slub: Introduce CONFIG_SLUB_RCU_DEBUG

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.)

Tested-by: syzbot+263726e59eab6b442723@syzkaller.appspotmail.com
Reviewed-by: Andrey Konovalov <andreyknvl@gmail.com>
Acked-by: Marco Elver <elver@google.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz> #slab
Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>

6 files changed, 182 insertions, 19 deletions

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 1570c7191176..00a3bf7c0d8f 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -196,15 +196,18 @@ static __always_inline bool kasan_slab_pre_free(struct kmem_cache *s,
 	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 still_accessible);
 /**
  * kasan_slab_free - Poison, initialize, and quarantine a slab object.
  * @object: Object to be freed.
  * @init: Whether to initialize the object.
+ * @still_accessible: Whether the object contents are still accessible.
  *
  * This function informs that a slab object has been freed and is not
- * supposed to be accessed anymore, except for objects in
- * SLAB_TYPESAFE_BY_RCU caches.
+ * supposed to be accessed anymore, except when @still_accessible is set
+ * (indicating that the object is in a SLAB_TYPESAFE_BY_RCU cache and an RCU
+ * grace period might not have passed yet).
  *
  * For KASAN modes that have integrated memory initialization
  * (kasan_has_integrated_init() == true), this function also initializes
@@ -220,10 +223,11 @@ bool __kasan_slab_free(struct kmem_cache *s, void *object, bool init);
  * @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 still_accessible)
 {
 	if (kasan_enabled())
-		return __kasan_slab_free(s, object, init);
+		return __kasan_slab_free(s, object, init, still_accessible);
 	return false;
 }
 
@@ -419,7 +423,8 @@ 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 still_accessible)
 {
 	return false;
 }
diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug
index afc72fde0f03..41a58536531d 100644
--- a/mm/Kconfig.debug
+++ b/mm/Kconfig.debug
@@ -70,6 +70,38 @@ config SLUB_DEBUG_ON
 	  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
+	# SLUB_RCU_DEBUG should build fine without KASAN, but is currently useless
+	# without KASAN, so mark it as a dependency of KASAN for now.
+	depends on 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
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index f26bbc087b3b..ed4873e18c75 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -230,14 +230,14 @@ static bool check_slab_allocation(struct kmem_cache *cache, void *object,
 }
 
 static inline void poison_slab_object(struct kmem_cache *cache, void *object,
-				      bool init)
+				      bool init, bool still_accessible)
 {
 	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(still_accessible))
 		return;
 
 	kasan_poison(object, round_up(cache->object_size, KASAN_GRANULE_SIZE),
@@ -255,12 +255,13 @@ bool __kasan_slab_pre_free(struct kmem_cache *cache, void *object,
 	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 still_accessible)
 {
 	if (!kasan_arch_is_ready() || is_kfence_address(object))
 		return false;
 
-	poison_slab_object(cache, object, init);
+	poison_slab_object(cache, object, init, still_accessible);
 
 	/*
 	 * If the object is put into quarantine, do not let slab put the object
@@ -518,7 +519,7 @@ bool __kasan_mempool_poison_object(void *ptr, unsigned long ip)
 	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;
 }
 
diff --git a/mm/kasan/kasan_test.c b/mm/kasan/kasan_test.c
index 7b32be2a3cf0..567d33b493e2 100644
--- a/mm/kasan/kasan_test.c
+++ b/mm/kasan/kasan_test.c
@@ -996,6 +996,51 @@ static void kmem_cache_invalid_free(struct kunit *test)
 	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)
@@ -1937,6 +1982,7 @@ static struct kunit_case kasan_kunit_test_cases[] = {
 	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),
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 1a2873293f5d..884e8e70a56d 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -511,6 +511,22 @@ void kmem_cache_destroy(struct kmem_cache *s)
 	/* in-flight kfree_rcu()'s may include objects from our cache */
 	kvfree_rcu_barrier();
 
+	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.
+		 *
+		 * It doesn't matter that we haven't looked at the slab refcount
+		 * yet - slabs with SLAB_TYPESAFE_BY_RCU can't be merged, so
+		 * the refcount should be 1 here.
+		 */
+		rcu_barrier();
+	}
+
 	cpus_read_lock();
 	mutex_lock(&slab_mutex);
 
diff --git a/mm/slub.c b/mm/slub.c
index 4946488cb5a7..95977f25a760 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2200,16 +2200,30 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab,
 }
 #endif /* CONFIG_MEMCG */
 
+#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)
 {
+	/* Are the object contents still accessible? */
+	bool still_accessible = (s->flags & SLAB_TYPESAFE_BY_RCU) && !after_rcu_delay;
+
 	kmemleak_free_recursive(x, s->flags);
 	kmsan_slab_free(s, x);
 
@@ -2219,7 +2233,7 @@ bool slab_free_hook(struct kmem_cache *s, void *x, bool init)
 		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 (!still_accessible)
 		__kcsan_check_access(x, s->object_size,
 				     KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ASSERT);
 
@@ -2233,6 +2247,28 @@ bool slab_free_hook(struct kmem_cache *s, void *x, bool init)
 	if (kasan_slab_pre_free(s, x))
 		return false;
 
+#ifdef CONFIG_SLUB_RCU_DEBUG
+	if (still_accessible) {
+		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
@@ -2256,7 +2292,7 @@ bool slab_free_hook(struct kmem_cache *s, void *x, bool init)
 		       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, still_accessible);
 }
 
 static __fastpath_inline
@@ -2270,7 +2306,7 @@ bool slab_free_freelist_hook(struct kmem_cache *s, void **head, void **tail,
 	bool init;
 
 	if (is_kfence_address(next)) {
-		slab_free_hook(s, next, false);
+		slab_free_hook(s, next, false, false);
 		return false;
 	}
 
@@ -2285,7 +2321,7 @@ bool slab_free_freelist_hook(struct kmem_cache *s, void **head, void **tail,
 		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;
@@ -4477,7 +4513,7 @@ void slab_free(struct kmem_cache *s, struct slab *slab, void *object,
 	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);
 }
 
@@ -4486,7 +4522,7 @@ void slab_free(struct kmem_cache *s, struct slab *slab, void *object,
 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
@@ -4505,6 +4541,33 @@ void slab_free_bulk(struct kmem_cache *s, struct slab *slab, void *head,
 		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;
+
+	kfree(delayed_free);
+
+	if (WARN_ON(is_kfence_address(object)))
+		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))
+		do_slab_free(s, slab, object, object, 1, _THIS_IP_);
+}
+#endif /* CONFIG_SLUB_RCU_DEBUG */
+
 #ifdef CONFIG_KASAN_GENERIC
 void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr)
 {