xarray: fix index jumping backwards in xas_find()

A bug in the XArray iterator xas_find() causes the iterator's index
(xas->xa_index) to jump backwards when iterating over a multi-index entry
(like a THP) that resides in a non-leaf node and is concurrently split.

When iterating over a multi-index entry in a non-leaf node, xas_load()
sets xas->xa_offset to the base offset of the entry, but leaves
xas->xa_index at the requested index.  When the caller subsequently wants
to advance to the next entry, xas_find() is called.  xas_find() attempts
to synchronize xas->xa_offset with xas->xa_index before advancing. 
However, the fixup logic was incorrectly restricted to leaf nodes
(!xas->xa_node->shift).  Because the THP resides in a non-leaf node, the
fixup is skipped.

As a result, xas_find() simply increments xas->xa_offset and recalculates
xas->xa_index based on this new offset.  This causes xas->xa_index to jump
backwards.  If the THP was concurrently split, the entry at the new offset
is a node pointer, so xas_find() descends into it and returns the folio at
the backwards index.  The caller (filemap_map_pages()) then calculates the
PTE pointer based on this backwards index, resulting in an invalid memory
access such as an out-of-bounds read or use-after-free on a page-table
page freed via tlb_remove_table_rcu().

A userspace access that faults in a file-backed mapping can trigger this
path.  When the index moves backwards, filemap_map_pages() can calculate a
PTE outside the page locked for fault-around and dereference a freed
page-table page, resulting in a KASAN-detected use-after-free read.

To fix this, check if xas->xa_offset matches get_offset(xas->xa_index,
xas->xa_node).  If it does not and the node is a non-leaf node, set
xas->xa_offset to get_offset(xas->xa_index, xas->xa_node) before
advancing.  Also add test cases in test_xarray to verify xas_find()
behavior when iterating over and splitting multi-index entries.

Link: https://lore.kernel.org/20260904121301.200049-1-krystianmkaniewski@gmail.com
Fixes: b803b42823d0 ("xarray: Add XArray iterators")
Assisted-by: Gemini:gemini-3.7-flash syzbot
Reported-by: syzbot+b72767277f29b6407083@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=b72767277f29b6407083
Link: https://syzkaller.appspot.com/ai_job?id=a01c56bd-74d0-411c-afb4-ee6f0cb6cb61
Signed-off-by: Krystian Kaniewski <krystianmkaniewski@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: <stable@vger.kernel.org>

2 files changed, 75 insertions, 3 deletions

diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index 5ca0aefee9aa..615f7730a5bd 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -1247,6 +1247,75 @@ static noinline void check_multi_find_3(struct xarray *xa)
 	}
 }
 
+static noinline void check_multi_find_4(struct xarray *xa)
+{
+#ifdef CONFIG_XARRAY_MULTI
+	unsigned int order = XA_CHUNK_SHIFT + 1;
+	unsigned long next = 1UL << order;
+	unsigned long start = next - 1;
+	XA_STATE(xas, xa, start);
+	XA_STATE_ORDER(split, xa, 0, 0);
+	void *entry;
+	unsigned long i;
+
+	/* Multi-index entry in two slots of a non-leaf node. */
+	xa_store_order(xa, 0, order, xa_mk_index(0), GFP_KERNEL);
+	XA_BUG_ON(xa, xa_store_index(xa, next, GFP_KERNEL) != NULL);
+
+	rcu_read_lock();
+	entry = xas_find(&xas, ULONG_MAX);
+	XA_BUG_ON(xa, entry != xa_mk_index(0));
+	XA_BUG_ON(xa, xas.xa_index != start);
+
+	entry = xas_find(&xas, ULONG_MAX);
+	XA_BUG_ON(xa, entry != xa_mk_index(next));
+	XA_BUG_ON(xa, xas.xa_index != next);
+
+	entry = xas_find(&xas, ULONG_MAX);
+	XA_BUG_ON(xa, entry != NULL);
+	rcu_read_unlock();
+
+	xa_erase_index(xa, next);
+	xa_erase_index(xa, 0);
+	XA_BUG_ON(xa, !xa_empty(xa));
+
+	/* Split the multi-index entry after a lookup begins inside it. */
+	xa_store_order(xa, 0, order, xa_mk_index(0), GFP_KERNEL);
+	XA_BUG_ON(xa, xa_store_index(xa, next, GFP_KERNEL) != NULL);
+
+	xas_set(&xas, start);
+	rcu_read_lock();
+	entry = xas_find(&xas, ULONG_MAX);
+	XA_BUG_ON(xa, entry != xa_mk_index(0));
+	XA_BUG_ON(xa, xas.xa_index != start);
+	rcu_read_unlock();
+
+	xas_split_alloc(&split, xa_mk_index(0), order, GFP_KERNEL);
+	if (xas_error(&split)) {
+		XA_BUG_ON(xa, true);
+		goto out;
+	}
+	xas_lock(&split);
+	xas_split(&split, xa_mk_index(0), order);
+	for (i = 0; i < next; i++)
+		__xa_store(xa, i, xa_mk_index(i), 0);
+	xas_unlock(&split);
+
+	rcu_read_lock();
+	entry = xas_find(&xas, ULONG_MAX);
+	XA_BUG_ON(xa, entry != xa_mk_index(next));
+	XA_BUG_ON(xa, xas.xa_index != next);
+
+	entry = xas_find(&xas, ULONG_MAX);
+	XA_BUG_ON(xa, entry != NULL);
+	rcu_read_unlock();
+
+out:
+	xa_destroy(xa);
+	XA_BUG_ON(xa, !xa_empty(xa));
+#endif
+}
+
 static noinline void check_find_1(struct xarray *xa)
 {
 	unsigned long i, j, k;
@@ -1370,6 +1439,7 @@ static noinline void check_find(struct xarray *xa)
 		check_multi_find_1(xa, i);
 	check_multi_find_2(xa);
 	check_multi_find_3(xa);
+	check_multi_find_4(xa);
 }
 
 /* See find_swap_entry() in mm/shmem.c */
diff --git a/lib/xarray.c b/lib/xarray.c
index bfe7bef80f34..3913c8d6486b 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -1409,9 +1409,11 @@ void *xas_find(struct xa_state *xas, unsigned long max)
 		entry = xas_load(xas);
 		if (entry || xas_not_node(xas->xa_node))
 			return entry;
-	} else if (!xas->xa_node->shift &&
-		    xas->xa_offset != (xas->xa_index & XA_CHUNK_MASK)) {
-		xas->xa_offset = ((xas->xa_index - 1) & XA_CHUNK_MASK) + 1;
+	} else if (xas->xa_offset != get_offset(xas->xa_index, xas->xa_node)) {
+		if (!xas->xa_node->shift)
+			xas->xa_offset = ((xas->xa_index - 1) & XA_CHUNK_MASK) + 1;
+		else
+			xas->xa_offset = get_offset(xas->xa_index, xas->xa_node);
 	}
 
 	xas_next_offset(xas);