userfaultfd: remap_pages: rmap preparation

As far as the rmap code is concerned, rmap_pages only alters the
page->mapping and page->index. It does it while holding the page
lock. However there are a few places that in presence of anon pages
are allowed to do rmap walks without the page lock (split_huge_page
and page_referenced_anon). Those places that are doing rmap walks
without taking the page lock first, must be updated to re-check that
the page->mapping didn't change after they obtained the anon_vma
lock. remap_pages takes the anon_vma lock for writing before altering
the page->mapping, so if the page->mapping is still the same after
obtaining the anon_vma lock (without the page lock), the rmap walks
can go ahead safely (and remap_pages will wait them to complete before
proceeding).

remap_pages serializes against itself with the page lock.

All other places taking the anon_vma lock while holding the mmap_sem
for writing, don't need to check if the page->mapping has changed
after taking the anon_vma lock, regardless of the page lock, because
remap_pages holds the mmap_sem for reading.

There's one constraint enforced to allow this simplification: the
source pages passed to remap_pages must be mapped only in one vma, but
this is not a limitation when used to handle userland page faults. The
source addresses passed to remap_pages should be set as VM_DONTCOPY
with MADV_DONTFORK to avoid any risk of the mapcount of the pages
increasing, if fork runs in parallel in another thread, before or
while remap_pages runs.

mm/huge_memory.c

@@ -1915,6 +1915,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 {
 	struct anon_vma *anon_vma;
 	int ret = 1;
+	struct address_space *mapping;
 
 	BUG_ON(is_huge_zero_page(page));
 	BUG_ON(!PageAnon(page));
@@ -1926,10 +1927,24 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	 * page_lock_anon_vma_read except the write lock is taken to serialise
 	 * against parallel split or collapse operations.
 	 */
-	anon_vma = page_get_anon_vma(page);
-	if (!anon_vma)
-		goto out;
-	anon_vma_lock_write(anon_vma);
+	for (;;) {
+		mapping = ACCESS_ONCE(page->mapping);
+		anon_vma = page_get_anon_vma(page);
+		if (!anon_vma)
+			goto out;
+		anon_vma_lock_write(anon_vma);
+		/*
+		 * We don't hold the page lock here so
+		 * remap_pages_huge_pmd can change the anon_vma from
+		 * under us until we obtain the anon_vma lock. Verify
+		 * that we obtained the anon_vma lock before
+		 * remap_pages did.
+		 */
+		if (likely(mapping == ACCESS_ONCE(page->mapping)))
+			break;
+		anon_vma_unlock_write(anon_vma);
+		put_anon_vma(anon_vma);
+	}
 
 	ret = 0;
 	if (!PageCompound(page))

mm/rmap.c

@@ -499,6 +499,7 @@ struct anon_vma *page_lock_anon_vma_read(struct page *page)
 	struct anon_vma *root_anon_vma;
 	unsigned long anon_mapping;
 
+repeat:
 	rcu_read_lock();
 	anon_mapping = (unsigned long)READ_ONCE(page->mapping);
 	if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
@@ -537,6 +538,14 @@ struct anon_vma *page_lock_anon_vma_read(struct page *page)
 	rcu_read_unlock();
 	anon_vma_lock_read(anon_vma);
 
+	/* check if remap_anon_pages changed the anon_vma */
+	if (unlikely((unsigned long) ACCESS_ONCE(page->mapping) != anon_mapping)) {
+		anon_vma_unlock_read(anon_vma);
+		put_anon_vma(anon_vma);
+		anon_vma = NULL;
+		goto repeat;
+	}
+
 	if (atomic_dec_and_test(&anon_vma->refcount)) {
 		/*
 		 * Oops, we held the last refcount, release the lock