Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 053837fc authored by Nick Piggin's avatar Nick Piggin Committed by Linus Torvalds
Browse files

[PATCH] mm: migration page refcounting fix 



Migration code currently does not take a reference to target page
properly, so between unlocking the pte and trying to take a new
reference to the page with isolate_lru_page, anything could happen to
it.

Fix this by holding the pte lock until we get a chance to elevate the
refcount.

Other small cleanups while we're here.

Signed-off-by: default avatarNick Piggin <npiggin@suse.de>
Signed-off-by: default avatarChristoph Lameter <clameter@sgi.com>
Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
parent e236a166

include/linux/mm_inline.h

+0 −21
Original line number Diff line number Diff line
@@ -39,24 +39,3 @@ del_page_from_lru(struct zone *zone, struct page *page) 
	}

}

/*

 * Isolate one page from the LRU lists.

 *

 * - zone->lru_lock must be held

 */

static inline int __isolate_lru_page(struct page *page)

{

	if (unlikely(!TestClearPageLRU(page)))

		return 0;



	if (get_page_testone(page)) {

		/*

		 * It is being freed elsewhere

		 */

		__put_page(page);

		SetPageLRU(page);

		return -ENOENT;

	}



	return 1;

}

include/linux/swap.h

+1 −0
Original line number Diff line number Diff line
@@ -167,6 +167,7 @@ extern void FASTCALL(lru_cache_add_active(struct page *)); 
extern void FASTCALL(activate_page(struct page *));

extern void FASTCALL(mark_page_accessed(struct page *));

extern void lru_add_drain(void);

extern int lru_add_drain_all(void);

extern int rotate_reclaimable_page(struct page *page);

extern void swap_setup(void);

mm/filemap.c

+1 −0
Original line number Diff line number Diff line
@@ -94,6 +94,7 @@ generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, 
 *    ->private_lock		(try_to_unmap_one)

 *    ->tree_lock		(try_to_unmap_one)

 *    ->zone.lru_lock		(follow_page->mark_page_accessed)

 *    ->zone.lru_lock		(check_pte_range->isolate_lru_page)

 *    ->private_lock		(page_remove_rmap->set_page_dirty)

 *    ->tree_lock		(page_remove_rmap->set_page_dirty)

 *    ->inode_lock		(page_remove_rmap->set_page_dirty)

mm/mempolicy.c

+17 −12
Original line number Diff line number Diff line
@@ -208,6 +208,17 @@ static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd, 
		page = vm_normal_page(vma, addr, *pte);

		if (!page)

			continue;

		/*

		 * The check for PageReserved here is important to avoid

		 * handling zero pages and other pages that may have been

		 * marked special by the system.

		 *

		 * If the PageReserved would not be checked here then f.e.

		 * the location of the zero page could have an influence

		 * on MPOL_MF_STRICT, zero pages would be counted for

		 * the per node stats, and there would be useless attempts

		 * to put zero pages on the migration list.

		 */

		if (PageReserved(page))

			continue;

		nid = page_to_nid(page);
@@ -216,11 +227,8 @@ static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd, 


		if (flags & MPOL_MF_STATS)

			gather_stats(page, private);

		else if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {

			spin_unlock(ptl);

		else if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))

			migrate_page_add(vma, page, private, flags);

			spin_lock(ptl);

		}

		else

			break;

	} while (pte++, addr += PAGE_SIZE, addr != end);
@@ -309,6 +317,10 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end, 
	int err;

	struct vm_area_struct *first, *vma, *prev;



	/* Clear the LRU lists so pages can be isolated */

	if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))

		lru_add_drain_all();



	first = find_vma(mm, start);

	if (!first)

		return ERR_PTR(-EFAULT);
@@ -555,15 +567,8 @@ static void migrate_page_add(struct vm_area_struct *vma, 
	if ((flags & MPOL_MF_MOVE_ALL) || !page->mapping || PageAnon(page) ||

	    mapping_writably_mapped(page->mapping) ||

	    single_mm_mapping(vma->vm_mm, page->mapping)) {

		int rc = isolate_lru_page(page);



		if (rc == 1)

		if (isolate_lru_page(page))

			list_add(&page->lru, pagelist);

		/*

		 * If the isolate attempt was not successful then we just

		 * encountered an unswappable page. Something must be wrong.

	 	 */

		WARN_ON(rc == 0);

	}

}

mm/rmap.c

+1 −1
Original line number Diff line number Diff line
@@ -33,7 +33,7 @@ 
 *     mapping->i_mmap_lock

 *       anon_vma->lock

 *         mm->page_table_lock or pte_lock

 *           zone->lru_lock (in mark_page_accessed)

 *           zone->lru_lock (in mark_page_accessed, isolate_lru_page)

 *           swap_lock (in swap_duplicate, swap_info_get)

 *             mmlist_lock (in mmput, drain_mmlist and others)

 *             mapping->private_lock (in __set_page_dirty_buffers)