lib: radix-tree: check accounting of existing slot replacement users

The bug in khugepaged fixed earlier in this series shows that radix tree
slot replacement is fragile; and it will become more so when not only
NULL<->!NULL transitions need to be caught but transitions from and to
exceptional entries as well.  We need checks.

Re-implement radix_tree_replace_slot() on top of the sanity-checked
__radix_tree_replace().  This requires existing callers to also pass the
radix tree root, but it'll warn us when somebody replaces slots with
contents that need proper accounting (transitions between NULL entries,
real entries, exceptional entries) and where a replacement through the
slot pointer would corrupt the radix tree node counts.

Link: http://lkml.kernel.org/r/20161117193021.GB23430@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Suggested-by: Jan Kara <jack@suse.cz>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox <mawilcox@linuxonhyperv.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

4 files changed, 8 insertions, 7 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index caa779f8797f..1ba726aef708 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -147,7 +147,7 @@ static int page_cache_tree_insert(struct address_space *mapping,
 						      false);
 		}
 	}
-	radix_tree_replace_slot(slot, page);
+	radix_tree_replace_slot(&mapping->page_tree, slot, page);
 	mapping->nrpages++;
 	if (node) {
 		workingset_node_pages_inc(node);
@@ -196,7 +196,7 @@ static void page_cache_tree_delete(struct address_space *mapping,
 			shadow = NULL;
 		}
 
-		radix_tree_replace_slot(slot, shadow);
+		radix_tree_replace_slot(&mapping->page_tree, slot, shadow);
 
 		if (!node)
 			break;
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 5d7c006373d3..7a50c726c5ae 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1426,7 +1426,7 @@ static void collapse_shmem(struct mm_struct *mm,
 		list_add_tail(&page->lru, &pagelist);
 
 		/* Finally, replace with the new page. */
-		radix_tree_replace_slot(slot,
+		radix_tree_replace_slot(&mapping->page_tree, slot,
 				new_page + (index % HPAGE_PMD_NR));
 
 		slot = radix_tree_iter_next(&iter);
@@ -1538,7 +1538,8 @@ tree_unlocked:
 			/* Unfreeze the page. */
 			list_del(&page->lru);
 			page_ref_unfreeze(page, 2);
-			radix_tree_replace_slot(slot, page);
+			radix_tree_replace_slot(&mapping->page_tree,
+						slot, page);
 			spin_unlock_irq(&mapping->tree_lock);
 			putback_lru_page(page);
 			unlock_page(page);
diff --git a/mm/migrate.c b/mm/migrate.c
index 66ce6b490b13..0ed24b1fa77b 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -482,7 +482,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
 		SetPageDirty(newpage);
 	}
 
-	radix_tree_replace_slot(pslot, newpage);
+	radix_tree_replace_slot(&mapping->page_tree, pslot, newpage);
 
 	/*
 	 * Drop cache reference from old page by unfreezing
@@ -556,7 +556,7 @@ int migrate_huge_page_move_mapping(struct address_space *mapping,
 
 	get_page(newpage);
 
-	radix_tree_replace_slot(pslot, newpage);
+	radix_tree_replace_slot(&mapping->page_tree, pslot, newpage);
 
 	page_ref_unfreeze(page, expected_count - 1);
 
diff --git a/mm/truncate.c b/mm/truncate.c
index 8d8c62d89e6d..3c631c357873 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -49,7 +49,7 @@ static void clear_exceptional_entry(struct address_space *mapping,
 		goto unlock;
 	if (*slot != entry)
 		goto unlock;
-	radix_tree_replace_slot(slot, NULL);
+	radix_tree_replace_slot(&mapping->page_tree, slot, NULL);
 	mapping->nrexceptional--;
 	if (!node)
 		goto unlock;