slab updates for 6.6

-----BEGIN PGP SIGNATURE-----
 
 iQEzBAABCAAdFiEEe7vIQRWZI0iWSE3xu+CwddJFiJoFAmTtvVUACgkQu+CwddJF
 iJou7Qf/ZY1TB8AFejTkArNa24Nvtp6yzgfdKpCdt4JkUDBJ5OFgKdE7wHYFqsOK
 Ml3s2L6/k97G0jkHZi/Wx0akv4GsMqWjJm2l+Oqjbf5GjwcTkuq6VEzlUrF2Febx
 MlzC8teLYtqkL/qDajUH80NdizlhdiyuQE+jM0qVg9K68ZS2w6Ky2GT7GHzgPELP
 3gQvkY6bjTwm6wVKV1Ou6xMnuMFFwpdI8Fsq8pon6NplktjG/2kvyLEDSdj/qk6Y
 PhDdYBupFfXqUdlY0FxCOqPo9LY/shSiYamGfGKsdJ7wBsIiR8DcmJMrbYSwy4a9
 ZQgtRv4Pxe0R2mH6Cj0oFbFzI/qIWw==
 =zBvx
 -----END PGP SIGNATURE-----

Merge tag 'slab-for-6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/vbabka/slab

Pull slab updates from Vlastimil Babka:
 "This happens to be a small one (due to summer I guess), and all
  hardening related:

   - Randomized kmalloc caches, by GONG, Ruiqi.

     A new opt-in hardening feature to make heap spraying harder. It
     creates multiple (16) copies of kmalloc caches, reducing the chance
     of an attacker-controllable allocation site to land in the same
     slab as e.g. an allocation site with use-after-free vulnerability.

     The selection of the copy is derived from the allocation site
     address, including a per-boot random seed.

   - Stronger typing for hardened freelists in SLUB, by Jann Horn

     Introduces a custom type for hardened freelist entries instead of
     "void *" as those are not directly dereferencable. While reviewing
     this, I've noticed opportunities for further cleanups in that code
     and added those on top"

* tag 'slab-for-6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/vbabka/slab:
  Randomized slab caches for kmalloc()
  mm/slub: remove freelist_dereference()
  mm/slub: remove redundant kasan_reset_tag() from freelist_ptr calculations
  mm/slub: refactor freelist to use custom type

include/linux/percpu.h

@@ -35,6 +35,12 @@
 #define PCPU_BITMAP_BLOCK_BITS		(PCPU_BITMAP_BLOCK_SIZE >>	\
 					 PCPU_MIN_ALLOC_SHIFT)
 
+#ifdef CONFIG_RANDOM_KMALLOC_CACHES
+#define PERCPU_DYNAMIC_SIZE_SHIFT      12
+#else
+#define PERCPU_DYNAMIC_SIZE_SHIFT      10
+#endif
+
 /*
  * Percpu allocator can serve percpu allocations before slab is
  * initialized which allows slab to depend on the percpu allocator.
@@ -42,7 +48,7 @@
  * for this.  Keep PERCPU_DYNAMIC_RESERVE equal to or larger than
  * PERCPU_DYNAMIC_EARLY_SIZE.
  */
-#define PERCPU_DYNAMIC_EARLY_SIZE	(20 << 10)
+#define PERCPU_DYNAMIC_EARLY_SIZE	(20 << PERCPU_DYNAMIC_SIZE_SHIFT)
 
 /*
  * PERCPU_DYNAMIC_RESERVE indicates the amount of free area to piggy
@@ -56,9 +62,9 @@
  * intelligent way to determine this would be nice.
  */
 #if BITS_PER_LONG > 32
-#define PERCPU_DYNAMIC_RESERVE		(28 << 10)
+#define PERCPU_DYNAMIC_RESERVE		(28 << PERCPU_DYNAMIC_SIZE_SHIFT)
 #else
-#define PERCPU_DYNAMIC_RESERVE		(20 << 10)
+#define PERCPU_DYNAMIC_RESERVE		(20 << PERCPU_DYNAMIC_SIZE_SHIFT)
 #endif
 
 extern void *pcpu_base_addr;

include/linux/slab.h

@@ -19,6 +19,7 @@
 #include <linux/workqueue.h>
 #include <linux/percpu-refcount.h>
 #include <linux/cleanup.h>
+#include <linux/hash.h>
 
 
 /*
@@ -345,6 +346,12 @@ static inline unsigned int arch_slab_minalign(void)
 #define SLAB_OBJ_MIN_SIZE      (KMALLOC_MIN_SIZE < 16 ? \
                                (KMALLOC_MIN_SIZE) : 16)
 
+#ifdef CONFIG_RANDOM_KMALLOC_CACHES
+#define RANDOM_KMALLOC_CACHES_NR	15 // # of cache copies
+#else
+#define RANDOM_KMALLOC_CACHES_NR	0
+#endif
+
 /*
  * Whenever changing this, take care of that kmalloc_type() and
  * create_kmalloc_caches() still work as intended.
@@ -361,6 +368,8 @@ enum kmalloc_cache_type {
 #ifndef CONFIG_MEMCG_KMEM
 	KMALLOC_CGROUP = KMALLOC_NORMAL,
 #endif
+	KMALLOC_RANDOM_START = KMALLOC_NORMAL,
+	KMALLOC_RANDOM_END = KMALLOC_RANDOM_START + RANDOM_KMALLOC_CACHES_NR,
 #ifdef CONFIG_SLUB_TINY
 	KMALLOC_RECLAIM = KMALLOC_NORMAL,
 #else
@@ -386,14 +395,22 @@ kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1];
 	(IS_ENABLED(CONFIG_ZONE_DMA)   ? __GFP_DMA : 0) |	\
 	(IS_ENABLED(CONFIG_MEMCG_KMEM) ? __GFP_ACCOUNT : 0))
 
-static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags)
+extern unsigned long random_kmalloc_seed;
+
+static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags, unsigned long caller)
 {
 	/*
 	 * The most common case is KMALLOC_NORMAL, so test for it
 	 * with a single branch for all the relevant flags.
 	 */
 	if (likely((flags & KMALLOC_NOT_NORMAL_BITS) == 0))
+#ifdef CONFIG_RANDOM_KMALLOC_CACHES
+		/* RANDOM_KMALLOC_CACHES_NR (=15) copies + the KMALLOC_NORMAL */
+		return KMALLOC_RANDOM_START + hash_64(caller ^ random_kmalloc_seed,
+						      ilog2(RANDOM_KMALLOC_CACHES_NR + 1));
+#else
 		return KMALLOC_NORMAL;
+#endif
 
 	/*
 	 * At least one of the flags has to be set. Their priorities in
@@ -580,7 +597,7 @@ static __always_inline __alloc_size(1) void *kmalloc(size_t size, gfp_t flags)
 
 		index = kmalloc_index(size);
 		return kmalloc_trace(
-				kmalloc_caches[kmalloc_type(flags)][index],
+				kmalloc_caches[kmalloc_type(flags, _RET_IP_)][index],
 				flags, size);
 	}
 	return __kmalloc(size, flags);
@@ -596,7 +613,7 @@ static __always_inline __alloc_size(1) void *kmalloc_node(size_t size, gfp_t fla
 
 		index = kmalloc_index(size);
 		return kmalloc_node_trace(
-				kmalloc_caches[kmalloc_type(flags)][index],
+				kmalloc_caches[kmalloc_type(flags, _RET_IP_)][index],
 				flags, node, size);
 	}
 	return __kmalloc_node(size, flags, node);

mm/Kconfig

@@ -337,6 +337,23 @@ config SLUB_CPU_PARTIAL
 	  which requires the taking of locks that may cause latency spikes.
 	  Typically one would choose no for a realtime system.
 
+config RANDOM_KMALLOC_CACHES
+	default n
+	depends on SLUB && !SLUB_TINY
+	bool "Randomize slab caches for normal kmalloc"
+	help
+	  A hardening feature that creates multiple copies of slab caches for
+	  normal kmalloc allocation and makes kmalloc randomly pick one based
+	  on code address, which makes the attackers more difficult to spray
+	  vulnerable memory objects on the heap for the purpose of exploiting
+	  memory vulnerabilities.
+
+	  Currently the number of copies is set to 16, a reasonably large value
+	  that effectively diverges the memory objects allocated for different
+	  subsystems or modules into different caches, at the expense of a
+	  limited degree of memory and CPU overhead that relates to hardware and
+	  system workload.
+
 endmenu # SLAB allocator options
 
 config SHUFFLE_PAGE_ALLOCATOR

mm/kfence/kfence_test.c

@@ -212,7 +212,9 @@ static void test_cache_destroy(void)
 
 static inline size_t kmalloc_cache_alignment(size_t size)
 {
-	return kmalloc_caches[kmalloc_type(GFP_KERNEL)][__kmalloc_index(size, false)]->align;
+	/* just to get ->align so no need to pass in the real caller */
+	enum kmalloc_cache_type type = kmalloc_type(GFP_KERNEL, 0);
+	return kmalloc_caches[type][__kmalloc_index(size, false)]->align;
 }
 
 /* Must always inline to match stack trace against caller. */
@@ -282,8 +284,9 @@ static void *test_alloc(struct kunit *test, size_t size, gfp_t gfp, enum allocat
 
 		if (is_kfence_address(alloc)) {
 			struct slab *slab = virt_to_slab(alloc);
+			enum kmalloc_cache_type type = kmalloc_type(GFP_KERNEL, _RET_IP_);
 			struct kmem_cache *s = test_cache ?:
-					kmalloc_caches[kmalloc_type(GFP_KERNEL)][__kmalloc_index(size, false)];
+					kmalloc_caches[type][__kmalloc_index(size, false)];
 
 			/*
 			 * Verify that various helpers return the right values

mm/slab.c

@@ -1670,7 +1670,7 @@ static size_t calculate_slab_order(struct kmem_cache *cachep,
 			if (freelist_size > KMALLOC_MAX_CACHE_SIZE) {
 				freelist_cache_size = PAGE_SIZE << get_order(freelist_size);
 			} else {
-				freelist_cache = kmalloc_slab(freelist_size, 0u);
+				freelist_cache = kmalloc_slab(freelist_size, 0u, _RET_IP_);
 				if (!freelist_cache)
 					continue;
 				freelist_cache_size = freelist_cache->size;

mm/slab.h

@@ -282,7 +282,7 @@ void setup_kmalloc_cache_index_table(void);
 void create_kmalloc_caches(slab_flags_t);
 
 /* Find the kmalloc slab corresponding for a certain size */
-struct kmem_cache *kmalloc_slab(size_t, gfp_t);
+struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags, unsigned long caller);
 
 void *__kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags,
 			      int node, size_t orig_size,

mm/slab_common.c

@@ -678,6 +678,11 @@ kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1] __ro_after_init =
 { /* initialization for https://bugs.llvm.org/show_bug.cgi?id=42570 */ };
 EXPORT_SYMBOL(kmalloc_caches);
 
+#ifdef CONFIG_RANDOM_KMALLOC_CACHES
+unsigned long random_kmalloc_seed __ro_after_init;
+EXPORT_SYMBOL(random_kmalloc_seed);
+#endif
+
 /*
  * Conversion table for small slabs sizes / 8 to the index in the
  * kmalloc array. This is necessary for slabs < 192 since we have non power
@@ -720,7 +725,7 @@ static inline unsigned int size_index_elem(unsigned int bytes)
  * Find the kmem_cache structure that serves a given size of
  * allocation
  */
-struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags)
+struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags, unsigned long caller)
 {
 	unsigned int index;
 
@@ -735,7 +740,7 @@ struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags)
 		index = fls(size - 1);
 	}
 
-	return kmalloc_caches[kmalloc_type(flags)][index];
+	return kmalloc_caches[kmalloc_type(flags, caller)][index];
 }
 
 size_t kmalloc_size_roundup(size_t size)
@@ -752,8 +757,11 @@ size_t kmalloc_size_roundup(size_t size)
 	if (size > KMALLOC_MAX_CACHE_SIZE)
 		return PAGE_SIZE << get_order(size);
 
-	/* The flags don't matter since size_index is common to all. */
+	/*
-	c = kmalloc_slab(size, GFP_KERNEL);
+	 * The flags don't matter since size_index is common to all.
+	 * Neither does the caller for just getting ->object_size.
+	 */
+	c = kmalloc_slab(size, GFP_KERNEL, 0);
 	return c ? c->object_size : 0;
 }
 EXPORT_SYMBOL(kmalloc_size_roundup);
@@ -776,12 +784,35 @@ EXPORT_SYMBOL(kmalloc_size_roundup);
 #define KMALLOC_RCL_NAME(sz)
 #endif
 
+#ifdef CONFIG_RANDOM_KMALLOC_CACHES
+#define __KMALLOC_RANDOM_CONCAT(a, b) a ## b
+#define KMALLOC_RANDOM_NAME(N, sz) __KMALLOC_RANDOM_CONCAT(KMA_RAND_, N)(sz)
+#define KMA_RAND_1(sz)                  .name[KMALLOC_RANDOM_START +  1] = "kmalloc-rnd-01-" #sz,
+#define KMA_RAND_2(sz)  KMA_RAND_1(sz)  .name[KMALLOC_RANDOM_START +  2] = "kmalloc-rnd-02-" #sz,
+#define KMA_RAND_3(sz)  KMA_RAND_2(sz)  .name[KMALLOC_RANDOM_START +  3] = "kmalloc-rnd-03-" #sz,
+#define KMA_RAND_4(sz)  KMA_RAND_3(sz)  .name[KMALLOC_RANDOM_START +  4] = "kmalloc-rnd-04-" #sz,
+#define KMA_RAND_5(sz)  KMA_RAND_4(sz)  .name[KMALLOC_RANDOM_START +  5] = "kmalloc-rnd-05-" #sz,
+#define KMA_RAND_6(sz)  KMA_RAND_5(sz)  .name[KMALLOC_RANDOM_START +  6] = "kmalloc-rnd-06-" #sz,
+#define KMA_RAND_7(sz)  KMA_RAND_6(sz)  .name[KMALLOC_RANDOM_START +  7] = "kmalloc-rnd-07-" #sz,
+#define KMA_RAND_8(sz)  KMA_RAND_7(sz)  .name[KMALLOC_RANDOM_START +  8] = "kmalloc-rnd-08-" #sz,
+#define KMA_RAND_9(sz)  KMA_RAND_8(sz)  .name[KMALLOC_RANDOM_START +  9] = "kmalloc-rnd-09-" #sz,
+#define KMA_RAND_10(sz) KMA_RAND_9(sz)  .name[KMALLOC_RANDOM_START + 10] = "kmalloc-rnd-10-" #sz,
+#define KMA_RAND_11(sz) KMA_RAND_10(sz) .name[KMALLOC_RANDOM_START + 11] = "kmalloc-rnd-11-" #sz,
+#define KMA_RAND_12(sz) KMA_RAND_11(sz) .name[KMALLOC_RANDOM_START + 12] = "kmalloc-rnd-12-" #sz,
+#define KMA_RAND_13(sz) KMA_RAND_12(sz) .name[KMALLOC_RANDOM_START + 13] = "kmalloc-rnd-13-" #sz,
+#define KMA_RAND_14(sz) KMA_RAND_13(sz) .name[KMALLOC_RANDOM_START + 14] = "kmalloc-rnd-14-" #sz,
+#define KMA_RAND_15(sz) KMA_RAND_14(sz) .name[KMALLOC_RANDOM_START + 15] = "kmalloc-rnd-15-" #sz,
+#else // CONFIG_RANDOM_KMALLOC_CACHES
+#define KMALLOC_RANDOM_NAME(N, sz)
+#endif
+
 #define INIT_KMALLOC_INFO(__size, __short_size)			\
 {								\
 	.name[KMALLOC_NORMAL]  = "kmalloc-" #__short_size,	\
 	KMALLOC_RCL_NAME(__short_size)				\
 	KMALLOC_CGROUP_NAME(__short_size)			\
 	KMALLOC_DMA_NAME(__short_size)				\
+	KMALLOC_RANDOM_NAME(RANDOM_KMALLOC_CACHES_NR, __short_size)	\
 	.size = __size,						\
 }
 
@@ -890,6 +921,11 @@ new_kmalloc_cache(int idx, enum kmalloc_cache_type type, slab_flags_t flags)
 		flags |= SLAB_CACHE_DMA;
 	}
 
+#ifdef CONFIG_RANDOM_KMALLOC_CACHES
+	if (type >= KMALLOC_RANDOM_START && type <= KMALLOC_RANDOM_END)
+		flags |= SLAB_NO_MERGE;
+#endif
+
 	/*
 	 * If CONFIG_MEMCG_KMEM is enabled, disable cache merging for
 	 * KMALLOC_NORMAL caches.
@@ -941,6 +977,9 @@ void __init create_kmalloc_caches(slab_flags_t flags)
 				new_kmalloc_cache(2, type, flags);
 		}
 	}
+#ifdef CONFIG_RANDOM_KMALLOC_CACHES
+	random_kmalloc_seed = get_random_u64();
+#endif
 
 	/* Kmalloc array is now usable */
 	slab_state = UP;
@@ -976,7 +1015,7 @@ void *__do_kmalloc_node(size_t size, gfp_t flags, int node, unsigned long caller
 		return ret;
 	}
 
-	s = kmalloc_slab(size, flags);
+	s = kmalloc_slab(size, flags, caller);
 
 	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;

mm/slub.c

@@ -360,44 +360,52 @@ static struct workqueue_struct *flushwq;
  * 			Core slab cache functions
  *******************************************************************/
 
+/*
+ * freeptr_t represents a SLUB freelist pointer, which might be encoded
+ * and not dereferenceable if CONFIG_SLAB_FREELIST_HARDENED is enabled.
+ */
+typedef struct { unsigned long v; } freeptr_t;
+
 /*
  * Returns freelist pointer (ptr). With hardening, this is obfuscated
  * with an XOR of the address where the pointer is held and a per-cache
  * random number.
  */
-static inline void *freelist_ptr(const struct kmem_cache *s, void *ptr,
+static inline freeptr_t freelist_ptr_encode(const struct kmem_cache *s,
-				 unsigned long ptr_addr)
+					    void *ptr, unsigned long ptr_addr)
 {
+	unsigned long encoded;
+
 #ifdef CONFIG_SLAB_FREELIST_HARDENED
-	/*
+	encoded = (unsigned long)ptr ^ s->random ^ swab(ptr_addr);
-	 * When CONFIG_KASAN_SW/HW_TAGS is enabled, ptr_addr might be tagged.
-	 * Normally, this doesn't cause any issues, as both set_freepointer()
-	 * and get_freepointer() are called with a pointer with the same tag.
-	 * However, there are some issues with CONFIG_SLUB_DEBUG code. For
-	 * example, when __free_slub() iterates over objects in a cache, it
-	 * passes untagged pointers to check_object(). check_object() in turns
-	 * calls get_freepointer() with an untagged pointer, which causes the
-	 * freepointer to be restored incorrectly.
-	 */
-	return (void *)((unsigned long)ptr ^ s->random ^
-			swab((unsigned long)kasan_reset_tag((void *)ptr_addr)));
 #else
-	return ptr;
+	encoded = (unsigned long)ptr;
 #endif
+	return (freeptr_t){.v = encoded};
 }
 
-/* Returns the freelist pointer recorded at location ptr_addr. */
+static inline void *freelist_ptr_decode(const struct kmem_cache *s,
-static inline void *freelist_dereference(const struct kmem_cache *s,
+					freeptr_t ptr, unsigned long ptr_addr)
-					 void *ptr_addr)
 {
-	return freelist_ptr(s, (void *)*(unsigned long *)(ptr_addr),
+	void *decoded;
-			    (unsigned long)ptr_addr);
+
+#ifdef CONFIG_SLAB_FREELIST_HARDENED
+	decoded = (void *)(ptr.v ^ s->random ^ swab(ptr_addr));
+#else
+	decoded = (void *)ptr.v;
+#endif
+	return decoded;
 }
 
 static inline void *get_freepointer(struct kmem_cache *s, void *object)
 {
+	unsigned long ptr_addr;
+	freeptr_t p;
+
 	object = kasan_reset_tag(object);
-	return freelist_dereference(s, object + s->offset);
+	ptr_addr = (unsigned long)object + s->offset;
+	p = *(freeptr_t *)(ptr_addr);
+	return freelist_ptr_decode(s, p, ptr_addr);
 }
 
 #ifndef CONFIG_SLUB_TINY
@@ -421,15 +429,15 @@ __no_kmsan_checks
 static inline void *get_freepointer_safe(struct kmem_cache *s, void *object)
 {
 	unsigned long freepointer_addr;
-	void *p;
+	freeptr_t p;
 
 	if (!debug_pagealloc_enabled_static())
 		return get_freepointer(s, object);
 
 	object = kasan_reset_tag(object);
 	freepointer_addr = (unsigned long)object + s->offset;
-	copy_from_kernel_nofault(&p, (void **)freepointer_addr, sizeof(p));
+	copy_from_kernel_nofault(&p, (freeptr_t *)freepointer_addr, sizeof(p));
-	return freelist_ptr(s, p, freepointer_addr);
+	return freelist_ptr_decode(s, p, freepointer_addr);
 }
 
 static inline void set_freepointer(struct kmem_cache *s, void *object, void *fp)
@@ -441,7 +449,7 @@ static inline void set_freepointer(struct kmem_cache *s, void *object, void *fp)
 #endif
 
 	freeptr_addr = (unsigned long)kasan_reset_tag((void *)freeptr_addr);
-	*(void **)freeptr_addr = freelist_ptr(s, fp, freeptr_addr);
+	*(freeptr_t *)freeptr_addr = freelist_ptr_encode(s, fp, freeptr_addr);
 }
 
 /* Loop over all objects in a slab */