ksm: rmap_walk to remove_migation_ptes

A side-effect of making ksm pages swappable is that they have to be placed
on the LRUs: which then exposes them to isolate_lru_page() and hence to
page migration.

Add rmap_walk() for remove_migration_ptes() to use: rmap_walk_anon() and
rmap_walk_file() in rmap.c, but rmap_walk_ksm() in ksm.c.  Perhaps some
consolidation with existing code is possible, but don't attempt that yet
(try_to_unmap needs to handle nonlinears, but migration pte removal does
not).

rmap_walk() is sadly less general than it appears: rmap_walk_anon(), like
remove_anon_migration_ptes() which it replaces, avoids calling
page_lock_anon_vma(), because that includes a page_mapped() test which
fails when all migration ptes are in place.  That was valid when NUMA page
migration was introduced (holding mmap_sem provided the missing guarantee
that anon_vma's slab had not already been destroyed), but I believe not
valid in the memory hotremove case added since.

For now do the same as before, and consider the best way to fix that
unlikely race later on.  When fixed, we can probably use rmap_walk() on
hwpoisoned ksm pages too: for now, they remain among hwpoison's various
exceptions (its PageKsm test comes before the page is locked, but its
page_lock_anon_vma fails safely if an anon gets upgraded).

Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Izik Eidus <ieidus@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Chris Wright <chrisw@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 79 insertions, 0 deletions

diff --git a/mm/rmap.c b/mm/rmap.c
index 2e38e9048327..c81bedd7d527 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1203,3 +1203,82 @@ int try_to_munlock(struct page *page)
 	else
 		return try_to_unmap_file(page, TTU_MUNLOCK);
 }
+
+#ifdef CONFIG_MIGRATION
+/*
+ * rmap_walk() and its helpers rmap_walk_anon() and rmap_walk_file():
+ * Called by migrate.c to remove migration ptes, but might be used more later.
+ */
+static int rmap_walk_anon(struct page *page, int (*rmap_one)(struct page *,
+		struct vm_area_struct *, unsigned long, void *), void *arg)
+{
+	struct anon_vma *anon_vma;
+	struct vm_area_struct *vma;
+	int ret = SWAP_AGAIN;
+
+	/*
+	 * Note: remove_migration_ptes() cannot use page_lock_anon_vma()
+	 * because that depends on page_mapped(); but not all its usages
+	 * are holding mmap_sem, which also gave the necessary guarantee
+	 * (that this anon_vma's slab has not already been destroyed).
+	 * This needs to be reviewed later: avoiding page_lock_anon_vma()
+	 * is risky, and currently limits the usefulness of rmap_walk().
+	 */
+	anon_vma = page_anon_vma(page);
+	if (!anon_vma)
+		return ret;
+	spin_lock(&anon_vma->lock);
+	list_for_each_entry(vma, &anon_vma->head, anon_vma_node) {
+		unsigned long address = vma_address(page, vma);
+		if (address == -EFAULT)
+			continue;
+		ret = rmap_one(page, vma, address, arg);
+		if (ret != SWAP_AGAIN)
+			break;
+	}
+	spin_unlock(&anon_vma->lock);
+	return ret;
+}
+
+static int rmap_walk_file(struct page *page, int (*rmap_one)(struct page *,
+		struct vm_area_struct *, unsigned long, void *), void *arg)
+{
+	struct address_space *mapping = page->mapping;
+	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+	struct vm_area_struct *vma;
+	struct prio_tree_iter iter;
+	int ret = SWAP_AGAIN;
+
+	if (!mapping)
+		return ret;
+	spin_lock(&mapping->i_mmap_lock);
+	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
+		unsigned long address = vma_address(page, vma);
+		if (address == -EFAULT)
+			continue;
+		ret = rmap_one(page, vma, address, arg);
+		if (ret != SWAP_AGAIN)
+			break;
+	}
+	/*
+	 * No nonlinear handling: being always shared, nonlinear vmas
+	 * never contain migration ptes.  Decide what to do about this
+	 * limitation to linear when we need rmap_walk() on nonlinear.
+	 */
+	spin_unlock(&mapping->i_mmap_lock);
+	return ret;
+}
+
+int rmap_walk(struct page *page, int (*rmap_one)(struct page *,
+		struct vm_area_struct *, unsigned long, void *), void *arg)
+{
+	VM_BUG_ON(!PageLocked(page));
+
+	if (unlikely(PageKsm(page)))
+		return rmap_walk_ksm(page, rmap_one, arg);
+	else if (PageAnon(page))
+		return rmap_walk_anon(page, rmap_one, arg);
+	else
+		return rmap_walk_file(page, rmap_one, arg);
+}
+#endif /* CONFIG_MIGRATION */