mm/slub.c: fix corrupted freechain in deactivate_slab()

The slub_debug is able to fix the corrupted slab freelist/page.
However, alloc_debug_processing() only checks the validity of current
and next freepointer during allocation path.  As a result, once some
objects have their freepointers corrupted, deactivate_slab() may lead to
page fault.

Below is from a test kernel module when 'slub_debug=PUF,kmalloc-128
slub_nomerge'.  The test kernel corrupts the freepointer of one free
object on purpose.  Unfortunately, deactivate_slab() does not detect it
when iterating the freechain.

  BUG: unable to handle page fault for address: 00000000123456f8
  #PF: supervisor read access in kernel mode
  #PF: error_code(0x0000) - not-present page
  PGD 0 P4D 0
  Oops: 0000 [#1] SMP PTI
  ... ...
  RIP: 0010:deactivate_slab.isra.92+0xed/0x490
  ... ...
  Call Trace:
   ___slab_alloc+0x536/0x570
   __slab_alloc+0x17/0x30
   __kmalloc+0x1d9/0x200
   ext4_htree_store_dirent+0x30/0xf0
   htree_dirblock_to_tree+0xcb/0x1c0
   ext4_htree_fill_tree+0x1bc/0x2d0
   ext4_readdir+0x54f/0x920
   iterate_dir+0x88/0x190
   __x64_sys_getdents+0xa6/0x140
   do_syscall_64+0x49/0x170
   entry_SYSCALL_64_after_hwframe+0x44/0xa9

Therefore, this patch adds extra consistency check in deactivate_slab().
Once an object's freepointer is corrupted, all following objects
starting at this object are isolated.

[akpm@linux-foundation.org: fix build with CONFIG_SLAB_DEBUG=n]
Signed-off-by: Dongli Zhang <dongli.zhang@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Joe Jin <joe.jin@oracle.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Link: http://lkml.kernel.org/r/20200331031450.12182-1-dongli.zhang@oracle.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/slub.c b/mm/slub.c
index b762450fc9f076841a410e8b51067d54beb569a6..6972c27ae394d7da2c8b3275f1e415e30a18576c 100644 (file)
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -679,6 +679,20 @@ static void slab_fix(struct kmem_cache *s, char *fmt, ...)
        va_end(args);
 }
 
+static bool freelist_corrupted(struct kmem_cache *s, struct page *page,
+                              void *freelist, void *nextfree)
+{
+       if ((s->flags & SLAB_CONSISTENCY_CHECKS) &&
+           !check_valid_pointer(s, page, nextfree)) {
+               object_err(s, page, freelist, "Freechain corrupt");
+               freelist = NULL;
+               slab_fix(s, "Isolate corrupted freechain");
+               return true;
+       }
+
+       return false;
+}
+
 static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
 {
        unsigned int off;       /* Offset of last byte */
@@ -1410,6 +1424,11 @@ static inline void inc_slabs_node(struct kmem_cache *s, int node,
 static inline void dec_slabs_node(struct kmem_cache *s, int node,
                                                        int objects) {}
 
+static bool freelist_corrupted(struct kmem_cache *s, struct page *page,
+                              void *freelist, void *nextfree)
+{
+       return false;
+}
 #endif /* CONFIG_SLUB_DEBUG */
 
 /*
@@ -2093,6 +2112,14 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page,
                void *prior;
                unsigned long counters;
 
+               /*
+                * If 'nextfree' is invalid, it is possible that the object at
+                * 'freelist' is already corrupted.  So isolate all objects
+                * starting at 'freelist'.
+                */
+               if (freelist_corrupted(s, page, freelist, nextfree))
+                       break;
+
                do {
                        prior = page->freelist;
                        counters = page->counters;