page);
 
 	if (unlikely(!page_ext))
 		return;
 
 	set_bit(PAGE_EXT_IDLE, &page_ext->flags);
+	page_ext_put(page_ext);
 }
 
 static inline void folio_clear_idle(struct folio *folio)
 {
-	struct page_ext *page_ext = lookup_page_ext(&folio->page);
+	struct page_ext *page_ext = page_ext_get(&folio->page);
 
 	if (unlikely(!page_ext))
 		return;
 
 	clear_bit(PAGE_EXT_IDLE, &page_ext->flags);
+	page_ext_put(page_ext);
 }
 #endif /* !CONFIG_64BIT */
 

diff --git a/mm/page_ext.c b/mm/page_ext.c
@@ -9,6 +9,7 @@
 #include <linux/page_owner.h>
 #include <linux/page_idle.h>
 #include <linux/page_table_check.h>
+#include <linux/rcupdate.h>
 
 /*
  * struct page extension
@@ -59,6 +60,10 @@
  * can utilize this callback to initialize the state of it correctly.
  */
 
+#ifdef CONFIG_SPARSEMEM
+#define PAGE_EXT_INVALID       (0x1)
+#endif
+
 #if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT)
 static bool need_page_idle(void)
 {
@@ -84,6 +89,7 @@ static struct page_ext_operations *page_ext_ops[] __initdata = {
 unsigned long page_ext_size = sizeof(struct page_ext);
 
 static unsigned long total_usage;
+static struct page_ext *lookup_page_ext(const struct page *page);
 
 static bool __init invoke_need_callbacks(void)
 {
@@ -125,6 +131,48 @@ static inline struct page_ext *get_entry(void *base, unsigned long index)
 	return base + page_ext_size * index;
 }
 
+/**
+ * page_ext_get() - Get the extended information for a page.
+ * @page: The page we're interested in.
+ *
+ * Ensures that the page_ext will remain valid until page_ext_put()
+ * is called.
+ *
+ * Return: NULL if no page_ext exists for this page.
+ * Context: Any context.  Caller may not sleep until they have called
+ * page_ext_put().
+ */
+struct page_ext *page_ext_get(struct page *page)
+{
+	struct page_ext *page_ext;
+
+	rcu_read_lock();
+	page_ext = lookup_page_ext(page);
+	if (!page_ext) {
+		rcu_read_unlock();
+		return NULL;
+	}
+
+	return page_ext;
+}
+
+/**
+ * page_ext_put() - Working with page extended information is done.
+ * @page_ext - Page extended information received from page_ext_get().
+ *
+ * The page extended information of the page may not be valid after this
+ * function is called.
+ *
+ * Return: None.
+ * Context: Any context with corresponding page_ext_get() is called.
+ */
+void page_ext_put(struct page_ext *page_ext)
+{
+	if (unlikely(!page_ext))
+		return;
+
+	rcu_read_unlock();
+}
 #ifndef CONFIG_SPARSEMEM
 
 
@@ -133,12 +181,13 @@ void __meminit pgdat_page_ext_init(struct pglist_data *pgdat)
 	pgdat->node_page_ext = NULL;
 }
 
-struct page_ext *lookup_page_ext(const struct page *page)
+static struct page_ext *lookup_page_ext(const struct page *page)
 {
 	unsigned long pfn = page_to_pfn(page);
 	unsigned long index;
 	struct page_ext *base;
 
+	WARN_ON_ONCE(!rcu_read_lock_held());
 	base = NODE_DATA(page_to_nid(page))->node_page_ext;
 	/*
 	 * The sanity checks the page allocator does upon freeing a
@@ -206,20 +255,27 @@ void __init page_ext_init_flatmem(void)
 }
 
 #else /* CONFIG_SPARSEMEM */
+static bool page_ext_invalid(struct page_ext *page_ext)
+{
+	return !page_ext || (((unsigned long)page_ext & PAGE_EXT_INVALID) == PAGE_EXT_INVALID);
+}
 
-struct page_ext *lookup_page_ext(const struct page *page)
+static struct page_ext *lookup_page_ext(const struct page *page)
 {
 	unsigned long pfn = page_to_pfn(page);
 	struct mem_section *section = __pfn_to_section(pfn);
+	struct page_ext *page_ext = READ_ONCE(section->page_ext);
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
 	/*
 	 * The sanity checks the page allocator does upon freeing a
 	 * page can reach here before the page_ext arrays are
 	 * allocated when feeding a range of pages to the allocator
 	 * for the first time during bootup or memory hotplug.
 	 */
-	if (!section->page_ext)
+	if (page_ext_invalid(page_ext))
 		return NULL;
-	return get_entry(section->page_ext, pfn);
+	return get_entry(page_ext, pfn);
 }
 
 static void *__meminit alloc_page_ext(size_t size, int nid)
@@ -298,9 +354,30 @@ static void __free_page_ext(unsigned long pfn)
 	ms = __pfn_to_section(pfn);
 	if (!ms || !ms->page_ext)
 		return;
-	base = get_entry(ms->page_ext, pfn);
+
+	base = READ_ONCE(ms->page_ext);
+	/*
+	 * page_ext here can be valid while doing the roll back
+	 * operation in online_page_ext().
+	 */
+	if (page_ext_invalid(base))
+		base = (void *)base - PAGE_EXT_INVALID;
+	WRITE_ONCE(ms->page_ext, NULL);
+
+	base = get_entry(base, pfn);
 	free_page_ext(base);
-	ms->page_ext = NULL;
+}
+
+static void __invalidate_page_ext(unsigned long pfn)
+{
+	struct mem_section *ms;
+	void *val;
+
+	ms = __pfn_to_section(pfn);
+	if (!ms || !ms->page_ext)
+		return;
+	val = (void *)ms->page_ext + PAGE_EXT_INVALID;
+	WRITE_ONCE(ms->page_ext, val);
 }
 
 static int __meminit online_page_ext(unsigned long start_pfn,
@@ -343,6 +420,20 @@ static int __meminit offline_page_ext(unsigned long start_pfn,
 	start = SECTION_ALIGN_DOWN(start_pfn);
 	end = SECTION_ALIGN_UP(start_pfn + nr_pages);
 
+	/*
+	 * Freeing of page_ext is done in 3 steps to avoid
+	 * use-after-free of it:
+	 * 1) Traverse all the sections and mark their page_ext
+	 *    as invalid.
+	 * 2) Wait for all the existing users of page_ext who
+	 *    started before invalidation to finish.
+	 * 3) Free the page_ext.
+	 */
+	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
+		__invalidate_page_ext(pfn);
+
+	synchronize_rcu();
+
 	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
 		__free_page_ext(pfn);
 	return 0;