Kernel/linux-next
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git synced 2024-12-28 16:52:18 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Xarray: do not return sibling entries from xas_find_marked()

Browse Source 
Patch series "Fixes and cleanups to xarray", v3.

This series contains some random fixes and cleanups to xarray. Patch 1-2
are fixes and patch 3-6 are cleanups. More details can be found in
respective patches.


This patch (of 5):

Similar to issue fixed in commit cbc0285433 ("XArray: Do not return
sibling entries from xa_load()"), we may return sibling entries from
xas_find_marked as following:

    Thread A:               Thread B:
                            xa_store_range(xa, entry, 6, 7, gfp);
			    xa_set_mark(xa, 6, mark)
    XA_STATE(xas, xa, 6);
    xas_find_marked(&xas, 7, mark);
    offset = xas_find_chunk(xas, advance, mark);
    [offset is 6 which points to a valid entry]
                            xa_store_range(xa, entry, 4, 7, gfp);
    entry = xa_entry(xa, node, 6);
    [entry is a sibling of 4]
    if (!xa_is_node(entry))
        return entry;

Skip sibling entry like xas_find() does to protect caller from seeing
sibling entry from xas_find_marked() or caller may use sibling entry as a
valid entry and crash the kernel.

Besides, load_race() test is modified to catch mentioned issue and
modified load_race() only passes after this fix is merged.

Here is an example how this bug could be triggerred in theory in nfs which
enables large folio in mapping:
Let's take a look at involved racer:
1. How pages could be created and dirtied in nfs.
write
 ksys_write
  vfs_write
   new_sync_write
    nfs_file_write
     generic_perform_write
      nfs_write_begin
       fgf_set_order
        __filemap_get_folio
      nfs_write_end
       nfs_update_folio
        nfs_writepage_setup
	 nfs_mark_request_dirty
	  filemap_dirty_folio
	   __folio_mark_dirty
	    __xa_set_mark

2. How dirty pages could be deleted in nfs.
ioctl
 do_vfs_ioctl
  file_ioctl
   ioctl_preallocate
    vfs_fallocate
     nfs42_fallocate
      nfs42_proc_deallocate
       truncate_pagecache_range
        truncate_inode_pages_range
	 truncate_inode_folio
	  filemap_remove_folio
	   page_cache_delete
	    xas_store(&xas, NULL);

3. How dirty pages could be lockless searched
sync_file_range
 ksys_sync_file_range
  __filemap_fdatawrite_range
   filemap_fdatawrite_wbc
    do_writepages
     writeback_use_writepage
      writeback_iter
       writeback_get_folio
        filemap_get_folios_tag
         find_get_entry
          folio = xas_find_marked()
          folio_try_get(folio)

In theory, kernel will crash as following:
1.Create               2.Search             3.Delete
/* write page 2,3 */
write
 ...
  nfs_write_begin
   fgf_set_order
   __filemap_get_folio
    ...
     /* index = 2, order = 1 */
     xa_store(&xas, folio)
  nfs_write_end
   ...
    __folio_mark_dirty

                       /* sync page 2 and page 3 */
                       sync_file_range
                        ...
                         find_get_entry
                          folio = xas_find_marked()
                          /* offset will be 2 */
                          offset = xas_find_chunk()

                                             /* delete page 2 and page 3 */
                                             ioctl
                                              ...
                                               xas_store(&xas, NULL);

/* write page 0-3 */
write
 ...
  nfs_write_begin
   fgf_set_order
   __filemap_get_folio
    ...
     /* index = 0, order = 2 */
     xa_store(&xas, folio)
  nfs_write_end
   ...
    __folio_mark_dirty

                          /* get sibling entry from offset 2 */
                          entry = xa_entry(.., 2)
                          /* use sibling entry as folio and crash kernel */
                          folio_try_get(folio)

Link: https://lkml.kernel.org/r/20241218154613.58754-2-shikemeng@huaweicloud.com
Link: https://lkml.kernel.org/r/20241213122523.12764-1-shikemeng@huaweicloud.com
Link: https://lkml.kernel.org/r/20241213122523.12764-2-shikemeng@huaweicloud.com
Signed-off-by: Kemeng Shi <shikemeng@huaweicloud.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This commit is contained in:
Kemeng Shi 2024-12-13 20:25:19 +08:00 committed by Andrew Morton
parent 649d7ad103
commit e6b6abc540
2 changed files with 6 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
lib/xarray.c
View File

@ -1387,6 +1387,8 @@ void *xas_find_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark)
entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset);
if (!entry && !(xa_track_free(xas->xa) && mark == XA_FREE_MARK))
continue;
if (xa_is_sibling(entry))
continue;
if (!xa_is_node(entry))
return entry;
xas->xa_node = xa_to_node(entry);

4
tools/testing/radix-tree/multiorder.c
View File

@ -227,6 +227,7 @@ static void *load_creator(void *ptr)
unsigned long index = (3 << RADIX_TREE_MAP_SHIFT) -
(1 << order);
item_insert_order(tree, index, order);
xa_set_mark(tree, index, XA_MARK_1);
item_delete_rcu(tree, index);
}
}
@ -242,8 +243,11 @@ static void *load_worker(void *ptr)
rcu_register_thread();
while (!stop_iteration) {
unsigned long find_index = (2 << RADIX_TREE_MAP_SHIFT) + 1;
struct item *item = xa_load(ptr, index);
assert(!xa_is_internal(item));
item = xa_find(ptr, &find_index, index, XA_MARK_1);
assert(!xa_is_internal(item));
}
rcu_unregister_thread();