mm: fix swapin race condition

commit 4969c1192d15afa3389e7ae3302096ff684ba655 upstream.

The pte_same check is reliable only if the swap entry remains pinned (by
the page lock on swapcache).  We've also to ensure the swapcache isn't
removed before we take the lock as try_to_free_swap won't care about the
page pin.

One of the possible impacts of this patch is that a KSM-shared page can
point to the anon_vma of another process, which could exit before the page
is freed.

This can leave a page with a pointer to a recycled anon_vma object, or
worse, a pointer to something that is no longer an anon_vma.

[Backport to 2.6.35.5 (anon_vma instead of anon_vma->root in ksm.h) by Hugh]

[riel@redhat.com: changelog help]
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Hugh Dickins <hughd@google.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

2 files changed, 34 insertions, 8 deletions

diff --git a/mm/ksm.c b/mm/ksm.c
index 6c3e99b4ae7c..17ee9df378ca 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1523,8 +1523,6 @@ struct page *ksm_does_need_to_copy(struct page *page,
 {
 	struct page *new_page;
 
-	unlock_page(page);	/* any racers will COW it, not modify it */
-
 	new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
 	if (new_page) {
 		copy_user_highpage(new_page, page, address, vma);
@@ -1540,7 +1538,6 @@ struct page *ksm_does_need_to_copy(struct page *page,
 			add_page_to_unevictable_list(new_page);
 	}
 
-	page_cache_release(page);
 	return new_page;
 }
 
diff --git a/mm/memory.c b/mm/memory.c
index 53cf85d44449..608420344784 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2626,7 +2626,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		unsigned int flags, pte_t orig_pte)
 {
 	spinlock_t *ptl;
-	struct page *page;
+	struct page *page, *swapcache = NULL;
 	swp_entry_t entry;
 	pte_t pte;
 	struct mem_cgroup *ptr = NULL;
@@ -2681,10 +2681,23 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	lock_page(page);
 	delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
 
-	page = ksm_might_need_to_copy(page, vma, address);
-	if (!page) {
-		ret = VM_FAULT_OOM;
-		goto out;
+	/*
+	 * Make sure try_to_free_swap didn't release the swapcache
+	 * from under us. The page pin isn't enough to prevent that.
+	 */
+	if (unlikely(!PageSwapCache(page)))
+		goto out_page;
+
+	if (ksm_might_need_to_copy(page, vma, address)) {
+		swapcache = page;
+		page = ksm_does_need_to_copy(page, vma, address);
+
+		if (unlikely(!page)) {
+			ret = VM_FAULT_OOM;
+			page = swapcache;
+			swapcache = NULL;
+			goto out_page;
+		}
 	}
 
 	if (mem_cgroup_try_charge_swapin(mm, page, GFP_KERNEL, &ptr)) {
@@ -2735,6 +2748,18 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page))
 		try_to_free_swap(page);
 	unlock_page(page);
+	if (swapcache) {
+		/*
+		 * Hold the lock to avoid the swap entry to be reused
+		 * until we take the PT lock for the pte_same() check
+		 * (to avoid false positives from pte_same). For
+		 * further safety release the lock after the swap_free
+		 * so that the swap count won't change under a
+		 * parallel locked swapcache.
+		 */
+		unlock_page(swapcache);
+		page_cache_release(swapcache);
+	}
 
 	if (flags & FAULT_FLAG_WRITE) {
 		ret |= do_wp_page(mm, vma, address, page_table, pmd, ptl, pte);
@@ -2756,6 +2781,10 @@ out_page:
 	unlock_page(page);
 out_release:
 	page_cache_release(page);
+	if (swapcache) {
+		unlock_page(swapcache);
+		page_cache_release(swapcache);
+	}
 	return ret;
 }