diff mbox series

[v3,3/9] cachefiles: fix slab-use-after-free in cachefiles_withdraw_cookie()

Message ID 20240628062930.2467993-4-libaokun@huaweicloud.com (mailing list archive)
State Accepted
Headers show
Series cachefiles: random bugfixes | expand

Commit Message

Baokun Li June 28, 2024, 6:29 a.m. UTC 
From: Baokun Li <libaokun1@huawei.com>

We got the following issue in our fault injection stress test:

==================================================================
BUG: KASAN: slab-use-after-free in cachefiles_withdraw_cookie+0x4d9/0x600
Read of size 8 at addr ffff888118efc000 by task kworker/u78:0/109

CPU: 13 PID: 109 Comm: kworker/u78:0 Not tainted 6.8.0-dirty #566
Call Trace:
 <TASK>
 kasan_report+0x93/0xc0
 cachefiles_withdraw_cookie+0x4d9/0x600
 fscache_cookie_state_machine+0x5c8/0x1230
 fscache_cookie_worker+0x91/0x1c0
 process_one_work+0x7fa/0x1800
 [...]

Allocated by task 117:
 kmalloc_trace+0x1b3/0x3c0
 cachefiles_acquire_volume+0xf3/0x9c0
 fscache_create_volume_work+0x97/0x150
 process_one_work+0x7fa/0x1800
 [...]

Freed by task 120301:
 kfree+0xf1/0x2c0
 cachefiles_withdraw_cache+0x3fa/0x920
 cachefiles_put_unbind_pincount+0x1f6/0x250
 cachefiles_daemon_release+0x13b/0x290
 __fput+0x204/0xa00
 task_work_run+0x139/0x230
 do_exit+0x87a/0x29b0
 [...]
==================================================================

Following is the process that triggers the issue:

           p1                |             p2
------------------------------------------------------------
                              fscache_begin_lookup
                               fscache_begin_volume_access
                                fscache_cache_is_live(fscache_cache)
cachefiles_daemon_release
 cachefiles_put_unbind_pincount
  cachefiles_daemon_unbind
   cachefiles_withdraw_cache
    fscache_withdraw_cache
     fscache_set_cache_state(cache, FSCACHE_CACHE_IS_WITHDRAWN);
    cachefiles_withdraw_objects(cache)
    fscache_wait_for_objects(fscache)
      atomic_read(&fscache_cache->object_count) == 0
                              fscache_perform_lookup
                               cachefiles_lookup_cookie
                                cachefiles_alloc_object
                                 refcount_set(&object->ref, 1);
                                 object->volume = volume
                                 fscache_count_object(vcookie->cache);
                                  atomic_inc(&fscache_cache->object_count)
    cachefiles_withdraw_volumes
     cachefiles_withdraw_volume
      fscache_withdraw_volume
      __cachefiles_free_volume
       kfree(cachefiles_volume)
                              fscache_cookie_state_machine
                               cachefiles_withdraw_cookie
                                cache = object->volume->cache;
                                // cachefiles_volume UAF !!!

After setting FSCACHE_CACHE_IS_WITHDRAWN, wait for all the cookie lookups
to complete first, and then wait for fscache_cache->object_count == 0 to
avoid the cookie exiting after the volume has been freed and triggering
the above issue. Therefore call fscache_withdraw_volume() before calling
cachefiles_withdraw_objects().

This way, after setting FSCACHE_CACHE_IS_WITHDRAWN, only the following two
cases will occur:
1) fscache_begin_lookup fails in fscache_begin_volume_access().
2) fscache_withdraw_volume() will ensure that fscache_count_object() has
   been executed before calling fscache_wait_for_objects().

Fixes: fe2140e2f57f ("cachefiles: Implement volume support")
Suggested-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Baokun Li <libaokun1@huawei.com>
---
 fs/cachefiles/cache.c  | 35 ++++++++++++++++++++++++++++++++++-
 fs/cachefiles/volume.c |  1 -
 2 files changed, 34 insertions(+), 2 deletions(-)
diff mbox series

Patch

diff --git a/fs/cachefiles/cache.c b/fs/cachefiles/cache.c
index 56ef519a36a0..9fb06dc16520 100644
--- a/fs/cachefiles/cache.c
+++ b/fs/cachefiles/cache.c
@@ -313,7 +313,39 @@  static void cachefiles_withdraw_objects(struct cachefiles_cache *cache)
 }
 
 /*
- * Withdraw volumes.
+ * Withdraw fscache volumes.
+ */
+static void cachefiles_withdraw_fscache_volumes(struct cachefiles_cache *cache)
+{
+	struct list_head *cur;
+	struct cachefiles_volume *volume;
+	struct fscache_volume *vcookie;
+
+	_enter("");
+retry:
+	spin_lock(&cache->object_list_lock);
+	list_for_each(cur, &cache->volumes) {
+		volume = list_entry(cur, struct cachefiles_volume, cache_link);
+
+		if (atomic_read(&volume->vcookie->n_accesses) == 0)
+			continue;
+
+		vcookie = fscache_try_get_volume(volume->vcookie,
+						 fscache_volume_get_withdraw);
+		if (vcookie) {
+			spin_unlock(&cache->object_list_lock);
+			fscache_withdraw_volume(vcookie);
+			fscache_put_volume(vcookie, fscache_volume_put_withdraw);
+			goto retry;
+		}
+	}
+	spin_unlock(&cache->object_list_lock);
+
+	_leave("");
+}
+
+/*
+ * Withdraw cachefiles volumes.
  */
 static void cachefiles_withdraw_volumes(struct cachefiles_cache *cache)
 {
@@ -381,6 +413,7 @@  void cachefiles_withdraw_cache(struct cachefiles_cache *cache)
 	pr_info("File cache on %s unregistering\n", fscache->name);
 
 	fscache_withdraw_cache(fscache);
+	cachefiles_withdraw_fscache_volumes(cache);
 
 	/* we now have to destroy all the active objects pertaining to this
 	 * cache - which we do by passing them off to thread pool to be
diff --git a/fs/cachefiles/volume.c b/fs/cachefiles/volume.c
index 89df0ba8ba5e..781aac4ef274 100644
--- a/fs/cachefiles/volume.c
+++ b/fs/cachefiles/volume.c
@@ -133,7 +133,6 @@  void cachefiles_free_volume(struct fscache_volume *vcookie)
 
 void cachefiles_withdraw_volume(struct cachefiles_volume *volume)
 {
-	fscache_withdraw_volume(volume->vcookie);
 	cachefiles_set_volume_xattr(volume);
 	__cachefiles_free_volume(volume);
 }