mm: fix rss count leakage during migration (9f9f1acd) · Commits · 戴 / test

Memory migration fills a pte with a migration entry and it doesn't update the rss counters. Then it replaces the migration entry with the new page (or the old one if migration failed). But between these two passes this pte can be unmaped, or a task can fork a child and it will get a copy of this migration entry. Nobody accounts for this in the rss counters. This patch properly adjust rss counters for migration entries in zap_pte_range() and copy_one_pte(). Thus we avoid extra atomic operations on the migration fast-path. Signed-off-by:

Konstantin Khlebnikov <khlebnikov@openvz.org> Cc: Hugh Dickins <hughd@google.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by:

Andrew Morton <akpm@linux-foundation.org> Signed-off-by:

Linus Torvalds <torvalds@linux-foundation.org>

mm/memory.c

+28 −9

Original line number	Diff line number	Diff line
		@@ -878,17 +878,26 @@ copy_one_pte(struct mm_struct dst_mm, struct mm_struct src_mm,
		}
		if (likely(!non_swap_entry(entry)))
		rss[MM_SWAPENTS]++;
		else if (is_write_migration_entry(entry) &&
		else if (is_migration_entry(entry)) {
		page = migration_entry_to_page(entry);

		if (PageAnon(page))
		rss[MM_ANONPAGES]++;
		else
		rss[MM_FILEPAGES]++;

		if (is_write_migration_entry(entry) &&
		is_cow_mapping(vm_flags)) {
		/*
		* COW mappings require pages in both parent
		* and child to be set to read.
		* COW mappings require pages in both
		* parent and child to be set to read.
		*/
		make_migration_entry_read(&entry);
		pte = swp_entry_to_pte(entry);
		set_pte_at(src_mm, addr, src_pte, pte);
		}
		}
		}
		goto out_set_pte;
		}

		@@ -1191,6 +1200,16 @@ again:

		if (!non_swap_entry(entry))
		rss[MM_SWAPENTS]--;
		else if (is_migration_entry(entry)) {
		struct page *page;

		page = migration_entry_to_page(entry);

		if (PageAnon(page))
		rss[MM_ANONPAGES]--;
		else
		rss[MM_FILEPAGES]--;
		}
		if (unlikely(!free_swap_and_cache(entry)))
		print_bad_pte(vma, addr, ptent, NULL);
		}

Admin message