Commit f15bdfa8 authored by Naoya Horiguchi's avatar Naoya Horiguchi Committed by Linus Torvalds
Browse files

mm/memory-failure.c: fix memory leak in successful soft offlining 



After a successful page migration by soft offlining, the source page is
not properly freed and it's never reusable even if we unpoison it
afterward.

This is caused by the race between freeing page and setting PG_hwpoison.
In successful soft offlining, the source page is put (and the refcount
becomes 0) by putback_lru_page() in unmap_and_move(), where it's linked
to pagevec and actual freeing back to buddy is delayed.  So if
PG_hwpoison is set for the page before freeing, the freeing does not
functions as expected (in such case freeing aborts in
free_pages_prepare() check.)

This patch tries to make sure to free the source page before setting
PG_hwpoison on it.  To avoid reallocating, the page keeps
MIGRATE_ISOLATE until after setting PG_hwpoison.

This patch also removes obsolete comments about "keeping elevated
refcount" because what they say is not true.  Unlike memory_failure(),
soft_offline_page() uses no special page isolation code, and the
soft-offlined pages have no elevated.

Signed-off-by: default avatarNaoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 9bde916b

mm/memory-failure.c

+18 −4
Original line number Original line Diff line number Diff line
@@ -1410,7 +1410,8 @@ static int __get_any_page(struct page *p, unsigned long pfn, int flags) 




	/*

	/*

	 * Isolate the page, so that it doesn't get reallocated if it

	 * Isolate the page, so that it doesn't get reallocated if it

	 * was free.

	 * was free. This flag should be kept set until the source page

	 * is freed and PG_hwpoison on it is set.

	 */

	 */

	set_migratetype_isolate(p, true);

	set_migratetype_isolate(p, true);

	/*

	/*
@@ -1433,7 +1434,6 @@ static int __get_any_page(struct page *p, unsigned long pfn, int flags) 
		/* Not a free page */

		/* Not a free page */

		ret = 1;

		ret = 1;

	}

	}

	unset_migratetype_isolate(p, MIGRATE_MOVABLE);

	unlock_memory_hotplug();

	unlock_memory_hotplug();

	return ret;

	return ret;

}

}
@@ -1494,7 +1494,6 @@ static int soft_offline_huge_page(struct page *page, int flags) 
		atomic_long_add(1 << compound_trans_order(hpage),

		atomic_long_add(1 << compound_trans_order(hpage),

				&num_poisoned_pages);

				&num_poisoned_pages);

	}

	}

	/* keep elevated page count for bad page */

	return ret;

	return ret;

}

}
@@ -1559,7 +1558,7 @@ int soft_offline_page(struct page *page, int flags) 
			atomic_long_inc(&num_poisoned_pages);

			atomic_long_inc(&num_poisoned_pages);

		}

		}

	}

	}

	/* keep elevated page count for bad page */

	unset_migratetype_isolate(page, MIGRATE_MOVABLE);

	return ret;

	return ret;

}

}
@@ -1625,7 +1624,22 @@ static int __soft_offline_page(struct page *page, int flags) 
			if (ret > 0)

			if (ret > 0)

				ret = -EIO;

				ret = -EIO;

		} else {

		} else {

			/*

			 * After page migration succeeds, the source page can

			 * be trapped in pagevec and actual freeing is delayed.

			 * Freeing code works differently based on PG_hwpoison,

			 * so there's a race. We need to make sure that the

			 * source page should be freed back to buddy before

			 * setting PG_hwpoison.

			 */

			if (!is_free_buddy_page(page))

				lru_add_drain_all();

			if (!is_free_buddy_page(page))

				drain_all_pages();

			SetPageHWPoison(page);

			SetPageHWPoison(page);

			if (!is_free_buddy_page(page))

				pr_info("soft offline: %#lx: page leaked\n",

					pfn);

			atomic_long_inc(&num_poisoned_pages);

			atomic_long_inc(&num_poisoned_pages);

		}

		}

	} else {

	} else {

CRA Git | Maintained and supported by SUSTech CRA and CCSE