Commit 4067196a authored by Kiryl Shutsemau's avatar Kiryl Shutsemau Committed by Andrew Morton
Browse files

mm/page_alloc: fix deadlock on cpu_hotplug_lock in __accept_page() 

When the last page in the zone is accepted, __accept_page() calls
static_branch_dec().  This function takes cpu_hotplug_lock, which can lead
to a deadlock if the allocation occurs during CPU bringup path as
_cpu_up() also takes the lock.

To prevent this deadlock, defer static_branch_dec() to a workqueue.

Call static_branch_dec() only when the workqueue is not yet initialized. 
Workqueues are initialized before CPU bring up, so this will not conflict
with the first scenario.

Link: https://lkml.kernel.org/r/20250329171030.3942298-1-kirill.shutemov@linux.intel.com


Fixes: 55ad43e8 ("mm: add a helper to accept page")
Signed-off-by: default avatarKirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reported-by: default avatarSrikanth Aithal <sraithal@amd.com>
Tested-by: default avatarSrikanth Aithal <sraithal@amd.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Ashish Kalra <ashish.kalra@amd.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: "Edgecombe, Rick P" <rick.p.edgecombe@intel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: "Mike Rapoport (IBM)" <rppt@kernel.org>
Cc: Thomas Lendacky <thomas.lendacky@amd.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
parent fc96b232

include/linux/mmzone.h

+3 −0
Original line number Diff line number Diff line
@@ -967,6 +967,9 @@ struct zone { 
#ifdef CONFIG_UNACCEPTED_MEMORY

	/* Pages to be accepted. All pages on the list are MAX_PAGE_ORDER */

	struct list_head	unaccepted_pages;



	/* To be called once the last page in the zone is accepted */

	struct work_struct	unaccepted_cleanup;

#endif



	/* zone flags, see below */

mm/internal.h

+1 −0
Original line number Diff line number Diff line
@@ -1595,6 +1595,7 @@ unsigned long move_page_tables(struct pagetable_move_control *pmc); 


#ifdef CONFIG_UNACCEPTED_MEMORY

void accept_page(struct page *page);

void unaccepted_cleanup_work(struct work_struct *work);

#else /* CONFIG_UNACCEPTED_MEMORY */

static inline void accept_page(struct page *page)

{

mm/mm_init.c

+1 −0
Original line number Diff line number Diff line
@@ -1441,6 +1441,7 @@ static void __meminit zone_init_free_lists(struct zone *zone) 


#ifdef CONFIG_UNACCEPTED_MEMORY

	INIT_LIST_HEAD(&zone->unaccepted_pages);

	INIT_WORK(&zone->unaccepted_cleanup, unaccepted_cleanup_work);

#endif

}

mm/page_alloc.c

+26 −2
Original line number Diff line number Diff line
@@ -7191,6 +7191,11 @@ static DEFINE_STATIC_KEY_FALSE(zones_with_unaccepted_pages); 


static bool lazy_accept = true;



void unaccepted_cleanup_work(struct work_struct *work)

{

	static_branch_dec(&zones_with_unaccepted_pages);

}



static int __init accept_memory_parse(char *p)

{

	if (!strcmp(p, "lazy")) {
@@ -7229,8 +7234,27 @@ static void __accept_page(struct zone *zone, unsigned long *flags, 


	__free_pages_ok(page, MAX_PAGE_ORDER, FPI_TO_TAIL);



	if (last)

		static_branch_dec(&zones_with_unaccepted_pages);

	if (last) {

		/*

		 * There are two corner cases:

		 *

		 * - If allocation occurs during the CPU bring up,

		 *   static_branch_dec() cannot be used directly as

		 *   it causes a deadlock on cpu_hotplug_lock.

		 *

		 *   Instead, use schedule_work() to prevent deadlock.

		 *

		 * - If allocation occurs before workqueues are initialized,

		 *   static_branch_dec() should be called directly.

		 *

		 *   Workqueues are initialized before CPU bring up, so this

		 *   will not conflict with the first scenario.

		 */

		if (system_wq)

			schedule_work(&zone->unaccepted_cleanup);

		else

			unaccepted_cleanup_work(&zone->unaccepted_cleanup);

	}

}



void accept_page(struct page *page)