@@ -194,28 +194,30 @@ static __always_inline bool kasan_slab_pre_free(struct kmem_cache *s,
{
if (kasan_enabled())
return __kasan_slab_pre_free(s, object, _RET_IP_);
return false;
}
-bool __kasan_slab_free(struct kmem_cache *s, void *object, bool init);
+bool __kasan_slab_free(struct kmem_cache *s, void *object, bool init,
+ bool after_rcu_delay);
/**
* kasan_slab_free - Possibly handle slab object freeing.
* @object: Object to free.
*
* This hook is called from the slab allocator to give KASAN a chance to take
* ownership of the object and handle its freeing.
* kasan_slab_pre_free() must have already been called on the same object.
*
* @Return true if KASAN took ownership of the object; false otherwise.
*/
static __always_inline bool kasan_slab_free(struct kmem_cache *s,
- void *object, bool init)
+ void *object, bool init,
+ bool after_rcu_delay)
{
if (kasan_enabled())
- return __kasan_slab_free(s, object, init);
+ return __kasan_slab_free(s, object, init, after_rcu_delay);
return false;
}
void __kasan_kfree_large(void *ptr, unsigned long ip);
static __always_inline void kasan_kfree_large(void *ptr)
{
@@ -405,13 +407,14 @@ static inline void *kasan_init_slab_obj(struct kmem_cache *cache,
static inline bool kasan_slab_pre_free(struct kmem_cache *s, void *object)
{
return false;
}
-static inline bool kasan_slab_free(struct kmem_cache *s, void *object, bool init)
+static inline bool kasan_slab_free(struct kmem_cache *s, void *object,
+ bool init, bool after_rcu_delay)
{
return false;
}
static inline void kasan_kfree_large(void *ptr) {}
static inline void *kasan_slab_alloc(struct kmem_cache *s, void *object,
gfp_t flags, bool init)
@@ -67,12 +67,42 @@ config SLUB_DEBUG_ON
equivalent to specifying the "slab_debug" parameter on boot.
There is no support for more fine grained debug control like
possible with slab_debug=xxx. SLUB debugging may be switched
off in a kernel built with CONFIG_SLUB_DEBUG_ON by specifying
"slab_debug=-".
+config SLUB_RCU_DEBUG
+ bool "Enable UAF detection in TYPESAFE_BY_RCU caches (for KASAN)"
+ depends on SLUB_DEBUG
+ depends on KASAN # not a real dependency; currently useless without KASAN
+ default KASAN_GENERIC || KASAN_SW_TAGS
+ help
+ Make SLAB_TYPESAFE_BY_RCU caches behave approximately as if the cache
+ was not marked as SLAB_TYPESAFE_BY_RCU and every caller used
+ kfree_rcu() instead.
+
+ This is intended for use in combination with KASAN, to enable KASAN to
+ detect use-after-free accesses in such caches.
+ (KFENCE is able to do that independent of this flag.)
+
+ This might degrade performance.
+ Unfortunately this also prevents a very specific bug pattern from
+ triggering (insufficient checks against an object being recycled
+ within the RCU grace period); so this option can be turned off even on
+ KASAN builds, in case you want to test for such a bug.
+
+ If you're using this for testing bugs / fuzzing and care about
+ catching all the bugs WAY more than performance, you might want to
+ also turn on CONFIG_RCU_STRICT_GRACE_PERIOD.
+
+ WARNING:
+ This is designed as a debugging feature, not a security feature.
+ Objects are sometimes recycled without RCU delay under memory pressure.
+
+ If unsure, say N.
+
config PAGE_OWNER
bool "Track page owner"
depends on DEBUG_KERNEL && STACKTRACE_SUPPORT
select DEBUG_FS
select STACKTRACE
select STACKDEPOT
@@ -227,43 +227,44 @@ static bool check_slab_allocation(struct kmem_cache *cache, void *object,
}
return false;
}
static inline void poison_slab_object(struct kmem_cache *cache, void *object,
- bool init)
+ bool init, bool after_rcu_delay)
{
void *tagged_object = object;
object = kasan_reset_tag(object);
/* RCU slabs could be legally used after free within the RCU period. */
- if (unlikely(cache->flags & SLAB_TYPESAFE_BY_RCU))
+ if (unlikely(cache->flags & SLAB_TYPESAFE_BY_RCU) && !after_rcu_delay)
return;
kasan_poison(object, round_up(cache->object_size, KASAN_GRANULE_SIZE),
KASAN_SLAB_FREE, init);
if (kasan_stack_collection_enabled())
kasan_save_free_info(cache, tagged_object);
}
bool __kasan_slab_pre_free(struct kmem_cache *cache, void *object,
unsigned long ip)
{
if (!kasan_arch_is_ready() || is_kfence_address(object))
return false;
return check_slab_allocation(cache, object, ip);
}
-bool __kasan_slab_free(struct kmem_cache *cache, void *object, bool init)
+bool __kasan_slab_free(struct kmem_cache *cache, void *object, bool init,
+ bool after_rcu_delay)
{
if (!kasan_arch_is_ready() || is_kfence_address(object))
return false;
- poison_slab_object(cache, object, init);
+ poison_slab_object(cache, object, init, after_rcu_delay);
/*
* If the object is put into quarantine, do not let slab put the object
* onto the freelist for now. The object's metadata is kept until the
* object gets evicted from quarantine.
*/
@@ -517,13 +518,13 @@ bool __kasan_mempool_poison_object(void *ptr, unsigned long ip)
slab = folio_slab(folio);
if (check_slab_allocation(slab->slab_cache, ptr, ip))
return false;
- poison_slab_object(slab->slab_cache, ptr, false);
+ poison_slab_object(slab->slab_cache, ptr, false, false);
return true;
}
void __kasan_mempool_unpoison_object(void *ptr, size_t size, unsigned long ip)
{
struct slab *slab;
@@ -993,12 +993,57 @@ static void kmem_cache_invalid_free(struct kunit *test)
*/
kmem_cache_free(cache, p);
kmem_cache_destroy(cache);
}
+static void kmem_cache_rcu_uaf(struct kunit *test)
+{
+ char *p;
+ size_t size = 200;
+ struct kmem_cache *cache;
+
+ KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_SLUB_RCU_DEBUG);
+
+ cache = kmem_cache_create("test_cache", size, 0, SLAB_TYPESAFE_BY_RCU,
+ NULL);
+ KUNIT_ASSERT_NOT_ERR_OR_NULL(test, cache);
+
+ p = kmem_cache_alloc(cache, GFP_KERNEL);
+ if (!p) {
+ kunit_err(test, "Allocation failed: %s\n", __func__);
+ kmem_cache_destroy(cache);
+ return;
+ }
+ *p = 1;
+
+ rcu_read_lock();
+
+ /* Free the object - this will internally schedule an RCU callback. */
+ kmem_cache_free(cache, p);
+
+ /*
+ * We should still be allowed to access the object at this point because
+ * the cache is SLAB_TYPESAFE_BY_RCU and we've been in an RCU read-side
+ * critical section since before the kmem_cache_free().
+ */
+ READ_ONCE(*p);
+
+ rcu_read_unlock();
+
+ /*
+ * Wait for the RCU callback to execute; after this, the object should
+ * have actually been freed from KASAN's perspective.
+ */
+ rcu_barrier();
+
+ KUNIT_EXPECT_KASAN_FAIL(test, READ_ONCE(*p));
+
+ kmem_cache_destroy(cache);
+}
+
static void empty_cache_ctor(void *object) { }
static void kmem_cache_double_destroy(struct kunit *test)
{
struct kmem_cache *cache;
@@ -1934,12 +1979,13 @@ static struct kunit_case kasan_kunit_test_cases[] = {
KUNIT_CASE(workqueue_uaf),
KUNIT_CASE(kfree_via_page),
KUNIT_CASE(kfree_via_phys),
KUNIT_CASE(kmem_cache_oob),
KUNIT_CASE(kmem_cache_double_free),
KUNIT_CASE(kmem_cache_invalid_free),
+ KUNIT_CASE(kmem_cache_rcu_uaf),
KUNIT_CASE(kmem_cache_double_destroy),
KUNIT_CASE(kmem_cache_accounted),
KUNIT_CASE(kmem_cache_bulk),
KUNIT_CASE(mempool_kmalloc_oob_right),
KUNIT_CASE(mempool_kmalloc_large_oob_right),
KUNIT_CASE(mempool_slab_oob_right),
@@ -447,12 +447,24 @@ static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work)
kmem_cache_release(s);
}
}
static int shutdown_cache(struct kmem_cache *s)
{
+ if (IS_ENABLED(CONFIG_SLUB_RCU_DEBUG) &&
+ (s->flags & SLAB_TYPESAFE_BY_RCU)) {
+ /*
+ * Under CONFIG_SLUB_RCU_DEBUG, when objects in a
+ * SLAB_TYPESAFE_BY_RCU slab are freed, SLUB will internally
+ * defer their freeing with call_rcu().
+ * Wait for such call_rcu() invocations here before actually
+ * destroying the cache.
+ */
+ rcu_barrier();
+ }
+
/* free asan quarantined objects */
kasan_cache_shutdown(s);
if (__kmem_cache_shutdown(s) != 0)
return -EBUSY;
@@ -2141,45 +2141,78 @@ static inline bool memcg_slab_post_alloc_hook(struct kmem_cache *s,
static inline void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab,
void **p, int objects)
{
}
#endif /* CONFIG_MEMCG_KMEM */
+#ifdef CONFIG_SLUB_RCU_DEBUG
+static void slab_free_after_rcu_debug(struct rcu_head *rcu_head);
+
+struct rcu_delayed_free {
+ struct rcu_head head;
+ void *object;
+};
+#endif
+
/*
* Hooks for other subsystems that check memory allocations. In a typical
* production configuration these hooks all should produce no code at all.
*
* Returns true if freeing of the object can proceed, false if its reuse
- * was delayed by KASAN quarantine, or it was returned to KFENCE.
+ * was delayed by CONFIG_SLUB_RCU_DEBUG or KASAN quarantine, or it was returned
+ * to KFENCE.
*/
static __always_inline
-bool slab_free_hook(struct kmem_cache *s, void *x, bool init)
+bool slab_free_hook(struct kmem_cache *s, void *x, bool init,
+ bool after_rcu_delay)
{
kmemleak_free_recursive(x, s->flags);
kmsan_slab_free(s, x);
debug_check_no_locks_freed(x, s->object_size);
if (!(s->flags & SLAB_DEBUG_OBJECTS))
debug_check_no_obj_freed(x, s->object_size);
/* Use KCSAN to help debug racy use-after-free. */
- if (!(s->flags & SLAB_TYPESAFE_BY_RCU))
+ if (!(s->flags & SLAB_TYPESAFE_BY_RCU) || after_rcu_delay)
__kcsan_check_access(x, s->object_size,
KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ASSERT);
if (kfence_free(x))
return false;
/*
* Give KASAN a chance to notice an invalid free operation before we
* modify the object.
*/
if (kasan_slab_pre_free(s, x))
return false;
+#ifdef CONFIG_SLUB_RCU_DEBUG
+ if ((s->flags & SLAB_TYPESAFE_BY_RCU) && !after_rcu_delay) {
+ struct rcu_delayed_free *delayed_free;
+
+ delayed_free = kmalloc(sizeof(*delayed_free), GFP_NOWAIT);
+ if (delayed_free) {
+ /*
+ * Let KASAN track our call stack as a "related work
+ * creation", just like if the object had been freed
+ * normally via kfree_rcu().
+ * We have to do this manually because the rcu_head is
+ * not located inside the object.
+ */
+ kasan_record_aux_stack_noalloc(x);
+
+ delayed_free->object = x;
+ call_rcu(&delayed_free->head, slab_free_after_rcu_debug);
+ return false;
+ }
+ }
+#endif /* CONFIG_SLUB_RCU_DEBUG */
+
/*
* As memory initialization might be integrated into KASAN,
* kasan_slab_free and initialization memset's must be
* kept together to avoid discrepancies in behavior.
*
* The initialization memset's clear the object and the metadata,
@@ -2197,42 +2230,42 @@ bool slab_free_hook(struct kmem_cache *s, void *x, bool init)
memset(kasan_reset_tag(x), 0, s->object_size);
rsize = (s->flags & SLAB_RED_ZONE) ? s->red_left_pad : 0;
memset((char *)kasan_reset_tag(x) + inuse, 0,
s->size - inuse - rsize);
}
/* KASAN might put x into memory quarantine, delaying its reuse. */
- return !kasan_slab_free(s, x, init);
+ return !kasan_slab_free(s, x, init, after_rcu_delay);
}
static __fastpath_inline
bool slab_free_freelist_hook(struct kmem_cache *s, void **head, void **tail,
int *cnt)
{
void *object;
void *next = *head;
void *old_tail = *tail;
bool init;
if (is_kfence_address(next)) {
- slab_free_hook(s, next, false);
+ slab_free_hook(s, next, false, false);
return false;
}
/* Head and tail of the reconstructed freelist */
*head = NULL;
*tail = NULL;
init = slab_want_init_on_free(s);
do {
object = next;
next = get_freepointer(s, object);
/* If object's reuse doesn't have to be delayed */
- if (likely(slab_free_hook(s, object, init))) {
+ if (likely(slab_free_hook(s, object, init, false))) {
/* Move object to the new freelist */
set_freepointer(s, object, *head);
*head = object;
if (!*tail)
*tail = object;
} else {
@@ -4439,40 +4472,67 @@ static __fastpath_inline
void slab_free(struct kmem_cache *s, struct slab *slab, void *object,
unsigned long addr)
{
memcg_slab_free_hook(s, slab, &object, 1);
alloc_tagging_slab_free_hook(s, slab, &object, 1);
- if (likely(slab_free_hook(s, object, slab_want_init_on_free(s))))
+ if (likely(slab_free_hook(s, object, slab_want_init_on_free(s), false)))
do_slab_free(s, slab, object, object, 1, addr);
}
#ifdef CONFIG_MEMCG_KMEM
/* Do not inline the rare memcg charging failed path into the allocation path */
static noinline
void memcg_alloc_abort_single(struct kmem_cache *s, void *object)
{
- if (likely(slab_free_hook(s, object, slab_want_init_on_free(s))))
+ if (likely(slab_free_hook(s, object, slab_want_init_on_free(s), false)))
do_slab_free(s, virt_to_slab(object), object, object, 1, _RET_IP_);
}
#endif
static __fastpath_inline
void slab_free_bulk(struct kmem_cache *s, struct slab *slab, void *head,
void *tail, void **p, int cnt, unsigned long addr)
{
memcg_slab_free_hook(s, slab, p, cnt);
alloc_tagging_slab_free_hook(s, slab, p, cnt);
/*
* With KASAN enabled slab_free_freelist_hook modifies the freelist
* to remove objects, whose reuse must be delayed.
*/
if (likely(slab_free_freelist_hook(s, &head, &tail, &cnt)))
do_slab_free(s, slab, head, tail, cnt, addr);
}
+#ifdef CONFIG_SLUB_RCU_DEBUG
+static void slab_free_after_rcu_debug(struct rcu_head *rcu_head)
+{
+ struct rcu_delayed_free *delayed_free =
+ container_of(rcu_head, struct rcu_delayed_free, head);
+ void *object = delayed_free->object;
+ struct slab *slab = virt_to_slab(object);
+ struct kmem_cache *s;
+
+ if (WARN_ON(is_kfence_address(rcu_head)))
+ return;
+
+ /* find the object and the cache again */
+ if (WARN_ON(!slab))
+ return;
+ s = slab->slab_cache;
+ if (WARN_ON(!(s->flags & SLAB_TYPESAFE_BY_RCU)))
+ return;
+
+ /* resume freeing */
+ if (!slab_free_hook(s, object, slab_want_init_on_free(s), true))
+ return;
+ do_slab_free(s, slab, object, object, 1, _THIS_IP_);
+ kfree(delayed_free);
+}
+#endif /* CONFIG_SLUB_RCU_DEBUG */
+
#ifdef CONFIG_KASAN_GENERIC
void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr)
{
do_slab_free(cache, virt_to_slab(x), x, x, 1, addr);
}
#endif
Currently, KASAN is unable to catch use-after-free in SLAB_TYPESAFE_BY_RCU slabs because use-after-free is allowed within the RCU grace period by design. Add a SLUB debugging feature which RCU-delays every individual kmem_cache_free() before either actually freeing the object or handing it off to KASAN, and change KASAN to poison freed objects as normal when this option is enabled. For now I've configured Kconfig.debug to default-enable this feature in the KASAN GENERIC and SW_TAGS modes; I'm not enabling it by default in HW_TAGS mode because I'm not sure if it might have unwanted performance degradation effects there. Note that this is mostly useful with KASAN in the quarantine-based GENERIC mode; SLAB_TYPESAFE_BY_RCU slabs are basically always also slabs with a ->ctor, and KASAN's assign_tag() currently has to assign fixed tags for those, reducing the effectiveness of SW_TAGS/HW_TAGS mode. (A possible future extension of this work would be to also let SLUB call the ->ctor() on every allocation instead of only when the slab page is allocated; then tag-based modes would be able to assign new tags on every reallocation.) Signed-off-by: Jann Horn <jannh@google.com> --- include/linux/kasan.h | 11 +++++--- mm/Kconfig.debug | 30 ++++++++++++++++++++ mm/kasan/common.c | 11 ++++---- mm/kasan/kasan_test.c | 46 +++++++++++++++++++++++++++++++ mm/slab_common.c | 12 ++++++++ mm/slub.c | 76 +++++++++++++++++++++++++++++++++++++++++++++------ 6 files changed, 169 insertions(+), 17 deletions(-)